IP Library › Granted Patent US 10,983,501
Granted Patent B2
US 10,983,501 · App. 16/381,738 · Granted Apr 20, 2021

Tool-life prediction system and method thereof

Inventors: Yi-Ming Chen (Taichung, TW); Chi-Cheng Lin (Taichung, TW); Shu-Chung Liao (Taichung, TW); Chen-Yu Kai (Pingtung County, TW); Ta-Jen Peng (Taichung, TW)
Assignee: INDUSTRIAL TECHNOLOGY RESEARCH INSTITUTE
G05B19/4065G06N3/08G05B2219/50185
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 10,983,501
App. No.
16/381,738
Granted
Apr 20, 2021
Kind
B2
Abstract

A tool-life prediction method, applicable to a machine tool having a machining end, includes steps of capturing a plurality of measurement data from a tool of the machining end, transforming each of the plurality of measurement data into a corresponding complex process capability index (Cpk), utilizing an artificial neural network being trained to generate a tool-life prediction scale with respect to the Cpk, and then based on the tool-life prediction scale to determine a remaining tool life of the tool. In addition, a tool life prediction system is also provided.

Claims (13)

1. A tool-life prediction method, applicable to a machine tool having a machining end, comprising the steps of:

(1) capturing a plurality of measurement data from a tool of the machining end;

(2) transforming each of the plurality of measurement data into a corresponding complex process capability index (Cpk);

(3) utilizing an artificial neural network being trained to generate a tool-life prediction scale with respect to the Cpk, including the steps of:

(31) establishing the artificial neural network according to a train database, wherein the train database includes the Cpk and the tool-life prediction scale;

(32) determining whether a training for the artificial neural network has finished, adopting a recurrent neural network (RNN) when finished, and going back to perform the step (2) when the training is not yet finished; and

(33) when the training is finished, applying the artificial neural network to estimate the tool-life prediction scale for the corresponding Cpk, and updating the train database; and

(4) determining a remaining tool life of the tool based on the tool-life prediction scale.

2. The tool-life prediction method of claim 1 , wherein the step (4) includes the steps of:

(41) determining whether a threshold for replacing the tool is exceeded based on the tool-life prediction scale; and

(42) if the threshold is exceeded, issuing a tool processing command to the tool.

3. The tool-life prediction method of claim 2 , wherein, after the step (41), if the threshold is not exceeded, then the tool-life prediction method goes back to perform the step (1).

4. The tool-life prediction method of claim 1 , wherein the plurality of measurement data is a dimension of the tool.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Apr 11, 2019
From: CHEN, YI-MING; LIN, CHI-CHENG; LIAO, SHU-CHUNG; KAI, CHEN-YU; PENG, TA-JEN
To: INDUSTRIAL TECHNOLOGY RESEARCH INSTITUTE
Reel/Frame 050160/0550 →
Priority Claims (1)
TW 108100008 · Jan 2, 2019 · national
Continuity (1)
Related Publication 20200209831A1 · Jul 2, 2020