期刊文献+

基于改进生成对抗网络的工业炉燃烧器噪声分类研究

Research on Noise Classification of Industrial Furnace Burner Based on Improved Generative Adversarial Network
下载PDF
导出
摘要 工业炉燃烧器噪声分类过程中易受到不均匀样本、非线性和工作环境等问题的干扰,噪声信号分离难度比较大,导致分类效果不佳。为了解决上述问题,提出基于改进生成对抗网络的工业炉燃烧器噪声分类方法。采用组合传感器采集工业炉燃烧器信号,通过声能叠加算法分离出噪声信号。采用小波包分解算法提取噪声信号特征,将提取的特征输入到改进后的生成对抗网络中,改进生成对抗网络通过分类函数完成工业炉燃烧器噪声分类。实验结果表明,所提方法的工业炉燃烧器噪声信号特征提取效果好、分类精度高、分类时间短,分类结果具备可靠性。 In the process of classifying industrial furnace burner noise,it is prone to interference from issues such as uneven samples,nonlinearity,and working environment,making it difficult to separate noise signals,resulting in poor classification performance.In order to solve the above problems,a noise classification method of industrial furnace burner based on improved Generative adversarial network is proposed.A combination sensor is used to collect signals from industrial furnace burners,and noise signals are separated through the acoustic energy superposition algorithm.The Wavelet packet decomposition algorithm is used to extract the noise signal features,and the extracted features are input into the improved Generative adversarial network.The improved Generative adversarial network completes the noise classification of industrial furnace burner through the classification function.The experimental results show that the proposed method has good feature extraction performance,high classification accuracy,short classification time,and reliable classification results for industrial furnace burner noise signals.
作者 王陆阳 张晓军 赵旭鹏 WANG Luyang;ZHANG Xiaojun;ZHAO Xupeng(Beijing Chemical and Occupational Disease Prevention Institute,Beijing 100093,China)
出处 《工业加热》 CAS 2024年第6期62-66,共5页 Industrial Heating
基金 北京市化工职业病防治院2020年院长基金(ZFY2003002)。
关键词 改进生成对抗网络 工业炉燃烧器 噪声分类 声能叠加算法 小波包分解算法 improving the generative adversarial network industrial furnace burner noise classification acoustic energy superposition algorithm wavelet packet decomposition algorithm
  • 相关文献

参考文献14

二级参考文献73

共引文献34

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部