Weighting Factor Design in Model Predictive Control of Power Electronic Converters: An Artificial Neural Network Approach
Weighting Factor Design in Model Predictive Control of Power Electronic Converters: An Artificial Neural Network Approach
复制标题
DOI：
10.1109/tie.2018.2875660
复制
发表时间：
2019-11-01
影响因子：
7.7
通讯作者：
Novak, Mateja
中科院分区：
文献类型：
--
作者：
Dragicevic, Tomislav;Novak, Mateja
本文提出用人工神经网络(ANN)来解决电力电子变流器有限集模型预测控制(FSMPC)中正在进行的研究挑战之一，即代价函数中加权因子的自动选择。这种方法的第一步是模拟详细的转换器电路模型或使用不同的加权系数组合多次运行实验。关键性能指标[例如，转换器的平均开关频率(f(Sw))、总谐波失真等]是从每个模拟中提取的。这些数据然后被用来训练神经网络，神经网络作为转换器的代理模型，可以为任何加权因子组合提供快速而准确的性能指标估计。因此，可以定义组合输出度量的任意用户定义的适应度函数，并且可以明确地找到优化给定函数的加权因子组合。在不间断供电系统FS-MPC稳压变流器的加权系数设计问题上，验证了所提方法的有效性。当应用于详细的仿真模型(误差小于3%)和实验试验台(误差小于10%)时，为两个示例性适应度函数设计的加权因子被证明对载荷变化是稳健的，并且产生接近预期的性能。
This paper proposes the use of an artificial neural network (ANN) for solving one of the ongoing research challenges in finite set-model predictive control (FSMPC) of power electronics converters, i.e., the automated selection of weighting factors in cost function. The first step in this approach is to simulate a detailed converter circuit model or run experiments numerous times using different weighting factor combinations. The key performance metrics [e.g., average switching frequency (f(sw)) of the converter, total harmonic distortion, etc.] are extracted from each simulation. This data is then used to train the ANN, which serves as a surrogate model of the converter that can provide fast and accurate estimates of the performance metrics for any weighting factor combination. Consequently, any arbitrary user-defined fitness function that combines the output metrics can be defined and the weighting factor combinations that optimize the given function can be explicitly found. The proposed methodology was verified on a practical weighting factor design problem in FS-MPC regulated voltage source converter for uninterruptible power supply system. Designed weighting factors for two exemplary fitness functions turned out to be robust to load variations and to yield close to expected performance when applied both to detailed simulation model (less than 3% error) and to experimental test bed (less than 10% error).