Machine learning-based secure data analyzing for FPGA-based solar PV FED speed control of brushless DC motor using versatile threshold optimization technique

Abstract

The predicted global energy emergency expected shortly is due to the fast exhaustion of conventional fossil non-renewable energy source assets and reliably decreasing expenses of solar photovoltaic (SPV) modules. This photovoltaic (PV) power conversion stage prompts an expanded cost, size, unpredictability and diminished effectiveness for automotive applications. As an advanced system, the solar PV fed brushless direct current motor (BLDCM) is being used for most of the automotive applications. A primary control method fit for working the solar PV array at its peak power utilizes a conventional voltage source inverter (VSI) to control proposed fractional order BLDCM chaos control utilizing versatile threshold optimization (VTO) algorithm. The SPV is used as primary sources while the battery as reinforcement. The proposed control takes out the BLDCM phase using current control techniques. No extra power is related to the speed control of BLDCM and its fine start. The suitability of proposed framework is shown through its execution assessment utilizing MATLAB2017a programming in light of the simulated results and experimental approval on a created model, under practical operating conditions. Execution of the proposed FPGA-based control drive of BLDC motor is likewise researched through experimental test setup utilizing SPARTAN-6 FPGA, the run-time data are analyzed through IOT network using Adaptive Least Square Regression. The proposed system simulation result is justified by the hardware result.