Adaptive Network-based Fuzzy Interference System Research Articles

ANFIS Control for Solar PV fed Modular Multilevel Inverter for Marine Water Pumping Applications

In this paper, we show our work developing and implementing a Modular Multilevel Inverter (MMI) for intelligent Induction Motor (IM) drive control. Pumping water from the sea is the primary focus of these methods. It has been suggested that an eleven-stage inverter could be used to regulate the speed of a photovoltaic solar-powered IM drive. It is estimated that pumps account for roughly half of a ship's total energy consumption. Therefore, the purpose of this study is to investigate and assess the proposed control design for an induction motor (IM) drive and MMI-based marine water pumping system. The primary motivation behind this design was to reduce the complexity of the controller. Controllers based on Proportional-Integral (PI), Fuzzy Logic (FL), and Adaptive Network-based Fuzzy Interference System (ANFIS) are tested alongside the inverter to see how well they improve performance. The Total Harmonic Distortion (THD) of inverters, controller settling times, and peak overshoot have all been compared to identify the most robust option. In order to establish which of these elements is superior, this comparison was performed. The suggested control scheme's novel feature is the design and integration of a marine-specific MMI, IM drive, and intelligent controller for use in marine water pumping applications.

Intelligent Medical Diagnostic System for Hepatitis B

The hepatitis B virus is the most deadly virus, which significantly affects the human liver. The termination of the hepatitis B virus is mandatory and can be done by taking precautions as well as a suitable cure in its introductory stage; otherwise, it will become a severe problem and make a human liver suffer from the most dangerous diseases, such as liver cancer. In this paper, two medical diagnostic systems are developed for the diagnosis of this life-threatening virus. The methodologies used to develop these models are fuzzy logic and the neuro-fuzzy technique. The diverse parameters that assist in the evaluation of performance are also determined by using the observed values from the proposed system for both developed models. The classification accuracy of a multilayered fuzzy inference system is 94%. The accuracy with which the developed medical diagnostic system by using Adaptive Network based Fuzzy Interference System (ANFIS) classifies the result corresponding to the given input is 95.55%. The comparison of both developed models on the basis of their performance parameters has been made. It is observed that the neuro-fuzzy technique-based diagnostic system has better accuracy in classifying the infected and non-infected patients as compared to the fuzzy diagnostic system. Furthermore, the performance evaluation concluded that the outcome given by the developed medical diagnostic system by using ANFIS is accurate and correct as compared to the developed fuzzy inference system and also can be used in hospitals for the diagnosis of Hepatitis B disease. In other words, the adaptive neuro-fuzzy inference system has more capability to classify the provided inputs adequately than the fuzzy inference system.

New Computational Artificial Intelligence Models for Generating Synthetic Formation Bulk Density Logs While Drilling

Synthetic well log generation using artificial intelligence tools is a robust solution for situations in which logging data are not available or are partially lost. Formation bulk density (RHOB) logging data greatly assist in identifying downhole formations. These data are measured in the field while drilling by using a density log tool in the form of either a logging while drilling (LWD) technique or (more often) by wireline logging after the formations are drilled. This is due to operational limitations during the drilling process. Therefore, the objective of this study was to develop a predictive tool for estimating RHOB while drilling using an adaptive network-based fuzzy interference system (ANFIS), functional network (FN), and support vector machine (SVM). The proposed model uses the mechanical drilling constraints as feeding input parameters, and the conventional RHOB log data as an output parameter. These mechanical drilling parameters are usually measured while drilling, and their responses vary with different formations. A dataset of 2400 actual datapoints, obtained from a horizontal well in the Middle East, were used to build the proposed models. The obtained dataset was divided into a 70/30 ratio for model training and testing, respectively. The optimized ANFIS-based model outperformed the FN- and SVM-based models with a correlation coefficient (R) of 0.93, and average absolute percentage error (AAPE) of 0.81% between the predicted and measured RHOB values. These results demonstrate the reliability of the developed ANFIS model for predicting RHOB while drilling, based on the mechanical drilling parameters. Subsequently, the ANFIS-based model was validated using unseen data from another well within the same field. The validation process yielded an AAPE of 0.97% between the predicted and actual RHOB values, which confirmed the robustness of the developed model as an effective predictive tool for RHOB.

Core log integration: a hybrid intelligent data-driven solution to improve elastic parameter prediction

Current oil prices and global financial situations underline the need for the best engineering practices to recover remaining hydrocarbons. A good understanding of the elastic behavior of the reservoir rock is extremely imperative in avoiding the severe well drilling problems such as wellbore in-stability, differential sticking, kicks, and many more. Therefore, it is plausible to have a good estimation of the rock elastic behavior for successful well operations. This study presents a generalized empirical model to predict static Poisson’s ratio of the carbonate rocks. Petrophysical well logs were used as inputs, and the laboratory measured static Poisson’s ratio was used as an output. Three supervised artificial intelligence (AI) techniques were used, viz. artificial neural network (ANN), support vectors regression, and adaptive network-based fuzzy interference system. An extensive prediction comparison was made between these three AI techniques. Based on the lowest average absolute percentage error (AAPE) and highest coefficient of determination (R2), the ANN model proposed to be the best model to predict static Poisson’s ratio. To transform black box nature of AI model into a white box, ANN-based empirical correlation is also developed to predict the static Poisson’s ratio. Comparison of the developed empirical correlation with previously established approaches to find static Poisson’s ratio on an unseen published dataset revealed that the equation of ANN can predict the static Poisson’s ratio with implicitly less AAPE and with high R2 value. The proposed model with the empirical correlation can assist geo-mechanical engineers to predict the static Poisson’s ratio in the absence of core data. The novelty of the new equation is that it can be used without the need of any AI software.

N-policy for redundant repairable system with multiple types of warm standbys with switching failure and vacation

This investigation is concerned with the reliability analysis of redundant repairable system which is supported by mixed standby and two repairmen who turn on according to a threshold N-policy. The first repairman never takes a vacation while the second repairman leaves for a vacation of random length when the number of failed components is less than N. The concepts of standby switching failure, degradation and common cause failure are incorporated to predict the performance metrics of the real time redundant repairable system. By developing Markov model, the transient queue size distribution and expressions for the system reliability, mean time to system failure and other performance measures are obtained. The sensitivity analysis is performed by taking numerical illustration. The model is also examined computationally by employing the adaptive network-based fuzzy interference system (ANFIS) approach to compute the system descriptors. Using supervised learning process, the comparison between the ANFIS results and analytical results are made.

ANFIS Technique Applied to the Control of a Robot Manipulator with Disturbances

The objective of this paper is to propose an ANFIS (Adaptive Network based Fuzzy Interference System) technique, which enables the controller to obtain different combinations of gain (Kp and Kd) with disturbance signals to reflect the real time performance of the manipulator. The outputs of these controllers are used to produce the final actuation signal based on current position errors. Numerical simulation using PD, Fuzzy+PD and ANFIS+PD is also determined and compared. Finally, the results of simulations indicates that, ANFIS based controllers reduce the position tracking error in a more effective manner. Thus the proposed ANFIS based controller works effectively in the tracking control of a robot manipulator © 2012 Published by Elsevier Ltd. Selection and/or peer-review under responsibility of Noorul Islam Centre for Higher Education

Adaptive Controllers for Permanent Magnet Brushless DC Motor Drive System using Adaptive-Network-based Fuzzy Interference System

Problem statement: The tuning methodology for the parameters of adaptive speed controller causes a transient deviation of the response from the set reference following variation in load torque in a permanent-magnet brushless DC (BLDC) motor drive system. Approach: This study develops a mathematical model of the BLDC drive system, firstly. Secondly, discusses a design of the closed loop drive system employing the Adaptive-Network-based Fuzzy Interference System (ANFIS). The nonlinear simulation model of the BLDC motors drive system with ANFIS control based is simulated in the MATLAB/SIMULINK platform. Results: The necessitated data for training the ANFIS control is generated by simulation of the system with conventional PI controller. Conclusion: The simulated electromagnetic torque and rotor speed signify the superiority of the proposed technique over the classical method.

Analysis of MEG Background Activity in Alzheimer’s Disease Using Nonlinear Methods and ANFIS

This study was designed to analyze the magnetoencephalogram (MEG) background activity from 20 patients with probable Alzheimer's disease (AD) and 21 control subjects by using two nonlinear methods: sample entropy (SampEn), and Lempel-Ziv complexity (LZC). The former quantifies the signal regularity, and the latter is a complexity measure. The signals were acquired with a 148-channel whole-head magnetometer placed in a magnetically shielded room. Our results show that MEG recordings are less complex and more regular in patients with AD than in control subjects. Significant differences between both groups were found in 16 MEG channels with SampEn and in 134 with LZC (p < 0.01, Student's t test with Bonferroni's correction). Using receiver operating characteristic curves with a leave-one-out cross-validation procedure, accuracies of 70.73 and 78.05% were reached with SampEn and LZC, respectively. Additionally, we wanted to assess whether both nonlinear methods and an adaptive-network-based fuzzy interference system (ANFIS) could improve AD diagnosis. With this classifier, an accuracy of 85.37% was achieved. Our findings suggest the usefulness of our methodology to increase our insight into AD.