基于多分类SVM的船用核动力装置主回路系统破口特征诊断技术研究

Study on Diagnostic Technique for Nuclear Power Plant Primary Coolant Circuit System Break Characteristics Based on Multi-classification SVM

  • 摘要: 失水事故发生时,在事故初期判断出事故类型对操纵员安全操作意义重大,为此提出一种基于监控参数的失水事故类型判断方法。该方法根据事故发生后13 s内监控参数的变化速率与破口类型的对应关系,提取故障征兆,建立事故判断模型,并根据建立的模型使用支持向量机分类的方法进行破口事故类型判断。试验结果表明,该方法在事故发生初期可准确、有效地判断出典型失水事故的破口尺寸和相对位置。

     

    Abstract: When LOCA happened, judging accident type at the beginning was quite important for the operator to safely operate nuclear power plant, thus, a method to judge accident type based on monitoring parameters was proposed. In this method, according to the mapping between the change rates of monitoring parameters and the accident types in the first 13 s after accident, the accident symptom was distilled and a judging model was built, with which accident types were judged by using SVM classify method. Test results show that the method can judge the break size and the relevant position of a typical LOCA exactly and effectively in the beginning of the accident.

     

/

返回文章
返回