关键词: 质量预测, 互信息法, 改进多隐层极限学习机, 混合核函数, 双向长短时神经网络, Circle混沌映射, Levy飞行, 改进灰狼算法

Abstract: In the process of product production,accurate and fast prediction of product quality helps enterprises to adjust the manufacturing process in time and reduce losses.Aiming at the problems of high dimensionality,complex correlation and difficult to accurately predict with traditional methods in the actual production process,a method based on Improved Multiple Hidden Layer Extreme Learning Machine （Improved Multiple Hidden Layer Extreme Learning Machine,LCGWO-DMKEA-BLSTM）is proposed.First,the collected feature parameters of the production process are screened by the Mutual Information (Mutual Information,MI) method to form the initial feature set of the model input.Secondly,the Gaussian kernel function and the inverse cosine kernel function are weighted and combined to construct a new hybrid kernel function,and an auto-encoder is introduced to improve the extreme learning machine,and the Deep Multi-Kernel Extreme Learning Machine Auto-encoder (Deep Multi-Kernel Extreme Learning Machine Auto-encoder,DMKEA) feature mining model is established.The DMKEA is a feature mining model that extracts the key feature information that best reflects the product quality from the high-dimensional complex process feature set,and inputs it into the Bidirectional Long Short-term Memory Network (Bidirectional Long Short-term Memory Network,BLSTM) for quality prediction.In DMKEA learning training,the Improved Grey Wolf Optimizer (Improved Grey Wolf Optimizer,LCGWO) based on Circle chaos mapping and Levy flight strategy is used to optimize the penalty coefficients,kernel parameters,and kernel function combination weights to improve the feature mining ability of DMKEA.Finally,the effectiveness of the proposed method is experimentally verified with process data from semiconductor thin-film transistor liquid crystal display production line.The research results help enterprises to realize accurate product quality prediction and also provide reference for data empowerment of enterprise production.

Key words: quality prediction, mutual information method, improved multiple hidden layer extreme learning machine, hybrid kernel function, bidirectional long short-term memory network, circle chaotic mapping, levy flight, improved grey wolf algorithm