Collaborative Dynamic Optimization Control for Municipal Solid Waste Incineration Process

Area of Science:

• Environmental Engineering
• Process Control
• Artificial Intelligence

Background:

• Municipal solid waste incineration (MSWI) faces challenges in operational optimization due to variable waste properties and dynamic conditions.
• Existing control schemes struggle with optimal set-point determination and effective tracking amidst process variations.
• Growing demands for pollution control and renewable energy necessitate advanced control strategies for MSWI.

Purpose of the Study:

• To propose a collaborative dynamic optimization control (CDOC) scheme for enhancing MSWI operational performance.
• To integrate optimization and control strategies within a multimodal optimization-based framework.
• To address challenges in set-point tracking and process variations in MSWI.

Main Methods:

• A data-driven surrogate-assisted dynamic optimization scheme using a parallel cell coordinate-based multimodal multiobjective competitive swarm optimization algorithm.
• A knowledge transfer-based dynamic response strategy to handle environmental changes.
• An adaptive multivariable model predictive control strategy for optimal control law derivation.

Main Results:

• The proposed CDOC scheme demonstrates superb tracking control performance on industrial data.
• The scheme achieves promising optimization performance, balancing multiple performance indices.
• Effective response to irregular changes in the optimization environment was observed.

Conclusions:

• The CDOC scheme offers an effective solution for optimizing MSWI processes under dynamic conditions.
• Integration of advanced optimization and adaptive control improves operational efficiency and reliability.
• The approach shows significant potential for real-world industrial applications in waste-to-energy sectors.