Vibration Analysis Utilizing Unsupervised Learning

Wescoat, Ethan; Krugh, Matthew; Henderson, Andrew; Goodnough, Josh; Mears, Laine

doi:10.1016/j.promfg.2019.06.160

Cited by 11 publications

(5 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…, 2019), decision trees (Yan et al ., 2016; Li, 2018; Patange et al ., 2019), nearest mean classifier (Glowacz et al. , 2017), Gaussian mixture model (GMM) (Wescoat et al. , 2019), or an ensemble of two or more methods (Hu et al.…”

Section: Literature Reviewmentioning

confidence: 99%

“…Although indirect measurements do not require expensive equipment, it requires pressure sensors and turning off the end-use equipment which limits its applicability.2.2 Machine learning methodsAnother challenge related to ML-based fault detection is the lack of a universal model that can be generalized to all fault scenarios. Different researchers used different methods for fault detection such as artificial and deep neural networks(Awad et al, 2017;M arquez et al, 2019;Vita et al, 2020;Kocyigit, 2015;Hashemian and Bean, 2011), support vector method (SVM)(Shamayleh et al, 2020;Han et al, 2019;Yan et al, 2017;Sukendi and Suherman, 2020;Natarajan, 2017;Toroghi and Sadighi, 2020), binary logistics regression(Barbieri et al, 2019), decision trees(Yan et al, 2016;Li, 2018;Patange et al, 2019), nearest mean classifier(Glowacz et al, 2017), Gaussian mixture model (GMM)(Wescoat et al, 2019), or an ensemble of two or more methods(Hu et al, 2012;Traini et al, 2019). For example,Patange et al (2019) used decision tree classification to extract nine features from a milling cutter data set and used it to detect failures.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Air leaks fault detection in maintenance using machine learning

Barakat,

Hajeir,

Alattal

et al. 2024

JQME

View full text Add to dashboard Cite

PurposeThe objective of this paper is to develop a condition-based maintenance (CBM) scheme for pneumatic cylinders. The CBM scheme will detect two common types of air leaking failure modes and identify the leaky/faulty cylinder. The successful implementation of the proposed scheme will reduce energy consumption, scrap and rework, and time to repair.Design/methodology/approachEffective implementation of maintenance is important to reduce operation cost, improve productivity and enhance quality performance at the same time. Condition-based monitoring is an effective maintenance scheme where maintenance is triggered based on the condition of the equipment monitored either real time or at certain intervals. Pneumatic air systems are commonly used in many industries for packaging, sorting and powering air tools among others. A common failure mode of pneumatic cylinders is air leaks which is difficult to detect for complex systems with many connections. The proposed method consists of monitoring the stroke speed profile of the piston inside the pneumatic cylinder using hall effect sensors. Statistical features are extracted from the speed profiles and used to develop a fault detection machine learning model. The proposed method is demonstrated using a real-life case of tea packaging machines.FindingsBased on the limited data collected, the ensemble machine learning algorithm resulted in 88.4% accuracy. The algorithm can detect failures as soon as they occur based on majority vote rule of three machine learning models.Practical implicationsEarly air leak detection will improve quality of packaged tea bags and provide annual savings due to time to repair and energy waste reduction. The average annual estimated savings due to the implementation of the new CBM method is $229,200 with a payback period of less than two years.Originality/valueTo the best of the authors’ knowledge, this paper is the first in terms of proposing a CBM for pneumatic systems air leaks using piston speed. Majority, if not all, current detection methods rely on expensive equipment such as infrared or ultrasonic sensors. This paper also contributes to the research gap of economic justification of using CBM.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

mentioning

confidence: 99%

Air leaks fault detection in maintenance using machine learning

Barakat,

Hajeir,

Alattal

et al. 2024

JQME

View full text Add to dashboard Cite

show abstract

“…Angelopoulos et al [31] present learning algorithms for fault detection in Industry 4.0 with little focus on how to design and deploy them. Some works [32]- [34] discuss unsupervised learning for predictive maintenance and anomaly detection without mentioning AI engineering aspects. Only recently, Husom et al [35] explicitly discuss and evaluate their AI-based approach (i.e., an unsupervised learning pipeline for sensor data validation) for industrial settings from the AI engineering perspective.…”

Section: Related Workmentioning

confidence: 99%

Replay-Driven Continual Learning for the Industrial Internet of Things

Sen

Nielsen

Husom

et al. 2023

2023 IEEE/ACM 2nd International Conference on AI Engineering – Software Engineering for AI (CAIN)

View full text Add to dashboard Cite

The Industrial Internet of Things (IIoT) leverages thousands of interconnected sensors and computing devices to monitor and control large and complex industrial processes. Machine learning (ML) applications in IIoT use data acquired from multiple sensors to perform tasks such as predictive maintenance. While remembering useful learning from the past, these applications need to adapt learning for evolving sensor data stemming from changes in industrial processes and environmental conditions. This paper presents a continual learning pipeline to learn from the evolving data while replaying selected parts of the old data. The pipeline is configured to produce ML experiences (e.g., training a baseline neural network model), improve the baseline model with the new data while replaying part of the old data, and infer/predict using a specific model version given a stream of IIoT sensor data. We have evaluated our approach from an AI Engineering perspective using three industrial case studies, i.e., predicting tool wear, remaining useful lifetime, and anomalies from sensor data acquired from CNC machining and broaching operations. Our results show that configuring experiences for replay-driven continual learning allows dynamic maintenance of ML performance on evolving data while minimizing the excessive accumulation of legacy sensor data.

show abstract

“…In the absence of labelled (labels indicating operational and defective life), real-time datasets of a lifetime of motors and unsupervised learning approaches have also been attempted. Wescoat et al describe vibration analysis of a paint dosing pump used for Condition Monitoring (CM) based maintenance using unsupervised learning [21]. The work majorly presents techniques to organize data using unsupervised approaches.…”

Section: Introductionmentioning

confidence: 99%

Predictive Maintenance System for Rotating Machinery Onboard Ships for Detecting Performance Degradation

Jayaswal,

Agrawal,

Jain

et al. 2023

SCPE

View full text Add to dashboard Cite

Maintenance of rotating machinery is crucial for extending the lifespan and increasing the reliability of equipment onboard ships. Presently, breakdown and preventive methodologies are used for the maintenance of equipment. Further, dataloggers collect critical machinery parameters, and parameter data is used for real-time parameter monitoring. The availability of such extensive monitoring data has also led to the adoption predictive maintenance methodologies in the industry, wherein machine learning-based analysis of recorded data is used to predict impending defects and prompt required maintenance. In this paper, we propose a predictive maintenance system that records data through a network of sensors installed over multiple electrical motor pump sets onboard the ship and uses statistical analysis to detect equipment degradation. Our system has been deployed onboard a ship to undertake real-time predictive maintenance of electrical motor pump sets used in firemain, AC plants, stabilizers, steering pumps and other auxiliary engine room machinery.

show abstract

Vibration Analysis Utilizing Unsupervised Learning

Cited by 11 publications

References 18 publications

Air leaks fault detection in maintenance using machine learning

Air leaks fault detection in maintenance using machine learning

Replay-Driven Continual Learning for the Industrial Internet of Things

Predictive Maintenance System for Rotating Machinery Onboard Ships for Detecting Performance Degradation

Contact Info

Product

Resources

About