Research on a Lightweight Rail Surface Condition Identification Method for Wheel–Rail Maximum Adhesion Coefficient Estimation
The rail surface condition is a critical factor influencing wheel–rail adhesion performance. To address the engineering challenges associated with existing rail surface condition identification models, such as high-parameter complexity, significant computational delay, and the difficulty of onboard...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-03-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/15/6/3391 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850089792486768640 |
|---|---|
| author | Kun Han Yushan Wang |
| author_facet | Kun Han Yushan Wang |
| author_sort | Kun Han |
| collection | DOAJ |
| description | The rail surface condition is a critical factor influencing wheel–rail adhesion performance. To address the engineering challenges associated with existing rail surface condition identification models, such as high-parameter complexity, significant computational delay, and the difficulty of onboard deployment, a lightweight rail surface condition identification method integrating knowledge distillation and transfer learning is proposed. A rail surface image dataset is constructed, covering typical working conditions, including dry, wet, and oily surfaces. A “teacher-student” collaborative optimization framework is developed, in which GoogLeNet, fine tuned via transfer learning, serves as the teacher network to guide the MobileNet student network, which is also fine tuned through transfer learning, thereby achieving model compression. Additionally, an FP16/FP32 mixed-precision computing strategy is employed to accelerate the training process. The experimental results demonstrate that the optimized student model has a compact size of only 4.21 MB, achieves an accuracy of 97.38% on the test set, and attains an inference time of 0.0371 s. Integrating this model into the estimation system of the maximum adhesion coefficient for heavy-haul locomotives enhances estimation confidence, reduces estimation errors under varying operating conditions, and provides real-time and reliable environmental perception for optimizing adhesion control strategies. This approach holds significant engineering value in improving adhesion utilization under complex wheel–rail contact conditions. |
| format | Article |
| id | doaj-art-ab669e39e4f7462da64dbdb5e8f4b72d |
| institution | DOAJ |
| issn | 2076-3417 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj-art-ab669e39e4f7462da64dbdb5e8f4b72d2025-08-20T02:42:41ZengMDPI AGApplied Sciences2076-34172025-03-01156339110.3390/app15063391Research on a Lightweight Rail Surface Condition Identification Method for Wheel–Rail Maximum Adhesion Coefficient EstimationKun Han0Yushan Wang1School of Traffic and Transportation Engineering, Central South University, 22 Shaoshan South Rd., Changsha 410075, ChinaSchool of Traffic and Transportation Engineering, Central South University, 22 Shaoshan South Rd., Changsha 410075, ChinaThe rail surface condition is a critical factor influencing wheel–rail adhesion performance. To address the engineering challenges associated with existing rail surface condition identification models, such as high-parameter complexity, significant computational delay, and the difficulty of onboard deployment, a lightweight rail surface condition identification method integrating knowledge distillation and transfer learning is proposed. A rail surface image dataset is constructed, covering typical working conditions, including dry, wet, and oily surfaces. A “teacher-student” collaborative optimization framework is developed, in which GoogLeNet, fine tuned via transfer learning, serves as the teacher network to guide the MobileNet student network, which is also fine tuned through transfer learning, thereby achieving model compression. Additionally, an FP16/FP32 mixed-precision computing strategy is employed to accelerate the training process. The experimental results demonstrate that the optimized student model has a compact size of only 4.21 MB, achieves an accuracy of 97.38% on the test set, and attains an inference time of 0.0371 s. Integrating this model into the estimation system of the maximum adhesion coefficient for heavy-haul locomotives enhances estimation confidence, reduces estimation errors under varying operating conditions, and provides real-time and reliable environmental perception for optimizing adhesion control strategies. This approach holds significant engineering value in improving adhesion utilization under complex wheel–rail contact conditions.https://www.mdpi.com/2076-3417/15/6/3391heavy-haul locomotiverail surface condition identificationmaximum adhesion coefficientadhesion controlfuzzy logic theory |
| spellingShingle | Kun Han Yushan Wang Research on a Lightweight Rail Surface Condition Identification Method for Wheel–Rail Maximum Adhesion Coefficient Estimation Applied Sciences heavy-haul locomotive rail surface condition identification maximum adhesion coefficient adhesion control fuzzy logic theory |
| title | Research on a Lightweight Rail Surface Condition Identification Method for Wheel–Rail Maximum Adhesion Coefficient Estimation |
| title_full | Research on a Lightweight Rail Surface Condition Identification Method for Wheel–Rail Maximum Adhesion Coefficient Estimation |
| title_fullStr | Research on a Lightweight Rail Surface Condition Identification Method for Wheel–Rail Maximum Adhesion Coefficient Estimation |
| title_full_unstemmed | Research on a Lightweight Rail Surface Condition Identification Method for Wheel–Rail Maximum Adhesion Coefficient Estimation |
| title_short | Research on a Lightweight Rail Surface Condition Identification Method for Wheel–Rail Maximum Adhesion Coefficient Estimation |
| title_sort | research on a lightweight rail surface condition identification method for wheel rail maximum adhesion coefficient estimation |
| topic | heavy-haul locomotive rail surface condition identification maximum adhesion coefficient adhesion control fuzzy logic theory |
| url | https://www.mdpi.com/2076-3417/15/6/3391 |
| work_keys_str_mv | AT kunhan researchonalightweightrailsurfaceconditionidentificationmethodforwheelrailmaximumadhesioncoefficientestimation AT yushanwang researchonalightweightrailsurfaceconditionidentificationmethodforwheelrailmaximumadhesioncoefficientestimation |