Light-emitting Diode (LED) lamps have been widely used due to versatility and energy efficiency. However, LEDs are nonlinear loads, the massive usage will inject harmonics into the lighting system, which has influenced the power quality. Total Harmonic Distortion (THD) is an important parameter to evaluate the power quality, but the prediction of THD for LEDs is a challenging task. This paper addresses this issue by designing harmonic characteristics detection experiment and using artificial intelligence algorithm. Firstly, LED lamps with different driving circuits were tested, the relevant data of each harmonic were sampled and analyzed. Then, a THD prediction method based on an improved AdaBoost algorithm is proposed. In this method, a Generalized Regression Neural Network (GRNN) model is established, and its parameters are optimized by Mind Evolution Algorithm (MEA) to improve the search ability of GRNN. On this basis, the AdaBoost algorithm is utilized to integrate multiple MEA-GRNN individuals to form a strong predictor, which improves the generalization ability of the model. To avoid the integration failure caused by improper selection of threshold value, a sigmoid adaptive factor is added to improve the accuracy of AdaBoost algorithm. Finally, the Ada-MEA-GRNN model is trained and simulated with the LED harmonic data collected by the experiment. The simulation results show that the prediction accuracy of the proposed method is better than BP and GRNN, which can reach 95.48%. Meanwhile, even if the input dimension is reduced, the error is still small.

中文翻译：

---

基于MEA-GRNN和改进的AdaBoost算法的LED谐波特性数据驱动的THD预测方法

发光二极管（LED）灯因其多功能性和能源效率而被广泛使用。但是，LED是非线性负载，大量使用会将谐波注入照明系统，从而影响了电能质量。总谐波失真（THD）是评估电源质量的重要参数，但是预测LED的THD是一项艰巨的任务。本文通过设计谐波特征检测实验并利用人工智能算法解决了这一问题。首先，对不同驱动电路的LED灯进行了测试，对每个谐波的相关数据进行了采样和分析。然后，提出了一种基于改进的AdaBoost算法的THD预测方法。通过这种方法，建立了广义回归神经网络（GRNN）模型，并通过思想进化算法（MEA）对参数进行了优化，以提高GRNN的搜索能力。在此基础上，利用AdaBoost算法将多个MEA-GRNN个体集成在一起，形成一个强大的预测因子，从而提高了模型的泛化能力。为了避免由于阈值选择不当而导致的积分失败，添加了S型自适应因子以提高AdaBoost算法的准确性。最后，通过实验收集的LED谐波数据对Ada-MEA-GRNN模型进行训练和仿真。仿真结果表明，该方法的预测精度优于BP和GRNN，可达到95.48％。同时，即使减小输入尺寸，误差仍然很小。AdaBoost算法用于整合多个MEA-GRNN个体，形成一个强大的预测因子，从而提高了模型的泛化能力。为了避免由于阈值选择不当而导致的积分失败，添加了S型自适应因子以提高AdaBoost算法的准确性。最后，通过实验收集的LED谐波数据对Ada-MEA-GRNN模型进行训练和仿真。仿真结果表明，该方法的预测精度优于BP和GRNN，可达到95.48％。同时，即使减小输入尺寸，误差仍然很小。AdaBoost算法用于整合多个MEA-GRNN个体，形成一个强大的预测因子，从而提高了模型的泛化能力。为了避免由于阈值选择不当而导致的积分失败，添加了S型自适应因子以提高AdaBoost算法的准确性。最后，通过实验收集的LED谐波数据对Ada-MEA-GRNN模型进行训练和仿真。仿真结果表明，该方法的预测精度优于BP和GRNN，可达到95.48％。同时，即使减小输入尺寸，误差仍然很小。为了避免由于阈值选择不当而导致的积分失败，添加了S型自适应因子以提高AdaBoost算法的准确性。最后，通过实验收集的LED谐波数据对Ada-MEA-GRNN模型进行训练和仿真。仿真结果表明，该方法的预测精度优于BP和GRNN，可达到95.48％。同时，即使减小输入尺寸，误差仍然很小。为了避免由于阈值选择不当而导致的积分失败，增加了S形自适应因子以提高AdaBoost算法的准确性。最后，通过实验收集的LED谐波数据对Ada-MEA-GRNN模型进行训练和仿真。仿真结果表明，该方法的预测精度优于BP和GRNN，可达到95.48％。同时，即使减小输入尺寸，误差仍然很小。