Adaptive Neuro-Fuzzy Inference System (ANFIS) blends advantages of both Artificial Neural Networks (ANNs) and Fuzzy Logic (FL) in a single framework. It provides accelerated learning capacity and adaptive interpretation capabilities to model complex patterns and apprehends nonlinear relationships. ANFIS has been applied and practiced in various domains and provided solutions to commonly recurring problems with improved time and space complexity. Standard ANFIS has certain limitations such as high computational expense, loss of interpretability in larger inputs, curse of dimensionality, and selection of appropriate membership functions. This paper summarizes that the standard ANFIS is unsuitable for complex human tasks that require precise handling of machines and systems. The state-of-the-art and practice research questions have been discussed, which primarily focus on the applicability of ANFIS in the diversifying field of engineering sciences. We conclude that the standard ANFIS architecture is vastly improved when amalgamated with metaheuristic techniques and further moderated with nature-inspired algorithms through calibration and tuning of parameters. It is significant in adapting and automating complex engineering tasks that currently depend on human discretion, prominent in the mechanical, electrical, and geological fields.
The machine learning domain contains a wide variety of models based on the learning ability, adaptiveness, complexity, and scalability. Some of the popular techniques are Fuzzy Logic, Extreme Learning Machine, Boosting, Bagging, Artificial Neural Networks, etc. Many researchers used machine learning algorithms based on these techniques like regression, decision trees, random forest, stochastic gradient, Support Vector Regressors (SVR), etc. and its ensembles other optimization techniques . Hybrids of such techniques have been proposed and developed that tend to solve their deficiencies as well as provide robustness and powerful prediction capabilities. One such technique with the inherent potential of both neural networks and fuzzy systems is ANFIS , which provides great estimation accuracy, i.e., low Mean Magnitude of Relative Error (MMRE) and high Prediction (PRED).
ANFIS is the most popular neuro-fuzzy model for approximating highly complex, nonlinear systems. The key aspects of ANFIS are the accuracy using the precise fuzzy modelling and interpretability, which improves its generalization ability. ANFIS has gained prominence amongst researchers for its robustness in modelling fuzzy sets into crisp inputs and providing crisp outputs from the fuzzy rules for reasoning purpose. Ironically, ANFIS has to balance the accuracy-interpretability trade-off . The advantages and disadvantages of ANFIS have been discussed in Table 1. It is of considerable importance in ANFIS to find the type and number of membership functions, suitable to the process or system. ANFIS is generally very efficient until the number of inputs is below five . Modern engineering systems have more inputs as the complexity of the problem increases, for instance, signal processing in a highly chaotic environment, flood susceptibility detection in watershed management, precise coordination of I&C systems in a nuclear plant, etc.
Originally, ANFIS was designed with the use of Gradient Descent (GD) and Least Square Estimation (LSE) for optimizing its parameters. GD is a very popular optimization algorithm that is commonly used to train neural networks. It uses backpropagation method to calculate gradients, thus having the easiest system of computation. LSE method of optimization is very common in regression-based models. It calculates the least sum of squared errors, finding the optimal coefficients of the errors. However, these are not efficient to model complex engineering tasks that are highly nonlinear in nature and require precise control over the systems. Then, it provides an opportunity to improve the capability of ANFIS.
This table presents the advantages and disadvantages of the original ANFIS system, as designed by J.S. Roger Jang. These limitations are unsuitable for use in modern, real-world systems and, hence, need to be resolved to be deployed in production on the machines.
Abstract: Featured ApplicationThis article belongs to the Section Mechanical Engineering. AbstractThe paper proposes an adaptive fuzzy position control for a 3-DOF hydraulic manipulator with large payload variation. The hydraulic manipulator uses electrohydraulic actuators as primary torque generators to enhance carrying payload of the manipulator. The proposed control combines backstepping sliding mode control, fuzzy logic system (FLS), and a nonlinear disturbance observer. The backstepping sliding mode control includes a sliding mode control for manipulator dynamics and a PI control for actuator dynamics. The fuzzy logic system is utilized to adjust the control gain and robust gain of the sliding mode control (SMC) based on the output of the nonlinear disturbance observer to compensate the payload. The Lyapunov approach and backstepping technique are used to prove the stability and robustness of the whole system. Some simulations are implemented, and the results are compared to other controllers to exhibit the effectiveness of the proposed control.Keywords: fuzzy logic system; electro-hydraulic actuator; sliding mode control; backstepping technique; disturbance observer; manipulator
Owing to the significant number of hybrid generation systems (HGSs) containing various energy sources, coordination between these sources plays a vital role in preserving frequency stability. In this paper, an adaptive coordination control strategy for renewable energy sources (RESs), an aqua electrolyzer (AE) for hydrogen production, and a fuel cell (FC)-based energy storage system (ESS) is proposed to enhance the frequency stability of an HGS. In the proposed system, the excess energy from RESs is used to power electrolysis via an AE for hydrogen energy storage in FCs. The proposed method is based on a proportional-integral (PI) controller, which is optimally designed using a grey wolf optimization (GWO) algorithm to estimate the surplus energy from RESs (i.e., a proportion of total power generation of RESs: Kn). The studied HGS contains various types of generation systems including a diesel generator, wind turbines, photovoltaic (PV) systems, AE with FCs, and ESSs (e.g., battery and flywheel). The proposed method varies Kn with varying frequency deviation values to obtain the best benefits from RESs, while damping the frequency fluctuations. The proposed method is validated by considering different loading conditions and comparing with other existing studies that consider Kn as a constant value. The simulation results demonstrate that the proposed method, which changes Kn value and subsequently stores the power extracted from the RESs in hydrogen energy storage according to frequency deviation changes, performs better than those that use constant Kn. The statistical analysis for frequency deviation of HGS with the proposed method has the best values and achieves large improvements for minimum, maximum, difference between maximum and minimum, mean, and standard deviation compared to the existing method.
In , a comparison is presented between the proposed fractional-order (FO)-fuzzy-PID controller method and different types of control techniques such as optimized FO-Fuzzy-PID, PID, FO-PID, and Fuzzy-PID. The droop controller and PID controller are used with superconducting magnetic energy storage (SMES) to inject power to the microgrid during sudden load changes, thus achieving the frequency stability aim . The proposed control strategy in  depends on two main control actions. The first is injecting active power from the battery to reach a constant power between the load and generation where the generated power from RESs is intermittent. The second control action is related to the frequency deviation, in which the proposed method is used to damp the frequency fluctuation and to compensate for the low-inertia of the system. The issue of reducing the lifetime of a battery energy storage system (BESS) (which helps in damping frequency deviation through a large amount of charging and discharging) is addressed in , where an adaptive droop control method is proposed between the BESS and FC through the controlling of the power-sharing between FC and battery.
One of the newest optimization algorithms is the grey wolf optimization (GWO) algorithm based on the meta-heuristic optimization technique . The GWO algorithm is used in many applications of electrical power systems because of its simplicity and easy applicability . Moreover, the GWO has several advantages such as flexibility, fewer algorithm parameters, comprehensiveness, and fast programmability features. The PID controller gains are used with the integral time absolute error (ITAE) as inputs to the control process that depends on the GWO to optimize the value of the PID gains, in order to achieve the secondary frequency control of an isolated multi-microgrid . The particle swarm optimization (PSO) and GWO techniques are applied with adaptive fuzzy logic control based on the PI controller to obtain the optimal values of membership functions (MFs) in the regulation and control of microgrid frequency .
The coordination control strategy between RESs and FC-based energy storage systems (ESS) is presented in , where an adaptive fuzzy PID controller is proposed based on a simplified GWO algorithm for the LFC of a distributed power generation system considering generation rate constraints and time delays to include nonlinearity features. It also presents a comparison between several optimization algorithms including the simplified GWO algorithm to show its superiority over other methods. One of the most important applications of a hydrogen production unit is presented in  to overcome the large-scale power curtailment resulting from the connection between RESs and large-scale power systems. The hydrogen production unit is suitable for such an application, since it can have large-capacity and long-term absorption of electric energy. 781b155fdc