Design a fuzzy controller for a train approaching station. Inputs are speed and Distance and output is Break power. Use triangular membership function. Consider two descriptor for input and three descriptors for output. Derive a set of rules for control action and de-fuzzification. The design should be supported by figures wherever possible. Design a fuzzy controller for a train with high speed and small distance. -

Mumbai University > Computer Engineering > Sem 7 > Soft Computing

Marks: 5 Marks

Year: Dec 2015

Since the output is Break Power, function of a fuzzy control system is to stop the train at a target position in the next station. This system controls the brake by using the distance pulse from the tacho-generator (TG) and point signal, which indicates that the train has passed a specific point (Fig. 1). The input to the control system is brake notch instruction related to the discrete deceleration. This input is currently used in many train control systems. In this type of system, the braking equipment corrects the deceleration power of an actual vehicle to the brake notch
instruction based on the weight of the train, measured by a load device. However, the nominal value reflects an error of about ±30% in actual deceleration of the brake. This error is caused by the change in the friction coefficient of the brake pads, the air pressure in the airbrake, the weight of the train, and so forth. An error of 0.32km/h/s is caused by a 1% gradient condition (a rise of 1m for every 100m), relative to the position of the train.; The detection of the speed is obtained from the distance pulse generated by the rotation of the wheel. It is a popular assumption that the resolution of the distance pulse is about 1cm. Therefore, if the sampling time is assumed to be 100 msec, the detection accuracy of the speed is 0.36 km/h, which shows rather poor resolution. Under such circumstances, it is difficult to control the object to be stopped at the target station. Because the input and output data are rough, and the system parameter varies depend on the gradient conditions along the route.

Based on the inputs, the decision of which output is to be chosen is decided here. For a two-input-one-output fuzzy controller, the form of rules can be shown where the inputs are speed and distance to cover according to which the output braking power will be applied to train in order to stop it.

The inputs are Distance and Speed, and the Output will be at what force the Break Power should be applied.

Inputs – Speed/Distance, Output – Break Power (light/heavy/etc.).

Fuzzy Control system for train: