An improved fuzzy logic controller for ship steering based on ior operator and neural rule extraction

Abstract

In this paper a fuzzy logic controller for ship steering is designed and simulated. The logic "ior" operator as well as wave filtering are used to obtain improved control performance as well as to get over the chattering problem associated with traditional fuzzy controllers. Moreover, an automatic neural networks-based rule generation and justification strategy is suggested to alleviate the need of manual rule extraction and pruning. This has the advantages of near-optimal easy rule generation as well as avoiding errors due to experts overlooking certain aspects of the control problem

A Framework for Bridging the Gap Between Symbolic and Non-Symbolic AI

“…The second memory type produced better results. Appendix A compares these results obtained using our approach with those obtained using conventional ANN [1,6,7] and ANFIS [8]. …”

“…Despite the successful deployment of the "ior" based rule extraction in several applications ( [1], [6] and [7]), it has several disadvantages. For example, the weights and biases of a hidden neuron have no direct clear logical interpretation.…”

“…In this appendix, we apply the conventional ANN formulation ( [1] , [6] , [7]) and ANFIS [8] to case 'B' of the adopted case study. It is noteworthy that strict application of the conventional ANN or ANFIS to this case study is not possible because the desired system output is unknown (it is not possible to evaluate the objective function except by using the robot simulator).…”

“…The first is rule extraction from weights of trained ANNs [4]- [7]. However, the proposed approaches often yield some "un-plausible" rules, thus rule pruning and retraining is often required.…”

A flexible system for initial ship design parameters estimation using a system of neural networks

“…This is due to the generalization property of ANNs. Fuzzy logic interpretation of neural networks decisions may be used in future research to guarantee the transparency of the system decisions to designers (Hamid et al 2008). Using a multi-ANN approach helps us to cope with three problems.…”