Deep Learning Based Predictive Analysis of BLDC Motor Control

Porselvi, T.; Barathwaj, Sr Y Aouthithiye; Cs, Sai Ganesh; Sangeetha, S.; Priya, J Shalini

doi:10.1109/gcat55367.2022.9972193

Cited by 15 publications

(2 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Despite minor disturbances affecting the motor, the control system's robustness is demonstrated, with suggested improvements for future work. Meanwhile, a separate research paper by Porselvi et al [37] presents a DL approach for predicting BLDC motor speed, achieving remarkable results and providing unique insights into various performance parameters. The study concentrates on forecasting the real speed of a motor within a 75-s timeframe, spanning from 0 to 75 s. The forecasted output relies on load torque, electromagnetic torque, and reference speed, acting as inputs during this interval.…”

Section: Simulation Resultsmentioning

confidence: 99%

Analysis of DC motor for process control application using neural network predictive controller

Prasad,

Kumar,

Singh

2024

Eng. Res. Express

View full text Add to dashboard Cite

A DC motor is a critical actuator in process control systems. This study investigates the effectiveness of a deep learning (DL) based Neural Network Predictive Controller (NNPC) for precise DC motor speed control. The NNPC anticipates the motor’s future behaviour based on its current state and control inputs. The controller then optimally generates inputs to minimise tracking errors and enhance system performance. The NNPC demonstrated a remarkable reduction in Mean Squared Error (MSE), achieving a training MSE of 2.75 × 10−14 and the best validation MSE of 9.2023 × 10−14. These quantitative outcomes affirm the reliability and robustness of the proposed NNPC for speed control in DC motor systems across diverse applications.

show abstract

Section: Simulation Resultsmentioning

confidence: 99%

Analysis of DC motor for process control application using neural network predictive controller

Prasad,

Kumar,

Singh

2024

Eng. Res. Express

View full text Add to dashboard Cite

show abstract

“…It is much more capable of dealing with constraints by using an open-loop optimization and closed-loop feedback system to continuously evaluate and upgrade the vehicle mass in real-time. Even now, MPC uses a deep learning artificial neural network (DLANN) algorithm to control the motor's speed and torque, additionally providing a more robust, simple, and effective operation with less settling time [204]. Again, for future development, the MPC coupled with the PWM method can effectively reduce current and torque ripples at lower or higher speeds without changing the circuit topology [210].…”

Section: Figure 11 Model Predictive Control Strategies Of Torque Ripp...mentioning

confidence: 99%

Critical Review on Torque Ripple Sources and Mitigation Control Strategies of BLDC Motors in Electric Vehicle Applications

Prabhu,

Thirumalaivasan,

Ashok

2023

IEEE Access

View full text Add to dashboard Cite

In recent years, electric vehicles (EVs) have attracted a lot of attention and are rapidly growing trends today due to their ability to compete with and overtake fossil fuel-powered vehicles among all electrified transportation tools. The primary focus of EV evolution is on improving driving range and optimizing energy consumption, both of which are essential demands achieved through improved and developing motor performance. The brushless direct current (BLDC) motor is one of the most superior choices for dynamic applications in EVs, providing the highest power density and capability of any motor. BLDCs are gaining popularity in EVs not only for their high performance in speed and position controls but also for meeting the requirements of smooth torque maintenance with torque ripple mitigation. This paper provides an overview of various advanced control strategies, such as field-oriented control (FOC), direct torque control (DTC), intelligent control (IC), controlling input voltage (CIV), current shaping techniques (CST), model predictive control (MPC), and sliding mode control (SMC). These strategies are used to regulate the torque ripples produced in BLDC motors, aiming to achieve energy-efficient EV performance for various applications. Additionally, it describes a cloud-based control system coupled with electric motor drives to address challenges in predicting current vehicle conditions for improved power distribution between the motor and battery systems. Furthermore, recent concerns and difficulties in advancing torque ripple mitigation control strategies are highlighted, with comparisons and discussions for future EV research. Finally, an evaluative study on BLDC motor drive in EVs with different control strategies reveals its significance and potential outcomes. INDEX TERMS Brushless Direct Current (BLDC) motor, Cloud based torque control, Control structural architecture, Electric Vehicles (EVs), Various control strategies for torque ripple mitigation.

show abstract