Search Results

This paper presents another application [1] of using Artificial Neural Networks (ANN) in adaptive tracking control of an electronic throttle system. The ANN learns to model the experimental direct inverse dynamic of the throttle servo system using a multilayer perceptron neural network structure with the dynamic back-propagation algorithm. An off-line training process was used based on an historical set of experimental measurements that covered all operating conditions. This provided sufficient information on the dynamics of the open-loop inverse nonlinear plant model. The identified ANN Direct Inverse Model (ANNDIM) was used as a feed-forward controller combined with an adaptive feed-back gains (PID) controller scheduled [2] at different operating conditions to provide the robustness in tracking control to un-modeled dynamics of the throttle servo system.

In this paper, a nonlinear Hammerstein model was used to represent the dynamic behavior of an electronic throttle body at different operating conditions. The structure of the Hammerstein model was nonlinear in its parameters. It consisted of a static nonlinear function representing the coulomb friction and limp-home return springs in series with dynamic piecewise-linear transfer functions. The mathematical modeling of the throttle body was derived in state-space discrete form. Separable least squares estimation and optimization methods were implemented as a means of simultaneously estimating and identifying both the linear and nonlinear elements to match the results obtained from the simulation of the nonlinear Hammerstein model and the experimental tests.

In this paper, we present an estimation of the coulomb friction and return spring effects in an automotive electronic throttle control (ETC) system using a nonlinear model-based estimator. The non-linear model-based estimator smoothly estimates this static non-linear behavior based on a priori knowledge of the feedback signals of the position error and the angular velocity of the throttle plate. Extensive simulations showed that the estimator sufficiently predicts the actual static non-linear behavior. The performance of the estimator was compared to an approximation based on the experimental nonlinear characteristics of the throttle. The non-linear model-based estimator can be used for compensation and can cancel the effect of the static nonlinearity in the throttle actuator to improve throttle position control.

The Electronic Throttle Control (ETC) system presented in this paper combines gain-scheduled Proportional, Integral and Derivative (PID) feedback control with feed-forward compensation of throttle plate friction. The non-linear model-based friction compensator was integrated along with the PID controller as a TargetLink block in the IAV Electronic Control Unit (ECU) engine controller software, implemented on a rapid prototype real-time system. The best gains for the PID controller were determined on-line using our Computer-Aided Calibration (CAC) methods. All experimental results revealed adequate tracking and satisfied requirements for both controller performance and cost. The control structure with friction compensation was robust and simple to implement. The influence of the throttle control on vehicle performance during slow and fast maneuvers is presented.

This paper presents the results of using Computer-Aided Calibration (CAC) methods for engine torque mapping. Mapping was done in three modes: stoichometric, power enrichment and catalyst protection. The spark advance and air/fuel ratio were optimized to find the minimum values for best torque. The optimized variables were subject to the limits of the catalyst temperature and engine knocking. CAC methods are not limited to engine torque mapping calibration; they can be applied to on-line verification, parameter tuning and off-line analysis.