TY - JOUR
T1 - Multiple profiles sensor-based monitoring and anomaly detection
AU - Zhang, Chen
AU - Yan, Hao
AU - Lee, Seungho
AU - Shi, Jianjun
N1 - Funding Information:
The authors are grateful for the valuable comments provided by the editors and referees. This article is partiallysupported by the NSF Grant ID 1233143.
Funding Information:
This article is partiallysupported by the NSF Grant ID 1233143.
Publisher Copyright:
© 2018 American Society for Quality.
PY - 2018
Y1 - 2018
N2 - Generally, in an advanced manufacturing system hundreds of sensors are deployed to measure key process variables in real time. Thus it is desirable to develop methodologies to use real-time sensor data for on-line system condition monitoring and anomaly detection. However, there are several challenges in developing an effective process monitoring system: (i) data streams generated by multiple sensors are high-dimensional profiles; (ii) sensor signals are affected by noise due to system-inherent variations; (iii) signals of different sensors have cluster-wise features; and (iv) an anomaly may cause only sparse changes of sensor signals. To address these challenges, this article presents a real-time multiple profiles sensor-based process monitoring system, which includes the following modules: (i) preprocessing sensor signals to remove inherent variations and conduct profile alignments, (ii) using multichannel functional principal component analysis (MFPCA)–based methods to extract sensor features by considering cluster-wise between-sensor correlations, and (iii) constructing a monitoring scheme with the top-R strategy based on the extracted features, which has scalable detection power for different fault patterns. Finally, we implement and demonstrate the proposed framework using data from a real manufacturing system.
AB - Generally, in an advanced manufacturing system hundreds of sensors are deployed to measure key process variables in real time. Thus it is desirable to develop methodologies to use real-time sensor data for on-line system condition monitoring and anomaly detection. However, there are several challenges in developing an effective process monitoring system: (i) data streams generated by multiple sensors are high-dimensional profiles; (ii) sensor signals are affected by noise due to system-inherent variations; (iii) signals of different sensors have cluster-wise features; and (iv) an anomaly may cause only sparse changes of sensor signals. To address these challenges, this article presents a real-time multiple profiles sensor-based process monitoring system, which includes the following modules: (i) preprocessing sensor signals to remove inherent variations and conduct profile alignments, (ii) using multichannel functional principal component analysis (MFPCA)–based methods to extract sensor features by considering cluster-wise between-sensor correlations, and (iii) constructing a monitoring scheme with the top-R strategy based on the extracted features, which has scalable detection power for different fault patterns. Finally, we implement and demonstrate the proposed framework using data from a real manufacturing system.
KW - Data fusion
KW - Functional PCA
KW - Multichannel profile monitoring
KW - Statistical process control
UR - http://www.scopus.com/inward/record.url?scp=85050728407&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85050728407&partnerID=8YFLogxK
U2 - 10.1080/00224065.2018.1508275
DO - 10.1080/00224065.2018.1508275
M3 - Article
AN - SCOPUS:85050728407
SN - 0022-4065
VL - 50
SP - 344
EP - 362
JO - Journal of Quality Technology
JF - Journal of Quality Technology
IS - 4
ER -