基于LS-SVM ARX模型的除湿机故障诊断  

Faults Diagnosis for Dehumidifier Based on LS-SVM ARX Model

作　　者：刘浩[1] 刘顺波[1] 高运广[1] 杨志国[1] 

机构地区：[1]第二炮兵工程学院,陕西西安710025

出　　处：《制冷空调与电力机械》2010年第5期47-51,共5页Refrigeration Air Conditioning & Electric Power Machinery

摘　　要：针对非线性系统故障诊断问题相对复杂的情况,以除湿机作为研究对象,应用ARX模型进行了研究。引入LS-SVM优化算法对ARX模型进行了改进,克服了传统SVM算法的不足。结合实验采集到的实际数据样本,对模型进行了训练。结果表明,改进的算法具有较低的运算复杂度和较快的学习训练速度,对于新的样本输入能够正确分析诊断。由此说明,将LS-SVM ARX模型应用于故障诊断是可行的。Aiming at the situation which faults diagnosis for nonlinear system was complicated,this paper studied ARX model based on dehumidifier.The LS-SVM algorithm was introduced to the ARX model for overcoming shortcomings in traditional SVM method.The model was trained with the data acquired from experiments.The results demonstrated the improved algorithm had lower of algorithmic complexity and faster learning speed,and could also analyze the new sample correctly.Thus,it was feasible to apply the improved LS-SVM ARX model for the fault diagnosis on dehumidifier.

关 键 词：故障诊断 除湿机 最小二乘支持向量机 外加输入自回归模型 

分 类 号：TU834.9[建筑科学—供热、供燃气、通风及空调工程]