Adaptive Neural Fuzzy Interface Research Articles

Solar forecasting for a PV-battery powered DC system

The photovoltaic (PV) power generation sector has been growing rapidly as a result of the rising need for solar power and the advancement of PV technology. PV Power generation is affected by weather factors such as cloud cover, solar irradiation, temperature, breeze direction and speed, and the amount of rain or snow. As a result, a highly precise PV power predictor is essential to improve security and reliability in the face of financial penalties and ambiguity. Hence, this paper suggests a novel approach to improve the efficiency of PV-battery-powered DC systems by combining solar irradiance prediction using the Long Short-Term Memory (LSTM) algorithm with a power electronic converter design that incorporates a bidirectional port. The LSTM algorithm was employed to predict one week of solar data with a remarkable R2 score of 0.96. A steady-state analysis of the proposed Three-Port Converter (TPC) is performed for five different operating modes to guarantee optimal performance. The suggested system's prediction performance was tested using several error metrics such as Mean Absolute Error (MAE), Mean Square Error (MSE), and Root Mean Squared Error (RMSE), which were computed as 0.0318, 0.0027, and 0.0526, respectively. Results from the above error measures show that the suggested approach performs more effectively in estimating solar irradiance. The Adaptive Neural-Fuzzy Interface System (ANFIS) and Incremental Conductance (IC) algorithms are employed for Maximum Power Point Tracking (MPPT) and assessed against various atmospheric conditions. From the MATLAB simulation results, the tracking efficiency of the ANFIS-based MPPT technique is 99.97 %, which is superior to the IC-based MPPT technique. Furthermore, it proved that the suggested approach improves the efficiency of PV-battery-powered DC systems, which is more appropriate for real-world applications such as DC microgrids and Electric Vehicles.

Modeling and optimization of osmotic dehydration of wax apple slices using adaptive neuro-fuzzy inference system

The effect of ultrasound on osmotic dehydration of wax apple was investigated using the Fuzzy inference system, and the process parameters of ultrasonic assisted osmotic dehydration were optimized. The effect of ultrasonication temperature (XUT; 25 - 45 °C), sonication time (XIt; 140 - 220 min), sugar concentration (XSC; 30 - 70%), and sample to solvent ratio (XSS; 1:6 - 1:14) was studied. The responses such as water loss, solid gain, and color change, were investigated by modeling the ultrasonic assisted osmotic dehydration of wax apple using an adaptive neural fuzzy interface (ANFIS). Three ANFIS models were developed for the responses with Gaussian and linear membership functions as the input and output membership functions, respectively. The developed ANFIS model had R2 value more than 0.985 and an RMSE value less than 0.04, indicating a higher predictive capability. The ANFIS output was considered as input for the genetic algorithm (GA) optimization, with the objective of achieving maximal water loss while minimizing solid gain and color change. The integrated ANFIS-GA optimized the process parameters with a fitness value of 2.8. The optimum values of ultrasonic assisted osmotic dehydration process parameters were ultrasonication temperature of 38.6 °C, sonication time of 186 min, sugar concentration of 62%, and solvent to sample ratio of 11.7 w/v. The predicted values of the response water loss, solid gain, and color change at the optimum condition were observed to be 40.698, 3.097, and 10.916, respectively.

An adaptive neural fuzzy interface structure optimisation for prediction of energy consumption and airflow of a ventilation system

Coal mines are prone to fatal vulnerabilities due to improper airflow, a susceptible threat that leads to vitiating safety and human resources. Hence, continuous monitoring of the underground mine’s airflow is essential for detecting any calamities. Various artificial intelligent methods estimate the underground mines’ airflow (non-linear parameter). However, these methods fall into local minima and low convergence rates. This article proposed a novel algorithm that integrates an Adaptive Neural Fuzzy Interface System (ANFIS) and genetic algorithm (GA) to predict the energy consumption and airflow of the ventilation system for underground mines. A GA is studied to automatically search and configure network architecture to reduce the manual tuning effort required for optimal network architecture. Two predictive reference models (i.e., particle swarm optimisation (PSO) and Bayesian optimisation (BO)) are introduced for comparison to demonstrate the capability of GA in identifying the best hyper-parameters of ANFIS and ANN. To validate the proposed model, extensive experiment analysis and comparison with several baseline approaches in terms of the statistical parameters that include root mean square error (RMSE), mean absolute error (MAE), and coefficient of determination (R2). In terms of the performance metric employed, the experiment findings indicate that the proposed model gives superior results over the baseline models. Thus, the proposed work advances the mine ventilation and monitoring system technologies to enhance performance and reliability, improve health and safety, reduce energy and operational cost, and enhance mine productivity.

ANFIS Supervised PID Controlled SAPF for Harmonic Current Compensation at Nonlinear Loads

ABSTRACT The smart devices comprise extensive embedding of small-size AC power-driven power electronics components. This improves the smart automation in the majority of applications in the industry and home system. But, the nonlinear characteristics of such component introduces several higher-order harmonics and generates possible deviation in performance measures. The long-term persistence of harmonic distortions in the current distribution may result in system failure and depreciation in system efficiency. This paper presents a soft computing technique for reactive power compensation of harmonic current using adaptive neural fuzzy interface system (ANFIS). The smart ANFIS supervises the PID controller for adequate gate signaling to shunt active power filter (SAPF) by hysteresis current control. The neural network is trained by adaptive data set of error and deviation in error with respect to hysteresis current control. The nonlinear load model is subjected to transformer-less SAPF to avoid the presence of insertion losses and improves the system compatibility. The proposed system reduces the harmonic distortion from 92.23 to 0.49% in the nonlinear power converter model with improved 0.99 power factor. Additionally, the proposed system is absolutely feasible and novel for real-time application in smart devices with adequate transient and regression response. The proposed system is realized for individual effects of PID, ANN and ANFIS to justify the candidature of the soft computing technique in real-time applications as per IEEE 519 standard.

Power quality improvement at nonlinear loads using transformer‐less shunt active power filter with adaptive neural fuzzy interface system supervised PID controllers

Power quality improvement at nonlinear loads using transformer‐less shunt active power filter with adaptive neural fuzzy interface system supervised <scp>PID</scp> controllers

Data Analytics for Substation Overloading Assessment of Solar Integrated Distribution System

It is an important concern to supply uninterrupted power to consumer under competitive environment. Therefore, available reserve margin of substation transformer is utmost concerns for power utilities due to its direct effects on power quality, reliability and revenue loss. This research work focus on data analytics application to predict substation overloading assessment for integrated distribution system. This paper has developed three adaptive neural fuzzy interface system (ANFIS) to predict the available substation reserve margin by considering base case and different solar integration scenarios. The ANFIS models were trained and tested using stochastic data obtained from load flow computation for a modified IEEE 37 feeder. To train ANFIS models, input variables are taken as “voltage unbalance factor, feeder power loss to load ratio, maximum branch loading, voltage deviation, and minimum power factor”, while target variable is taken as substation reserve margin”. All predications of ANFIS models are compared with those values obtained from load flow computation. It was found that predicated results have good agreement with load flow computational data and R-squared value fall in the range of 0.9182 to 0.9173. The proposed research work is useful to predict operational performance of integrated solar distribution system in smart grid environment.

Anfis Controller Based Reconfigurable Solar Converter for Single Stage Power Conversion-PV Battery System

In this paper, analysis of Reconfigurable Solar Converter (RSC) based on Adaptive Neural Fuzzy Interface System (ANFIS) controller is presented for PV battery application. The major concept of RSC is to use single stage three phase grid tie solar PV converter system to perform both dc/ac and dc/dc operations. The conversion stages are decreased and cost, weight reduces. ANFIS controller improves the performance of the system. An effective Mat lab / Simulation result presents the attractive performance of proposed system.

Supervised control strategy in trajectory tracking for a wheeled mobile robot

In this study, a single input interval type-2 fuzzy logic (SI-IT2-FLC) supervised adaptive neural-fuzzy interface system (ANFIS) controller is proposed for the velocity tracking task of a two-wheeled mobile robot (WMR). The suggested technique can handle the inherent nonlinearities, uncertainties and external disturbances in the system model by a new supervised controller. The robot control design is accomplished by two separate phases including kinematic controller, which is characterized using the kinematic model of the robot, and dynamic controller, which is designed using the physical features of the robot dynamics. In particular, an SI-IT2-fuzzy PD (SI-IT2-FPD) controller is initially applied for the trajectory tracking problem in the two-WMR. In this way, the impact of the footprint of uncertainty (FOU) on control surface (CS) generation is studied, i.e. several CSs were generated by changing a single coefficient which shapes the FOU. Then, a new SI-IT2-FPD supervised ANFIS controller is developed for the concerned robot system. To enhance the efficiency of the suggested controller, the baseline PD gains of the SI-IT2-FPD are adjusted in a heuristic manner. Finally, a prototype of the concerned robot is implemented to investigate the feasibility and applicability of the proposed framework in a real-time platform.

Prediction of biodiesel density for extended ranges of temperature and pressure using adaptive neuro-fuzzy inference system (ANFIS) and radial basis function (RBF)

Density is a very important fuel property because of its direct relation with the fuel injection process for engines. This paper presents models based on Adaptive Neural Fuzzy interface System (ANFIS) and Radial Basis Function (RBF) to predict the density of biodiesel in a wide temperature and pressure range. Furthermore, this study is also aimed to evaluate and compare the predicted density of biodiesel by using ANFIS and RBF. The models ANFIS and RBF developed in this study were trained and tested with the experimental data obtained from literature. The temperature and pressure were the input variables in the models. The results indicated that there is an excellent agreement between the predicted and experimental data, with high R2. Consequently, The R-squared was 0.95 in ANFIS model and 0.93 in RBF model.

The Design and Implementation of Adsorptive Removal of Cu(II) from Leachate Using ANFIS

Clinoptilolite was investigated for the removal of Cu(II) ions from industrial leachate. Adaptive neural fuzzy interface system (ANFIS) was used for modeling the batch experimental system and predicting the optimal input values, that is, initial pH, adsorbent dosage, and contact time. Experiments were studied under laboratory batch and fixed bed conditions. The outcomes of suggested ANFIS modeling were then compared to a full factorial experimental design (23), which was utilized to assess the effect of three factors on the adsorption of Cu(II) ions in aqueous leachate of industrial waste. It was observed that the optimized parameters are almost close to each other. The highest removal efficiency was found as about 93.65% at pH 6, adsorbent dosage 11.4 g/L, and contact time 33 min for batch conditions of 23 experimental design and about 90.43% at pH 5, adsorbent dosage 15 g/L and contact time 35 min for batch conditions of ANFIS. The results show that clinoptilolite is an efficient sorbent and ANFIS, which is easy to implement and is able to model the batch experimental system.

Sequential combination of statistics, econometrics and Adaptive Neural-Fuzzy Interface for stock market prediction

Since last decade advanced data simulations help to identify hidden trends in a time series. Our purpose is to identify uncertainties during recession period using statistical analysis, econometrical analysis and Adaptive Neural-Fuzzy networks. In this paper, initially through computational analysis we are testing financial data using correlation tests, likelihood tests, heteroscedastic characteristics analysis and hypothesis tests. These statistical and econometrical tests give us exact nature of data set and relation between data points. All tests and analysis are studied on NASDAQ Stock Market over last 2-years. Then after, optimized subtractive data clustering method is used to cluster the data and create fuzzy membership functions by using Sugeno-type Fuzzy Interface System (FIS). Finally, we are using optimized hybrid learning algorithm in customized Adaptive Neural Fuzzy Interface System (ANFIS) to train the network. Hence, we got an efficient Adaptive Neural-Fuzzy network to check and test the data sets and use it for forecasting the stock market index. During this, the hybrid learning algorithm combines Least-Square method and the Back-propagation gradient descent methods for training the Fuzzy Interface System (FIS) with the help of optimized membership functions and parameters. This paper presents a state-of-art for Adaptive Neural-Fuzzy Network (ANFN) application to forecast stock market index and involved market uncertainties by combining the econometrical test to optimize the ANFIS and FIS function.