PID controllers are widely used and adaptable to various types of systems. However, for the response to be adequate under different conditions, the PID gains must be adjusted. The tuning is made according to the difference between the reference value and the real value (error). This work presents a self-adjusting PID controller based on a backpropagation artificial neural network. The network calculates the appropriate gains according to the desired output, that is, the dynamic response desired which is composed of the transient part and the stationary part of the step response of a system. The contribution of the work is that in addition to using the error for network training, the maximum desired values of overshoots, settling times, and stationary errors were used as input data for the network. An offline training database was created using genetic algorithms to obtain the dynamic response data associated with PID gains. The genetic algorithm allows getting data in different operating ranges and allows using only stable gains combinations. The database was used for training. Subsequently, the neural network estimates an appropriate gain combination, adapting to the error and the desired response. The method performance is evaluated by controlling the speed of a direct current motor. The results indicate an average error of 4% for the database between the requested and system response. On the other hand, the gains estimated by the network in the test dataset (1544 combinations) did not cause instability and complying with the expected dynamic response in 86% of the dataset.

Backstepping is a control technique based on Lyapunov’s theory that has been successfully implemented in the control of motors and robots by several nonlinear methods. However, there are no standardized methods for tuning control gains (unlike the PIDs). This paper shows the tuning gains of the backstepping controller, using Genetic Algorithms (GA), for an Unmanned Aerial Vehicle (UAV), quadrotor type, designed for autonomous trajectory tracking. First, a dynamic model of the vehicle is obtained through the Newton‒Euler methodology. Then, the control law is obtained, and self-tuning is performed, through which we can obtain suitable values of the gains in order to achieve the design requirements. In this work, the establishment time and maximum impulse are considered as such. The tuning and simulations of the system response were performed using the MATLAB-Simulink environment, obtaining as a result the compliance of the design parameters and the correct tracking of different trajectories. The results show that self-tuning by means of genetic algorithms satisfactorily adjusts for the gains of a backstepping controller applied to a quadrotor and allows for the implementation of a control system that responds appropriately to errors of different magnitude.

In the contemporary world, where the escalating demand for energy and the imperative for sustainable sources, notably solar energy, have taken precedence, the investigation into solar radiation (SR) has become indispensable. Characterized by its intermittency and volatility, SR may experience considerable fluctuations, exerting a significant influence on energy supply security. Consequently, the precise prediction of SR has become imperative, particularly in the context of the potential proliferation of photovoltaic panels and the need for optimized energy management. Several works in the existing literature review the state of the art in SR prediction, focusing on trends identified using machine learning (ML) or deep learning (DL) techniques. However, there is a gap in the literature regarding the integration of optimization algorithms with ML and DL techniques for SR prediction. This systematic review addresses this gap by studying prediction models for SR that leverage metaheuristic optimization algorithms alongside artificial intelligence (AI) techniques, aiming primarily for maximum prediction accuracy. Metaheuristic algorithms such as Particle Swarm Optimization (PSO) and Genetic Algorithm (GA) have featured in 29% and 12.1% of the analyzed articles, respectively, while intelligent approaches like Convolutional Neural Networks (CNN), Extreme Learning Machine (ELM), and Multilayer Perceptron (MLP) have emerged as the predominant choices, collectively accounting for 43.9% of the studies. Analysis has encompassed studies examining SR across hourly, daily, and monthly intervals, with daily intervals representing 48.7% of the focus. Noteworthy variables including temperature, humidity, wind speed, and atmospheric pressure have surfaced, capturing proportions of 90%, 68.2%, 56%, and 41.4%, respectively, within the reviewed literature.

The direct current (DC) motors are widely used; therefore, they are subject to multiple studies, different control techniques or analyses require a dynamic DC motor model. The parameters are needed to complete the model, which can be challenging to obtain. Therefore, multiple parametric estimation techniques have been developed. This paper presents a metaheuristic cuckoo search algorithm modified for motors as a parametric estimation tool. A cost function is based on the current and velocity error obtained when an input voltage step is applied to the motor. The main difference with similar works is that we used the steady-state equations to determine the parameters. The algorithm proposed is compared with the Steiglitz-McBride and the original cuckoo search algorithms to evaluate its performance objectively. Simulated and experimental results show that the algorithm proposed can calculate the parameters with better accuracy than the original cuckoo search and Steiglitz-McBride. The modifications made to the original algorithm of the cuckoo search allowed finding the values of the parameters motor with a root mean square error of less than 0.1% for signals obtained with simulation and less than 1% for real signals sampled at 0.001 s.

Although healthcare and medical technology have advanced significantly over the past few decades, heart disease continues to be a major cause of mortality globally. Electrocardiography (ECG) is one of the most widely used tools for the detection of heart diseases. This study presents a mathematical model based on transfer functions that allows for the exploration and optimization of heart dynamics in Laplace space using a genetic algorithm (GA). The transfer function parameters were fine-tuned using the GA, with clinical ECG records serving as reference signals. The proposed model, which is based on polynomials and delays, approximates a real ECG with a root-mean-square error of 4.7% and an $R^2$ value of $0.72$. The model achieves the periodic nature of an ECG signal by using a single periodic impulse input. Its simplicity makes it possible to adjust waveform parameters with a predetermined understanding of their effects, which can be used to generate both arrhythmic patterns and healthy signals. This is a notable advantage over other models that are burdened by a large number of differential equations and many parameters.

This paper presents a physically constrained grey-box identification framework for electromechanical systems, illustrated through the dynamics of brushed DC motors. The method estimates all electromechanical parameters by minimizing a normalized residual that combines current, velocity, and steady-state algebraic constraints under a current-limit condition. Classical approaches such as least-squares and black-box identification often lack physical interpretability and do not explicitly enforce steady-state consistency, making their estimates susceptible to nonphysical parameter drift. The proposed formulation incorporates these physical constraints within a Levenberg–Marquardt scheme with signal normalization, enabling the joint minimization of current and velocity errors. Validation was performed using step-response data from two DC motors under both synthetic and experimental conditions. When applied to unfiltered measurements, the method maintained steady-state relative errors below 1% and achieved low trajectory discrepancies, with NRMSE in velocity between 2.6 and 3.2% and NRMSE in current between 0.9 and 1.2% across both motors. Embedding physical and steady-state constraints directly into the cost function improves robustness and ensures physically consistent parameter estimates, even under high measurement noise and without filtering. The approach provides a general strategy for dynamic system identification under physical consistency requirements and is suitable for rapid calibration, diagnostic monitoring, and controller tuning in robotic and mechatronic applications.