摘要
针对自然语言描述的雷达侦察装备故障诊断问题,提出了一种基于文本分类技术和支持向量机的故障诊断方法。首先,对获取的故障文本集进行分析,提取故障特征建立故障特征词库;然后,采用布尔模型实现文本向量的表示,构建故障向量库;最后,通过SVM多分类中的一对一算法建立故障诊断分类模型,并采用网格搜索法进行参数优化,实现了雷达侦察装备的故障诊断。实验分析验证了该方法的有效性和正确性,并最终将故障诊断的最大识别精度提高到90%。
To the fault diagnosis of radar reconnaissance equipment described with natural language, a fault diagnosis approach based on text classification and support vector machine was proposed. First, a fault feature lexicon was built up by analyzing the fault text sets and extracting the fault features. Then, the text vectors were represented with the Boolean model to construct the fault vector library. Finally, the diagnosis classification model was established by One-Against-One method of the SVM classification, and the parameters were optimized by result shows the diagnosis US1 effe ng grid search method. And thus the fault diagnosis was implemented. The experimental etiveness and the validity of the approach, and the maximum recognition accuracy of be improved to 90% ultimately.
出处
《电光与控制》
北大核心
2016年第2期94-98,共5页
Electronics Optics & Control
关键词
雷达侦察装备
故障诊断
文本分类
支持向量机
radar reconnaissance equipment
fault diagnosis
text classification
Support Vector Machine (SVM)