A multi-task model for failure identification and GPS assessment in metro trains
Air and oil leaks are two of the predominant operational failures in metro trains, which can cause severe issues and a lot of downtime. Predictive maintenance on such machinery can be of great use. This work aimed to develop a deep learning algorithm for fault analysis in metro trains. The MetroPT d...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
AIMS Press
2024-11-01
|
| Series: | AIMS Environmental Science |
| Subjects: | |
| Online Access: | https://www.aimspress.com/article/doi/10.3934/environsci.2024048 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832590251389878272 |
|---|---|
| author | Pratik Vinayak Jadhav Sairam V. A Siddharth Sonkavade Shivali Amit Wagle Preksha Pareek Ketan Kotecha Tanupriya Choudhury |
| author_facet | Pratik Vinayak Jadhav Sairam V. A Siddharth Sonkavade Shivali Amit Wagle Preksha Pareek Ketan Kotecha Tanupriya Choudhury |
| author_sort | Pratik Vinayak Jadhav |
| collection | DOAJ |
| description | Air and oil leaks are two of the predominant operational failures in metro trains, which can cause severe issues and a lot of downtime. Predictive maintenance on such machinery can be of great use. This work aimed to develop a deep learning algorithm for fault analysis in metro trains. The MetroPT dataset was used for this work. A multi-task artificial neural network was developed for the simultaneous identification of failures and GPS quality assessment. The network had common dense, batch normalization, and Gaussian noise layers, followed by output sigmoid layers for each output. The algorithm was trained for 20 epochs with a batch size of 5000 using the using Adam optimizer. The local interpretable model agnostic explanations (LIME) technique was used to provide explanations for the model predictions. Finally, a dashboard was developed for the same application consisting of the best-trained algorithm for decision-making, along with trend visualizations and explanations. The developed multi-task model produced 98.89$ \% $, 99.12$ \% $, and 99.24$ \% $ accuracies in the testing set for failure type, failure location, and GPS quality predictions, respectively. The model produced 99.56$ \% $, 99.67$ \% $, and 99.84$ \% $ precision in the testing set for failure type, failure location, and GPS quality predictions, respectively. The loss values for the trained model on the testing set were 0.0035, 0.0026, and 0.0033 for the three tasks, respectively. The deep learning model took 43 seconds for training and 1 second for inferencing for test data. The LIME technique produced explanations for each predictive task with feature importance in positive and negative impacts. On the whole, the proposed framework can be effective for fast and accurate fault analysis in metro trains. |
| format | Article |
| id | doaj-art-4ec7e00ef6c94cb39cf174b7af6174f4 |
| institution | Kabale University |
| issn | 2372-0352 |
| language | English |
| publishDate | 2024-11-01 |
| publisher | AIMS Press |
| record_format | Article |
| series | AIMS Environmental Science |
| spelling | doaj-art-4ec7e00ef6c94cb39cf174b7af6174f42025-01-24T01:31:33ZengAIMS PressAIMS Environmental Science2372-03522024-11-0111696098610.3934/environsci.2024048A multi-task model for failure identification and GPS assessment in metro trainsPratik Vinayak Jadhav0Sairam V. A1Siddharth Sonkavade2Shivali Amit Wagle3Preksha Pareek4Ketan Kotecha5Tanupriya Choudhury6Symbiosis Institute of Technology (Pune Campus), Symbiosis International Deemed University, Pune 411215, IndiaSymbiosis Institute of Technology (Pune Campus), Symbiosis International Deemed University, Pune 411215, IndiaSymbiosis Institute of Technology (Pune Campus), Symbiosis International Deemed University, Pune 411215, IndiaSymbiosis Institute of Technology (Pune Campus), Symbiosis International Deemed University, Pune 411215, IndiaComputer Engineering Department, Thakur College of Engineering and Technology, Mumbai 400101,IndiaSymbiosis Centre for Applied Artificial Intelligence, Symbiosis Institute of Technology, Symbiosis International Deemed University, Pune 412115, IndiaSymbiosis Institute of Technology (Pune Campus), Symbiosis International Deemed University, Pune 411215, IndiaAir and oil leaks are two of the predominant operational failures in metro trains, which can cause severe issues and a lot of downtime. Predictive maintenance on such machinery can be of great use. This work aimed to develop a deep learning algorithm for fault analysis in metro trains. The MetroPT dataset was used for this work. A multi-task artificial neural network was developed for the simultaneous identification of failures and GPS quality assessment. The network had common dense, batch normalization, and Gaussian noise layers, followed by output sigmoid layers for each output. The algorithm was trained for 20 epochs with a batch size of 5000 using the using Adam optimizer. The local interpretable model agnostic explanations (LIME) technique was used to provide explanations for the model predictions. Finally, a dashboard was developed for the same application consisting of the best-trained algorithm for decision-making, along with trend visualizations and explanations. The developed multi-task model produced 98.89$ \% $, 99.12$ \% $, and 99.24$ \% $ accuracies in the testing set for failure type, failure location, and GPS quality predictions, respectively. The model produced 99.56$ \% $, 99.67$ \% $, and 99.84$ \% $ precision in the testing set for failure type, failure location, and GPS quality predictions, respectively. The loss values for the trained model on the testing set were 0.0035, 0.0026, and 0.0033 for the three tasks, respectively. The deep learning model took 43 seconds for training and 1 second for inferencing for test data. The LIME technique produced explanations for each predictive task with feature importance in positive and negative impacts. On the whole, the proposed framework can be effective for fast and accurate fault analysis in metro trains.https://www.aimspress.com/article/doi/10.3934/environsci.2024048predictive maintenancemulti-task learningmachine learningdeep learningmetro trainsindustry 4.0 |
| spellingShingle | Pratik Vinayak Jadhav Sairam V. A Siddharth Sonkavade Shivali Amit Wagle Preksha Pareek Ketan Kotecha Tanupriya Choudhury A multi-task model for failure identification and GPS assessment in metro trains AIMS Environmental Science predictive maintenance multi-task learning machine learning deep learning metro trains industry 4.0 |
| title | A multi-task model for failure identification and GPS assessment in metro trains |
| title_full | A multi-task model for failure identification and GPS assessment in metro trains |
| title_fullStr | A multi-task model for failure identification and GPS assessment in metro trains |
| title_full_unstemmed | A multi-task model for failure identification and GPS assessment in metro trains |
| title_short | A multi-task model for failure identification and GPS assessment in metro trains |
| title_sort | multi task model for failure identification and gps assessment in metro trains |
| topic | predictive maintenance multi-task learning machine learning deep learning metro trains industry 4.0 |
| url | https://www.aimspress.com/article/doi/10.3934/environsci.2024048 |
| work_keys_str_mv | AT pratikvinayakjadhav amultitaskmodelforfailureidentificationandgpsassessmentinmetrotrains AT sairamva amultitaskmodelforfailureidentificationandgpsassessmentinmetrotrains AT siddharthsonkavade amultitaskmodelforfailureidentificationandgpsassessmentinmetrotrains AT shivaliamitwagle amultitaskmodelforfailureidentificationandgpsassessmentinmetrotrains AT prekshapareek amultitaskmodelforfailureidentificationandgpsassessmentinmetrotrains AT ketankotecha amultitaskmodelforfailureidentificationandgpsassessmentinmetrotrains AT tanupriyachoudhury amultitaskmodelforfailureidentificationandgpsassessmentinmetrotrains AT pratikvinayakjadhav multitaskmodelforfailureidentificationandgpsassessmentinmetrotrains AT sairamva multitaskmodelforfailureidentificationandgpsassessmentinmetrotrains AT siddharthsonkavade multitaskmodelforfailureidentificationandgpsassessmentinmetrotrains AT shivaliamitwagle multitaskmodelforfailureidentificationandgpsassessmentinmetrotrains AT prekshapareek multitaskmodelforfailureidentificationandgpsassessmentinmetrotrains AT ketankotecha multitaskmodelforfailureidentificationandgpsassessmentinmetrotrains AT tanupriyachoudhury multitaskmodelforfailureidentificationandgpsassessmentinmetrotrains |