TY - GEN
T1 - Pushing distributed vibration analysis to the edge with a low-resolution companding autoencoder
T2 - 2020 Annual Conference of the Prognostics and Health Management Society, PHM 2020
AU - Trilla, Alexandre
AU - Miralles, David
AU - Fernandez, Veronica
N1 - Publisher Copyright:
© 2020 Prognostics and Health Management Society. All rights reserved.
PY - 2020/11/3
Y1 - 2020/11/3
N2 - The Industrial Internet-of-Things (IIoT) has disrupted the way of collecting physical data for predictive maintenance purposes. At present, networks of intelligent wireless sensors are pervasive, finding success in many environments and industries, including the railways. However, when it comes to data-intensive applications like vibration monitoring that require the delivery of large amounts of records, the limitations of these devices arise. The shortfalls are mainly driven by the low-bandwidth transmission capacity of their radio interfaces, and the low-power features of their battery-operated (and/or energy-harvested) electronics. In sight of these limited resources, this article explores a vibration data compression strategy for diagnosis purposes. To maximise the amount of transferred information with the least amount of bytes this method works in three stages: first, it extracts the most useful features for vibration-based analytics. Then, it compresses the raw signal waveform using an Autoencoder neural network with an undercomplete representation, assessing its optimum regularisation approach: the denoising, sparse, and contractive configurations. Finally, it reduces the resolution of the compressed data by quantising all the resulting real values into single-byte unsigned integers. The proposed strategy is evaluated with a dataset of railway axle bearings with different levels of degradation. The results of the analysis show that with compression rates up to 10 the vibration signals are practically unaffected by this procedure, and once the signals are reconstructed with a minimum quality standard, many diagnosis goals like anomaly detection, fault location, and severity appraisal can be performed. This approach yields a wide range of business opportunities for on-board predictive maintenance with IIoT technology.
AB - The Industrial Internet-of-Things (IIoT) has disrupted the way of collecting physical data for predictive maintenance purposes. At present, networks of intelligent wireless sensors are pervasive, finding success in many environments and industries, including the railways. However, when it comes to data-intensive applications like vibration monitoring that require the delivery of large amounts of records, the limitations of these devices arise. The shortfalls are mainly driven by the low-bandwidth transmission capacity of their radio interfaces, and the low-power features of their battery-operated (and/or energy-harvested) electronics. In sight of these limited resources, this article explores a vibration data compression strategy for diagnosis purposes. To maximise the amount of transferred information with the least amount of bytes this method works in three stages: first, it extracts the most useful features for vibration-based analytics. Then, it compresses the raw signal waveform using an Autoencoder neural network with an undercomplete representation, assessing its optimum regularisation approach: the denoising, sparse, and contractive configurations. Finally, it reduces the resolution of the compressed data by quantising all the resulting real values into single-byte unsigned integers. The proposed strategy is evaluated with a dataset of railway axle bearings with different levels of degradation. The results of the analysis show that with compression rates up to 10 the vibration signals are practically unaffected by this procedure, and once the signals are reconstructed with a minimum quality standard, many diagnosis goals like anomaly detection, fault location, and severity appraisal can be performed. This approach yields a wide range of business opportunities for on-board predictive maintenance with IIoT technology.
UR - http://www.scopus.com/inward/record.url?scp=85102950867&partnerID=8YFLogxK
U2 - 10.36001/phmconf.2020.v12i1.1119
DO - 10.36001/phmconf.2020.v12i1.1119
M3 - Conference contribution
AN - SCOPUS:85102950867
T3 - Proceedings of the Annual Conference of the Prognostics and Health Management Society, PHM
BT - Proceedings of the Annual Conference of the Prognostics and Health Management Society, PHM
A2 - Saxena, Abhinav
PB - Prognostics and Health Management Society
Y2 - 9 November 2020 through 13 November 2020
ER -