Deep Neural Koopman Operator-based Economic Model Predictive Control of Shipboard Carbon Capture System

2025-04-09

AI Summary

Addressing the challenge of simultaneously ensuring safety, energy efficiency, and economic viability for shipboard carbon capture systems in international shipping, this paper proposes a data-driven, time-varying Koopman operator modeling framework integrated with convex economic model predictive control (EMPC). We innovatively develop a deep neural network–enhanced, time-varying parameter Koopman dynamical model to enable accurate prediction of economic cost and critical outputs under partially observable states. Furthermore, we design a convex EMPC formulation that rigorously enforces hard operational constraints, guaranteeing real-time feasibility and constraint satisfaction for nonlinear, time-varying systems. High-fidelity simulations across four representative sea conditions demonstrate significant improvements in carbon capture rate and economic performance, while achieving 100% compliance with all safety and emission constraints—thereby validating the method’s safety, energy efficiency, and engineering practicality.

Technology Category

• Search and Optimization: Sampling/Simulation-based Search
• Constraint Satisfaction and Optimization: Constraint Optimization
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Systems and Infrastructure for Web, Mobile and WoT: Sustainability and carbon-aware systems for Web, mobile, and WoT
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Shipboard carbon capture is a promising solution to help reduce carbon emissions in international shipping. In this work, we propose a data-driven dynamic modeling and economic predictive control approach within the Koopman framework. This integrated modeling and control approach is used to achieve safe and energy-efficient process operation of shipboard post-combustion carbon capture plants. Specifically, we propose a deep neural Koopman operator modeling approach, based on which a Koopman model with time-varying model parameters is established. This Koopman model predicts the overall economic operational cost and key system outputs, based on accessible partial state measurements. By leveraging this learned model, a constrained economic predictive control scheme is developed. Despite time-varying parameters involved in the formulated model, the formulated optimization problem associated with the economic predictive control design is convex, and it can be solved efficiently during online control implementations. Extensive tests are conducted on a high-fidelity simulation environment for shipboard post-combustion carbon capture processes. Four ship operational conditions are taken into account. The results show that the proposed method significantly improves the overall economic operational performance and carbon capture rate. Additionally, the proposed method guarantees safe operation by ensuring that hard constraints on the system outputs are satisfied.

Problem

• Model shipboard carbon capture for energy-efficient operation
• Predict economic costs using dynamic Koopman operator modeling
• Ensure safe operation with constrained predictive control

Innovation

• Deep neural Koopman operator for dynamic modeling
• Time-varying parameter Koopman model for cost prediction
• Convex economic predictive control for efficient operation