Five-axis machine tool fault monitoring using volumetric errors fractal analysis

Xing, Kanglin; Rimpault, Xavier; Mayer, Josef; Châtelain, Jean-François; Achiche, Sofiane

doi:10.1016/j.cirp.2019.04.079

Cited by 9 publications

(4 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These influences are cumbersome to reproduce in purely physical models approaches, wherefore many recently published PHM approaches in manufacturing incorporate statistical models. Prominent examples for the application of data driven models in monitoring are described by e.g., [10][11][12][13][14][15], relevant studies on data-based approaches for prognosis are described by [9,[16][17][18]. Both the PHM approach, as well as the applied learning algorithm strongly impact the capabilities and performance of the application.…”

Section: Failure Detection and Prognostics And Health Management (Phmmentioning

confidence: 99%

“…The degradation curves are matched to other failure curves, in order to estimate the remaining useful lifetime (RUL). Reference [14] extracts features from volumetric errors (VE) on a five-axis machine tool via fractal analysis, to recognize changes in VEs as degradations. Duan et al apply an auto-regression on multivariate numerical control (NC) signals of circular machine tool tests, where residuals due to anomalies are used to model the machine state as a semi-Markov Process [22].…”

Section: Failure Detection and Prognostics And Health Management (Phmmentioning

confidence: 99%

“…Duan et al apply an auto-regression on multivariate numerical control (NC) signals of circular machine tool tests, where residuals due to anomalies are used to model the machine state as a semi-Markov Process [22]. Malhotra's and most other PHM approaches rely on simulated degradation for model training, as it is also the case e.g., for Sobie et al [9] and Xing et al [14]. They conclude that PHM models trained on simulated degradation data show an inferior performance to those trained on real machine data in a comparative study.…”

Section: Failure Detection and Prognostics And Health Management (Phmmentioning

confidence: 99%

See 2 more Smart Citations

Machine Tool Component Health Identification with Unsupervised Learning

Gittler

Scholze²,

Rupenyan

et al. 2020

JMMP

View full text Add to dashboard Cite

Unforeseen machine tool component failures cause considerable losses. This study presents a new approach to unsupervised machine component condition identification. It uses test cycle data of machine components in healthy and various faulty conditions for modelling. The novelty in the approach consists of the time series representation as features, the filtering of the features for statistical significance, and the use of this feature representation to train a clustering model. The benefit in the proposed approach is its small engineering effort, the potential for automation, the small amount of data necessary for training and updating the model, and the potential to distinguish between multiple known and unknown conditions. Online measurements on machines in unknown conditions are performed to predict the component condition with the aid of the trained model. The approach was exemplarily tested and verified on different healthy and faulty states of a grinding machine axis. For the accurate classification of the component condition, different clustering algorithms were evaluated and compared. The proposed solution demonstrated encouraging results as it accurately classified the component condition. It requires little data, is straightforward to implement and update, and is able to precisely differentiate minor differences of faults in test cycle time series.

show abstract

Section: Failure Detection and Prognostics And Health Management (Phmmentioning

confidence: 99%

Section: Failure Detection and Prognostics And Health Management (Phmmentioning

confidence: 99%

Section: Failure Detection and Prognostics And Health Management (Phmmentioning

confidence: 99%

See 1 more Smart Citation

Machine Tool Component Health Identification with Unsupervised Learning

Gittler

Scholze²,

Rupenyan

et al. 2020

JMMP

View full text Add to dashboard Cite

show abstract

“…More recently, the method has been applied for kinematic fault diagnosis. 14 The core focus with artefact probing procedures and commercial software is error identification for machine capability checking or calibration activities. Generally speaking, performance monitoring and fault diagnosis in machine tools are of interest to the community; recent research has considered the mining of general inprocess data across networks of machining centres, 15 analysing the energy usage to detect abnormalities 16 or vibration response to assess the health of the axis drives.…”

Section: Introductionmentioning

confidence: 99%

Machining centre performance monitoring with calibrated artefact probing

Rooker

Stammers

Worden

et al. 2020

Proceedings of the Institution of Mechanical Engineers, Part B:

View full text Add to dashboard Cite

Maintaining high levels of geometric accuracy in five-axis machining centres is of critical importance to many industries and applications. Numerous methods for error identification have been developed in both the academic and industrial fields; one commonly-applied technique is artefact probing, which can reveal inherent system errors at minimal cost and does not require high skill levels to perform. The primary focus of popular commercial solutions is on confirming machine capability to produce accurate workpieces, with the potential for short-term trend analysis and fault diagnosis through interpretation of the results by an experienced user. This paper considers expanding the artefact probing method into a performance monitoring system, benefitting both the onsite Maintenance Engineer and visiting specialist Engineer with accessibility of information and more effective means to form insight. A technique for constructing a data-driven tolerance threshold is introduced, describing the normal operating condition and helping protect against unwarranted settings induced by human error. A multifunctional graphical element is developed to present the data trends with tolerance threshold integration to maintain relevant performance context, and an automated event detector to highlight areas of interest or concern. The methods were developed on a simulated, demonstration dataset; then applied without modification to three case studies on data acquired from currently operating industrial machining centres to verify the methods. The data-driven tolerance threshold and event detector methods were shown to be effective at their respective tasks, and the merits of the multifunctional graphical display are presented and discussed.

show abstract