基于XGBoost-RF的制冷剂泄漏故障检测与诊断
摘要：针对冷水机组运行中正常数据多于故障数据情况和制冷系统中最常见的制冷剂泄漏故障，本文采用极端梯度提升算法(XGBoost)建立故障检测模型，采用随机森林(RF)算法建立故障诊断模型，研究了检测阈值改变对检测模型的影响及有、无正常样本训练的诊断模型的对比。结果表明，在检测阈值设定为0.99时，可保证大部分故障样本均能被检测出来，且虚警率低，仅由故障数据训练得到的诊断模型整体性能最佳，可最大限度发挥检测模型和诊断模型的优势。
关键词：冷水机组制冷剂泄漏故障检测与诊断极端梯度提升随机森林阈值
尊敬的用户，本篇文章需要2元，点击支付交费后阅读
限时优惠福利：领取VIP会员
全年期刊、VIP视频免费!
全年期刊、VIP视频免费!
参考文献[1] COMSTOCK M C,BRAUN J E,GROLL E A.A survey of common faults for chillers / discussion[G]//ASHRAE.ASHRAE transactions 2002:part 1.Atlanta:ASHRAE Inc.,2002:819- 825.
[2] 李浩，孙浩然，胡海涛，等.适用于制冷系统泄漏探测的制冷剂质量计算模型[J].制冷学报，2019,40(6):78- 81.
[3] 钱长华，于林.空调系统中制冷剂泄漏浅析[J].暖通空调，2008,38(3):122- 124,86.
[4] 肖坤，李绍斌，谭泽汉，等.基于决策树算法的多联机制冷剂泄漏在线故障诊断[J].制冷技术，2018,38(6):12- 18.
[5] 徐廷喜，杜志敏，吴斌，等.基于支持向量数据描述算法的变频空调系统制冷剂泄漏故障诊断研究[J].制冷技术，2019,39(4):25- 31.
[6] 潘进，丁强，江爱朋，等.基于XGBoost的冷水机组不平衡数据故障诊断[J].机械强度，2021,43(1):27- 33.
[7] ZHANG S,ZHU X,ANDUV B,et al.Fault detection and diagnosis for the screw chillers using multi-region XGBoost model[J].Science and technology for the built environment,2021,27(5):608- 623.
[8] CHAKRABORTY D,ELZARKA H.Early detection of faults in HVAC systems using an XGBoost model with a dynamic threshold[J].Energy and buildings,2019,185:326- 344.
[9] CHEN T,GUESTRIN C.XGBoost:a scalable tree boosting system[C]//Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining,2016:785- 794.
[10] LI B,FRIEDMAN J,OLSHEN R.Classification and regression trees (CART)[M].New York:Springer,2008:1- 65.
[11] FREUND Y,SCHAPIRE R.A short introduction to boosting[J].Journal of Japanese society for artificial intelligence,1999,14(5):771- 780.
[12] SVETNIK V,LIAW A,TONG C,et al.Random forest:a classification and regression tool for compound classification and QSAR modeling[J].Journal of chemical information and computer sciences,2003,43(6):1947- 1958.
[13] 陈德鑫.空调制冷剂充注量异常检测算法设计与实现[D].武汉：华中科技大学，2016:13- 18.
[14] RUGGIERI S.Efficient C4.5[classification algorithm][J].IEEE transactions on knowledge and data engineering,2002,14(2):438- 444.
[15] CHEN J,LUO D L,MU F X.An improved ID3 decision tree algorithm[C]//2009 4th International Conference on Computer Science & Education,2009:127- 130.
[16] DORFMAN R.A formula for the Gini coefficient[J].The review of economics and statistics,1979,61(1):146- 149.
[17] 连克强.基于Boosting的集成树算法研究与分析[D].北京：中国地质大学，2018:25- 32.
[18] 王晓佩.基于随机森林的冷水机组典型故障诊断方法研究[D].广州：华南理工大学，2020:19- 22.
[19] COMSTOCK M C,BRAUN J E,BERNHARD R.Development of analysis tools for the evaluation of fault detection and diagnostics in chillers[R].West Lafayette:Deliverable for ASHRAE Research Project,1999:26- 40.
[20] 韩华.基于顺序集成方法的制冷系统故障检测与诊断研究[D].上海：上海交通大学，2012:34- 35.
[2] 李浩，孙浩然，胡海涛，等.适用于制冷系统泄漏探测的制冷剂质量计算模型[J].制冷学报，2019,40(6):78- 81.
[3] 钱长华，于林.空调系统中制冷剂泄漏浅析[J].暖通空调，2008,38(3):122- 124,86.
[4] 肖坤，李绍斌，谭泽汉，等.基于决策树算法的多联机制冷剂泄漏在线故障诊断[J].制冷技术，2018,38(6):12- 18.
[5] 徐廷喜，杜志敏，吴斌，等.基于支持向量数据描述算法的变频空调系统制冷剂泄漏故障诊断研究[J].制冷技术，2019,39(4):25- 31.
[6] 潘进，丁强，江爱朋，等.基于XGBoost的冷水机组不平衡数据故障诊断[J].机械强度，2021,43(1):27- 33.
[7] ZHANG S,ZHU X,ANDUV B,et al.Fault detection and diagnosis for the screw chillers using multi-region XGBoost model[J].Science and technology for the built environment,2021,27(5):608- 623.
[8] CHAKRABORTY D,ELZARKA H.Early detection of faults in HVAC systems using an XGBoost model with a dynamic threshold[J].Energy and buildings,2019,185:326- 344.
[9] CHEN T,GUESTRIN C.XGBoost:a scalable tree boosting system[C]//Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining,2016:785- 794.
[10] LI B,FRIEDMAN J,OLSHEN R.Classification and regression trees (CART)[M].New York:Springer,2008:1- 65.
[11] FREUND Y,SCHAPIRE R.A short introduction to boosting[J].Journal of Japanese society for artificial intelligence,1999,14(5):771- 780.
[12] SVETNIK V,LIAW A,TONG C,et al.Random forest:a classification and regression tool for compound classification and QSAR modeling[J].Journal of chemical information and computer sciences,2003,43(6):1947- 1958.
[13] 陈德鑫.空调制冷剂充注量异常检测算法设计与实现[D].武汉：华中科技大学，2016:13- 18.
[14] RUGGIERI S.Efficient C4.5[classification algorithm][J].IEEE transactions on knowledge and data engineering,2002,14(2):438- 444.
[15] CHEN J,LUO D L,MU F X.An improved ID3 decision tree algorithm[C]//2009 4th International Conference on Computer Science & Education,2009:127- 130.
[16] DORFMAN R.A formula for the Gini coefficient[J].The review of economics and statistics,1979,61(1):146- 149.
[17] 连克强.基于Boosting的集成树算法研究与分析[D].北京：中国地质大学，2018:25- 32.
[18] 王晓佩.基于随机森林的冷水机组典型故障诊断方法研究[D].广州：华南理工大学，2020:19- 22.
[19] COMSTOCK M C,BRAUN J E,BERNHARD R.Development of analysis tools for the evaluation of fault detection and diagnostics in chillers[R].West Lafayette:Deliverable for ASHRAE Research Project,1999:26- 40.
[20] 韩华.基于顺序集成方法的制冷系统故障检测与诊断研究[D].上海：上海交通大学，2012:34- 35.
Refrigerant leakage fault detection and diagnosis based on extreme gradient boosting and random forest algorithm
Abstract: Aiming at the situation where the normal data in the chiller unit exceeds the fault data and the most common refrigerant leakage fault in the refrigeration system, this paper uses the extreme gradient boosting(XGBoost) algorithm to establish the fault detection model, and the random forest(RF) algorithm to establish the fault diagnosis model, and studies the influence of the detection threshold change on the detection model and the comparison of the diagnostic model with and without normal sample training. The results show that when the detection threshold is set to 0.99, most of the fault samples can be detected, the false alarm rate is low, and the diagnostic model trained only by the fault data makes the best overall performance, which can maximize the advantages of the detection model and diagnostic model.
Keywords: chiller; refrigerant leakage; fault detection and diagnosis; extreme gradient boosting (XGBoost); random forest (RF); threshold;
593
0
0