A Study on Wheel Member Condition Recognition Using Machine Learning (Support Vector Machine)
The wheels of railway vehicles are of paramount importance in relation to railroad operations and safety. Currently, the management of railway vehicle wheels is restricted to post-event inspections of the wheels whenever physical phenomena, such as abnormal vibrations and noise, occur during the ope...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-10-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/20/8455 |
| _version_ | 1797572329442639872 |
|---|---|
| author | Jin-Han Lee Jun-Hee Lee Kwang-Su Yun Han Byeol Bae Sun Young Kim Jae-Hoon Jeong Jin-Pyung Kim |
| author_facet | Jin-Han Lee Jun-Hee Lee Kwang-Su Yun Han Byeol Bae Sun Young Kim Jae-Hoon Jeong Jin-Pyung Kim |
| author_sort | Jin-Han Lee |
| collection | DOAJ |
| description | The wheels of railway vehicles are of paramount importance in relation to railroad operations and safety. Currently, the management of railway vehicle wheels is restricted to post-event inspections of the wheels whenever physical phenomena, such as abnormal vibrations and noise, occur during the operation of railway vehicles. To address this issue, this paper proposes a method for predicting abnormalities in railway wheels in advance and enhancing the learning and prediction performance of machine learning algorithms. Data were collected during the operation of Line 4 of the Busan Metro in South Korea by directly attaching sensors to the railway vehicles. Through the analysis of key factors in the collected data, factors that can be used for tire condition classification were derived. Additionally, through data distribution analysis and correlation analysis, factors for classifying tire conditions were identified. As a result, it was determined that the <i>z</i>-axis of acceleration has a significant impact, and machine learning techniques such as SVM (Linear Kernel, RBF Kernel) and Random Forest were utilized based on acceleration data to classify tire conditions into in-service and defective states. The SVM (Linear Kernel) yielded the highest recognition rate at 98.70%. |
| first_indexed | 2024-03-10T20:54:43Z |
| format | Article |
| id | doaj.art-6e016dddd916457aabb2624961f7fbec |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T20:54:43Z |
| publishDate | 2023-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-6e016dddd916457aabb2624961f7fbec2023-11-19T18:03:13ZengMDPI AGSensors1424-82202023-10-012320845510.3390/s23208455A Study on Wheel Member Condition Recognition Using Machine Learning (Support Vector Machine)Jin-Han Lee0Jun-Hee Lee1Kwang-Su Yun2Han Byeol Bae3Sun Young Kim4Jae-Hoon Jeong5Jin-Pyung Kim6Busan Transportation Corporation, Busan 47353, Republic of KoreaSchool of Software Engineering, Kunsan National University, Gunsan 54150, Republic of KoreaBusan Transportation Corporation, Busan 47353, Republic of KoreaSchool of Software Engineering, Kunsan National University, Gunsan 54150, Republic of KoreaSchool of Mechanical Engineering, Kunsan National University, Gunsan 54150, Republic of KoreaSchool of Software Engineering, Kunsan National University, Gunsan 54150, Republic of KoreaGlobal Bridge Co., Ltd., Incheon 21990, Republic of KoreaThe wheels of railway vehicles are of paramount importance in relation to railroad operations and safety. Currently, the management of railway vehicle wheels is restricted to post-event inspections of the wheels whenever physical phenomena, such as abnormal vibrations and noise, occur during the operation of railway vehicles. To address this issue, this paper proposes a method for predicting abnormalities in railway wheels in advance and enhancing the learning and prediction performance of machine learning algorithms. Data were collected during the operation of Line 4 of the Busan Metro in South Korea by directly attaching sensors to the railway vehicles. Through the analysis of key factors in the collected data, factors that can be used for tire condition classification were derived. Additionally, through data distribution analysis and correlation analysis, factors for classifying tire conditions were identified. As a result, it was determined that the <i>z</i>-axis of acceleration has a significant impact, and machine learning techniques such as SVM (Linear Kernel, RBF Kernel) and Random Forest were utilized based on acceleration data to classify tire conditions into in-service and defective states. The SVM (Linear Kernel) yielded the highest recognition rate at 98.70%.https://www.mdpi.com/1424-8220/23/20/8455recognizing condition algorithmmachine learning algorithmwheeltire |
| spellingShingle | Jin-Han Lee Jun-Hee Lee Kwang-Su Yun Han Byeol Bae Sun Young Kim Jae-Hoon Jeong Jin-Pyung Kim A Study on Wheel Member Condition Recognition Using Machine Learning (Support Vector Machine) Sensors recognizing condition algorithm machine learning algorithm wheel tire |
| title | A Study on Wheel Member Condition Recognition Using Machine Learning (Support Vector Machine) |
| title_full | A Study on Wheel Member Condition Recognition Using Machine Learning (Support Vector Machine) |
| title_fullStr | A Study on Wheel Member Condition Recognition Using Machine Learning (Support Vector Machine) |
| title_full_unstemmed | A Study on Wheel Member Condition Recognition Using Machine Learning (Support Vector Machine) |
| title_short | A Study on Wheel Member Condition Recognition Using Machine Learning (Support Vector Machine) |
| title_sort | study on wheel member condition recognition using machine learning support vector machine |
| topic | recognizing condition algorithm machine learning algorithm wheel tire |
| url | https://www.mdpi.com/1424-8220/23/20/8455 |
| work_keys_str_mv | AT jinhanlee astudyonwheelmemberconditionrecognitionusingmachinelearningsupportvectormachine AT junheelee astudyonwheelmemberconditionrecognitionusingmachinelearningsupportvectormachine AT kwangsuyun astudyonwheelmemberconditionrecognitionusingmachinelearningsupportvectormachine AT hanbyeolbae astudyonwheelmemberconditionrecognitionusingmachinelearningsupportvectormachine AT sunyoungkim astudyonwheelmemberconditionrecognitionusingmachinelearningsupportvectormachine AT jaehoonjeong astudyonwheelmemberconditionrecognitionusingmachinelearningsupportvectormachine AT jinpyungkim astudyonwheelmemberconditionrecognitionusingmachinelearningsupportvectormachine AT jinhanlee studyonwheelmemberconditionrecognitionusingmachinelearningsupportvectormachine AT junheelee studyonwheelmemberconditionrecognitionusingmachinelearningsupportvectormachine AT kwangsuyun studyonwheelmemberconditionrecognitionusingmachinelearningsupportvectormachine AT hanbyeolbae studyonwheelmemberconditionrecognitionusingmachinelearningsupportvectormachine AT sunyoungkim studyonwheelmemberconditionrecognitionusingmachinelearningsupportvectormachine AT jaehoonjeong studyonwheelmemberconditionrecognitionusingmachinelearningsupportvectormachine AT jinpyungkim studyonwheelmemberconditionrecognitionusingmachinelearningsupportvectormachine |