Investigating the Impact of Signal Resolution on Machine Learning based Multi-Class Fault Detection

被引:0
作者
Akin, Vehbi [1 ]
Mete, Mutlu [2 ]
机构
[1] McMillen High Sch, Murphy, TX 75094 USA
[2] Texas A&M Univ Commerce, Dept Comp Sci & Informat Syst, Commerce, TX USA
来源
17TH IEEE DALLAS CIRCUITS AND SYSTEMS CONFERENCE, DCAS 2024 | 2024年
关键词
signal resolution; machine learning; classification; ADC; electric motors; bearing faults;
D O I
10.1109/DCAS61159.2024.10539911
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Signal resolution is crucial for diverse applications, notably impacting accuracy, signal-to-noise ratio, and system performance. Today, microcontrollers (MCUs) designed for industrial purposes provide analog-to-digital converter (ADC) resolutions ranging from 10 to 16 bits. Therefore, evaluating the ADC resolution of machine learning algorithms is crucial to enhance the system's performance and cost-effectiveness. This study explores the impact of signal resolutions of 10, 11, 12, and 16-bit sensor data, emphasizing their significance in machine learning classification tasks specifically aimed at motor fault detection. By conducting controlled experiments, this study utilizes a comprehensive sensor dataset obtained from two industrial motors to assess the effects on signal quality and information retrieval. Since AC drives account for over 50% of global electricity consumption and find widespread use in various industrial applications, the findings shed light on the trade-offs associated with different resolution levels in real-world applications, particularly industrial settings. The research contributes to signal processing understanding, aiding the selection of resolutions for specific contexts, and facilitating informed decisions in motor-driven systems and machine learning classification.
引用
收藏
页数:4
相关论文
共 7 条
  • [1] Buzzoni M., Blind deconvolution based on cyclo stationarity maximization and its application to fault identification
  • [2] An improved envelope spectrum via candidate fault frequency optimization-gram for bearing fault diagnosis
    Cheng, Yao
    Wang, Shengbo
    Chen, Bingyan
    Mei, Guiming
    Zhang, Weihua
    Peng, Han
    Tian, Guangrong
    [J]. JOURNAL OF SOUND AND VIBRATION, 2022, 523
  • [3] Detection of Generalized-Roughness and Single-Point Bearing Faults Using Linear Prediction-Based Current Noise Cancellation
    Dalvand, Fardin
    Kang, Myeongsu
    Dalvand, Satar
    Pecht, Michael
    [J]. IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS, 2018, 65 (12) : 9728 - 9738
  • [4] github, 42 Time Domain Features
  • [5] Kang M., 2018, PROGNOSTICS HLTH MAN, P111, DOI DOI 10.1002/9781119515326.CH5
  • [6] Minimum entropy deconvolution optimized sinusoidal synthesis and its application to vibration based fault detection
    Li, Gang
    Zhao, Qing
    [J]. JOURNAL OF SOUND AND VIBRATION, 2017, 390 : 218 - 231
  • [7] Data Preprocessing Techniques in Convolutional Neural Network Based on Fault Diagnosis Towards Rotating Machinery
    Tang, Shengnan
    Yuan, Shouqi
    Zhu, Yong
    [J]. IEEE ACCESS, 2020, 8 : 149487 - 149496