Fuzzy logic means something that is not clear. When we talk about the real world, there are certain situations when a situation cannot be termed as true or false. At this time, fuzzy logic will provide valuable flexibility for reasoning. In fuzzy logic, inaccuracies and uncertainties in a situation can be considered. Fuzzy is the approach for computing that is based on “degrees of truth” than the common approach of “true or false”, that is, 1 or 0 (Boolean logic). Modern computers are based on Boolean logic.
In Boolean logic, a true value is represented by 1, and a false value is represented by 0. But, in a fuzzy system, there are other intermediate values that define a value that is partially true and partially false.
Fuzzy logic is an approach that gives the ability of variable processing. Variable processing also allows multiple truth values to be processed on the same variable.
Fuzzy logic provides attempts to solve problems with an open, imprecise spectrum of data and heuristics which will make it possible for obtaining an array of accurate conclusions.
History of fuzzy logic
Fuzzy logic was proposed first by Lotfi Zadeh in 1965 proposing a fuzzy set theory for the journal Information and Control. It was studied from the 1920s by Lukasiewicz and Tarski. After this, fuzzy logic has been applied in machine control systems, image processing, artificial intelligence, and other fields which are based on signals with ambiguous interpretations.
Components of Fuzzy logic
The fuzzy logic has the following components:
1. Fuzzification
Fuzzification is the process in which specific input values are converted into some degree of membership of fuzzy sets. So, here the crisp numbers are converted into fuzzy sets. The crisp inputs are basically the exact inputs that are measured by sensors and are passed into the control system for further processing. Ex: temperature, pressure, flow, etc. There are three types of fuzzifiers in the fuzzification component of fuzzy logic.
- Singleton Fuzzifier
- Gaussian Fuzzifier
- Trapezoidal/triangular Fuzzifier
- Fuzzy Rules/Rule Base:
Fuzzy rules are a set of rules which have the IF-THEN conditions within them. Fuzzy rules are conditions that experts provide for governing the decision-making system, based on linguistic information. Due to recent development in fuzzy theory, several effective methods for the design and tuning of fuzzy controllers are available. Most of the developments aimed at reducing the number of fuzzy rules.
2. Inference Engine
The inference engine is used to determine the matching degree of the current fuzzy input with respect to each rule. The inference engine also decides which rules are to be fired according to the input field. These fired rules are also combined to form control actions.
3. Defuzzification
Defuzzification is a process of converting fuzzy conclusions to detailed output values. So, the defuzzification component is used to convert the fuzzy set obtained by the inference engine into a crisp value. Many defuzzification methods are available. From these, the best-suited one is chosen with a specific expert system to reduce the error.
Difference between Fuzzy logic and Neural Network
The artificial neural network is a computational system that is designed for imitating the problem-solving process like the human nervous system. It differs from fuzzy logic in the way a set of rules is designed to reach the conclusion from imprecise data. Neural networks and fuzzy logic both have applications in computer science but are in distinct fields.
Advantages of Fuzzy Logic
The advantages of fuzzy logic are as follows:
- The fuzzy logic system can work with any type of input irrespective of whether they are imprecise, distorted, or noisy inputs.
- Fuzzy logic systems have an easy and understandable construction.
- Fuzzy logic uses mathematical concepts of set theory and reasoning which are easy to understand.
- Fuzzy logic provides a very efficient solution for complex problems in all fields of life. This is due to the fact that it resembles human reasoning and decision-making.
- Fuzzy logic has algorithms that can be described with little data. Hence less memory is required.
- Fuzzy logic can provide accurate results with inaccurate or imprecise data.
Disadvantages of Fuzzy Logic
The disadvantages of fuzzy logic are as follows:
- Sometimes a solution through fuzzy logic provides ambiguity. This is because there is no systematic approach to solving a given problem through fuzzy logic.
- Proving the characteristics is quite difficult because in most cases it is difficult to get a mathematical description of the approach each time.
- Fuzzy logic works on imprecise and precise data. So, accuracy is compromised.
Applications
- In automobiles, it is used for gear selection. It is based on factors such as engine load, road conditions, and style of driving.
- In dishwashers, it is used to determine the washing strategy and the amount of power needed. It is based on factors such as the number of dishes and the level of food residue on the dishes.
- In copy machines, it is used to adjust drum voltage. It is done based on factors such as humidity, picture density, and temperature.
- In aerospace, it is used to manage altitude control for satellites and spacecraft. It is done based on environmental factors.
- In medicine, it is used to provide a computer-aided diagnosis. It is done based on factors such as symptoms and medical history.
- It is used to control pH and temperature variables in Chemical distillation.
- Fuzzy logic is used with neural networks because it mimics the way a person makes decisions, but it is at a faster rate. This is made possible by the aggression of data and changing it into more meaningful data, by performing partial truths as Fuzzy sets.
