基于神经网络方法的峰值电流控制Boost变换器数据驱动建模

A Data-driven Model of Peak Current Control Boost Converter Based on Neural Network Method

开关电源是一种高频电能转换装置,在许多领域有着广泛的应用。然而,如何快速、准确地对变换器进行建模仍是一个亟待解决的问题。针对峰值电流控制的Boost变换器,提出一种基于神经网络(Neural network,NN)的数据驱动建模方法进行损耗建模分析。为了选择数据驱动模型的关键输入输出参数,对Boost变换器的工作机理进行了分析。然后,介绍了基于神经网络的数据驱动建模方法,并将其应用于Boost变换器的建模。最后,用该方法对系统的输入特性和损耗特性进行了分析。与传统的机理建模方法相比,数据驱动建模能绕开复杂的内部机理,利用数据之间的映射关系所建立的模型具有速度快、精度高的优点。

Switching power supply is a kind of high frequency electric energy conversion device and is widely applied to many fields.However,how to model the converter quickly and accurately remains to be solved.A data-driven modeling method is proposed to analyze the power loss of a peak current controlled Boost converter by UC3842 control chip based on neural network(NN).In order to select the key input and output parameters for data-driven model,the operation mechanism of the Boost converter is studied.Then,data-driven modeling method based on neural network is introduced and applied to model the Boost converter.Finally,the input characteristic and the inner loss characteristic are analyzed by the proposed method.Compared with traditional mechanism modeling method,data-driven modeling can bypass the complex internal mechanism and the model established by using the mapping relationship between data has the advantages of high speed and high accuracy.