Pipelines are structural elements of many systems. For example, they are used in water supply and heat supply systems, in chemical production facilities, aircraft manufacturing, and in the oil and gas industry. Accidents in piping systems result in significant economic damage. An important factor for ensuring the reliability of energy transportation systems is the assessment of real technical conditions of pipelines. Methods for assessing the state of pipeline systems by their vibro-acoustic parameters are widely used today. Traditionally, the Fourier transform is used to process vibration signals. However, as a rule, the oscillations of the pipe-liquid system are non-linear and non-stationary. This reduces the reliability of devices based on the implementation of classical methods of analysis. The authors used neural network methods for the analysis of vibro-signals, which made it possible to increase the reliability of diagnosing pipeline systems. The present work considers a method of neural network analysis of amplitude-frequency measurements in pipelines to identify the presence of a defect and further clarify its variety.

No abstract

No abstract

Abstract. In this paper discusses issues related to increasing the reliability of heat supply systems. To determine the diagnostic criteria for defects in the numerical modelling of pipeline components and determined the frequency ranges in which it is necessary to analyze the acoustic signals.

Pipelines of heat networks are an important element of heat supply to cities and industrial facilities. To increase the reliability of the operation of pipelines of heating networks, reducing the number of their accidents and increasing the economic parameters of transportation of heat energy, it is required to constantly increase the volumes and quality of complex diagnostics. The instruments currently used for the diagnosis of pipelines have many shortcomings. Among them, low reliability of detection of defects and subjectivity of decision-making, as well as lack of funds for diagnostics of pre-insulated pipelines (in polyurethane foam insulation). To simplify, accelerate and improve the reliability of monitoring the technical condition of pipelines, the authors set the goal of diagnosing the object of research using acoustic methods, using neural network technologies to process acoustic signals. The article describes experimental studies of pipelines of heating networks in polyurethane foam insulation with various sizes of defects and an analysis of the acoustic signals obtained at the same time is made. The frequency of natural oscillations of the pipeline is chosen as the determining parameter of the acoustic signal. To process and analyze the frequencies obtained as a result of the experiments, a neural network of back propagation of the error was constructed.The results of the classification of the neural network of back propagation of the error trained by the neural network showed its good ability to analyze unknown samples and a high degree of reliability of their recognition.