.png){kind=icon}
.png){kind=icon}
Return
Adaptive Mode Switching Nonlinear Predictive Control Based on Continuous Learning Framework With Industrial Application
.png){kind=icon}
PRE
AI
DOI：10.1109/TASE.2026.3652581.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Industrial processes often exhibit multiple operational modes, driven by variations in production conditions, raw material properties, or operational settings. A single predictive model struggles to accommodate multimodal dynamics, leading to suboptimal performance in model predictive control (MPC). In addition, most multimode MPC approaches necessitate the development of separate predictive models for each operational mode, making the effectiveness of MPC heavily reliant on the mode switching strategy. In this paper, a novel adaptive mode-switching nonlinear predictive control (AMSNPC) method is proposed to improve both modeling robustness and control accuracy in dynamic industrial scenarios. First, a multimode modeling method based on continual learning framework is investigated to eliminate the need for explicit mode switching logic. Then, an adaptive error-triggered correction mechanism is designed to automatically detects mode switching based on output prediction errors and accelerate the response speed to the target values during operational mode switching. Finally, a heuristic optimization algorithm named state transition algorithm (STA) is adopted to find the global optimal control solution for nonlinear MPC problem. A numerical simulation experiment and an industrial case study are conducted to demonstrate that the AMSNPC method achieves high control accuracy and minimizes overshoot in multimode processes control. Note to Practitioners-The multimode processes is a common scenario in industries such as chemical manufacturing, energy production, and material processing. Traditional model predictive control methods often struggle with multimode dynamics, requiring separate predictive models for each mode and complex switching strategies. In this paper, an adaptive mode-switching nonlinear predictive control method is introduced to overcome these limitations. First, a multimode continual learning framework (MCLF) is proposed to capture multimode dynamics efficiently. Second, an adaptive error-triggered correction mechanism is developed to ensure rapid response during mode switching, while the STA optimizes control performance. Finally, the effectiveness of AMSNPC is verified by a numerical example and an industrial application of the evaporation process of alumina. The experimental results show that AMSNPC can achieve satisfied operation performance in control accuracy and overshoot.
Keywords:
Switches
Predictive models
Predictive control
Optimization
Adaptation models
Feature extraction
Production
Prediction algorithms
Automation
Optimal control
Continuous learning
multimode processes
nonlinear model predictive control
heuristic optimization
Journal
IF:
6.4
Papers:
4.9K
Citations:
1.6W