【作者】 王浩东； 王昕； 王振雷； 曹晨鑫；

【Author】 WANG Hao-dong;WANG Xin;WANG Zhen-lei;CAO Chen-xin;Key Laboratory of Advanced Control and Optimization for Chemical Processes, East China University of Science and Technology;Electrical and Electronic Experimental Teaching Center, Shanghai Jiao Tong University;

【机构】 华东理工大学化工过程先进控制和优化技术教育部重点实验室； 上海交通大学电工电子实验教学中心；

【摘要】 针对化工过程中因输入输出数据间非线性关系造成在线性能评估准确度不足的问题,提出一种基于多数据空间非线性迭代偏最小二乘和高斯过程回归(multi-space nonlinear iterative partial least squares and gaussian process regression,Ms-NIPLS-GPR)的性能分级评估方法。首先将性能相近的过程历史数据划分成不同性能等级的集合,利用Ms-NIPLS方法提取不同性能等级训练数据的特征子空间,然后用GPR方法获得特征子空间与性能等级标签之间的非线性映射结构,建立输入数据与性能等级之间的离线模型。得到模型后,在线评估当前过程性能以及判断其所处状态。最后,将该方法应用到乙烯裂解过程在线性能评估中,说明该性能评估方法的有效性和准确性。更多还原

【Abstract】 A performance assessment method based on multi-space nonlinear iterative partial least squares and gaussian process regression is proposed to solve the insufficient accuracy caused by the non-linear relationship between input and output data of chemical process. First,this method divides the similar historical datasets into different sets of performance grades, extracting the feature subspaces of training datasets by Ms-NIPLS method,and then using GPR to obtain a non-linear mapping structure between the feature subspaces and the performance grades labels to achieve off-line modeling. With the model obtained, current performance can be assessed online,the steady-state performance grades and the transition performance grades are recognized and distinguished.Finally, the method in this paper is applied to the online performance assessment of ethylene cracking process,which shows the effectiveness and accuracy of the performance assessment method proposed.更多还原