Tool condition monitoring system

Patent metadata

Field	Value
Publication number	US-12135258-B2
Application number	US-202117551652-A
Country	US
Kind code	B2
Filing date	Dec 15, 2021
Priority date	Dec 15, 2020
Publication date	Nov 5, 2024
Grant date	Nov 5, 2024

Abstract

Systems, methods, and computer program products for monitoring a health condition of a tool. Operational data is collected from a machine while the machine is operating in a predetermined manner with the tool in each of at least two known health conditions. A plurality of features is extracted from the operational data, a training dataset is generated from the extracted features, and an analytic model is trained using the training dataset. The analytic model can then be used to determine the health condition of the tool by providing features extracted from operational data received from one or more field machines to the analytic model. The analytic model may then determine a health condition of the tool in the field machine based on like features extracted from the operational data from the one or more field machines.

First claim

What is claimed is:

1. A system for monitoring a tool health condition, comprising:
one or more processors; and
a memory coupled to the one or more processors and including program code that, when executed by the one or more processors, causes the system to:
collect first operational data from a machine while the machine is operating in a predetermined manner with a tool including a plurality of pockets, the tool being in a first known health condition defined by operatively coupling a first number of inserts into a like number of the plurality of pockets;
collect second operational data from the machine while the machine is operating in the predetermined manner with the tool in a second known health condition defined by operatively coupling a second number of inserts into a like number of the plurality of pockets, the second number being different from the first number;
extract a first plurality of features from the first operational data;
extract a second plurality of features from the second operational data;
generate a training dataset from the first plurality of features and the second plurality of features; and
train an analytic model to determine the health condition of the tool using the training dataset.

2. The system of claim 1 , wherein the program code causes the system to generate the training dataset from the first plurality of features and the second plurality of features by:
comparing each feature of the first plurality of features to a like feature of the second plurality of features; and
selecting a subset of features from each of the first plurality of features and the second plurality of features as the training dataset based on the comparisons.

3. The system of claim 2 , wherein the program code causes the system to compare each feature of the first plurality of features to the like feature of the second plurality of features by determining a magnitude of a difference between the features being compared.

4. The system of claim 3 , wherein the program code causes the system to select the subset of features from each of the first plurality of features and the second plurality of features as the training dataset based on the comparisons by selecting one or more features based on the magnitudes of the differences.

5. The system of claim 1 , wherein the first number is equal to a total number of pockets in the tool, and the second number is less than the first number.

6. The system of claim 1 , wherein the program code causes the system to operate the machine in the predetermined manner by causing the machine to rotate the tool at a predetermined speed.

7. The system of claim 1 , wherein the machine includes a motor operatively coupled to a spindle, and each of the first operational data and the second operational data includes data indicative of one or more of a vibration, a power consumption of the motor, a speed of the motor, an amount of torque generated by the motor, a position of the spindle, a movement of the spindle, and a force applied to the spindle.

8. The system of claim 1 , wherein each plurality of features includes one or more of a frequency domain feature, a time domain feature, and a time-frequency domain feature.

9. A method of monitoring a tool health condition, comprising:
collecting first operational data from a machine while the machine is operating in a predetermined manner with a tool including a plurality of pockets, the tool being in a first known health condition defined by operatively coupling a first number of inserts into a like number of the plurality of pockets;
collecting second operational data from the machine while the machine is operating in the predetermined manner with the tool in a second known health condition defined by operatively coupling a second number of inserts into a like number of the plurality of pockets, the second number being different from the first number;
extracting a first plurality of features from the first operational data;
extracting a second plurality of features from the second operational data;
generating a training dataset from the first plurality of features and the second plurality of features; and
training an analytic model to determine the health condition of the tool using the training dataset.

10. The method of claim 9 , wherein generating the training dataset from the first plurality of features and the second plurality of features includes:
comparing each feature of the first plurality of features to a like feature of the second plurality of features; and
selecting a subset of features from each of the first plurality of features and the second plurality of features as the training dataset based on the comparisons.

11. The method of claim 10 , wherein comparing each feature of the first plurality of features to the like feature of the second plurality of features includes determining a magnitude of a difference between the features being compared.

12. The method of claim 11 , wherein selecting the subset of features from each of the first plurality of features and the second plurality of features as the training dataset based on the comparisons includes selecting one or more features based on the magnitudes of the differences.

13. The method of claim 9 , wherein the first number is equal to a total number of pockets in the tool, and the second number is less than the first number.

14. The method of claim 9 , wherein operating the machine in the predetermined manner includes causing the machine to rotate the tool at a predetermined speed.

15. The method of claim 9 , wherein the machine includes a motor operatively coupled to a spindle, and each of the first operational data and the second operational data includes data indicative of one or more of a vibration, a power consumption of the motor, a speed of the motor, an amount of torque generated by the motor, a position of the spindle, a movement of the spindle, and a force applied to the spindle.

16. The method of claim 9 , wherein each plurality of features includes one or more of a frequency domain feature, a time domain feature, and a time-frequency domain feature.

17. A computer program product for monitoring a tool health condition, comprising:
a non-transitory computer-readable storage medium; and
program code stored on the non-transitory computer-readable storage medium that, when executed by one or more processors, causes the one or more processors to:
collect first operational data from a machine while the machine is operating in a predetermined manner with a tool including a plurality of pockets, the tool being in a first known health condition defined by operatively coupling a first number of inserts into a like number of the plurality of pockets;
collect second operational data from the machine while the machine is operating in the predetermined manner with the tool in a second known health condition defined by operatively coupling a second number of inserts into a like number of the plurality of pockets, the second number being different from the first number;
extract a first plurality of features from the first operational data;
extract a second plurality of features from the second operational data;
generate a training dataset from the first plurality of features and the second plurality of features; and
train an analytic model to determine the health condition of the tool using the training dataset.

Assignees

• Univ Cincinnati
• Mazak Corp

Inventors

• Azamfar Moslem
• Pandhare Vibhor
• Miller Marcella
• Li Fei
• Li Pin
• Singh Jaskaran
• Davari Hossein
• Lee Jay
• Sanders Jr Joseph Frank
• Yamaguchi Keita

Classifications

• B23Q17/2457

  of tools · CPC title

• G06F30/27

  using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model · CPC title

• G05B23/0254

  based on a quantitative model, e.g. mathematical relationships between inputs and outputs; functions: observer, Kalman filter, residual calculation, Neural Networks · CPC title

• G01M13/00 Primary

  Testing of machine parts · CPC title

• G05B23/0237 Primary

  based on parallel systems, e.g. comparing signals produced at the same time by same type systems and detect faulty ones by noticing differences among their responses · CPC title