Automated and Risk-Aware Engine Control Calibration Using Constrained Bayesian Optimization

TL;DR

This work tackles automated calibration of internal combustion engine controls to maximize thermal efficiency under safety and combustion stability constraints. It introduces a self-learning calibration framework that couples Principal Component Decomposition of in-cylinder pressure with constrained Bayesian Optimization, guided by a cost based on an Idealised Thermodynamic Cycle and an Otto-cycle model. The approach updates a Gaussian Process Regression model of pressure-component weights online and uses a constrained acquisition strategy alongside a constrained Particle Swarm Optimizer to efficiently locate optimal fuelling parameters, achieving near-optimal performance with fast convergence (e.g., a $0.017\%$ gap in GIE and $64.4\,\mathrm{s}$ in simulation). The method does not require prior system knowledge and demonstrates safe operation within a simulated Reactivity Controlled Compression Ignition engine, suggesting strong potential for rapid, data-driven calibration in complex, multi-parameter engines.

Abstract

Decarbonization of the transport sector sets increasingly strict demands to maximize thermal efficiency and minimize greenhouse gas emissions of Internal Combustion Engines. This has led to complex engines with a surge in the number of corresponding tunable parameters in actuator set points and control settings. Automated calibration is therefore essential to keep development time and costs at acceptable levels. In this work, an innovative self-learning calibration method is presented based on in-cylinder pressure curve shaping. This method combines Principal Component Decomposition with constrained Bayesian Optimization. To realize maximal thermal engine efficiency, the optimization problem aims at minimizing the difference between the actual in-cylinder pressure curve and an Idealized Thermodynamic Cycle. By continuously updating a Gaussian Process Regression model of the pressure's Principal Components weights using measurements of the actual operating conditions, the mean in-cylinder pressure curve as well as its uncertainty bounds are learned. This information drives the optimization of calibration parameters, which are automatically adapted while dealing with the risks and uncertainties associated with operational safety and combustion stability. This data-driven method does not require prior knowledge of the system. The proposed method is successfully demonstrated in simulation using a Reactivity Controlled Compression Ignition engine model. The difference between the Gross Indicated Efficiency of the optimal solution found and the true optimum is 0.017%. For this complex engine, the optimal solution was found after 64.4s, which is relatively fast compared to conventional calibration methods.

Figures (7)

• Figure 1: Schematic representation of the optimisation approach presented in this work.
• Figure 2: Solving the acr:bo using $\alpha_\text{NEI}$ with default constraint settings. New samples (green), old sample (red); best observed iteration (square), optimum (circle).
• Figure 3: Important observed parameters over time using $\alpha_\text{EI}$ (red), $\alpha_\text{NEI}$ (blue), $\alpha_\text{PI}$ (green) and $\alpha_\text{NPI}$ (black)
• Figure 4: Actuator settings over time using $\alpha_\text{EI}$ (red), $\alpha_\text{NEI}$ (blue), $\alpha_\text{PI}$ (green) and $\alpha_\text{NPI}$ (black)
• Figure 5: Solving the acr:bo using $\alpha_\text{EI}$ with default constraint settings. New samples (green), old sample (red); best observed iteration (square), optimum (circle).