In the present work, a new regression method based on wavelet analysis and multivariate analysis is proposed. Referred to as wavelet coefficient regression (WCR), the proposed method can build a statistical model that relates operation profiles with product quality in a batch process. In WCR, selected wavelet coefficients of operation profiles are used as input variables of a statistical model, and thus time-related information such as timing of manipulation can be successfully modeled. In addition, by integrating multivariate analysis and wavelet analysis, WCR can cope with correlation of input variables. As a result, WCR enables us to build an accurate statistical model of a batch process.

On the basis of WCR, a data-driven method for improving product quality in a batch process is also proposed. The proposed method can determine operation profiles that can achieve the desired product quality and optimize the operation profiles under a given performance index and various constraints.

The usefulness of the proposed WCR and quality improvement method is demonstrated through a case study of lysine production based on a semi-batch fermentation process. A more accurate statistical model was built by using the proposed WCR than conventional methods such as multiway PLS. Furthermore, WCR-based optimization of operation profile functioned successfully for finding the best profile to achieve any given objective, such as maximizing throughput and minimizing operation cost, under various constraints.

Extended Abstract Status: File Uploaded