Search Results

In this paper, the Artificial Neural Network (ANN) control strategy based on the Nonlinear Auto Regressive Moving Average-Level 2 (NARMA-L2) technique has been used for tracking control of an electronic throttle body. The NARMA-L2 nonlinear plant model is first identified offline by training using a set of input-output data pairs measured at different operating conditions. This data was collected from an actual operation of the throttle body running in a closed-loop control system on a prototype vehicle. The identified NARMA-L2 plant model was then inverted and used to force the throttle output position to approximately track any reference inputs with multiple set-point changes at different operating conditions. The NARMA-L2 model was reconfigured to be an equivalent model of a feed-forward controller that can cancel not only the actual dynamic behavior of the throttle body but also the nonlinearity effects.

This paper describes first, the use of Powertrain Energy Estimator (PEE) tool to simulate and analyze the performance of the Pure Electric Vehicles (PEV’s) with all the powertrain components. The PEE uses basic physics calculations and measured components performance with the available vehicle parameters to model and simulate any conceptual PEV. The tool calculates the predicted torques, speeds, voltages, efficiency and power passed from one component to another then saves all the simulation results in a database for further user’s analysis. Secondly, we present a methodology to estimate the maximum power capacity required for PEV driving electric machine (E-Motor). The estimation approach is based on creating a power map, which combines the contour lines for all power levels over vehicle speeds/road climbing grades required for the PEV powertrain driving component (E-Motor) to meet all the vehicle’s performance requirements.

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.

The purpose of this paper is to use a multilayer perceptron neural network model to identify and control a non-linear electronic throttle system. The neural network model, which represents the dynamic behaviour of the non-linear throttle servo system, was first identified at different operating conditions. The neural network controller model was then designed (or trained) with the throttle identifier network model, so that the tracking control position of the throttle system follows a reference model. The neural network controller training is computationally expensive and requires the use of the dynamic backpropagation algorithm, which is significantly time consuming during on-line implementation. For this reason, the throttle identifier network model is used to assist in training the neural controller in off-line mode. The neural network controller was trained with the same inputs that are fed to the actual throttle system to produce the same output.

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.