Identification of a driver's starting intention based on an artificial neural network for vehicles equipped with an automated manual transmission

The driver's starting intention, which coordinates the engine output torque and the engagement speed of clutch for a vehicle equipped with an automated manual transmission, may be the key state for automated manual transmission clutch control. Fast and accurate identification of the starting intention can ensure a smooth clutch engagement and a smooth start of a vehicle. In this paper, a novel method based on an artificial error back-propagation neural network is proposed to identify the driver's starting intention. By analysis of the experimental data, the driver's starting intention can be defined strictly and divided into three modes: a slow start, a medium start and a fast start. The statistical regularity of the acceleration pedal opening is obtained on the basis of a novel method for processing the experimental data. Because in the first period of time in a starting process, the time proportion of the acceleration pedal opening over a certain value is closely related to the driver's starting intention, therefore, this statistical regularity of the acceleration pedal opening is regarded as the input of the neural network, and the Broyden-Fletcher-Goldfarb-Shanno algorithm is applied to train the neural network. The real-vehicle test results with different drivers show that the identification accuracy of the driver's starting intention is greater than 95% during the first 600 ms with the proposed artificial error back-propagation neural network. This can provide a reasonable quantization method of the driver's starting intention for smooth automated manual transmission clutch control.