Unsupervised Anomaly Detection in Production Lines

Graß, Alexander; Beecks, Christian; Soto, José Angel Carvajal

doi:10.1007/978-3-662-58485-9_3

Cited by 17 publications

(11 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recent works have addressed anomaly detection for PdM supported by learning strategies on sequential data [ 2 , 39 , 106 , 115 , 116 , 117 , 118 ]. In the last few years, several papers were published approaching Anomaly Detection with Time-Series data applied to the most different domains, including industry, public water, and energy systems, among many others [ 1 , 109 , 112 , 114 , 118 , 119 , 120 , 121 , 122 , 123 , 124 , 125 , 126 , 127 , 128 , 129 , 130 , 131 , 132 , 133 , 134 , 135 , 136 , 137 , 138 , 139 , 140 ].…”

Section: Discussionmentioning

confidence: 99%

A Survey on Data-Driven Predictive Maintenance for the Railway Industry

Davari

Veloso

Costa

et al. 2021

Sensors

View full text Add to dashboard Cite

In the last few years, many works have addressed Predictive Maintenance (PdM) by the use of Machine Learning (ML) and Deep Learning (DL) solutions, especially the latter. The monitoring and logging of industrial equipment events, like temporal behavior and fault events—anomaly detection in time-series—can be obtained from records generated by sensors installed in different parts of an industrial plant. However, such progress is incipient because we still have many challenges, and the performance of applications depends on the appropriate choice of the method. This article presents a survey of existing ML and DL techniques for handling PdM in the railway industry. This survey discusses the main approaches for this specific application within a taxonomy defined by the type of task, employed methods, metrics of evaluation, the specific equipment or process, and datasets. Lastly, we conclude and outline some suggestions for future research.

show abstract

Section: Discussionmentioning

confidence: 99%

A Survey on Data-Driven Predictive Maintenance for the Railway Industry

Davari

Veloso

Costa

et al. 2021

Sensors

View full text Add to dashboard Cite

show abstract

“…To ensure the final product quality, each assembly machine has an integrated inspection system that is supported by high-speed vision cameras to measure each assembled piece's dimensions. Additionally, each assembly machine has different specification limits depending on the design of the product to be assembled [2].…”

Section: Introductionmentioning

confidence: 99%

“…The final product quality is ensured bypassing the product design specification limits to the inspection system in the assembly machine and after the inspection system measuring each assembled part dimensions. In case any part's measurements exceeded the design specification limits, the assembled part will be considered as an anomaly and automatically rejected and thrown to the trash [2], [3].…”

Section: Introductionmentioning

confidence: 99%

Assembly Line Anomaly Detection and Root Cause Analysis Using Machine Learning

Abdelrahman

Keikhosrokiani

2020

IEEE Access

View full text Add to dashboard Cite

Anomaly detection is becoming widely used in Manufacturing Industry to enhance product quality. At the same time, it plays a great role in several other domains due to the fact that anomaly may reveal rare but represent an important phenomenon. The objective of this paper is to detect anomalies and identify the possible variables that caused these anomalies on historical assembly data for two series of products. Multiple anomaly detection techniques were performed; HBOS, IForest, KNN, CBLOF, OCSVM, LOF, and ABOD. Moreover, we used AUROC and Rank Power as performance metrics, followed by Boosting ensemble learning method to ensure the best anomaly detectors robustness. The techniques that gave the highest performance are KNN, ABOD for both product series datasets with 0.95 and 0.99 AUROC respectively. Finally, we applied a statistical root cause analysis on the detected anomalies with the use of Pareto chart to visualize the frequency of the possible causes and its cumulative occurrence. The results showed that there are seven rejection causes for both product series, whereas the first three causes are responsible for 85% of the rejection rates. Besides, assembly machines engineers reported a significant reduction in the rejection rates in both assembly machines after tuning the specification limits of the rejection causes identified by this research results.

show abstract

“…In [3] different mathematical models or artificial intelligence (AI) algorithms have been developed for different conditions. The taxonomies of the physical, statistical, and machine learning methods [9,10] are summarized in Figure 1.Energies 2019, 12, x FOR PEER REVIEW 2 of 18 health management (PHM) are obtaining a lot of attention recently, as evidenced by the literature. In particular, condition-based maintenance (CBM), which is usually applied in practice [3], consists of data collection, data processing, and maintenance decision-making [4].…”

mentioning

confidence: 99%

mentioning

confidence: 99%

Data Science for Vibration Heteroscedasticity and Predictive Maintenance of Rotary Bearings

et al. 2019

View full text Add to dashboard Cite

Electric motors are widely used in our society in applications like cars, household appliances, industrial equipment, etc. Costly failures can be avoided by establishing predictive maintenance (PdM) policies or mechanisms for the repair or replacement of the components in electric motors. One of key components in the motors are bearings, and it is critical to measure the key features of bearings to support maintenance decision. This paper proposes a data science approach with embedded statistical data mining and a machine learning algorithm to predict the remaining useful life (RUL) of the bearings in a motor. The vibration signals of the bearings are collected from the experimental platform, and fault detection devices are developed to extract the important features of bearings in time domain and frequency domain. Regression-based models are developed to predict the RUL, and weighted least squares regression (WLS) and feasible generalized least squares regression (FGLS) are used to address the heteroscedasticity problem in the vibration dataset. Support vector regression (SVR) is also applied for prediction benchmarking. Case studies show that the proposed data science approach handled large datasets with ease and predicted the RUL of the bearings with accuracy. The features extracted from time domain are more significant than those extracted from frequency domain, and they benefit engineering knowledge. According to the RUL results, the PdM policy is developed for component replacement at the right moment to avoid the catastrophic equipment failure.

show abstract

Unsupervised Anomaly Detection in Production Lines

Cited by 17 publications

References 4 publications

A Survey on Data-Driven Predictive Maintenance for the Railway Industry

A Survey on Data-Driven Predictive Maintenance for the Railway Industry

Assembly Line Anomaly Detection and Root Cause Analysis Using Machine Learning

Data Science for Vibration Heteroscedasticity and Predictive Maintenance of Rotary Bearings

Contact Info

Product

Resources

About