Intelligent prediction on air intake flow of spark ignition engine by a chaos radial basis function neural network
- PDF / 1,654,390 Bytes
- 9 Pages / 595.22 x 842 pts (A4) Page_size
- 81 Downloads / 250 Views
Intelligent prediction on air intake flow of spark ignition engine by a chaos radial basis function neural network LI Yue-lin(李岳林)1, 2, LIU Bo-fu(刘博夫)1, WU Gang(吴钢)1, 2, LIU Zhi-qiang(刘志强)1, 2, DING Jing-feng(丁景峰)1, 2, ABUBAKAR Shitu3 1. Key Laboratory of Safety and Design and Reliability Technology of Engineering Vehicles in Hunan Province, Changsha 410114, China; 2. College of Automotive and Mechanical Engineering, Changsha University of Science and Technology, Changsha 410114, China; 3. College of Mechanical and Electrical Engineering, Central South University, Changsha 410083, China © Central South University Press and Springer-Verlag GmbH Germany, part of Springer Nature 2020 Abstract: To ensure the control of the precision of air-fuel ratio (AFR) of port fuel injection (PFI) spark ignition (SI) engines, a chaos radial basis function (RBF) neural network is used to predict the air intake flow of the engine. The data of air intake flow is proved to be multidimensionally nonlinear and chaotic. The RBF neural network is used to train the reconstructed phase space of the data. The chaos algorithm is employed to optimize the weights of output layer connection and the radial basis center of Gaussian function in hidden layer. The simulation results obtained from Matlab/Simulink illustrate that the model has higher accuracy compared to the conventional RBF model. The mean absolute error and the mean relative error of the chaos RBF model can reach 0.0017 and 0.48, respectively. Key words: intake air flow; spark ignition engine; chaos; RBF neural network Cite this article as: LI Yue-lin, LIU Bo-fu, WU Gang, LIU Zhi-qiang, DING Jing-feng, ABUBAKAR Shitu. Intelligent prediction on air intake flow of spark ignition engine by a chaos radial basis function neural network [J]. Journal of Central South University, 2020, 27(9): 2687−2695. DOI: https://doi.org/10.1007/s11771-020-4491-y.
1 Introduction Due to the growing shortage of energy [1−3] and energy crisis in the world, many countries have been paying more attention to adopting measures to decrease energy waste and emissions [4−7] from engines. An spark ignition (SI) engine is considered as a dynamic, multivariable, highly nonlinear and delayed time- varying system. To decrease fuel consumption and control emissions from the engines [8, 9], some advanced combustion [10−13] and after treatment technology [14−16] have been
used in direct-injection (DI) engines and these previous pieces of literature concluded that the air-fuel ratio (AFR) has a great effect on engine performance and emissions, and realizing a perfect AFR value according to the measured air intake flow data is a key issue for injecting the corresponding perfect fuel mass [17, 18]. The successful applications of artificial neural network in the combustion and emission control of the engines [19−21] provide a new way to solve these problems. It is well known that traditional ANN model is oversimplified so that the actual characteristics of biological neurons cannot be well
Foundation item: Project(51176014) su
Data Loading...
