SIMPLIFIED FUZZY INFERENCE RULE-BASED GENETICALLY OPTIMIZED HYBRID FUZZY NEURAL NETWORKS

2008 ◽  
Vol 16 (02) ◽  
pp. 245-274 ◽  
Author(s):  
BYOUNG-JUN PARK ◽  
WITOLD PEDRYCZ ◽  
SUNG-KWUN OH
Keyword(s):  
Neural Networks ◽  
Fuzzy Inference ◽  
Inference Rule ◽  
Least Square Method ◽  
Fuzzy Neural Networks ◽  
Least Square ◽  
Rule Based ◽  
Fuzzy Partition ◽  
Fuzzy Neural ◽  
Input Variables

In this study, we introduce an advanced architecture of genetically optimized Hybrid Fuzzy Neural Networks (gHFNN) and develop a comprehensive design methodology supporting their construction. A series of numeric experiments is included to illustrate the performance of the networks. The construction of gHFNN exploits fundamental technologies of Computational Intelligence (CI), namely fuzzy sets, neural networks, and genetic algorithms (GAs). The architecture of the gHFNNs results from a synergistic usage of the genetic optimization-driven hybrid system generated by combining Fuzzy Neural Networks (FNN) with Polynomial Neural Networks (PNN). In this tandem, a FNN supports the formation of the condition part of the rule-based structure of the gHFNN. The conclusion part of the gHFNN is designed using PNNs. We distinguish between two types of the simplified fuzzy inference rule-based FNN structures showing how this taxonomy depends upon the type of a fuzzy partition of input variables. As to the conclusion part of the gHFNN, the development of the PNN dwells on two general optimization mechanisms: the structural optimization is realized via GAs whereas in case of the parametric optimization we proceed with a standard least square method-based learning. To evaluate the performance of the gHFNN, we experimented with three representative numerical examples. A comparative analysis demonstrates that the proposed gHFNN come with higher accuracy as well as superb predictive capabilities when compared with other neurofuzzy models.

scholarly journals Auto-control of pumping operations in sewerage systems by rule-based fuzzy neural networks

2011 ◽  
Vol 15 (1) ◽  
pp. 185-196 ◽  
Author(s):  
Y.-M. Chiang ◽  
L.-C. Chang ◽  
M.-J. Tsai ◽  
Y.-F. Wang ◽  
F.-J. Chang
Keyword(s):  
Neural Networks ◽  
Fuzzy Inference ◽  
Fuzzy Neural Networks ◽  
Water Levels ◽  
Inference System ◽  
Rule Based ◽  
Pumping Stations ◽  
Fuzzy Neural ◽  
On Line ◽  
Model Efficiency

Abstract. Pumping stations play an important role in flood mitigation in metropolitan areas. The existing sewerage systems, however, are facing a great challenge of fast rising peak flow resulting from urbanization and climate change. It is imperative to construct an efficient and accurate operating prediction model for pumping stations to simulate the drainage mechanism for discharging the rainwater in advance. In this study, we propose two rule-based fuzzy neural networks, adaptive neuro-fuzzy inference system (ANFIS) and counterpropagation fuzzy neural network for on-line predicting of the number of open and closed pumps of a pivotal pumping station in Taipei city up to a lead time of 20 min. The performance of ANFIS outperforms that of CFNN in terms of model efficiency, accuracy, and correctness. Furthermore, the results not only show the predictive water levels do contribute to the successfully operating pumping stations but also demonstrate the applicability and reliability of ANFIS in automatically controlling the urban sewerage systems.

scholarly journals Auto-control of pumping operations in sewerage systems by rule-based fuzzy neural networks

2010 ◽  
Vol 7 (5) ◽  
pp. 6725-6756 ◽  
Author(s):  
Y.-M. Chiang ◽  
L.-C. Chang ◽  
M.-J. Tsai ◽  
Y.-F. Wang ◽  
F.-J. Chang
Keyword(s):  
Neural Networks ◽  
Fuzzy Inference ◽  
Fuzzy Neural Networks ◽  
Water Levels ◽  
Inference System ◽  
Rule Based ◽  
Pumping Stations ◽  
Fuzzy Neural ◽  
On Line ◽  
Model Efficiency

Abstract. Pumping stations play an important role in flood mitigation in metropolitan areas. The existing sewerage systems, however, are facing a great challenge of fast rising peak flow resulting from urbanization and climate change. It is imperative to construct an efficient and accurate operating prediction model for pumping stations to simulate the drainage mechanism for discharging the rainwater in advance. In this study, we propose two rule-based fuzzy neural networks, adaptive neuro-fuzzy inference system (ANFIS) and counterpropagatiom fuzzy neural network (CFNN) for on-line predicting of the number of open and closed pumps of a pivotal pumping station in Taipei city up to a lead time of 20 min. The performance of ANFIS outperforms that of CFNN in terms of model efficiency, accuracy, and correctness. Furthermore, the results not only show the predictive water levels do contribute to the successfully operating pumping stations but also demonstrate the applicability and reliability of ANFIS in automatically controlling the urban sewerage systems.

Prediction of Concrete Strength Using Fuzzy Neural Networks

2011 ◽  
Vol 243-249 ◽  
pp. 6121-6126 ◽  
Author(s):  
Jing Xu ◽  
Xiu Li Wang
Keyword(s):  
Neural Networks ◽  
Compressive Strength ◽  
Fuzzy Inference System ◽  
Fuzzy Inference ◽  
Concrete Strength ◽  
Fuzzy Neural Networks ◽  
Output Data ◽  
Inference System ◽  
Neuro Fuzzy ◽  
Fuzzy Neural

The purpose of this paper is to develop the Ⅰ-PreConS (Intelligent PREdiction system of CONcrete Strength) that predicts the compressive strength of concrete to improve the accuracy of concrete undamaged inspection. For this purpose, the system is developed with adaptive neuro－fuzzy inference system (ANFIS) that can learn cube test results as training patterns. ANFIS does not need a specific equation form differ from traditional prediction models. Instead of that, it needs enough input-output data. Also, it can continuously re-train the new data, so that it can conveniently adapt to new data. In the study, adaptive neuro－fuzzy inference system (ANFIS) based on Takagi-Sugeno rules is built up to prediction concrete strength. According to the expert experience, the relationship between the rebound value and concrete strength tends to power function. So the common logarithms of rebound value and strength value are used as the inputs and outputs of the ANFIS. System parameter sets are iteratively adjusted according to input and output data samples by a hybrid-learning algorithm. In the system, in order to improve of the ANFIS, condition parameter sets can be determined by the back propagation gradient descent method and conclusion parameter sets can be determined by the least squares method. As a result, the concrete strength can be inferred by the fuzzy inference. The method takes full advantage of the characteristics of the abilities of Fuzzy Neural Networks (FNN) including automatic learning, generation and fuzzy logic inference. The experiment shows that the average relative error of the predicted results is 10.316% and relative standard error is 12.895% over all the 508 samples, which are satisfied with the requirements of practical engineering. The ANFIS-based model is very efficient for prediction the compressive strength of in-service concrete.

Neuro-Fuzzy Systems Approaches

1999 ◽  
Vol 3 (3) ◽  
pp. 177-185 ◽  
Author(s):  
Danuta Rutkowska ◽  
◽  
Yoichi Hayashi ◽  
Keyword(s):  
Neural Networks ◽  
Fuzzy Systems ◽  
Transfer Functions ◽  
Fuzzy Inference ◽  
Back Propagation ◽  
Fuzzy Neural Networks ◽  
Nonparametric Approach ◽  
Neuro Fuzzy ◽  
Fuzzy Neural ◽  
Fuzzy Weights

Two major approaches to neuro-fuzzy systems are distinguished in the paper. The previous one refers to fuzzy neural networks, which are neural networks with fuzzy signals, and/or fuzzy weights, as well as fuzzy transfer functions. The latter approach concerns neuro-fuzzy systems in the form of multilayer feed-forward networks, which differ from standard neural networks, because elements of particular layers conduct different operations than standard neurons. These structures are neural network representations of fuzzy systems and they are also called connectionist models of fuzzy systems, adaptive fuzzy systems, fuzzy inference neural networks, etc. Two different defuzzifiers, applied to fuzzy systems, are in focus of the paper. Center-of-sums method is an example of parametric defuzzification. Standard neural networks a defuzzifier presents nonparametric approach to defuzzification. For both cases learning algorithms of neuro-fuzzy systems are proposed. These algorithms take a form of recursions derived based on the momentum back-propagation method. Computer simulation demonstrates a comparison between performance of neuro-fuzzy systems with the parametric and nonparametric defuzzifier. Truck backer-upper control problem has been used to illustrate the systems performance. Conclusions concerning the simulation results are summarized. The paper pertains many references on neuro-fuzzy systems, especially selected publications of Czogala, whom it is dedicated.

Sign in / Sign up

Export Citation Format

Share Document