Current-Signal-Based Fault Diagnosis of Railway Point Machines Using Machine Learning
The majority of railway operators still implement conventional maintenance for railway point machines (RPMs), which is one of the most vital pieces of equipment for ensuring the safety of train operation. The conventional maintenance method lacks accuracy, is less efficient, and has high labor costs...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-12-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/14/1/267 |
| _version_ | 1827384921790873600 |
|---|---|
| author | Ahmad Sugiana Willy Anugrah Cahyadi Yasser Yusran |
| author_facet | Ahmad Sugiana Willy Anugrah Cahyadi Yasser Yusran |
| author_sort | Ahmad Sugiana |
| collection | DOAJ |
| description | The majority of railway operators still implement conventional maintenance for railway point machines (RPMs), which is one of the most vital pieces of equipment for ensuring the safety of train operation. The conventional maintenance method lacks accuracy, is less efficient, and has high labor costs. This study developed a cost-effective and accurate fault diagnosis (FD) method based on current data to increase the overall efficiency of RPM maintenance. The FD method for RPM equipment discussed in this paper consists of three working conditions: normal, working, and failure. The method was proposed based on time-series current signals, which were gathered when the RPM was in operation. Time-series data were extracted and filtered using time-domain feature extraction based on scalable hypothesis testing. The selected features became the datasets for machine learning modeling. Six machine learning algorithms were compared in order to find the algorithm with the best FD accuracy. The results showed 100% accuracy for the Decision Tree and Random Forest algorithms in the FD method. The results of the FD method could be important for maintenance teams in determining suitable maintenance activities based on RPM working conditions. |
| first_indexed | 2024-03-08T15:11:37Z |
| format | Article |
| id | doaj.art-61d6a911c4fd48da8e44bfe91d1fb998 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-08T15:11:37Z |
| publishDate | 2023-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-61d6a911c4fd48da8e44bfe91d1fb9982024-01-10T14:51:32ZengMDPI AGApplied Sciences2076-34172023-12-0114126710.3390/app14010267Current-Signal-Based Fault Diagnosis of Railway Point Machines Using Machine LearningAhmad Sugiana0Willy Anugrah Cahyadi1Yasser Yusran2School of Electrical Engineering, Telkom University, Jl. Telekomunikasi Terusan Buah Batu, Bandung 40257, IndonesiaSchool of Electrical Engineering, Telkom University, Jl. Telekomunikasi Terusan Buah Batu, Bandung 40257, IndonesiaSchool of Electrical Engineering, Telkom University, Jl. Telekomunikasi Terusan Buah Batu, Bandung 40257, IndonesiaThe majority of railway operators still implement conventional maintenance for railway point machines (RPMs), which is one of the most vital pieces of equipment for ensuring the safety of train operation. The conventional maintenance method lacks accuracy, is less efficient, and has high labor costs. This study developed a cost-effective and accurate fault diagnosis (FD) method based on current data to increase the overall efficiency of RPM maintenance. The FD method for RPM equipment discussed in this paper consists of three working conditions: normal, working, and failure. The method was proposed based on time-series current signals, which were gathered when the RPM was in operation. Time-series data were extracted and filtered using time-domain feature extraction based on scalable hypothesis testing. The selected features became the datasets for machine learning modeling. Six machine learning algorithms were compared in order to find the algorithm with the best FD accuracy. The results showed 100% accuracy for the Decision Tree and Random Forest algorithms in the FD method. The results of the FD method could be important for maintenance teams in determining suitable maintenance activities based on RPM working conditions.https://www.mdpi.com/2076-3417/14/1/267railway point machinefault diagnosismachine learningpredictive maintenance |
| spellingShingle | Ahmad Sugiana Willy Anugrah Cahyadi Yasser Yusran Current-Signal-Based Fault Diagnosis of Railway Point Machines Using Machine Learning Applied Sciences railway point machine fault diagnosis machine learning predictive maintenance |
| title | Current-Signal-Based Fault Diagnosis of Railway Point Machines Using Machine Learning |
| title_full | Current-Signal-Based Fault Diagnosis of Railway Point Machines Using Machine Learning |
| title_fullStr | Current-Signal-Based Fault Diagnosis of Railway Point Machines Using Machine Learning |
| title_full_unstemmed | Current-Signal-Based Fault Diagnosis of Railway Point Machines Using Machine Learning |
| title_short | Current-Signal-Based Fault Diagnosis of Railway Point Machines Using Machine Learning |
| title_sort | current signal based fault diagnosis of railway point machines using machine learning |
| topic | railway point machine fault diagnosis machine learning predictive maintenance |
| url | https://www.mdpi.com/2076-3417/14/1/267 |
| work_keys_str_mv | AT ahmadsugiana currentsignalbasedfaultdiagnosisofrailwaypointmachinesusingmachinelearning AT willyanugrahcahyadi currentsignalbasedfaultdiagnosisofrailwaypointmachinesusingmachinelearning AT yasseryusran currentsignalbasedfaultdiagnosisofrailwaypointmachinesusingmachinelearning |