Efficient Cuk-Negative Luo Integrated Converter for Hybrid Solar–Wind Systems fed BLDC-Driven Industrial Pumps with Clouded Leopard Optimization Algorithm and Systems-Biology Informed Neural Network

Brushless DC (BLDC) motors and hybrid solar–wind systems provide an effective and environmentally friendly way to power industrial pumps. These systems combine solar and wind energy sources to ensure a consistent and reliable power supply, utilizing the complementary characteristics of renewable resources. Hybrid solar–wind systems frequently suffer from their reliance on the environment, which can result in uneven energy output when used to power industrial pumps. This paper proposes an Efficient Cuk-Negative Luo Integrated Converter for Hybrid Solar-Wind Systems fed BLDC driven Industrial Pumps with Clouded Leopard Optimization Algorithm and Systems-Biology Informed Neural Network. The proposed hybrid technique is the joint execution of each the Clouded Leopard Optimization Algorithm (CLOA) and Systems-Biology Informed Neural Network (SBINN). Hence, it is named as CLOA–SBINN. The CLOA method is utilized to maximize the variables of the PID controller. The SBINN is used to predict the gain parameter of the PID controller. The goal is to optimize the PID controller’s performance parameters and minimize control errors for the Cuk-Negative Luo Integrated Converter system. Introduces a Cuk-negative Luo integrated (CLIC) DC–DC converter designed for interfacing a hybrid solar PV-wind system intended for BLDC-driven Industrial Pumps. The proposed system utilizes a single Cuk-negative Luo converter that combines common components from both Cuk and negative Luo converters. The study involves a solar photovoltaic and a wind system with a capacity of employing Maximum Power Point Tracking (MPPT). A three-phase (3[Formula: see text]) inverter is used to link the BLDC motor to the output voltage of the CLIC. It is also intended to regulate the BLDC motor’s speed. The proposed strategy is put into practice on the MATLAB platform. The proposed method provides better results than the existing methods, like Modified Invasive Weed Optimization (MIWO), Whale Optimization Algorithm (WOA) and Grey Wolf Optimization (GWO). The simulation result of the proposed method attains 1.05% lower Peak overshoot, 0.9% lower settling time and attains 98% higher efficiency of CLIC.