Model-based multiscale performance monitoring for batch process

Batch process is one of the most important processes in chemical industry, and how to monitor the performance of batch processes has always been one of the most active research areas in process control. An integrated framework for batch process monitoring is presented in this paper, which combines neural network (NN) for nonlinear mapping and multiscale principal component analysis (MSPCA) for features extraction at all scales. MSPCA combines PCA and wavelet transformation, and is employed to generate monitoring charts at all scales based on the multivariable residuals derived from the differences between the process outputs and the NN prediction. The advantage of proposed method over the traditional MPCA is demonstrated on the industrial streptomycin fermentation process.