Prediction of tool breakage in face milling using support vector machine

Hsueh, Yao-Wen; Yang, Chan-Yun

doi:10.1007/s00170-007-1034-8

Cited by 38 publications

(12 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…When that is not a constraint, a data-driven approach avoids the difficulty of specifying complex process models. Support Vector Machines have been used by Cho et al [13] and Hsueh and Yang [14] to detect tool breakage in milling operations based on the force signature of the process. Tax et al [15] have proposed a closely related Support Vector method to analyze machine vibration and Althoefer et al [16] have used a neural network to monitor the insertion of self-tapping threaded fasteners using torque signals.…”

Section: Previous Workmentioning

confidence: 99%

Failure detection in assembly: Force signature analysis

Rodríguez

Bourne

Mason

et al. 2010

2010 IEEE International Conference on Automation Science and Engineering

View full text Add to dashboard Cite

This paper addresses failure detection in automated parts assembly, using the force signature captured during the contact phase of the assembly process. We use a supervised learning approach, specifically a Support Vector Machine (SVM), to distinguish between successful and failed assemblies. This paper describes our implementation and experimental results obtained with an electronic assembly application. We also analyze the tradeoff between system accuracy and number of training examples. We show that a less expensive sensor (a single-axis load cell instead of a six-axis force/torque sensor) provides enough information to detect failure. Finally, we use Principal Component Analysis (PCA) to compress the force signature and as a result reduce the number of examples required to train the system.

show abstract

Section: Previous Workmentioning

confidence: 99%

Failure detection in assembly: Force signature analysis

Rodríguez

Bourne

Mason

et al. 2010

2010 IEEE International Conference on Automation Science and Engineering

View full text Add to dashboard Cite

show abstract

“…In order to address the same and to make the process more versatile towards various tool work-material combinations they used multiple regression model. In 2008 [73], a method using state vector machine (SVM) was proposed to predict tool breakage in face milling. Use of SVM over other approaches like fuzzy, ANN, and so forth has the advantage that the final results depend on very few parameters which lie on the classifier boundary.…”

Section: Machine Learning and Prediction Estimation Basedmentioning

confidence: 99%

Applicability of Tool Condition Monitoring Methods Used for Conventional Milling in Micromilling: A Comparative Review

Mandal

2014

Journal of Industrial Engineering

View full text Add to dashboard Cite

Micromilling is a contact based material removal process in which a rotating tool with nose radius in microns is fed over a stationary workpiece. In the process small amount of material gets chipped off from the workpiece. Due to continuous contact between tool and workpiece significant damage occurs to the cutting tools. Mitigating tool damage to make micromilling systems more reliable for batch production is the current research trend. In macroscale or conventional milling process a number of methods have been proposed for tool condition monitoring. Few of them have been applied for micromilling. This paper reviews different methods proposed and used in last two decades for monitoring the condition of micromilling tools. Applicability of tool condition monitoring methods used in conventional milling has been compared with the similar ones proposed for micromilling. Further, the challenges and opportunities on the applicability issues have been discussed.

show abstract

“…The force/torque signatures were investigated with respect to relative changes in several different layers that could be used to discriminate nominal behavior from errors. Machine learning has also been used for detecting failures, e.g., [4] and [10], where support vector machines were used to detect tool breakage in milling processes.…”

Section: Introductionmentioning

confidence: 99%

Detection of contact force transients in robotic assembly

Stolt

Linderoth

Robertsson

et al. 2015

2015 IEEE International Conference on Robotics and Automation (ICRA)

View full text Add to dashboard Cite

A robotic assembly task is usually implemented as a sequence of simple motions, and the transitions between the motions are made when some events occur. These events can usually be detected with thresholds on some signal, but faster response is possible by detecting the transient on that signal. This paper considers the problem of detecting these transients. A force-controlled assembly task is used as an experimental case, and transients in measured force/torque data are considered. A systematic approach to train machinelearning based classifiers is presented. The classifiers are further implemented in the assembly task, resulting in a 15 % reduction of the total assembly time.

show abstract

Prediction of tool breakage in face milling using support vector machine

Cited by 38 publications

References 11 publications

Failure detection in assembly: Force signature analysis

Failure detection in assembly: Force signature analysis

Applicability of Tool Condition Monitoring Methods Used for Conventional Milling in Micromilling: A Comparative Review

Detection of contact force transients in robotic assembly

Contact Info

Product

Resources

About