为提高信号调制识别的能力 ,提出了一种以最直接、最直观的信号波形的复杂度 -分形维数为特征 ,并运用测度理论来组合多个在小信噪比范围内对通信信号调制类型有较高识别率的分类器 ,从而实现大信噪比范围内识别率明显改善的新方法 ,同时 ,应用该方法也可简化单个分类器的设计 ,提高分类识别效率。计算机模拟结果证实了此方法的有效性 In order to improve the capability of signal modulation recognition, this paper proposes a method which combines the complexity of the most direct and intuitive signal waveform - fractal dimension and uses the measurement theory to combine multiple modulations of communication signals in the small signal-to-noise ratio And a classifier with a higher classification rate to achieve a significantly improved recognition rate within a large signal-to-noise ratio range. Meanwhile, this method also simplifies the design of a single classifier and improves classification efficiency. Computer simulation results confirm the effectiveness of this method