【摘要】 随着照明系统体量和复杂程度不断提高，传统的故障诊断方法过度依赖人工导致故障诊断效率低、难度大。针对上述问题利用知识图谱对大数据较强的知识关联与分析能力，辅助进行照明系统故障诊断工作。首先，自顶向下定义照明系统故障诊断知识图谱的整体架构，形成知识图谱的模式层；然后，在自建数据集的基础上构建并训练BERT-BiLSTM-CRF模型进行知识抽取，自底向上构建知识图谱的数据层；其次，结合推演格算法构建并优化故障诊断规则模块；最后使用Neo4j图数据库对该知识图谱进行可视化展示并对其在故障诊断中的应用进行分析。实验结果表明，BERT-BiLSTM-CRF模型在照明数据知识抽取任务上较BiLSTM-CRF模型的精确率提高了17.58%,具有更好的准确性和有效性。提出了构建照明系统故障诊断知识图谱的方法，并建立了故障诊断规则模块，有效提高了照明系统故障诊断的可靠性及其智能化水平。更多还原

【Abstract】 The size and complexity of lighting system are constantly increasing, and the traditional fault diagnosis methods rely excessively on manual work, resulting in low efficiency and difficulty in fault diagnosis. In view of the above problems, it is proposed to use the strong knowledge association and analysis ability of knowledge graph on big data to assist fault analysts in the lighting system fault diagnosis. Firstly, the schema layer of the knowledge graph in the top-down style is designed, which defines the overall architecture of the lighting system fault diagnosis knowledge graph. Secondly, the BERT-BiLSTM-CRF model is constructed and trained for knowledge extraction by using self-built data set, and the data layer of the knowledge graph in the bottom-up style is built. Then, the fault diagnosis rule module is constructed and optimized by combining the knowledge graph with the deduction lattice algorithm. Finally, the knowledge graph is visualized by using the Neo4j graph database and its application process in fault diagnosis is analyzed. The experimental results show that the BERT-BiLSTM-CRF model has a 17.58% improvement in precision over the BiLSTM-CRF model for the lighting data knowledge extraction task, and has better accuracy and effectiveness. The method of constructing the lighting system fault diagnosis knowledge graph is proposed, and the fault diagnosis rule module is built, which effectively improves the reliability of lighting system fault diagnosis and its intelligence level.更多还原