Welcome. Everyone and thank you for joining us today on this live webinar that digital, twin technology, now it seems that this is a popular, buzzword right now but is it just another marketing, label, is a real value, in, what, the technology, has to offer process, industries, well, you can be the judge after listening to this webinar, this, webinar is a, collaboration. Between Yokogawa. And KBC a Yokogawa, company now, I'm not sure if you're aware but KBC, was founded in 1979. By Creek whore Krekorian John, Bryce and pizza close and. The name KBC was formed, from the initial letters of their surnames, in 2016. KBC, was acquired by Yokogawa, an integration. Of KB C's distinct, consulting, and software capabilities. With Yokogawa's excellence, and industrial automation field, will, ensure that we continue, to deliver superior. Results, for you our customer, I would. Like to introduce our presenters, Duncan, MacLean and Kevin, Fannin to you today, Duncan. Is, responsible. For the business strategy and marketing, functions of KBC a Yokogawa, company as well, as Yokogawa's North America business he. Is passionate about technology and, the value it can unlock Duncan. Started his career in engineering industry. With ammok where he provided health safety, and environmental, liability. Management advice on mergers and acquisitions. Covering. Upstream production assets refining. And petrochemicals. After. Moving to KBC he has held business, management roles focused, on business development strategy. Restructuring. And planning, kevin. Finan is a system. Consultant, at Yokogawa, and has over 30 years of experience with, oil and gas measurement process. Automation, and SCADA systems, he, was previously an, independent, consultant serving. The automation and measurement industries, vice. President, of marketing for CSE, semaphore. And director, of marketing at Bristol Babcock, again. Welcome and thank you for joining us today please remember you can send in your questions and type them into the Q&A box at, any time right. Let's get started over to you Duncan thank you Thank. You Christy, well good morning good. Afternoon and good evening everyone, thank, you for joining Kevin. DNA on this webinar about digital, twin now. Digital. Twins can't, just be thought of as, a nebula. Concept, or abstract. Enabling. Technology. They're. An enabling, technology in, the journey towards, autonomous, operations. So. In this webinar we'll look at the journey towards, autonomous. Operations, and with, that concept, in mind focus. On the digital twin in terms, of, what. It is where. Does it exist, what. Is the scope of insight. Derived, the. Scalability. Of the digital. Twin what. It's not. How. It can be hosted in the cloud or on-premise, the. Potential, business model impacts, that, this that the digital twin, has and finally. The value. Digital. Twins aren't all made the same so, we'll focus on two, case, studies. I'd. Like to open by asking. Everyone. On this webinar one question, as you. Seek to squeeze, incremental. Value from your people processes. Technologies. And physical assets are, you, guilty of just pursuing, a faster, horse or. Is there another perhaps. Better. Way. Your. Horse may have been serving you well over the years and we're, pleased for that but, will your horse carry you forward at the pace this, new world we live in which. Is a lot more digital. Affords. We. Look forward to sharing our passion on, the other perhaps better way through, the digital twin. Before. We dive into the nuts and bolts of digital twins the. Pursuit and adoption, of these technologies in. The, context. Of a digitalization. Journey driven. By, both internal. And external factors. The. Process industries, drive towards, semi and fully autonomous, operations. Coupled. With energy, transition, realities, and pressures are forcing. Operating, companies, to seek digital, platforms, and fully, adopt, disruptive. Technologies. As their, normal way of doing business in their quest for superior. Results. Sustained. As Christy. Mentioned, Yokogawa. Along with its subsidiary, KBC, a Yokogawa company, is, digitalising. The energy and chemical, industry, through. A unique combination, of domain. Knowledge and experience, be. A technical, commercial. Or in operations. Technology. Be, it AI IIT, Digital. Twin and automation, and thirdly. Through. Digitally, wise and, digitally, savvy, methodologies. Roadmaps. And change, management techniques.
But. Delivering superior results sustained, does, involve, some subjectivity. For. A business that, is at the low end of the operational, excellence maturity. Spectrum, as you see here, success. May be continued. Loss minimization. Whereas. For a more operationally. Mature business, towards, the right success. May be positive. Cash flow or repeats. Repeatable. Results, you. Can see these at the base of each of the vulnerable. Accepting. And structured. Pillars, but. Irrespective, of maturity. Effective. Progression, on the journey from left to right involves. Accepting. Your current maturity. Deciding. What the improvement, ambition, is ie. The, desired, end goal for example. Is it the structured, maturity. Pillar and then. Agreeing, a realistic, timeframe of which the improvement, needs to happen. What. We found is things always take, longer than, you'd like, it's. Often a multi-year, process for. Coherent. Progression, of all, aspects. Of the operating, model people. Processes. Technologies. And physical, assets. The. Starting, point of the evolution, is always. A set, of high, fidelity first. Principles, based models, of the business, incorporated. Within a multi-purpose. Lifecycle. Simulation, platform these. Are really the heartbeat of the business and provides. Situational, awareness. Without. Them you're just guessing. At. The beginning of the journey. Towards, the left hand side there are low levels of automation the. Plant is manually, operated, by a large front line workforce. Executing. A collection, of best practices. Supported. By, first principles, models, as the. Plant implements, more and more manufacturing, execution systems. It becomes. More automated, and in, doing so achieves. A smaller front line workforce footprint. Who, are primarily, executing. Advice, based actions, in open-loop, all. The while the, stability, controllability, and, predictability, of, the, plant is being enhanced for. Widespread adoption of, closed-loop. Control, and procedure. Automation, ultimately. In closed-loop. Optimization. Different. Parts of the energy and chemical industry are further, along in this journey than others for example discrete. Discrete, batch, processes. In. Specialty. And fine chemicals, have been able to advance faster. Than say, refining. Liquefaction, or other complex. Continuous. Processes. Key. To the progression is the, implementation, of mes, analytics. AI and, machine learning technologies. Through. This process the plant becomes more empowered, to run, learn, adapt, and thrive in, an increasingly, dynamic business, environment. So. You're probably wondering where. Does the digital twin, fit in. What. Is interesting about the previous illustration is, that each progression. Towards. Autonomous, operation, involves. Evolution. In. How. Decisions. Are made a, digital. Twin is a decision, support tool that, enables, improved, safety reliability and profit and profitability, in, design. Operations, it is. A virtual, digital copy of a device a system. A human. Or process, that accurately. Mimics, actual performance, in real, time there's. Executable. And can, be manipulated, allowing, a better future to be developed so. To. Be a virtual, digital copy of a device. Human, or process, means that the. Digital twin, can exist at any, level within, the traditional, is a, 95. Architecture. And be. Scalable, to integrate, with. Other components. In, subsequent. Slides I'll make further reference, to the scalability, of the digital twin as will, my colleague Kevin.
As. Far as scope of insight. Is concerned. Digital. Twins work in the present, mirroring. The actual, human device system, or process in simulated. Mode but, with full knowledge of its historical. Performance and, accurate, understanding, of its future, potential, in this. Way the digital twin allows the, full scope of hindsight. Insight. Foresight, and, oversight. To be delivered, but. Why is this important, well. It. Allows. Understanding. Of what is happening or has, happened it, allows, an understanding. Of why it has happened and then. Switching, to the future what. Will or might or can happen and lastly. What should, happen and, this. Is not just about a bunch, of graphical, dashboards, it goes well beyond, that to incorporate, first, principles, models. So. Let's move away from, conceptual. And theoretical to. Real, delivered. Value. Will. Do this through, two case studies, one. Involving, a subsea. Production system. Feeding, an FPSO. The. Other involving, a, 55,000. Barrel a day FCC. In refining the. Concepts, and realities, are equally, applicable in, petrochemicals. Too. Let's. Start with, the. Upstream, example. So. Reservoir. Fluid characterization. On the, seabed. KB. C's multi. Flash software can be used to provide a digital twin, of the, reservoir, fluid phase behavior under. Different pressures. Volumes. And temperatures. This. Is vital. For assuring. The integrity, of. Line fluid, flow. Building. On the multi flash-based digital. Twin is a. Twin, representation. Of the entire subsea, production network, of, whatever. Complexity. Including. Wells. Chokes, flow lines and a, wide range of processing, equipment. This. Is done using Maximus. With. The multi flash twin. Capabilities. Natively, integrated, into, the more expansive Maximus. Model of the, production, system flow. Across the whole network can. Be optimized. Building. Yet again on the, multi flash and Maximus, models is a, representation. Of the entire production system. Including. Topside facilities, and power generation be. It an FPSO, or offshore. Platform, the. Incorporation, of power generation is absolutely. Key because, power generation, systems. Apart, from constituting. A major variable, cost, drive. A number, of critical production processes. Such as compression. Systems, oil, export, pumps, and utility. Systems. Offshore. Powers offshore, power generation, systems, of. 5,200, megawatts, are not uncommon. The. Challenge with offshore power, generation, is that the power, generation, feedstock. Is also, the product for export in order. To ensure power generation, resilience, there's, a need to better understand, production. Dynamics, in conjunction. With power generation. The. Petrol sim model incorporating. Multi flash and Maximus. Allow matching, of power generation, - well deliverability, which. Is worth a lot of money as we'll, see on the next slide. How. Much money in short, one, hundred and eighty million dollars per annum for, this particular case. The. Asset comprise just over 20 Wells feeding, a self-powered, fpso, the. FPSO, had a capacity, of 90,000, barrels a day of oil 10. To 20 million cubic feet per day of fuel gas handling, and treated. Water injection, rates of up to 30,000. Hours a day. Matching. Well deliverability to, topside, power generator, and compressor, availability. In a, single, model, environment. Was able to boost FPSO, production, by nine thousand, barrels a day these. Results, involved. No, capex, investment, use, onboard, equipment only and matched. Subsurface, to, surface pressure and flow, first. Time power production balance, was implemented, resulting, in a new production regime, with. Altered, production, rates driving, significant. Incremental. Value as you, see here, as. I. Move on to the next slide I won't spend a lot of time on these, but. I would like to, point out how in, this, first screenshot you'll, see how, well. Models, and subsurface, templates, along with FPSO, trains power, generation, and on-board compressors, were, represented, in an integrated, manner. Cumulative. And system-wide, production, dynamics, were, able, to be rigorously, represented. This. Next slide shows a little bit more detail, when you drill down into, the individual. System, components. With. A lot more detail available. Which. Obviously, you can't see through this screen but each of these components. Can be drilled down a lot, further. Lastly. The. Chart on the next slide shows the nonlinear, relationship, between pressure, and flow at different, turbine intensities.
Without. The model. The. Nonlinear, relationship would, not have been apparent and. The. Optimum, operating, conditions, would have been a lot more difficult to. Observe. That's. All I'm going to cover on this case study but, if you'd, be interested in receiving a, more, detailed write-up on this please email me at Duncan. McClung at us, Yokogawa, comm. So. This nick's case. Study i realize. Not everyone plays in the upstream world so switching to downstream, and specifically, a 55,000. Ballad AFCC unit, this. Is a key unit, as, many, of you know in around, 50%, of, refineries, worldwide for, converting. Heavy. Gas oil vacuum. Gas oil or residue. Feedstock, components, into significantly, higher value products. The. Problem today is that the, tools used in the roof, in. The refinery in this case the FCC, to forecast, economic, performance are not, necessarily. Conducive, for use by the engineers, actually operating. The plant and who are responsible, for delivering the, operating, plan, this. Case studies about how. Over. A million dollars per year can be made through, much tighter monitoring. Of youth unit performance, by comparing, actual unit. Performance, with. High fidelity model. Simulated. And the. LP. On. The. Next on this chart on the next slide the. Actual performance is in, red, the. Simulated, plant. Performance using, high, fidelity models, is in blue and the. Yellow line is the, LP model of the plant. It's. Clear the best representation. Of the plant comes, from the first principles, models, so. It makes sense to use these, for. More of the operating decisions, on the, front line for. Identifying, profit, opportunities, and reoptimize. Encapsulating. Benefit. Of the. LP is its speed. Enhancements. In compute, power and multi-threading, of first principles technologies. Is making them increasingly, ripe to be used for, more of the. Optimization. Decisions. This. Particular example. Involves. An FCC the same, can be scaled for, other, units around the refinery, of. Particular. Interest, in today's, and business environment, being say the hydro cracker and the coca for bottom's, conversion. So. Far I've mentioned, simulators. Models. And digital, twins are, these the same. No. Models. Exist in the context, of traditional. Simulators. As well, as digital, to, but. Traditional, simulators, are different to, digital twins the. Best analogy of a traditional, simulator, is a. Traditional, calculator. Inputs. Are punched, in manually for, a particular calculation, the. Result is a static, snap, snapshot, in time and the. Result is available to. Only, but a few people who, are standing around the calculator, or consider, on the other. Hand a digital twin is an, accurate representation, over. Its full range of operation, all the time with, the history captured, for. Say data mining, as well. As the, future for what if what's, best and what's, next. Analyses. Instead. Of being manual it's automated, and the, outputs. Are, democratized. Or, can be democratized much. More easily across, the organization, for joined, up thinking and. Action, across silos. But. What does the digital twin, look like in practice, what's. An example and, I'll. Show you on the next slide. It. Simply involves a high, fidelity model. Of the, asset built say using petrol Sun so. That. Can include upstream, production facilities, LNG. Gas processing plants. Refineries olefins. And aromatics units. Models. Built are then, fed real-time production, data from the assets, DCs, historian. And lab system, and by. The way this is not difficult to set up the. Application, of complex, first principles, physics, and chemistry based, algorithms. To. DCs, historian. And lab system, data in, real time opens, up phenomenal, new insights, for. Supply chain optimization and. Production management. But. Instead, of the gems of insight remaining, siloed, to the engineers, running, the model what's. Key is they, liberated, to, the rest of the organization, with, both the the PI, system and the. Petro sim-based twin always. Remaining, aligned, now. This is a game-changer. For driving, convergence, in decisions. And actions across, engineering. Operations. And, other. Consumers. Of data from. The. OSI, soft. System. And other plant. Technologies, that feed in and feed off that. So. With. That in mind that's just one, example I'm. Gonna hand over to my colleague Kevin. Who's going to talk to you about, a few others. Thank. You Duncan we, do offer a broad portfolio of, digital twins with widely varying purposes, and, I won't describe all of them but should mention those that perhaps you might not expect for.
Instance Enterprise. Insight, is a digital, boardroom, that comprises, a series of business and financial KPIs. Which are updated in real time as part of an enterprise wide balanced, scorecard, the underlying. KPI calculations. Combine simple dashboarding, of measured parameters, with, integrated, logic, that. Could be linked to other digital, twins that optimize the process energy, consumption. In the supply chain you might see where we're going this but I'll explain some of the other digital twins first. Capability. Assurances, the suite of digital twins, that includes a human, knowledge twin, which, captures, work processes. Those. Can be tracked and manipulated, in real time they. Comply with is a 106, modular, procedure automation, for, example one of our customers implemented, modular procedural, automation by putting their best operative, practices on paper, not. Exactly digitalized, but still a quantum leap over the prior standard, operating procedures, but. Then they did digitalize, them to take advantage of change management, then. Further that deployment. Of digital twins for all of the work processes, has minimized, the learning curve for incoming users and it vastly improves, validation, of operating, scenarios, there's. Also a safety time I'll describe in a minute, operator. Training, simulation. Or OTS. Digital twins substantially, enhanced earlier model-based. In inferential LTS implementations. Through artificial intelligence, and real-time enablement, OTS. Digital twins work seamlessly with human knowledge digital, twins to, completely optimize, all human, aspects, in the enterprise. Now. The automation, and control integrity, digital, twins use digital copies, of the, live planning. In all processes and, all. Automation, algorithms, they, allow engineers to conduct fundamental, process control tests at their workstations. They, include any proposed adjustments, before they apply them to the life process, is an, example a customer wanted to see the interactions, not only within the controller, but, exactly how the process responded.
To Changes, in the, application, code a. Safety. Instrumented system, digital twin, also uses, a digital copy of the life plan and processes. But incorporate, safety logic, in place of the process, control logic now, keeping up on certified, functional, safety management policies, is a big issue safety. Systems change, over time, Duncan. Earlier, mentioned the hindsight, insight. Foresight, and oversight, the digital twin provides those, have turned out to be key to maintaining that. Functional, safety certification. As, the safety system involves, now. In addition, all. These digital twins could be combined like the safety instrumented system, and, automation and control integrity, difficult winds could be combined for both integrated. Process, control, and safety. Also. A combination of the safety digital twin and the, human knowledge digital, twin mentioned earlier provides full safety visibility, including. Future scenarios, to, an operator and the, management, team. Now. We can describe the other digital. Twins further in QA or, even afterward, if you want to contact us via email I think they're probably more in line with solutions, you'd expect from Yokogawa, and KBC that is evolutions. Of the simulation. Technologies. That Duncan described earlier. So. Again this portfolio digital, twins can operate independently or. Together, providing. A single version of the truth but. Now the question is where, will that lead. Our. View of it is digital nirvana. Contemporary. Digital twin, technology's, evolving, in a way that is leading to a single, multi. Purpose, digital twin, instead. Of multiple, digital twins each, of which serves a different purpose. The. Single, digital twin encompasses, today's multiple. Digital twins in a supplier agnostic, manner and it, aligns all assets, and the, value chain. Ubiquitous. Data sources, replace the ad hoc siloed, data to, provide a completely coordinated, and connected, environment. To. Illustrate a typical situation. Subject. Matter experts, use their domain knowledge to, operate the plan and then. They combine that with facilities, simulation, technology, for process, and production optimization. The. Models built are placed online, and they're, fed with real-time operations, data instead. Of a simulator, that creates. A digital twin, delivering real-time insight, and augmented. We're needed with insight, from beyond, the plant rather. Than simply data as a service, that, in turn enables, outcomes. As a service. So. We've just mentioned, the cloud so far but, a running the digital twin in the cloud does shift. The business model sometimes. Substantially, by the way in. The cloud the, digital twin not only serves the entire enterprise, but, can also engage subject, matter expertise, and technology, from outside, the corporate boundaries. That, could be vast. External. Data feeds and analytics, expand, your agility and radically. Reduce infrastructure. Costs. This. Enables, new business, models, that best exploit, the subject matter expert, domain knowledge and simulation. Technologies, to provide. Bi-directional. Added, value now, that's between corporate, assets, central. Or remote operation centers support. Teams and third. Parties, it also. Enables, third party suppliers to offer outcome. As a service, again for example instead, of a catalyst, the partner third party supplier, could offer catalyst. Performance. As a service. So. Now I'll hand it back over to Duncan, to conclude, with where the digital twin fits in and how, it is delivered, through a discipline, roadmap. Thanks. Kevin. So. On this, next slide if, these, are the four, main pillars of your operating, model in terms, of your, people, physical. Assets. Systems. And practices, where, does the, digital twin, fit. In well. It sits at the interface, or, of people, and the, physical assets being, or to be operated, as, I. Mentioned earlier it is a decision, support, tool, it's. Where each of the attributes meet. Where, significant. Value can be unlocked, where. People interact, with systems, it's, important, that the right data is available it's. Clean it's. Supported, by the technology. Infrastructure, it's. Made available in, a way that it is actionable. And that, the the, people to act on the data are, competent. Where. Systems interact, with practices, the, technologies, in place need, to support, execution. Of business, processes, to deliver the hindsight insight. Foresight and oversight. Often. This is often. This information. Is sufficient. To guide day-to-day. Frontline, actions, of operators, however, to really understand, the implications. Of these, possible actions, more. Rigorous, tools are needed for decision making to be able to accommodate what if what's, next, and what's best, analyses. Particularly. Where as I mentioned, previously, nonlinear. Relationships. May, exist. So. It's here, that.
Digital Twins and first principles, models, are of the. Highest value. Lastly. To actually move the plants, operations, so say decisions. Have been made the. Actions need to be taken on, the front line at the, interface, of practices. And systems. Initially. Operational. Execution. Or moving, the plant is done manually based on best practices, and then, moves to open loop and closed, loop -, procedure automation, and eventually, closed loop optimization. As. I mentioned before this doesn't happen overnight. And it does take a phase. Progression. But. A deliberate. Progression. All. Of this, underpins. The. KBC. Digitalization. Roadmap, which, involves, initially. Ensuring. Readiness. Moving. On to situational. Awareness and. Only. Once these two epps have been accomplished, should. The digital twin be considered, for implementation, because, as I mentioned previously, when. We were saying we'll what's, the difference between a traditional simulator. And a digital twin, if you, are going to be automating. This then. Readiness. Is. Absolutely. Vital. Before, you start to try and automate. And. Lastly. The. Final two steps beyond. This. Involve, execution. And sustainment, the, twin makes this significantly. Easier. With. That said I'm, going to hand back to Christie but before doing that I hope that if. You. Are. Or, have been guilty of pursuing, a faster, horse please, consider, the digital twinners perhaps a better, more, valuable way of achieving your business goals if, you'd. Like it a more, detailed write-up, of the thinking behind the digitalization roadmap. Again, please do email me at Duncan. McClure, met us tokugawa. Comm and lastly. Kevin. Did make reference to the. Different types of digital twin, please. Do look out for. Other digital, twin webinars, that will be running as part of this digital twin series these. Will be focused, on the. More specific, twin technologies, and their, application. And value. And so. With that back. To you Christy thank you thank. You so much Duncan, and Kevin for that fascinating presentation, and it's really great to hear about the two case studies and and real-life examples. Of where digital twin, technology, is bringing value to the. Process industries, right. We're going to look at the, Q&A now so if you would like to send through your questions please, type. Your question, in the Q&A section, and send it to all panelists. Our. First question received. You. Stated, that digital, twins accurately. Mimic actual, performance, in real time how, do you define real time Kevin do you want to tell, us more about this. Real. Time is relative. To the speed of the process the, key point that it is is supposed to historical, and it, has to use sufficient, resolution in, terms of time to capture process, dynamics for. Example, turbomachinery requires, a resolution in terms of tens of milliseconds. Flow. Processes, are typically about one second, and a, level or temperature, processes. Are slower they could be in multiple seconds, or even minutes. Thank. You Kevin a second. Question received, our digital. Twins either real-time, or historical. But, not both. They. Are both the, digital twin, works in the present, marrying. The actual human, device, system, or, the process, in simulated, mode but, it has a full knowledge of his historical, performance and, an, accurate understanding of, its future potential, in. This way the digital to analyze the full scope of hindsight insight. Foresight and, oversight. To be achieved, thank. You and we will gather up the rest of the questions, and answer, them by email we appreciate.
The Hosts Kevin and Duncan joining us today thank you very much and, thank. You for joining us we look forward to having you on another Yokogawa, webinar in the future everyone. Have a good day thank you so much.
2020-06-03