PNIPU: EnergyDesc Complex for the development of digital twins of complex technical systems

The main stories are:

• CAD Computer-aided design systems
• Neural networks (neural networks)
• Digital Twin of Organization (DTO)

2022: EnergyDesc Submission

The program for the digital cloning of complex technological systems was developed at the Perm Polytechnic, which announced this on August 8, 2022.

As you know, the digitalization of production provides an increase in the capacity of the enterprise, provides high flexibility in the formation of business models and helps to reach potential customers. Young scientists of the Perm Polytechnic University have developed a software complex for the development of digital twins of complex technical systems called "EnergyDesc." The technology will significantly increase the efficiency of enterprises as a whole.

The complex is designed for the development of a gas turbine power plant, a gas transmission system or any other complex technological system not in the form of mathematical formulas, but in the form of a neural network model. The main idea is to increase the capabilities of specialists by combining different stages of the development of digital twins of complex technical systems into one software complex, "said Grigory Kilin, project manager, senior lecturer at the Department of Electrical Engineering and Electromechanics.

The key factor in the development of the EnergyDesc software complex is, first of all, the interest of industrial enterprises and the state in the transition of industry to advanced digital intelligent production technologies. This interest is formulated in the "Strategy for Scientific and Technological Development of the Russian Federation."

Usually, when developing a digital twin, many specialists are required, each of whom works in his own software and thinks about solving a specific part of the problem. The EnergyDesc complex differs from existing analogues in that all the possibilities for creating a digital copy of complex technological objects are achieved thanks to the use of algorithms artificial intelligence neural network technologies, combining different stages of model construction into one software complex integration and with already purchased software, - said one of the developers, assistant of the Department of Electrical Engineering and Electromechanics Artem Suslov.

According to young scientists, at the beginning of August 2022, the functionality of the system is enough for implementation at enterprises in a pilot format. However, the product will be refined in accordance with the individual requirements of the enterprise.