International Scientific Journals
of Scientific Technical Union of Mechanical Engineering "Industry 4.0"

Approaches to machine and equipment maintenance based on data analytics and artificial intelligence are trending in modern manufacturing. These methods are used to predict the remaining useful life (RUL) of equipment and thus enable forward maintenance planning. However, for predictive maintenance systems, it is also necessary to detect anomalies in operation and classify the occurring errors. Classical approaches of supervised machine learning are often in this case unusable because those methods require a large amount of run-to-failure data (R2F), which is often not possible to collect due to the undesirable character of failure states in the manufacturing process. The paper presents and tests several methods of detecting device fault states using an autoencoder network, which offers a beneficial solution in the case of the unavailability of R2F data in the system.

Artificial intelligence become more widespread in all manufacturing subjects. In manufacturing artificial intelligence deals with such tasks as quality control, robot navigation, computer vision, processes controlling, etc. The area of maintenance in machining is a great prospect for implementing artificial intelligence tools for analysis, prediction of monitored parameters, optimization, and improvement of the quality of the maintenance process. In particular, the article refers to predictive maintenance as a modern trend in mechanical engineering. In this article, a quick review of using methods of artificial intelligence and predictive analytics in maintenance and one p ractical implementation case of NAR network for time-series prediction was provided.

This article describes the actual trends and applications in industry where artificial intelligence models are deployed. This paper provides a more detailed description of the principles and methods of deploying models in the field of quality evaluation in industry and also in the areas of predictive maintenance and data analytics in the manufacturing process. Computer vision is increasingly coming to the fore due to its wide range of applications – object detection, categorisation of objects, reading QR codes and others. The area of predictive maintenance is important in terms of reducing downtime and saving costs for machine components. Models designed for data analytics, in turn, help to optimize the parameters of the production process so that the desired parameter is maximized or its optimal value is achieved.