Quality-Relevant Monitoring of Batch Processes Based on Stochastic Programming with Multiple Output Modes

Abstract

To implement the quality-relevant monitoring scheme for batch processes with multiple output modes, this paper presents a novel methodology based on stochastic programming. Bringing together tools from stochastic programming and ensemble learning, the developed methodology focuses on the robust monitoring of process quality-relevant variables by taking the stochastic nature of batch process parameters explicitly into consideration. To handle the problem of missing data and lack of historical batch data, a bagging approach is introduced to generate individual quality-relevant sub-datasets, which are used to construct the corresponding monitoring sub-models. For each model, stochastic programming is used to construct an optimal quality trajectory, which is regarded as the reference for online quality monitoring. Then, for each sub-model, a corresponding control limit is obtained by computing historical residuals between the actual output and the optimal trajectory. For online monitoring, the current sample is examined by all sub-models, and whether the monitoring statistic exceeds the control limits is recorded for further analysis. The final step is ensemble learning via Bayesian fusion strategy, which is under the probabilistic framework. The implementation and effectiveness of the developed methodology are demonstrated through two case studies, including a numerical example, and a simulated fed-batch penicillin fermentation process.

LSTM Soft Sensor Development of Batch Processes With Multivariate Trajectory-Based Ensemble Just-in-Time Learning

“…Finally, the current value of system output can be estimated according to the latent cell state aŝ y t = σ W y h t + b y (7) where W y denotes the weighting parameter and b y is the output bias. In summary, the complete forward pass network structure of LSTM has been demonstrated referring to (1) to (7). To train a LSTM neural network, the back propagation through time (BPTT) can be used, which is demonstrated in Appendix A.…”

Phase partition and KPI‐related process monitoring for batch processes using a novel canonical correlation analysis strategy

“…Served as the first priority of process safety, how to have the earliest detection of faults became the primary task in quality control and cost‐saving effect. [ 5,6 ]…”

“…Served as the first priority of process safety, how to have the earliest detection of faults became the primary task in quality control and cost-saving effect. [5,6] Since the semiconductor industry has rapidly developed, it is now possible to measure and store massive amounts of machine data. Hence, data-driven modelling methods have been core to batch process monitoring.…”

Improved Mahalanobis Distance Based JITL-LSTM Soft Sensor for Multiphase Batch Processes

“…Both batch and continuous processes are important modes of production in modern industry. Recently, with the rapid development of process industry, the proportion of batch processes is growing due to the increasing demand of highvalue products such as pharmaceuticals, polymers and semiconductors [1][2][3][4][5][6]. In terms of the situation, researchers focus on the quality prediction and monitoring problem of batch processes to ensure the product quality and process safety.…”