Learning via acceleration spectrograms of a DC motor system with application to condition monitoring

Lee, Wo Jae; Wu, Hong; Huang, Aihua; Sutherland, John W.

doi:10.1007/s00170-019-04563-8

Cited by 18 publications

(12 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There have been several works to study a failure detection in manufacturing processes using single or multi-sensor data [ 20 , 32 , 33 ]. Specifically, the recent work [ 20 ], in which the kernel principal component analysis based anomaly detection system was proposed to detect a cutting tool failure in a machining process.…”

Section: Related Workmentioning

confidence: 99%

Anomaly Detection and Inter-Sensor Transfer Learning on Smart Manufacturing Datasets

Abdallah

Joung

Lee

et al. 2023

Sensors

Self Cite

View full text Add to dashboard Cite

Smart manufacturing systems are considered the next generation of manufacturing applications. One important goal of the smart manufacturing system is to rapidly detect and anticipate failures to reduce maintenance cost and minimize machine downtime. This often boils down to detecting anomalies within the sensor data acquired from the system which has different characteristics with respect to the operating point of the environment or machines, such as, the RPM of the motor. In this paper, we analyze four datasets from sensors deployed in manufacturing testbeds. We detect the level of defect for each sensor data leveraging deep learning techniques. We also evaluate the performance of several traditional and ML-based forecasting models for predicting the time series of sensor data. We show that careful selection of training data by aggregating multiple predictive RPM values is beneficial. Then, considering the sparse data from one kind of sensor, we perform transfer learning from a high data rate sensor to perform defect type classification. We release our manufacturing database corpus (4 datasets) and codes for anomaly detection and defect type classification for the community to build on it. Taken together, we show that predictive failure classification can be achieved, paving the way for predictive maintenance.

show abstract

Section: Related Workmentioning

confidence: 99%

Anomaly Detection and Inter-Sensor Transfer Learning on Smart Manufacturing Datasets

Abdallah

Joung

Lee

et al. 2023

Sensors

Self Cite

View full text Add to dashboard Cite

show abstract

“…Pooling layer-The pooling layer, usually after a convolutional layer, is to reduce the dimension of the feature map [28]. The widely used max-pooling approach is employed to downsample the input of the pooling layer using a max-filter [29]. The filter size of 2×2 is chosen to reduce the dimension of Hr to half at each pooling layer.…”

Section: B Source DL Model 1) the Architecturementioning

confidence: 99%

A Flame Imaging-Based Online Deep Learning Model for Predicting NOₓ Emissions From an Oxy-Biomass Combustion Process

Qin

Lü

Hossain

et al. 2022

IEEE Trans. Instrum. Meas.

View full text Add to dashboard Cite

show abstract

“…With the booming of the cyber–physical system [110], AI technology [111] is expected to play a vital role in the domain of GM, especially machine learning‐based manufacturing, e.g. deep learning [112], which has been constantly increasing research interests in the recent years.…”

Section: Implications For Future Researchmentioning

confidence: 99%

Twenty‐year retrospection on green manufacturing: A bibliometric perspective

Pei

et al. 2021

IET Collab Intel Manufact

View full text Add to dashboard Cite

In the modern age of Industry 4.0 and manufacturing servitisation, energy saving and environment consciousness are regarded as vital themes in manufacturing processes to reduce carbon tax and achieve sustainable development. For the past 20 years, the concept of green manufacturing has grown from infancy to a fully formed framework agreed upon by world-leading enterprises. With the unprecedented development of the information technology today, the industrial data collected could assist in the in-depth study on green manufacturing, which ranges from the operations of machining tools all the way to supply chain management. The wide scope of research promises a tremendous amount of annual publications in this field. To better facilitate follow-up research work, the present study provides a systematic overview of green manufacturing-related areas, including research progress and the developed features. The article set retrieved from the Web of Science contains 5989 documents related to green manufacturing. It is revealed that Journal of Cleaner Production is the most productive journal, archiving documents within the scope of green manufacturing. P. R. China tops the list of the number of documents with 1357 documents (22.66%), while Zhejiang University is the most productive institution. As the cooperation network indicates, P. R. China and the United States maintain the strongest collaborative links with other countries/regions. Finally, possible future directions are recommended based on the findings in the study. For instance, additive manufacturing technology and industrial IoT both have a great potential in green manufacturing; the weak link between the disciplines of manufacturing engineering and environmental science is expected to be strengthened, and a stronger international cooperation is believed to be beneficial to the field for the otherwise isolated countries/regions. K E Y W O R D S bibliometric analysis, energy efficient, energy saving, green manufacturing, green production, sustainable manufacturingThis is an open access article under the terms of the Creative Commons Attribution-NonCommercial-NoDerivs License, which permits use and distribution in any medium, provided the original work is properly cited, the use is non-commercial and no modifications or adaptations are made.

show abstract

Learning via acceleration spectrograms of a DC motor system with application to condition monitoring

Cited by 18 publications

References 25 publications

Anomaly Detection and Inter-Sensor Transfer Learning on Smart Manufacturing Datasets

Anomaly Detection and Inter-Sensor Transfer Learning on Smart Manufacturing Datasets

A Flame Imaging-Based Online Deep Learning Model for Predicting NOₓ Emissions From an Oxy-Biomass Combustion Process

Twenty‐year retrospection on green manufacturing: A bibliometric perspective

Contact Info

Product

Resources

About