Neuro Fuzzy Modeling

Neuro fuzzy modeling is a useful technique that combines the advantages of neural networks and fuzzy inference systems. In this approach, the fuzzy model is architecturally the same as a neural network. In this case one could use, for example error back-propagation to train the network to find the parameters of the fuzzy model. The most well-known method is the so-called ANFIS method the Adaptive-Network based Fuzzy Inference System. The method will be explained in this chapter and several examples will be developed as an illustration. 

In fuzzy systems we saw that human-understandable linguistic terms can be used to capture and express the knowledge about the system. 

The neuro-fuzzy approach can easily be extended to include other types of fuzzy reasoning rules. 

---

The architecture of an ANFIS model is shown in Figure 14.4. As can be seen, the proposed neuro-fuzzy model in ANFIS is a multilayer neural network-based fuzzy system, which has a total of five layers. The input (layer 1) and output (layer 5) nodes represent the descriptors and the response, respectively. Layer 2 is the fuzzification layer in which each node represents a membership. In the hidden layers, there are nodes functioning as membership functions (MFs) and rules. This eliminates the disadvantage of a normal NN, which is difficult for an observer to understand or to modify. The detailed description of ANFIS architecture is given elsewhere (31). 

Sezer,E.A., Pradhan, B.,Gokceoglu,C.2011. Manifestation of an adaptive neuro-fuzzy model on landslide susceptibility mapping Klang valley, Malaysia. Expert Systems with Applications 38(7) 8208-8219. 

Reigles, D.G. 6c Symans, M.D. 2006. Supervisory fuzzy control of a base isolated benchmark building utilizing a neuro-fuzzy model of controllable fluid viscous dampers. Journal of Structural Control and Health Monitoring, 13, 724—747. 

A model was developed using both regression and neuro-fuzzy models to predict thrust force and torque in the drilling operation of GFRP composites. The neuro-fuzzy model showed much better accuracy than the regression model. The average absolute errors for thrust force and torque were found to be 5.83 per cent and 4.57 per cent respectively with the neuro-fuzzy model, whereas for the regression model, they were 17.3 per cent and 26.67 per cent respectively (Jayabal and Natarajan, 2010). 

Jayabal, S. and Natarajan, U. (2010) Regression and neuro fuzzy models for prediction of thrust force and torque in drilling of glass fiber reinforced composites, J Sci Ind Res, 69 741-5. 

---