A Hybrid Physics-Based and Stochastic Neural Network Model Structure for Diesel Engine Combustion Events
نویسندگان
چکیده
Estimation of combustion phasing and power production is essential to ensuring proper load control. However, archetypal control-oriented physics-based models can become computationally expensive if highly accurate predictive capabilities are achieved. Artificial neural network (ANN) models, on the other hand, may provide superior computational capabilities. using classical ANNs for model-based prediction control be challenging, since their heuristic deterministic black-box nature make them intractable or create instabilities. In this paper, a hybridized modeling framework that leverages advantages both stochastic approaches utilized capture CA50 (the timing when 50% fuel energy has been released) along with indicated mean effective pressure (IMEP). The performance compared ANN physics-based-only in environment. To ensure high robustness low burden hybrid framework, input parameters IMEP captured Bayesian regularized (BRANN) then integrated into an overall 0D Wiebe model. outputs successively fine-tuned BRANN transfer learning (TLMs). study shows presence Gaussian-distributed model uncertainty, proposed achieve RMSE 1.3 × 10−5 CAD 4.37 kPa 45.4 3.6 s total runtime IMEP, respectively, over 200 steady-state engine operating conditions. As such, useful tool real-time where in-cylinder feedback limited.
منابع مشابه
A dynamic PCCI combustion model for Diesel engine control design
Subject of this work is a dynamic simulation model for PCCI combustion that can be used in closed-loop control development. A detailed multi-zone chemistry model for the high-pressure part of the engine cycle is extended by a mean value model accounting for the gas exchange losses. The resulting model is capable of describing PCCI combustion with stationary exactness. It is at the same time ver...
متن کاملArtificial Neural Network Based Multi-Objective Evolutionary Optimization of a Heavy-Duty Diesel Engine
In this study the performance and emissions characteristics of a heavy-duty, direct injection, Compression ignition (CI) engine which is specialized in agriculture, have been investigated experimentally. For this aim, the influence of injection timing, load, engine speed on power, brake specific fuel consumption (BSFC), peak pressure (PP), nitrogen oxides (NOx), carbon dioxide (CO2), Carbon mon...
متن کاملA Semi-empirical Model to Predict Diesel Engine Combustion Parameters
To carry out the investigation, a cylinder pressure model was developed based on the position of the crankshaft, engine load, engine speed, and fuel injection time. This model takes into account the maximum number of parameters involved. The accuracy of the model was verified by experimental results. The average error of the cylinder pressure, the average radical of the square of the error of t...
متن کاملA Hybrid model based on neural network and Data Envelopment Analysis model for Evaluation of unit Performance
Efficiency and evaluation is one of the main and most important demands of organizations, companies and institutions. As these organizations deal with a large amount of data, therefore, it is necessary to evaluate them on the basis of scientific methods to improve their efficiency. Data envelopment analysis is a suitable method for measuring the efficiency and performance of organizations. This...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Vehicles
سال: 2022
ISSN: ['2624-8921']
DOI: https://doi.org/10.3390/vehicles4010017