南京航空航天大学学报（英文版）2023，Vol.40Issue(3)：323-335,13.DOI:10.16356/j.1005-1120.2023.03.008
基于视听融合的宽频带振动频谱提取
Extraction of Broadband Vibration Spectrum Based on Audio-Visual Fusion
摘要
Abstract
Vibration spectrum extraction is essential for fault diagnosis of rotating machinery.Environmental diversification and the presence of noise limit the performance of traditional single-modal vibration extraction methods.Since visual and audio signals have different sampling frequencies,noise and environmental constraints,audio-visual fusion can effectively solve the problem caused by single modality.Based on this,this paper proposes a wideband spectrum extraction method based on an audio-visual fusion deep convolutional neural network,which fully fuses the effective information of different modalities to complement each other.The proposed model uses a dual-stream encoder to extract features from different modalities,and a deep residual fusion module extracts high-level fusion features and feeds them to the decoder.The experimental results show that the performance of this model is superior to the latest vibration extraction methods,and the proposed model outperforms other state-of-the-art models such as RegNet,MFCNN,and L2L,which improves the accuracy of vibration spectrum extraction by 15％ in noisy environment.关键词
振动频谱提取/视听融合/卷积神经网络/故障诊断/深度学习Key words
vibration spectrum extraction/audio-visual fusion/convolutional neural network/fault diagnosis/deep/learning分类
信息技术与安全科学引用本文复制引用
程遥,于若颜,彭聪..基于视听融合的宽频带振动频谱提取[J].南京航空航天大学学报（英文版）,2023,40(3):323-335,13.基金项目
This work was supported by the Na-tional Science Foundation of China(No.62122038)and the Natural Science Foundation of Jiangsu Province(No.BK20211565). （No.62122038）
