Software implemented fault diagnosis of natural gas pumping unit based on feedforward neural network

Mykola Kozlenko,Olena Zamikhovska,Leonid Zamikhovskyi

doi:10.15587/1729-4061.2021.229859

Abstract

In recent years, more and more attention has been paid to the use of artificial neural networks (ANN) for the diagnostics of gas pumping units (GPU). Usually, ANN training is carried out on GPU workflow models, and generated sets of diagnostic data are used to simulate defect conditions. At the same time, the results obtained do not allow assessing the real state of the GPU. It is proposed to use the characteristics of the acoustic and vibration processes of the GPU as the input data of the ANN. A descriptive statistical analysis of real vibration and acoustic processes generated by the operation of the GPU type GTK-25-i (Nuovo Pignone, Italy) was carried out. The formation of batches of diagnostic features arriving at the input of the ANN was carried out. Diagnostic features are the five maximum amplitude components of the acoustic and vibration signals, as well as the value of the standard deviation for each sample. Diagnostic features are calculated directly in the ANN input data pipeline in real time for three technical states of the GPU. Using the frameworks TensorFlow, Keras, NumPy, pandas, in the Python 3 programming language, an architecture was developed for a deep fully connected feedforward ANN, trained on the backpropagation algorithm. The results of training and testing the developed ANN are presented. During testing, it was found that the signal classification precision for the “nominal” state of all 1,475 signal samples is 1.0000, for the “current” state, precision equals 0.9853, and for the “defective” state, precision is 0.9091. The use of the developed ANN makes it possible to classify the technical states of the GPU with an accuracy sufficient for practical use, which will prevent the occurrence of GPU failures. ANN can be used to diagnose GPU of any type and power

Highlights

Long-term operation of the gas transmission system (GTS) of Ukraine has led to the fact that most of the gas-pumping units (GPU) have reached the end of their service life or are close to it
There are practically no references to the use of experimental data, with the exception of [7, 10], for training the proposed neural networks regarding the diagnosis of modular units or elements of gas turbine unit (GTU), gas turbine engine (GTE) and jet engine (JE)
There is a need to analyze the possibility of using recurrent architectures, in particular, with a long short-term memory (LSTM), which may be the subject of further research

Summary

Introduction

Long-term operation of the gas transmission system (GTS) of Ukraine (about 40 years) has led to the fact that most of the gas-pumping units (GPU) have reached the end of their service life or are close to it In this regard, there are numerous GPU failures both in their modular units and elements (in the mechanical part), and in the automatic control systems (ACS). The transfer of the obtained diagnostic results to the ACS will allow the control of the GPU operation according to the actual state This will improve the reliability of their operation and the efficiency of the gas compression process

Literature review and problem statement

The aim and objectives of the study

Findings

Conclusions