The manual tuning of controller parameters, for example, tuning proportional integral derivative (PID) gains often relies on tedious human engineering. To curb the aforementioned problem, we propose an artificial intelligence-based deep reinforcement learning (RL) PID controller (three variants) compared with genetic algorithm-based PID (GA-PID) and classical PID; a total of five controllers were simulated for controlling and trajectory tracking of the ball dynamics in a linearized ball-and-plate (B&P) system. For the experiments, we trained novel variants of deep RL-PID built from a customized deep deterministic policy gradient (DDPG) agent (by modifying the neural network architecture), resulting in two new RL agents (DDPG-FC-350-R-PID & DDPG-FC-350-E-PID). Each of the agents interacts with the environment through a policy and a learning algorithm to produce a set of actions (optimal PID gains). Additionally, we evaluated the five controllers to assess which method provides the best performance metrics in the context of the minimum index in predictive errors, steady-state-error, peak overshoot, and timeresponses. The results show that our proposed architecture (DDPG-FC-350-E-PID) yielded the best performance and surpasses all other approaches on most of the evaluation metric indices. Furthermore, an appropriate training of an artificial intelligencebased controller can aid to obtain the best path tracking.

No abstract

An increasing desire is to produce eco-friendly materials for varied engineering applications, such as natural fiber-reinforced composites (NFRCs). Although many research works on natural fiber polymer matrix composite exist, not much is known on the thermo-mechanical properties of acetic acid-treated particulate banana-sisal fiber reinforced polyester composite. Additionally, establishing the fiber constituent with a detrimental effect on thermal and mechanical properties for acetic acid-treated particulate banana-sisal reinforced polyester matrix composite is not well known. This work aims to examine the effect of banana-sisal particulate fiber on the thermal and mechanical properties of banana-sisal reinforced polyester matrix composites to address the gap. The composites were produced via the mechanical stir mix technique. Thermal, Fourier-transform infrared spectroscopy (FTIS), compressive, flexural, and impact analysis were conducted according to appropriate test standards. The results revealed that the thermal properties of the developed composites were not dependent on hybridization. Also, hybridization significantly enhanced the compressive and flexural properties, with 70B/30S and 50B/50S particulate fiber reinforced polyester matrix composite found to have the most superior compressive and flexural properties. A major contribution of this study is that the impact properties of the developed composites were dependent on the fiber composition and decreased as the sisal content percentage increased. In general, reinforced polyester matrix composite with 70B/30S particulate fiber has a preferable combination of thermal and mechanical properties.

Maximum power point tracking (MPPT) entails constraining photovoltaic (PV) modules to operate under a specified power condition. It has previously been shown that some meta-heuristic techniques often suffer from steady-state oscillations around maximum points and experience difficulty in adapting to environmental variations, such as irradiation and/or temperature. To address the aforementioned limitation, this work proposed an adaptable reinforcement learning (RL) technique based on a novel deep deterministic policy gradient (DDPG) agent and a reward function. The actor–network top layer uses a sigmoid activation function and the critic–network contains bottleneck layers with non-uniform nodal distributions as well as exponential linear unit (ELU) activation functions in some of the layers. The RL based on DDPG method was compared with Particle Swarm Optimization (PSO) and Perturb-and-Observe (P&O) in order to determine the optimal duty-cycle command needed for controlling the PV modules MPPT. All the investigated systems were implemented in MATLAB/Simulink. The results show that the proposed RL technique based on DDPG agent yielded superior tracking efficiency than all the other approaches. However, as the step change in irradiation at a constant temperature increases, the RL technique based on DDPG agent shows a decrease in tracking efficiency.

Many research works on Weibull parameter estimation has focused on graphical or analytical techniques, with little effort devoted towards the use of population based optimization algorithm. Accurate estimation of failure distributive parameter such as Weibull is a key requirement for efficient reliability analysis. In this study Particle Swarm Optimization Algorithm (PSOA), with particle position and velocity iteratively updated was used to estimate Weibull parameters. Probability density function and reliability plots were generated using the results obtained. Generally, PSOA shows better parameter estimation in comparison with analytical method based on Maximum Likelihood Estimator (MLE).