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

2021-04-30

Eastern-European Journal of Enterprise Technologies

AI Summary

Natural gas pumping units (GPUs) suffer from challenges in real-time condition assessment and delayed fault预警. Method: This paper proposes an online intelligent diagnostic method leveraging field-measured acoustic and vibration signals—specifically, five amplitude components and their standard deviations—as direct inputs to a feedforward neural network, eliminating reliance on simulated data for training. A fully connected neural network is implemented using TensorFlow/Keras, integrated with a real-time feature engineering pipeline to enable end-to-end classification of three technical states: normal, incipient fault, and failure. Contribution/Results: The approach significantly enhances model generalizability across GPU types and power ratings. Experimental evaluation yields test accuracies of 1.0000 (normal), 0.9853 (incipient fault), and 0.9091 (failure), collectively satisfying industrial-grade reliability requirements.

Technology Category

• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning
• Intelligent Robots: State Estimation
• Machine Learning: Matrix & Tensor Methods

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

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

Problem

• Develop fault diagnosis for natural gas pumping units
• Use ANN to classify GPU technical states accurately
• Prevent GPU failures using real-time signal analysis

Innovation

• Feedforward neural network for GPU diagnosis
• Acoustic and vibration data as ANN inputs
• Real-time diagnostic feature calculation