A Gradual Refreshing Scheme for Improving Tool Utilization

Maintaining tool availability is the key to ensure machining quality. To evaluate tool availability so as to improve its utilization, the tool diagnosis models for tool-remaining-useful-life (RUL) estimation and tool-state classification are required. These models need sufficient samples to cover all the variations of tool coating and chip friction. However, in general, it is not easy to collect enough samples in the early stage. This issue will delay the readiness of the tool diagnosis models. The purpose of this letter is to propose a gradual refreshing scheme for modeling, running, and refreshing tool diagnosis models. In addition, a sample extension method is presented for reducing modeling time and enhancing accuracy of tool-state classification. The examples of engine-case machining are adopted in this letter to illustrate how the system works for estimating tool-RUL, classifying tool-states, and further, improving tool utilization.

[1]  K. Mohandas,et al.  Comparative study of two soft computing techniques for the prediction of remaining useful life of cutting tools , 2015, J. Intell. Manuf..

[2]  Dong Yoon Lee,et al.  Process Monitoring Technology Based on Virtual Machining , 2017 .

[3]  Alessandro Rinaldo,et al.  Distribution-Free Predictive Inference for Regression , 2016, Journal of the American Statistical Association.

[4]  Liang Guo,et al.  A recurrent neural network based health indicator for remaining useful life prediction of bearings , 2017, Neurocomputing.

[5]  Tadeusz Mikolajczyk,et al.  Predicting tool life in turning operations using neural networks and image processing , 2018 .

[6]  Nicolas Le Roux,et al.  Out-of-Sample Extensions for LLE, Isomap, MDS, Eigenmaps, and Spectral Clustering , 2003, NIPS.

[7]  S. Wold,et al.  PLS-regression: a basic tool of chemometrics , 2001 .

[8]  Takaya Saito,et al.  The Precision-Recall Plot Is More Informative than the ROC Plot When Evaluating Binary Classifiers on Imbalanced Datasets , 2015, PloS one.

[9]  Eduardo Carlos Bianchi,et al.  Evaluation of neural models applied to the estimation of tool wear in the grinding of advanced ceramics , 2015, Expert Syst. Appl..

[10]  Fan-Tien Cheng,et al.  Evaluating Reliance Level of a Virtual Metrology System , 2008, IEEE Transactions on Semiconductor Manufacturing.

[11]  Imtiaz Ahmed Choudhury,et al.  Application of acoustic emission sensor to investigate the frequency of tool wear and plastic deformation in tool condition monitoring , 2016 .

[12]  Denis P. Dowling,et al.  Tool Wear in Milling of Medical Grade Cobalt Chromium Alloy - Requirements for Advanced Process Monitoring and Data Analytics , 2016 .

[13]  Haw Ching Yang,et al.  A cyber-physical scheme for predicting tool wear based on a hybrid dynamic neural network , 2017 .

[14]  T. Kurfess,et al.  Tool life predictions in milling using spindle power with the neural network technique , 2016 .

[15]  Kwan-Hee Yoo,et al.  A tool breakage detection system using load signals of spindle motors in CNC machines , 2016, 2016 Eighth International Conference on Ubiquitous and Future Networks (ICUFN).

[16]  Gilberto A. Paula,et al.  An extension of log-symmetric regression models: R codes and applications , 2016 .

[17]  D. E. Dimla,et al.  Sensor signals for tool-wear monitoring in metal cutting operations—a review of methods , 2000 .

[18]  Jian-Huang Lai,et al.  Out-of-Sample Extensions for Non-Parametric Kernel Methods , 2017, IEEE Transactions on Neural Networks and Learning Systems.

[19]  Fan-Tien Cheng,et al.  Developing an Automatic Virtual Metrology System , 2012, IEEE Transactions on Automation Science and Engineering.

[20]  Juan José Rodríguez Diez,et al.  Online breakage detection of multitooth tools using classifier ensembles for imbalanced data , 2014, Int. J. Syst. Sci..

[21]  Zaheer Ullah Khan,et al.  Discrimination of acidic and alkaline enzyme using Chou's pseudo amino acid composition in conjunction with probabilistic neural network model. , 2015, Journal of theoretical biology.