Abstract
Estimation of combustion phasing and power production is essential to ensuring proper combustion and load control. However, archetypal control-oriented physics-based combustion models can become computationally expensive if highly accurate predictive capabilities are achieved. Artificial neural network (ANN) models, on the other hand, may provide superior predictive and computational capabilities. However, using classical ANNs for model-based prediction and control can be challenging, since their heuristic and deterministic black-box nature may make them intractable or create instabilities. In this paper, a hybridized modeling framework that leverages the advantages of both physics-based and stochastic neural network modeling approaches is utilized to capture CA50 (the timing when 50% of the fuel energy has been released) along with indicated mean effective pressure (IMEP). The performance of the hybridized framework is compared to a classical ANN and a physics-based-only framework in a stochastic environment. To ensure high robustness and low computational burden in the hybrid framework, the CA50 input parameters along with IMEP are captured with a Bayesian regularized ANN (BRANN) and then integrated into an overall physics-based 0D Wiebe model. The outputs of the hybridized CA50 and IMEP models are then successively fine-tuned with BRANN transfer learning models (TLMs). The study shows that in the presence of a Gaussian-distributed model uncertainty, the proposed hybridized model framework can achieve an RMSE of 1.3 × 10−5 CAD and 4.37 kPa with a 45.4 and 3.6 s total model runtime for CA50 and IMEP, respectively, for over 200 steady-state engine operating conditions. As such, this model framework may be a useful tool for real-time combustion control where in-cylinder feedback is limited.
Highlights
Stricter emissions regulations and renewed interest in reducing the carbon footprint of internal combustion engines have prompted the evolution of the fuel and air pathways of modern diesel engines, in order to maximize efficiency while minimizing exhaust emissions [1,2]
The direct classical Artificial neural network (ANN) indicated mean effective pressure (IMEP) model returned a Pearson product–moment correlation coefficient (PPMCC) of 99.4% and an RMSE of 6.33 kPa, while the hybrid Bayesian regularized ANN (BRANN) IMEP model had a PPMCC of 99.6% and an RMSE 4.94 kPa
We have demonstrated the use of an integrated approach using combustion physics and ANNs for combustion phasing modeling of a modern diesel engine for use in real-time combustion and engine load control
Summary
Stricter emissions regulations and renewed interest in reducing the carbon footprint of internal combustion engines have prompted the evolution of the fuel and air pathways of modern diesel engines, in order to maximize efficiency while minimizing exhaust emissions [1,2]. Some of the complex subsystems introduced in modern diesel engines include the turbocharger and high- and low-pressure exhaust gas recirculation loops [1]. Powerful algorithms for online nonlinear model parameter estimation have made least-squaresbased minimization methods feasible for real-time engine modeling and control [8–11]. These computationally efficient recursive algorithms may augment a model’s fidelity and improve the robustness of models so as to better handle system constraints and uncertainties. Improvements in model accuracy could alleviate the need for expensive high-precision sensors in closed-loop control
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
