Output Of Fuzzy Logic System Research Articles

Zeroing neural network with fuzzy parameter for cooperative manner of multiple redundant manipulators

In this work, a distributed scheme based on quadratic programming for cooperative manner of multiple redundant manipulators with limited space constraints is studied. For the solution of the distribute scheme, a fuzzy parameter zeroing neural network (FPZNN) is presented for the coordinated motion planning of multiple redundant manipulators via absorbing fuzzy logic strategy. The fuzzy logic strategy is generated by fuzzy logic system (FLS), which can adjust the systematic parameter according to the convergent error. The scaling parameters included in the design of FPZNN are appropriately tuned with well-defined FLS output values. Theoretical analyses prove that in the absence of noise, all the manipulators can reach their desired position after the given tasks no matter for the initial joints position with an exponential position convergence. Furthermore, FPZNN with sig-bi-power activation function (SBP-AF) is applied to solve the distributed scheme of multiple redundant manipulators and obtain finite convergent rate for position error of each joint. In addition, comparative experiments prove that the FPZNN model has superior performance for the solution of the distributed manner with multiple redundant manipulators compared with the corresponding ZNN model combining with different AFs.

A multi-response optimal design of bistable compliant mechanism using efficient approach of desirability, fuzzy logic, ANFIS and LAPO algorithm

Compliant mechanisms are promising candidates in precision engineering, soft robotics, space, and bioengineering due to their advantages of free friction, free lubricant, no backlash, monolithic structure, and minimal assembly. However, designing and analyzing of compliant mechanisms are facing the high complexity due to a coupling of kinematic and mechanical behavior in comparison to rigid-body mechanisms. Especially, considering a multi-objective optimization design for compliant mechanisms, the problem is more complicated. Thus, this paper presents a new efficient hybrid methodology for solving the multi-objective optimization design. A hybridization is developed through a combination of finite element method, statistical technique, desirability function approach, fuzzy logic system, adaptive neuro-fuzzy inference system (ANFIS), and Lightning attachment procedure optimization (LAPO). A bistable compliant mechanism is investigated as an application example of the proposed method. First, design variables of the mechanism are determined, and then central composite design is employed to construct a numerically experimental matrix. Though using analysis of variance and Taguchi approach, the design variables are refined to make new populations. Subsequently, desirability values of two performances of the mechanism are computed, and the results are transferred into the fuzzy logic system. The output of fuzzy logic system is considered as single combined objective function. By developing the ANFIS model, the relation between the refined design variables and the output of fuzzy logic system is established. Finally, LAPO algorithm is adopted for solving the multi-objective optimization problem for the mechanism. Three numerical examples are investigated to validate the performance efficiency of the proposed method. The results demonstrate that the proposed method is more efficient than Taguchi-based fuzzy logic. Besides, through Wilcoxon signed rank test and Friedman test, it reveals that the performances of proposed approach are superior to those of the Jaya algorithm and TLBO algorithm. The results of this article can be extended for other complex compliant mechanisms as well as optimization problems with multiple objective functions and more complex constraints.

An effective hybrid approach of desirability, fuzzy logic, ANFIS and LAPO algorithm for optimizing compliant mechanism

This paper proposes an efficient hybrid approach for solving multi-objective optimization design of a compliant mechanism. The approach is developed by integrating desirability function approach, fuzzy logic system, adaptive neuro-fuzzy inference system, and Lightning attachment procedure optimization. Box–Behnken design is used to form a numerically experimental matrix. First, a refinement of design variables is conducted through analysis of variance and Taguchi approach in terms of considerably eliminating space of design variables and computation efforts. Next, desirability of two objective functions is computed and transferred into the fuzzy logic system. The output of fuzzy logic system is regarded as single combined objective function. Subsequently, a modeling for fuzzy output is developed via adaptive neuro-fuzzy inference system. Then, LAPO algorithm is adopted for solving the optimization problem. By investigating three different numerical examples, performance of the proposed approach is validated. Numerical results revealed that the proposed approach has a computational accuracy better than that of Taguchi-based fuzzy logic reasoning. Finally, case study 1 is chosen as an optimal solution for the mechanism. Furthermore, the effectiveness of proposed approach is greater than that of the Jaya algorithm and TLBO algorithm through Wilcoxon signed rank test and Friedman test. The proposed approach can be used for related engineering fields.

A FUZZY LOGIC APPROACH FOR DRONE CAPABILITY ANALYSIS ON DISASTER RISK ASSESSMENT

Abstract. The paper proposes a fuzzy logic approach for drone capability analysis on disaster risk assessment. In particular, a fuzzy logic model is designed as a hierarchical system with several inputs and one output. The system inputs corresponds to the linguistic variables, describing the of levels of the external and internal input factors, which determine the capability levels of analysed drone in respect to disaster risk assessment. As external input factors are used, for example: disaster type (flood, landslide, wildfire); weather conditions (wind speed, fog, cloud cover); operational area (urban, mountain, plain), etc. As internal input factors are considered the drone characteristics such as drone type, flight performance (stall speed, turn radius, flight endurance), payload capabilities (camera resolution, accuracy, weight, sensors), etc. The fuzzy logic system output gives the level of the drone capability on disaster risk assessment in defined conditions. The model is designed in Matlab computer environment using Fuzzy Logic Toolbox. Several computer simulations are carried out to validate the proposed model. The designed fuzzy logic model is part of an information system for disaster risk management using drones, which is under development.

Heuristic design of a fuzzy controller for a flexible robot

A ratio is identified as a heuristic to assist in designing fuzzy logic system (FLS) controllers with a low number of membership functions (MFs), high tracking precision, and fast execution time for the control of a two-link flexible space robot. Comparing simulation results for an FLS with three, five, seven, and nine triangular and Gaussian membership functions provides a combination of type and number of MF for optimal tracking control and execution time. Optimal control occurs when the ratio of the FLS output scaling gain to the number of MFs is equal to the output variable universe of discourse. The optimal FLS design is chosen with three triangular membership functions at an output scaling gain of 15, giving a design ratio of five and execution time of 1 min 40 s while tracking a square trajectory