A supervisor-based neural-adaptive shift controller for automatic transmissions considering throttle opening and driving load

Recently, many passenger cars have adopted automatic transmissions for shif ting gears, and. thus the smooth and precise control of gear shifts of pass enger car automatic transmissions has become more and more essential for th e riding comfort of vehicles equipped with automatic transmissions. In this article, a neural network-based supervisor for an automotive shift control ler considering the throttle opening, variations in throttle opening, and t he driving load is presented. For using the driving load information, an ob server-based driving load estimation algorithm is proposed. A proportional- integral-derivative controller along with an open loop controller is used a s a low level controller for controlling the gear shifts, and a supervisory controller for properly adapting the shift control parameters of the low l evel shift controller is designed using ANFIS. To evaluate the control perf ormance of the proposed supervisor-based shift controller, both simulation studies and experimental studies are performed for various shifting situati ons.