用麦克风+数据驱动法，精准识别42类机械故障类型与严重程度。
Intelligent Fault Diagnosis of Type and Severity in Low-Frequency, Low Bit-Depth Signals
- 基于声音信号的多特征融合方法，结合时频分析与统计特征。
- 8kHz/8bit低资源下达99.54%准确率，仅需6棵树的XGBoost模型。
- 适合边缘部署的轻量级故障诊断，尤其适用于资源受限场景。
本研究针对旋转机械的智能故障诊断（IFD），采用单麦克风和数据驱动方法，成功识别42类故障类型与严重程度。研究基于不平衡的MaFaulDa数据集，旨在兼顾高精度与低资源消耗。测试中涵盖采样、量化、归一化、静音去除、维纳滤波、缩放、分窗、增强及XGBoost分类器调优等配置。通过时间、频率、梅尔频率及统计特征分析，在8 kHz、8 bit配置下，仅用6棵提升树即实现99.54%的准确率和99.52%的F-Beta得分。仅使用MFCC及其一阶、二阶导数时，准确率达97.83%，F-Beta为97.67%。通过贪心包裹式特征选择，选取50个特征（多为MFCC导数）后，准确率为96.82%，F-Beta达98.86%。
原文摘要 · Abstract (English)
This study focuses on Intelligent Fault Diagnosis (IFD) in rotating machinery utilizing a single microphone and a data-driven methodology, effectively diagnosing 42 classes of fault types and severities. The research leverages sound data from the imbalanced MaFaulDa dataset, aiming to strike a balance between high performance and low resource consumption. The testing phase encompassed a variety of configurations, including sampling, quantization, signal normalization, silence removal, Wiener filtering, data scaling, windowing, augmentation, and classifier tuning using XGBoost. Through the analysis of time, frequency, mel-frequency, and statistical features, we achieved an impressive accuracy of 99.54% and an F-Beta score of 99.52% with just 6 boosting trees at an 8 kHz, 8-bit configuration. Moreover, when utilizing only MFCCs along with their first- and second-order deltas, we recorded an accuracy of 97.83% and an F-Beta score of 97.67%. Lastly, by implementing a greedy wrapper approach, we obtained a remarkable accuracy of 96.82% and an F-Beta score of 98.86% using 50 selected features, nearly all of which were first- and second-order deltas of the MFCCs.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。