Data-based ensemble approach for semi-supervised anomaly detection in machine tool condition monitoring

Denkena, Berend; Dittrich, Marc-André; Nöske, H. D.; Stoppel, Dennis; Lange, D.H.

doi:10.1016/j.cirpj.2021.09.003

Cited by 18 publications

(3 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As stated by [27], when the components of a linear axis begin to wear, it may cause operational errors in positioning, straightness, and angular motions. Most recently, the research works in this field have focused in detecting localized wear, such as spalling, in the different components of the axis including the leadscrew, linear guide rail, and carrier block [21,[28][29][30][31][32][33]. Despite these efforts, from a maintenance perspective, if localized damage has already developed in the linear axis component, it warrants the need to immediately be replaced.…”

Section: Related Workmentioning

confidence: 99%

Linear Axis Guide Rail Misalignment Detection and Localization Using a Novel Signal Segmentation Analysis Technique

Hurtado Carreon,

DePaiva,

Veldhuis

2024

Applied Sciences

View full text Add to dashboard Cite

Maintenance of the linear axis and its components such as the linear guide can be significantly costly due to the difficult nature of the repair procedure and the downtime the machine exhibits while being repaired. This is a decision that must be made carefully and with proper justification. Therefore, it is crucial that the condition-based monitoring (CBM) system in the machine can detect and localize faults in the linear axis. The presented paper proposes a novel vibration signal segmentation analysis technique that detects and localizes misalignment in the linear guide rail, which is considered a leading root-cause failure fault. The results demonstrated that the usability of time domain features such as RMS was doubled by applying segmentation analysis. Also, evaluating both stroke directions aided in the localization of the misalignment. Overall, the practical value of the proposed technique is to function as both a localization and repair verification tool when performing linear axis maintenance.

show abstract

Section: Related Workmentioning

confidence: 99%

Linear Axis Guide Rail Misalignment Detection and Localization Using a Novel Signal Segmentation Analysis Technique

Hurtado Carreon,

DePaiva,

Veldhuis

2024

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…We focus on the manufacturing industry, specifically plants that produce industrial machinery. These installations require meticulous attention to detail and precision in all stages of production, from initial design to welding and final assembly [28]. Constant monitoring through sensors is essential to guarantee product quality and maintain safety and efficiency on the production line.…”

Section: Environment Descriptionmentioning

confidence: 99%

Tamper Detection in Industrial Sensors: An Approach Based on Anomaly Detection

Villegas-Ch,

Govea,

Jaramillo-Alcazar

2023

Sensors

View full text Add to dashboard Cite

The Industrial Revolution 4.0 has catapulted the integration of advanced technologies in industrial operations, where interconnected systems rely heavily on sensor information. However, this dependency has revealed an essential vulnerability: Sabotaging these sensors can lead to costly and dangerous interruptions in the production chain. To address this threat, we introduce an innovative methodological approach focused on developing an anomaly detection algorithm specifically designed to track manipulations in industrial sensors. Through a series of meticulous tests in an industrial environment, we validate the robustness and accuracy of our proposal. What distinguishes this study is its unique adaptability to various sensor conditions, achieving high detection accuracy and prompt response. Our algorithm demonstrates superiority in accuracy and sensitivity compared to previously established methodologies. Beyond detection, we incorporate a proactive alert and response system, guaranteeing timely action against detected anomalies. This work offers a tangible solution to a growing challenge. It lays the foundation for strengthening security in industrial systems of the digital age, harmonizing efficiency with protection in the Industry 4.0 landscape.

show abstract

“…B. Denkena et al monitored the machine parts based on data, used the sensor data of normal state of the machine for semisupervised anomaly detection training, and obtained high-quality spindle torque information by comprehensively considering the characteristics of power spectral density and peak value of fast Fourier transform [13]. Su Chunyan and others explored the construction method of CPS-based intelligent manufacturing system, and adopted C# programming language and SQL Server database management system, which not only realized the collection, processing and preservation of the operation data of networked machine tools, but also realized the management of production information [14].…”

Section: Cnc Machine Toolmentioning

confidence: 99%

Design and research of digital twin machine tool simulation and monitoring system

Guo

Fang

et al. 2022

Int J Adv Manuf Technol

View full text Add to dashboard Cite

With the application of digital manufacturing technology and intelligent manufacturing technology in manufacturing industry, the existing simulation and monitoring methods of machine tools can not meet the requirements of enterprises, and gradually tend to use digital twin, OPC and other technologies to remote simulation and monitoring of machine tools. In order to prevent the accidental collision of machine tools, this paper builds the virtual model of machine tools based on the digital twin (DT) technology, detects the tool and machine tool collision model based on the improved GJK collision detection algorithm, and automatically controls the machine tool to stop when the tool and machine tool are about to collide. In order to improve the level of machine tool intelligent management, potential information extraction machine run time, this paper proposes a fast simulation method, machine tool CNC code used to detect the code is correct, and in the process of running through a visual component implementation monitoring the running state of the machine tool manufacturing process by monitoring data visualization and testing of large data, extracting the potential information, Realize the online prediction function of tool wear. Taking a turning process of Marine diesel engine cylinder liner as an example, the experimental test results show that the system can quickly judge the correctness of CNC code, effectively monitor the data of machine tool, predict tool wear degree and reduce the risk of tool collision.

show abstract

Data-based ensemble approach for semi-supervised anomaly detection in machine tool condition monitoring

Cited by 18 publications

References 20 publications

Linear Axis Guide Rail Misalignment Detection and Localization Using a Novel Signal Segmentation Analysis Technique

Linear Axis Guide Rail Misalignment Detection and Localization Using a Novel Signal Segmentation Analysis Technique

Tamper Detection in Industrial Sensors: An Approach Based on Anomaly Detection

Design and research of digital twin machine tool simulation and monitoring system

Contact Info

Product

Resources

About