通过基于非线性自回归神经网络与外源输入 (NARX-NN) 的混合机器学习方法的BLDC电机的转速和扭矩建模
Muhammad Aseer Khan1, Husan Ali1, Dur-E-Zehra Baig2
1Department of Electrical and Avionics Engineering, Air University Aerospace and Aviation Campus Kamra, Attock, Pakistan.
PloS one
|November 21, 2025
概括
本研究介绍了一种混合机器学习模型,用于预测无刷直流电机转速和扭矩. 具有外源输入的先进非线性自回归神经网络实现了高精度,改善了运动控制.
科学领域:
- 电气工程 电气工程
- 控制系统 控制系统
- 机器学习 机器学习
背景情况:
- 无刷直流电机在工业中至关重要,但模拟它们复杂的非线性动力学以准确预测速度和扭矩仍然具有挑战性.
- 现有的方法难以高效率预测,需要新的方法.
研究的目的:
- 为准确建模无刷直流电机转速和扭矩响应提出混合机器学习方法.
- 通过使用先进的神经网络技术,提高非线性动态系统的预测准确性.
主要方法:
- 开发了一种混合方法,将非线性自回归神经网络与外源输入 (NARX) 和系统识别技术结合起来.
- 选择了最佳的时间延迟和神经网络层大小,以在多步进口信号下准确捕获波纹效应.
- 70-15-15数据分割用于培训,验证和测试,并进行额外的测试以进行概括.
主要成果:
- 拟议的模型实现了平均平方误差值低至[公式:参阅文本]的速度和[公式:参阅文本]的扭矩.
- 在所有数据阶段获得了1.000的速度和0.998的扭矩的一致回归系数.
- 这些模型在测试不同的输入信号时,在预测速度和扭矩方面表现出了强度和优越性.
结论:
- 开发的混合NARX模型为无刷直流电机的转速和扭矩提供了高准确度的预测.
- 这些发现证实了与现有文献相比,拟议方法的稳定性和卓越性能.
- 这些模型可以成为先进控制器的基础,以有效调节转速和减轻扭矩波动.
相关概念视频
Electro-mechanical Systems
1.6K
Electromechanical systems are intricate configurations that effectively combine electrical and mechanical elements to achieve a desired outcome. Central to many of these systems is the DC motor, a device that converts electrical energy into mechanical motion, enabling various applications ranging from simple fans to complex robotic mechanisms.
A key component of the DC motor is the armature, a rotating circuit positioned within a magnetic field. As an electric current passes through the...
A key component of the DC motor is the armature, a rotating circuit positioned within a magnetic field. As an electric current passes through the...
1.6K
Simplified Synchronous Machine Model
733
The Synchronous Machine Model is a fundamental tool in analyzing and ensuring the transient stability of power systems. This model simplifies the representation of a synchronous machine under balanced three-phase positive-sequence conditions, assuming constant excitation and ignoring losses and saturation. The model is pivotal for understanding the behavior of synchronous generators connected to a power grid, particularly during transient events.
In this model, each generator is connected to a...
In this model, each generator is connected to a...
733
Motor Units
7.4K
The motor unit is a fundamental component of the neuromuscular system and plays a crucial role in coordinating muscle contractions. It consists of a somatic motor neuron, which connects and controls multiple skeletal muscle fibers, forming a single functional segment. The axon of the motor neuron branches out and establishes synaptic connections known as neuromuscular junctions with individual muscle fibers within the motor unit.
Motor units come in different sizes, with smaller units...
Motor units come in different sizes, with smaller units...
7.4K
Motor Units
61.7K
A motor unit consists of two main components: a single efferent motor neuron (i.e., a neuron that carries impulses away from the central nervous system) and all of the muscle fibers it innervates. The motor neuron may innervate multiple muscle fibers, which are single cells, but only one motor neuron innervates a single muscle fiber.
61.7K
Node Analysis for AC Circuits
619
Consider an angioplasty system featuring a catheter equipped with a turbine, a critical tool for removing plaque deposits from coronary arteries. This intricate medical device operates using a circuit model reminiscent of a dual-node RLC circuit powered by a current-controlled voltage source.
To unravel the complexities of this system, nodal analysis is employed, a powerful technique founded on Kirchhoff's current law (KCL), which remains valid for phasors. AC circuits can effectively be...
To unravel the complexities of this system, nodal analysis is employed, a powerful technique founded on Kirchhoff's current law (KCL), which remains valid for phasors. AC circuits can effectively be...
619
Linear Approximation in Frequency Domain
332
Linear systems are characterized by two main properties: superposition and homogeneity. Superposition allows the response to multiple inputs to be the sum of the responses to each individual input. Homogeneity ensures that scaling an input by a scalar results in the response being scaled by the same scalar.
In contrast, nonlinear systems do not inherently possess these properties. However, for small deviations around an operating point, a nonlinear system can often be approximated as linear....
In contrast, nonlinear systems do not inherently possess these properties. However, for small deviations around an operating point, a nonlinear system can often be approximated as linear....
332


