S.S. Antsyferov1, K. N. Fazilova2, K. E. Rusanov3

1–3 MIREA – Russian Technological University (Moscow, Russia)
1,3 c_standard@fel.mirea.ru, 2 fazilova@mirea.ru

Currently, the most progressive and flexible production systems include the so-called "Smart Production", "Smart Factory", "Production 4.0", "Intelligent Production". Intelligent production systems involve the integration into a single communication network of all operations within the enterprise by stages of production and use monitoring methods and tools to control quality and obtain the information flow of data necessary to adapt to new requirements.

The immediate prospect is the creation of intelligent machine-building industries, functioning exclusively under the control of artificial intelligence. Intelligent machine-building production is basically a set of interconnected technological processes and robot machines connected to a network for effective functioning and generation of information necessary for analytics. Technological processes are subject to high requirements for the accuracy of manufactured products, as well as for ultra-high accuracy in the field of nanotechnology, which can be achieved through the extensive use of accumulated knowledge, their replenishment and effective use. In accordance with this, each technological process (technological operation) must contain a local knowledge system, means of accumulating and processing information, decision-making, as well as interface means of input-output and exchange with other processes (operations). An important aspect is timely access and processing of information about the state of the technological process, monitoring the quality level of the process for rapid, if necessary, updating and operational reorientation, taking into account possible intensive increments of knowledge. In turn, the quality of the technological process is largely determined by the accuracy of the technological operations combined into a single technological process.

In this regard, it seems relevant to develop a methodology for quality control of technological processes, taking into account the accuracy of technological operations, replenishment of knowledge and their use.

An algorithm for probabilistic evaluation of the accuracy of technological operations has been developed. As a mathematical model of the dynamics of the quality of technological processes of intelligent machine-building production, a nonlinear differential equation is proposed that allows tracking trends in the quality of the process depending on the accuracy of technological operations, the increment of knowledge and their use. A quality control methodology has been developed based on the comparison of the real quality indicator with the established boundary values of the quality area. The methodology includes an algorithm for constructing the boundary values of the quality area and an algorithm for evaluating the real quality indicator.

Practical testing of the developed methodology has shown that it can be used to solve a number of practical problems related to quality control of technological processes of intelligent machine-building production.

Antsyferov S.S., Fazilova K.N., Rusanov K.E. Methods of quality control of technological processes of intelligent machine-building production. Science Intensive Technologies. 2023. V. 24. № 7. P. 39−43. DOI: https://doi.org/10.18127/ j19998465-202307-05 (in Russian)

1. Ancyferov S.S., Sigov A.S. Tekhnologicheskie osnovy postroeniya intellektual'nyh sistem. Problemy iskusstvennogo intellekta. 2016. № 1 (2). S. 34–44 (in Russian).
2. Ancyferov S.S., Fazilova K.N., Rusanov K.E. Standartizaciya pokazatelej neravnovesnoj ustojchivosti kognitivnyh sistem. Naukoemkie tekhnologii. 2017. T. 18. № 5. S. 15–20 (in Russian).
3. Antsyferov S.S., Fazilova K.N., Rusanov K.E. Evaluation algorithm of cognitive systems non-equilibrium stability. Problems of Artificial Intelligence. 2018. № 3 (10). P. 57–64.
4. Antsyferov S.S., Fazilova K.N. Evaluation of cognitive systems structural elements effectiveness. Problems of Artificial Intelligence. 2019. № 3 (14). P. 40–46.
5. Antsyferov S.S., Fazilova K.N., Rusanov K.E. Method for controlling the cognitive systems functioning in non-equilibrium stability mode. Journal of Physics: Conference Series. 2020. V. 1679. P. 032068.
6. Ancyferov S.S., Fazilova K.N., Rusanov K.E. Metodika ocenki effektivnosti strukturnyh elementov kognitivnyh sistem v real'nom masshtabe vremeni. Nelinejnyj mir. 2020. № 3. S. 33–41 (in Russian).
7. Ancyferov S.S., Fazilova K.N. Metodologiya ocenki sostoyanij kognitivnyh sistem. Problemy iskusstvennogo intellekta. 2020. №3(18). S. 19–28 (in Russian).
8. Ancyferov S.S., Sigov A.S., Fazilova K.N. Metodologiya kontrolya funkcionirovaniya neravnovesno-ustojchivyh tekhnicheskih sistem. Problemy iskusstvennogo intellekta. 2021. № 1 (20). S. 18–26 (in Russian).
9. Antsyferov S.S., Fazilova K.N., Rusanov K.E. Algorithms for monitoring the functioning of nonequilibrium information processing systems. Journal of Physics: Conference Series. 2021. V. 2094. P. 022024.
10. Antsyferov S.S., Fazilova K.N., Rusanov K.E. Modeling of control processes of nonequilibrium systems functioning. AIP Conference Proceedings. 2021. V. 2402. P. 050006.
11. Ancyferov S.S., Fazilova K.N. Kontrol' kachestva funkcionirovaniya intellektual'nyh proizvodstv. Kachestvo i zhizn'. 2022. T. 34. № 2. S. 11–13 (in Russian).