数控机床的故障信息类型繁多，且包含有大量噪声，从这些数据中精确抓取出机床的故障识别特征信息难度较大。此次研究为准确抽取数控机床中的故障信息实体关系，使用卡尔曼滤波器和变压器双向编码器(Bidirectional Encoder Representations from Transformers，BERT)构建出数控机床故障信息实体关系抽取与故障识别模型。实验结果表明，此次研究设计的模型在测试集上的故障识别精度明显高于所有对比模型，说明设计出的模型能更加准确地抽取出数控机床故障信息实体关系，具有较大的应用潜力。
Research on Entity-Relationship Extraction of CNC Machine Tool Fault Information Based on BERT Model
The fault information of CNC machine tools is of various types and contains a large amount of noise,so it is difficult to accurately extract the fault identification feature information of machine tools from these data.In this study,in order to accurately extract the fault information entity relationship in CNC machine tools,the Kalman filter and Bidirectional Encoder Representations from Transformers(BERT)are used to construct a CNC machine tool fault information entity relationship extraction and fault identification model.The experimental results show that the fault recognition accuracy of the model designed in this research on the test set is significantly higher than that of all the comparative models,indicating that the designed model can more accurately extract the CNC machine tool fault information entity relations and has a greater potential for application.
NETL
NSTL
万方数据
