June 23, 2017 Creation of a three-dimensional Digital Twin is included in the list of standard functionality of Winnum®, a platform for the industrial Internet of things. With Winnum®, creating 3D Digital Twins is now as easy as connecting sensors.

“Digital twin” is a computer representation of a specific physical product, group of products, mechanical or technological process, which completely repeats everything that its physical prototype does, starting from movements and kinematics, and ending with a representation of its physical environment and current operating conditions, including movement liquids and gases. A digital twin acts as an intermediary between a physical product and important information about it, such as operation or maintenance data. Now, with the help of Winnum, a full-fledged Feedback based on collecting data from the real world and transferring this data to the digital world.

What is 3D Digital twin?

A three-dimensional Digital Twin is a computer-generated 3D representation of a specific physical product, group of products, mechanical or technological process, which includes not only three-dimensional geometry, specifications and current operating parameters, but also other important information- environment and operating conditions, technical condition and operating time, interaction with other objects, predictive analytics data, including forecasting failures and failures. A digital twin can be either simplified or very detailed and reflect a wide range of different characteristics of both the product itself and technological and production processes.

The presence of a three-dimensional Digital Twin helps to organize the connection of the product with objects connected to it, software responsible for managing the product, monitoring the operating state and operating process, etc. A 3D Digital Twin is especially valuable when it most accurately reflects the actual state and performance characteristics of its physical counterpart. No matter how accurate, detailed and elaborate the actions are at the stages of design, modeling and pre-production, in real life, as a rule, the processes proceed a little differently and it is the Digital Twin that can act as a bridge to necessary information about the actual operation of products. This information can be used in different ways, for example, to assess bottlenecks, opportunities for improvement and change, confirm the feasibility of changes, etc. In addition, since the Digital Twin is a three-dimensional object, working with it is much clearer for a person than working with any tables or graphs. A 3D Digital Twin allows you to look inside a real physical object while it is running, without having to stop the equipment or open panels that block access to parts that require inspection.

Winnum's unique functionality allows our customers to create and manage 3D digital twins by combining information from physical objects and real-world processes with information generated by various computer-aided design (CAD) systems. Winnum supports loading 3D CAD models in neutral formats such as STL, VRML and OBJ, with direct loading available for Blender and Collada. The presence of ready-made 3D libraries of robots, equipment, sensors and other geometric objects further speeds up and simplifies the process of creating Digital Twins, even for those companies that cannot boast of having fully digitized products in 3D form.

3D scenes and smart Digital Twins (Smart Digital Twin)

Each Digital Twin corresponds to one specific instance of the product. That is, if a company uses 100 pieces of equipment or produces hundreds of thousands of products, then for each piece of equipment/product there is its own Digital Twin. Winnum's unique Big Data capabilities help you work with so many digital twins to solve daily tasks and ensure high system performance regardless of their number.

3D scenes are used to combine Digital Twins and gain insight into their overall performance and performance, common environmental variances, etc. Winnum's 3D scenes are not just 3D environments, as is common in CAD systems. 3D scenes in Winnum are the ability to create a full-fledged 3D world with a wide range of tools for working with light sources (including Raytracing, specular views, fog, intensity, transparency), textures (including dynamic textures with video stream), custom cameras and mechanisms for interacting with 3D objects (selecting an object, clicking on an object, transferring a control action).

All actions of a 3D scene and all tools for working with a 3D Digital Twin are available exclusively in the Web browser.

About companySignum

Signum (SIGNUM) is a global provider of solutions for the Industrial Internet of Things (IIoT). The company's solutions help transform the processes of creating, operating and maintaining products using Industrial Internet of Things (IIoT) technologies. The next-generation Winnum™ platform gives companies the tools they need to collect, analyze and generate additional value from the large volumes of data generated by connected data. computer network controllers, sensors, products and systems.

Neural networks, digital twins, artificial intelligence. Industry 4.0 technologies will change the oil industry beyond recognition

Architects of the Digital Age

Usually the most technologically advanced spheres are considered to be information technologies and biomedicine. The attitude towards companies in traditional industries, such as metal rolling or oil production and refining, is completely different. At first glance, they seem conservative, but many experts call them the main architects of the new digital era.

Industrial giants began automating production processes back in the mid-30s of the last century. For many decades, hardware and software continuously improved and became more complex. Automation of production processes - for example, in oil refining - has made great progress. The operation of a modern oil refinery is monitored by hundreds of thousands of sensors and instruments, and fuel supplies are monitored in real time by satellite navigation systems. Every day, the average Russian refinery produces more than 50,000 terabytes of information. For comparison, the 3 million books stored in the digital storage of the Russian State Library occupy hundreds of times less - “only” 162 terabytes.

This is the same “big data”, or Big Data, a flow comparable to the information loading of the largest websites and social networks. The accumulated array of data represents a unique resource that can be used in business management. But traditional methods of information analysis are no longer suitable for this. Working truly effectively with such a volume of data is only possible with the help of Industry 4.0 technologies. In the context of a changing economic paradigm, rich industrial “historical experience” is a serious advantage. Big data is at the heart of artificial intelligence. Its ability to learn, understand reality and predict processes directly depends on the amount of loaded knowledge. At the same time, industrial companies have a powerful engineering school and are actively involved in introducing and improving new technologies. This is another circumstance that makes them key players in the “new economy”.

Best of the week

Finally, domestic industrialists know the price of business efficiency. Russia is a country of long distances. Often, production assets are located at a great distance from consumers. In these conditions, it is very difficult to quickly respond to market fluctuations. Traditional technologies allow saving no more than a tenth of a percent. Meanwhile, digital solutions today make it possible to reduce costs by up to 10-15% per month. The fact is obvious: in the era of the fourth industrial revolution, the one who learns to most effectively apply new technologies in the context of accumulated experience will be competitive.

Petr Kaznacheev, Director of the Center for Resource Economy, RANEPA: “As a first step towards an “integrated” artificial intelligence system in oil and gas, one could consider “smart” management and corporate planning. In this case, we could talk about creating an algorithm for digitizing all key information about the company’s activities - from the field to the gas station. This information could be sent to a single automated center. Based on this information, using artificial intelligence methods, forecasts and recommendations could be made to optimize the company’s work.”

Leader of digital transformation

Realizing this trend, industrial leaders in Russia and the world are restructuring business processes that have developed over decades, introducing Industry 4.0 technologies into production based on the industrial Internet of things, artificial intelligence and Big Data. The most intensive transformation is taking place in the oil and gas industry: the industry is dynamically “digitalizing”, investing in projects that seemed fantastic just yesterday. Factories controlled by artificial intelligence and capable of predicting situations, installations that tell the operator the optimal operating mode - all this is already becoming a reality today.

At the same time, the maximum task is to create a management system for production, logistics, production and sales that would unite “smart” wells, factories and gas stations into a single ecosystem. In an ideal digital model, the moment a consumer pulls the nozzle lever, company analysts in the operations center instantly receive information about what brand of gasoline is being filled into the tank, how much oil needs to be extracted, delivered to the plant and refined to meet demand in specific region. So far, none of the Russian and foreign companies have been able to build such a model. However, Gazprom Neft has advanced the furthest in solving this problem. Its specialists are currently implementing a number of projects, which should ultimately become the basis for creating a unified platform for managing processing, logistics and sales. A platform that no one else in the world has yet.

Digital twins

Today, Gazprom Neft refineries are among the most modern in the industry. However, the fourth industrial revolution opens up qualitatively new opportunities, while simultaneously placing new demands on automation. More precisely, we are talking not so much about automation, but about almost complete digitization of production.

The basis of the new stage will be the so-called “digital twins” - virtual copies of refinery installations. 3D models reliably describe all processes and relationships occurring in real prototypes. They are based on the work of artificial intelligence based on neural networks. The “digital twin” can suggest optimal operating modes for equipment, predict its failures, and recommend repair times. Among its other advantages is the ability to constantly learn. The neural network itself finds errors, corrects and remembers them, thereby improving its performance and forecast accuracy.

The basis for training the “digital twin” is an array of historical information. Modern oil refining plants are as complex as the human body. Hundreds of thousands of parts, tens of thousands of sensors. Technical documentation Each installation occupies a room the size of an assembly hall. To create a “digital twin”, all this information must first be uploaded to neural network. Then the most difficult stage begins - the stage of training artificial intelligence to understand the installation. It includes readings from sensors and instrumentation collected over the last few years of plant operation. The operator simulates various situations, forces the neural network to answer the question “what will happen if you change one of the operating parameters?” - for example, replacing one of the raw material components or increasing the energy supply of the installation. The neural network analyzes the experience of past years and, using a calculation method, excludes non-optimal modes from the algorithm, and learns to predict the future operation of the installation.

Best of the week

Gazprom Neft has already completely “digitized” two industrial complexes involved in the production of automobile fuel - a hydrotreating unit for catalytic cracking gasoline at the Moscow Oil Refinery and an installation operating at the company’s oil refinery in Omsk. Tests have shown that artificial intelligence is able to simultaneously take into account a huge number of parameters of their “digital twins”, make decisions and notify about possible deviations in work even before the moment when the trouble threatens to develop into a serious problem.

At the same time, Gazprom Neft is testing comprehensive solutions that will minimize the impact of the human factor on the scale of the entire production. Similar projects are currently being implemented at the company’s bitumen plants in Ryazan and Kazakhstan. Successful solutions found experimentally can subsequently be scaled up to the level of large refineries, which will ultimately create an effective digital production management platform.

Nikolay Legkodimov, Head of the Advanced Technologies Advisory Group at KPMG in Russia and the CIS:“Solutions that simulate various components, assemblies and systems have been known and used for quite a long time, including in the oil and gas industry. We can talk about a qualitative leap only when a sufficient breadth of coverage of these models has been achieved. If we manage to combine these models with each other, to combine them into a whole complex chain, then this will indeed make it possible to solve problems at a completely new level - in particular, to simulate the behavior of the system in critical, unprofitable and simply dangerous operating conditions. For those areas where re-equipment and modernization of equipment are very expensive, this will allow preliminary testing of new components.”

Performance Management

In the future, the entire added value chain in the logistics, refining and sales block of Gazprom Neft will be united by a single technological platform based on artificial intelligence. The “brain” of this organism will be the Performance Management Center, created a year ago in St. Petersburg. This is where information from “digital twins” will flow, here it will be analyzed and here, based on the data obtained, management decisions will be made.

Already today, in real time, more than 250 thousand sensors and dozens of systems transmit information to the Center from all the company’s assets included in the perimeter of the Gazprom Neft logistics, refining and sales block. Every second 180 thousand signals arrive here. It would take a person about a week just to view this information. The digital brain of the Center does this instantly: in real time it monitors the quality of products and the quantity of petroleum products along the entire chain - from the exit from the refinery to the end consumer.

The strategic goal of the Center is to radically increase the efficiency of the downstream segment, using the technologies and capabilities of Industry 4.0. That is, it’s not just about managing processes - this can be done within the framework of traditional systems, but making these processes more efficient: through predictive analytics and artificial intelligence at every stage of business, reducing losses, optimizing processes and preventing losses.

In the near future, the Center must learn to solve several key problems that affect the efficiency of business management. This includes forecasting the future 60 days in advance: how the market will behave in two months, how much oil will need to be processed to satisfy the demand for gasoline at the current moment in time, what condition the equipment will be in, whether the installations will be able to cope with the upcoming load and whether they need repairs. At the same time, in the next two years, the Center must reach 50% capacity and begin to monitor, analyze and forecast the amount of petroleum product reserves at all oil depots and fueling complexes of the company; V automatic mode monitor more than 90% of production parameters; analyze the reliability of more than 40% of process equipment and develop measures to prevent losses of petroleum products and a decrease in their quality.

By 2020, Gazprom Neft sets a goal to reach 100% of the capabilities of the Performance Management Center. Among the stated indicators are analysis of the reliability of all equipment, prevention of losses in the quality and quantity of products, and predictive management of technological deviations.

Daria Kozlova, senior consultant at VYGON Consulting:“In general, integrated solutions bring significant economic benefits to the industry. For example, according to Accenture estimates, the economic effect of digitalization could amount to more than $1 trillion. Therefore, when we are talking about large vertically integrated companies, the implementation of integrated solutions is very justified. But it is also justified for small companies, since increased efficiency can free up their additional funds by reducing costs, increasing the efficiency of working capital management, etc.”

Discuss 0

More recently, German Gref, President of Sberbank, said that in 5 years artificial intelligence will replace many people: 80% of decisions will be made by machines, and this will lead to tens of thousands of people losing their jobs.

Machine learning and artificial intelligence expert Pedro Domingos goes even further: he suggests that people will acquire a computer psychological model of their personality. What will it be like?

Sex, lies and machine learning

The digital future begins with an awareness of the fact that when you interact with a computer - be it your own smartphone or a server thousands of kilometers away - you do so on two levels every time. The first is the desire to immediately get what you need: an answer to a question, a desired product, a new credit card. At the second level, strategic and most important, you tell the computer about yourself.

The more you teach him, the better he will serve you or manipulate you.

What model of your personality do you want to present to a computer? What data can be given to him so that he can build this model? These are questions to keep in mind whenever you interact with a machine learning algorithm, just as you would when interacting with people.

Digital mirror

Think about all your data that is stored in all the computers in the world. This emails, MS Office documents, texts, tweets, Facebook and LinkedIn accounts, Internet search history, clicks, downloaded files and orders, credit history, taxes, telephone and medical records, driving information recorded in on-board computer your car, a map of movements registered by your mobile phone, every photograph you've ever taken, briefly appearing in security camera footage.

If a would-be biographer had access only to this data dump and nothing else, what picture would he or she emerge? Probably pretty accurate.

Imagine that you took all your data and gave it to the real Supreme Algorithm of the future, which already has knowledge about human life that we can teach it. It will create your model and you can carry it on a flash drive in your pocket. Of course, this will be an excellent tool for self-analysis - like looking at yourself in the mirror. But the mirror would be digital and would show not only your appearance, but also everything that can be learned by watching you. The mirror could come to life and talk.

The benefits of a digital twin

What would you like to do, what tasks to entrust to your digital half? Probably the first thing you would want from your model is to instruct her to negotiate with the world on your behalf: release her into cyberspace so that she looks for all sorts of things for you.

Of all the books in the world, she'll recommend the top ten you'll want to read first, and the advice will be so deep that Amazon never dreamed of it. The same thing will happen with movies, music, games, clothes, electronics, whatever. Of course, your refrigerator will always be full. The model will filter your email, voicemail, Facebook news, and Twitter updates, and when appropriate, respond for you.

It takes care of all the annoying little things of modern life, like checking your credit card accounts, appealing bad transactions, planning your schedule, renewing your subscriptions, and filing your taxes. She will select a medicine for you, check with your doctor and order it from the online store.

The model will tell you who you like. And after you get to know and like each other, your model will team up with your chosen one and choose restaurants that you both might like. And this is where it gets really interesting.

Model Society

In the very fast-approaching future, you will not be the only person with a “digital soulmate” who does your bidding around the clock. Everyone will have a similar personality model, and the models will communicate with each other all the time.

If you are looking for a job and company X is looking for employees, then their model will interview yours. Their “conversation” will in many ways resemble a real, “live” one - your model will be well instructed, for example, it will not give out negative information about you - but the whole process will only take a split second.

In the world of the Supreme Algorithm, “my people will contact your people” will become “my program will contact your program.” Each person will have a retinue of bots, designed to make his path around the world easier and more enjoyable. Deals, negotiations, meetings - all this will be organized before you have time to lift a finger.

Your digital soulmate will be like power steering: life will go where you want it to go, but with less effort on your part.

This does not mean that you will find yourself in a “filter bubble” and begin to see only what you are guaranteed to like, without any surprises. The digital personality will be much smarter, she will have instructions to leave room for chance, let you come into contact with new experiences, look for happy accidents.

As models improve, the interaction will become more and more similar to what would happen in the real world, but it will happen in silico and a million times faster. The cyberspace of tomorrow will turn into a very vast parallel world, which will begin to select all the most promising things to try in reality. It will be like a new, global subconscious, the collective “Id” of humanity, or “It”.

Today's world is remarkable in that theories of mind have begun to appear in computers. While these theories are still primitive, they are developing rapidly, and we will have to work with them as much as with other people to get what we want.

Based on materials from the book “The Supreme Algorithm”

Perhaps, anyone who watched the Terminator films or The Matrix wondered when artificial intelligence will become a part of our daily lives, and whether people and robots will be able to coexist in peace and harmony. This future is much closer than you think. Today we will tell you about a technology called “digital twins,” which is already widely used in industry and, perhaps, will soon become part of our everyday life.

Who are digital twins?

It is a mistake to believe that the term “digital twins” refers to robots and artificial intelligence in the guise of some kind of humanoid creature. The term itself is currently applied mostly to industrial production. The concept of “digital twins” first appeared in 2003. The term came into use after the publication of an article by Michael Greaves, professor and assistant director of the Center for Lifecycle Management and Innovation at the Florida Institute of Technology, “Digital Twins: Manufacturing Excellence Based on a Virtual Prototype Factory.” The concept itself was invented by a NASA engineer who was a colleague of the professor.

1971yes/bigstock.com

At its core, “digital twins” are a concept that combines artificial intelligence, computer learning and software with specific data to create living digital models. These “digital twins” are constantly updated as the physical prototypes change.

Where do digital twins get their data for self-updating?

The digital copy, as befits artificial intelligence, constantly learns and improves itself. To this end, the “digital twin” uses knowledge from people, other similar machines, more large systems and the environment of which it is a part.

Michael Greaves proposed his three requirements that “digital twins” must meet. The first is compliance with the appearance of the original object. You need to understand that similar appearance– this is not only the whole picture, but also the correspondence of individual parts to the real “twin”. The second requirement is related to the behavior of the double during testing. The last and most difficult thing is the information that is received from artificial intelligence about the advantages and disadvantages of a real product.

1971yes/bigstock.com

As Michael Greaves points out, when digital copies were introduced, even the criterion of superficial similarity was considered difficult to achieve. Today, as soon as digital twin identical in the first parameters, it can already be used to solve practical problems.

Why do we need digital twins?

Digital copies are created to optimize the performance of physical prototypes, entire systems and production processes.

According to Colin J. Parris, Ph.D., vice president of software research at GE Global Research Center, digital twins are a hybrid model (both physical and digital) that are created specifically for specific business purposes, e.g. predict failures, reduce maintenance costs, prevent unplanned outages.

1971yes/bigstock.com

Colin J. Parris states that when we talk about “digital twins”, this system works in three stages: seeing, thinking and doing. The “seeing” stage is about obtaining data about the situation. This information is of two types: operational data (for example, boiling point) and data from environment. Next step, which Colin J. Parris conventionally called “thinking,” is due to the fact that at this stage, the “digital twin” can provide options for various requests on how best to act in a given situation or which options are preferable for business purposes. Artificial intelligence uses for analysis, for example, historical information, revenue and expense forecasts and provides several options that are based on risks and the confidence that these proposals can reduce them. The last step - “doing” - is directly related to the implementation of what needs to be done.

1971yes/bigstock.com

With the help of “digital twins”, for example, can see from within the problem of a physical object.

In production, we no longer need to see, for example, the entire turbine in front of us in order to detect a hole. Digital twin technology will allow you to see the problem in real time using computer visualization.

According to Zvi Feuer, executive vice president of software development at Siemens, the digital twin is a PLM solution on the path to Industry 4.0.

What types of “digital twins” already exist?

As we said earlier, “digital twins” are actively used in industry: part twins (which are built for a specific production part), product twins (related to the release of a product, their main task is to reduce the cost Maintenance), process twins (their goal may be, for example, to increase service life), system twins (optimization of the entire system as a whole).

1971yes/bigstock.com

According to the high-tech research and consulting agency Gartner, hundreds of millions of “digital twins” will soon replace human labor. Some companies already use this. It is not necessary to have an employee on staff who would diagnose problems in production. In real time, with the help of “digital twins”, you can receive all the necessary data and be ready to repair equipment in advance.

What about the “digital twin” of the person himself?

chagpg/bigstock.com

For those who want to have a Terminator friend who thinks like you, helps in everything, is a brother and a friend, we have good news. According to futurist and technologist John Smith, such a future is already near. He believes that in the near future there will be so-called software agents that will predict in advance the wishes and behavior of their real copy and will perform some actions for their human counterpart.

The “Digital Twin” will be able to make purchases, make business decisions, engage in social activities - in general, will be able to do everything that we sometimes do not have enough time for.

We will also be able to transfer all the routine work to our double. In addition, according to John Smith, our digital clones will know our interests, preferences, political views and, if necessary, will be able to defend them, since they will have a more complete historical context and see the modern picture of the world as a whole. And even a feeling of compassion. For example, a “digital twin” will show affection towards us, as it will be able to guess our emotional state.

This all sounds like a utopian movie script. I feel something is wrong. What are the disadvantages of “digital twins”?

The disadvantages of digital twins are obvious. First of all, the question of our safety arises. Digital clones will use all possible resources to supplement information about us. These are algorithms that collect data from social network accounts, and our personal correspondence, and any documents and files that, in one way or another, concern us. Of course, this cannot but be alarming: as we have already found out, “digital twins” are capable of constantly updating and improving. Therefore, one of the primary tasks should be the creation of a legal framework for determining the “limits of permissibility” of artificial intelligence.

chagpg/bigstock.com

However, do not panic about this. Take John Smith as an example: he remains optimistic and believes that “digital twins” will not replace humanity. They will simply become different versions of humans who can peacefully coexist with us.

If you find an error, please highlight a piece of text and click Ctrl+Enter.

More and more enterprises are showing interest in the topic of digitalization of production. The organizers of the regional scientific and technical conference“Digitalization of production processes. Application of industrial software for building digital enterprises,” which took place recently in Samara.

It was initiated by the SMS-Automation group of companies, known as a universal integrator specializing in the creation and support of industrial automation systems, together with the Digital Manufacturing department of Siemens, one of the world's largest concerns in the field of automation and electrical products, with which Samara developers have had more than two decades of fruitful cooperation.

Forum of manufacturers and developers information systems The Ministry of Industry and Technology of the Samara Region also supported it. Its specialists have repeatedly noted the successes of the group of companies in the field of industrial automation and the construction of large information systems.

Representatives of industrial enterprises in the Samara region were introduced to the conceptual framework and specific tools for building effective digital production. Industrial automation is only part of digitalization, or digitalization, as it is also called. Digitalization is the automation of processes in everything life cycle products, equipment, enterprises. The project, its functioning, and modernization fit into it.

The report of the Chairman of the Board of Directors of the SMS-Automation Group of Companies, Andrey Sidorov, “Industrial Software as a Digitalization Tool,” aroused great interest among the conference participants. “We are on the threshold of the intellectualization of control systems,” noted Andrey Sidorov (in the bottom photo). - Now equipment manufacturers in the West are changing their production model. Equipment begins to have a digital twin. Changing business models will mean that a digital twin will be a significant factor when choosing a supplier.”

Digitalization also means testing situations on virtual digital models, which allows you to save enormous amounts of money. Siemens is already at its digitalization site, without waiting for the arrival of a machine for the production of parts, having received it virtual image, connects virtual robots to it and begins debugging technological processes without wasting time.

The topics raised by experts related to the use of specific digital production tools were received with interest by conference participants and raised many questions and discussions. In addition to the reports, the attention of conference guests was attracted by demo stands with practical examples implementation of the principles of digitalization in the reality of process control systems of industrial enterprises in Russia. Special attention at the conference was paid to the issues information security modern systems automation. Acquaintance with current trends in the development of enterprises within the framework of the Industry 4.0 concept, according to experts, can become an additional tool in the process of increasing competitiveness in the era of Industry 4.0.