Researches On Statistical Performance Monitoring And Control Of Batch Processes Based On PLS/STATIS Methods

The safety of production procedure and consistency of product quality are always two goals of the process industry. It is only timely and effectively finding and restoring fault in process that can create conditions for providing products with good performance and consistent quality, which is also the object and motivation of process monitoring. Batch processes play important role in process industry. Due to the flexibility, batch processes are widely used in fine industry, food industry and Pharmaceuticals. Based on historical operation data, batch SMPC (statistical performance monitoring & control) establishes monitoring and fault diagnosis models off-line and applies them in the on-line monitoring of batch process operation. Because batch SMPC dose not need the accurate models of the processes and the theory and methods gained from research work can be quickly used, it has become one of the most active research areas in process industry. The main research works are as follows:1. A survey of the aim, the need and the main methods of the process monitoring. The history and status of MSPC are also introduced.2. The basic theory and methods of statistical performance monitoring are introduced and a basic framework for statistical performance monitoring of batch processes is given.3. A method for statistical performance monitoring of batch processes based on robust MPLS is proposed to construct monitoring models when outliers are present in historical data. Applications on SBR batch polymerization process show the efficiency of robust MPLS method. Robust MPLS eliminates the effect of outliers efficiently while tradition MPLS is strongly affected by them.4. A method for statistical performance monitoring of batch processes based on STATIS is proposed. Batch process is not a continuous process and is different in production periods. Batch process data have not always perfect structure. STATIS, a three-way method for data analysis is introduced to batch SPMC. STATIS method can deal with imperfect tri-linear data structure directly without any data warping. Applications on DuPont batch polymerization process show that the STATIS method is robust.Finally, there are concluded with a summary and some further research areas in this thesis.