In human civilization, Water Pumping Systems (WPS) are fundamental for industrial, drinking, and agricultural applications. One of the best practical solutions for reducing grid load demand and supplying electricity in various regions is a locally installed standalone Solar Photovoltaic (SPV) - powered WPS. Generally, WPS is drawn to Brushless DC Motors (BLDCMs) among other motors because of their many benefits. However, adding battery banks to WPS can raise the maintenance needs and cost, which farmers cannot afford. This study thus explores and applies a sensorless speed control method of a BLDCM powered by SPV energy, eliminating the need for a battery. Partial Shading Conditions (PSCs) typically impair the power generated by SPV systems, and the conventional P&O mechanism fails, preventing the systems from producing maximum availability of electricity. This work integrates the Botox Optimization Algorithm (BOA) with the traditional P&O technique to address this issue. The Hybrid Botox Optimization-P&O (BOPO) method can efficiently harvest the most power from SPV under both normal and partial shade circumstances. For MPPT under PSC, the outcomes are contrasted with those of Modified Grey Wolf Optimization (MGWO), Particle Swarm Optimization (PSO), and Modified Invasive Weed Optimization (MIWO) algorithms. By integrating the BOPO technique with the inverter’s control method, the inverter also functions as a MPPT converter of the SPV unit, lowering system costs. Therefore, an additional DC-DC converter won’t be needed for the operation of MPPT. In order to validate the suggested system in both transient and steady state scenarios, extensive results are shown using OPAL-RT. Furthermore, this work presents hardware results based on dSPACE to validate the proposed method.

In the era of fast industrialization and urbanization manufacturing sectors need sophisticated automation to guarantee effective production monitoring and cost estimation. This work presents a Python-based graphical user interface (GUI) using multiple linear regression (MLR) in machine learning to maximize decision-making in industrial production. To precisely forecast production quantity (PQ), unit production cost (PC), total PC per item, and total manufacturing expenses on a fixed profit margin (PM) set up by the industry, the proposed approach incorporates theoretical assumption data nominated as modified synthetic dataset (MSD) of proportional industrial variables based on the economics of industrial operation. Embedded with a GUI, the suggested Python-based computational model provides high-accuracy production prediction and real-time cost estimation. Precise predictions are ensured by MSD of experimental data showing an exceedingly low mean square error (MSE) of 1.210139×10 ^–23 and coefficient of determination (R ² ) values close to 1.0. Moreover, a significant comparison of comparable machine learning (ML) techniques, featuring a combination of linear, regularized, kernel-based, and ensemble learning methods, was conducted on the same platform to assess the proposed MLR model as the optimal choice. By lowering hand computations and errors, this automated approach greatly improves manufacturing cost estimation and planning. For cost engineers and production managers, the GUI is a useful tool since it helps enable complex industrial decision-making and resource control in a very straightforward way. The results of this study show that the suggested GUI model is a dependable and useful tool for contemporary industrial sectors, therefore promoting better operational efficiency and cost-effectiveness in the case of the modern manufacturing sector.