Optimization of a photovoltaic/wind/battery energy-based microgrid in distribution network using machine learning and fuzzy multi-objective improved Kepler optimizer algorithms.

In this study, a fuzzy multi-objective framework is performed for optimization of a hybrid microgrid (HMG) including photovoltaic (PV) and wind energy sources linked with battery energy storage (PV/WT/BES) in a 33-bus distribution network to minimize the cost of energy losses, minimizing the voltage oscillations as well as power purchased minimization from the HMG incorporated forecasted data. The variables are microgrid optimal location and capacity of the HMG components in the network which are determined through a multi-objective improved Kepler optimization algorithm (MOIKOA) modeled by Kepler's laws of planetary motion, piecewise linear chaotic map and using the FDMT. In this study, a machine learning approach using a multilayer perceptron artificial neural network (MLP-ANN) has been used to forecast solar radiation, wind speed, temperature, and load data. The optimization problem is implemented in three optimization scenarios based on real and forecasted data as well as the investigation of the battery's depth of discharge in the HMG optimization in the distribution network and its effects on the different objectives. The results including energy losses, voltage deviations, and purchased power from the HMG have been presented. Also, the MOIKOA superior capability is validated in comparison with the multi-objective conventional Kepler optimization algorithm, multi-objective particle swarm optimization, and multi-objective genetic algorithm in problem-solving. The findings are cleared that microgrid multi-objective optimization in the distribution network considering forecasted data based on the MLP-ANN causes an increase of 3.50%, 2.33%, and 1.98%, respectively, in annual energy losses, voltage deviation, and the purchased power cost from the HMG compared to the real data-based optimization. Also, the outcomes proved that increasing the battery depth of discharge causes the BES to have more participation in the HMG effectiveness on the distribution network objectives and affects the network energy losses and voltage deviation reduction.

The remarkable potential of machine learning algorithms in estimating water permeability of concrete incorporating nano natural pozzolana.

This paper aims to estimate the permeability of concrete by replacing the laboratory tests with robust machine learning (ML)-based models. For this purpose, the potential of twelve well-known ML techniques was investigated in estimating the water penetration depth (WPD) of nano natural pozzolana (NNP)-reinforced concrete based on 840 data points. The preparation of concrete specimens was based on the different combinations of NNP content, water-to-cement (W/C) ratio, median particle size (MPS) of NNP, and curing time (CT). Comparing the results estimated by the ML models with the laboratory results revealed that the hist-gradient boosting regressor (HGBR) and K-nearest neighbors (KNN) algorithms were the most and least robust models to estimate the WPD of NNP-reinforced concrete, respectively. Both laboratory and ML results showed that the WPD of NNP-reinforced concrete decreased with the increase of the NNP content from 1 to 4%, the decrease of the W/C ratio and the MPS, and the increase of the CT. To further aid in the estimation of concrete's WPD for engineering challenges, a graphical user interface for the ML-based models was developed. Proposing such a model may be effectively employed in the management of concrete quality.

Experimental Investigation into the Influence of the Process Parameters of Wire Electric Discharge Machining Using Nimonic-263 Superalloy.

Nimonic alloy is difficult to machine using traditional metal cutting techniques because of the high cutting forces required, poor surface integrity, and tool wear. Wire electrical discharge machining (WEDM) is used in a number of sectors to precisely machine complex forms of nickel-based alloy in order to attempt to overcome these challenges and provide high-quality products. The Taguchi-based design of experiments is utilized in this study to conduct the tests and analyses. The gap voltage (GV), pulse-on time (Ton), pulse-off time (Toff), and wire feed (WF), are considered as the variable process factors. GRA is used for the WEDM process optimization for the Nimonic-263 superalloy, which has multiple performance qualities including the material removal rate (MRR), surface roughness (SR), and kerf width (KW). ANOVA analysis was conducted to determine the factors' importance and influence on the output variables. Multi objective optimization techniques were employed for assessing the machining performances of WEDM using GRA. The ideal input parameter combinations were determined to be a gap voltage (GV) of 40 V, a pulse-on time (Ton) of 8 µs, a pulse-off time (Toff) of 16 µs, and a wire feed (WF) of 4 m/min. A material removal rate of 8.238 mm3/min, surface roughness of 2.83 µm, and kerf width of 0.343 mm were obtained. The validation experiments conducted also demonstrated that the predicted and experimental values could accurately forecast the responses.