Data-Driven Adaptive Sparse Modeling For Process Monitoring and Control
Date
2023-06-28Metadata
Show full item recordAbstract
Chemical processes are complex and often characterized by nonlinearity, time-variation, and uncertainty. As a result, data-driven modeling approaches have gained widespread popularity in industry and academia for modeling these processes. One such data-driven approach is the sparse identification of nonlinear dynamics (SINDy), which aims to identify sparse and interpretable process models from historical data. An important application of developing a process model is to deploy it for real-time prediction purposes. However, a model trained offline is not sufficient to deal with process uncertainties, which are prevalent in chemical processes. This limitation necessitates an adaptive modeling approach that can predict nonlinear process dynamics in real-time by coping with process uncertainties.
To this end, this doctoral study presents an online adaptive sparse identification of systems (OASIS) framework that extends the capabilities of SINDy for accurate and automatic approximation of process models. The OASIS method combines the goodness of SINDy and deep learning for modeling nonlinear process systems and predicting dynamics in real-time. First, SINDy is utilized to identify multiple local process models from historical process data recorded from varying operating conditions. Next, a deep neural network is built using the identified local SINDy models and their training data. The objective of training a deep neural network is to learn the functional relationship between SINDy coefficients and operating conditions, such that when the trained deep neural network is employed online, it will readily provide a suitable local SINDy model based on the current operating conditions. The effectiveness of the OASIS algorithm is demonstrated through multiple compelling case studies, each highlighting its applicability in different domains. These case studies include model predictive control of a continuous stirred tank reactor (CSTR), fault prediction of a reactor-separator system, and modeling, lifetime estimation, and charge optimization of a Li-ion battery. Through these diverse applications, the OASIS framework demonstrates its potential for developing adaptive process models capable of handling the inherent uncertainties and variations present in chemical processes.
Subject
machine learningdata-driven model
adaptive model
sparse model
process monitoring
process control
deep learning
Citation
Bhadriraju Venkata Naga Sai, Bhavana (2023). Data-Driven Adaptive Sparse Modeling For Process Monitoring and Control. Doctoral dissertation, Texas A&M University. Available electronically from https : / /hdl .handle .net /1969 .1 /199854.