Application of Reinforcement Learning Algorithm Model in Gas Path Fault Intelligent Diagnosis of Gas Turbine

Gas turbine is widely used because of its advantages of fast start and stop, no pollution, and high thermal efficiency. However, the working environment of high temperature, high pressure, and high speed makes the gas turbine prone to failure. The traditional gas path fault intelligent diagnosis scheme of the gas turbine has the problems of poor control effect and low scheduling accuracy. Experiment studies the application of neural network and reinforcement learning algorithm in gas path fault intelligent diagnosis of the gas turbine. The accurate control of fault diagnosis planning is realized from gas path fault diagnosis, daily maintenance, service condition monitoring, power utilization rate, and other aspects of the gas turbine. The reinforcement learning model can realize the intelligent diagnosis and record of gas path fault of the gas turbine, to achieve diversified analysis and intelligent diagnosis scheme. Through neural network algorithm and deep learning technology, the whole process monitoring of the gas turbine is realized, and the failure rate of the gas turbine in the working process is reduced. The experimental results show that, compared with the thermal fault diagnosis method and the fault diagnosis method of the electric percussion drill, using thermal imaging, the gas turbine gas path fault intelligent diagnosis model based on the reinforcement learning algorithm can complete the data information in the process of real-time data transmission. The quantified conversion and processing of the system has the advantages of higher control accuracy and faster response speed, which can effectively improve the diagnostic efficiency and accuracy.

A Novel Gas Path Fault Diagnostic Model for Gas Turbine Based on Explainable Convolutional Neural Network With LIME Method

Gas turbine is widely used in aviation and energy industries. Gas path fault diagnosis is an important task for gas turbine operation and maintenance. With the development of information technology, especially deep learning methods, data-driven approaches for gas path diagnosis are developing rapidly in recent years. However, the mechanism of most data-driven models are difficult to explain, resulting in lacking of the credibility of the data-driven methods. In this paper, a novel explainable data-driven model for gas path fault diagnosis based on Convolutional Neural Network (CNN) using Local Interpretable Model-agnostic Explanations (LIME) method is proposed. The input matrix of CNN model is established by considering the mechanism information of gas turbine fault modes and their effects. The relationship between the measurement parameters and fault modes are considered to arrange the relative position in the input matrix. The key parameters which contributes to fault recognition can be achieved by LIME method, and the mechanism information is used to verify the fault diagnostic proceeding and improve the measurement sensor matrix arrangement. A double shaft gas turbine model is used to generate healthy and fault data including 12 typical faults to test the model. The accuracy and interpretability between the CNN diagnosis model built with prior mechanism knowledge and built by parameter correlation matrix are compared, whose accuracy are 96.34% and 89.46% respectively. The result indicates that CNN diagnosis model built with prior mechanism knowledge shows better accuracy and interpretability. This method can express the relevance of the failure mode and its high-correlation measurement parameters in the model, which can greatly improve the interpretability and application value.

Aero Engine Gas-Path Fault Diagnose Based on Multimodal Deep Neural Networks

Aeroengine, served by gas turbine, is a highly sophisticated system. It is a hard task to analyze the location and cause of gas-path faults by computational-fluid-dynamics software or thermodynamic functions. Thus, artificial intelligence technologies rather than traditional thermodynamics methods are widely used to tackle this problem. Among them, methods based on neural networks, such as CNN and BPNN, cannot only obtain high classification accuracy but also favorably adapt to aeroengine data of various specifications. CNN has superior ability to extract and learn the attributes hiding in properties, whereas BPNN can keep eyesight on fitting the real distribution of original sample data. Inspired by them, this paper proposes a multimodal method that integrates the classification ability of these two excellent models, so that complementary information can be identified to improve the accuracy of diagnosis results. Experiments on several UCR time series datasets and aeroengine fault datasets show that the proposed model has more promising and robust performance compared to the typical and the state-of-the-art methods.