Artificial Neuro-fuzzy Inference Systems Research Articles

Generic compressive strength prediction model applicable to multiple lithologies based on a broad global database

In this study, we present a global database of ten parameters, which include measurements of rock index properties, strength stiffness and dynamic properties. Hoek–Brown constant mi, is included, and was estimated, using Hoek and Brown proposed guidelines for determining mi values for different rock types that can be used for preliminary design when triaxial tests are not available. This broad database is compiled from 96 studies and is labelled as “ROCK/10/4025”, to describe the type of geomaterial, the number of the parameters, and the number of the data samples included. It consists of 35.4 % igneous, 54.8 % sedimentary, and 9.2% metamorphic rocks. The purpose of this paper is to propose a generic soft computing model applicable to multiple lithologies, that can become more reliable and perhaps more suitable for a specific site study when used in order to densify often limited similar site-specific data. To this end four broad samples of data were selected, and served as training data sets for developed machine learning models, to develop a generic compression strength prediction model applicable to multiple lithologies. The suggested algorithms in this study are Back-Propagation Artificial Neural Networks, Artificial Neuro-Fuzzy Inference Systems, Support Vector Machines, Nearest Neighbour classifiers and Ensemble Bagged Trees. According to the findings of this study, Artificial Neuro-Fuzzy Inference Systems model performance was found to be marginally superior, while Back Propagation Artificial Neural Networks, Support Vector Machines and Ensemble Bagged Trees models were found to have good performance. Constant mi seems to be an important training parameter when training predictive models centred on data from multiple lithologies. As a result, we can suggest that these models are powerful tools that allow for a reliable estimation of compressive strength, based on the performance indicators. The performance was found to be 70%–82% when the problem of compressive strength prediction was approached as a classification problem (that is successful prediction of class from very weak to very strong), and 80%–96% when solved as a function approximation problem.

Investigations on mechanical and wear behaviour of graphene and zirconia reinforced AA6061 hybrid nanocomposites using ANN and Sugeno-type fuzzy inference systems

This research work investigates the mechanical and wear behaviour of graphene (C) and zirconium di-oxide (ZrO2) reinforced Aluminium alloy 6061 hybrid nano composites (AMMHNCs) fabricated by ultrasonic-assisted stir casting method. Graphene and ZrO2 are selected as reinforcements for increasing the wear resistance and hardness of the base alloy AA6061. The mixing proportions of graphene and ZrO2 reinforced with AA6061 in weight are 100% AA6061/0% Graphene/0% ZrO2, 98.5% AA6061/0.5% Graphene/1% ZrO2, 97.5% AA6061/0.5% Graphene/2% ZrO2, 98% AA6061/1% Graphene/1% ZrO2, 97% AA6061/1% Graphene/2% ZrO2. Microstructural study was carried out using optical and scanning electron microscopic images to analyse the dispersion of reinforcements in the composite. The results shown that, ultrasonic-assisted stir casting method improves the uniformity in dispersion of reinforcements. The hardness, tensile, impact and wear test were carried out based on ASTM standards to analyse the properties in the proposed composite specimens. It was observed that, the hardness, tensile strength and impact strength are increases by 21.88%, 69.42% and 78.57% respectively and percentage elongation is decreased by 63.52% with the increase of reinforcements. Wear resistance increases with the increase of reinforcements. In order to analyse the wear behaviour originality of new composite under wear test parameters, Artificial Neural Network (ANN) and Artificial Neuro Fuzzy Inference Systems (ANFIS) models were used to predict the wear rate for experimented and non-experimented parameters. The prediction analysis was useful in studying the wear behaviour of the composite. Comparative analysis for ANN and ANFIS was performed and the results shown that, ANFIS model predicted with accuracy of R2 with 99.9%.

Application of Artificial Intelligence to Estimate Oil Flow Rate in Gas-Lift Wells

Optimization and monitoring schemes for oil well and reservoir system require accurate estimation of production rate. Real-time monitoring is conducted typically using flow transmitters that contain their own inherent uncertainties due to flow of multiple fluids. Because of these limitations, industrial practices involve the usage of wellhead conditions and intermittent well test data to estimate well flow rates through certain established correlations such as Gilbert’s empirical model. These correlations, however, have become ineffective due to inadequate well test data and associated operational and cost-intensive commitments. The main objective of this work was to utilize artificial intelligence (AI) techniques to develop robust correlation to predict oil rates in gas-lift wells. The AI techniques implemented in this study are artificial neural network (ANN), artificial neuro-fuzzy inference systems, support vector machines, and functional networks. In addition, ANN was used to develop physical equation to predict oil flow rate. Separator test dataset from multiple wells of an oil field operating on continuous gas lift was collected. Extensive data analytics were performed before feeding it in the algorithms. The inputs consisted of only the easily available surface parameters. All the developed AI models were compared among themselves as well as with conventionally used empirical models. The comparison was conducted based on average absolute error percentage and coefficient of determination. The newly developed AI model can predict oil rates with accuracy exceeding 98% that is extremely efficient, and examples of such results have not been reported previously.

Prediction of life of piercing punches using artificial neural network and adaptive neuro fuzzy inference systems

Predicting the life of piercing punch is one of the major concerns in the design of compound dies. Finite element analysis is performed to determine the maximum and minimum principal stresses through which fatigue limit of punch is estimated. The factors affecting the life of punch are examined and a mathematical model is established using artificial neural network (ANN) and adaptive neuro fuzzy inference systems (ANFIS). The developed model is utilised to evaluate the life of punch for varied load conditions. Comparative evaluation of ANN and ANFIS results suggested that the later model is superior in predicting the life of punch and it can be effectively utilised in machine tool applications.

Neuro-Fuzzy Modelling of the Metallic Surface Characterization on Linear Dry Contact between Plastic Material Reinforced with SGF and Alloyed Steel.

This paper presents the modelling of wear data resulting from linear dry contact using artificial neural networks (ANN) and adaptive neuro-fuzzy inference systems (ANFIS) with the aim of constructing predictor models for the depth and volume of the wear scar, with great impact in the characterization of new industrial processes utilizing existing materials. The dataset is the result of laboratory testing, presenting both numerical and categorical variables whose inclusion into the model allows for a number of possibilities. The width of the wear scar was measured on a microscope, and its depth was calculated. A multitude of experimental tests was performed with normal loads and different speeds, which led to some conclusive results, but in some cases, with relatively high variance. Various options for the automatic generation of fuzzy inference systems were also approached (genfis2). The innovative approach was compared with a baseline model featuring multivariate linear regression optimized using gradient descent, drawing on previous experimentation on the same dataset. The models developed can be implemented in future research and in practical applications under similar conditions, aiming to optimize performance by applying Computer Science. The obtained results lead to highly accurate prediction models which are further integrated into various metallic surface characterizations in the wear process for tribological and robotics research in new industrial processes using short glass fiber reinforced polymers.

A filtering of message in online social network using hybrid classifier

In emerging trend of society based on online social networking (OSN), it is useful for associative with social relationship. It is mainly used to share all moments via messages with their private and public sector. In this social network, most of the people used to send indecent text to others. So, non-essential text will be neglected from user to view desirable messages on their OSN walls. This paper explores the use of short text classifier includes latent semantic analysis for extracting meaningful text to present on their user wall by preventing useless messages. The proposed algorithm concerns hybrid combination of text classifiers such as support vector machine SVM–ELM, SVM–NAIVE, NAIVE–ELM, and NAIVE–artificial neuro-fuzzy inference systems. Comparative study of these techniques contributes which will gives higher prediction accuracy in evaluation process.

Using ANFIS and Neural Networks to Predict the Volume Percentage of Matrix and Fluid

In the common methods to find percentage of lithology and fluids, well log information, petrophysical tests, and high-skill experts are needed. Therefore, designing a model that is able to evaluate the percentage of lithology using well log data without laboratory information will be very economical. Today, by using artificial neural networks, lithology can be predicted very well from the lowest information and time. Various artificial neuro-fuzzy inference systems and radial basis function and back propagation neural network were implied (about 1,500 accredited data and evaluated lithology and fluid volume percentages were available). In this article, first several kinds of features tested by artificial neuro-fuzzy inference systems model and finally neutron porosity (NPHI), conductive log (CT), resistivity log (RT), density (RHOB), natural gamma (GR), and photo electron (PE) logs were determined as the best logs to predict the percentage of lithology and fluid’s volume. Then these logs were used as input variable for radial basis function and back propagation neural network. In the second optimization, several training functions were implemented to select the best structure by lowest error. Comparison between targets and a network’s output data shows that neural networks are suitable tools for predicting the percentage of lithology and fluid’s volume, consuming less time and reducing cost.

Comparative Modeling and Analysis of the Mass Transfer Coefficient in a Turbulent Bed Contactor using Artificial Neural Network and Adaptive Neuro-Fuzzy Inference Systems

This study deals with predicting the gas film volumetric mass transfer coefficient (Koga) in a turbulent bed contactor (TBC), using both artificial neural network (ANN) and adaptive neuro-fuzzy inference system (ANFIS) techniques. The networks have been trained and evaluated with the experimental data available in the literature. Input variables to the networks are process variables such as gas and liquid phase concentration, gas and liquid superficial velocities and also specific area of packings. The results obtained the ability of developed ANN and ANFIS for prediction of Koga. Although it was observed that both ANN and ANFIS models provided a good statistical prediction in terms of coefficient of determination (R2), mean relative error (MRE) and root mean square error (RMSE), the accuracies of ANFIS predictions were better than those of ANN predictions.

Adaptive voltage regulation of self excited induction generator using FACTS controllers

This paper introduces an adaptive terminal voltage regulation of a standalone self excited induction generator using flexible AC transmission systems (FACTS). FACTS in the form of static VAR compensator (SVC) is introduced. SVC is used to regulate the terminal voltage of self excited induction generator-based (SEIG) wind generator working with variable speed and load. Since, the wind generator operates over a wide range of operating conditions; the terminal voltage of the induction generator is not regulated. This terminal voltage is controlled by adapting the value of the excitation capacitance of SVC using artificial neural networks (ANN) and adaptive neuro-fuzzy inference systems (ANFIS). Changing the excitation capacitance is performed by controlling the firing angle of SVC under different operating conditions to control the terminal voltage. A mathematical model of SEIG with variable load and speed along with SVC is developed and simulated in MATLAB to get the excitation capacitance required for voltage control. Simulation results are used to train both ANN and ANFIS for on-line prediction of the suitable firing angles required to control the terminal voltage of the system under these operating conditions. Results signify the supremacy of ANFIS over ANN in terms of performance measures.

Macrocell path loss prediction using artificial intelligence techniques

The prediction of propagation loss is a practical non-linear function approximation problem which linear regression or auto-regression models are limited in their ability to handle. However, some computational Intelligence techniques such as artificial neural networks (ANNs) and adaptive neuro-fuzzy inference systems (ANFISs) have been shown to have great ability to handle non-linear function approximation and prediction problems. In this study, the multiple layer perceptron neural network (MLP-NN), radial basis function neural network (RBF-NN) and an ANFIS network were trained using actual signal strength measurement taken at certain suburban areas of Bauchi metropolis, Nigeria. The trained networks were then used to predict propagation losses at the stated areas under differing conditions. The predictions were compared with the prediction accuracy of the popular Hata model. It was observed that ANFIS model gave a better fit in all cases having higher R2 values in each case and on average is more robust than MLP and RBF models as it generalises better to a different data.

Competitive performance improvement by operational budget allocation using ANFIS and fuzzy quality function deployment: a case study

A budget is a detailed and comprehensive plan estimated to use a company's resources over a specific period, and a primary purpose of budget allocation is to drive all activities towards organizational goals. But it seems, often, there is no logical and coherent relationship between overall objectives and action plans. This paper has drawn a consistent relationship between an organization's strategic plans to operational budgeting in a competitive environment. According to the step-by-step model proposed in this article, a strategic plan's importance considers the main competitors of the market as an external environment factor and a balanced scorecard factors as an internal envi- ronment. Both are calculated by an artificial neuro-fuzzy inference systems approach to outshine competing compa- nies. Then, sub-progress must be hierarchically determined in specific plans. In passing, a fuzzy quality function de- ployment method translates a strategic plan' sw eight to detailed task importance (as the smallest component of an operational program) at the mercy of four houses of a quality matrix. An operational budget is allocated to pro- grams for propagating strategic plans in a competitive envi- ronment. Finally, a case study in an automobile industry is presented and discussed to illustrate the application of the developed pattern.

A comparison of neural networks and adaptive neuro-fuzzy inference systems for the prediction of water diffusion through carbon nanotubes

Given the fact that artificial intelligence tools such as neural network and fuzzy logic are capable of learning and inferencing from the past to capture the patterns that exist in the data, this study presents an intelligent method for the forecasting of water diffusion through carbon nanotubes where predictions are generated from neuro-fuzzy structures using molecular dynamics data. Therefore, this research was mainly focused on combining molecular dynamics with artificial intelligence methods in order to reduce the computational time of biomolecular and nanofluidic simulations. Two different artificial intelligence methods are applied for the time-dependent water diffusion forecasting: artificial neural network (ANN) and adaptive neuro-fuzzy inference systems (ANFISs). The effects of different sizes of training sample sets on forecasting performance of ANN and ANFIS are investigated as well. Four different evaluation methods are used to measure the performance and forecasting accuracy of these two methods. As a result, ANFIS presents the higher accuracy than neural network method based on the comparison of these different evaluation methods adopted in this research. The results reported in this research demonstrate that combining of molecular dynamics with artificial intelligence methods can be one of the most powerful and beneficial tools for prediction of important nanofluidic parameters.

Crack identification in curvilinear beams by using ANN and ANFIS based on natural frequencies and frequency response functions

This paper presents different artificial intelligence (AI) techniques for crack identification in curvilinear beams based on changes in vibration characteristics. Vibration analysis has been performed by applying the finite element method (FEM) to compute natural frequencies and frequency response functions (FRFs) for intact and damaged beams. The analysis reveals the changes in natural frequencies and amplitudes of FRFs of the beams for cracks of different sizes at different locations. These changes are used as input data for single and multiple artificial neural networks (ANN) and multiple adaptive neuro-fuzzy inference systems (ANFIS) in order to predict the size of the crack and its location. To avoid large models, the principal component analysis (PCA) approach has been carried out to reduce the computed FRFs data. The analysis of different techniques shows that the average prediction errors in the multiple ANN models is less than those in the single ANN model and in the multiple ANFIS. It is shown that the cracks longer than 5 mm can be located with satisfactory accuracy, even if the input data are corrupted with various level of noise. Multiple ANFIS is adopted to construct a more reliable and less sensitive model for noise excitation.

Differentiating between good credits and bad credits using neuro-fuzzy systems

To evaluate consumer loan applications, loan officers use many techniques such as judgmental systems, statistical models, or simply intuitive experience. In recent years, fuzzy systems and neural networks have attracted the growing interest of researchers and practitioners. This study compares the performance of artificial neuro-fuzzy inference systems (ANFIS) and multiple discriminant analysis models to screen potential defaulters on consumer loans. Using a modeling sample and a test sample, we find that the neuro-fuzzy system performs better than the multiple discriminant analysis approach to identify bad credit applications. Further, neuro-fuzzy systems have many advantages over traditional computational methods. Neuro-fuzzy system models are flexible, more tolerant of imprecise data, and can model non-linear functions of arbitrary complexity.