基于不平衡分类的Bagging集成污水处理故障诊断  

Bagging Ensemble Fault Diagnosis Modeling with Imbalanced Classification in Wastewater Treatment Plant

作　　者：许玉格[1] 赖春伶 罗飞[1] XU Yuge ,LAI Chunling ,LUO Fei(School of Automation Science and Engineering, South China University of Technology, Guangzhou 510640, Guangdong, China)

机构地区：[1]华南理工大学自动化科学与工程学院,广东广州510640

出　　处：《华南理工大学学报（自然科学版）》2018年第8期107-115,共9页Journal of South China University of Technology(Natural Science Edition)

基　　金：国家自然科学基金资助项目(61473121);广东省科技计划项目(2016A020221008;2017B010117007;2017B090910011)~~

摘　　要：在污水处理过程故障会导致出水水质下降、运行费用增高甚至造成环境的二次污染,而污水处理故障诊断数据的典型不平衡特性,严重影响了故障诊断的效果,尤其会导致故障分类的正确率偏低.针对此问题,文中提出了一种基于加权极限学习机的改进Bagging集成污水处理故障诊断建模方法;以加权极限学习机为基分类器,以Bagging集成框架建立集成分类器;定义可调整的过采样倍率公式,通过虚拟少数过采样算法(SMOTE)对少数类样本进行过采样,以保证基分类器间的多样性;以不平衡分类性能指标G-mean值为基础,定义新的基分类器输出权值更新公式,以提高故障类别识别率.仿真实验表明,该污水处理故障诊断模型的性能优于其他对比算法,可有效提高G-mean值和整体分类正确率,特别是提高了故障类别的识别正确率.Operation faults in wastewater treatment plant may lead to reduce effluent water quality, raise operation costs and secondal-y environmental pollution. The representative imbalanced data for fault diagnosis in wastewater treatment process seriously affects the fault diagnosis pereomlance, especially results in the lower accuracy of faulty classes. To address this problem, this paper proposes an improved bagging ensemble fault diagnosis method based on weighted extreme learning machine in wastewater treatment process. This method establishes the ensemble cla ssifier in bagging framework, and the weight extreme leanfing machine algorithm is selected to build the basic cla-ssifiers. Defining adjustable oversampling rate fommla, the diversity of basic classifiers is ensred by oversampling the minority data with SMOTE method. Based on the imbalance classification peffommnce index G-mean, an updating fommla of the output weight value in the base classifier is defined to improve the recognition accuracy in faulty class. Simulation experiments show that the proposed fault diagnosis model over peffomls the other algo-rithms. The proposed method can effectively improve G-mean value and overall classification accuracy on fault diagnosis in wastewater treatment process, and in particular, raise the recognition accuracy in faulty class.

关 键 词：不平衡分类 加权极限学习机 Bagging集成算法 污水处理 故障诊断 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]