Fault Diagnosis of Subway Sliding Plug Door Based on Machine Learning and Motor Current Signal

Huang, Jiaman; Guo, S.Y.; Jiang, Jierui; Shi, Fanghui; Liu, Wenxiu; Liu, Dong

doi:10.1109/ddcls55054.2022.9858351

Cited by 2 publications

(3 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Volume 26 (2024), Issue 2 operators. In our team's previous research, we first proposed using motor currents to detect the subway sliding plug door faults, studied three faults and extracted 24 features with a classification accuracy of 93.6% [19]. To detect more fault types and improve the classification accuracy, we proposed the adaptive empirical mode decomposition and recursive feature elimination based on the cross-validation (AEMD-RFECV) method to diagnose 12 sliding plug door faults with 98.96% accuracy [36].…”

Section: Eksploatacja I Niezawodnosc -Maintenance and Reliabilitymentioning

confidence: 99%

Reliability analysis of subway sliding plug doors based on improved FMECA and Weibull distribution

Wang,

Liu,

Fang

et al. 2024

Eksploatacja i Niezawodność – Maintenance and Reliability

View full text Add to dashboard Cite

Using traditional FMECA to analyze the hazard of subway sliding plug door system, there are problems such as easy-to-take repetitive values, irrational allocation of expert's weights, and failure to consider the weights of evaluation factors. Hence, this paper proposes to improve FMECA by using linear interpolation to increase the differentiation of the same fault probability occurrence among various fault modes. Apply the DUOWA to dynamically assign weights to different experts. The AHP is used to endow weights to diverse evaluation factors to make them more suitable for engineering needs. The operation records of metro trains were collected from the Shanghai subway manufacturing plant for 1836 days. The hazards of the 17 common faults of the door were first analyzed using an improved FMECA,the EDCU is the component most prone to failure. Next, use a RCM strategy to determine maintenance periods for different faults. Finally, through the Weibull distribution fitting test, the fault rate function of the door is obtained, and the RUL of the door is predicted.

show abstract

Section: Eksploatacja I Niezawodnosc -Maintenance and Reliabilitymentioning

confidence: 99%

Reliability analysis of subway sliding plug doors based on improved FMECA and Weibull distribution

Wang,

Liu,

Fang

et al. 2024

Eksploatacja i Niezawodność – Maintenance and Reliability

View full text Add to dashboard Cite

show abstract

“…Meanwhile, generate fluctuating torque and causes changes in motor current, supporting the maintenance of the subway sliding plug door. In the previous study, our team proposed a health fault diagnosis model for subway sliding plug door based on random forest model [26]. In addition, we also presented an Isomap and grey wolf pack optimized SVM [27], with a fault recognition rate of 92.77%.…”

Section: Introductionmentioning

confidence: 99%

“…Cao et al diagnosed nine faults by analyzing sound signals in subway sliding plug doors, extracting eight features with a classification accuracy of 97.87% [36]. Our research team first proposed using motor currents to detect the subway sliding plug door faults, but previous work only studied three faults, extracting 24 features with a classification accuracy of 93.6% [26]. To detect more fault types and improve the classification accuracy, we proposed the adaptive empirical mode decomposition and recursive feature elimination based on cross-validation (AEMD-RFECV) method to diagnose 12 sliding plug door faults with 98.96% accuracy.…”

Section: Introductionmentioning

confidence: 99%

Fault detection system of subway sliding plug door based on adaptive EMD method

Wang,

Liu,

Lin

et al. 2023

Meas. Sci. Technol.

View full text Add to dashboard Cite

With the rapid development of urban rail transit, the safety of subway sliding plug door has become a great concern. To improve the operational reliability of the sliding plug door, we designed a fault detection system based on the adaptive empirical mode decomposition (AEMD). Firstly, to address the impact of noise on signal analysis, the AEMD denoising method is proposed. Intrinsic mode functions (IMFs) are obtained. Then appropriate IMF components are selected for reconstruction according to the adaptive threshold of Hausdorff distance to achieve a better denoising effect. Secondly, this paper uses feature selection methods and machine learning techniques to classify the 12 fault types of the subway sliding plug door. Our proposed method is implemented with a hardware acquisition device and analysis software. The experimental results show that the identification accuracy reaches 98.96% on the practical platform. Practical tests, ablation studies using AEMD, and comparison results prove the effectiveness and robustness of the proposed method.

show abstract

Fault Diagnosis of Subway Sliding Plug Door Based on Machine Learning and Motor Current Signal

Cited by 2 publications

References 2 publications

Reliability analysis of subway sliding plug doors based on improved FMECA and Weibull distribution

Reliability analysis of subway sliding plug doors based on improved FMECA and Weibull distribution

Fault detection system of subway sliding plug door based on adaptive EMD method

Contact Info

Product

Resources

About