198-多联机系统制冷剂充注量故障检测研究.pdfVIP

多联机系统制冷剂充注量故障检测研究 1 1∗ 1 1 1 2 郭亚宾 ，陈焕新 ，王江宇 ，黄耀 ，寻惟德 ，谭泽汉 （1 华中科技大学能源与动力工程学院，湖北 武汉 430074； 2 空调设备及系统运行节能国家重点实验室，珠海 517907） 摘 要：本文通过回归方法建立了一种制冷剂充注量故障检测模型。该方法首先挑选出 对于多联机系统制冷剂充注量敏感的特征参数，然后分别通过多元线性回归和支持向量回归 建立制冷剂充注量故障检测的回归模型。该模型的训练过程只需要制冷剂充注量正常的运行 数据，不需要完整的制冷剂充注量故障数据。对于建立的故障检测模型，采用制冷剂充注量 不当数据和泄漏数据进行了实验验证。结果表明：支持向量回归模型的检测性能要优于多元 线性回归模型。对于泄漏故障，SVR 模型在制冷剂泄漏3 分钟时便可以检测出故障。 关键字：多联机；故障检测；多元线性回归；支持向量回归；制冷剂充注量 Regression method based refrigerant charge fault detection for variable refrigerant flow system (Yabin Guo1, Huanxin Chen1, Jiangyu Wang 1, Yao Huang 1, Xun Weide1, Tan Zehan2) (1Department of Refrigeration Cryogenics, Huazhong University of Science and Technology, Wuhan, China; 2State Key Laboratory of Energy Saving for Air Conditioning Equipment and Systems. Zhuhai, China) Abstract ：A refrigerant charge fault detection strategy was proposed using regression method. First, characteristic variable parameters that are sensitive to the refrigerant charge level of VRF system were select. Then, regression models of refrigerant charge amount fault detection were established by using multiple linear regression and support vector regression respectively. The training process of the regression model only needs the normal refrigerant charge operation data, which does not need the complete refrigerant charge level experimental data. Refrigerant charge fault experimental data which contains refrigerant undercharge, overcharge and leakage were used to test the developed fault detection models. Results show that the detection performance of the support vector regression model is better than the multiple linear regression model. In addition, for the refrigerant leakage fault, the support vector regression model can detect the leakage fault after 3 minutes of refrigerant leakage. Keywords: Variabl