Want to keep learning?

This content is taken from the Taipei Medical University's online course, Applications of AI Technology. Join the course to learn more.

Skip to 0 minutes and 14 secondsNow Let’s go a little deeper applying Fuzzy Set Theory to Fuzzy Logic Controller. It can be seen here, the fuzz logic controller is constructed of three parts. They are “Fuzzifier”, “Inference Engine” and “Defuzzifier”. When a crisp input goes into the fuzzy logic controller, it is firstly mapped to fuzzy set to determine the membership degrees of fuzzy sets by the fuzzier. Then, it goes to “inference engine” where the experts’ knowledge is placed. The experts’ knowledge is described by the fuzzy rules that are if-then rules. Finally, through Defuzzifier, a crisp command is made to control the plant. Maybe the fuzzy logic controller is still fuzzy for you.

Skip to 1 minute and 25 secondsSo I am going to show an design example to help you to understand fuzzy logic controller more clearly. The purpose of the example is to design the fuzzy controller to control the air-conditioner such that the room temperature maintain suitable. The input of the fuzzy controller is the room temperature. The output of the fuzzy controller is the Command of Heating, Maintaining or Cooling. At first, we have to design the fuzzifier. We use the fuzzy sets shown in this figure. Assume that the room temperature is 21 degree. Hence the membership degree in cold is 0.75 and in suitable is 0.25. Then we can go to the Inference Engine. The inference engine is where the Experts’ experience placed.

Skip to 2 minutes and 36 secondsWe can easily complete the fuzzy rules in the inference engine.

Skip to 2 minutes and 42 secondsRule 1: If the room temperature is Hot, then take the action of Cooling. Rule 2 If the room temperature is Comfortable, then take the action of Maintaining. Rule 3 If the room temperature is Cold, then take the action of Heating.

Skip to 3 minutes and 8 secondsFinally Defuzzifier can determine: What percent of effort it would take to heat up the room temperature. What percent of effort it would take to cool down the room temperature. or To maintain the room temperature. In the case of 21 degree room temperature, the membership degree in cold is 0.75 and in suitable is 0.25. According to rule 2 and rule 3, the fuzzy logic controller will give a command of heating at 75 percent effort. Finally we can see some Applications of Fuzzy Set Theory and Fuzzy Logic Controller. The fuzzy set theory can be used for clustering. This is a grey scale image of human brain. We can use fuzzy clustering approach for image segmentation to help doctors diagnose.

Skip to 4 minutes and 23 secondsThe fuzzy logic controller can be used to automatic control systems, for example, autonomous vehicle systems. Also we can use the concept of Fuzzy Set Theory to help us make decision in various areas such as in finance and management.

Fuzzy Logic Control Systems Applications

Prof. Cheng will explain the Fuzzy Logic Controller. He starts with the graph. Fuzzy Logic Controller is constructed of three parts, Fuzzifier, Inference Engine, and Defuzzifier.

To better understand, he will use example of the air-conditioner. The input of the fuzzy controller is room temperature. The output of the fuzzy controller is the Command of Heating, Maintaining or Cooling. You will be able to see how Fuzzy Logic Controller sustain the room temperature.

The fuzzy logic controller can be applied to automatic control systems, for example, autonomous vehicle systems. Also, we can use the concept of Fuzzy Set Theory to help us make a decision in various areas such as finance and management. We will see more applications of controller in the later steps.

Share this video:

This video is from the free online course:

Applications of AI Technology

Taipei Medical University