Journal of Intelligent & Fuzzy Systems - Volume 21, issue 1, 2

Authors: Boubertakh, H. | Tadjine, M. | Glorennec, P.-Y.

Article Type: Research Article

Abstract: This paper proposes a new fuzzy logic-based navigation method for a mobile robot moving in an unknown environment. This method endows the robot with the capabilities of obstacles avoidance and goal seeking without being stuck in local minima. A simple Fuzzy controller is constructed based on the human sense and a reinforcement learning algorithm is used to fine tune the fuzzy rule base parameters. The advantages of the proposed method are its simplicity, its easy implementation for industrial applications, and the robot joins its objective despite the environment complexity. Some simulation results of the proposed method and a comparison with …some previous works are provided. Show more

Keywords: Fuzzy logic, reinforcement learning, mobile robot navigation, obstacle avoidance

DOI: 10.3233/IFS-2010-0440

Citation: Journal of Intelligent & Fuzzy Systems, vol. 21, no. 1, 2, pp. 113-119, 2010

Authors: Kizir, S. | Bingul, Z. | Oysu, C.

Article Type: Research Article

Abstract: In this study, a real-time control of the cart-pole inverted pendulum system was developed using fuzzy logic controller (FLC). Swing-up and stabilization of the inverted pendulum were implemented directly in the FLC. The FLC designed in the Matlab-Simulink environment was embedded in a dSPACE DS1103 DSP controller board. The FLC for swing-up brings the pendulum near to its inverted position from downward position between 5 and 10 seconds. The FLC for stabilization maintains the pendulum near to inverted position with average ±1 degree of error and the cart near to zero position with average ±0.02m of error. In order to …test the robustness of the FLC, internal (changing model parameters) and external disturbances (applying external forces) were applied on the inverted pendulum. The maximum errors of the pendulum angle to the impulse force input were obtained between 1.89° and 4.6449° in the internal disturbance tests. The errors obtained from external disturbance tests vary with applied forces. Based on robustness tests, the inverted pendulum system with the FLC was shown to be robust to the external and internal disturbances. Show more

Keywords: Inverted pendulum, swing up, swing up, fuzzy logic

DOI: 10.3233/IFS-2010-0441

Citation: Journal of Intelligent & Fuzzy Systems, vol. 21, no. 1, 2, pp. 121-133, 2010

Authors: Tay, K.M. | Lim, C.P.

Article Type: Research Article

Abstract: Traditional Failure Mode and Effect Analysis (FMEA) adopts the Risk Priority Number (RPN) ranking model to evaluate failure risks, to rank failures, as well as to prioritize actions. Although this approach is simple, it suffers from several shortcomings. In this paper, we investigate a number of fuzzy inference techniques for determining the RPN scores, in an attempt to overcome the weaknesses associated with the traditional RPN model. The main objective is to examine the possibility of using fuzzy rule interpolation and reduction techniques to design new fuzzy RPN models. The performance of the fuzzy RPN models is evaluated using a …real-world case study pertaining to the test handler process in a semiconductor manufacturing plant. The FMEA procedure for the test handler is performed, and a fuzzy RPN model is developed. In addition, improvement to the fuzzy RPN model is proposed by refining the weights of the fuzzy production rules, hence a new weighted fuzzy RPN model. The ability of the weighted fuzzy RPN model in failure risk evaluation with a reduced rule base is also demonstrated. Show more

Keywords: FMEA, fuzzy inference system, fuzzy production rules, weighted fuzzy production rules, reduced rule base

DOI: 10.3233/IFS-2010-0442

Citation: Journal of Intelligent & Fuzzy Systems, vol. 21, no. 1, 2, pp. 135-146, 2010

Authors: Ignatius, J. | Motlagh, S.M.H. | Sepehri, M.M. | Behzadian, M. | Mustafa, A.

Article Type: Research Article

Abstract: This paper provides a novel design for two hybrid models in modeling decision making under uncertainty: AHP-Fuzzy PROMETHEE and AHP-Fuzzy TOPSIS. The analytic hierarchy process' (AHP) excellent ability in problem structuring allows weights of criteria to be easily gathered from experts in the decision problem. Nonetheless, the pairwise comparisons required are immense, thus inducing decision making fatigue as the number of evaluation objects and criteria increase. We show that the number of pairwise comparisons can be reduced by integrating PROMETHEE or TOPSIS into AHP. The former two techniques are distance based methods. PROMETHEE allows the evaluators to choose a set …of preference function and calculates the distance between the evaluator’s judgment and his limits. TOPSIS, on the other hand, computes the distance of a judgment from the best and worst cases. Fuzzy linguistics are incorporated into PROMETHEE and TOPSIS, thus effectively modeling decision making subjectivity – aside from eliminating the need for evaluators to specify their preference limits in PROMETHEE. These techniques are applied in a strategic outsourcing decision of a company that seeks to evaluate their training providers. The final results indicate that both AHP-Fuzzy TOPSIS and AHP-Fuzzy PROMETHEE achieved consistent results and arrived at the same ranking order. Show more

Keywords: AHP, PROMETHEE, TOPSIS, fuzzy MCDM, service outsourcing, decision analysis

DOI: 10.3233/IFS-2010-0443

Citation: Journal of Intelligent & Fuzzy Systems, vol. 21, no. 1, 2, pp. 147-162, 2010