YT YouTube2Text

YouTube2Text → Transcripts → Practical Applications of Digitalization in the Petroleum Industry, Eng. Marwa Hassan, Lecture 01/04

Practical Applications of Digitalization in the Petroleum Industry, Eng. Marwa Hassan, Lecture 01/04 — Transcript

by PioPetro · 9,503 words · 1,767 segments · language en · Watch on YouTube

Open in transcriber Summarize with AI Download SRT/VTT

Full transcript

0:00hello everyone good morning good
0:02afternoon and good evening to everyone
0:04who's tuning in
0:06on behalf of pio petro arab oil and gas
0:08academy academy
0:10and spe egypt section i'd like to
0:12welcome you to today's session
0:14my name is shahad bhajit i'm a third
0:16year petroleum engineering student at
0:18knu
0:19in kurdistan iraq and i'll be your
0:21moderator for today
0:23before we start i'd like to remind you
0:24to please drop your questions in the q a
0:28section below
0:29please keep the chat box professional
0:31and ethical
0:32and please submit your quizzes before
0:34the deadline
0:36now without further ado please give a
0:38warm welcome to engineer
0:39maru hassan who will be giving us a
0:42short course that consists of four
0:43webinars
0:44on practical applications on
0:47digitalization
0:48in the oil and gas industry engineer
0:51marwa hasan holds an msc
0:53in nuclear engineering she is the global
0:56production
0:56technical marketing manager for
0:58schlumberger digital
1:00and integration segment based in houston
1:02us
1:03barwa's experience is on defining
1:06delivering
1:06and communicating digital solutions
1:09around production data acquisition
1:11surveillance and analysis and
1:13optimization
1:14prior to her current role marwa held a
1:17variety of positions in the middle east
1:19and europe
1:20focusing on digital oil field and
1:22integrated
1:23operation implementation she was also
1:26involved in many digital solutions that
1:28range from automating
1:30one simple routine task up to complex
1:33production optimization solutions
1:36prior to joining schlumberger engineer
1:38marwa spent three years as a nuclear
1:40engineer
1:41in egypt's second research reactor and
1:43as a lecturer in alexandria
1:45university engineer marwa has delivered
1:48more than 200 courses and presentations
1:51globally
1:52the latest paper on digitalization was
1:55recently featured in gapt
1:57japan association for petroleum
1:59technology with a title
2:01from digital oil field to operational
2:04excellence
2:05engineer marwa thank you so much for
2:07coming and the mic
2:08is yours thank you very much chad thanks
2:11a lot for this warm introduction
2:13uh and thank you all for attending this
2:15uh course
2:17um as chef mentioned we're gonna have
2:19like four sessions
2:20talking about the digitalization in oil
2:22and gas and
2:26i'm very passionate about this topic
2:28specifically because
2:30many engineers many petroleum engineers
2:32and many people think that
2:33digitalization is related to i.t
2:36and that's why um when i discussed with
2:39professor ahmed
2:40the importance of starting thinking
2:42about digitalization
2:44as early as possible he agreed with me
2:47and i'm i'm gonna take this chance
2:50to introduce what do we do in digital or
2:54what do we mean by digital in oil and
2:55gas
2:56and uh it's a very heavy topic i know
2:59that
2:59and i'm very well aware of that so if
3:01you have any questions or if you need
3:03any
3:04information please feel free to
3:08to drop the questions for me now
3:11uh for the purpose of this session
3:13specifically we're going to talk about
3:16the current status of digital and oil
3:18and gas
3:19which is mainly a word that you all
3:21heard about which is digital oil field
3:23that's what we currently have on the
3:25next session i'm gonna show you the
3:27the the future of the digital uh in oil
3:30and gas so something related to
3:31artificial intelligence machine learning
3:34uh specific solutions that
3:38takes a smile away from how we currently
3:41deliver deliver kpos
3:45on oil and gas uh i'm
3:48i'm a bit of a business person so uh
3:52i'm gonna use business terms if if you
3:55don't know or you don't understand any
3:57of those terms please feel free to
3:59to ask me anytime now
4:04the objective of basically this
4:06presentation
4:07is three important things that i want
4:09you to to get away from this session
4:12first of all what is digital oil field
4:14digital oil field has been in this in
4:15the in the industry for more than
4:1715 years right now uh uh it's been
4:20evolving but it exists so
4:22um i'm assuming that i'm talking to
4:24students
4:25who will soon be part of the oil and gas
4:28industry
4:29when you join a company you will hear a
4:31lot the word digital oil field
4:33and then i'm going to take a slide or
4:36two to explain to you why you should
4:37care as a petroleum engineer why do you
4:39care about
4:40the digital and why do you want to be
4:42part
4:43of the digital uh revolution not only
4:46leave it to
4:47uh to i.t or software's engineers
4:51and then in this session we're going to
4:53talk about one example of digital oil
4:55field implementations
4:56in some around malaysia and if we have
4:59time i'm gonna show you something about
5:01what we're gonna discuss
5:02the next session just to get you uh give
5:04you a little bit flavor
5:05of what we have now digital oil field
5:09you probably heard
5:10or you would read a lot about many the
5:12uh terminologies
5:14uh schlumberger we use the word digital
5:16oil fields
5:17bp used the word smart fields uh others
5:20use the word ifield if you're working in
5:22kuwait
5:23we have quiddif kuwait digital oil field
5:26uh if you work in in malaysia you
5:29probably heard about
5:30asset optimization so there are many
5:32differentiations or many terms
5:34that you will hear when you start
5:36working in oil and gas
5:38all lead to the same
5:41terminology which is the digitalization
5:43of oil and gas
5:45what is the objective why do we do a
5:46digital oil field or why do we care
5:48about digitalization in the oil
5:50in the oil and gas industry because
5:53we're looking into four important parts
5:55first of all increasing the efficiency
5:58we want people to work smarter
6:00we want things to to to happen quicker
6:03than possible
6:04accelerating production all the oil and
6:06gas producers the enp
6:08companies are looking to get production
6:10as soon as possible from hitting the
6:12ground
6:13reducing losses you want to minimize the
6:15amount of time you spend
6:17in shut-ins you want to minimize the
6:20amount of time
6:21you spend inspecting machines and
6:23expecting failures
6:26and as soon as possible you want to
6:27maximize the the recovery
6:30from oil and gas right as a petroleum
6:32engineer so this is the kpo's that
6:35ceos and ceos looks for right
6:38this is the higher people in the company
6:40looking for
6:41as a production engineer or as a
6:43reservoir engineer as a geoscience
6:45you're looking into different objectives
6:47at this stage when you enter the company
6:49you're looking into you want to reduce
6:51the amount of data you're looking at
6:53right you don't want to look into all
6:55the data if you're managing the 400
6:57wells and it might happen to you
6:58you don't want to be looking into data
7:00coming from 400 wealth right
7:02you want to look into important
7:03information that can give you insight
7:06on what's happening on each well and
7:08where can you focus
7:09right you want to detect anomalies
7:13so basically you want to you want the
7:15the digital oil field or
7:17you want the program that you're working
7:18at is to give you
7:20warning signs to tell you that this well
7:23uh
7:24pressure is increasing or for example to
7:27give you information such as that
7:29wax is being deposited on this well so
7:31this is the kind of information that you
7:33expect from a digital oil field
7:36program it links
7:39information into the applications what
7:41does that mean it means that
7:44you're a reservoir engineer or you're a
7:45production engineer you're a
7:46geoscientist
7:47but then you realize that you cannot
7:50work alone
7:51you need information coming from
7:52reservoir engineers you need information
7:54coming from geoscience
7:56you need information coming from
7:57different part of the system as a
7:59production engineer as a process
8:00engineer you guys need to work together
8:02so this is the purpose of having a
8:03digital oil field is to
8:06share the information and link it into
8:08different process
8:09i know right now if you're in university
8:11you've been probably working on
8:13with software's like python or eclipse
8:16or petrel and those software starts and
8:19finish on a specific part of the system
8:21so if we're talking about pipes and for
8:23example for production engineer
8:24you start from the completion and you
8:26finish by the gathering center but
8:28that's not the reality
8:30in the oil and gas industry right you
8:32before the completion you're part of the
8:34reservoir
8:34and after the gathering center you're
8:36part of the process system so you need
8:38something that can give you the
8:39continuousity
8:40of the hypocarbon bath
8:44pathway
8:47you also want to perform optimization
8:50we're going to talk about this later
8:51right so you you want to be able to
8:54understand how you can optimize your
8:55system
8:56or work to the better of the system
9:00so that's basically the objective of why
9:03you want to implement digital oil fields
9:08the normal applications that you have
9:10gives you huge amounts
9:11of information it gives you huge
9:14amounts of
9:17data and analysis and
9:21status but basically linking
9:25those systems and applications together
9:28is what gives you the importance of
9:31understanding the full
9:32system and how you can do optimization
9:35and enhancement
9:36on the full system
9:40so when you hear the word digital oil
9:42field or when you hear the word
9:44asset optimization or smart field what
9:47should you think about
9:49you should think about any part of the
9:51system
9:53that can deliver to you uh
9:56the four things that we talked about the
9:58increase in efficiency
10:00the optimization or enhancement in
10:03production
10:04the return of investment that that the
10:07company need
10:08so for example you can look into operate
10:11optimizing a specific uh operation that
10:14you're doing like sagitty for example
10:16right so through
10:20through implementing sensors that can
10:22read
10:23the data automatically from your system
10:26automating the workflows
10:28of the sagdi you're able to make a
10:30proper decision
10:32on what exactly the parameters that you
10:34need to introduce into the system
10:37another part of digital oil field could
10:39be logistics simply if you look into
10:40number two this is
10:42uh in the drilling part
10:47bringing the material if you're working
10:48on unconventional for example bringing
10:50the the fluids
10:51uh the mod into the the field so
10:55optimizing the fleet operation
10:58and if you're an operational engineer
10:59this is a huge amount of cost
11:02on what's being put on your shoulders
11:06so optimizing the the coast and the
11:08operation of the fleet
11:10bringing the fluids and materials to to
11:13the drilling
11:14and production uh this is
11:18digital oil fields another important
11:21part if we're looking for example into
11:25bringing the information into people
11:28into in the office
11:29so you you usually have people on the
11:32field and people in the office
11:34the ones on the field um if you're
11:36working manually you're getting the
11:38information on excel sheet for example
11:40or you're writing information on the
11:41excel sheet
11:42the amount of time you spend to correct
11:44this information and sending it into the
11:46people in the office
11:47to uh to analyze the data and make use
11:50of it and
11:50provide information and significant
11:53recommendations to you
11:55is is huge so by connecting by making
11:59wireless connection
12:00and connectivity between the field and
12:03the office
12:04this is called digital oil fields
12:07if you if you're using remote monitoring
12:10uh
12:11to perform inspection in any of your
12:12facilities uh
12:14that's called digital oil fields so
12:17again if if we're looking into reducing
12:20downtime
12:21uh in any of the planets
12:24of or improving asset reliability for
12:26example that's digital field
12:28the use of drones into monitoring
12:31any assets into looking into leak
12:33detection into the pipelines
12:35for example that's called digital oil
12:37field
12:39uh if if you're looking into uh personal
12:42safety hse
12:43uh reducing the amount of time that
12:46people spend in
12:47in hazardous situations for example
12:49that's also digital oil field
12:51right so looking into
12:55each part of the system and optimizing
12:58each part
12:59can be called digital oil fields so as
13:02long as you're
13:03doing an optimization or increasing the
13:05efficiency
13:07using a new technology
13:10new technology could be as simple as
13:12implementing sensors
13:13or fiber optics on the field and it
13:16could be as
13:16as difficult as using drones for example
13:19uh
13:20in in the field right so
13:24so the word digitalization or digital
13:26oil field can be
13:28called on any part where you're linking
13:31technology to uh um
13:34technology with uh domain
13:38which is can be facility engineering can
13:41be
13:41trolling engineering can be production
13:42engineering to
13:44to prefer to provide the roi that you're
13:47looking for
13:48so basically that's a digital oil field
13:51so
13:52to simplify this your operation engineer
13:55why do you do
13:55digitalization this is very simple as a
13:58production engineer
13:59your job or as an operational engineer
14:02job is to make sure
14:03that your production rate is uh
14:07optimized right but accidents happen
14:10and when accident happens if you don't
14:12have a good digitalization
14:14project or a good digitalization program
14:17your oil
14:18or your production will start to drop
14:20right so here you see the drop
14:24now what happened is that you will not
14:26notice if you don't have a
14:27digitalization if you don't have sensors
14:29for example if you're not reading if you
14:30if you get
14:31information from the field everyone
14:33every month for example
14:35you're going to spend some time until
14:36you detect that your production is
14:39actually
14:40being lost that you have a lot of
14:41production or your production being
14:42declined
14:43so by the time you're gonna take to
14:45detect the problem
14:47you're gonna spend more time analyzing
14:49what's the issue
14:51and then you're gonna take an action to
14:53bring
14:54production back to its uh
14:57to its current status right
15:02now why do you do digitalization to
15:04bring everything faster
15:08detecting the problem as soon as
15:09possible analyzing it as soon as
15:12possible
15:13bringing the production to actions as
15:16soon as possible
15:17detection through automated workflows by
15:19having sensors
15:21by linking the information as we said
15:23together
15:24so that your intervening your
15:26intervening in the software is
15:28as less as possible by using analytical
15:32tools
15:33to provide you with analysis and by
15:35maintaining well intervention activity
15:37planning
15:38logistics as soon as possible you're
15:40able to save
15:42your losses from production as soon as
15:44possible right
15:46so and this is a cycle so you you will
15:49perform it
15:50you you want to perform it as soon as
15:54possible or as quick as possible
15:56detect a warning sign that your
15:59production is declining
16:00you and a detection to the anomaly or
16:03the behavior
16:04the strange behavior that you have and
16:06then analyzing
16:07the tool analyzing the situation and
16:10taking the proper action
16:12to respond to the situation saving
16:15saving
16:15the production now the next sessions
16:18we're going to talk about prediction so
16:19i'm going to show you
16:20how actually you can predict so instead
16:23of waiting for production to decline
16:25which is currently unfortunately what we
16:28have in many of the fields
16:30because you have a sensor so you're
16:31relying on a current
16:33reading from the sensor that tells you
16:37that production is declining
16:38what we want and what we're going to
16:40discuss on the next sessions
16:41is prediction before you have a decline
16:46in the production or before the issue
16:48happens
16:49uh to you you're gonna be able to
16:51understand that this
16:52there's something happening and you take
16:54actions before
16:56uh the situation gets worse and
16:59optimization it's it's quite different
17:01in optimization your rate is not
17:02declining right but you're looking into
17:04optimizing your
17:05your production so you're looking into
17:08enhancing the will operations
17:10enhancing the field operation and
17:12enhancing enterprise operation
17:14what does that mean it means that you're
17:15looking into an integrated solution
17:18that will not only rely on the wheel
17:19operation but it will rely on the full
17:22system that you have as we said before
17:24when you're looking into the bigger
17:25picture
17:27where you can look into the way
17:28operation you can look into the facility
17:29operation you can look into the
17:31reservoir operation
17:32but tying those or integrating the full
17:35operation together is what gives you
17:38optimization
17:39and by optimization i don't mean only
17:41increasing production
17:42optimization by the way might be
17:44reducing your production but increasing
17:46efficiency
17:47might be a reducing time
17:51it might be increasing
17:54reducing hse for example things like
17:57that
17:58okay so that's when we're talking about
18:00optimization right
18:02now there are four essentials uh sorry
18:05five essentials components when we talk
18:07about digital oil fields
18:10those components uh can be
18:14taken on a level on on the same level a
18:17complete digital oil field on your field
18:20or it can be you can choose and pick and
18:22choose based on the workflow
18:24that you're looking for and i'm going to
18:25show you this later but basically you
18:27need to look into five things
18:31the first one is online data and the
18:33reason i wrote online data and i didn't
18:35write real-time data is because many of
18:37the time people say oh we
18:38want to put sensors that read
18:41multi-seconds
18:43of uh of data but sometimes you really
18:45don't need that that it depends on the
18:47operation that you're doing if you're
18:48looking into your reservoir for example
18:50and optimizing your reservoir
18:52you haven't having a data a daily data
18:55or a weekly data might be enough for you
18:58to perform
18:59the application that you want but if
19:01you're looking into a machine
19:02optimizing the machine if you're looking
19:04into esp performance for example
19:06then having a secondly or month or
19:09sorry or daily data
19:14or minutes of data might be very
19:17efficient
19:18might be it might give you
19:21the the opportunity to save the esp from
19:24failure
19:25right so that's the reason i wrote on
19:27online data
19:29because you need to be smart enough to
19:32understand do i need to put sensors
19:34everywhere
19:36do i need to to to read the data
19:39on the edge do i re is it enough for me
19:42to get a monthly data from this fee
19:44from this well it depends really on the
19:46requirements that you have
19:48now the second part is automating
19:50operational tasks
19:52what kind of tasks i can automate
19:56and minimize the human interaction on
19:59these tasks
20:00this is something very important can i
20:02for example
20:04loading the data do i need to have a
20:06specific operator or a specific person
20:08to really load the data or can this be
20:10done automatically
20:12estimating the wear rates do i need
20:15someone
20:15to perform to open pipe sim or prosper
20:18or gab
20:19and and do a well-raised estimation
20:22every single day on 400 wells or this is
20:25something that i can automate
20:27and a production engineer can only look
20:29into those five or six wells
20:31where their well-rated nation doesn't
20:35really uh um allah is not aligned with
20:38the production
20:40of this well right the third part
20:44is you want to minimize losses right
20:46that's that's a very important part
20:47you want to increase production by
20:49minimizing the losses that you have
20:51what kind of losses that you that you
20:53might have for example
20:54losses might be things related to flu
20:56assurance issues
20:58you have hydrates on your pipeline and
21:01you don't know about it
21:02knowing that you have hydrate
21:04accumulating in your pipeline
21:06will will save you at least uh maybe 15
21:1010 to 10 to 20 days of downtime
21:14required uh for operators to clean the
21:17pipeline
21:18right so so as long as soon as possible
21:20when you understand that you have an
21:22issue and you're able to inject methanol
21:24for example or able to
21:26to uh to perform a specific task that
21:28will
21:29[Music]
21:31that will make you lose this this
21:33hydrate
21:34then that case you've saved from 10 to
21:3620 days
21:37of losses of production
21:42effectiveness through cross-discipline
21:44collaboration as i said before
21:46with with the digital oil field most of
21:48the companies like vp or shell
21:50or uh or petroplast for example aramco
21:54who who perform digital uh oil field
21:57prefer to have a collaboration
21:59center where they have reservoir
22:01engineers they have production engineers
22:02they have operators work
22:03together why to share information and to
22:06share knowledge
22:09i know we study each part we have a
22:13when we're in college we have a course
22:14called drilling engineer we have a
22:15course called reservoir engineer but in
22:17reality
22:18this doesn't work alone you need to work
22:20together and collaborate together
22:22the most effective part is technology
22:24technology means that
22:26you're linking uh you're using sensors
22:30for example you're using software you're
22:31using ecosystems you're using cloud
22:33solutions
22:34you're using connectivity you're using
22:37different digital solutions
22:39to be able to connect this online data
22:42with the softwares or with the domain
22:45the production or the reservoir domain
22:46that you have
22:48and with your uh enterprise and
22:51organization
22:52right so for example if you're a
22:55production engineer
22:56and a production operation and you're
22:59getting the data
23:00uh um through uh
23:04through sensors and you are
23:07responsible for looking into the losses
23:10the production losses and preparing the
23:12production report
23:14that goes into management you want a
23:17link
23:17between the sensors and your system
23:20which is for example sap system or
23:21oracle
23:22your enterprise system your erp system
23:25right
23:27oil and gas is not only about the domain
23:29that you have it's also about
23:31linking the system together so at the
23:33end you want all this information to go
23:35into an
23:36enterprise system where you can prepare
23:38your your daily report
23:40or your monthly report so that's
23:42something that's very
23:43essential uh when you're talking about
23:46digital oil field
23:47having domain is not enough anymore in
23:50the oil and gas industry
23:55now do i have a very essential question
23:58that always
24:01comes to to operate your mind
24:04is do do i really need to do it seems
24:07like a lot of effort it seems that i
24:08need to
24:09uh put sensors everywhere i need to
24:12perform optimization i need to do
24:14diagnostic i need to do many levels of
24:17hierarchy
24:18to be able to call this a digital oil
24:19field
24:22and it's costly and and this is
24:24something that we 15 years ago we
24:26started to do
24:27digital oil field was extremely costly
24:29but not anymore
24:30why because the most important our
24:33essential part that you need to look at
24:34is the data
24:37you need to look into two important
24:38parts do i have enough
24:40data to perform to validate it
24:44and to transmit it and to use it
24:49on the five layers that you see above
24:53do i have this data or not if i don't
24:55have data
24:57can i afford to implement sensors within
25:00the field to provide me with this data
25:03if i don't have enough money or it's
25:05going to be costly
25:07to have a return of investment on this
25:09can i use
25:10analytical tool to um
25:15to perform uh data
25:19to how do you say that to perform data
25:21prediction with that with the less
25:23data or the minimum data that i have
25:26coming
25:27on monthly uh for monthly um
25:31operations for example like i can test
25:32the well what i can do for example
25:34with the cost that i have is test the
25:36well every month that's what i have
25:38okay perfect so can i have any tool
25:42that predicts the the missing data or
25:45the missing information that i have for
25:47me
25:47so data is essential for me sorry
25:51data is essential for me i need to see
25:54if i can
25:55have control over the field or not using
25:58edge
25:58using sensors using connectivity can i
26:01transmit
26:01the data or not can i manage the data
26:03can i do validation
26:05or not now above from that
26:08there are four layers sorry there are
26:10five layers that based on the workflow
26:13that you're that that you intend to do
26:16or the challenge that you have
26:18you need to to understand so for example
26:20your purpose is only to know
26:22if you have a specific issue happening
26:26so in that case you can only go for the
26:28layer of surveillance
26:29right all you need to know is do i have
26:33an issue
26:33or not okay
26:37now you have huge amount of wealth
26:39you're working on a field where you have
26:413 000 wealth you don't have enough
26:43people to really analyze
26:45the situation for you so in that case
26:47you want digital oil field
26:49to detect the issue and you also want
26:53the the the system to identify the root
26:56causes for you and tell you
26:57where to focus you don't have people to
26:59look into 3000 bills right
27:02and so on so based on the solution or
27:05based on the workflow that you're going
27:06to implement
27:07you will be able to choose the layer
27:09that you want to stop at so digital if
27:11it doesn't have to be costly doesn't
27:12have to be expensive you don't need to
27:14think about the full procedure
27:16when you're thinking digital oil field
27:17you only need to think about your needs
27:20what does that mean it means that
27:23hundreds of challenges
27:24face us when we talk about oil and gas
27:26industry
27:28when i'm looking into flu assurance
27:31hydrates wax
27:32kale salt
27:36in that case i'm only looking into
27:39identifying
27:40will i have an issue or not as simple as
27:42that
27:43but if i'm looking into uh
27:48lifting and popping if i'm looking at
27:49vsp for example
27:51esp is costly to to purchase an esp pump
27:54to install it
27:55and to let it fail and then spend time
27:58uh changing the esp
28:02and shutting the well to change the esp
28:03is costly so
28:05you don't only want to stop on the part
28:08of surveillance you want
28:09you want to predict and you want to move
28:11into diagnostic you want to save
28:13the esp life right and the same goes
28:16into uh surveillance and optimization
28:18and planning on the right hand side when
28:19you look into asset management
28:21as management you want to look into the
28:22full circle you want to look into up
28:24till optimization
28:26how do i make sure that while i'm saving
28:29the esp
28:30pump for example i'm not really damaging
28:32the weld
28:33and i'm not really affecting the
28:34reservoir at this process so you want to
28:36look into the full
28:37picture together so really it depends on
28:40the kpis the key performance indicators
28:43of your field and your management
28:48am i looking into a quick gain for
28:51example or am i looking into
28:52long-term depends so for example if
28:56you're an operator
28:58if you're an operator you're you're
29:00you're a quick person right
29:01you're looking into seconds you want to
29:03you want to you don't want h2s to leak
29:05so that's the second of matters you
29:07don't want
29:08gas to leak you know you want you want
29:10to look into your compressors
29:12being optimized so you want to be a very
29:15quick and very efficient person you want
29:16to look into seconds
29:18of what's happening into your field but
29:20if you're a reservoir engineer
29:22then you're uh what i call that the
29:24brain people right the
29:26the the people who sit with eclipse or
29:29intersect for
29:30for hours and hours and hours performing
29:34really uh um
29:37history matching for the for the for the
29:39field and spending time so you're really
29:41looking into
29:43uh years of optimization right you're
29:46not only looking into
29:47seconds so you want to have information
29:51uh as slow as possible and you want to
29:54have information
29:56from different parts of the fields and
29:58you want to reach
29:59the optimization part in this part right
30:03so again it depends on where you're
30:05looking are you looking into
30:07production optimization are you looking
30:08into the full field optimization
30:11your objective are you looking to
30:12maximizing recovery are you looking into
30:14anticipating production issues it will
30:16all depend
30:18on uh your role in the organization
30:21and the kpos that you're looking for
30:26i can't explain this it's a bit
30:27difficult to explain right now but i'm
30:29gonna spend some time just to
30:31uh to make you um get the flavor
30:34of the tiers or the layers of digital
30:38oil field
30:39which is the first part that we talk
30:40about so i'm taking this from samarang
30:43so this is a project
30:44uh of digital oil field uh for samarang
30:47field
30:48in malaysia right so what we've done
30:51first of all was
30:52looking into the data as i said data
30:54management layer
30:56how much data do we have from the field
30:57do we need to install sensors or not
30:59uh do we have a historian or not do we
31:03have a scada system or not
31:05and based on that we have
31:08the data management layer
31:12and we make it connect and communicate
31:14with each other
31:16and then the application layer the
31:18application layer is who
31:20is going to talk to who this will be
31:22based on
31:24the workflow tier so before we put the
31:26application here we look into the
31:27workflow tier
31:28what are we going to do are we going to
31:29look into the web performance are we
31:31going to look into artificial
31:32left facility monitoring flow assurance
31:34based on that
31:35we choose the applications
31:38that will we will connect together to
31:40create the workflow
31:41for example if we're talking about
31:42artificial left
31:44so do we want to connect for example
31:46pipe sim with
31:48prospering gap for example and create a
31:50specific workflow
31:51where we will look into the performance
31:53of the uh pump
31:55and then detect any issues and then
31:58predict the the rate the
32:02estimated rate based on that for looking
32:04into will performance
32:06do we need to connect eclipse with uh
32:09pipe sim for example and look into
32:12the production rate the issues that's
32:15happened it's happening do we need to
32:16and so on right so you look into what
32:18type of workflow
32:20you will you will want to do and based
32:23on that you connect
32:24the applications and you store the data
32:26you you call
32:28the data that you're storing in the
32:29historian and the
32:31database to be used into this
32:34application
32:35this all is being automated what does
32:38that mean
32:38it means that the first three layers
32:41that you see
32:43are the layers that are provided to the
32:45end users
32:47automated you don't interfere on it
32:50you interfere on the visualization layer
32:52so you get the information
32:54individualization layer you know for
32:57example that your production rate is
32:58this amount
32:59you would know that you have a hydrate
33:01issue you have a wax
33:02issue your esp pump is alarm
33:06because you have a an issue with the
33:08speed for example or
33:10or rotators being broken whatever
33:12whatever is happening
33:14this is the layer that you interact with
33:16based on that you start diagnosing
33:18the issue and you start analyzing so
33:20what we've done here or what we do in
33:23the digital oil field is that
33:24you're saving time by automating
33:27the first three layers the data
33:29management according
33:31acquiring the data managing the data
33:34validating the data
33:35and then linking this data in the
33:38information and the information that you
33:40have into the applications
33:41that will perform analysis and
33:44diagnostic and surveillance to you
33:46and designing the workflows
33:49that you have
33:52now we have around maybe 20 minutes or
33:56something
33:56so i want to take you into an example a
33:59real example
34:00of digital oil fields right
34:04what are the simple steps that we take
34:07to perform
34:08a digital oil field and how do we think
34:11about
34:12implementing digital oil fields now
34:17what we have here and i'm gonna take you
34:20step by step into this
34:22what happens is that people will look
34:24into the reservoir right or their
34:26or their feel and they say uh uh
34:29i'm having an issue i'm having a
34:31depleted asset with stacked reservoir um
34:34i have a minimum instrumentations i
34:37don't have a good data on the field
34:39and i need to uh because it's depleted
34:42field and i'm trying to
34:44a brownfield and i'm trying to optimize
34:45this field i need to
34:48use a enhanced oil recovery scheme to
34:51improve the sweep efficiency
34:53so the questions were okay what do
34:56i do first of all to recognize
35:00the the where to implement how to
35:02implement
35:03the the the the eor scheme that i have
35:06in mind
35:08uh understand uh uh who's involved in
35:11the process
35:12what can i what can i do to to
35:14compensate for the lack of measurements
35:16that i have and which wills will benefit
35:20from this scheme
35:23so we start with a challenge with the
35:25asset challenge or a field challenge
35:28right what we want to do is to establish
35:31a framework
35:32that will benefit the business case and
35:34implementation strategy for this
35:41the part the first part that we start
35:43with is a site assessment what does site
35:45assessment mean
35:46it means that we look into a complete
35:48understanding
35:49to the current status of the assets what
35:52are the available data what are the
35:53current practices and processes
35:55who are the engineers what do they do
35:57what's the current instrumentations on
35:59the field
36:00a complete gap analysis to understand
36:03the missing points on the asset
36:06how many process engineers do you have
36:08how many petroleum engineers and who's
36:09responsible for what
36:11once you understand the the situation
36:16you need to understand the the data
36:18situation
36:20fully how do you capture your data what
36:23measures
36:23of validation do you apply how many
36:25databases do you have
36:27any replication of the data the answers
36:29to all of those questions shows if your
36:31data is
36:32reliable to be utilized in digital
36:35workflows or different measures need to
36:37be taken
36:38such as implementing sensors for example
36:40in your wellheads
36:41doing well tests more frequently or data
36:44aggregation methods
36:46now after making sure that
36:49petronas data is reliable
36:52there is a stage in looking into the
36:54technical and business workflows
36:58how many whales are using multi-dynamic
37:00simulation to help in identifying your
37:02flu assurance issues for example if we
37:05automate
37:05specific tasks would that save your
37:07engineer times and so on
37:10and then the next step is looking into
37:11resources management
37:13what does that mean it means how does
37:16each person
37:17perform and accomplish a specific task
37:22and how can we how can we introduce
37:25this or how can we fit this priority
37:29into the digital oil field application
37:32and then the last is what we call change
37:34management this is a bigger step
37:37and the purpose we do that change
37:38management management or what the change
37:40management management means you guys
37:42will
37:42understand this perfectly when you're at
37:46college and we introduce a new
37:48system for you you take time to adapt to
37:51the system
37:52and if the old system still exists then
37:54you're probably because
37:55we are used to our own habits
37:58you're probably gonna dismiss the the
38:00new system and go back to the old system
38:03so when you have a system like digital
38:04oil field where you're implementing so
38:06many processes
38:07and investing huge amount of time and
38:10money
38:11you need to spend time
38:14training and teaching the people how to
38:17use the new system
38:18to adapt to the new system and not to
38:20dismiss it
38:22now let's let's talk technical a little
38:24bit right the
38:25this this was more of a business
38:29slide a bit of a high level slide of a
38:31business but
38:32but now let's talk technical
38:36some wrong fields like any other field
38:38they
38:39they want to implement digital oil
38:40fields
38:42so we looked closely into the challenges
38:45that we had that we have and what did we
38:46realize
38:47we realized that first of all the
38:49injection of gas
38:50was done based on assumptions so sitting
38:53at an optimized strategy for gas lift
38:55will be a priority
38:56so basically engineers will assume that
38:59this is
39:00the amount of gas that we need to inject
39:03uh within each well right
39:06so optimizing this gas injection is a
39:08priority
39:10second challenge that we we discovered
39:12was that due to lack of data
39:14it took the team up to one month or more
39:17to realize that some wells were down so
39:20a quick system that shows well status
39:22and notify changes is necessary
39:24so they spend them a huge amount of time
39:26time we discovered that wells
39:29were down and to get it back into track
39:33and then the third challenge that we
39:36looked at was due to lack of measurement
39:38allocation was not correct
39:39wealth is validation and correct
39:42procedures
39:42for allocation is required
39:46several bottlenecks were identified and
39:48it was to establish that applying best
39:51practices
39:52and instrumentation will give huge value
39:55to
39:57this field
40:04oh a bit of a complex slide
40:08so let's try to simplify it
40:14now when you move to the next step after
40:16identifying the challenge the first step
40:18we've done the site assessment we
40:20identified the challenges
40:21in the field we now know what do we need
40:24to solve or the problems that we need to
40:26solve
40:26on the on this reservoir or in this
40:28field now we
40:30need to move into ensuring that data
40:33is the data quality
40:36is there if you don't in any project
40:40in digitalization if you don't ensure
40:42the data quality
40:43is um important or is reliable
40:47then garbage in garbage out whatever you
40:49get in whatever you're going to get out
40:52so at this stage data was being
40:54collected mainly on monthly basis
40:56there was a need to have high frequency
40:57data because you're looking
40:59into optimization
41:02so instrumenting the field and fixing
41:05any faults in current instrumentation
41:06was essential
41:08we also spent around three months
41:09correcting data and the existing
41:11historian to ensure that all information
41:13is correct
41:14quality rules we've done something
41:16called quality rules and aggregation
41:18quality rules mean that within the
41:20system you inform
41:21the system you know your your reservoir
41:23very well so you know for example that
41:25pressure
41:25will not drop below specific uh
41:29amount or it will not increase beyond
41:32specific amount
41:33temperature so those parameters you can
41:36put
41:36something called data
41:40aggregation or quality rules where
41:43you're saying that
41:44an alarm will be provided if the data is
41:48below or above
41:49specific parameters specific points
41:54and then what we've done was
41:57[Music]
41:58was that we we provided the next layer
42:01or
42:02extra layer to compare between the
42:04operational results
42:06and the theoretical results that you
42:08have for example
42:09you do a monthly test to under to see
42:11how much is your production rate
42:13but you can also perform a a daily
42:18rate estimation using pipesome for
42:19example or prosper right
42:21comparing the operational results to
42:24comparing the wealth test
42:25the rate coming from the well test with
42:27your monthly or
42:29daily production will give you
42:32a
42:33[Music]
42:35an understanding if this will is
42:37underperforming
42:39right
42:43now what we want to do once we have
42:45confidence in data
42:47what we want to do is to move from being
42:50reactive from discovering that there is
42:52a specific
42:52issue after one month to being proactive
42:55what does that mean
42:56means into looking into gas lift
42:58performance now what you see here
43:00is identifying that there is an
43:03opportunity
43:04for example related to gasoline for
43:06example uh
43:07i hope i hope you can see from here i'm
43:11realizing now that
43:12maybe this is a little bit small but
43:16let's explain it together right uh this
43:18is gaslight's performance
43:20increasing the gas injection would
43:22reflect an increase in production giving
43:24the engineer time to perform validation
43:26and ensure the extract so here
43:28you have a recommendation to increase
43:30gas lifting
43:31injection into specific specific frame
43:35now sorry
43:39usually uh when i show
43:43something like this to engineers they
43:46get a little bit skeptical
43:47right they say if
43:50the system is giving us the
43:52recommendations
43:54what's the benefit of having an engineer
43:57and there is an important
44:00benefit of having always having an
44:02engineer is that this is a system
44:04it needs someone to manage it what does
44:06that mean it means that if the system is
44:07giving you recommendation
44:09it's your responsibility as an engineer
44:10to validate the recommendation
44:12to validate if really increasing the gas
44:15lift to this amount
44:16will give you the benefit or not it's
44:19also your job to evaluate if
44:20economically this is
44:23advisable or not so just because the
44:25system is giving you
44:26a recommendation doesn't mean that you
44:28need to imply
44:29or apply this recommendation you are the
44:32person who
44:33uh responsible for giving the
44:36advices to the operators right so you
44:39are the person who will look into
44:44comparing specific recommendations
44:46choosing the right one
44:48and then see if economically it's
44:51advisable to do that or not
44:55it can only not only it can give you an
44:57opportunity right not only we provided
44:58some around good opportunity but
45:00also we looked into the risks so here
45:04there is a risk of wax deposition
45:07uh so before
45:10wax becomes an issue it blocks the the
45:13pipeline
45:14and uh you need to close or you need to
45:16shut in the will
45:18and shorten the performance of the the
45:20whole network
45:21and start cleaning the pipeline the
45:23system is able to give you
45:27a risk that you are
45:30critically there is a wax deposition in
45:31this well and you need to start
45:33acting on it it also as you see it also
45:36gives you a recommendation
45:37up to you to take it or not and
45:41everything like this you can look into
45:42high original velocity we've done a
45:44specific
45:46visualization tools for samara
45:50where they are able to
45:53look into opportunities and look into
45:56risks
45:58as quick as possible and not wait
46:01for issues to happen
46:09now remember
46:13remember when we were talking about um
46:16[Music]
46:18pre-orderizing if you're gonna go into
46:20surveillance if you're gonna go into
46:22optimization
46:23or if you will uh look only into the
46:27surveillance part for example what are
46:28you going to do
46:29this is an example of how you think
46:32about that the return of investment
46:34and operational guidelines right for
46:37example you're looking into
46:40when we're looking into sorry it's a bit
46:43i'm trying to simplify it but
46:44it's it's a bit difficult but let's
46:47let's
46:48simplify it together uh now i've given
46:51the insights to the engineers
46:53engineers now have the insights right
46:56engineers
46:56needs to prioritize what are the
46:58workflows that
47:00when implemented will give
47:04highest return of investments for
47:05example in summary there are two
47:07workflows that were identified that
47:09they are on top the gas lift
47:11optimization
47:12and reviving the quitting well and we
47:15decided to start with gas lift
47:17optimization until the field automation
47:19is complete
47:20because the later workflow depends
47:22heavily on measurements unlike gas lift
47:24which depends more into simulation
47:26right
47:29and then we worked with petronas to
47:31understand each workflow as
47:33this situation and designed a new to be
47:36workflow
47:37what does that mean it means that how do
47:39you do that optimization
47:40where are the gaps or why why you're not
47:43performing very well when you when it
47:44comes to basic optimization
47:46let's change this into the insights that
47:49we've seen before
47:51for each workflow it's very important to
47:53identify rules and responsibility of
47:55each user
47:56who is going to look into the data who's
47:58going to collect the data who's going to
48:00transmit it who's going to validate it
48:02who is going to perform get gas lift
48:04injection who is going to perform
48:06uh optimization over the wealth
48:08optimization over the field and so on
48:10right and then due to lack of data
48:14do we go into data driven or model
48:17driven
48:18right
48:21uh we think about this process
48:25on each workflow that we do so i'm just
48:28showing you that
48:29digitalization is not uh complex but
48:32it's also not simple it really depends
48:34on uh the workflow that you're doing
48:37so for each um challenge that you're
48:40targeting
48:41you need to think the steps that we were
48:44talking
48:45before on each challenge
48:48now this is the part that i always like
48:52is looking into the successful case
48:54or or or how did people or what what was
48:57the benefit of using digital oil fields
49:00uh on on
49:03on the field challenges right
49:07so remember we talked about gaslight
49:09samara has an issue with gas
49:10utilization right diagnostic the value
49:13of gasoline diagnostic and optimization
49:14workflow
49:15is mainly for automating most of the
49:17process instead of being handled
49:19manually what does that mean
49:20it means that workflow will give an
49:22insight that will
49:24that the well was multi-pointing based
49:26on several parameters
49:28the system they will then check the weld
49:30test parameters
49:31and perform diagnostic to confirm the
49:34multiple
49:35pointing then the workflow will then
49:38recommend
49:38deepest injection points to the engineer
49:44now this is the part now what did we do
49:46we saved engineer time
49:48in in performing uh this diagnostic
49:52the engineer will will run the run
49:54sensitivity study on operating
49:56conditions to validate the
49:57recommendation
49:58and perform any diagnostic any further
50:01diagnostic required
50:03then the office will send a request to
50:05reduce
50:07for example the chp to optimize the weld
50:11production
50:13right so it's an automated process
50:16where the system will will perform
50:19specific
50:20points and will raise an alarm due to
50:22multi-pointing we'll
50:24look into the sub optimal oil production
50:26then we look into the
50:28the deepest injection point then the
50:30engineer
50:31will run sensitivity in the operating
50:33conditions
50:34and identify the issue
50:37then solution is being communicated to
50:41the field
50:42right to being performed how much
50:44samaran saved i know
50:50i know you guys are most of most of you
50:51are engineers
50:53so you care about the technical uh more
50:56than the business but business is linked
50:58especially in oil and gas is linked
51:00to technical so the most important part
51:02is once you've done
51:04and you invested in this workflow how
51:06much really did you gain from it
51:08the game here was that they were able to
51:11reduce the gasoline consumption
51:13from consumption from 0.9 to 0.4
51:17uh millions cups per day and they were
51:20able to
51:20increase 200 parents per day
51:24for production right so at the end this
51:27is what
51:28you're looking for what did you gain
51:31from implementing the digital id
51:34now let's look into another example
51:38in this particular case wind was flowing
51:41at no beam with low
51:44flow hit temperature which was
51:46fluctuating between 60 to 80
51:49psig suggesting that the well was
51:51slightly surging
51:54now chp was very low and was
51:56insufficient to ensure deepest and
51:58single point to injection
51:59with the higher gas lift injection as
52:01well the system suggested that injection
52:03on six
52:04mandrel but when the engineer performed
52:07well diagnostic
52:08he confirmed that this was impossible
52:11and his recommendation was to
52:12investigate the valve
52:14status which was found falling and was
52:17fished out
52:18right then the wave model recommended
52:21the optimum court size
52:22office to have the highest gain which
52:25was installed
52:27so this is a completely different
52:30situation
52:31where the gaslight bulb
52:34pollen was detected
52:38the diagnostic of the engineer who
52:41didn't know
52:41that that the gas left to
52:45was not in place was to inject on the
52:47sixth mandarin
52:49which was impossible the system
52:50recommendation was that this was
52:52impossible to do
52:53and the recommendation
52:56was given to fish out the fallen gas
52:58lift and to install a new window
53:02what was the benefit of using this
53:07workflow or process is to increase well
53:09production
53:10by 62 barrels per day and
53:140.6 million cups per day which was
53:17injected
53:18extra trying to optimize the weight
53:19production
53:23now
53:26another example of uh
53:29[Music]
53:31a workflow that was limited in samara
53:33right in that case the world was flowing
53:35with high growth rates so well status
53:37immediately changed
53:38so here you can see well uh
53:42notification on on growing gas right
53:45the wealth status an alarm was given to
53:48the engineer
53:49immediately that a well-known gas
53:52condition
53:52is being detected and the recommendation
53:55was to check the subsurface safety
53:56valves
53:58the asset manager assigned this as a
54:00ticket to the field
54:02engineer so this is all automatically
54:04right you assign a ticket to the field
54:05engineer
54:06the field engineer will will observe the
54:11fthp dropping which is a sign that
54:14will quite after chp bleedo
54:18then he checked the subsurface safety
54:21valve
54:22status and it was found closed and set
54:24it back to open
54:26and will was back into production
54:29this is all something that's being
54:31digitalized
54:33right so uh when you are in the field
54:37detecting that the safety valve is is
54:40being closed
54:41it's not something easy changing it to
54:44open
54:45remotely is not something easy so
54:47digitalizing allowing you
54:49to to perform those remotely operations
54:53uh within the comforter office
54:56similar to how we do zoom right now
54:58right i don't need to come to you to
55:00perform
55:01presentation i don't need to come to
55:02each person's house to
55:04present or we don't need to meet we meet
55:06globally through zoom it's the same
55:08thing
55:08digitalization allows you to remotely
55:10perform
55:11um uh to remotely perform
55:16uh processes and applique and and
55:18instructions
55:20uh very quickly without the need to
55:23manually
55:23uh instruct things so just
55:27by applying digitalization on this wheel
55:29we in this well
55:31uh or in this workflow when he was back
55:33to production
55:34uh having 450 barrels
55:37per day right
55:40so uh we're almost one hour and i
55:43usually
55:43i still have some flights but i usually
55:45honestly don't like to go beyond the one
55:47hour
55:48when it comes i think i think this is
55:50huge too much information
55:53to uh to really um
55:56how do you say that to really understand
56:00it in one hour
56:02so i want to stop on this part and
56:05i'll use this into the next uh
56:08presentations
56:09um what i want you to get out of
56:13out of today's presentation before we go
56:15into the q a session
56:17is that
56:20when you move into digitalization
56:25uh when you move into visit sorry let me
56:28oh yes
56:28when you move into digitalization you
56:31actually
56:32um
56:35move from shifting from being reactive
56:37into being proactive
56:40you don't wait until the issues occur or
56:43happen to you
56:44you actually know
56:47the situation you're really very well
56:49aware of what's happening around you
56:51that your will is not performing very
56:53well and that you will can be optimized
56:55you're increasing the efficiency of your
56:58team and increasing the efficiency
57:00of your productivity of the way you're
57:02working and increasing
57:03the profitability and you're enhancing
57:05the collaboration with your team
57:07not working alone you're not relying on
57:09yourself
57:10you're relying on many uh people around
57:13you
57:13right um i i will share with you this
57:18presentation i've put some spe papers
57:20for you to
57:21to read about digital oil field
57:24because uh because tomorrow uh sorry the
57:27next session
57:28we're gonna talk about about the shift
57:30on digitalization so
57:32i'm gonna show you the shift on
57:33digitalization to prediction
57:35and why this shift is happening and
57:37we're gonna cover two slides
57:39that we didn't cover on this session
57:42about
57:43why you should care about digitalization
57:45as a production engineer
57:46and why you should really take some
57:48extra time
57:49to familiarize yourself with analytics
57:52solutions
57:53familiarize yourself with the with
57:54digital oil field
57:56and and some of this
57:59terminologies right
58:03so i've come to the end of my
58:04presentation in
58:06case we want to take the q a yeah thank
58:09you engineer hassan for a very
58:11informative webinar
58:12i'm sure the audience benefit greatly
58:14from it
58:15in the meantime i've collected a few
58:17questions for a quick q a session
58:20the first question is what is the
58:23difference between
58:24enterprise and field operations
58:27oh perfect this is a very very good
58:30question
58:31uh field operation so let me actually
58:35know it's easier to
58:36look into this let's go back
58:40into the first few slides that we have
58:43this one when we talk about fields
58:47we're talking about the the facility the
58:49wells the reservoir
58:51the wells the network and
58:54uh uh the gathering centers for example
58:56and the facilities right
58:58when you're talking about logistics
59:00situation
59:01when you're talking about uh
59:04petrochemicals when you're talking about
59:08erp system or shipping points for
59:10example you're here going into
59:12enterprise level
59:14right as an engineer you deal with
59:18let me show you something
59:21yes as an engineer you deal with the
59:24challenges on the field you deal with
59:26the network you deal with the facilities
59:27you deal with the reservoir
59:29but putting everything together dealing
59:31with sap systems for example
59:33that will read your data and perform
59:36some calculations for you
59:38linking this systems into hr
59:42for example uh how many engineers do you
59:46have
59:46are your resources optimized or not for
59:48example
59:49this is part of your enterprise system
59:53right um am i clear
59:57or uh hopefully so
1:00:00um yeah the second question is
1:00:04is it possible to face a situation where
1:00:06the cost of digitalization
1:00:08is higher than the computed roi if so
1:00:12how does the engineer handle this
1:00:13situation
1:00:15uh honestly i love the questions very
1:00:19much
1:00:19uh i was a bit skeptical that maybe this
1:00:21topic is a bit
1:00:22uh higher but about seeing the questions
1:00:25i'm very very happy
1:00:27that we're doing this presentation yes
1:00:30especially at the beginning when we've
1:00:33started doing digital oil field in the
1:00:34industry 15 years ago
1:00:36there are many situations that we faced
1:00:38where we discovered that we are running
1:00:41on a very high cost
1:00:45and the roi is not as much as what
1:00:48operators expected and that's why
1:00:51we introduced what we called um
1:00:56remember when we were looking into
1:01:00where was it
1:01:03when we were talking about uh samaran
1:01:06we talked about having comprehensive
1:01:08site assessments and on the site
1:01:10assessment what we do
1:01:11is that basically we sit with higher
1:01:13management and we understand the key
1:01:15eyes of management we understand okay
1:01:18you want to increase production you want
1:01:20to reduce cost you want to have a proper
1:01:23field management
1:01:24what do you want to do exactly and then
1:01:26we sit with engineers and we see
1:01:28uh the way they do or the way they
1:01:31perform
1:01:32uh their diagnostic their analysis the
1:01:35way
1:01:35they want to do and then we we come up
1:01:38with our
1:01:39as this situation and we come up with
1:01:42the new situation and what does the new
1:01:44situation will save for them
1:01:46based on that we decide if the cost
1:01:50is applicable or not now if the cost is
1:01:52not as applicable and and as we were
1:01:54talking for example we said okay do you
1:01:55have
1:01:56data no can you implement sensors uh can
1:01:59you implement sensors for example
1:02:01no it's it's too expensive for example
1:02:04because the the the the the
1:02:06field is remotely uh established so it's
1:02:09gonna be very difficult
1:02:10to implement uh sensors
1:02:13okay can we implement at least one or
1:02:15two sensors no can we implement
1:02:16analytical solution
1:02:18to provide for the lack of data of not
1:02:20coming from sensors and so on right
1:02:23so right now what you do before make
1:02:25sure
1:02:26before you implement any digital oil
1:02:28field is to do a comprehensive site
1:02:31assessment
1:02:31before anything a report that will tell
1:02:35you
1:02:35this is your return of investments this
1:02:38is the current situation that you have
1:02:40and this is what you're going to do to
1:02:42receive
1:02:43to our to reach this return of
1:02:45investment and this is how much it will
1:02:47cost you
1:02:50great the third question is during data
1:02:53optimization what are the specific steps
1:02:55to know which data can be useful
1:02:57and which is not
1:03:00uh this is again a very good question
1:03:02the data that's going to be useful or
1:03:04not will depends on the workflow
1:03:06that you're uh implementing right
1:03:09so let me see if for example
1:03:14for example when when we were talking
1:03:15about samurai we said that we're going
1:03:17to do gas left optimization right
1:03:19so is it really useful for you
1:03:22to uh to collect data
1:03:25related to um facilities for example
1:03:29you're not going to do anything on
1:03:30facility itself you're you're focused on
1:03:32gas left optimization
1:03:33so um the data required to do gas left
1:03:37optimization as an engineer when you're
1:03:38doing gas left optimization manually
1:03:40those are the data that are important to
1:03:42you
1:03:43in the workflow that that that you're
1:03:47identifying so the first part is
1:03:48identifying the kpos
1:03:50identifying the workflows and based on
1:03:52identifying the workflows that will give
1:03:54you the return of investment that you
1:03:55need
1:03:56you can identify the data that are
1:03:58important to you
1:04:01okay thank you for answering engineering
1:04:03this concludes our
1:04:04quick q a session so thank you again
1:04:08for dedicating some time of your surely
1:04:10busy schedule um
1:04:12thank you attendees for tuning in from
1:04:14all around the world
1:04:15please stay safe wear a mask and have a
1:04:18great day
1:04:19thank you very much chef thank you all
1:04:21very much and thank you for surrendering
1:04:22for the prototype

About this transcript

This page contains the full transcript of Practical Applications of Digitalization in the Petroleum Industry, Eng. Marwa Hassan, Lecture 01/04 by PioPetro, generated from the public captions YouTube serves with the video. The transcript has 9,503 words across 1,767 segments, with the original timestamps preserved so you can click any line to jump to that moment in the embedded player.

What you can do with it

Use the transcript to take notes, quote the speaker, build a study guide, generate a summary with ChatGPT or Claude via the YouTube Summary tool, or export it as a timed subtitle file with YouTube to SRT. You can also re-open it in the transcriber to translate the transcript into 100+ languages.

Free YouTube transcript tool

YouTube2Text is a free YouTube transcript generator — no signup, no daily limit. Paste any YouTube link and get the full transcript instantly, with timestamps, click-to-jump, translation to 100+ languages, AI prompts for ChatGPT, Claude, and Gemini, and exports to TXT, SRT, VTT, or Markdown.