A modified diagonal recurrent neural network (MDRNN) model is presented in this paper as a model that allows the modeling and control of nonlinear dynamic systems. In practical applications, neural network models may experience challenges such as slow convergence and limited generalization performance when applied to complex nonlinear dynamic systems. These limitations have been overcome via improvements to the original diagonal recurrent neural network (DRNN), in addition to enhancing adaptation capability and learning performance. Moreover, this paper also presents another better optimization strategy, which is the improved adaptive moment optimization (IAdam) strategy, an enhanced structure of the traditional Adam (adaptive moment estimation) optimization strategy. The proposed IAdam optimization method is able to dynamically adjust the weight variables of the proposed model so that it can be trained efficiently, and the model can be more adaptable under various circumstances in the system. The MDRNN model is analyzed in detail in many nonlinear dynamical systems, where it outperforms the standard neural network models both in terms of its accuracy and convergence rates. An indirect control scheme is used to implement an MDRNN-based controller to operate a nonlinear dynamical system. The dynamics of the proposed controller are simulated by varying the parameters and using a disturbance signal to determine the ability of the controller to recover. The simulation results show that our methodology offers both an accurate and consistent method of identification and control of complex dynamical systems, and therefore, it is a very useful tool in real applications of control systems, signal processing, and time series forecasting.

Efficient operation of a fuzzy-logic controller depends on the quality and compactness of its rule base. However, a large number of fuzzy rules often increases computational cost and memory usage. To overcome this limitation, this paper presents a Polar Fuzzy Regulator (PFR) optimized through the Puma Optimization (PO) algorithm for Automatic Generation Control (AGC) in a restructured power system comprising thermal and gas units. The proposed controller employs a generalized bell-shaped (gbell) membership function on the input side and explores multiple output membership functions, including gbell, psig, triangular, gauss 2 mf, and trapezoidal. The PO algorithm is used to determine optimal PFR parameters that minimize the Integral of Time multiplied Absolute Error (ITAE) performance index. Simulation results show that the PO-based PFR achieves faster frequency recovery and smoother tie-line power restoration than conventional genetic algorithm-based tuning methods. A sensitivity analysis with $\mathbf{\pm 2 0 \%}$ parameter variation validates the robustness and adaptability of the proposed scheme in diverse operating conditions.

In today's global economy, every sector increasingly demands open and competitive markets. The power industry, in particular, often seeks greater flexibility in electricity procurement for end users, aiming to benefit both utility companies and their customers. This work focuses on enhancing the frequency responsiveness of a restructured nuclear-gas-solar power system. To achieve this, a GA-optimized hybrid FOPI-FOPD and polar fuzzy controller is developed. The performance of the proposed controller is evaluated against several competing control strategies across a range of power contract scenarios. Through comparative analysis, the proposed approach is shown to be both practical and realistic. In real-world applications, the DPM matrix may vary due to fluctuations in the dynamic market economy. Additionally, the demand for supplementary power and load disturbances introduced by the DISCO may change over time. To assess robustness, the behaviour of the proposed controller is examined under these varying conditions using the same optimized parameters, thereby conducting a thorough sensitivity analysis.

Partial shading conditions cause suboptimal power output and intensify voltage differentials, leading to mismatch losses and localized potential degradation in solar cell performance. However, the impact of partial shading can be mitigated to a large extent through the reconfiguration of PV arrays. The proposed method group sequence rotation array (GSRA), a generalized reconfiguration strategy for total-cross-tied arrays applicable to both square and rectangular configurations. GSRA operates without additional MPPT hardware, sensors, or complex switching circuits, offering a low-cost and scalable solution. Simulations performed on 9 × 9 and 5 × 5 arrays, along with experimental validation on a 6 × 4 prototype, demonstrate that GSRA increases power extraction and reduces shading-induced losses. Compared with the conventional TCT topology, GSRA achieves approximately 40

The paper describes a new neural network design, which is known as the Local Recurrent Sigma-Pi Artificial Neural Network (LRSPANN), to model and control nonlinear dynamical systems. The given model includes local recurrent self-feedback links in the hidden layer, which contribute to the dynamic memory and make it possible to effectively represent the behavior of the temporal system. The backpropagation learning algorithm is a gradient-descent-based method that is effectively used in updating network parameters and reducing modeling error. A Lyapunov-based stability analysis is conducted to achieve reliable learning and closed-loop stability. The effectiveness of the proposed LRSPANN is tested with the help of comparative simulations with Sigma-Pi Artificial Neural Network (SPANN), Elman Recurrent Neural Network (ERNN), and Feed-Forward Neural Network (FFNN). The proposed model has the lowest mean squared error (MSE)4.7 & times;10(-7) of in Example 1 and a mean squared error of 6.1 & times;10(-8) in Example 2, which is better than any other compared network. These findings illustrate that the proposed methodology is the most accurate and efficient for modeling and controlling nonlinear systems.

This paper discusses the extensive research in hybrid renewable energy system (HRES) that demands the increasing need for eco-friendly and sustainable energy worldwide. The extensively used renewable energy resources mainly includes solar photovoltaic (PV) and wind. Though, due to their multi-distributed character do not favor stable and reliable grid-connected power generation. In this study, the integrated windphotovoltaic power system is model for grid support purposes. The proposed concept utilizes a voltage source converter (VSC) interfacing to the grid and encloses a wind turbine and solar panel with an associated photovoltaic array combined through a shared DC link. DC link voltage is regulated and both active power (P) and reactive power (Q) are controlled by synchronizing technology and pulse width modulation (PWM) in the VSC. The results of simulation shows that the power combination controller can perform the stable running, reasonable distribution power for sources and specified capacity in constant wind speed and solar irradiance. This hybrid scheme emerges as a reliable and efficient unfolding for smart grid systems and sustainable grid integration.

The study introduces an enhanced damping controller using a battery energy storage system to mitigate sub-synchronous resonance in transmission lines equipped with static series compensation associated with a doubly fed induction generator-based wind power facility. This project aims to create a resilient damping controller that ensures stability under diverse operating situations and to refine controller settings using an innovative optimization technique for enhanced damping efficacy. In contrast to traditional damping controllers, the suggested controller incorporates an additional damping signal integrated into the d – q axis of the control channels. The auxiliary damping signal utilizes angular speed deviation, obtained by a large-area measuring method, as its input signal. A hybrid method integrating eigenvalue analysis with an advanced particle swarm optimization technique is used to optimize damping performance across diverse operating situations by determining the best gain coefficients. The variability of wind speed and fluctuations in series compensation levels are assessed to determine the resilience of thef proposed controller in real-world and extreme circumstances. Time-domain simulations were conducted in MATLAB/Simulink to assess their efficacy. The findings confirm that the proposed upgraded controller successfully stabilizes all previously unstable system modes at wind speeds of 7 m/s, 9 m/s, and 11 m/s, as well as at compensation levels of 40%, 55%, and 60%. The suggested controller demonstrates enhanced damping performance and elevated damping coefficients relative to conventional damping controllers, signifying increased stability and resilience across various operating conditions.

This article presents a comprehensive modeling, controllability analysis, and robust controller design for a nonisolated time-multiplexed multiport fault-tolerant (TMMFT) DC–DC power electronic interface intended for light electric vehicle (LEV) applications. A detailed switched linear system (SLS) model for the TMMFT converter is developed by incorporating the effects of parasitic to improve modeling accuracy. From the SLS, a small-signal model (SSM) and nominal transfer functions are derived and validated experimentally. The small-signal transfer functions corresponding to multiple operating modes are also derived and validated experimentally. To ensure robust closed-loop operation, a PI controller design methodology based on the stability boundary locus approach in conjunction with Kharitonov’s theorem is introduced to explicitly account for system parameter uncertainties. In addition, sensitivity and complementary sensitivity characteristics are analyzed under both healthy and open-circuit switch fault (OCSF) conditions, demonstrating robust stability and effective disturbance rejection. The fault-tolerant capability of the converter is further validated through experimental evaluation under single- and multiswitch fault scenarios. The proposed control strategy ensures stable operation across multiple operating states, load variations, and fault conditions, thereby enhancing the reliability and performance of the TMMFT converter.

This study presents a novel approach for identifying nonlinear dynamical systems by developing a modified Jordan recurrent neural network (MJRNN) model. The proposed MJRNN is an extended version of the standard Jordan recurrent neural network (JRNN) architecture. In addition, an adaptive pruning strategy based on the significance of hidden neurons is introduced for artificial neural network (ANN) models to reduce computational complexity and enhance learning performance. The proposed pruning algorithm removes less significant hidden neurons during the training process, resulting in a more compact network structure. Two simulation examples are presented to evaluate the effectiveness of the proposed model. The performance of the MJRNN model is compared with conventional ANN architectures, including JRNN, DRNN, and FFNN, under both fixed and adaptive neuron configurations. The simulation results demonstrate that the proposed MJRNN model with the adaptive pruning strategy achieves superior performance compared with the other ANN models.

In this paper, a novel Modified Jordan Recurrent Neural Network (MJRNN) model is presented to identify complex nonlinear dynamical systems. The nonlinear dynamic system identification using artificial neural networks is the most commonly used method in control system engineering, due to their capabilities. The structure of the presented model is an extended version of the original Jordan recurrent neural network model. The parameter update equations are obtained by using the back-propagation optimization algorithm, which is the most frequently used method as a learning approach for the training of the proposed model's parameters. The effectiveness of the suggested neural network is evaluated in comparison to other neural networks model such as Jordan recurrent neural network(JRNN), Elman recurrent neural Network(ERNN), Diagonal recurrent neural network(DRNN), and Feedforward neural network(FFNN) model. The robustness of the proposed model is also tested with parameter variation and disturbance signal. The simulation results have shown that the proposed model performs better than the other neural network models.

With the advent of AI-based image synthesis tools and techniques, Deepfakes have become a serious problem as they pose a massive threat to one’s information security and personal privacy. Several architectures have been proposed to achieve robust Deep Fake detection. However, these methods suffer a drastic drop in performance if the images are visually degraded or have low resolution. To resolve these two issues, a novel FreqFaceNet model has been proposed that employs two novel attentions namely, Wavelet Attention and Fourier Attention, for extracting important frequency-based features from low-resolution images. The extraction of frequency-based features ensures minimal interference of noise due to image compression or low resolution. The proposed model excels on two public benchmark datasets—the DFDC and CelebDF. On the DFDC dataset, FreqFaceNet achieves 98.041

Several new rivals are entering the market as a result of the global restructuring of the electric power sector, which is also intensifying competition among existing market players. Better services, greater choices, and less expensive power are all intended to benefit consumers. For such systems to be more reliable, new control techniques with hybrid ESS are crucial. The CSOA-based hybrid ESS for a restructured T-G-S power system combines a polar fuzzy controller (PFC) with an FOPID controller. Testing is done on this controller’s resilience with CTD, random load demand, and parameter uncertainty. Additionally, a reconstructed N-G-S system is used to assess the viability of the suggested controller. A CSOA-based combined FOPID controller and polar fuzzy controller using hybrid ESS can improve frequency responses for Area-1 and Area-2 by 15.59% and 21.83%, respectively, and enhance the response of power variation of the tie-line under contract violation by 27.16% when compared to the CSOA: PIIʎDDµ controller. The effectiveness of a CSOA-based combination (1 + FOID) controller and a polar fuzzy controller for a restructured T-H-G power system is demonstrated in another study. Other controllers, including GA: 1 + PFC, SOA: FOPID, SOA: PID, GA: PID, and OARs, are used to verify its performance. These controllers include a variety of linkages, including a control variable ∆Pdc with the turbine’s controller. The proposed control scheme has the lowest cost function among various control strategies and has been shown to outperform several existing control methods. Moreover, it offers incredibly dependable performance under different load conditions.

An artificial respiratory system provides support to critically ill patients. Optimizing the control of airway pressure in an artificial respiratory system is difficult due to its non-linear characteristics. A PID controller is most widely used for artificial respiratory systems. This paper presents the optimization of a PID controller for controlling airway pressure in an artificial respiratory system based on a Teaching Learning-Based Optimization Algorithm. The artificial respiratory system is modeled mathematically, and a transfer function is derived to design the proposed controller. A comparative study of the proposed TLBO-based controller is done with a Particle Swarm Optimization, PSO-based controller, and a conventional Zeigler-Nichols tuned controller in terms of performance indices. The proposed controller was also tested for robustness by varying lung compliance and leakage resistance from - 20

Supervisory control and data acquisition (SCADA) systems play a crucial role in monitoring the behavior of critical process variables and integrating geographically dispersed subsystems within industrial plants. The majority of critical infrastructure networks like the production of electricity, mining deposits, natural gas, oil pipelines, heating systems and chemical product distribution use SCADA for monitoring, control and supervision. This paper presents a Programmable logic controller (PLC) and SCADA-based control framework to automate the process industry plant and monitor all the processes using a single-screen human-machine interface (HMI). This paper aims to address a dynamic real-world problem for the mixing of raw materials, filling of final product composition, capping, labeling and sorting of containers based on both size and type (metallic and non-metallic) using a single assembly line. In this context, a ratio control framework is proposed for adjusting the ratio and mixing of raw materials. The OMRON (NX1P2-9024DT1) PLC controls the entire process, with its programming carried out using the ladder programming language in Sysmac Studio automation software. Wonderware Intouch SCADA software is used to visualize the two stages independently. A mathematical and simulation model is proposed to minimize the assembly line timings, the workforce and overall cost of production. The developed model is applied in a real-life case study of an assembly line from a chemical process industry supplier in northern India. In addition, the results of a real-world case study verify the design for effectively balancing a real-world assembly line and show that the proposed system improves the productivity, efficiency, throughput, workforce, cost and time of a process industry.

This study introduces a newly developed Modified Sigma-Pi Neural Network (MSPNN) architecture designed to identify the dynamics of the plant. The proposed structure is an extension of the classical sigma-pi neural network (SPNN) and includes a self-feedback loop at the output node of the output layer. Since sigma-pi artificial neural networks contain additive and multiplicative units in their structure. We apply the back-propagation optimization algorithm to train the proposed MSPNN model. The results of the proposed neural network are compared with preexisting models, such as the Jordan neural network, the feedforward neural network, and the sigma-pi neural network. An analysis of the simulation data indicates that the proposed architecture of MSPNN is more effective than the other models.

This paper presents metaheuristic algorithm-based controllers for level control of conical tank system. Due to the conical shape of the tank, level control becomes a nonlinear problem. One of the industry's most widely used types of controllers is the PID controller. It becomes challenging to tune or choose PID gains when using PID controllers in nonlinear processes or plants. In these situations, conventional tuning approaches do not produce the expected outcomes. The PSO, AVO, and TLBO algorithms are used in the suggested method to adjust the PID gains. The step responses obtained are compared with the conventional IMC tuned response. The AVO tuned and TLBO tuned PID controllers gave better response as compared to PSO tuned controller and IMC tuned controller in terms of rise time and overshoot.

The growing shift toward a free market framework across all sectors of the global economy has significantly influenced the power industry. In this evolving landscape, procurement flexibility has become a critical factor for power providers, enabling efficient energy supply to end-users and benefiting both consumers and businesses. The primary objective of this research is to evaluate the performance of a composite energy storage system (ESS) integrated with a hybrid control strategy that combines a cascade FOPI-FOPD controller and a polar fuzzy controller. The goal is to enhance the frequency regulation capability of a restructured nuclear-gas-solar (N-G-S) power system operating under deregulated conditions. The proposed methodology involves applying the same set of optimized controller parameters to multiple operating scenarios to ensure a fair and consistent performance assessment. Additionally, the Disco Participation Matrix (DPM) is varied to reflect the dynamic nature of the market economy, where load disturbances induced by distribution companies (DISCOs) and their corresponding power demands can fluctuate significantly. The key findings demonstrate that the proposed control strategy effectively improves system frequency response, enhances system stability under varying market conditions, and exhibits strong adaptability to different DPM scenarios. These results confirm that the approach is both practical and robust, making it suitable for realworld implementation in modern deregulated power systems.

Rapid transformations are prevalent in today’s electric power network. One of the primary operational responsibilities of a utility is automatic generation control (AGC), which tracks fluctuations in demand while preserving system frequency, net tie-line exchanges, and optimal generation set points. Therefore, it is crucial to continuously explore advanced methods for situational management. This research investigates a restructured thermal system featuring 3% generation rate constraint (GRC). The system employs three controllers: PI ${ }^{\mathrm{A}} \mathrm{D}^{\mu} \mathrm{D}^{2}$, fractional-order PID (FOPID), and conventional PID. The skill optimization algorithm (SOA) tunes the $\mathrm{PI}^{\mathrm{A}} \mathrm{D}^{\mu} \mathrm{D}^{2}$ controller. All three controllers are applied in the proposed system, with a 10% step load deviation introduced in each control region under varying power transactions. The performance of the $\mathbf{P I}^{\boldsymbol{A}} \mathbf{D}^{\boldsymbol{\mu}} \mathbf{D}^{\mathbf{2}}$ controller is compared with that of the FOPID and PID controllers. The assessment of sensitivity is performed by modifying system parameters to gauge resilience. The presentation of the simulation results highlights the unique characteristics and advantages of this study.

This paper presents a robust voltage-mode controlled (VMC) strategy and controllability analysis of a time-multiplexed dc-dc multiport (TMDCM) converter for non-minimum phase (NMP) conditions. The instability mitigation is presented using a systematically designed PI controller using the stability boundary locus (SBL) method and Kharitonov's theorem, incorporating structured uncertainties and external disturbances. A robust stability region is defined within the K-p and K-i plane, and a section with optimal gain values to meet the desired performance criteria. The proposed approach uses voltage feedback from both the output ports of the TMDCM converter. Additionally, it inherently accounts for input and load variations, enhancing voltage regulation performance. A robust single-loop voltage-mode controller with structured uncertainties is analytically designed for a time-multiplexed switched-boost converter exhibiting a right-half-plane (RHP) zero. The switched-boost mechanism, combined with time-multiplexed control, enables a multiport converter output that provides bidirectional functionality for charging and discharging management of the battery energy storage system, along with other load output ports. The laboratory prototype is developed, and the real-time performance of the converter is demonstrated for effective voltage regulation under varying source and load conditions, confirming controller robustness, non-fragility, and improved disturbance rejection.

The operation of the power system involves both conventional and contemporary controlling techniques related to the transfer of power from one location of generation to another location of consumption. Regarding their operational and observational performance in a wide area network system, they are in conflict with one another. The contemporary marine power system. The amount of electricity needed on a daily basis has significantly increased in recent years. One of the main limitations in the fields of power transmission and electricity generating is power limits. While the new maritime power system is dynamic and more observable in nature, the conventional system uses a non-dynamic type controller. Power electronic devices such as SCR, MOSFET, IGBT, GTO, Power BJT, and others are frequently used in the design of modern power controllers. Power can be delivered to or absorbed by a system in both modes thanks to the dynamic controller. A controller device is a useful instrument that may also reduce a network system's power outage. A number of metrics, including the system's voltage profile, real power, and reactive power using FACTS devices, such as UPFC, are covered in the study. For more accurate measurement of each of these parameters on each bus, the WLS Technique is chosen. The IEEE 14 Bus system using the WLS Technique and FACTS device integration is used to demonstrate the suggested paradigm. The simulation platform, which is based on MATLAB, is used to design and manage the model.