2017
DOI: 10.1016/j.engappai.2017.06.012
|View full text |Cite
|
Sign up to set email alerts
|

Online feature learning for condition monitoring of rotating machinery

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
21
0

Year Published

2019
2019
2023
2023

Publication Types

Select...
7
1
1

Relationship

0
9

Authors

Journals

citations
Cited by 44 publications
(22 citation statements)
references
References 32 publications
0
21
0
Order By: Relevance
“…Thus, low-power solutions enabling learning and recognition of complex patterns with less energy has many potential applications, for example in embedded intelligence and deep edge sensor systems. In particular, ultra-low power solutions operating at the order of milliwatts is a key enabler for advanced wireless sensor systems, for example for machine monitoring (Martin del Campo and Sandin, 2017;Martin del Campo et al, 2013) where the system needs to operate autonomously with limited resources over the expected lifetime of the monitored machine (Häggström, 2018;. Searching for effective SNN architectures for pattern recognition that are suitable for implementation in ultra-low power dynamic neuromorphic processors like the DYNAP-SE, we adapted and investigated the aforementioned cricket auditory feature detection circuit.…”
Section: Discussionmentioning
confidence: 99%
“…Thus, low-power solutions enabling learning and recognition of complex patterns with less energy has many potential applications, for example in embedded intelligence and deep edge sensor systems. In particular, ultra-low power solutions operating at the order of milliwatts is a key enabler for advanced wireless sensor systems, for example for machine monitoring (Martin del Campo and Sandin, 2017;Martin del Campo et al, 2013) where the system needs to operate autonomously with limited resources over the expected lifetime of the monitored machine (Häggström, 2018;. Searching for effective SNN architectures for pattern recognition that are suitable for implementation in ultra-low power dynamic neuromorphic processors like the DYNAP-SE, we adapted and investigated the aforementioned cricket auditory feature detection circuit.…”
Section: Discussionmentioning
confidence: 99%
“…This section describes other AI-based early fault diagnosis methods. Martin-del-Campo et al [171] used dictionary learning to automatically derive signal features for characterizing different operational conditions and faults of rolling bearings. Almeida et al [172] used time-domain features as input of generic multi-layer perceptron for bearing fault identification.…”
Section: Other Methodsmentioning
confidence: 99%
“…Martin-del-Campo et al [171] Dictionary learning Almeida et al [172] Time-domain features + generic multi-layer perceptron Li et al [173] Wavelet transformation + ant colony optimization Brkovic et al [174] Wavelet transformation + quadratic classifier Li et al [175] Fuzzy lattice neurocomputing Cruz-Vega et al [176] Discrete wavelet + binary classification tree Martínez-Rego et al [177] Time domain features + one-class classifier…”
Section: Authors Methodologiesmentioning
confidence: 99%
“…A discussion on the effects of varying the learning step size is found in. 48 Furthermore, an evaluation of additional sparse coding algorithms, in addition to matching pursuit, using the same data as in this evaluation is available in. 30 Time-domain features.…”
Section: %mentioning
confidence: 99%