Neuro-fuzzy Technique Research Articles

Neuro-fuzzy technique to predict air-overpressure induced by blasting

In addition to all benefits of blasting in mining and civil engineering applications, blasting has some undesirable impacts on surrounding areas. Blast-induced air-overpressure (AOp) is one of the most important environmental impacts of blasting operation which may cause severe damage to nearby residents and structures. Hence, it is a major concern to predict and subsequently control the AOp due to blasting. This paper presents an adaptive neuro-fuzzy inference system (ANFIS) model for prediction of blast-induced AOp in quarry blasting sites. For this purpose, 128 blasting operations were monitored in three quarry sites, Malaysia. Several models were constructed to obtain the optimum model in which each model involved five inputs and one output. Values of maximum charge per delay, powder factor, burden to spacing ratio, stemming length, and distance between monitoring station and blast face were set as input parameters to predict AOp. For comparison purposes, considering the same data, AOp values were predicted through the pre-developed artificial neural network (ANN) model and multiple regression (MR) technique. The results demonstrated the superiority of the ANFIS model to predict AOp compared to other methods. Moreover, results of sensitivity analysis indicated that the maximum charge per delay and powder factor and distance from the blast face are the most influential parameters on AOp.

Power system reconfiguration in a radial distribution network for reducing losses and to improve voltage profile using modified plant growth simulation algorithm with Distributed Generation (DG)

Abstract Network reconfiguration which is constrained non linear optimization problem has been solved for loss minimization, load balancing, etc. for last two decades using various heuristic search evolutionary algorithms like binary particle swarm optimization, neuro-fuzzy techniques, etc. The contribution of this paper lies in considering distributed generation which are smaller power sources like solar photovoltaic cells or wind turbines connected in the customer roof top. This new connection in the radial network has made unidirectional current flow to become bidirectional there by increasing the efficiency but sometimes reducing stability of the system. Modified plant growth simulation algorithm has been applied here successfully to minimize real power loss because it does not require barrier factors or cross over rates because the objectives and constraints are dealt separately. The main advantage of this algorithm is continuous guiding search along with changing objective function because power from distributed generation is continuously varying so this can be applied for real time applications with required modifications. This algorithm here is tested for a standard 33 bus radial distribution system for loss minimization and test results here shows that this algorithm is efficient and suitable for real time applications.

Plunging Flow Depth Estimation in a Stratified Dam Reservoir Using Neuro-Fuzzy Technique

The cold river water inflow often plunges below the ambient dam reservoir water and becomes density underflow through the reservoir. The hydrodynamics of density currents and plunging are difficult to study in the natural environment and laboratory condition due to small-scale, entrainment and turbulent flows. Numerical modeling of plunging flow and defining of the plunging depth can provide valuable insights for the dam reservoir sedimentation and water quality problem. In this study, an adaptive neuro-fuzzy (NF) approach is proposed to estimate plunging flow depth in dam reservoir. The results of the NF model are compared with two-dimensional hydrodynamic model, artificial neural network (ANN), and multi linear regression (MLR) model results. The two-dimensional model is adapted to simulate density plunging flow simulation through a reservoir with sloping bottom. The model is developed using nonlinear and unsteady continuity, momentum, energy and k-e turbulence model equations in the Cartesian coordinates. Density flow parameters such as velocity, plunging points, and plunging depths are determined from the simulation and model results. Mean square errors (MSE), mean absolute errors (MAE) and determination coefficient (R2) statistics are used as comparing criteria for the evaluation of the models’ performances. The NF model approach for the data yields the small MSE (1.18 cm), MAE (0.86 cm), and high determination coefficient (0.95–0.98). Based on the comparisons, it was found that the NF computing technique performs better than the other models in plunging flow depth estimation for the particular data sets used in this study.

Application of adaptive neuro-fuzzy technique to predict the unconfined compressive strength of PFA-sand-cement mixture

The paper addresses the application of an adaptive neuro-fuzzy (ANFIS) computing technique to predict the unconfined compressive strength of the pulverized fuel ash–cement–sand mixture. A series of unconfined compressive tests were performed on several mixtures of cement, pulverized fuel ash (PFA), and sand for checking and training data for the ANFIS network. Although some mathematical functions were applied to model the unconfined compressive strength of the construction materials, numerous setbacks of the models were observed. The artificial neural network (ANN) can be used as an analytical method for various prediction purposes because it provides the benefit of independency on the knowledge of internal system parameters, compressed compact solution in terms of multi-variable problems and rapid computation. The ANFIS is a particular class of the ANN family with attractive estimation and learning potentials. This provides a suitable platform when the analysis is aimed to counter the uncertainties in a system. The ANFIS RMSE was 0.0617 for prediction of the unconfined compressive strength of the pulverized fuel ash–cement–sand mixture.

Neuro-fuzzy modeling of Cu(II) and Cr(VI) adsorption from aqueous solution by wheat straw

In this study, an intelligent architecture-based neuro-fuzzy technique is used for the prediction of removal capacity of Cu(II) and Cr(VI) from aqueous solution using wheat straw as a biosorbent. The effect of operating parameters such as initial pH, temperature, contact time, straw particle size, and biosorbent’s chemical treatment are studied to optimize the conditions for maximum removal capacity. A large database is collected from the different carried out experiments to allow the modelization of the adsorption process. This process could be described using classical mathematical models such as Langmuir, Freundlich, or a hybrid model. However, the learnt neuro-fuzzy architecture with the obtained experimental data presents good correlation (R2=0.9999) and shows that the intelligent model is able to predict accurately the removal amount of Cu(II) and Cr(VI) from wheat straw under different conditions.

Economic lot sizing for unreliable production system with shortages

The purpose of the present study is to analyse the optimal lot size in an unreliable single-machine production system with shortages. The production system is subject to failure due to machine breakdown. Breakdown times are considered to be according to Weibull distribution. It is assumed that the shortages are allowed and backlogged. During each production, the set-up preventive (regular) maintenance is performed. The corrective (i.e., emergency) maintenance is carried out immediately after breakdown. For the illustration purpose, numerical results are provided for the special cases. To obtain the optimal cost per unit time, we also employ the artificial neuro-fuzzy inference system (ANFIS) approach which has the learning capability of neural network as well as advantages of rule-base fuzzy system. It is noted that the results obtained by neuro-fuzzy technique are at par with the results computed by the analytical techniques.

Computational Investigation of Aerodynamic Characteristics and Drag Reduction of a Bus Model

It is well-known that buses comprise an important part of mass transportation and that there are many types of buses. At present, the bus transportation is cheaper and easier to use than other means of transportation. However, buses have some disadvantages such as air pollution due to engine exhaust. This study is an attempt to reduce the gas emissions from buses by reducing the aerodynamic drag. Several ideas were applied to achieve this goal including slight modification of the outer shape of the bus. Thus, six different cases were investigated. A computational model was developed to conduct this study. It was found that reduction in aerodynamic drag up to 14% can be reached, which corresponds to 8.4 % reduction in fuel consumption. Also, Neuro-Fuzzy technique was used to predict the aerodynamic drag of the bus in different cases.

Compensation Control of Dissolved Oxygen in an Activated Sludge System via Hybrid Neuro Fuzzy Technique

Effective treatment of wastewater relies on a dissolved oxygen (DO) concentration level. Insufficient supply of the DO worsen the quality of the effluent (treated water) whereas too much high dissolved oxygen level maximizes energy consumption and cost. Therefore, DO control is highly crucial for economic, performance improvement as well as safety reasons. However, nonlinearities, influent fluctuations together with the time varying parameters of the system make DO control very difficult using classical control techniques. This paper presents compensation control of dissolved oxygen in the system based on hybrid neuro fuzzy technique. The performance of the proposed control algorithm is demonstrated by set-point tracking. For comparison a PID controller tuned using Zeigler-Nicholas method was used. The simulation results indicate that the proposed strategy is quite effective by tracking well the DO set-point trajectories. This kind of control strategy can be applied to real wastewater treatment system.

Artificial intelligence based approach to forecast PM2.5 during haze episodes: A case study of Delhi, India

Delhi has been listed as the worst performer across the world with respect to the presence of alarmingly high level of haze episodes, exposing the residents here to a host of diseases including respiratory disease, chronic obstructive pulmonary disorder and lung cancer. This study aimed to analyze the haze episodes in a year and to develop the forecasting methodologies for it. The air pollutants, e.g., CO, O3, NO2, SO2, PM2.5 as well as meteorological parameters (pressure, temperature, wind speed, wind direction index, relative humidity, visibility, dew point temperature, etc.) have been used in the present study to analyze the haze episodes in Delhi urban area. The nature of these episodes, their possible causes, and their major features are discussed in terms of fine particulate matter (PM2.5) and relative humidity. The correlation matrix shows that temperature, pressure, wind speed, O3, and dew point temperature are the dominating variables for PM2.5 concentrations in Delhi. The hour-by-hour analysis of past data pattern at different monitoring stations suggest that the haze hours were occurred approximately 48% of the total observed hours in the year, 2012 over Delhi urban area. The haze hour forecasting models in terms of PM2.5 concentrations (more than 50 μg/m3) and relative humidity (less than 90%) have been developed through artificial intelligence based Neuro-Fuzzy (NF) techniques and compared with the other modeling techniques e.g., multiple linear regression (MLR), and artificial neural network (ANN). The haze hour's data for nine months, i.e. from January to September have been chosen for training and remaining three months, i.e., October to December in the year 2012 are chosen for validation of the developed models. The forecasted results are compared with the observed values with different statistical measures, e.g., correlation coefficients (R), normalized mean square error (NMSE), fractional bias (FB) and index of agreement (IOA). The performed analysis has indicated that R has values 0.25 for MLR, 0.53 for ANN, and NF: 0.72, between the observed and predicted PM2.5 concentrations during haze hours invalidation period. The results show that the artificial intelligence implementations have a more reasonable agreement with the observed values. Finally, it can be concluded that the most convincing advantage of artificial intelligence based NF model is capable for better forecasting of haze episodes in Delhi urban area than ANN and MLR models.

Adaptive Neuro-Fuzzy Technique for Autonomous Ground Vehicle Navigation

This article proposes an adaptive neuro-fuzzy inference system (ANFIS) for solving navigation problems of an autonomous ground vehicle (AGV). The system consists of four ANFIS controllers; two of which are used for regulating both the left and right angular velocities of the AGV in order to reach the target position; and other two ANFIS controllers are used for optimal heading adjustment in order to avoid obstacles. The two velocity controllers receive three sensor inputs: front distance (FD); right distance (RD) and left distance (LD) for the low-level motion control. Two heading controllers deploy the angle difference (AD) between the heading of AGV and the angle to the target to choose the optimal direction. The simulation experiments have been carried out under two different scenarios to investigate the feasibility of the proposed ANFIS technique. The simulation results have been presented using MATLAB software package; showing that ANFIS is capable of performing the navigation and path planning task safely and efficiently in a workspace populated with static obstacles.

Application of Statistical and Intelligent Techniques for Modeling of Metallurgical Performance of a Batch Flotation Process

Froth flotation is one of the most frequently used processes for separation of valuable from gangue minerals. Modeling and simulation of the flotation process is a difficult task because of nonlinear and dynamic nature of the process. In this contribution, the relationship between the process variables (i.e., gas flow rate, slurry solids%, frother/collector dosages, and pH) and the metallurgical parameters (i.e., copper/mass/water recoveries and concentrate grade) in the batch flotation of a copper sulfide ore is discussed and modeled. Statistical (i.e., nonlinear regression) and intelligent (i.e., neural network and adaptive neuro-fuzzy) techniques are applied to model the process behavior at different conditions. The results indicate that intelligent approaches are more efficient tools for modeling of the complicated process like flotation, which are of central importance for development of the model-based control systems.

A multi-criteria recommendation system using dimensionality reduction and Neuro-Fuzzy techniques

Multi-criteria collaborative filtering (MC-CF) presents a possibility to provide accurate recommendations by considering the user preferences in multiple aspects of items. However, scalability and sparsity are two main problems in MC-CF which this paper attempts to solve them using dimensionality reduction and Neuro-Fuzzy techniques. Considering the user behavior about items' features which is frequently vague, imprecise and subjective, we solve the sparsity problem using Neuro-Fuzzy technique. For the scalability problem, higher order singular value decomposition along with supervised learning (classification) methods is used. Thus, the objective of this paper is to propose a new recommendation model to improve the recommendation quality and predictive accuracy of MC-CF and solve the scalability and alleviate the sparsity problems in the MC-CF. The experimental results of applying these approaches on Yahoo!Movies and TripAdvisor datasets with several comparisons are presented to show the enhancement of MC-CF recommendation quality and predictive accuracy. The experimental results demonstrate that SVM dominates the K-NN and FBNN in improving the MC-CF predictive accuracy evaluated by most broadly popular measurement metrics, F1 and mean absolute error. In addition, the experimental results also demonstrate that the combination of Neuro-Fuzzy and dimensionality reduction techniques remarkably improves the recommendation quality and predictive accuracy of MC-CF in relation to the previous recommendation techniques based on multi-criteria ratings.

Partial Discharge Localization in Power Transformers Using Neuro-Fuzzy Technique

Partial discharge (PD) is the most common sources of insulation failure in power transformers. The most important tools for quality assessment of power transformers are PD detection, measurement, and classification. As for the maintenance and repair of transformers, the major importance is the techniques for locating a PD source. The transfer function-based (TF) method for power transformers' winding in the high-frequency range is commonly used in power engineering applications, such as transient analysis, insulation coordination, and in transformer design. Although it is possible to localize PD in transformer winding using the transfer function (TF) method, this method cannot be used for transformers with no design data. Previous attempts toward finding a feature that localizes PD in transformers in general that lineate with PD location were found to be less successful. Therefore, in this paper, a neuro-fuzzy technique that uses unsupervised pattern recognition was proposed to localize PD source in power transformers. The proposed method was tested on a medium-voltage transformer winding in the laboratory. The results showed a significant improvement in localizing PD for major types of PD compared to currently available techniques, such as orthogonal transforms and the calibration line method.

A practical neuro-fuzzy model for estimating modulus of elasticity of concrete

The mechanical characteristics of materials are very essential in structural analysis for the accuracy of structural calculations. The estimation modulus of elasticity of concrete (<TEX>$E_c$</TEX>), one of the most important mechanical characteristics, is a very complex area in terms of analytical models. Many attempts have been made to model the modulus of elasticity through the use of experimental data. In this study, the neuro-fuzzy (NF) technique was investigated in estimating modulus of elasticity of concrete and a new simple NF model by implementing a different NF system approach was proposed. A large experimental database was used during the development stage. Then, NF model results were compared with various experimental data and results from several models available in related research literature. Several statistic measuring parameters were used to evaluate the performance of the NF model comparing to other models. Consequently, it has been observed that NF technique can be successfully used in estimating modulus of elasticity of concrete. It was also discovered that NF model results correlated strongly with experimental data and indicated more reliable outcomes in comparison to the other models.

Adaptive neuro-fuzzy inference system (ANFIS) applied for spectrophotometric determination of fluoxetine and sertraline in pharmaceutical formulations and biological fluid

The UV-spectrophotometric method of analysis was proposed for simultaneous determination of fluoxetine (FLX) and sertraline (SRT). Considering the strong spectral overlap between UV-Vis spectra of these compounds, a previous separation should be carried out in order to determine them by conventional spectrophotometric techniques. Here, full-spectrum multivariate calibrations adaptive neuro-fuzzy inference system (ANFIS) method is developed. Adaptive network based fuzzy inference system (ANFIS) is a neuro fuzzy technique where the fusion is made between the neural network and the fuzzy inference system that is a computational method. The experimental calibration matrix was constructed with 30 samples. The concentration ranges considered were 5-120 〖μg.mL〗^(-1) fluoxetine and 10-120 〖μg.mL〗^(-1) sertraline .Absorbance data of the calibration standards were taken between 200-300nm with UV-Vis spectrophotometer. The method was applied to accurately and simultaneously determine the content of pharmaceutical in several synthetic mixtures and real samples. Assaying various synthetic mixtures of the components validated the presented methods. Mean recovery values were found to be 101.26% and 100.24%, respectively for determination of FLX and SRT.

TVA generating unit modeling using MATLAB

In the present paper, the numerical evaluation of Markov model transient behavior is considered. It is focused on finding the transient-state probabilities of well-known four Tennessee Valley Authority (TVA) models. Three computational approaches are examined to find the three transient probabilities after modeling. These approaches are the Laplace Transforms, curve fitting and Neuro-Fuzzy. The MATLAB Simulink 7.10 package is used to obtain the transient state-probabilities for the four TVA models and at the same interval of time these solutions are reproduced by Laplace Transforms. For each model the three-state probabilities of the TVA models are derived. Each model is considered as a 3-state model, where its equations are obtained using the curve fitting and Neuro-Fuzzy techniques. All techniques used and applied in the present study are used to formulate and obtain the TVA models, where the Laplace Transforms is re-derived and re-used for a double check to model and obtain the results.

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.

Demand forecasting for apparel manufacturers by using neuro-fuzzy techniques

Purpose – According to literature research and conversations with apparel manufacturers' specialists, there is not any common analytic method for demand forecasting in apparel industry and to the authors' knowledge, there is not adequate number of study in literature to forecast the demand with adaptive network-based fuzzy inference system (ANFIS) for apparel manufacturers. The purpose of this paper is constructing an effective demand forecasting system for apparel manufacturers. Design/methodology/approach – The ANFIS is used forecasting the demand for apparel manufacturers. Findings – The results of the proposed study showed that an ANFIS-based demand forecasting system can help apparel manufacturers to forecast demand accurately, effectively and simply. Originality/value – ANFIS is a new technique for demand forecasting, combines the learning capability of the neural networks and the generalization capability of the fuzzy logic. In this study, the demand is forecasted in terms of apparel manufacturers by using ANFIS. The input and output criteria are determined based on apparel manufacturers' requirements and via literature research and the forecasting horizon is about one month. The study includes the real-life application of the proposed system, and the proposed system is tested by using real demand values for apparel manufacturers.

House selling price assessment using two different adaptive neuro-fuzzy techniques

Abstract It is of high importance to estimate the house selling prices because sellers and buyers need this information in an accurate way at time of sale. As a result of the fact that the estimation of the house prices is extorsive considerable research has been published in the literature on estimating house prices. This study covers the application of two different adaptive neuro-fuzzy (ANFIS) approaches for the estimation of house selling price. In this study, two different ANFIS models, namely ANFIS with grid partition (ANFIS-GP) and ANFIS with sub clustering (ANFIS-SC), were used in forecasting house prices, and the results were evaluated. Comparison of results from the two techniques indicated that the ANFIS-GP models performed better than the ANFIS-SC models. The study suggests that the ANFIS-GP technique can be successfully used in the estimation of house prices in the construction sector.

Adaptive Neural Fuzzy Inference System for Employability Assessment

Employability is potential of a person for gaining and maintains employment. Employability is measure through the education, personal development and understanding power. Employability is not the similar as ahead a graduate job, moderately it implies something almost the capacity of the graduate to function in an employment and be capable to move between jobs, therefore remaining employable through their life. This paper introduced a new adaptive neural fuzzy inference system for assessment of employability with the help of some neuro fuzzy rules. The purpose and scope of this research is to examine the level of employability. The concern research use both fuzzy inference systems and artificial neural network which is known as neuro fuzzy technique for solve the problem of employability assessment. This paper use three employability skills as input and find a crisp value as output which indicates the glassy of employee. It uses twenty seven neuro fuzzy rules, with the help of Sugeno type inference in Mat-lab and finds single value output. The proposed system is named as Adaptive Neural Fuzzy Inference System for Employability Assessment (ANFISEA).