Harvest time prediction for batch processes. (2nd September 2018)

• Record Type: Journal Article
• Authors: Spooner, Max; Kold, David; Kulahci, Murat
• Is Part Of: Computers & chemical engineering. Volume 117(2018)
• Page Start: 32
• Page End: 41
• Publication Date: 2018-09-02
• Subjects: Batch process -- Prediction -- Dynamic time warping -- Partial least squares -- Lasso regression; Chemical engineering -- Data processing -- Periodicals; 660.0285
• DOI: 10.1016/j.compchemeng.2018.05.019
• Languages: English
• ISSNs: 0098-1354

Abstract

Highlights: Many batch processes contain variability in the durations (harvest times) of batches. A case study is presented of a bacteria fermentation batch process that displays harvest time variability. A method is presented for predicting the harvest time at an early stage in the process using dynamic time warping and lasso regression. Warping information from dynamic time warping is used to update the harvest time predictions online during the process. Abstract: Batch processes usually exhibit variation in the time at which individual batches are stopped (referred to as the harvest time). Harvest time is based on the occurrence of some criterion and there may be great uncertainty as to when this criterion will be satisfied. This uncertainty increases the difficulty of scheduling downstream operations and results in fewer completed batches per day. A real case study is presented of a bacteria fermentation process. We consider the problem of predicting the harvest time of a batch in advance to reduce variation and improving batch quality. Lasso regression is used to obtain an interpretable model for predicting the harvest time at an early stage in the batch. A novel method for updating the harvest time predictions as a batch progresses is presented, based on information obtained from online alignment using dynamic time warping.