基于BAM网络的坦克火控系统在线故障诊断方法研究

Research on Online Fault Diagnosis Method of Fire Control System Based on BAM Neural Network

鉴于传统的坦克火控系统故障诊断技术诊断速度慢,对多故障复合情况难以快速定位等缺点,提出了一种基于BAM网络的在线故障诊断方法;结合BAM网络模型和算法,利用层次分析法建立系统故障模型,使用最小割集对模型进行分解,生成训练BAM网络的正交学习样本空间,给出了一种最优化的权值矩阵生成方法,并应用该方法对某型坦克进行故障诊断;实例证明此方法能够有效减少测试点数量,简化网络结构,实现了单故障和复合型故障的快速定位,提高了故障诊断效率。

The traditional fault diagnosis method of fire control system has the disadvantages that the speed of diagnosis was slow and was not able to locate the faults when some faults occurred at one time. A new fault diagnosis technology based on discrete BAM neural network theory was introduced here. The article introduced the model and the basic algorithm of BAM, established the system model by using hierar- chical analysis method. Then the minimal cut set method was used to decompose the model and obtain learning sample space. A optimal method of generating the weighted matrix was proposed. At last the issue presented an example to illustrate the application. The result showed that the new method could decrease the number of the network input nerve cells, ameliorated network inner structural, solved the cases in which simple fault or complex faults occurred. It was effective to solve these issues.