对DC-DC变换器进行有效的反馈控制，避免进入混沌态的前提是能根据变换器输出信号的特性，对变换器的工作行为做出正确的判断，并采取相应的控制措施。该文以PWM型BUCK变换器为研究对象，对其在不同电路参数下的输出信号进行分析研究，提出并证明用傅里叶描述符法提取输出信号特征值来作为判断变换器工作行为的依据。为实现用神经网络对变换器工作行为进行智能化监控奠定了基础。The output signal of the PWM BUCK converter under different circuit parameters has been analyzed. The Fourier des criptor method to extract output signals characteristics is put forward to identify and classify the behavior of the DC-DC converter. This method shows a way to watch and control DC-DC converter intelligently by using neural network.