Improvement of Defect Detectability in Machine Tools Using Sensor-based Condition Monitoring Applications

D’Emilia, Giulio; Gaspari, Antonella; Hohwieler, Eckhard; Laghmouchi, Abdelhakim; Uhlmann, Eckart

doi:10.1016/j.procir.2017.12.221

Cited by 32 publications

(20 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Regarding the problem of anomaly detection for collections of time series, the problem has also been studied in the field of commercial software solutions [11] and academic research [12][13][14][15]. What these previous works have in common is their approach based on the extraction of features from the time series and performing data analysis on those features.…”

Section: Discussionmentioning

confidence: 99%

“…From those statistics, a system of thresholds was established to determine anomalies. The researchers in [15] included in their analysis, features such as variance, crest factor, skewness, and wavelet energy. Using those previously mentioned features, the authors proposed a supervised problem where the data is analyzed towards the identification of a collection of known types of failures.…”

Section: Discussionmentioning

confidence: 99%

“…To the best of our knowledge, no anomaly detection method based on DTW in the field of machine tool was previously presented. Previous approaches to these problems [11][12][13][14][15] are based in the extraction of features from the time series, with the consequent loss of dimension and information, while our approach uses the whole time series to determine anomalous behaviors. It also introduces a suggestion for segmenting machine data from the CNC into operations.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Machine Tools Anomaly Detection Through Nearly Real-Time Data Analysis

Herranz

Antolínez

Escartin

et al. 2019

JMMP

View full text Add to dashboard Cite

This work presents a new methodology for machine tools anomaly detection via operational data processing. The previous methodology has been field tested on a milling-boring machine in a real production environment. This paper also describes the data acquisition process, as well as the technical architecture needed for data processing. Subsequently, a technique for operational machine data segmentation based on dynamic time warping and hierarchical clustering is introduced. The formerly mentioned data segmentation and analysis technique allows for machine tools anomaly detection thanks to comparison between near real-time machine operational information, coming from strategically positioned sensors and outcomes collected from previous production cycles. Anomaly detection techniques shown in this article could achieve significant production improvements: “zero-defect manufacturing”, boosting factory efficiency, production plans scrap minimization, improvement of product quality, and the enhancement of overall equipment productivity.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Machine Tools Anomaly Detection Through Nearly Real-Time Data Analysis

Herranz

Antolínez

Escartin

et al. 2019

JMMP

View full text Add to dashboard Cite

show abstract

“…Validation of models by experimental techniques can also be supported by advanced data processing techniques, including advanced machine learning, deep learning and neural network algorithms, which are commonly used in many experimental fields [17], [18].…”

Section: Introductionmentioning

confidence: 99%

Uncertainty assessment for measurement and simulation in selective laser melting: a case study of an aerospace part

et al. 2020

Self Cite

View full text Add to dashboard Cite

<p class="Abstract"><span lang="EN-US">In this work, the additive manufacturing process selective laser melting is analysed with the aim of realising a complex piece for aerospace applications. In particular, the effect of the manufacturing process and of the following thermal treatments on the dimensions of the workpiece is evaluated. The study is based on a hybrid approach including a simulation of the whole manufacturing process by advanced software packages and the dimensional measurements of the realised pieces taken by a coordinate measuring machine (CMM). The integrated use of simulation and measurements is carried out with the aim of validating the simulation results and of identifying the operational limits of both approaches; this analysis is based on metrological evaluation of the results of both the simulation and the tests, taking into account the uncertainty of the data. In addition, the main causes of uncertainty for the simulation activity and the experimental data have been identified, and the effects of some of them have also been experimentally evaluated. Based on the experimental validation, the simulation seems to predict the absolute displacement of the supports of the piece in a satisfactory way, while it is unable, in the actual configuration, to assess the conformity of the surface to its very tight shape tolerances. Conformity assessment of the surface should be carried out by CMM measurement. Integrated use of simulation and experimental results is expected to strongly improve the accuracy of simulation results for the effective and accurate design and control of the additive manufacturing process, including dimensional control and thermal treatments to mitigate induced thermal stresses.</span></p>

show abstract

“…Sometimes, specific tasks are of interest, like a suitable definition of the working parameters at the set-up of the system and/or identification of critical conditions due to fault and/or wear for smart maintenance [3,4,5,6,7], to now be realized in modern operating scenarios like Industry 4.0 or IoT [8].…”

Section: Introductionmentioning

confidence: 99%

Physical and Metrological Approach for Feature’s Definition and Selection in Condition Monitoring

D’Emilia

Gaspari

Natale

2019

Sensors

Self Cite

View full text Add to dashboard Cite

In this paper, a methodology is described aiming at emphasizing physical and metrological criteria in feature selection for condition monitoring of a real scale mechatronic system. The device is used for packaging applications according to the movements of its end effector, driven by a couple of brushless servomotors and a kinematic mechanical linkage. The approach is hybrid, meaning that the starting feature set is built with reference to both experimental data from different sensors and to the indication of a simplified kinematic and dynamic model of the mechanical linkage itself. A critical comparison and mixing of theoretical and experimental data, based also on a physical interpretation of differences, suggests some more features, with respect to the classical ones, of hybrid type, which could be mostly correlated to the effects of statuses and defects of the system to be identified. The whole procedure is step by step validated, in order to evaluate the variability of features, throughout the whole procedure. The variability is analyzed depending on the actions that are realized in order to define, select, and use the proposed features for data processing by advanced algorithms, like the most typically used classifiers and artificial neural networks. A comparison with the state-of-the-art automatic feature’s selection procedure is also presented. Experimental results show that the proposed methodology is able to classify with high accuracy many statuses of the mechatronic system, which are only slightly different as for set-up settings and/or mechanical wear and lubrication conditions of mechanical parts of the mechatronic system. Issues to be pursued to a more effective generalization of the method are also discussed.

show abstract

Improvement of Defect Detectability in Machine Tools Using Sensor-based Condition Monitoring Applications

Cited by 32 publications

References 17 publications

Machine Tools Anomaly Detection Through Nearly Real-Time Data Analysis

Machine Tools Anomaly Detection Through Nearly Real-Time Data Analysis

Uncertainty assessment for measurement and simulation in selective laser melting: a case study of an aerospace part

Physical and Metrological Approach for Feature’s Definition and Selection in Condition Monitoring

Contact Info

Product

Resources

About