Test case generation of onboard ATP for heavy haul rail based on hybrid whale optimization algorithm

Combinatorial Testing (CT) of the onboard Automatic Train Protection (ATP) function in heavy haul railway train control systems can significantly enhance equipment safety. However, the large number of input parameters influencing ATP correctness, combined with complex inter-parameter constraints, often results in redundant test cases and combinatorial explosion. To address multi-parameter interactions, this study proposes a Hybrid Whale Optimization Algorithm (HWOA)-based test case generation method, using the train overspeed protection scenario as a case study. First, the key parameters affecting ATP overspeed protection are identified based on the train control system’s requirements specification. Next, parameter interactions are analyzed to construct a combinatorial testing model that satisfies the constraints. To meet the testing requirements of the onboard ATP system, the Q-learning algorithm dynamically optimizes the control parameters of the Whale Optimization Algorithm (WOA), enabling adaptive search strategy adjustments and balancing exploration-exploitation phases. Additionally, a Lévy flight disturbance strategy is introduced to expand the optimal solution search space, preventing local optima entrapment and premature convergence, thereby generating a constraint-compliant test suite. The proposed algorithm is validated using the Shuozhou-Huanghua Railway train control system simulation platform, incorporating real-world track data and equipment parameters. Results demonstrate that, compared to the standard WOA, the HWOA reduces test case counts by 13.3%, 11.4%, and 6.7% at coverage strengths of 2, 3, and 4, respectively, while shortening generation time by 0.156 s, 1.23 s, and 3.09 s. Furthermore, the HWOA exhibits faster convergence, higher accuracy, and superior search capability when benchmarked against WOA, PSO, and APSO algorithms. These findings provide valuable insights for the safety validation of heavy haul railway onboard ATP systems.

Authors

Institutions

Publication Details

Journal
Journal of Railway Science and Technology
Published
2025-06-18
DOI
https://doi.org/10.1016/j.jrst.2025.06.002
Primary Topic
Railway Systems and Energy Efficiency
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Test case generation of onboard ATP for heavy haul rail based on hybrid whale optimization algorithm

Sen Zhang, Yanpeng Zhang, Yanmin Wu, Le Yang et al.
Journal of Railway Science and Technology
Railway Systems and Energy Efficiency
article

Test case generation of onboard ATP for heavy haul rail based on hybrid whale optimization algorithm

Sen Zhang, Yanpeng Zhang, Yanmin Wu, Le Yang, Daofei Dou
article en

Abstract

Combinatorial Testing (CT) of the onboard Automatic Train Protection (ATP) function in heavy haul railway train control systems can significantly enhance equipment safety. However, the large number of input parameters influencing ATP correctness, combined with complex inter-parameter constraints, often results in redundant test cases and combinatorial explosion. To address multi-parameter interactions, this study proposes a Hybrid Whale Optimization Algorithm (HWOA)-based test case generation method, using the train overspeed protection scenario as a case study. First, the key parameters affecting ATP overspeed protection are identified based on the train control system’s requirements specification. Next, parameter interactions are analyzed to construct a combinatorial testing model that satisfies the constraints. To meet the testing requirements of the onboard ATP system, the Q-learning algorithm dynamically optimizes the control parameters of the Whale Optimization Algorithm (WOA), enabling adaptive search strategy adjustments and balancing exploration-exploitation phases. Additionally, a Lévy flight disturbance strategy is introduced to expand the optimal solution search space, preventing local optima entrapment and premature convergence, thereby generating a constraint-compliant test suite. The proposed algorithm is validated using the Shuozhou-Huanghua Railway train control system simulation platform, incorporating real-world track data and equipment parameters. Results demonstrate that, compared to the standard WOA, the HWOA reduces test case counts by 13.3%, 11.4%, and 6.7% at coverage strengths of 2, 3, and 4, respectively, while shortening generation time by 0.156 s, 1.23 s, and 3.09 s. Furthermore, the HWOA exhibits faster convergence, higher accuracy, and superior search capability when benchmarked against WOA, PSO, and APSO algorithms. These findings provide valuable insights for the safety validation of heavy haul railway onboard ATP systems.

Journal of Railway Science and TechnologyVol. 1(1)
Lanzhou Jiaotong University (CN), China Academy of Railway Sciences (CN)
Openalex Percentile: Top 80%
Railway Systems and Energy Efficiency
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.