Research On Process Monitoring Method Of Grinding Classification Based On Semi-supervised Learning

With the rapid development of computer technology and instrument technology,a large amount of process data has been reserved.The process monitoring and fault diagnosis methods based on data driven have been widely researched and applied,However,In the process of grinding and grading production,as a result of the complexity and uncertainty of the productive process,the traditional process monitoring method is difficult to accurately monitor the fault.Therefore,based on the analysis of the existing process monitoring methods,combined with the actual situation of modern grinding-classification process has widely used the computer and instrument technology,with full use of a lot of operation data of grinding-classification process and knowledge from expert,the research on the method of fault monitoring for grinding classification process is started,which is based on semi-supervised learning,the main contents include:(1)Firstly,the process monitoring methods are summarized,and the research status of data-driven process monitoring methods is analyzed.focusing on analyzing the basic principles and main problems of process monitoring methods of machine learning.then propose the overall research strategy of this thesis.(2)Graph based semi-supervised learning is a transductive semi-supervised learning method,Prediction matrix for new data can not be predicted directly,the problem of real time difference,In this paper,by introducing a sparse feature selection framework with the linear mapping function,proposes an inductive process monitoring method of graph based semi-supervised learning.In the composition,In the graph Hessian regularization,the function value can be linearly changed with the geodesic distance,and the local manifold structure can be better maintained,and the inference ability is better.The method uses a small amount of labeled data and a large number of unlabeled data,and the semi-supervised learning based on graph Hessian regularization model is used to monitor the process.This method not only can identify the fault accurately,but also can directly determine the specific fault types.(3)In the actual grinding-classification production process,since affected by factors of the production equipment failure,sensor sensitivity failure,human error and other reasons,the production data contains noise,which will seriously affect the monitoring results.In view of this situation,this paper proposes a new anti-noise performance process monitoring method based on semi-supervised learning.Through the low rank representation of the sample data and the prediction tag matrix to remove noise information from data and extract common low rank representation matrix.Combining the semi-supervised learning,the state label matrix of process data samples is solved,so as to judge the running state of the process.(4)Through the simulation experiments of the actual operation data of the grinding-classification process,the validity and practicability of the above methods in identifying the unknown faults and handling the label noise are proved.