Adaptive Neuro Research Articles

Intelligent ANFIS-Based Distributed Generators Energy Control and Power Dispatch of Grid- Connected Microgrids Integrated into Distribution Network

Power supply management is a critical problem in the operation of a distribution network, considering the causes of large power losses and interruptions in the main grid caused by the unknown connection of loads and DGs that affect power delivery to customers downstream of a distribution network. The above-mentioned problems can be reduced by the integration of microgrids close to load centers and developing a controller using adaptive control techniques to enhance reliable power supply. For this reason, this paper presents an intelligent method for distributed generators' energy control and power dispatch of microgrids integrated into a distribution network employing an Adaptive Neuro- Fuzzy Inference System (ANFIS). The aim is to control distributed generators energy sources, loads, and power dispatch of grid-connected microgrids among multiconnected power sources to maintain a stable power supply without using any optimization techniques. The proposed intelligent ANFIS system is trained for power-sharing purposes and applied to the microgrid controllers. The mathematical modeling of distributed generators, system design, simulation, and testing of the proposed method were done using MATLAB/Simulink software. The results show that the proposed controller is capable of power dispatch and controls the energy harvest of distributed generators. Additionally, it can assign microgrid power source(s) to additional load(s) connected to the active distribution network without interruptions of power flow. The obtained results outperform similar works that used hybrid ANFISPID (Adaptive Neural Fuzzy Inference System-Proportional- Integral-Derivative), PSO-ANFIS (Particle Swarm Optimization-Adaptive Neural Fuzzy Inference System), and GA-ANFIS (Genetic Algorithm-Adaptive Neuro-Fuzzy Inference System) by automatically connecting and controlling distributed generators energy sources with effective power dispatch in mitigating downtime of grid power operations.

An Effective Internet of Things based Assessment of ANN and ANFIS algorithms for Cardiac Arrhythmia

Reducing the influence of significant noise signal components on the obtained raw ECG signal is essential for precise identification of cardiac arrhythmias (CA), which frequently present as irregularities in heart rate or rhythm. Preprocessing is used to remove noise signals and baseline drift from the ECG wave that is recorded using the internet of things (IoT). After that, the denoised signal is subjected to dimensionality reduction and feature extraction. In order to determine whether classification method is more effective in detecting cardiac arrhythmias, this study compares two methods: an adaptive neuro-fuzzy inference system and artificial feed-forward neural networks trained with the back-propagation learning algorithm. An Adaptive Neuro Fuzzy Inference System analyses ICA features obtained by non-parametric power spectral estimates, and an Artificial Neural Network (ANN) classifier uses the ECG signal's morphological and statistical aspects to identify patterns. The creation of artificial feed-forward neural networks provides a rich framework for studying the Back Propagation Algorithm. Sensitivity, specificity, accuracy, and positive predictiveivity are some of the performance characteristics that are thoroughly examined. An overall accuracy of 97.79%, sensitivity of 99.82%, specificity of 99.68%, and positive predictivity of 98.58% were seen in the results of the Artificial Neural Feed Forward Network (ANFFN). The Adaptive Neuro Fuzzy Inference System (ANFIS) outperforms these metrics with an astounding overall accuracy of 99.62%, specificity of 98.63%, and positive predictivity of 99.46%. With a classification accuracy of 99.82%, ANFIS demonstrates to be the most effective classifier for identifying cardiac arrhythmias.

Improving the Performance of Hybrid System-Based Renewable Energy by Artificial Intelligence

Abstract Artificial intelligence (AI) has emerged as a critical indicator of technological progress in recent years. The present study uses AI to enhance the efficiency of a hybrid system that operates on renewable energy sources. The hybrid system we propose consists of a wind energy conversion system (WECS), a photovoltaic system (PVS), a battery storage system (BSS) and electronic power converters. AI manages these converters cleverly. We use the maximum power point tracking (MPPT)-based fuzzy logic controller (FLC) to regulate the boost converter in the PVS and the WECS. We propose an adaptive neuro fuzzy inference system (ANFIS)-based controller to control the bidirectional converter of the storage system. The design of this module intends to maintain voltage stability on the direct current (DC) bus and improve energy quality. We study and simulate this system using MATLAB/SIMULINK. The results of this research show that the FLC-MPPT technique outperforms the Perturb and Observe (P&O) algorithm in terms of efficiency in power production. The console we propose also shows good results in maintaining the voltage stability in the DC bus in comparison with the proportional integral (PI) controller. This paper has the potential to contribute to the development of environmentally friendly resource performance.

Hybrid method for analyzing air thermal conditions in underground mines

Thermal prediction of underground mine air is required to develop control measures against heat problems. Researchers have extensively studied this topic using numerical simulations; however, these require long processing times. Recently, researchers have begun using artificial intelligence algorithms; however, the predictive capabilities of the model are still limited because an intelligent system is formed from field measurement data. This study presents a fast and accurate prediction of the Wet Bulb Globe Temperature (WBGT) in underground mines using a hybrid integrated numerical method and an adaptive neuro fuzzy inference system (ANFIS) method. The mine air thermal conditions in various scenarios were analyzed by numerical simulation, and the results were utilized to develop intelligence for ANFIS model-based predictors. A case study was conducted in two underground gold mine areas to demonstrate the effectiveness of this method. The ANFIS model was trained and tested with 81 scenarios generated from numerical simulations. Accurate predictors were obtained, with a coefficient of determination (R2) of 0.98 and 0.97. In addition to predicting the WBGT, the developed ANFIS model optimized the selection of the auxiliary fan power, minimizing the power consumption while simultaneously providing a comfortable WBGT.

Adaptive Neuro Fuzzy Inference System based Water Quality Index for Godavari River (India)

Adaptive Neuro Fuzzy Inference System based Water Quality Index for Godavari River (India)

Solar Fed 15 Level Cascaded Multilevel Inverter with ANFIS Control Strategy for Enhancement of Power Quality

Solar PV energy conversion systems suffer from degraded power quality issues because of harmonics in the system. In order to eliminate harmonics, this paper focuse on a solar-powered 15-level cascaded inverter. A number of controllers such as PI, Fuzzy Logic Neural Network and ANFIS are used in this study in order to manage the PWM frequency (Proportional Integral, Fuzzy Logic, NN and Adaptive Neuro Fuzzy Inference System, respectively). A PV-fed 15-level cascaded multilevel inverter for power quality improvement will be developed by using an ANFIS controller. The suggested ANFIS controller has a lower harmonic distortion than conventional controllers; hence the quality of the power improves. The PI, FL, ANN, and ANFIS controllers simulated results are analysed in MATLAB.

Enhancing Solar Air Heater Performance with Quatrefoil Artificial Roughness: An Adaptive Neuro-Fuzzy System Approach

Solar air Collector is used to transform the solar energy into heat energy. Solar heating technologies use only free, renewable and clean energy. More number of previous studies was done. The roughness element is changed to enhance the airflow’s capacity to absorb heat. In this study Experimental investigates the glazed solar air heater with quatrefoil shaped artificial roughness is placed above the absorber plate in the solar air heater. The solar air heaters (SAH) with quatrefoil shaped artificial roughness and conventional solar air heater are tested. The outcome indicates that the maximum temperatures for conventional SAH and purposely roughened SAH are 670C and 470C, respectively. By the increased of heat transfer area and increased the turbulence lead to higher heat recovery rate of quatrefoil shaped artificial roughness is 47% more compared to conventional type. The solar air heater is predicted by using Adaptive Neuro Fuzzy Inference System (ANFIS) and accuracy is measured as 90%.

HETEROGENEOUS SERVER RETRIAL QUEUEING MODEL WITH FEEDBACK AND WORKING VACATION USING ARTIFICIAL BEE COLONY OPTIMIZATION ALGORITHM

This research delves into the dynamics of a retrial queueing system featuring heterogeneous servers with intermittent availability, incorporating feedback and working vacation mechanisms. Employing a matrix geometric approach, this study establishes the steady-state probability distribution for the queue size in this complex heterogeneous service model. Additionally, a range of system performance metrics is developed, alongside the formulation of a cost function to evaluate decision variable optimization within the service system. The Artificial Bee Colony (ABC) optimization algorithm is harnessed to determine service rates that minimize the overall cost. This work includes numerical examples and sensitivity analyses to validate the model's effectiveness. Also, a comparison between the numerical findings and the neuro-fuzzy results has been examined by the adaptive neuro fuzzy interface system (ANFIS).

Application of Hybrid ANFIS Tool for Laser Beam Welding of Inconel 625 Alloy

Over the past decade, there has been a steady rise in the application of laser sources; this has led to reduced costs and enhanced output. One aspect that has played a part and helped to the quickening of this phenomena is the invention of new techniques such as laser beam welding systems. These developments in technology have made it feasible to produce both tiny and large parts. The usage of nickel alloy can provide considerable benefits in a wide variety of contexts. The advantages acquired from combining difficult materials, such as metal alloys, are responsible for these benefits. Manufacturing equipment for the chemical, nuclear, maritime, aeronautical, and automotive industries all rely on components made from Inconel 625. It can withstand potentially corrosive situations without losing its outstanding mechanical qualities. Investigation of nickel alloy weldments is required for the improvement of the production method. The goal of this piece is to develop an ANFIS (Adaptive Neuro Fuzzy Inference System) based on Grey theory that can reliably forecast LBW variables. The values predicted by the model were compared with the results of the experiments, and it was discovered that the values found in the experiments are closely related to the values anticipated by the model. The manufacturer can make decisions that are more in accordance with the available facts due to the evidence provided by the performance investigation.

Sensorless speed and position control of permanent magnet BLDC motor using particle swarm optimization and ANFIS

This paper describes the operation of a Permanent Magnet Brushless Direct Current (PMBLDC) motor without a position sensor. In this case, the sensorless operation is enhanced by an effective hybrid technique that detects the back electromotive force (Back EMF) of the zero crossing point (ZCP) from the terminal voltages. The Adaptive Neuro Fuzzy Interference System (ANFIS) controller, which is based on Particle Swarm Optimization (PSO) and uses PSO to train its operation, is combined in the proposed hybrid analysis. The PMBLDC motor's ANFIS controller receives the line voltages as input, and it uses this information to estimate the sample signals that are then sent to the ZCP detection circuit. Appropriate commutation control of the inverter is generated by the ZCP detecting circuit. By varying the ANFIS consequent parameters, the PSO algorithm iterates until the error between the sample output and the real training data reaches a low value. The MATLAB/Simulink platform is utilized to implement the suggested sensorless controller action. To verify the controller's performance, a comparison with the other soft computing methods is also carried out.

Adaptive Neuro Fuzzy Inference System based classifier in diagnosis of breast cancer

Millions of individuals live longer and healthier lives due to modern medical innovations. The advancement of modern medicine to combat numerous ailments has benefited humanity a lot. Breast cancer is one of the most fatal diseases affecting women globally. Early detection is essential for lowering the fatality rate. The objective of the paper is to create a computer-aided diagnostic model that helps in the early detection of breast cancer and hence decreases the death rate. The study introduces a hybrid strategy for effectively diagnosing breast cancer by using a Novel Relief algorithm for feature selection with an Adaptive Neuro-Fuzzy Inference System (ANFIS). The efficiency of this proposed hybrid model and the ANFIS model without using any feature selection technique is estimated using the Wisconsin Breast Cancer Data set (WBCD). The study finds that the new hybrid model has attained the highest accuracy of 99.30% and is ideal for detecting breast cancer.

A stochastic variance reduction gradient-based GSO-ANFIS optimized method for maximum power extraction of proton exchange membrane fuel cell

Proton Exchange Membrane Fuel Cells (PEMFCs) play a pivotal role in the clean energy landscape, yet their efficiency is contingent upon effective power optimization. This paper presents Maximum PowerPoint Tracking (MPPT) control schemes for PEMFCs, focusing on a ground-breaking methodology. Traditional MPPT controllers are instrumental in maintaining optimal performance; however, they often struggle with dynamic operating conditions. In response to this challenge, this research work presents a pioneering MPPT control scheme employing a stochastic variance reduction gradient system. The novelty of this approach lies in its fusion with the Glow Swarm Optimization (GSO) and the Adaptive Neuro Fuzzy Inference System (ANFIS), resulting in a robust hybrid controller. In the pursuit of optimizing the PEMFC system, the proposed GSO-ANFIS controller is subjected to rigorous testing under dynamic variations in both PEMFC temperature and load. Notably, PEMFCs, due to fluctuations in pressure and temperature, exhibit stochastic behaviour, forming a Gaussian surface. In this research, the popular Perturb and Observe (P&O) and Incremental Conductance methods are evaluated alongside the newly introduced GSO-ANFIS model. The proposed GSO-ANFIS controller outperforms its counterparts, showcasing an impressive accuracy level of 89.97%. In contrast, the Artificial Neural Network (ANN) achieves 80.33% accuracy, and the standalone ANFIS controller attains 86.5% accuracy. This disparity underscores the efficacy and potential of the novel hybrid approach, which not only adeptly handles the stochastic nature of PEMFCs but also significantly enhances accuracy in power optimization. This research not only contributes a valuable addition to the field of MPPT control but also offers a promising trajectory for the future development of efficient and reliable PEMFC systems.

A new cockroach-like compliant mechanism with SLA-3D printing for micromanipulation and micropolishing of biomaterials

The traditional compliant mechanisms often employ displacement amplification mechanisms to magnitude the workspace but their displacements are still smaller than 1 mm. Unlike previous studies, the present paper proposes a new conceptual design of compliant mechanism which is inspired from biomechanics of cockroach animal. The developed compliant mechanism for two specific functions, such as microgripper and micropositioner which can handle biomaterials. It can permit a large stroke over 1 mm. Modeling of the performances of the proposed mechanism are built by a couple of adaptive neuro fuzzy inference system (ANIFS) and particle swarm optimization (PSO) where PSO is to optimize the ANFIS. To enhance the performances of the mechanism, accelerated particle swarm optimization (APSO) is utilized to search the optimal design parameters. Lastly, the optimized mechanism is printed by Stereolithography (SLA) 3D technique, and the experimental verifications are performed. The results indicated that circumstance #1, the stroke is about 1.5279 mm, the frequency is 49.02103 Hz, the crosstalk error is 0.01108 mm, and the stress is 8.50514 MPa. In circumstance #2, the stroke is 1.44544 mm, the frequency is 54.51361 Hz, the crosstalk error is 0.0248 mm, and the stress is 8.35604 MPa. In last circumstance, the optimized results are achieved the stroke of 1.62369 mm, frequency of 51.62278 Hz, crosstalk of 0.028141 mm, and stress of 7.71713 MPa. The results indicated that the safety factor of three cases are over 2.5 to ensure a safe operation. The tested results are well satisfied with the simulated results.

Design and performance analysis of braking system in an electric vehicle using adaptive neural networks

Research article emphasizes on the impact of braking concepts considering regenerative braking system and energy consumption aspects in electric vehicles through a new perspective. The electric vehicle system is modeled and simulated using the MATLAB/Simulink software. A dataset is developed using the virtual simulation environment created by co-simulation using the MATLAB/Simulink and the IPG Carmaker software. This dataset is also used in a neural network model based on adaptive neuro fuzzy logic and the system performance is analyzed. Parameters considered for training the neural network are the brake pedal displacement, braking change rate and the need for brake application. The highlight of this study is the focus on a front wheel driven electric vehicle, which uses a standard drive cycle input to validate the model. The significant parameters evaluated in this study include the braking effects, kinetic energy, regenerative braking torque, battery state of the charge and the motor torque. The torque generation and its intended braking force requirements based on the acceleration, deceleration and braking conditions are the notable observations. The regenerative capability of this proposed system design is also illustrated along with the surface plots based on the training dataset. Investigation and analysis reveal that, the battery state of charge could be revived throughout the drive with a steady and stable increase. Transitions of motor torques between tractive and regenerative phases are also illustrated and explained for clarity and brevity.

An experimental investigation on kinetic analysis of thermal degradation of shape stable composite phase change materials and adaptive neuro fuzzy inference system modeling for predicting mass loss

An experimental investigation on kinetic analysis of thermal degradation of shape stable composite phase change materials and adaptive neuro fuzzy inference system modeling for predicting mass loss

A Multi-Objective Optimization-Algorithm-Based ANFIS Approach for Modeling Dynamic Customer Preferences with Explicit Nonlinearity

In previous studies, customer preferences were assumed to be static when modeling their preferences based on online reviews. However, in fact, customer preferences for products are dynamic and changing over time. Few research has been conducted to model dynamic customer preferences as the time series data of customer preference are difficult to be obtained. Based on online reviews, an adaptive neuro fuzzy inference system (ANFIS) was introduced to model customer preferences, which can take into account the fuzzy nature of customers’ emotions and the nonlinearity of the model. However, ANFIS is plagued with black box problems, and the nonlinearity of the model cannot be directly demonstrated. To address the above research issues, a multi-objective chaos optimization algorithm (MOCOA)-based ANFIS approach is proposed to generate customer preferences models by using online reviews, which has explicit nonlinear inputs. Firstly, a sentiment analysis approach is used to derive information from online reviews by periods, which is used as the time series data sets of the proposed model. A MOCOA is combined into ANFIS to identify the nonlinear inputs, which include single items, interactive items, and terms of second order and/or higher-order terms. Consequently, the fuzzy rules in ANFIS are expressed in polynomial form, which allows for the explicit representation of the nonlinearity between customer preferences and product attributes. A case study of sweeping robots is used to compare the validation results of the proposed approach with those of ANFIS, subtractive cluster-based ANFIS, fuzzy c-means-based ANFIS, and K-means-based ANFIS. Moreover, the proposed approach provides better performance than the other four approaches in terms of mean relative error and variance of error.

The nexus between quality of customer relationship management systems and customers' satisfaction: Evidence from online customers’ reviews

Customer Relationship Management (CRM) is a method of management that aims to establish, develop, and improve relationships with targeted customers in order to maximize corporate profitability and customer value. There have been many CRM systems in the market. These systems are developed based on the combination of business requirements, customer needs, and industry best practices. The impact of CRM systems on the customers' satisfaction and competitive advantages as well as tangible and intangible benefits are widely investigated in the previous studies. However, there is a lack of studies to assess the quality dimensions of these systems to meet an organization's CRM strategy. This study aims to investigate customers' satisfaction with CRM systems through online reviews. We collected 5172 online customers' reviews from 8 CRM systems in the Google play store platform. The satisfaction factors were extracted using Latent Dirichlet Allocation (LDA) and grouped into three dimensions; information quality, system quality, and service quality. Data segmentation is performed using Learning Vector Quantization (LVQ). In addition, feature selection is performed by the entropy-weight approach. We then used the Adaptive Neuro Fuzzy Inference System (ANFIS), the hybrid of fuzzy logic and neural networks, to assess the relationship between these dimensions and customer satisfaction. The results are discussed and research implications are provided.

3EDANFIS: Three Channel EEG-Based Depression Detection Technique with Hybrid Adaptive Neuro Fuzzy Inference System

Background: Depression is a mental disorder that often negatively impacts the actions and feelings of the affected person. No laboratory tests are available to detect and properly diagnose depression. Presently, the detection of depression is done based on standardized questionnaires like Diagnostic and Statistical Manual of Mental Disorders-fifth edition (DSM-V) and Hamilton Depression Rating Scale (HAM-D) which is subjective in nature. Objective: The purpose of the study is to propose a framework for more accurate detection of depression from EEG signals using only three channels, which makes the system portable as well as efficient. Methods: In this study, we propose a classification model using EEG signal with the help of Adaptive Neuro Fuzzy Inference System optimized by nature-inspired algorithm. The proposed model is efficient, accurate, and portable as the features are extracted from only three channels, namely, Fp1, Fp2, and Fz. The three Data Channel (3EDANFIS) Adaptive Neuro Fuzzy Inference System (ANFIS) for detection of depression as well as three variants of Hybrid ANFIS – Adaptive Neuro Fuzzy Inference System-Genetic Algorithm (ANFIS-GA), Adaptive Neuro Fuzzy Inference System- Particle Swam Optimization (ANFIS-PSO) and Adaptive Neuro Fuzzy Inference System- Firefly Algorithm (ANFIS-FA) has been analyzed in this study. The features extracted are delta, theta, alpha, and beta and their corresponding sub-bands delta1, delta2, theta1, theta2, alpha1, alpha2, beta1, and beta2. Genetic Algorithm (GA), Particle Swam Optimization (PSO), and Firefly Algorithm (FA) are all nature-inspired metaheuristic algorithms which are used to optimize ANFIS by adapting the premise and consequent parameters. Results: The analysis showed that the GA and FA perform equally well in optimizing ANFIS with the highest accuracy of 83.33 % using delta1 power as well as delta power. Overall accuracy of the ANFIS-GA is found to be higher than that of the ANFIS-PSO, ANFIS-FA, and ANFIS. It was also found that the sub-band classification accuracy is higher than that of the band itself for delta, theta, and alpha bands. In case of the ANFIS, ANFIS-GA, ANFIS-PSO, and ANFIS-FA, delta1 was found to be having higher accuracy than delta power, theta1 was found to be having higher accuracy than theta power, and both alpha1 and alpha2 showed higher accuracy than alpha power. Conclusion: The use of only three EEG channels for data recording makes our technique to be more feasible, portable, convenient, and faster and hence can act as an adjunct tool for psychiatrists in the future.

ANFIS based method for faults detection in the photovoltaic system

<span>As the case with all electrical and electronic systems, a photovoltaic (PV) system can be exposed to several failures causing it to malfunction; several studies have found that the reliability of the PV systems is highly dependent on the material used for the construction of the PV panels, temperature, humidity and solar radiation. A PV system can have several faults, whether construction type faults, or material and electrical faults caused by climatic conditions. This requires identification, the main objective of which is to provide a tool that can detect and locate these faults in order to guarantee optimal performance of the system, and thus reduce maintenance costs and above all increase productivity by increasing the availability rate facilities in order to have a better performance. The objective of this article is to propose a technique for detecting and locating faults in a PV system, the proposed algorithm is based on adaptive neuro fuzzy inference system (ANFIS). This algorithm is based on the technique of artificial neural networks and fuzzy logic. Nine faults will be examined with simulation results under MATLAB-Simulink in PV system (array, converter DC-DC and battery).</span>

Improved Performance of a Grid-Connected Inverter with Two PV Array Input under Different Environment Conditions using Adaptive Neuro Fis Based Control

Grid-connected inverters based on solar PV cells are becoming increasingly common. At times, the PV can be subjected to a certain environmental situation, such as varying irradiance or temperature. Present developments in gird-connected PV inverters do not have many reliable yields or reliability in this case. In this article, an improved control framework system is intended for two PV that are mismatched in various ways, resulting in a highly effective grid-connected solar inverter with THD under 1% for both voltage and current. The regulator employs a control scheme comprised of an ANFIS-based control system that works in tandem with the incremental conductance technique of MPPT. The outcomes are simulated and validated using MATLAB Simulink.