Type-2 Fuzzy Research Articles

Reinforced Interval Type-2 Fuzzy Clustering-Based Neural Network Realized Through Attention-Based Clustering Mechanism and Successive Learning

Reinforced Interval Type-2 Fuzzy Clustering-Based Neural Network Realized Through Attention-Based Clustering Mechanism and Successive Learning

Rolling Detection Event-Triggered Output Regulation for Switched Interval Type-2 Fuzzy Systems Against Data Integrity and Derivative Injection Attacks

Rolling Detection Event-Triggered Output Regulation for Switched Interval Type-2 Fuzzy Systems Against Data Integrity and Derivative Injection Attacks

Design and modelling of an AI governed type-2 Fuzzy tilt control strategy for AGC of a multi-source power grid in constraint to optimal dispatch

The robust design and application of a novel type-2 fuzzy tilt controller (Type2-FTC) has been well demonstrated in this manuscript. This controller is anticipated to build automatic generation control (AGC) of a multi-area hybrid power system in concern to the optimal power generation scheduling. The combined action of AGC and optimal scheduling of a power system is referred as economic AGC or commonly ELD-AGC. At the initial stage of the analysis, the concept of only AGC has been discussed through various robust approaches. Then the extensive study on ELD-AGC of the proposed power system has been progressed under various controller actions. Further, the proposed Type2-FTC controller is designed ideally with employing an innovative quassi-opposition path finder algorithm (QO-PFA) in various operating conditions. The effectiveness and the viability of the proposed Type2-FTC controller has been verified over type-I fuzzy PID and conventional PID controllers for AGC as well as ELD-AGC of the multi area power system. In controller comparison study, it has been revealed that proposed Type2-FTC is a potential candidate to improve frequency stability of the system. Further, the analysis over technique study justifies supremacy of the suggested QO-FPA algorithm over standard PFA and PSO algorithms for optimal designing all implemented controllers.

Maximum power point tracking improvement using type-2 fuzzy controller for wind system based on the double fed induction generator

Introduction. In this paper, to maximize energy transmission in wind power system, various Maximum Power Point Tracking (MPPT) approaches are available. Among these techniques, we have proposed the one based on typical fuzzy logic. Despite the somewhat reduced performance of fuzzy MPPT. For a number of reasons, fuzzy MPPT can replace conventional optimization techniques. In practice, the effectiveness of conventional MPPT methods depends mainly on the accuracy of the information given and the wind speed or knowledge of the aerodynamic properties of the wind system. Novelty. Our new MPPT for monitoring the maximum power point has been proposed. We developed an algorithm to improve control performance and govern the stator’s developed active and reactive power using the typical fuzzy logic 2 and enable robust control of a grid-connected, doubly fed induction generator. Purpose. MPPT which implies the wind turbine’s rotating speed should be modified in real time to capture the most wind energy, is necessary to achieve high efficiency for wind energy conversion, according to the aerodynamic characteristics of the wind turbine. Methods. Developing a mathematical model for a wind energy production system is complex, can be strongly affected by wind variation and is a non-linear problem. Thanks to these characteristics, thus, the Lyapunov technique is combined with a sliding mode control to ensure overall asymptotic stability and robustness with regard to parametric fluctuations in order to accomplish this goal. We contrasted our fuzzy type-2 algorithm’s performance with that of the fuzzy type-1 and Perturbation & Observation (P&O) suggested in the literature. Practical value. The simulation results demonstrate that the control performance is satisfactory when using the fuzzy logic technique. From these results, it can be said for the optimization of energy conversion in wind systems, the fuzzy type-2 technique may offer a workable option. Since it presents a great possibility to avoid problems either technical or economics linked to conventional strategies.

Sustainable-resilient-responsive supply chain with demand prediction: An interval type-2 robust programming approach

This study configures a novus multi-objective three-stage supply chain network that aims at optimizing sustainability, resilient and responsive measures, simultaneously. At first, a novel prediction model based on Markov chain, Dempster-Safer evidence theory and Shapely value is developed under trapezoidal interval type-2 fuzzy ambience to predict the demand of future scenarios. The prediction model prevents undesired loss occurred due to illogical demand consideration. To encounter interval type-2 fuzziness as well as risk in decision making, an unprecedented trapezoidal interval type-2 fuzzy robust possibilistic programming approach is introduced. The DEcision MAking Trial and Evaluation Laboratory method is suggested in the framework of trapezoidal interval type-2 fuzzy to prioritize the objective function by scrutinizing the interrelationship among different objective function components. As a result, the subjectiveness in the decision making framework is reduced. The generated configuration is then analysed using a blended approach that merges multi-choice reference goal programming with utility functions and particle swarm optimization. The integrated approach produces high-quality solution in lesser computational time. The insightful explorations are delivered based on a case study of hydrogen fuel supply chain in India. The outcomes show how resilient tactics are quite effective and can significantly enhance social, environmental, and economic aspects. It is determined that the best results for supply chain are obtained when the suggested sustainable, resilience and responsiveness tactics are used jointly. Moreover, the sensitivity analysis results suggest that the objective functions are substantially affected by the responsive level; therefore, managers ought to envisage the trade-off between responsiveness and other objective functions.

Robust control technique for wind turbine system with interval type-2 fuzzy strategy on a dual star induction generator

This work presents a robust and innovative technique implemented using an interval type 2 fuzzy logic controller (IT2-FLC) for a dual star induction generator (DSIG) based wind turbine system. The proposed study uses variable wind speed to generate the mechanical energy needed to operate a 1.5 MW DSIG-based wind turbine system. While traditional type 1 fuzzy logic controllers (T1-FLC) have been successful in various applications, they struggle with high uncertainty in complex, nonlinear systems. In contrast, the IT2-FLC technique provides improved capabilities to effectively manage uncertainty and unreliability of information. To address this, the IT2-FLC technique has been developed due to its superior uncertainty management, where the Gaussian IT2 fuzzy sets are employed in this paper due to their concise representation and simultaneous capability to capture sufficient uncertainties. The utilization of type 2 fuzzy membership functions in the controller ensures robust performance and eliminates the necessity for a model-based adaptive control scheme. The proposed IT2-FLC strategy for DSIG was implemented in a Matlab environment, where variable wind speed was used for this purpose. Performance comparisons were made between an IT2-FLC and a T1-FLC technique, revealing the robustness of the latter in terms of track references, rise time, total harmonic distortion (THD) of current, and overshoot. The results prove that the IT2-FLC strategy reduced the THD value of current by rates estimated at 14.72% and 25.88% in the two tests compared to the T1-FLC strategy. Also, the overshoot value was reduced by an estimated ratio of 9.21% in the first test compared to the T1-FLC strategy. The IT2-FLC strategy reduced the rise time value by rates estimated at 4% and 9.75% compared to the T1-FLC strategy. These ratios show the satisfactory performance of the IT2-FLC strategy in improving the properties of DSIG.

Accuracy Analysis of Type-2 Fuzzy System in Predicting Parkinson’s Disease Using Biomedical Voice Measures

Accuracy Analysis of Type-2 Fuzzy System in Predicting Parkinson’s Disease Using Biomedical Voice Measures

Legendre wavelet method based solution of fractional order prey–predator model in type-2 fuzzy environment

Researchers have recently examined several fractional-order prey–predator population models in a crisp or type-1 fuzzy environment. But incompleteness in the membership may also be present. In this regard, type-2 fuzzy numbers are employed in this inquiry to address the system’s imprecision since they are more realistic than type-1 fuzzy numbers in light of the uncertain membership grades. To numerically estimate the solution, the Legendre wavelet method (LWM) is used in conjunction with the r2-cut of the r1-plane form of the type-2 fuzzy parameters. To test the applicability of the present method, three cases are examined. The present solutions are quantitatively compared with the RK4 solutions in the crisp case. Approximations of the type-2 fuzzy prey and predator populations are also included. In addition, two- and three-dimensional plots are depicted to examine the behaviour of prey and predator populations in crisp and type-2 fuzzy cases. To assess the LWM’s efficacy, comparison graphs of the acquired solutions and the results of the RK4 approach are also provided. Numerical validation against the RK4 method in crisp cases demonstrates strong agreement, while revealing contrasting population behaviours in first two scenarios, whereas in the third case, both populations reduce with time. Further, the behaviour of the fuzzy solution has also been shown graphically using the footprint of uncertainty (FOU).

A hybrid traffic controller system based on flower pollination algorithm and type-2 fuzzy logic optimized with crow search algorithm for signalized intersections

In this study, a hybrid traffic signal control (HTSC) system based on phase and time optimization was developed. The Flower Pollination Algorithm (FPA) approach was used for phase optimization, while Type-2 Fuzzy Logic, optimized with the Crow Search Algorithm (CSA), was utilized for time optimization. The hybrid system's performance was investigated using nine different traffic conditions and four different intersection geometries. The hybrid system was compared with three controller systems which are a fixed-time signal controller, a signal controller based on the FPA approach (FPA_TSC), and the optimized Type-1 fuzzy logic signal controller (Type-1 FL-TSC). The HTSC approach achieved the best performance with about 32% improvement over the fixed-time traffic controller and it showed 5% and 6% better performance than the FPA_TSC and Type-1 FL-TSC, respectively. Considering the performance of the new hybrid system, it is effective in minimizing delays and driver dissatisfaction occurring from signalization. It also contributes to the reduction of emissions and fuel consumption. The HTSC approach can be used as an alternative signal control method in the control of intersections with high traffic volume due to its fast and effective performance.

A Type-2 Fuzzy-Based Explainable AI System for Predictive Maintenance Within the Water Pumping Industry

Industrial maintenance has undergone a paradigm shift due to the emergence of artificial intelligence (AI), the Internet of Things (IoT), and cloud computing. Rather than accepting the drawbacks of reactive maintenance, leading firms worldwide are embracing "predict-and-prevent" maintenance. However, opaque box AI models are sophisticated and complex for the average user to comprehend and explain. This limits the AI employment in predictive maintenance, where it is vital to understand and evaluate the model before deployment. In addition, it's also important to comprehend the maintenance system's decisions. This paper presents a type-2 fuzzy-based Explainable AI (XAI) system for predictive maintenance within the water pumping industry. The proposed system is optimised via Big-Bang Big-Crunch (BB-BC), which maximises the model accuracy for predicting faults while maximising model interpretability. We evaluated the proposed system on water pumps using real-time data obtained by our hardware placed at real-world locations around the United Kingdom and compared our model with Type-1 Fuzzy Logic System (T1FLS), a Multi-Layer Perceptron (MLP) Neural Network, an effective deep learning method known as stacked autoencoders (SAEs) and an interpretable model like decision trees (DT). The proposed system predicted water pumping equipment failures with good accuracy (outperforming the T1FLS accuracy by 8.9% and DT by 529.2% while providing comparable results to SAEs and MLPs) and interpretability. The system predictions comprehend why a specific problem may occur, which leads to better and more informed customer visits to reduce equipment failure disturbances. It will be shown that 80.3% of water industry specialists strongly agree with the model's explanation, determining its acceptance.

Retracted: Correlation Coefficient and Entropy Measures Based on Complex Dual Type-2 Hesitant Fuzzy Sets and Their Applications

Retracted: Correlation Coefficient and Entropy Measures Based on Complex Dual Type-2 Hesitant Fuzzy Sets and Their Applications

An innovative fuzzy logic based controller for solid oxide fuel cells

The solid oxide fuel cell (SOFC) stands out as a vital component in sustainable distributed generation systems, thanks to its reliability and adaptable power generation capabilities. This adaptability allows the SOFC to efficiently balance grid power by adjusting its power output. Nevertheless, maintaining the desired fuel usage rate and achieving rapid load tracking pose considerable hardships in SOFC control. To deal with these difficulties, this study introduces a novel approach, the Cascaded Double Input Interval Type-2 Fuzzy Logic Controller (C-DIT2-FLC), designed for SOFC control. In this innovative model, the Improved Salp Swarm Algorithm (ISSA) is applied to determine the crucial parameters of Proportional Integral-Proportional Derivative (PI-PD) cascade controllers. The C-DIT2-FLC dynamically adjusts the controller gains, which are optimized using ISSA, to enhance the effectiveness of SOFC operations. The research results substantiate the superior efficacy of the C-DIT2-FLC over conventional controllers, thereby providing enhanced control and performance capabilities for SOFC systems.

A 3D Membership Function-Based Type-2 Fuzzy Brain Emotional Learning Predictor for Forecasting Taiwan Stock Price

A 3D Membership Function-Based Type-2 Fuzzy Brain Emotional Learning Predictor for Forecasting Taiwan Stock Price

Optimization of the energy management system in hybrid electric vehicles considering cabin temperature

The air conditioning (AC) system provides passengers with a comfortable temperature environment and is one of the main energy consumers in modern plug-in hybrid electric vehicles (PHEV). However, the AC system is often overlooked when designing the energy management system (EMS) for PHEVs. To improve the energy efficiency of PHEVs, this paper integrates the Genetic Simulated Annealing Algorithm (GASA) with fuzzy control to propose an energy management system for PHEVs that considers the internal temperature of the vehicle. First, considering the uncertainty of the vehicle's driving environment, an optimized Interval Type-2 Fuzzy Controller (IT2-FC) was designed for real-time torque distribution. Second, an iteratively modified genetic simulated annealing algorithm was used to optimize control parameters, correcting the defect of genetic algorithms tending to get trapped in local optima and lingering around optimal positions. Then, considering the energy consumption of the AC system, a vehicle-integrated thermal management model oriented towards control was established. Lastly, the performance of the proposed EMS was discussed. The results show that, compared to the rule-based methods, the proposed EMS reduces fuel consumption by 17.77% and 17.727% in cooling and heating modes, respectively, and compared to the A-ECMS methods, it reduces fuel consumption by 7.38% and 6.31% in cooling and heating modes, respectively. At the same time, the proposed EMS ensures thermal comfort in the cabin. In cooling mode, the traditional rule-based strategy failed to maintain the cabin temperature within the preset range, while the proposed EMS showed significant improvement. In heating mode, the EMS reaches and maintains the cabin's set temperature 35% faster than the rule-based strategy, and 8.75% faster than the A-ECMS strategy.

Noninvasive system for weight estimation in cactus crops: A YOLOv5-decision tree approach based on interval type-2 fuzzy sets

This study proposes a noninvasive system to estimate the weight of a prickly pear cactus (Opuntia ficus-indica), which combines a model based on deep learning to detect and estimate its area and a model based on supervised learning and developed under a type-2 interval fuzzy sets approach to estimate its weight. YOLOv5 was used for detection, which achieved results with an accuracy of 0.999, recall of 0.999, mAP_0.5 of 0.995, and mAP_0.5:0.95 of 0.990. Area estimation is performed based on the object's coordinates in the image. To perform the weight estimation task, a comparative analysis of models based on supervised learning was performed to identify the model that best described the response variable, selecting a decision tree model. The training and adjustment process included the uncertainty in a weight evaluation system using a granatary scale to enhance the weight estimation capability. Using a trapezoidal membership function, the type-2 interval fuzzy set approach was used to convert the collected data into fuzzy numbers. The model findings for the weight estimation task were also favorable, with a model-explained variance R2 of 0.98, a root mean square error (RMSE) of 10.02, and a mean absolute error (MEA) of 6.33 g. Finally, both models were incorporated into a graphical user interface to facilitate their use in the real weight estimation process. A real case application with the proposed system demonstrated its effectiveness in detecting and estimating weight dynamically with an error of 9 g. Therefore, its viability as an alternative system for weight estimation in cactus crops was demonstrated. Furthermore, a comparative analysis demonstrated the superiority of the proposed hybrid approach over similar approaches in the literature.

Analyzing stability and structural aspects of embedded fuzzy type 2 PID controller for robot manipulators

This study delves into the development and analysis of a novel Embedded Fuzzy Type 2 PID Controller for Robot Manipulators, motivated by the increasing need for enhanced control systems in robotic applications to improve precision and stability. In the background section, the limitations of conventional PID controllers in addressing uncertainties and disturbances, especially in complex tasks performed by robot manipulators, are presented. The concept of fuzzy logic and the Type 2 fuzzy system is introduced, highlighting their potential to manage imprecise and uncertain information. Through rigorous analysis and simulation, the superior performance of the Embedded Fuzzy Type 2 PID Controller is demonstrated when compared to traditional PID controllers and even Type 1 fuzzy controllers. The results showcase enhanced tracking accuracy, disturbance rejection, and adaptability, making it a promising solution for advanced robotic applications. In conclusion, this research provides a robust solution for improving the control of robot manipulators in uncertain and dynamic environments. The Embedded Fuzzy Type 2 PID Controller offers a new paradigm in control theory, ensuring stability and precision even in the face of unpredictable factors. This innovation holds great promise for advancing the capabilities of robotic systems and underlines the potential for further research in embedded fuzzy control systems.

Interval Type-2 Fuzzy Deep Reinforcement Learning based Operational Optimization of Industrial Aerodynamic System

Interval Type-2 Fuzzy Deep Reinforcement Learning based Operational Optimization of Industrial Aerodynamic System

Process accident prediction using Bayesian network based on IT2Fs and Z-number: A case study of spherical tanks.

This study aimed to propose a novel method for dynamic risk assessment using a Bayesian network (BN) based on fuzzy data to decrease uncertainty compared to traditional methods by integrating Interval Type-2 Fuzzy Sets (IT2FS) and Z-numbers. A bow-tie diagram was constructed by employing the System Hazard Identification, Prediction, and Prevention (SHIPP) approach, the Top Event Fault Tree, and the Barriers Failure Fault Tree. The experts then provided their opinions and confidence levels on the prior probabilities of the basic events, which were then quantified utilizing the IT2FS and combined using the Z-number to reduce the uncertainty of the prior probability. The posterior probability of the critical basic events (CBEs) was obtained using the beta distribution based on recorded data on their requirements and failure rates over five years. This information was then fed into the BN. Updating the BN allowed calculating the posterior probability of barrier failure and consequences. Spherical tanks were used as a case study to demonstrate and confirm the significant benefits of the methodology. The results indicated that the overall posterior probability of Consequences after the failure probability of barriers displayed an upward trend over the 5-year period. This rise in IT2FS-Z calculation outcomes exhibited a shallower slope compared to the IT2FS mode, attributed to the impact of experts' confidence levels in the IT2FS-Z mode. These differences became more evident by considering the 10-4 variance compared to the 10-5. This study offers industry managers a more comprehensive and reliable understanding of achieving the most effective accident prevention performance.

Intelligent Enhanced Mobile Robotics Navigation: Integrating Neural Networks with Type-2 Fuzzy Logic for Dynamic Environments

Intelligent mobile robots move on uncertain grounds, thus requiring good navigation strategies for things like path tracking and obstacle avoidance. This research uses an Omni-drive mobile robot to autonomously approach given objectives in different situations encountered in static and dynamic environments. The paper compares two distinct controllers – fuzzy logic controller and neural network controller- that lead the mobile robot towards its destination without hitting obstacles. These are responsible for adjusting the linear and angular velocities of a mobile robot which makes adaptive navigation possible during real-time. The experimental results have depicted the adaptability of each controller as well as its efficiency especially when dealing with uncertainties involved with the mobile robot navigation system. By systematically evaluating and contrasting them, this study brings out the best performance between Fuzzy Logic and Neural Network Controllers regarding enhancing the autonomy and robustness of Mobile Robots. This research helps to advance knowledge in autonomous systems for practical applications, which will give rise to more efficient navigational techniques for mobile robots; thus, efficient systems that are autonomous become more reliable today. The results show that these controllers are effective in safely steering the robot from its starting point to a specified destination without hitting obstacles.

Design of Ultra-Local Model Control Based on Interval Type-2 Fuzzy Logic for Nine-Level Packed E-Cell

Design of Ultra-Local Model Control Based on Interval Type-2 Fuzzy Logic for Nine-Level Packed E-Cell