Application of Maximum Generalized Rayleigh Entropy in Diagnosing Train Air-conditioning Refrigerant Charge
Journal Title: Urban Mass Transit - Year 2024, Vol 27, Issue 10
Abstract
Objective In diagnosing train air-conditioning refrigerant charge using machine learning methods, numerous features often appear, posing a dilemma in feature selection for diagnosis. Excessive feature selection leads to high algorithm resource costs, while insufficient feature selection results in poor learning of fault information, negatively affecting the diagnostic model performance. Currently, a commonly used method for feature selection is PCA (principal component analysis), and another less frequently cited method is MRE (Maximum Rayleigh Entropy). Both methods, however, face the problem of high resource costs due to excessive features. The research is specially carried out aiming to reduce resource costs and the effectiveness of these two methods is compared. Method For this purpose, the typical SVM (support vector machine) and K-means clustering model are selected for comparison, and a small sample of historical data is used to construct dimensionality reduction algorithm, instead of using the entire sample to construct MRE dimensionality reduction algorithm, representing an improvement to the algorithm under the same goal of reducing resource costs. MRE dimensionality reduction based on small historical data sample and the commonly used PCA dimensionality reduction are compared in terms of their performance on F1 score, accuracy rate, and time cost in K-means clustering and SVM models. Result & Conclusion The results indicate that the fault diagnosis and detection time resource costs of SVM machine using MRE is only 3% that of SVM model trained on original data. Whether using K-means clustering or SVM, the test data accuracy rate after using the projected data from MRE is closer to 100% compared to other models.
Authors and Affiliations
Mengyuan ZHANG, Zhao WANG, Chao BAO, Huanxin CHEN, Jianxin ZHANG, Henda CHENG
Keywords
Related Articles
- EP ID EP749248
- DOI 10.16037/j.1007-869x.2024.10.045
- Views 97
- Downloads 0
Detection Method for Rail Bottom Cracks Based on Frequency Response Function Curvature Differential Correlation Analysis
［Objective］ Detection methods based on vibration characteristics are widely applied for structural damage monitoring in urban rail transit systems. However, in practical applications, it is challenging to obtain the mo...
Comprehensive Evaluation Method and Practice of Equipment Health Grade on Signaling System Service Life Prolonging Requirements
Objective Evaluation methods for conventional equipment health grade tend to be one-sided and limited in scope. There is a need to develop an evaluation method tailored to the stringent safety demands of signaling system...
Research on Shanghai Rail Transit Signaling System Evolution Scheme
Objective With the rapid development of urban rail transit, the operational volume of trains has significantly increased. The existing CBTC (communication-based train control) system can no longer meet the signaling syst...
Spatial Function Optimization of Transfer Station with Different Waiting and Security Check Modes under Integrated Operation of Intercity Railway and Metro
Objective There exist some differences between intercity railway stations and metro stations in operational management rules and mechanisms. In order to achieve smooth transfer, function integration, advanced application...
Design of Fully Automated Depot Train Inspection Operation Management System Architecture Based on Digital Twin
[Objective] Digital twin technology is the booster for many industries to embark on the path of intelligence, information, and digitalization. To promote the digital development of urban rail transit vehicle bases, a ful...