CN115597803A - Cutting wheel state detection system and cutting wheel state detection method - Google Patents

Abstract

A cutting wheel state detection system and a cutting wheel state detection method are provided. The system comprises a first sensor, a first controller, a second sensor, a third sensor, a second controller and a host device. The first sensor is configured on the glass clamp, and the first controller provides a clamp state signal based on the opening and closing state signal of the pneumatic cylinder. The second sensor and the third sensor are configured on a cutting head with a cutting wheel, and the second controller provides vibration data of the cutting head based on vibration of the cutting head and current data of the press-in motor based on current of the press-in motor. The host device receives the vibration data and the current data based on the clamp state signal, and analyzes the vibration data and the current data through a cutting wheel health degree model so as to obtain cutting wheel health degree information.

Description

Cutting wheel state detection system and cutting wheel state detection method

Technical Field

The present invention relates to a detecting system, and more particularly, to a cutting wheel status detecting system and a cutting wheel status detecting method.

Background

In a process using a glass substrate, a cutting process needs to be applied to the glass base material so that the glass substrate assumes a desired size. However, in the cutting process, the cutting wheel may be damaged due to the impact, aging and the like. However, the general method of replacing the cutter wheel is to manually detect an abnormality or to replace the cutter wheel by the number of miles (e.g., 25000 m) to replace the cutter wheel. However, the inspection of the cutting wheel by manpower is time-consuming, inefficient, and difficult to manage abnormal risks. Moreover, when the cutting wheel is not damaged, the cost of the cutting tool is increased due to the fact that the cutting wheel is replaced by mileage.

Disclosure of Invention

The invention provides a cutting wheel state detection system and a cutting wheel state detection method, which can monitor the cutting output state in real time to predict the health degree of the cutting wheel, thereby optimizing the production cost and reducing the risk of cutting wheel abnormity.

The state detection system of the cutting wheel comprises a first sensor, a first controller, a second sensor, a third sensor, a second controller and a host device. The first sensor is configured on the glass clamp to detect the opening and closing state signal of the pneumatic cylinder of the glass clamp. The first controller is coupled to the first sensor to provide a clamp state signal based on the pneumatic cylinder open/close state signal. The second sensor is arranged on the cutting head with the cutting wheel to detect the vibration of the cutting head. The third sensor is configured on the press-in motor for driving the cutting wheel so as to detect the current of the press-in motor. The second controller is coupled to the second sensor and the third sensor to provide vibration data of the cutting head based on the vibration of the cutting head and to provide current data of the push motor based on the current of the push motor. The host device is coupled with the first controller and the second controller, receives the vibration data and the current data based on the clamp state signal, and analyzes the vibration data and the current data through a cutting wheel health degree model to provide cutting wheel health degree information comprising at least one health degree estimation of the cutting wheel.

The invention relates to a state detection method of a cutting wheel, which comprises the following steps. The opening and closing state signals of the pneumatic cylinder of the glass clamp are detected through a first sensor arranged on the glass clamp so as to provide clamp state signals. Vibration data of the cutting head and current data of a pressing motor driving the cutting wheel are provided through a second sensor and a third sensor which are arranged on the cutting head with the cutting wheel. The vibration data and the current data are received via the host device based on the clamp state signal. The vibration data and the current data are analyzed through the cutting wheel health degree model to provide cutting wheel health degree information including at least one health degree estimation of the cutting wheel.

Based on the above, the system for detecting the state of the cutting wheel and the method for detecting the state of the cutting wheel in the embodiments of the present invention monitor the vibration of the cutting bit and the current of the pressing motor in real time through the second sensor and the third sensor, so as to obtain the vibration data during cutting. Then, the vibration data during cutting is analyzed to generate cutting wheel health degree information including at least one health degree estimation of the cutting wheel. Therefore, the state of the cutting wheel can be monitored in real time because the cutting wheel health information is generated in real time through the system.

In order to make the aforementioned and other features and advantages of the invention more comprehensible, embodiments accompanied with figures are described in detail below.

Drawings

FIG. 1 is a system diagram of a process equipment monitoring system according to one embodiment of the present invention.

Fig. 2 is a schematic diagram of a simulation of the health information of the cutting wheel according to an embodiment of the invention.

FIG. 3 is a schematic diagram illustrating an analysis of current data according to an embodiment of the invention.

Fig. 4 is a diagram illustrating the separation of vibration data according to an embodiment of the invention.

Fig. 5 is a flowchart illustrating a method for detecting a status of a cutting wheel according to an embodiment of the invention.

Description of the reference numerals:

10: process equipment monitoring system

11: process equipment

13: process control computer

15: database with a plurality of databases

17: machine learning module

19: local end interface

21: remote interface

100: state detection system

110: first controller

120: second controller

130: host device

CTH: cutting tool bit

CTW: cutting wheel

DCU: current data

DCV: vibration characteristic data

DMT: press-in motor

DVT: vibration data

DVTX: cut vibration data

GDX: gas volume data

GFX: glass clamp

MH: cutting wheel health degree model

ICH: cutting wheel health information

PCT: during cutting

And (2) PNC: during non-cutting period

PPX: process parameters

SFX: clamp status signal

SR1: first sensor

SR2: second sensor

SR3: third sensor

S510-S550: step (ii) of

Detailed Description

Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the relevant art and the present invention and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.

It will be understood that, although the terms first, second, third, etc. may be used herein to describe various elements, components, regions, layers and/or sections, these elements, components, regions, and/or sections should not be limited by these terms. These terms are only used to distinguish one element, component, region, layer or section from another element, component, region, layer or section. Thus, a "first element," "component," "region," "layer" or "portion" discussed below could be termed a second element, component, region, layer or portion without departing from the teachings herein.

The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms, including "at least one", unless the content clearly indicates otherwise. "or" means "and/or". As used herein, the term "and/or" includes any and all combinations of one or more of the associated listed items. It will be further understood that the terms "comprises" and/or "comprising," when used in this specification, specify the presence of stated features, regions, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, regions integers, steps, operations, elements, components, and/or groups thereof.

FIG. 1 is a system diagram of a process equipment monitoring system according to one embodiment of the present invention. Referring to fig. 1, in the embodiment of the present invention, a process equipment monitoring system 10 includes process equipment 11, a process control computer 13, a database 15, a machine learning module 17, a local interface 19, a remote interface 21, and a status detection system 100 of a cutting wheel CTW. The process equipment 11 includes, for example, at least a cutter head CTH having a cutter wheel CTW, a press-in motor DMT driving the cutter wheel CTW and provided on the cutter head CTH, and a glass clamp GFX for fixing the glass substrate, wherein the press-in motor DMT controls the degree of press-in of the cutter wheel CTW to the glass substrate, but does not actively rotate the cutter wheel CTW.

The status detecting system 100 for cutting wheel includes a first sensor SR1, a first controller 110, a second sensor SR2, a third sensor SR3, a second controller 120 and a host device 130. The first sensor SR1 is configured on the glass clamp GFX to detect the gas amount data GDX of the glass clamp GFX, wherein the gas amount data GDX may comprise a pneumatic cylinder open/close state signal indicating the open/close state of a pneumatic cylinder (not shown) of the glass clamp GFX. The first controller 110 is coupled to the first sensor SR1 to provide a clamp status signal SFX based on the air volume data GDS (or based on the pneumatic cylinder opening/closing status signal).

The second sensor SR2 is disposed on the cutting head CTH having the cutting wheel CTW to detect the vibration of the cutting head CTH. The third sensor SR3 is disposed on the push-in motor DMT driving the cutting wheel CTW to detect a current of the push-in motor DMT. The second controller 120 is coupled to the second sensor SR2 and the third sensor SR3 to provide vibration data DVT of the cutting bit CHT based on the vibration of the cutting bit CHT and to provide current data DCU of the press-in motor DMT based on the current of the press-in motor DMT.

The host device 130 is coupled to the first sensor 110 and the second sensor 120, the host device 130 receives the vibration data DVT and the current data DCU based on the clamp state signal SFX, determines whether a cutting sequence of at least one long side of the panel and at least one short side of the panel conforms to a preset sequence based on the current data DCU, and analyzes the vibration data DVT and the current data DCU through the cutting wheel health model MH based on the cutting sequence conforming to the preset sequence to provide at least one estimated health information ICH of the cutting wheel CTW.

Fig. 2 is a schematic diagram of a simulation of the health information of the cutting wheel according to an embodiment of the invention. Referring to fig. 1 and 2, in the present embodiment, the cutting wheel health information ICH may be stored in a database to transmit the health of the cutting wheel CTW to the local operator and the remote system administrator through the local interface 19 and the remote interface 21. The local operator can make relevant replacement mechanisms, such as confirming whether the use of the cutting wheel reaches the mileage limit (e.g., 50,000 meters), by himself or according to the notification of the system administrator; whether the cutting wheel knife pressure reaches the upper limit (such as 0.1 Newton (0.1N)); the cutting wheel health is continuously low (e.g., 50% for one hour) and is not improved after cleaning; and, an abnormality occurs and it is confirmed that the cutting wheel has been damaged.

Therefore, since the cutting wheel health information ICH is generated in real time by the system, the status of the cutting wheel can be monitored in real time. If the health degree of the cutting wheel is monitored to be abnormally low, the cutting wheel can be stopped immediately for examination, and the cutting quality of the panel is effectively prevented from being influenced by the abnormity of the cutting wheel. Moreover, the health index of the cutting wheel can be used for replacing the traditional cutting distance (mileage) to manage and measure the use standard of the cutting wheel. In addition, the health degree of using the cutting wheel is used as the index whether the cutting wheel is changed, each cutting wheel can be used to the limit of the physique of the cutting wheel, and the waste is effectively avoided. Moreover, the health degree of the cutting wheel is used as an index for judging whether the cutting wheel is replaced, so that the influence on the product quality caused by the temporary abnormity of the cutting wheel can be effectively avoided.

Referring to fig. 1 again, in the present embodiment, the predetermined sequence is determined based on at least one process parameter PPX from the processing equipment 11 having the cutting head CHT. In other words, the process parameters PPX include at least one cutting pressure applied to the glass substrate, at least one cutting position, at least one cutting displacement, at least one cutting speed, at least one cutting start waiting time, and at least one cutting end waiting time, so that the host device 130 can determine the predetermined cutting sequence of the cutting wheel CTW according to the process parameters PPX.

In addition, in the embodiment of the present invention, the host device 130 determines whether to receive the vibration data DVT and the current data DCU based on the comparison between the clamp state signal SFX and the clamp threshold. In other words, the host device 130 can determine whether the glass clamp GFX clamps the glass substrate based on the comparison between the clamp status signal SFX and the clamp threshold, and receive the vibration data DVT and the current data DCU only when the glass clamp GFX clamps the glass substrate, or not receive the vibration data DVT and the current data DCU.

In the embodiment of the present invention, the host device 130 analyzes the current data DCU to determine at least one cutting period PCT during which the cutting wheel CTW is pressed into the glass substrate and at least one non-cutting period PNC during which the cutting wheel CTW is not pressed into the glass substrate. For example, the host device 130 performs a moving average on the current data DCU, and determines at least one cutting period PCT and at least one non-cutting period PNC based on the current data DCU after the moving average. Moreover, the host device 130 can further determine at least one cutting period PCT and at least one non-cutting period PNC based on a cutting start waiting time and a cutting end waiting time provided by the processing equipment 11.

Then, the host device 130 acquires the vibration data DVT based on the at least one cutting period PCT to generate at least one vibration feature data DCV, and analyzes the at least one vibration feature data DCV to provide the cutting wheel health information ICH. In an embodiment of the present invention, the host device 130 may perform band-pass filtering on the vibration data DVT in the at least one cutting period PCT, and then perform at least one of basic statistical feature extraction, fourier Transform, wavelet packet feature extraction, and Hilbert-yellow Transform (Hilbert-Huang Transform) on the band-pass filtered vibration data DVT in the at least one cutting period PCT to perform feature extraction, so as to generate the vibration feature data DCV.

In the embodiment of the invention, the basic statistical feature extraction includes one of a maximum extraction, a minimum extraction, a mean extraction, a median extraction, a standard deviation extraction, a variance extraction, a skewness extraction and a kurtosis extraction.

In the embodiment of the present invention, the host device 130 determines the cutting direction of a cutting operation of each cutting period PCT for the data length of the vibration data DVT in at least one cutting period PCT, and marks corresponding vibration characteristic data DCV. Moreover, the host device 130 marks at least one vibration characteristic data DCV based on at least one process parameter PPX.

In the embodiment of the present invention, the host device 130 can communicate with the first sensor 110 and the second sensor 120 through an internet of things (IoT). In addition, the host device 130 employs an Outlier Detection (Outlier Detection) algorithm to clean at least one Outlier in the cutting wheel health information ICH.

In the embodiment of the present invention, the host device 130 stores at least one vibration characteristic data DCV in a database 15, so as to establish a cutting wheel health model MH via the machine learning module 17 based on a plurality of past vibration characteristic data DCV stored in the database 15. In one embodiment, the training and prediction process of the MH comprises: marking the vibration characteristic data DCV of each process action under the condition that the currently used cutting wheel is a 'normal cutting wheel' or an 'abnormal cutting wheel'; the data amplification technology is used for enabling the number proportion of the vibration characteristic data DCV of the normal data to be equal to that of the vibration characteristic data DCV of the abnormal data; selecting suitable frequency domain characteristics such as 0.5 frequency doubling, 1 frequency doubling, 2 frequency doubling, 3 frequency doubling, 4 frequency doubling, 5 frequency doubling and the like according to the rotating speed of the cutting wheel (converted through the cutting speed); selecting the vibration characteristic data DCV with the same cutting direction to ensure that the difference is not too large due to the relation of the directions; feature screening using sequence forward selection (Sequential feature selection); and, using the machine learning module 17, an Artificial Intelligence (AI) learns the vibration characteristic data DCV of the cutting wheel CTW in different cutting states, thereby training the cutting wheel health model MH having the capability of predicting the cutting wheel state.

In an embodiment of the invention, a cutting wheel health model MH of maximized Area Under the Curve (AUC) score can be obtained using Distributed hyper parameter Optimization.

The prediction result is converted into a health estimation of the cutting wheel CTW according to the similarity brought by the artificial intelligence (such as the cutting wheel health model MH) and is used as an index for evaluating the validity of the cutting wheel CTW. The data source of the machine learning module 17 is a database 15 storing vibration feature data DCV which has completed data preprocessing. The machine learning module 17 will continuously detect whether new DCV data is generated, and if so, predict the generated DCV data according to the conditions and output the result to the database 15 for storage, thereby providing subsequent visualization and equipment adjustment.

FIG. 3 is a schematic diagram illustrating analysis of current data according to an embodiment of the invention. Referring to fig. 1 and 3, in the present embodiment, part (a) is current data DCU, part (B) is current data DCU after moving average, and part (C) indicates a time period for cutting. According to part (C), a period in which cutting is performed may be denoted as a cutting period PCT, and other periods may be denoted as a non-cutting period PNC. Wherein the cutting period PCT and the non-cutting period PNC can be calibrated based on the cutting start waiting time and the cutting end waiting time provided by the process equipment 11.

FIG. 4 is a diagram illustrating the separation of vibration data according to an embodiment of the present invention. Referring to fig. 1 and 4, in the present embodiment, when the clamp state signal SFX transitions (e.g., rises to a high level), the host device 130 receives the vibration data DVT and the current data DCU (as shown in part (a)). Then, the cutting period PCT and the non-cutting period PNC are determined according to the current data DCU (as shown in fig. 3). Wherein the vibration data DVT in the non-cutting period PNC is masked, that is, only the vibration data DVT of the cutting period PCT is obtained, thereby generating a plurality of cut vibration data DVTX. The host device 130 may process the cut vibration data DVTX to generate vibration characterization data DCV.

FIG. 5 is a flowchart illustrating a method for detecting the status of a cutting wheel according to an embodiment of the invention. Referring to fig. 5, in the present embodiment, the method for detecting the status of the cutting wheel includes the following steps. In step S510, the air volume data (i.e., the pneumatic cylinder open/close status signal) of the glass clamp is detected by the first sensor disposed on the glass clamp to provide a clamp status signal. In step S520, vibration data of the cutting tip and current data of the pressing motor driving the cutting wheel are provided through the second sensor and the third sensor disposed on the cutting tip having the cutting wheel. In step S530, vibration data and current data are received via the host device based on the clamp status signal. In step S540, it is determined whether the cutting sequence of the long edge and the short edge of the at least one panel conforms to a predetermined sequence based on the current data via the host device. In step S550, the vibration data and the current data are analyzed by the cutting wheel health degree model via the host device based on the cutting sequence conforming to the predetermined sequence to provide cutting wheel health degree information including at least one health degree estimate of the cutting wheel. The sequence of steps S510 to S550 is for illustration, and the embodiment of the invention is not limited thereto. The details of steps S510-S550 can be shown in the embodiments of fig. 1-4, and are not repeated herein.

In summary, the system for detecting the status of the cutting wheel and the method for detecting the status of the cutting wheel according to the embodiments of the present invention monitor the vibration of the cutting head and the current of the pressing motor in real time through the second sensor and the third sensor to obtain the vibration data during cutting. Then, the vibration data during cutting is analyzed to generate cutting wheel health degree information including at least one health degree estimation of the cutting wheel. Therefore, the cutting wheel health information is generated in real time through the system, so that the state of the cutting wheel can be monitored in real time. Under the condition that the health degree of the cutting wheel is abnormally low, the cutting wheel can be stopped immediately for checking so as to effectively avoid the abnormal condition of the cutting wheel from influencing the cutting quality of the panel. And, the health degree that uses the cutting wheel comes as the index whether the cutting wheel is changed, can let each cutting wheel all use the limit of self physique, effectively avoids extravagant emergence.

Although the present invention has been described with reference to the above embodiments, it should be understood that various changes and modifications can be made therein by those skilled in the art without departing from the spirit and scope of the invention.

Claims (32)

1. A cutting wheel condition detection system, comprising:

a first sensor, configured on a glass clamp, for detecting an opening/closing state signal of a pneumatic cylinder of the glass clamp;

a first controller coupled to the first sensor for providing a clamp status signal based on the pneumatic cylinder open/close status signal;

a second sensor, which is arranged on a cutting knife head with the cutting wheel to detect the vibration of the cutting knife head;

a third sensor, configured to a press-in motor driving the cutting wheel, for detecting a current of the press-in motor;

a second controller coupled to the second sensor and the third sensor for providing a vibration data of the cutting bit based on the vibration of the cutting bit and providing a current data of the push motor based on the current of the push motor;

the host device receives the vibration data and the current data based on the clamp state signal, and analyzes the vibration data and the current data through a cutting wheel health degree model to provide cutting wheel health degree information comprising at least one health degree estimation of the cutting wheel.

2. The system for detecting the condition of the cutting wheel as claimed in claim 1, wherein the pressing motor controls a degree of pressing of the cutting wheel into a glass substrate.

3. The system of claim 1, wherein the host device determines whether a cutting sequence of at least one panel long side and at least one panel short side is in accordance with a predetermined sequence based on the current data, and analyzes the vibration data and the current data through the cutting wheel health model based on the cutting sequence being in accordance with the predetermined sequence.

4. The system for detecting the status of a cutting wheel as claimed in claim 3, wherein the predetermined sequence is determined based on at least one process parameter from a process tool having the cutting head.

5. The system of claim 4, wherein the host device determines whether to receive the vibration data and the current data based on a comparison of a clamp status signal and a clamp threshold.

6. The cut-off wheel condition detection system of claim 4 wherein the host device analyzes the current data to determine at least one cut period and at least one non-cut period, acquires the vibration data based on the at least one cut period to generate at least one vibration signature data, and analyzes the at least one vibration signature data to provide the cut-off wheel health information.

7. The system for detecting status of a cutting wheel as claimed in claim 6, wherein the host device performs moving average on the current data, and determines the at least one cutting period and the at least one non-cutting period based on the current data after moving an average line.

8. The system for detecting the status of the cutoff wheel as claimed in claim 6, wherein the host device band-pass filters the vibration data during the at least one cutting period to generate the at least one vibration characterization data.

9. The system for detecting the status of a cutting wheel as claimed in claim 8, wherein the host device performs at least one of a basic statistic feature extraction, a fourier transform, a wavelet packet feature extraction, and a hilbert-yellow transform on the vibration data band-pass filtered during the at least one cutting period to generate the at least one vibration feature data.

10. The system of claim 9, wherein the basic statistical feature extraction comprises one of a maximum extraction, a minimum extraction, a mean extraction, a median extraction, a standard deviation extraction, a variance extraction, a skewness extraction, and a kurtosis extraction.

11. The system for detecting the status of a cutoff wheel according to claim 6, wherein the host device further determines the at least one cutting period and the at least one non-cutting period based on a cutting start wait time and a cutting end wait time provided by the processing tool.

12. The system of claim 6, wherein the host device determines a cutting direction of a cutting operation during each cutting period according to a data length of the vibration data during the at least one cutting period and marks corresponding vibration characteristic data.

13. The system of claim 6, wherein the host device stores the at least one vibration signature data in a database to establish the cutting wheel health model via machine learning based on past vibration signatures stored in the database.

14. The system of claim 6, wherein the host device marks the at least one vibration signature based on the at least one process parameter.

15. The system of claim 4, wherein the at least one process parameter comprises at least one cutting pressure applied to the glass substrate, at least one cutting position, at least one cutting displacement, at least one cutting speed, at least one cutting start wait time, and at least one cutting end wait time.

16. The cut-off wheel condition detection system of claim 1 wherein the host device employs an outlier detection algorithm to clean at least one outlier datum of the cut-off wheel health information.

17. The system of claim 1, wherein the host device communicates with the first sensor and the second sensor via an internet of things.

18. A method for detecting the state of a cutting wheel comprises the following steps:

detecting an opening and closing state signal of a pneumatic cylinder of a glass clamp through a first sensor arranged on the glass clamp so as to provide a clamp state signal;

providing a vibration data of the cutting head and a current data of a pressing motor driving the cutting wheel through a second sensor and a third sensor which are arranged on the cutting head with the cutting wheel;

receiving the vibration data and the current data based on the clamp state signal through a host device; and

the vibration data and the current data are analyzed through a cutting wheel health degree model through the host device so as to provide cutting wheel health degree information including at least one health degree estimation of the cutting wheel.

19. The status detecting method of the cutting wheel as set forth in claim 18, further comprising:

judging whether a cutting sequence of at least one panel long edge and at least one panel short edge accords with a preset sequence or not through the host device based on the current data; and

the vibration data and the current data are analyzed through the cutting wheel health degree model based on the cutting sequence and the preset sequence by the host device.

20. The status detecting method of the cutting wheel as set forth in claim 19, further comprising:

the predetermined sequence is determined based on at least one process parameter from a process tool having the cutting tip.

21. The status detecting method of the cutting wheel as set forth in claim 20, further comprising:

whether to receive the vibration data and the current data is judged by the host device based on the comparison between a clamp state signal and a clamp critical value.

22. The status detecting method of the cutting wheel as set forth in claim 20, further comprising:

analyzing the current data by the host device to determine at least one cutting period and at least one non-cutting period;

acquiring the vibration data based on the at least one cutting period through the host device to generate at least one vibration characteristic data; and

the host device analyzes the at least one vibration characteristic data to provide health information of the cutting wheel.

23. The status detecting method of the cutting wheel as set forth in claim 22, further comprising:

performing a moving average on the current data via the host device; and

the host device determines the at least one cutting period and the at least one non-cutting period based on the current data after moving averaging.

24. The status detecting method of the cutting wheel as set forth in claim 22, further comprising:

the host device band-pass filters the vibration data during the at least one cutting period to generate the at least one vibration characteristic data.

25. The status detecting method of the cutting wheel as set forth in claim 24, further comprising:

the host device performs at least one of a basic statistical feature extraction, a Fourier transform, a wavelet packet feature extraction, and a Hilbert-Huang transform on the vibration data subjected to band-pass filtering during the at least one cutting period to generate the at least one vibration feature data.

26. The method of claim 25, wherein the basic statistical feature extraction comprises one of a maximum extraction, a minimum extraction, a mean extraction, a median extraction, a standard deviation extraction, a variance extraction, a skewness extraction, and a kurtosis extraction.

27. The status detecting method of the cutting wheel as set forth in claim 22, further comprising:

the at least one cutting period and the at least one non-cutting period are determined by the host device further based on a cutting start waiting time and a cutting end waiting time provided by the processing equipment.

28. The status detecting method of the cutting wheel as set forth in claim 22, further comprising:

the cutting direction of a cutting action in each cutting period is judged according to the data length of the vibration data in the at least one cutting period by the host device, and corresponding vibration characteristic data are marked.

29. The method of claim 22, wherein the host device stores the at least one vibration signature data in a database for establishing the cutting wheel health model via machine learning based on a plurality of past vibration signature data stored in the database.

30. The status detecting method of the cutting wheel as set forth in claim 22, further comprising:

the host device marks the at least one vibration characteristic data based on the at least one process parameter.

31. The method of claim 20, wherein the at least one process parameter comprises at least one cutting pressure applied to the glass substrate, at least one cutting position, at least one cutting displacement, at least one cutting speed, at least one cutting start wait time, and at least one cutting end wait time.

32. The status detecting method of the cutting wheel as set forth in claim 18, further comprising:

the host device cleans at least one outlier data in the cutting wheel health information by using an outlier detection algorithm.

Images