冷水机组运行数据分布有不平衡、非高斯、非线性、含噪声的特点,这给基于数据的冷水机组故障诊断带来了挑战。针对这些特点,提出了一种将局部密度过采样算法(Minority Oversampling under Local Area Density,MOLAD)和极限梯度提升算法(e Xtreme Gradient Boosting,XGBoost)相结合的复合算法应用于冷水机组故障诊断中,以克服样本分布不平衡问题,引入代价敏感学习理论来提升重要故障的召回率。基于离心式冷水机组常见的七个故障监测数据进行仿真,结果表明:XGBoost相比于对照组能够更好的对冷水机组状态监测数据进行分类;MOLAD-XGBoost复合模型能够有效处理数据不平衡问题;代价敏感权重可以有效提高重要故障的召回率。
In this study, a linear model predictive control(MPC) approach with optimal filters is proposed for handling unmeasured disturbances with arbitrary statistics. Two types of optimal filters are introduced into the framework of MPC to relax the assumption of integrated white noise model in existing approaches. The introduced filters are globally optimal for linear systems with unmeasured disturbances that have unknown statistics. This enables the proposed MPC to better handle disturbances without access to disturbance statistics. As a result, the effort required for disturbance modeling can be alleviated. The proposed MPC can achieve offset-free control in the presence of asymptotically constant unmeasured disturbances. Simulation results demonstrate that the proposed approach can provide an improved disturbance ?rejection performance over conventional approaches when applied to the control of systems with unmeasured disturbances that have arbitrary statistics.
针对一类支持向量机(One-class Support Vector Machine,OCSVM)对训练样本中离群点敏感问题,提出一种基于距离权重和局部密度权重的附加权重一类支持向量机模型(Additional Weighted One-class Support Vector Machine,AWOCSVM)。该方法利用训练样本点之间的欧氏距离挖掘自身包含的信息,在模型训练时给每个样本赋予附加权重,在主元分析(PCA)对样本数据降维的基础上,构建出冷水机组正常运行的单分类超平面,并构造D和T2统计量进行故障检测。通过离心式冷水机组故障模拟数据验证表明,基于PCA-AWOCSVM的故障检测方法提高了模型的鲁棒性,可以有效降低制冷系统故障检测的漏报率。