Knowledge Graph-Based Evaluation Method for LEU Software Safety Function Test Cases
Software safety function test cases for Lineside Electronic Units (LEU) are commonly written as long natural-language texts. They involve safety chains such as default telegram output, communication interruption, untrusted input failure, open/short-circuit monitoring, and recovery after abnormal conditions. Manual review suffers from low efficiency, insufficient consistency, and limited reuse of domain knowledge. To address these problems, this paper proposes a rule-dominant LEU software safety function test case evaluation method enhanced by controlled knowledge graph reasoning. The method takes benchmark evaluation items as the basic units, integrates structured rules, a state-failure-behavior safety chain, and evaluation profiles to perform basic judgment. For boundary items located in the neighborhood of the coverage threshold, relations among standard clauses, test stages, safety functions, functional transitions, and scenario-closure nodes are used to provide bounded gains. A negative guard mechanism is also introduced to prevent graph-based associative evidence from overriding explicit counter-evidence. Experiments are conducted on a frozen blind validation set containing 24 cases and 187 annotated items. The results show that the fusion-enhanced model achieves a Precision of 0.9606, Recall of 0.8243, F1-score of 0.8873, and Accuracy of 0.8342, outperforming both the rule-based model and the controlled KG-enhanced model in recall, F1-score, and overall judgment consistency.