Prediction of automotive engine power and torque using least squares support vector machines and Bayesian inference

A self tuning PID control strategy using reinforcement learning is proposed in this paper to deal with the control of wind energy conversion systems (WECS). Actor-Critic learning is used to tune PID parameters in an adaptive way by taking advantage of the model-free and on-line learning properties of reinforcement learning effectively. In order to reduce the demand of storage space and to improve the learning efficiency, a single RBF neural network is used to approximate the policy function of Actor and the value function of Critic simultaneously. The inputs of RBF network are the system error, as well as the first and the second-order differences of error. The Actor can realize the mapping from the system state to PID parameters, while the Critic evaluates the outputs of the Actor and produces TD error. Based on TD error performance index and gradient descent method, the updating rules of RBF kernel function and network weights were given. Simulation results show that the proposed controller is efficient for WECS and it is perfectly adaptable and strongly robust, which is better than that of a conventional PID controller.

/pdf/adaptive-pid-controller-based-on-reinforcement-learning-for-1ess5kscy8.pdf

Adaptive PID Controller based on Reinforcement Learning for Wind Turbine Control

Great efforts have been made to resolve the serious environmental pollution and inevitable declining of energy resources. A review of Chinese fuel reserves and engine technology showed that compressed natural gas (CNG)/diesel dual fuel engine (DFE) was one of the best solutions for the above problems at present. In order to study and improve the emission performance of CNG/diesel DFE, an emission model for DFE based on radial basis function (RBF) neural network was developed which was a black-box input-output training data model not require priori knowledge. The RBF centers and the connected weights could be selected automatically according to the distribution of the training data in input-output space and the given approximating error. Studies showed that the predicted results accorded well with the experimental data over a large range of operating conditions from low load to high load. The developed emissions model based on the RBF neural network could be used to successfully predict and optimize the emissions performance of DFE. And the effect of the DFE main performance parameters, such as rotation speed, load, pilot quantity and injection timing, were also predicted by means of this model. In resume, an emission prediction model for CNG/diesel DFE based on RBF neural network was built for analyzing the effect of the main performance parameters on the CO, NOx emissions of DFE. The predicted results agreed quite well with the traditional emissions model, which indicated that the model had certain application value, although it still has some limitations, because of its high dependence on the quantity of the experimental sample data.

Study of CNG/diesel dual fuel engine's emissions by means of RBF neural network

Modern automotive engines are controlled by the Electronic Control Unit (ECU). The engine ECU calibration is done empirically through tests on the dynamometer because no exact mathematical engine model is yet available. With Least Squares Support Vector Machines (LS-SVM), the approximate engine power performance model can be determined by training the sample data acquired from the dynamometer. Besides, Kernel Principal Components Analysis (KPCA) is proposed to transform unimportant adjustable variables into a compact subset for shortening model construction time and improving model accuracy. Experimental results show that KPCA+LS-SVM can really improve the training time and accuracy of an engine model.

Data preprocessing and modelling of electronically-controlled automotive engine power performance using kernel principal components analysis and least squares support vector machines

As a complex mechatronic system, the running stability, safety, and comfort of high-speed train are affected by many design variables. It is of great difficulty to identify a set of effective design parameters to optimize its running performance. The current simulation systems like the SIMPACK can simulate the running dynamics, but cannot be used effectively for optimal design of the train and rail system because there are too many design variables being supposed to be dealt with. Therefore, there is a need to make a software solution from simulation analysis to optimal design so that the computer-aided design (CAD) and engineering (CAE) can be integrated into an integral design process. This paper presents a new method to identify the key design variables against the running performance indicators based on the sensitivity analysis, which in turn bases itself on simulation-oriented surrogate models. In this way, the optimal design of a high-speed train can be successfully conducted because (1) the surrogate model can reduce the simulation time greatly and (2) the design variable space with the key variables will be reduced significantly. The research shows that this method is of practical significance for speeding up the design of high-speed train or similar complex mechatronic systems.

Identification of key design parameters of high-speed train for optimal design

In order to predict and improve the performance of natural gas/diesel dual fuel engine (DFE), a combustion rate model based on forward neural network was built to study the combustion process of the DFE. The effect of the operating parameters on combustion rate was also studied by means of this model. The study showed that the predicted results were good agreement with the experimental data. It was proved that the developed combustion rate model could be used to successfully predict and optimize the combustion process of dual fuel engine.

Chong-guang Zhou

Papers

Application of neural network in the study of combustion rate of natural gas/diesel dual fuel engine