Ido Amihai, Arzam Kotriwala, Diego Pareschi, Moncef Chioua and Ralf Gitzel
Paper (2021)
|
Open Access to the full text of this document Published Version Terms of Use: Creative Commons Attribution Download (605kB) |
Abstract
In this paper, we describe a machine learning approach for predicting machine health indicators with a large time horizon into the future. The approach uses state-of-the-art neural network architectures for sequence modelling and can incorporate numerical-sensor and categorical data using entity embeddings. Moreover, we describe an unsupervised labelling approach where classes are generated using continuous sensor values in the training data and a clustering algorithm. To validate our approach, we performed an ablation study to verify the effectiveness of each of our model’s components. In this context, we show that entity embeddings can be used to generate effective features from categorical inputs, that state-of-the-art models, while originally developed for a different set of problems, can nonetheless be transferred to perform industrial asset health classification and provide a performance boost over simpler networks that have been traditionally used, such as relatively shallow recurrent or convolutional networks. Taken together, we present a machine health monitoring system that can accurately generate asset health predictions. This system can incorporate both numerical and categorical information, the current state-of-the-art for sequence modelling, and generate labels in an unsupervised fashion when explicit labels are unavailable.
Uncontrolled Keywords
neural networks; time series; sequence modelling; machine health monitoring; predictive maintenance
Subjects: |
1800 Chemical engineering > 1800 Chemical engineering 2500 Electrical and electronic engineering > 2500 Electrical and electronic engineering 2500 Electrical and electronic engineering > 2509 Control systems 2700 Information technology > 2713 Algorithms |
---|---|
Department: | Department of Chemical Engineering |
Funders: | ABB |
PolyPublie URL: | https://publications.polymtl.ca/9386/ |
Conference Title: | 7th International Conference on Time Series and Forecasting (ITISE 2021) |
Conference Location: | Gran Canaria, Spain |
Conference Date(s): | 2021-07-19 - 2021-07-21 |
Journal Title: | Engineering Proceedings (vol. 5, no. 1) |
Publisher: | MDPI |
DOI: | 10.3390/engproc2021005007 |
Official URL: | https://doi.org/10.3390/engproc2021005007 |
Date Deposited: | 16 Aug 2023 12:23 |
Last Modified: | 28 Sep 2024 08:21 |
Cite in APA 7: | Amihai, I., Kotriwala, A., Pareschi, D., Chioua, M., & Gitzel, R. (2021, July). Using learned health indicators and deep sequence models to predict industrial machine health [Paper]. 7th International Conference on Time Series and Forecasting (ITISE 2021), Gran Canaria, Spain (9 pages). Published in Engineering Proceedings, 5(1). https://doi.org/10.3390/engproc2021005007 |
---|---|
Statistics
Total downloads
Downloads per month in the last year
Origin of downloads
Dimensions