Method and Algorithm of Enrichment of High-Frequency Multidimensional Signals on the Example of Diagnosing the Technical Condition of Centrifugal Pump and Rolling Bearings

This paper is devoted to methods and algorithms of enriching high-frequency multidimensional signals, which are a key aspect of data analysis in the field of equipment condition diagnostics, where high sensitivity to changes in signals is required. High-frequency signals are characterised by fast changes in time and may contain a large amount of information, requiring special processing techniques to extract meaningful patterns. In this paper, we consider various approaches to enrichment of high-frequency multidimensional signals used in modern methods of diagnosing the technical condition of rotating mechanisms on the basis of machine learning algorithms and deep neural networks. In particular, this concerns the diagnosing of the technical condition of centrifugal pumps and rolling bearings. In our research, we propose new method and algorithm for enrichment of high-frequency multidimensional signals on the example of diagnosing the technical condition of a centrifugal pump and rolling bearings using machine learning algorithms. The suggested method and algorithm have a wide range of applications: from real-time signal processing to the analysis of high-frequency time series. The development of new approaches to the enrichment of high-frequency multidimensional signals is an important task that opens new prospects for research in data analysis and decision-making based on high-frequency data.