Review—Deep Learning Methods for Sensor Based Predictive Maintenance and Future Perspectives for Electrochemical Sensors
Source abstract
Abstract
The downtime of industrial machines, engines, or heavy equipment can lead to a direct loss of revenue. Accurate prediction of such failures using sensor data can prevent or reduce the downtime. With the availability of Internet of Things (IoT) technologies, it is possible to acquire the sensor data in real-time. Machine Learning and Deep Learning (DL) algorithms can then be used to predict the part and equipment failures, given enough historical data. DL algorithms have shown significant advances in problems where progress has eluded the practitioners and researchers for several decades. This paper reviews the DL algorithms used for predictive maintenance and presents a case study of engine failure prediction. We also discuss the current use of sensors in the industry and future opportunities for electrochemical sensors in predictive maintenance.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Fault Detection and Control Systems · Machine Fault Diagnosis Techniques · Non-Destructive Testing Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (87)
Show source-provided references
1. Lughofer · 201910.1007/978-3-030-05645-2 ↗
2. Machine performance degradation assessment and remaining useful life prediction using proportional hazard model and support vector machine10.1016/j.ymssp.2012.02.015 ↗
3. Condition-Based Maintenance of Naval Propulsion Systems with supervised Data Analysis10.1016/j.oceaneng.2017.12.002 ↗
4. Predicting remaining useful life of rotating machinery based artificial neural network10.1016/j.camwa.2010.03.065 ↗
5. Using Deep Learning Based Approaches for Bearing Remaining Useful Life Prediction10.36001/phmconf.2016.v8i1.2570 ↗
6. Data-driven methods for predictive maintenance of industrial equipment: a survey10.1109/JSYST.2019.2905565 ↗
7. A Survey on Predictive Maintenance Through Big Data10.1007/978-3-319-23597-4_31 ↗
8. Smart manufacturing: past research, present findings, and future directions10.1007/s40684-016-0015-5 ↗
9. Data science approaches for electrochemical engineers: an introduction through surrogate model development for lithium-ion batteries10.1149/2.1391714jes ↗
10. Deep Learning10.1038/nature14539 ↗
11. Electrochemical H2O2 sensors based on Au/CeO2 nanoparticles for industrial applications10.3303/CET1543123 ↗
12. Response characteristics of a stable mixed potential ammonia sensor in simulated diesel exhaust10.1149/2.1271709jes ↗
13. Editors’ Choice—Field trials testing of mixed potential electrochemical hydrogen safety sensors at commercial California hydrogen filling stations10.1149/2.1491713jes ↗
14. Highly sensitive detection of gallic acid in food samples by using robust NiAl2O4 nanocomposite materials10.1149/2.0121902jes ↗
15. Directly determining nitrate under wide ph range condition using a Cu-deposited Ti electrode10.1149/2.052310jes ↗
16. Green electrochemical sensor for caffeine determination in environmental water samples: the bismuth film screen-printed carbon electrode10.1149/2.0571707jes ↗
17. An integrated screen-printed potentiometric strip for determination of Ca2+ in seawater10.1149/2.0251908jes ↗
18. Facile synthesis of tungsten carbide nanosheets for trace level detection of toxic mercury ions in biological and contaminated sewage water samples: an electrocatalytic approach10.1149/2.0181910jes ↗
19. Surface-enhanced raman scattering sensors for food safety and environmental monitoring10.1149/2.0161808jes ↗
20. Heavy metal toxicity and the environment10.1007/978-3-7643-8340-4_6 ↗
21. Power sources for the internet of things10.1149/2.0181808jes ↗
22. A model for safe transport of critical patients in unmanned drones with a “watch” style continuous anesthesia sensor10.1149/2.0111808jes ↗
23. Continuous monitoring of wound healing using a wearable enzymatic uric acid biosensor10.1149/2.0231808jes ↗
24. Smart gardening iot soil sheets for real-time nutrient analysis10.1149/2.0201808jes ↗
25. Iot sensor network approach for smart farming: An application in food, energy and water system10.1109/GHTC.2018.8601701 ↗
26. Holfelder · 1985
27. Principles of solid state oxygen sensors for lean combustion gas control10.1016/S0013-4686(01)00761-7 ↗
28. Artificial intelligence based mobile application for water quality monitoring10.1149/2.0081909jes ↗
29. Corrosion sensors to reduce aircraft maintenance
30. A brief survey of dimension reduction10.1007/978-3-030-02698-1_17 ↗
31. Generating feature sets for fault diagnosis using denoising stacked auto-encoder10.1109/ICPHM.2016.7542865 ↗
32. Anomaly Detection and Fault Disambiguation in Large Flight Data: A Multi-modal Deep Auto-encoder Approach10.36001/phmconf.2016.v8i1.2549 ↗
33. Transfer learning for time series anomaly detection
34. Iot healthcare analytics: the importance of anomaly detection10.1109/AINA.2016.158 ↗
35. Yan · 2019
36. A comparative evaluation of outlier detection algorithms: experiments and analyses10.1016/j.patcog.2017.09.037 ↗
37. Malhotra · 2016
38. Murphy · 2012
39. Goodfellow · 2016
40. Automotive internal-combustion-engine fault detection and classification using artificial neural network techniques10.1109/TVT.2014.2317736 ↗
41. Accurate bearing remaining useful life prediction based on Weibull distribution and artificial neural network10.1016/j.ymssp.2014.10.014 ↗
42. Performance analysis of machine learning and pattern recognition algorithms for Malware classification10.1109/NAECON.2016.7856826 ↗
43. Automated quantification of DNA damage via deep transfer learning based analysis of comet assay images10.1117/12.2529352 ↗
44. Convolutional Neural Net and Bearing Fault Analysis
45. Real-time vibration-based structural damage detection using one-dimensional convolutional neural networks10.1016/j.jsv.2016.10.043 ↗
46. Design of deep convolutional neural network architectures for automated feature extraction in industrial inspection10.1016/j.cirp.2016.04.072 ↗
47. Recurrent Neural Network Based Language Model10.21437/Interspeech.2010-343 ↗
48. Cho · 2014
49. Zaremba · 2014
50. Long short-term memory10.1162/neco.1997.9.8.1735 ↗
51. Classification of Malware programs using autoencoders based deep learning architecture and its application to the microsoft malware Classification challenge (BIG 2015) dataset10.1109/NAECON.2017.8268747 ↗
52. Bearing fault diagnosis method based on stacked autoencoder and softmax regression10.1109/ChiCC.2015.7260634 ↗
53. Ng · 2010
54. Extracting and Composing Robust Features with Denoising Autoencoders10.1145/1390156.1390294 ↗
55. Yoon · 2017
56. A survey of deep neural network architectures and their applications10.1016/j.neucom.2016.12.038 ↗
57. Pascanu · 2013
58. Bearing fault diagnosis based on SVD feature extraction and transfer learning classification10.1109/PHM.2015.7380088 ↗
59. On cross-domain feature fusion in gearbox fault diagnosis under various operating conditions based on transfer component analysis10.1109/ICPHM.2016.7542845 ↗
60. Artificial neural network based fault diagnostics of rolling element bearings using time-domain features10.1006/mssp.2001.1462 ↗
61. Neural-network-based motor rolling bearing fault diagnosis10.1109/41.873214 ↗
62. Induction machine condition monitoring using neural network modeling10.1109/TIE.2006.888786 ↗
63. Convolutional neural network based fault detection for rotating machinery10.1016/j.jsv.2016.05.027 ↗
64. Gearbox fault identification and classification with convolutional neural networks10.1155/2015/390134 ↗
65. A multi-scale convolution neural network for featureless fault diagnosis10.1109/ISFA.2016.7790137 ↗
66. Small Fault Diagnosis of Front-end Speed Controlled Wind Generator Based on Deep Learning
67. Real-time motor fault detection by 1-d convolutional neural networks10.1109/TIE.2016.2582729 ↗
68. Deep Convolutional Neural Network Based Regression Approach for Estimation of Remaining Useful Life,10.1007/978-3-319-32025-0_14 ↗
69. Fault diagnosis and remaining useful life estimation of aero engine using LSTM neural network10.1109/AUS.2016.7748035 ↗
70. Machine health monitoring with LSTM networks10.1109/ICSensT.2016.7796266 ↗
71. Deep neural networks: a promising tool for fault characteristic mining and intelligent diagnosis of rotating machinery with massive data10.1016/j.ymssp.2015.10.025 ↗
72. Rolling bearing fault diagnosis based on stft-deep learning and sound signals10.1155/2016/6127479 ↗
73. A sparse auto-encoder-based deep neural network approach for induction motor faults classification10.1016/j.measurement.2016.04.007 ↗
74. Neural-network based analog-circuit fault diagnosis using wavelet transform as preprocessor10.1109/82.823545 ↗
75. Intelligent condition based monitoring of rotating machines using sparse auto-encoders10.1109/ICPHM.2013.6621447 ↗
76. Deep neural networks: a promising tool for fault characteristic mining and intelligent diagnosis of rotating machinery with massive data10.1016/j.ymssp.2015.10.025 ↗
77. Fault diagnosis method study in roller bearing based on wavelet transform and stacked auto-encoder10.1109/CCDC.2015.7162738 ↗
78. Fault diagnosis of rotary machinery components using a stacked denoising autoencoder-based health state identification10.1016/j.sigpro.2016.07.028 ↗
79. Bearing fault diagnosis with auto-encoder extreme learning machine: a comparative study10.1177/0954406216675896 ↗
80. 01/14/2020
81. A generic probabilistic framework for structural health prognostics and uncertainty management10.1016/j.ymssp.2011.10.019 ↗
82. Learning to monitor machine health with convolutional bi-directional LSTM networks10.3390/s17020273 ↗
83. Feature representation and data augmentation for human activity classification based on wearable imu sensor data using a deep lstm neural network10.3390/s18092892 ↗
84. Deep convolutional and lstm recurrent neural networks for multimodal wearable activity recognition10.3390/s16010115 ↗
85. Zhang · 201210.1007/978-1-4419-9326-7 ↗
86. Hosmer · 2000
87. The relationship between precision-recall and ROC curves10.1145/1143844.1143874 ↗