Artificial Neuro-fuzzy Inference System Research Articles

A Comparative Analysis of Sediment Concentration Using Artificial Intelligence and Empirical Equations

Morphological changes in canals are greatly influenced by sediment load dynamics, whose estimation is a challenging task because of the non-linear behavior of the sediment concentration variables. This study aims to compare different techniques including Artificial Intelligence Models (AIM) and empirical equations for estimating sediment load in Upper Chenab Canal based on 10 years of sediment data from 2012 to 2022. The methodology involves utilization of a newly developed empirical equation, the Ackers and White formula and AIM including 20 neural networks with 10 training functions for both Double and Triple Layers, two Artificial Neuro-Fuzzy Inference System (ANFIS), Particle Swarm Optimization, and Ensemble Learning Random Forest models. Sensitivity analysis of sediment concentration variables has also been performed using various scenarios of input combinations in AIM. A state-of-the-art optimization technique has been used to identify the parameters of the empirical equation, and its performance is tested against AIM and the Ackers and White equation. To compare the performance of various models, four types of errors—correlation coefficient (R), T-Test, Analysis of Variance (ANOVA), and Taylor’s Diagram—have been used. The results of the study show successful application of Artificial Intelligence (AI) and empirical equations to capture the non-linear behavior of sediment concentration variables and indicate that, among all models, the ANFIS outperformed in simulating the total sediment load with a high R-value of 0.958. The performance of various models in simulating sediment concentration was assessed, with notable accuracy achieved by models AIM11 and AIM21. Moreover, the newly developed equation performed better (R = 0.92) compared to the Ackers and White formula (R = 0.88). In conclusion, the study provides valuable insights into sediment concentration dynamics in canals, highlighting the effectiveness of AI models and optimization techniques. It is suggested to incorporate other AI techniques and use multiple canals data in modeling for the future.

Implementation of Passivity-based Control of Four-Leg Inverter for Transformerless Three-Phase Solar Photovoltaic Systems

This study explores the application of a passivity-based control technique (PBC) with an artificial neuro-fuzzy inference system (ANFIS) in a grid-connected Solar Photovoltaic (SPV) generating system for estimating reference grid currents. To optimise the tracking of the maximum power point (MPPT) between the solar photovoltaic (SPV) system and the DC bus, a DC – DC boost converter (BC) is utilised. This converter is connected to a four-leg, three-level neutral-point-clamped converter (4-leg 3L-NPC), interfaced with a three-phase, four-wire distribution system. The four-leg 4-leg 3L-NPC of the SPV generating system with Space vector pulse width modulation technique (SVPWM) is utilised for reducing common-mode voltage (CMV), leakage current (LC), reactive power for zero voltage regulation, power factor correction, load balancing, and the elimination of load harmonic currents in the proposed distribution system.The performance analysis of the proposed system is conducted on the Matlab/Simulink platform. Additionally, a comparative analysis is presented, contrasting the proposed system with a 3-phase 4-leg T-type neutral-point-clamped converter (TNPC) employing the PBC technique followed by ANFIS.

Cascaded H-bridge multilevel inverter-based DSTATCOM with an artificial neural fuzzy inference systembased controller

<span>In this paper, <span>a voltage source inverter is utilized as a distributed static compensator (DSTATCOM). The DSTATCOM is used for the elimination of harmonics caused by the nonlinear load. The reference currents of DSTATCOM were estimated with a synchronous reference frame (SRF). Conventionally, the SRF uses voltage, load current and filter current to compute the reference current to track desired source current for DSTATCOM. The sliding mode controller and feedback linearization are used to design the current controller. The feedback linearization technique and sliding mode control are used to cancel nonlinearities and offer invariant stability due to modeling uncertainties due to the DSTATCOM parameter and external load disturbance. The sliding mode controller requires a rigorous mathematical model of the system. To overcome this, an artificial neuro-fuzzy inference system (ANFIS) is devised for the control of DSTATCOM. The training data of the ANFIS controller is generated from the sliding mode controller algorithm. The overall system of DSTATCOM including the ANFIS algorithm is implemented in MATLAB/Simulink SimPower block sets. The simulated response of DSTATCOM was found to be improved and better than the sliding mode controller scheme.</span></span>

Humanoid Walking Control Using LQR and ANFIS

Humanoid robots possess remarkable mobility and adaptability for diverse environments. Nonetheless, accurate walking pattern tracking remains challenging, especially when employing the linear quadratic regulator (LQR) due to delays in high-mobility setpoint tracking. We propose a novel control approach to address this limitation by integrating an artificial neuro-fuzzy inference system (ANFIS) with the LQR to enhance pattern tracking. The research contributes to developing a control system that combines LQR and ANFIS to enable humanoid robots to follow various walking patterns with increased precision and efficiency and also the scheme to incorporate LQR and ANFIS. The study involves four experiments: step response, walking phase, static straight walking, and varied straight walking. Each test runs for 5 seconds with a 100-millisecond sampling rate, repeated five times, and employs the Integral Absolute Value (IAE) metric for evaluation. The LQR-ANFIS method exhibits superior performance, achieving a maximum overshoot of 0%, a rise time of 0.3 seconds, a settling time of 0.3 seconds, and a steady-state error of 0% in the step response experiment. The proposed control system also enables stable walking with step periods ranging from 0.15 to 4 seconds and step ranges of 0.05 to 0.03 meters. In conclusion, the integration of ANFIS with the LQR significantly enhances the mobility of humanoid robots, enabling them to navigate diverse environments and accurately track various walking patterns proficiently.

Fruit type classification using deep learning and feature fusion

Machine and deep learning applications play a dominant role in the current scenario in the agriculture sector. To date, the classification of fruits using image features has attained the researcher’s attraction very much from the last few years. Fruit recognition and classification is an ill-posed problem due to the heterogeneous nature of fruits. In the proposed work, Convolution neural network (CNN), Recurrent Neural Network (RNN), and Long-short Term Memory (LSTM) deep learning methods are used to extract the optimal image features, and to select features after extraction, and finally, use extracted image features to classify the fruits. To evaluate the performance of the proposed approach, the Support vector machine (SVM) unsupervised learning method, Artificial neuro-fuzzy inference system (ANFIS), and Feed-forward neural network (FFNN) classification results are compared, and observed that the proposed fruit classification approach results are quite efficient and promising.

Artificial intelligence-based controller for rotor current of doubly fed induction generator in wind turbine system

The demand for energy is increasing that can be met with Doubly Fed Induction Generator (DFIG) based Wind Energy Conversion System (WECS). In this paper, A 2 MW DFIG was used as the plant. To limit the shortcomings of a Proportional-Integral (PI) controller, Fuzzy Logic (FL), Fuzzy-PI, and Artificial Neuro-Fuzzy Inference System (ANFIS) controllers are being designed. The system is modeled in a MATLAB/Simulink. A comparative analysis of PI, Fuzzy, Fuzzy-PI, and ANFIS are presented. Taking a steady state error (SSE) as an objective function of performance index, the PI controller results with a 2.9084 A, Fuzzy with 0.8668 A, Fuzzy-PI with 7.654 A, and ANFIS, with 11.5472 A. Hence, the Fuzzy logic controller-based system is found to be the best candidate for SSE control of rotor current. An ANFIS-based controller has the best settling time for rotor currents control, whereas the Fuzzy-PI found to be best for SSE and torque control.

Frequency Support Studies of a Microgrid Having DG-WTG Using ANFIS and with the Application of HAE-FC and RFB

The micro-grid (μ-grid) has picked up momentum worldwide with the ability to supply cost-effective, clean, and reliable electrical power to the present-day demand. The practical μ-grids are comprised of non-conventional and conventional sources such as wind turbine generators (WTG) and diesel generators (DG). Due to the encouragement of wind power which is exceedingly sporadic in nature and thus the frequency of the μ-grid is exceedingly vulnerable due to the erratic nature of wind speed. Variations in the load demand have also added to the vulnerability of the μ-grid at distinctive moments of time. Consequently, this paper appears to be a novel plan that utilizes artificial neuro-fuzzy inference system (ANFIS) within the built frequency regulation of the μ-grid. The proposed research has been employed within the μ-grid, and the application outcomes have taken all possibilities, such as load variety at the distinctive moment of time, modification of the load demand on the μ-grid, and step alteration of the wind input. The achieved results are coordinated with a few of the most recent results, which presents the ANFIS ahead over other strategies. Although there is a probable scope for improvement which subsequently involves the fuel cell (FC) with a hydrogen aqua electrolyzer (HAE) unit, as well as a redox flow battery (RFB), that is introduced one at a time in the μ-grid and the results of μ-grid are calculated for various working conditions to show the impact that the ANFIS technology has upon storage devices with regards to the μ-grid architecture.

Design of high voltage gain converter for fuel cell based EV application with hybrid optimization MPPT controller

From the previously available articles, the fuel cell dependent power supply systems are increasing every year. Also, these systems are playing a major focus on the microgrid renewable energy networks. However, the fuel cell gives less output power extraction at different operating temperature values. In addition, the working point of the fuel cell vary with respect to the hydrogen supply, and water membrane content. In order to achieve the high output power of the fuel stack, a Maximum Power Point Tracking (MPPT) is used to track the peak power point of the proposed system. In this article, Artificial Neuro Fuzzy Inference System (ANFIS) controller is utilized in order to generate the smooth output voltage waveform of the fuel cell stack. The optimization of ANFIS controller have been done by using the Genetic Algorithm (GA). The advantages of ANFIS based MPPT controller are high output power extraction, and less distortions of converter voltages. Here, the Proton Exchange Membrane Fuel Cell (PEMFC) device is used as a source. The features of PEMFC are fast start-up, and high efficient. The PEMFC generates less voltage which is enhanced by using the interleaved non-isolated boost converter. The proposed fuel cell based interleaved system is analyzed by using the MATLAB/Simulink software.

Decision making support system for medical devices maintenance using artificial neuro fuzzy inference system

Decision making support system for medical devices maintenance using artificial neuro fuzzy inference system

Improved Medium Term Approach for Load Forecasting of Nigerian Electricity Network Using Artificial Neuro-Fuzzy Inference System: A Case Study of University of Nigeria, Nsukka

The demand for electrical energy continues to rise at an alarming rate, while supply is not proportional to power demand. Thus, in order to accomplish appropriate preparation and operation of an electrical power system network, it is crucial to properly assess the present and future consumption of electric power systems. Meeting the electric load needs entails actively anticipating the amount of energy required to meet the subscribers' power demand. To forecast energy demand, many algebraic and artificial intelligence schemes have been used. This paper proposes an improved medium-term forecasting scheme that employs an artificial neural network (ANN). The model was developed and trained with the help of an artificial neuro-fuzzy inference system (ANFIS). The data used, which ranged from 2014 to 2019, was obtained from the University of Nigeria Nsukka's (UNN) research and energy Centre, and the works department of the same university. The model was designed and simulated using MATLAB 2018a, and the results were evaluated using MAPE. The proposed system used a robust machine learning based scheme. Unlike conventional systems, the system demonstrated a MAPE of 4.34% and a correlation of 0.91144315 at predicted and actual loads, as shown in Table 2. The proposed system shows that the predicted loads has 25th and 75th percentiles of 0.58MW and 0.98WM, while that of the actual loads are 0.649MW and 0.936MW.

A Resilience-Oriented Bidirectional ANFIS Framework for Networked Microgrid Management

This study implemented a bidirectional artificial neuro-fuzzy inference system (ANFIS) to solve the problem of system resilience in synchronized and islanded grid mode/operation (during normal operation and in the event of a catastrophic disaster, respectively). Included in this setup are photovoltaics, wind turbines, batteries, and smart load management. Solar panels, wind turbines, and battery-charging supercapacitors are just a few of the sustainable energy sources ANFIS coordinates. The first step in the process was the development of a mode-specific control algorithm to address the system’s current behavior. Relative ANFIS will take over to greatly boost resilience during times of crisis, power savings, and routine operations. A bidirectional converter connects the battery in order to keep the DC link stable and allow energy displacement due to changes in generation and consumption. When combined with the ANFIS algorithm, PV can be used to meet precise power needs. This means it can safeguard the battery from extreme conditions such as overcharging or discharging. The wind system is optimized for an island environment and will perform as designed. The efficiency of the system and the life of the batteries both improve. Improvements to the inverter’s functionality can be attributed to the use of synchronous reference frame transformation for control. Based on the available solar power, wind power, and system state of charge (SOC), the anticipated fuzzy rule-based ANFIS will take over. Furthermore, the synchronized grid was compared to ANFIS. The study uses MATLAB/Simulink to demonstrate the robustness of the system under test.

A review of recent developments in the application of machine learning in solar thermal collector modelling.

Over the past few decades, the popularity of solar thermal collectors has increased dramatically because of many significant advantages like being a free, natural, environmentally friendly and permanent energy source. Today, developing and optimising different solar thermal energy systems are more important than before. Thus, there are various methods for investigating the performance of these systems, such as experimental, numerical and mathematical methods. One of the cutting-edge methods is artificial intelligence, which can predict key and effective parameters in solar collector efficiency. This review identified recent machine learning modelling, including multilayer perceptron artificial neural network (MLP-ANN), group method of data handling (GMDH), radial basis function (RBF), artificial neuro-fuzzy inference system (ANFIS), support vector machine (SVM) and studies regarding different types of solar thermal collectors, namely non-concentration and concentration. Furthermore, it investigated the effect of various essential factors on the accuracy, potential issues and challenges facing the application of artificial intelligence in these systems. Finally, it will also be recommended opportunities for future research.

Nigeria Generating Station Capacity and Load Demand Requirement Using Regression Analysis (Least Square) and Artificial Neuro-Fuzzy Inference System (Anfis) for Reliable Power Supply

The increasing demand of electrical energy is growing exponential rate while there is mismatched between power supply and power demand. This means that there is strong record to determine the existing state of the system for purpose of future projection of power generation to avoid system collapse. Evidently, to conduct the analysis of system forecast for energy demand, many mathematical techniques and artificial machine learning which is based on artificial intelligence. This paper considered the application of least – square regression technique and artificial neuro-fuzzy inference system (ANFIS) and artificial neural network (ANN) principle, on the view to train the data set for Nigeria energy consumption (residential. Commercial and industrial) on the view to determine total system consumption pattern for reliable power supply. The data used ranges from (2000-2012) as input for the projection plan of 2013-2035, was determined for Nigeria power system. This is modelled and simulated in matlab software tool (version 19.0). the purposed artificial intelligence system based on Artificial neural fuzzy inference system (ANFIS) which provided high machine learning fixtures to predicts close to the actual value as compared to the traditional least square algorithms. The results were evaluated using mean absolute percentage error (MAPE) of 5.73%. The proposed technique ANFIS predicted load forecast (2013-2035) to provide energy data for electric utilities and to plan successfully for efficient power generation. Application of Adaptive Neuron – fuzzy inference in artificial intelligence involved both neural network (NN) and fuzzy logic (FL) principle together an adaptive neuro-fuzzy inference system (ANFIS), is an artificial neural network that is based on a fuzzy inference system. ANFIS is a very useful system to extract numerical model from numerical data since it integrates both neural network and fuzzy logic principle together, it is capable of adapting the benefits of both in a single framework. An adaptive neuro-fuzzy inference system (ANFIS) is an application of adaptive neuro-fuzzy logic that uses frame work of artificial intelligence (AI). Hence its inference system corresponds to a code of IF – THEN RULE in fuzzy neuro network. It has a learning capability to approximate non-linear functions hence adaptive neurofuzzy inference system (ANFIS) deserves to be considered as good estimator.

Machine learning assisted prediction of biochar yield and composition via pyrolysis of biomass

Biochar production via pyrolysis of various organic waste has potential to reduce dependence on conventional energy sources and mitigate global warming potential. Existing models for predicting biochar yield and compositions are computationally-demanding, complex, and have low accuracy for extrapolative scenarios. Here, two data-driven machine learning models based on Multi-Layer Perceptron Neural Network and Artificial Neuro-Fuzzy Inference System are developed. The data-driven models predict biochar yield and compositions for a variety of input feedstock compositions and pyrolysis process conditions. Feature importance assessment of the input dataset revealed their competitive significance for predicting biochar yield and compositions. Overall, the predictive accuracy of the models was up to 12.7% better than the Random Forest and eXtreme Gradient Boosting machine learning algorithms reported in the literature. The models developed are valuable for environmental footprint assessment of biochar production and rapid system optimization.

Soft Computing-Based Models for Predicting the Characteristic Impedance of Igneous Rock from Their Physico-mechanical Properties

Rock properties are important for design of surface and underground mines as well as civil engineering projects. Among important rock properties is the characteristic impedance of rock. Characteristic impedance plays a crucial role in solving problems of shock waves in mining engineering. The characteristics impedance of rock has been related with other rock properties in literature. However, the regression models between characteristic impedance and other rock properties in literature do not consider the variabilities in rock properties and their characterizations. Therefore, this study proposed two soft computing models [i.e., artificial neural network (ANN) and adaptive neuro-fuzzy inference system (ANFIS)] for better predictions of characteristic impedance of igneous rocks. The performances of the proposed models were statistically evaluated, and they were found to satisfactorily predict characteristic impedance with very strong statistical indices. In addition, multiple linear regression (MLR) was developed and compared with the ANN and ANFIS models. ANN model has the best performance, followed by ANFIS model and lastly MLR model. The models have Pearson's correlation coefficients of close to 1, indicating that the proposed models can be used to predict characteristic impedance of igneous rocks.

The fuzzy-based systems in the communication between a human and a humanoid robot

Abstract The communication between a human and a humanoid robot is a real challenge for the researchers in the field of the robotics. Despite of the progress in the acoustic modelling and in the natural languages the humanoid robots are overtaken by the humans when the humanoid robots are engaged in the real life because the speech and the human emotions are extremely ambiguous due to the noises and the external audio events from the robot’s environment. The humans assign a correct interpretation to the perceived ambiguous signal, but the humanoids robots cannot interpret the ambiguous signal. The most common software used in the interpretation of the ambiguous signal is a fuzzy based software. The artificial neuro-fuzzy inference system, shortly known as ANFIS is the emotion recognition system based on the fuzzy sets which acts as the thalamus of the human brain and it is responsible for the sensorial perception of the humanoid robot. Our goal in this work is to create the fuzzy-based sound signals software and the fuzzy-based genetic algorithm with high performance in the communication between the human and the humanoid robots which help the humanoid robots to think, to understand the human speech and the human emotions and all the ambiguous signals from the robot’s environment in a way that it is distinguishable for every humanoid robot as the human.

Textile wastewater heavy metal removal using Luffa cylindrica activated carbon: an ANN and ANFIS predictive model evaluation

This study investigated the application of soft computing models [Artificial neural network (ANN) and Adaptive neuro-fuzzy inference system (ANFIS)] in removing heavy metals [chromium (VI), vanadium (V) and iron (II)] from textile wastewater using Luffacylindrica activated carbon (LAC). The effect of pH, contact time and adsorbent dosage on the adsorptive potential of the prepared LAC were determined using a batch mode experiment. Fourier Transform Infrared Spectroscopy and scanning electron micrograph assessed the potential of the adsorbent in this study. ANN and ANFIS were evaluated using the coefficient of determination (R2) and mean square error (MSE). The result showed that the models demonstrated significant predictive behavior with R2 (9.9999E−1), MSE (5.985E−14) for chromium(VI) removal, R2 (9.9999E−1), MSE (2.33856E−13) for iron(II) removal and R2 (9.9999E−1), MSE (7.22197E−12) for vanadium(V) removal for ANN, while ANFIS predicted R2 (0.76305), MSE (0.037105) for chromium(VI) removal, R2 (0.67652), MSE (0.846) for iron(II) removal, R2 (0.22673), MSE (0.65925) for vanadium(V) removal. Sensitivity analysis carried out with ANFIS (exhaustive search) indicated that the parameters (time, pH and adsorbent dosage) significantly impact the heavy metal removal. Thus, this study shows that ANN and ANFIS are reliable tools for modelling heavy metal removal using LAC. The parameter results obtained are relevant in process design and control.

Decision Making Support System for Medical Devices Maintenance Using Artificial Neuro Fuzzy Inference System

Decision Making Support System for Medical Devices Maintenance Using Artificial Neuro Fuzzy Inference System

Rule-based database intrusion detection using coactive artificial neuro-fuzzy inference system and genetic algorithm

Rule-based database intrusion detection using coactive artificial neuro-fuzzy inference system and genetic algorithm

Rule-based Database Intrusion Detections Using Coactive Artificial Neuro-Fuzzy Inference System and Genetic Algorithm

Rule-based Database Intrusion Detections Using Coactive Artificial Neuro-Fuzzy Inference System and Genetic Algorithm