PSRONet: A Deep Reinforcement Learning-Based Sensor Configuration Framework in Railway Point Machines Fault Diagnosis
Top Cited Papers
- 16 January 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 75 (00189456) , 1-13
Abstract
Despite rapid progress in data-driven fault diagnosis for railway point machines (RPMs), most studies tacitly assume a fixed sensing setup: predefined sensor types, placements, channels, and sampling rates. This leaves a critical gap: the sensing layer (i.e., the sensor configuration of the monitoring system) itself is rarely optimized for the diagnostic task, cost constraints, or robustness to real-world disturbances. We address this gap by formulating sensor-configuration optimization as a Markov decision process (MDP), framing it as a task-aligned decision problem. To solve this, we introduce the policy-guided sensor reduction and optimization network (PSRONet), a deep reinforcement learning (DRL) framework that learns a deployable sensing policy (selected channels and sampling interval) to maximize diagnostic accuracy under acquisition budgets. The PSRONet optimizes a multiobjective reward that balances accuracy and sensor cost (quantified by data overhead), and explicitly incorporates robustness terms reflecting sensor anomalies and environmental interference encountered in field deployments. Trained offline with a fast “Fidelity Oracle” surrogate of the downstream classifier, the PSRONet outputs a deterministic configuration that is simple to implement on existing hardware. Experiments on real-world RPM data across diverse operating conditions show that the PSRONet establishes a stronger accuracy–cost Pareto frontier than many existing methods. It retains near 91% of full-data diagnostic performance with over 92% lower acquisition overhead and remains robust to sensor anomalies and environmental interference. To our knowledge, this is the first RPM-oriented, DRL-based framework that directly optimizes the sensor layer for fault diagnosis, providing a practical path toward cost-aware and robust PHM in railway operation and maintenance (O&M).Keywords
Funding Information
- Tianjin Municipal Science and Technology Program (AB22035008)
This publication has 27 references indexed in Scilit:
- Few-shot fault diagnosis of rail transit switch machine based on sparse convolution capsule relation networkNondestructive Testing and Evaluation, 2025
- A class-center fine-tuning prototypical network for few-shot fault diagnosis of turnout switch machine driven by multi-source signalsMeasurement, 2024
- Simultaneous Fault Diagnosis for Sensor and Railway Point Machine for Autonomous Rail System2024
- Railway Switch Machine Fault Diagnosis Considering Sensor Abnormality Scenarios2023
- Intelligent fault diagnosis for rail transit switch machine based on adaptive feature selection and improved LightGBMEngineering Failure Analysis, 2023
- Data-driven technology of fault diagnosis in railway point machines: review and challengesTransportation Safety and Environment, 2022
- Deep reinforcement learning in smart manufacturing: A review and prospectsCIRP Journal of Manufacturing Science and Technology, 2022
- A hierarchical method based on improved deep forest and case-based reasoning for railway turnout fault diagnosisEngineering Failure Analysis, 2021
- A Voronoi-Based Optimized Depth Adjustment Deployment Scheme for Underwater Acoustic Sensor NetworksIEEE Sensors Journal, 2020
- A Dynamic Approach to Sensor Network Deployment for Mobile-Target Detection in Unstructured, Expanding Search AreasIEEE Sensors Journal, 2016