摘要
冷水机组是一个高度非线性的复杂系统,其系统故障会导致系统的运行偏离正常状态,不仅会造成工作空间空气质量的下降,更会造成机组能耗的增加。在选取RP-1043实验数据中的一组正常数据之后,又选取了其中七组故障数据,建立了训练数据。通过支持向量机(SVM)方法进行分类,以测试其对于冷水机组故障诊断的性能,并采用正确率(correct rate,CP)、命中率(hit rate,HR)、虚警率(false alarm rate,FAR)三个指标来评价模型的分类性能。同时引入四种不同程度故障,分析SVM方法随着故障程度变化的分类准确率变化。
Chiller is a highly nonlinear complex system, the fault of its system will lead to an abnormal operation, I will not only cause a decline in air quality in the work space, but also cause an increase in chiller energy consumption. In this paper, a group of normal data from Research Project-1043 and seven sets of fault data were selected to jointly establish training data. And support vector machine （SVM） method was used to classify the data to test its fault diagnosis performance for chillers. Three indicators were used to evaluate the classification performance of the model, they are correct rate （CP）, hit rate （HR） and false alarm rate （FAR）. At the same time, four different levels of fault were introduced to analysis classification accuracy of SVM with varying fault degrees.
出处
《制冷与空调（四川）》
2016年第4期377-381,共5页
Refrigeration and Air Conditioning
基金
国家自然科学基金资助项目51328602
供热供燃气通风及空调工程北京市重点实验室研究基金资助课题NR2013K02
2013年压缩机技术国家重点实验室开放基金项目
关键词
支持向量机
故障诊断
冷水机组
正确率
Support vector machines
Fault diagnosis
Chiller
Correct rate
