Unsupervised and non-parametric learning-based anomaly detection system using vibration sensor data

Park, Seyoung; Kang, Jaewoong; Kim, Jongmo; Lee, Seongil; Sohn, Mye M.

doi:10.1007/s11042-018-5845-4

Cited by 5 publications

(3 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In order to ensure successful and steady training of the generative confrontation model, the system is led by periodic supplemental prompts. Seyoung et al [26] proposed a machine anomaly detection system that combines unsupervised and non-parametric learning to detect abnormalities during machine operations using vibration data collected by the sensor.…”

Section: Related Workmentioning

confidence: 99%

Unsupervised Outlier Detection Mechanism for Tea Traceability Data

Yang

et al. 2022

IEEE Access

View full text Add to dashboard Cite

The presence of outliers in tea traceability data can mislead customers and have a significant impact on the reputation and profits of tea companies. To solve this problem, an unsupervised outlier detection mechanism for tea traceability data is proposed. Firstly, tea traceability data is uploaded to the MySQL database, and then the data is preprocessed to aggregate features based on relevance, which makes it easier to identify abnormal features. Secondly, the LOKI algorithm based on Local Outlier Factor (LOF), Isolation Forest (IForest), and K-Nearest Neighbors (KNN) algorithms is used to achieve unsupervised outlier detection of tea traceability data. In addition, a Density-Based Spatial Clustering of Applications with Noise (DBSCAN-based) tuning method for unsupervised outlier detection algorithms is also provided. Finally, the types of anomalies among the identified outliers are identified to investigate the causes of the anomalies in order to develop remedial procedures to eliminate the anomalies, and the analysis results are fed back to the tea companies. Experiments on real datasets show that the DBSCAN-based tuning method can effectively help the unsupervised outlier detection algorithm optimize the parameters, and that the LOF-KNN-IForest (LOKI) algorithm can effectively identify the outliers in tea traceability data. This proves that the unsupervised outlier detection mechanism for tea traceability data can effectively guarantee the quality of tea traceability data.

show abstract

Section: Related Workmentioning

confidence: 99%

Unsupervised Outlier Detection Mechanism for Tea Traceability Data

Yang

et al. 2022

IEEE Access

View full text Add to dashboard Cite

show abstract

“…The authors included in their model different types of data collected from vibration transmitters, temperature and pressure transmitters. Unsupervised anomaly detection models developed by Park et al (2019) for vibration diagnostics of washing machine and by Oliveira et al (2019) using 257 attributes, such as real measurements from thermal, acoustic and impact sensors installed in a heavy haul railway line in Brazil. Principi et al (2019) presented unsupervised method for diagnosing faults of electric motors.…”

Section: Ml-based Anomaly Detectionmentioning

confidence: 99%

Helicopter Bolt Loosening Monitoring using Vibrations and Machine Learning

Gildish¹,

Grebshtein²,

Aperstein

et al. 2022

PHME_CONF

View full text Add to dashboard Cite

The existing helicopter Health and Usage Management Systems (HUMS) collect and process flight operational parameters and sensors data such as vibrations to provide health monitoring of the helicopter dynamic assemblies and engines. So far, structure-related mechanical faults, such as looseness in bolted structures, have not been addressed by vibration-based condition monitoring in existing HUMS systems. Bolt loosening was identified as a potential risk to flight safety demanding periodical visual monitoring, and increased maintenance and repair expenses. Its automatic identification in helicopters by using vibration measurements is challenging due to the limited number of known events and the presence of high-energy vibrations originating in rotating parts, which shadow the low-level signals generated by the bolt loosening. New developed bolt loosening monitoring approach was tested on HUMS vibrations data recorded from the IAF AH-64 Apache helicopters fleet. ML-based unsupervised anomaly detection was utilized in order to address the limited number of faulty cases. The predictive power of health features was significantly improved by applying the Harmonic filtering differentiating between the high-energy vibrations generated by rotating parts compared with the low-energy structural vibrations. Different unsupervised anomaly detection techniques were examined on the dataset. The experimental results demonstrate that the developed approach enable successful bolt loosening monitoring in helicopters and can potentially be used in other health monitoring applications.

show abstract

“…For this purpose, vibration data is used, which very well suited for the detection abnormalities in machines during operation. Additionally, considering various other characteristics of abnormalities among data (such as scarcity and diversity), a new approach is designed to detect abnormal behavior using normal patterns instead of abnormal patterns from machines [17]. Liu [18] discussed the influence of stiffness in nut, coupling, radial, along with the length and speed of screw on table vibration of torsional and axial vibration.…”

Section: Literature Reviewmentioning

confidence: 99%

Study of dynamic vibration characteristics and suppression of CNC machine tool during operation

Qiu¹,

Xing-zhou²,

Hui³

et al. 2020

J. vibroeng.

View full text Add to dashboard Cite

The rapid development of aerospace, automobile, national defense and other manufacturing industries has continuously improved the performance requirements of high speed and high positioning accuracy of the CNC machine tool feed system. As the thermal deformation error increases, the system structural rigidity decreases, the vibration increases, and accuracy of machine tool reduces. Existing research mainly focuses on the properties of mechanical and single thermal feed system, and less considers the dynamic performance under the action of thermal-mechanical coupling. For the improvement of feed system performance, it is very beneficiary. This paper takes the high-speed tool of CNC feed system as objective, combined with the actual working conditions to analyze the thermal characteristics, dynamic characteristics and vibration characteristics of the system under the effect of thermal-mechanical coupling. The thermal resistance and convective heat transfer of the key joint surface, the application of moving thermal loads, and the establishment of a simulation model to complete the steady-state temperature field, transient temperature field and thermal-structure coupling analysis. The results show that the maximum temperature rise of the feed system is 21.08 °C, The maximum thermal deformation is 17.264 um. The study found that the parameters such as flow rate and airflow temperature have a significant impact on the cooling effect, so the cooling device was further optimized. This paper proposes a control method for cutting chatter of CNC machine tools based on coupling of characteristics of thermal and mechanical. The thermal characteristic of the feed system and the thermal-mechanical coupling vibration characteristic test provides the maximum temperature error of 3.2 %, verifying the correctness of the theoretical method and analysis model. The highest temperature obtained by the test is 39.7 °C, indicating that the high-speed feed system has a large thermal effect. The relative error of the vibration amplitude of the test and simulation is 12.5 %, which verifies coupling in terms of thermal-mechanical. The accuracy of the vibration analysis method; the experiment depicts that the vibration amplitude increases by 19.7 % under the coupling effect of thermal and mechanical, indicating the effectiveness of dynamic characteristics of the high-speed feed system considering the thermal-mechanical coupling effect.

show abstract

Unsupervised and non-parametric learning-based anomaly detection system using vibration sensor data

Cited by 5 publications

References 33 publications

Unsupervised Outlier Detection Mechanism for Tea Traceability Data

Unsupervised Outlier Detection Mechanism for Tea Traceability Data

Helicopter Bolt Loosening Monitoring using Vibrations and Machine Learning

Study of dynamic vibration characteristics and suppression of CNC machine tool during operation

Contact Info

Product

Resources

About