The article discusses modern approaches to the design and implementation of data processing architectures in intelligent transport systems (ITS) with a focus on ensuring technological sovereignty. Special attention is paid to the integration of machine learning practices to automate the full lifecycle of machine learning models: from data preparation and streaming to real-time monitoring and updating of models. Architectural solutions using distributed computing platforms such as Hadoop and Apache Spark, in-memory databases on Apache Ignite, as well as Kafka messaging brokers to ensure reliable transmission of events are analyzed. The importance of infrastructure flexibility and scalability, support for parallel operation of multiple models, and reliable access control, including security issues, and the use of transport layer security protocols, is emphasized. Recommendations are given on the organization of a logging and monitoring system for rapid response to changes and incidents. The presented solutions are focused on ensuring high fault tolerance, safety and compliance with the requirements of industrial operation, which allows for efficient processing of large volumes of transport data and adaptation of ITS systems to import-independent conditions.

Keywords: data processing, intelligent transport systems, distributed processing, scalability, fault tolerance

Overview of existing methods for diagnosing faults in synchronous electric motors and methods for their detection. Classification and analysis of existing methods, their applicability in detecting faults, advantages and disadvantages. Three classes of possible faults in synchronous permanent magnet motors are considered and described: electrical faults, mechanical faults, and demagnetization. The article discusses three classes of diagnostic methods: based on the construction of a mathematical model of a real electric motor and modeling its errors, based on processing signals from sensors, and intelligent methods based on processing collected data using artificial intelligence. The following error detection methods based on modeling are considered: detection based on the model of the electrical schematic, based on the analytical model, and based on the digital simulation model. The following frequency-time analysis methods of the obtained signals from the sensors are considered: analysis using fast Fourier transform, short-time Fourier transform, wavelet transform, Hilbert-Huang transform, and Wigner-Ville distribution. The following intelligent diagnostic methods are considered: diagnosis using convolutional neural networks, recurrent neural networks, support vector machines, fuzzy logic, and sparse representation.

Keywords: Synchronous motor with permanent magnets, faults of electric motor, modeling, fast Fourier transform, wavelet transform, Hilbert-Huang transform, Wigner-Ville distribution, neural networks, fuzzy logic, support vector machine, sparse representation.

In this work, we studied the effect of fog on machine vision systems, in particular, on the correctness of the pattern recognition algorithm. As part of this work, a filter is implemented that eliminates distortions caused by fog. A corrective filter has been developed, an analysis of the operation of a neural network with images of various definitions has been carried out, on the basis of which recommendations have been made to improve the accuracy of pattern recognition.

Keywords: image processing, image filtering, machine vision systems, pattern recognition