Hybrid Derivative Dynamic Time Warping for Online Industrial Batch-End Quality Estimation

Abstract

This paper discusses the design of an inferential sensor for the online prediction of the end-quality of an industrial batch polymerization process. Owing to unequal batch speeds, measurement profiles must be synchronized before modeling. This makes profile alignment an integral part of any inferential sensor. In this work, a novel online hybrid derivative dynamic time warping data alignment technique is presented. The proposed technique allows for automatic adjustment of the warping resolution to achieve optimal alignment results for both slowly and rapidly varying parts of the measurement profiles. The proposed online data alignment technique is combined with a multiway partial least-squares black box model to yield online predictions of the final quality of a running batch process. It is demonstrated that this inferential sensor is capable of accurately predicting the quality online for an industrial polymerization process, even when the production process is only halfway, that is, well before lab measurements become available. As a result of this early warning, batches violating the quality specifications can be corrected or even stopped. This leads to fewer off-spec batches, saves production time, lowers operational costs, and reduces waste material and energy.

An extensive reference dataset for fault detection and identification in batch processes

“…The raw data could be used, for example, for testing other data synchronization methods, such as Dynamic Time Warping (DTW) [44], Correlation Optimized Warping (COW) [29], and their various variations and combinations [7,34]. Because the growth of biomass and production of penicillin are the major driving forces governing the behavior of the Pensim process, reducing batch-to-batch differences between these (unmeasured) variables could result in better process monitoring.…”

Sequential Time Slice Alignment Based Unequal-Length Phase Identification and Modeling for Fault Detection of Irregular Batches

“…Obviously, a lower injection velocity results in more injection time and thus a longer batch with more process data. Here, the injection velocity is artificially set to change from 22 samples, where maximal injection phase duration is 99 sample intervals corresponding to injection velocity 22 mm/s and the minimal filling duration is 84 associated with velocity 26 mm/s. Therefore, the difference of filling duration is 15 samples.…”

Bilinear modeling of batch processes. Part III: parameter stability

“…From these results, the application of other SCT-based synchronization methods (e.g., [21,22]) may deserve further research.…”