## Designing Fuzzy Net Controllers using Genetic Algorithms (1995)

Venue: | IEEE Control Systems Magazine |

Citations: | 14 - 0 self |

### BibTeX

@ARTICLE{Kim95designingfuzzy,

author = {Jinwoo Kim and Yoonkeon Moon and Bernard P. Zeigler},

title = {Designing Fuzzy Net Controllers using Genetic Algorithms},

journal = {IEEE Control Systems Magazine},

year = {1995},

volume = {15},

pages = {66--72}

}

### Years of Citing Articles

### OpenURL

### Abstract

As control system tasks become more demanding, more robust controller design methodologies are needed. A Genetic Algorithm (GA) optimizer, which utilizes natural evolution strategies, offers a promising technology that supports optimization of the parameters of fuzzy logic and other parameterized non-linear controllers. This paper shows how GAs can effectively and efficiently optimize the performance of fuzzy net controllers employing high performance simulation to reduce the design cycle time from hours to minutes. Our results demonstrate the robustness of a GA-based Computer-Aided System Design methodology for rapid prototyping of control systems. Keywords: Genetic Algorithms; Fuzzy Logic Control; Oxygen Production System; Inverted Pendulum. Introduction Computer-Aided System Design (CASD) should support designing various functions of high autonomy systems[10], such as normal operation control, fault-tolerance, communication, planning and scheduling. Since conventional control schem...

### Citations

1809 |
Genetic algorithms in search, optimization, and machine learning
- Goldberg
(Show Context)
Citation Context ...evaluated individuals replace its parent individual if fitness is higher than that of its parent. The selection for new individual is performed based on roulette wheel:slot sized according to fitness =-=[6]-=-. Interaction of the FNC module with GA Optimizer Figure 4 shows the interconnection of the FNC, simulation model and GA optimizer. The FNC operates the simulation model of the target system to be con... |

434 | ANFIS: adaptive-network-based fuzzy inference system
- Jang
- 1993
(Show Context)
Citation Context ...y, fuzzy control processing can be viewed as a parallel neural network where each neuron represents a fuzzy membership function and each link represents the weight of a fuzzy rule. See the references =-=[7, 8] for-=- more detail explanation of fuzzy net controller. In our application, we employ a bell-shaped membership function with a maximum of 1 and minimum of 0, such as, ��A i (x) = 1 1+[( x\Gammac i a i )... |

420 |
Fuzzy logic in control systems: fuzzy logic controller - part I
- Lee
- 1990
(Show Context)
Citation Context ... plants. Fuzzy Net Control Systems The basic idea of fuzzy control centers around the labeling process, in which the reading of a sensor is translated into a label as done by human expert controllers =-=[5]-=-. With expert supplied membership functions for labels, sensor readings can be fuzzified and through fuzzy logic eventually defuzzified to generate analog control commands. It is important to note tha... |

123 | Serial and parallel genetic algorithms as function optimisers
- Gordon, Whitley
- 1993
(Show Context)
Citation Context ...ms where each experiment requires a simulation can be very time consuming. Therefore, we developed new forms of GA which are especially oriented to simulation-based optimization on parallel computers =-=[2, 11]-=-. Asynchronous Genetic Algorithms in High Performance Simulation Environments The GA is a probabilistic algorithm which maintains a population of individuals, P (t) = x 1 (t); . . . ; x n (t) for iter... |

65 | Self-learning fuzzy controller based on temporal back propagation
- Jang
- 1992
(Show Context)
Citation Context ...y, fuzzy control processing can be viewed as a parallel neural network where each neuron represents a fuzzy membership function and each link represents the weight of a fuzzy rule. See the references =-=[7, 8] for-=- more detail explanation of fuzzy net controller. In our application, we employ a bell-shaped membership function with a maximum of 1 and minimum of 0, such as, ��A i (x) = 1 1+[( x\Gammac i a i )... |

34 |
Genetic algorithms in Controller Design and Tuning
- Varsek, Filipic
- 1993
(Show Context)
Citation Context ...ver, the parallel scheme affords a straightforward basis for GA optimization. Recently there has been research in developing well-performing fuzzy membership functions without help of human expertise =-=[1]-=-. To do this, it is necessary to employ computer-aided optimization. Tuning the membership functions requires adjusting many parameters simultaneously and is difficult to do manually. As indicated bef... |

7 |
Asynchronous genetic algorithms on parallel computers
- Zeigler, Kim
- 1993
(Show Context)
Citation Context ...ms where each experiment requires a simulation can be very time consuming. Therefore, we developed new forms of GA which are especially oriented to simulation-based optimization on parallel computers =-=[2, 11]-=-. Asynchronous Genetic Algorithms in High Performance Simulation Environments The GA is a probabilistic algorithm which maintains a population of individuals, P (t) = x 1 (t); . . . ; x n (t) for iter... |

4 |
Genetic Algorithm + Data Structure = Evolution Programming
- Miachalewicz
- 1992
(Show Context)
Citation Context ...modality, and non-linear constraints which wreak havoc on gradient-based direct search methods. A genetic algorithm (GA) is a parallel, global search technique that emulates natural genetic operations=-=[12]-=-. Because it simultaneously evaluates many points in the parameter space, it is more likely to converge toward the global solution. It need not assume that the search space is differentiable or contin... |

3 |
Event-based Fuzzy Logic Control System
- Zeigler, Kim
- 1993
(Show Context)
Citation Context ...], the links between layers 3 and 4 in our fuzzy net controller are not fixed. These links represent consequents of fuzzy rules which could be optimized by GA. While an earlier Fuzzy Logic Controller =-=[3]-=- was implemented in rule-based (if-then) form, the current FNC employs a parallel inferencing network structure. Due to such parallelization, the FNC can provide better real-time performance. Moreover... |

3 |
Hierarchical, Asynchronous Parallel Genetic Algorithms For Simulation-Based System Design
- Kim
- 1994
(Show Context)
Citation Context ...n-linear controllers. The results reported here show how the GA optimizer for the FNC affords more reliability in global optimization than does an adaptive neural net approach [7]. Our subsequent work=-=[9]-=- has developed new techniques for GA/simulation-based design including a) the intentional use of noise to more efficiently sample continuous parameter spaces, and b) a hierarchical architecture that e... |

1 |
High Performance Parallel Genetic Algorithms for System Optimization: Performance Prediction and Verification on the Massively Parallel CM-5", submitted to IEEE Expert
- Zeigler, Kim
(Show Context)
Citation Context ... was tested with various test functions [2]. Recently, the scheme was ported to the CM-5 massively parallel computer. The performance benefits predicted by simulation were remarkably well corroborated=-=[4]-=-. Figure 3 shows the operation of Asynchronous Genetic Algorithms in Connection Machine Simulation Process GA_Controller (new individual, fitness) GA_agent (processing nodes) (control processor) Gene-... |

1 |
High Autonomy
- Schooley, Cellier, et al.
- 1993
(Show Context)
Citation Context ...netic Algorithms; Fuzzy Logic Control; Oxygen Production System; Inverted Pendulum. Introduction Computer-Aided System Design (CASD) should support designing various functions of high autonomy systems=-=[10]-=-, such as normal operation control, fault-tolerance, communication, planning and scheduling. Since conventional control schemes are limited in their range of practical applications, Fuzzy Logic Contro... |