Fuzzy Inference Method Research Articles

Efficiency of Equipment State Assessment System Implementation

The article is concerned with problems of modern power industry in Russia in the context of technical state assessment of power plants and substations' equipment. Operations algorithm of automated model implemented with the use of Takagi-Sugeno fuzzy inference method are presented in the article. Performance analysis of implementation of automated system of equipment actual state assessment in toolset of power plants maintenance services was performed.

An Approach to Composition Based MISO Algorithms for Fuzzy Inference Schemes Based on the View of Weighted Information

In this article, we will construct multiple-input, single-output (MISO) algorithms for fuzzy inference schemes based on the techniques of aggregation of weighted information. First, by an example, we examine various aspects of a crisp discrete multivariable function under fuzzy environment and obtain many its new functional representations. Next, following the merits of such representations, we build four classes of (new) composition based MISO algorithms as a realization of fuzzy interpolation (extension) of the previous new functional representations, in which, the class of Mamdani-type MISO algorithms are rediscovered. Finally, as an application, we provide an alternative approach to the equivalence conditions of some fuzzy inference methods issued by Seki and Mizumoto recently. In Seki and Mizumoto's approach, they showed that three widely used as fuzzy control methods— the product-sum-gravity method, the simplified fuzzy inference method and the fuzzy singleton- type inference method, are equivalent to each other; and obtained some equivalence conditions between these three methods with two other fuzzy inference methods, while in our approach, we show that all these fuzzy inference methods are closely related with a MISO algorithm of specific type.

KNOWLEDGE-ORIENTED TECHNOLOGIES IN HIGHLY AUTOMATED PRODUCTION

The expansion of Zadeh-Mamdani method in problems of fuzzy inference on knowledge is considered. A modified method of fuzzy inference is proposed and justified. The proposed method is based on interpretation of components of fuzzy Petri nets as production rules and solving of logical equations in the state space of membership functions of the model, followed by their defuzzification. The process of perceptron learning as procedure of adjusting the weights and shifts to decrease the difference between target and real signals on its output, using a definite tuning (learning) rule is defined. Modified methods of gradient procedures based on the method of back-propagation for multilayer neural networks are developed. Application of the proposed approaches based on advanced hybrid models with solving the problems of fuzzy inference and operative informed decision making allowed to reduce the time to identify, locate and eliminate the causes of failure on the set of alternatives, which is confirmed by experiment. The method appears to be universal in decision-making problems and allows to increase the adequacy of hybrid model and the accuracy of decisions.

Simulink Simulation of<i> </i>Fuzzy-PID Algorithm and its Application in the Servo Drive System Based on Fuzzy PID Controller

In this paper, based on fuzzy PID controller, a fuzzy inference method is utilized to realize automatic regulating PID parameter, and the application of the controller in motion control system is studied with Matlab Simulink. The results of simulation indicate that the cont roller gives a good control performance and has a high reference value for further applications..

A weighted CREAM model for maritime human reliability analysis

Human error can be regarded as a significant factor contributing to marine accidents. Crew onboard vessels often perform duties in circumstances where technological, environmental and social factors emerge which may contribute to the occurrence of human failures. Fuzzy Cognitive Reliability and Error Analysis Methods (CREAM) is one of the most recognized HRA methods capable of tackling such difficulties. However, shortcomings are still disclosed and weaken the applicability of such an approach. These include the lack of considering input weights, the dubitation of the logicality of adopting rule base approaches to evaluate the relations between inputs and output and the loss of useful information due to the application of min–max fuzzy inference method. A new fuzzy CREAM methodology capable of resolving the aforementioned difficulties is proposed based on a rule base approach. The framework is validated using two axioms and demonstrated by virtue of an oil tanker example. The results are consistent with the principles evolved from the axioms since the outcomes are sensitive to the minor alterations of input data and weights. It is concluded that the weighted CREAM model is able to produce reliable human performance failure results and the strengths will not be compromised even if applied in circumstances where membership function shapes of fuzzy sets are various from traditional studies.

A new approach for improving the performance of freight train timetabling of a single-track railway system

A new approach for improving the performance of freight train timetabling for single-track railways is proposed. Using the idea of a fixed-block signaling system, we develop a matrix representation to express the occupation of inter- and intra-station tracks by trains illustrating the train blocking time diagram in its entirety. Train departure times, dwell times, and unnecessary stopping are adjusted to reduce average train travel time and single train travel time. Conflicts between successive stations and within stations are identified and solved. A fuzzy logic system is further used to adjust the range of train departure times and checks are made to determine whether dwell times and time intervals can be adjusted for passenger and freight trains at congested stations to minimize train waiting times. By combining manual scheduling expertise with the fuzzy inference method, timetable efficiency is significantly improved and becomes more flexible.

Розробка методу оцінки небезпеки зсувів на ділянках автомобільних доріг в умовах нечіткої інформації

Factors of landslide hazard on areas of highways have been analyzed. The main steps of fuzzy inference method are described. The method of landslide hazard assessment on areas of highways in terms of fuzzy information has been developed. The example of landslide hazard assessment on areas of highways in terms of fuzzy information in Matlab has been provided.

Adaptive Fault Diagnosis Method Based on FNN

In complex manufacturing, the system parameters have dynamic and nonlinear characters. Existing parameters setting methods show low efficiency and accuracy, and some setting experience accumulated in engineering practice can not be fully used. Therefore, an online parameter setting method with improved adaptive neuro-based fuzzy inference model is proposed in this paper. The advantages of ANFIS in self-learning and fuzzy inference method of fuzzy mathematics are combined effectively to determine the fuzzy rules and fuzzy membership. Then the neural network predictor is introduced to enhance the adaptive ability and nonlinear approximation ability of fuzzy neural network. The parameters and the structure of fuzzy rules are regulated and updated by the nearest neighbor clustering algorithm, which improves the accuracy of fuzzy inference and enhances the fault-tolerance and robustness of system. In our experiments, by the simulations of transformer fault diagnosis and soldering technology, we find improved ANFIS model can better reflect the actual operating state of transformer and it can make modeling and control for nonlinear I/O system in the manufacturing process like soldering. The improved system is also proved by experiments to have better performance in robustness and convergence.

A Weather-Based Hybrid Method for 1-Day Ahead Hourly Forecasting of PV Power Output

To improve real-time control performance and reduce possible negative impacts of photovoltaic (PV) systems, an accurate forecasting of PV output is required, which is an important function in the operation of an energy management system (EMS) for distributed energy resources. In this paper, a weather-based hybrid method for 1-day ahead hourly forecasting of PV power output is presented. The proposed approach comprises classification, training, and forecasting stages. In the classification stage, the self-organizing map (SOM) and learning vector quantization (LVQ) networks are used to classify the collected historical data of PV power output. The training stage employs the support vector regression (SVR) to train the input/output data sets for temperature, probability of precipitation, and solar irradiance of defined similar hours. In the forecasting stage, the fuzzy inference method is used to select an adequate trained model for accurate forecast, according to the weather information collected from Taiwan Central Weather Bureau (TCWB). The proposed approach is applied to a practical PV power generation system. Numerical results show that the proposed approach achieves better prediction accuracy than the simple SVR and traditional ANN methods.

Free vibration control of smart composite beams using particle swarm optimized self-tuning fuzzy logic controller

This paper deals with active free vibrations control of smart composite beams using particle-swarm optimized self-tuning fuzzy logic controller. In order to improve the performance and robustness of the fuzzy logic controller, this paper proposes integration of self-tuning method, where scaling factors of the input variables in the fuzzy logic controller are adjusted via peak observer, with optimization of membership functions using the particle swarm optimization algorithm. The Mamdani and zero-order Takagi–Sugeno–Kang fuzzy inference methods are employed. In order to overcome stability problem, at the same time keeping advantages of the proposed self-tuning fuzzy logic controller, this controller is combined with the LQR making composite controller. Several numerical studies are provided for the cantilever composite beam for both single mode and multimodal cases. In the multimodal case, a large-scale system is decomposed into smaller subsystems in a parallel structure. In order to represent the efficiency of the proposed controller, obtained results are compared with the corresponding results in the cases of the optimized fuzzy logic controllers with constant scaling factors and linear quadratic regulator.

PID Parameter Fuzzy Self-Tuning of the Motion Control System

In the motion control system, the fuzzy self-tuning of PID parameter is the combination of fuzzy control strategy and traditional PID control, and it is an effective method to improve the control precision. The paper discussed the principle of fuzzy self-adapted PID controller and the parameter fuzzy adjustment, and it realized self-tuning online of PID parameter for the motion control system by using a fuzzy inference method, and the controller was simulated in application of motion control system under the environment of Matlab/Simulink. The simulation result indicated the self-adaptive PID controller enable the motion control system to achieve the satisfied effect.

Fuzzy estimation for heat flux distribution at the slab continuous casting mold surface

A fuzzy inference method for estimating the heat flux distribution at the metal-mold interface in slab continuous casting is established in this paper. The finite element method is applied to solve the direct heat conduction problem. A set of decentralized fuzzy inference units are established, and the deviations between the calculated and measured temperatures acquired with the thermocouples buried in the mold are taken as the input parameters of fuzzy inference units, and the corresponding inference components are obtained by fuzzy inference. Then the inference components are weighted and synthesized by a weighted integrated approach based on normal distribution function to gain the compensations of the guessed heat flux distribution. Finally, a decentralized fuzzy inference (NDFI) method based on normal distribution weighted approach is formed. Some numerical experiments are performed to study the effects of the number of temperature sensors, different initial guesses of heat flux distribution and measurement errors on the reversion results. Comparisons with both the existing decentralized fuzzy inference (DFI) method and the conjugate gradient method (CGM) are also conducted, and they all show the validity of the inversion method established in this paper.

Evaluation of Enterprise Performance Based on FLI-GA Model

Purpose: There are many kinds of methods to evaluate the performance of enterprise, but they still have some distinct shortcomings. In order to achieve a better evaluation result, we put forward a new model named F LI- G A (Fuzzy logic inference & Genetic algorithm). A pproach: This model , mainly based on the fuzzy logic inference method, uses fuzzy rule-based system (FRBS) to avoid the drawbacks of FRBS . G enetic algorithm is applied in this model. Findings: FLI-GA model can be used to evaluate certain enterprise performance, and its evaluation results are more accurate than fuzzy logic inference method. Originality: T his model combines the genetic algorithm with the unclear reasoning methods so as to make the appraisal results more reasonable and more satisfying.

Neuro-fuzzy techniques to optimize an FPGA embedded controller for robot navigation

This paper describes how low-cost embedded controllers for robot navigation can be obtained by using a small number of if-then rules (exploiting the connection in cascade of rule bases) that apply Takagi–Sugeno fuzzy inference method and employ fuzzy sets represented by normalized triangular functions. The rules comprise heuristic and fuzzy knowledge together with numerical data obtained from a geometric analysis of the control problem that considers the kinematic and dynamic constraints of the robot. Numerical data allow tuning the fuzzy symbols used in the rules to optimize the controller performance. From the implementation point of view, very few computational and memory resources are required: standard logical, addition, and multiplication operations and a few data that can be represented by integer values. This is illustrated with the design of a controller for the safe navigation of an autonomous car-like robot among possible obstacles toward a goal configuration. Implementation results of an FPGA embedded system based on a general-purpose soft processor confirm that percentage reduction in clock cycles is drastic thanks to applying the proposed neuro-fuzzy techniques. Simulation and experimental results obtained with the robot confirm the efficiency of the controller designed. Design methodology has been supported by the CAD tools of the environment Xfuzzy 3 and by the Embedded System Tools from Xilinx.

Prediction of Conductivity by Adaptive Neuro-Fuzzy Model

Electrochemical impedance spectroscopy (EIS) is a key method for the characterizing the ionic and electronic conductivity of materials. One of the requirements of this technique is a model to forecast conductivity in preliminary experiments. The aim of this paper is to examine the prediction of conductivity by neuro-fuzzy inference with basic experimental factors such as temperature, frequency, thickness of the film and weight percentage of salt. In order to provide the optimal sets of fuzzy logic rule bases, the grid partition fuzzy inference method was applied. The validation of the model was tested by four random data sets. To evaluate the validity of the model, eleven statistical features were examined. Statistical analysis of the results clearly shows that modeling with an adaptive neuro-fuzzy is powerful enough for the prediction of conductivity.

Estimating thermal boundary conditions of boiler membrane water-wall using decentralized fuzzy inference with sensitivity weighting

The thermal boundary conditions including the fireside heat flux, temperature of water–steam mixture in water-wall tubes and heat transfer coefficient on the inner surface of membrane water-wall, are estimated at the same time using the decentralized fuzzy inference (DFI) method with the sensitivity weighting based on the local measured temperature on the back of membrane water-wall. The influences of different initial guessed thermal boundary conditions, the measurement points, and the temperature measurement errors on the estimated results are discussed, and comparisons with the conjugate gradient method (CGM) are conducted. The study shows that the thermal boundary conditions of membrane water wall, the temperature distribution on the fireside and the positions of the dangerous points can be determined more accurately by the proposed method. It is concluded that DFI method with the sensitivity weighting is of better anti ill-posed characteristic. It would provide necessary basis for analyzing and monitoring the operation state of power plant boilers.

Fuzzy inference method for material loss and cost estimation under uncertainty: A case study of wooden product manufacturing

Wood is a natural derivative, it possesses randomly distributed inherent defects all over its mass. This complicates the cost estimation process; data collected showed that even planks with similar defect pattern would have different percentage of material loss. Such uncertain loss was caused by changes in cutting parameters. In this study, a Fuzzy Inference (FI) method was employed to predict wood loss in a rubber wooden toy manufacturing cutting process. Notable variables are: length of cut, and area of cut. Prediction accuracy from the FI method was compared with that of other alternative methods. Common practice assumes a constant defective proportion, resulting in inaccurate cost estimation. A regression equation allows the loss to be varied by the cutting parameters; but only one parameter was found to be significant. Experimental results show that the FI method greatly outperformed regression and conventional methods. These findings emphasize the influence of cutting parameters on product cost. Accurate cost estimation enables better planning for efficient pricing strategies and enhances business competitiveness.

The fuzzy mapping aggregation operator based on rimer and its application

AbstractA fuzzy mapping aggregation operator based on RIMER and its application in Chinese word semantic proofing system for special domain are discussed deeply in this paper. Firstly, the fuzzy mapping aggregation operator based on RIMER are introduced and followed by the corresponding fuzzy inference method. Secondly, the collection of the sensitive words and their substitutions and the soft inference are discussed mainly based on our previous achievements. Then the new flowchart of the semantic analysis and the bases and the modules in the Chinese word proofing system are illustrated subsequently. The experiment shows that it is more feasible and practical method for semantic analysis.

A Hybrid Grey Based KOHONEN Model and Biogeography-Based Optimization for Project Portfolio Selection

The problem of selection and the best option are the main subject of operation research science in decision-making theory. Selection is a process that scrutinizes and investigates several quantitative and qualitative, and most often incompatible, factors. One of the most fundamental management issues in multicriteria selection literature is the multicriteria adoption of the projects portfolio. In such decision-making condition, manager is seeking for the best combination to build up a portfolio among the existing projects. In the present paper, KOHONEN algorithm was first employed to build up a portfolio of the projects. Next, each portfolio was evaluated using grey relational analysis (GRA) and then scheduled risk of the project was predicted using Mamdani fuzzy inference method. Finally, the multiobjective biogeography-based optimization algorithm was utilized for drawing risk and rank Pareto analysis. A case study is used concurrently to show the efficiency of the proposed model.

The Construction Protest Management Study with NIMBY Conflict

Conflicts often occur with public facility construction. In sociology terms, the factor caused opposite opinions and flights from neighborhood people called NIMBY (Not In My Back Yard) phenomenon. Although NIMBY has been mentioned and discussed in lots of related researches, but there is no particular one to focus on making NIMBY phenomenon into quantization based on construction job-site interface. In this study, the Wastewater Sewer System construction project has been taken as a real case to find main factors caused NIMBY phenomenon and then makes the affiliated NIMBY phenomenon into quantization. The Wastewater Sewer System construction project is taken as the demonstration case due to wastewater facility belong to low accepting and high NIMBY within all public construction projects. In this study, the questionnaire and consulting survey are made to investigate the professional opinions of experts of sewer system facility and NIMBY response of citizens. The questionnaire is designed by fuzzy linguistic scale and quantized by Fuzzy Delphi Method. Then mainly factors caused NIMBY phenomenon and corresponding improvement measures are derived by the result of questionnaires and anti-NIMBY self-check list which can be established and used in daily process at construction job-site. This research develops NIMBY curves to estimate the NIMBY affection of citizens under the unsure circumstance of noise, air and water pollution with sewer system construction. Also the fuzzy rule base can be discovered by predicting NIMBY affection under the various violence of noise, air and water pollution in Fuzzy Inference Method. The anti-NIMBY self-check list for sewer system construction developed by this study can be used for examining the factor caused NIMBY and finding corresponding improvement measures in pre-construction period and construction period for managing workers at construction field. During construction period, the NIMBY Conflict Index system calculated from fuzzy rule based on NIMBY affection can be executed persistently to control NIMBY affection to avoid NIMBY conflict events happened.