Automotive engine torque and air-fuel ratio control using dual heuristic dynamic programming

In this paper, we present our work on self-learning engine control using "derivative' adaptive critics. In the derivative version of adaptive critic designs, the derivative of the cost function of dynamic programming with respect to the state of the process is estimated. As the goal of dynamic programming is to maximize the overall cost function, direct estimation of the cost function derivatives will naturally lead to better algorithm performance. In our previous studies of the regular version of adaptive critic techniques, a model of the process for controller training was not necessary. However, for the implementation of the "derivative" version of adaptive critic designs, a process model in the form of neural network is required. In this way, the derivative information can be propagated back to the controller in order to update the controller parameters. The objectives of the present learning control design for automotive engines are to improve performance, reduce emissions and maintain optimum performance under various operating conditions. Using data from the test vehicle equipped with a 5.3L V8 engine, we built a neural network model of the engine. The model is then used in the development of self-learning neural network controllers based on the idea of approximate dynamic programming to achieve optimal control for both engine torque and exhaust air-fuel ratio control. The goals of the engine torque and air-fuel ratio control are to track the commanded torque and to regulate the air-fuel ratio at specified set-points, respectively. For both control problems, reasonably good neural network controller transient performance under a wide range of operating conditions have been achieved and reported.