节点文献
基于贝叶斯网络的空调冷水阀故障检测与诊断
A Fault Detection and Diagnosis Technology for Chilled Water Valve Based on Bayesian Network
【摘要】 针对空调系统运行中所产生的很多不确定性故障问题,建立了贝叶斯网络模型,开发了多故障状态的贝叶斯概率计算模型,利用Leaky Noisy-Max模型进行贝叶斯网络参数学习,提出了基于故障特征准则和阈值判别的故障检测与诊断技术。采用现场实测数据,以冷水阀故障为例,验证了该技术的可行性。结果表明,该技术能够诊断出冷水阀故障,诊断结果能够快速定位故障产生源,从而提高空调运行系统的稳定性。
【Abstract】 In terms of many uncertain faults in the operation of the air conditioning system,the Bayesian network model was established and the Bayesian probability calculation model of multi-fault state was developed.The Leaky Noisy-Max model was used to learn Bayesian networks parameters.The fault detection and diagnosis technology based on fault feature criterion and threshold discrimination has been proposed.Using the field measured data,the proposed fault detection and diagnosis technology was applied to the chilled water valve.The results show that the technology can diagnose the chilled water valve,and the diagnosis results can quickly locate the fault source,thus improving the stability of the air conditioning system.
【Key words】 Bayesian network; chilled water valve; fault detection and diagnosis; air conditioning system; field measured data; Leaky Noisy-Max;
- 【文献出处】 东华大学学报(自然科学版) ,Journal of Donghua University(Natural Science) , 编辑部邮箱 ,2020年01期
- 【分类号】TU831
- 【被引频次】1
- 【下载频次】245