Intelligente Überwachung von Werkzeugverschleiß/Intelligent monitoring of tool wear based on machine internal data

Numerische Steuerungen für Werkzeugmaschinen erfassen eine erhebliche Menge an Sensordaten für die Achsregelung. Diese liefern nicht nur Informationen über die aktuellen Achspositionen oder die Ströme, sondern können mithilfe von Modellen auch für das Monitoring von anderen Prozessgrößen verwendet werden. In diesem Beitrag wird ein Machine-Learning-Verfahren zur Überwachung von Werkzeugverschleiß untersucht, welches allein auf maschinen-internen Daten basiert.   Numerical controls for machine tools acquire a considerable amount of sensor data for axis control. This information, such as the current axis position or the motor currents, can be used for monitoring other process variables with the aid of models. This article investigates a machine learning method for monitoring tool wear in machine tools, based on machine-internal data only.

Download Full-text

Machine Tools’ Running State Monitoring in the Learning Factory—Based on Machine Learning Method and Vibration Data

SSRN Electronic Journal ◽

10.2139/ssrn.3863168 ◽

2021 ◽

Author(s):

Rui Yang ◽

Weimin Zhang ◽

Weinan Cai ◽

Shulian Xie ◽

Christopher Ehrmann

Keyword(s):

Machine Learning ◽

Machine Tools ◽

Machine Learning Method ◽

Learning Method ◽

State Monitoring ◽

Vibration Data

Download Full-text

A Multi-Index Generative Adversarial Network for Tool Wear Detection with Imbalanced Data

Complexity ◽

10.1155/2020/5831632 ◽

2020 ◽

Vol 2020 ◽

pp. 1-10

Author(s):

Guokai Zhang ◽

Haoping Xiao ◽

Jingwen Jiang ◽

Qinyuan Liu ◽

Yimo Liu ◽

...

Keyword(s):

Machine Learning ◽

Decision Making ◽

Tool Wear ◽

Imbalanced Data ◽

Temporal Correlation ◽

Monitoring Tool ◽

Generative Adversarial Network ◽

Multi Index ◽

Machine Learning Methods ◽

Adversarial Network

The scarcity of abnormal data leads to imbalanced data in the field of monitoring tool wear conditions. In this paper, a novel multi-index generative adversarial network (MI-GAN) is proposed to detect the tool wear conditions subject to imbalanced signal data. First, the generator in the MI-GAN is trained to produce fake normal signals, and the discriminator computes scores of testing signals and generated signals. Next, the generator detects abnormal signals based on the performance of imitating testing signals, and the discriminator will compute the scores of testing signals and generated signals. Subsequently, two indexes, i.e., L 2 -norm and temporal correlation coefficient (CORT), are put forward to measure the similarity between generated signals and testing signals. Finally, our decision-making function further combines L 2 -norm and CORT with two discriminator scores to determine the tool conditions. Experimental results show that our method obtains 97% accuracy in tool wear detection based on imbalanced data without manual feature extraction, which outperforms traditional machine learning methods.

Download Full-text

Enhancing Cloud Availability via Intelligent Monitoring using Time Series Database and Machine Learning

International Journal of Software Science and Computational Intelligence ◽

10.4018/ijssci.285591 ◽

2022 ◽

Vol 14 (1) ◽

pp. 0-0

Keyword(s):

Machine Learning ◽

Time Series ◽

Production Systems ◽

Technical Support ◽

Machine Learning Techniques ◽

Cloud Provider ◽

Monitoring Tool ◽

Intelligent Monitoring ◽

Learning Techniques ◽

Proactive Measures

Every cloud provider, wishes to provide 99.9999% availabil- ity for the systems provisioned and operated by them for the customer i.e. may it be SaaS or PaaS or IaaS model, the availability of the system must be greater than 99.9999%.It becomes vital for the provider to mon- itor the systems and take proactive measures to reduce the downtime.In an ideal scenario, the support colleagues (24*7 technical support) must be aware of the on-going issues in the production systems before it is raised as an incident by the customer. But currently, there is no effective alert monitoring solutions for the same. The proposed solution presented in this paper is to have a central alert monitoring tool for all cloud so- lutions offered by the cloud provider. The central alert monitoring tool constantly observes the time series database which contains metric val- ues populated by HA and compares the incoming metric values with the defined thresholds. When a metric value exceeds the defined threshold, using machine learning techniques the monitoring tool decides & takes actions.

Download Full-text

Simple machine learning allied with data-driven methods for monitoring tool wear in machining processes

The International Journal of Advanced Manufacturing Technology ◽

10.1007/s00170-020-05785-x ◽

2020 ◽

Vol 109 (9-12) ◽

pp. 2491-2501

Author(s):

Adalto de Farias ◽

Sérgio Luiz Rabelo de Almeida ◽

Sergio Delijaicov ◽

Vanessa Seriacopi ◽

Ed Claudio Bordinassi

Keyword(s):

Machine Learning ◽

Tool Wear ◽

Data Driven ◽

Monitoring Tool ◽

Machining Processes ◽

Simple Machine

Download Full-text

Binary Spectrum Feature for Improved Classiﬁer Performance

10.36227/techrxiv.12993122 ◽

2020 ◽

Author(s):

Nalika Ulapane ◽

Karthick Thiyagarajan ◽

sarath kodagoda

Keyword(s):

Machine Learning ◽

Classification Performance ◽

Feature Reduction ◽

Sensor Data ◽

Machine Learning Techniques ◽

Support Vector ◽

Svm Classifier ◽

Monitoring Task ◽

Classifier Performance ◽

Spectrum Feature

<div>Classiﬁcation has become a vital task in modern machine learning and Artiﬁcial Intelligence applications, including smart sensing. Numerous machine learning techniques are available to perform classiﬁcation. Similarly, numerous practices, such as feature selection (i.e., selection of a subset of descriptor variables that optimally describe the output), are available to improve classiﬁer performance. In this paper, we consider the case of a given supervised learning classiﬁcation task that has to be performed making use of continuous-valued features. It is assumed that an optimal subset of features has already been selected. Therefore, no further feature reduction, or feature addition, is to be carried out. Then, we attempt to improve the classiﬁcation performance by passing the given feature set through a transformation that produces a new feature set which we have named the “Binary Spectrum”. Via a case study example done on some Pulsed Eddy Current sensor data captured from an infrastructure monitoring task, we demonstrate how the classiﬁcation accuracy of a Support Vector Machine (SVM) classiﬁer increases through the use of this Binary Spectrum feature, indicating the feature transformation’s potential for broader usage.</div><div> </div>

Download Full-text

Speech Organ Contour Extraction Using Real-Time MRI and Machine Learning Method

10.21437/interspeech.2019-1593 ◽

2019 ◽

Author(s):

Hironori Takemoto ◽

Tsubasa Goto ◽

Yuya Hagihara ◽

Sayaka Hamanaka ◽

Tatsuya Kitamura ◽

...

Keyword(s):

Machine Learning ◽

Real Time ◽

Machine Learning Method ◽

Learning Method ◽

Contour Extraction

Download Full-text

Automatic Identification of Upper Extremity Rehabilitation Exercise Type and Dose Using Body-Worn Sensors and Machine Learning: A Pilot Study

Digital Biomarkers ◽

10.1159/000516619 ◽

2021 ◽

pp. 158-166

Author(s):

Noah Balestra ◽

Gaurav Sharma ◽

Linda M. Riek ◽

Ania Busza

Keyword(s):

Machine Learning ◽

Upper Extremity ◽

Sensor Data ◽

Inpatient Setting ◽

Accelerometer Data ◽

Data Set ◽

Machine Learning Classification ◽

Exercise Type ◽

Exercise Dose ◽

Rehabilitation Exercises

Background: Prior studies suggest that participation in rehabilitation exercises improves motor function poststroke; however, studies on optimal exercise dose and timing have been limited by the technical challenge of quantifying exercise activities over multiple days. Objectives: The objectives of this study were to assess the feasibility of using body-worn sensors to track rehabilitation exercises in the inpatient setting and investigate which recording parameters and data analysis strategies are sufficient for accurately identifying and counting exercise repetitions. Methods: MC10 BioStampRC® sensors were used to measure accelerometer and gyroscope data from upper extremities of healthy controls (n = 13) and individuals with upper extremity weakness due to recent stroke (n = 13) while the subjects performed 3 preselected arm exercises. Sensor data were then labeled by exercise type and this labeled data set was used to train a machine learning classification algorithm for identifying exercise type. The machine learning algorithm and a peak-finding algorithm were used to count exercise repetitions in non-labeled data sets. Results: We achieved a repetition counting accuracy of 95.6% overall, and 95.0% in patients with upper extremity weakness due to stroke when using both accelerometer and gyroscope data. Accuracy was decreased when using fewer sensors or using accelerometer data alone. Conclusions: Our exploratory study suggests that body-worn sensor systems are technically feasible, well tolerated in subjects with recent stroke, and may ultimately be useful for developing a system to measure total exercise “dose” in poststroke patients during clinical rehabilitation or clinical trials.

Download Full-text