KR20220055160A - Apparatus and method for simultaneous monitoring of bearing and tool condition - Google Patents

Abstract

The present invention relates to an apparatus and a method for simultaneously monitoring states of a bearing and a tool, and the apparatus comprises: a data measurement unit that measures vibration data generated when a machine tool is operated; a bearing diagnosis model unit that generates a bearing diagnosis model by extracting characteristics of the vibration data generated in conditions of a normal bearing and a broken bearing and constructing learning data; a tool state diagnosis model unit that generates a tool state diagnosis model by extracting characteristics of the vibration data generated in a processing process using normal and worn tools and constructing learning data; and a monitoring unit that simultaneously monitors the bearing and the tool of the machine tool through the bearing diagnosis model and the tool state diagnosis model based on the measured vibration data in order to diagnose states of the bearing and the tool. The present invention can improve productivity by diagnosing in real-time the states of the bearing and the tool.

Description

Apparatus and method for simultaneous monitoring of bearing and tool condition

The present invention relates to a bearing and tool condition monitoring technology, and more particularly, a bearing and tool capable of simultaneously performing bearing and tool monitoring and diagnosing the condition of bearing and tool by collecting vibration data in real time in a machine tool machining process. It relates to an apparatus and method for simultaneous state monitoring.

Composite rotating body machines are generally subject to unpredictable component failure due to noise or other factors. Malfunctions in the rotating body of a machine tool appear in the tools and spindle bearings that process the workpiece. Since bearings constitute an important part of rotating machines, various data such as vibration and temperature were measured to predict or diagnose bearing conditions. The tool of the machine tool is a factor that determines the quality of the workpiece, and the state of the tool was diagnosed with the data collected using various sensors (accelerometer, acoustic sensor, etc.) or the level of tool wear was measured using measuring equipment.

The existing machine tool monitoring system estimates the state of the bearing using the spindle load indicated by the NC or measures the worn part of the tool through a sensor to measure the worn part of the tool and the bearing to individually monitor the bearing and tool status. Diagnosis takes a lot of time, which lowers the productivity of the machining process.

Korean Patent No. 10-1957711 (2019.03.07) uses a cutting characteristic map that maps the processing position and physical processing and cutting characteristic values according to the processing time in the processing coordinate system to intelligently monitor and diagnose the cutting state and cutting conditions It relates to an intelligent CNC machine tool control system that can control Technology that can perform a function to monitor the cutting state, diagnose whether the cutting state is defective, etc., and to change and control defective and low-productive cutting conditions into high-quality and high-productive cutting conditions when performing machining. start about

Korean Patent Laid-Open Patent No. 10-2018-0024093 (2018.03.08) relates to a tool damage monitoring method of a machine tool based on a cutting load reflecting the actual movement speed, information on the tool, workpiece, processing path and feed rate Calculating the arithmetic cutting load considering Including the steps of calculating the cutting load, measuring the actual cutting load input to the tool when processing the workpiece through the tool, and judging whether the tool is damaged in comparison with the actual cutting load and the reference cutting load. Disclosed is a technology that can increase the accuracy of condition monitoring.

Korean Patent Registration No. 10-1957711 (2019.03.07) Korean Patent Publication No. 10-2018-0024093 (2018.03.08)

An embodiment of the present invention provides an apparatus and method for simultaneous monitoring of bearing and tool conditions that can perform bearing and tool monitoring at the same time and diagnose the condition of bearing and tool by collecting vibration data in real time in a machine tool machining process want to

An embodiment of the present invention generates a machine learning-based bearing and tool condition diagnosis model by utilizing the spindle acceleration signal of the machine tool, and uses the bearing diagnosis model and the tool condition diagnosis model in real time during the cutting process of the machine tool. And it is an object of the present invention to provide an apparatus and method for simultaneous monitoring of a bearing and a tool state that can improve productivity by diagnosing the tool state.

An embodiment of the present invention attaches a 3-axis acceleration sensor to a spindle and applies acceleration data measured during the machining process to a bearing diagnosis model and a tool condition diagnosis model to simultaneously perform bearing monitoring and tool monitoring. An object of the present invention is to provide an apparatus and method for monitoring.

Among the embodiments, the device for simultaneous monitoring of the bearing and tool condition includes a data measuring unit that measures vibration data generated when the machine tool is operating, extracting characteristics of vibration data generated under normal bearing and damaged bearing conditions, and learning data A bearing diagnosis model unit that creates a bearing diagnosis model by configuring and a monitoring unit diagnosing the state of the bearing and the tool by simultaneously monitoring the bearing and the tool of the machine tool through the bearing diagnosis model and the tool state diagnosis model based on the measured vibration data.

The data measuring unit may attach an acceleration sensor to the spindle of the machine tool and measure vibration according to the spindle operation through the acceleration sensor.

The bearing diagnosis model unit may extract the characteristic data for the natural frequency of the bearing defect compared to the normal data by separating the frequency component from the vibration data generated in the normal bearing and the damaged bearing through the empirical mode decomposition method.

The bearing diagnosis model unit may generate a bearing diagnosis model for classifying normal and abnormal bearings through machine learning by selecting the characteristic data extracted through the correlation function and inputting the selected characteristic data.

The bearing diagnosis model unit clusters the extracted characteristic data through a correlation function to form a first cluster consisting of characteristic data of a normal bearing and a second cluster consisting of characteristic data for each defect of a damaged bearing, and the first cluster and the second cluster The feature data may be selected based on dissimilarity between clusters.

The bearing diagnosis model unit may calculate the dissimilarity according to the following [Equation].

[Equation]

Here, r _c1 is the radius of the cluster of normal data, r _c2 is the radius of the cluster of abnormal data, and D _c1,c2 is the distance between the centers of the two clusters.

The bearing diagnosis model unit may generate a bearing diagnosis model by inputting the selected characteristic data into a support vector machine.

The tool condition diagnosis model unit collects vibration data of the machining process using a worn tool and a normal tool through an acceleration sensor, extracts features from the collected vibration data, and learns the extracted feature data as an input by neural network learning to classify normal and wear. A tool condition diagnosis model can be created.

The tool state diagnosis model unit may display the classified normality and wear in a confusion matrix to check the normality and wear classification rate of the tool.

Among the embodiments, the method for simultaneous monitoring of bearing and tool conditions includes extracting features based on vibrations generated in normal bearing and broken bearing conditions and constructing learning data to generate a bearing diagnostic model; Extracting features based on vibrations generated in the used machining process and constructing learning data to generate a tool condition diagnosis model, measuring vibration data generated when the machine tool is operated, and using the measured vibration data and diagnosing the state of the bearing and the tool by simultaneously monitoring the bearing and the tool of the machine tool based on the bearing diagnosis model and the tool state diagnosis model.

The bearing diagnostic model generation step includes the steps of collecting vibration data generated under conditions of normal bearings and damaged bearings, separating frequency components from the collected vibration data and extracting characteristic data for the natural frequency of bearing defects compared to normal data; It may include selecting the extracted feature data for identifying the abnormality of the bearing through a correlation function, and generating a bearing diagnostic model by performing machine learning with the selected feature data.

In the bearing diagnosis model generation step, the dissimilarity calculated by calculating the dissimilarity between the first cluster composed of the characteristic data of the normal bearing and the second cluster composed of the characteristic data for each defect of the damaged bearing through the following equation in the characteristic data selection process may select feature data that satisfies a specific criterion.

[Equation]

Here, r _c1 is the radius of the cluster of normal data, r _c2 is the radius of the cluster of abnormal data, and D _c1,c2 is the distance between the centers of the two clusters.

The tool state diagnosis model generation step includes the steps of collecting vibration data of the machining process using a worn tool and a normal tool, extracting features from the collected vibration data, and learning a neural network using the extracted feature data as an input to obtain normal and wear It may include generating a tool state diagnosis model by classifying the .

The disclosed technology may have the following effects. However, this does not mean that a specific embodiment should include all of the following effects or only the following effects, so the scope of the disclosed technology should not be understood as being limited thereby.

An apparatus and method for simultaneous monitoring of a bearing and a tool state according to an embodiment of the present invention collects vibration data in real time in a machine tool machining process, performs bearing and tool monitoring at the same time, and diagnoses the state of the bearing and tool .

An apparatus and method for simultaneous monitoring of a bearing and a tool state according to an embodiment of the present invention generates a machine learning-based bearing and tool state diagnosis model, respectively, by utilizing the spindle acceleration signal of a machine tool, and diagnoses a bearing diagnosis model and a tool state. Through the model, productivity can be improved by diagnosing bearing and tool conditions in real time during the cutting process of machine tools.

An apparatus and method for simultaneous monitoring of a bearing and a tool state according to an embodiment of the present invention attaches a 3-axis acceleration sensor to a spindle and applies acceleration data measured during machining to a bearing diagnosis model and a tool condition diagnosis model to monitor the bearing and tool monitoring can be performed simultaneously.

1 is a view for explaining a system for simultaneously monitoring a bearing and a tool state according to an embodiment of the present invention.
FIG. 2 is a view for explaining an apparatus for simultaneous monitoring of bearing and tool conditions in FIG. 1 .
3 is a flowchart illustrating a bearing diagnosis model generation process of the bearing diagnosis model unit of FIG. 2 .
FIG. 4 is a flowchart illustrating a process of generating a tool state diagnosis model of the tool state diagnosis model unit of FIG. 2 .
5 is an exemplary diagram illustrating a configuration of a bearing diagnosis test apparatus according to an exemplary embodiment.
6 is an exemplary view illustrating a defect type of a bearing according to an embodiment.
7A-7B are exemplary views illustrating characteristics of vibration data according to normal and defective bearings according to an embodiment.
8 is an exemplary view illustrating a state in which characteristic data according to normal and defective bearings according to an embodiment are displayed in a coordinate system.
9 is an exemplary diagram illustrating clustering using a correlation function of characteristic data according to normal and defective bearings according to an embodiment.
10 is an exemplary diagram illustrating the size distribution of vibration data according to time of a normal tool and a worn tool according to an embodiment.
11 is an exemplary diagram illustrating a neural network structure for a tool state diagnosis model according to an embodiment.
12 is an exemplary diagram illustrating a confusion matrix in which normal and wear of the tool state diagnosis model according to an embodiment are classified.
13 is an exemplary view illustrating a simultaneous monitoring screen of a bearing and a tool state according to an embodiment.

Since the description of the present invention is merely an embodiment for structural or functional description, the scope of the present invention should not be construed as being limited by the embodiment described in the text. That is, since the embodiment may have various changes and may have various forms, it should be understood that the scope of the present invention includes equivalents capable of realizing the technical idea. In addition, since the object or effect presented in the present invention does not mean that a specific embodiment should include all of them or only such effects, it should not be understood that the scope of the present invention is limited thereby.

On the other hand, the meaning of the terms described in the present application should be understood as follows.

Terms such as “first” and “second” are for distinguishing one component from another, and the scope of rights should not be limited by these terms. For example, a first component may be termed a second component, and similarly, a second component may also be termed a first component.

When a component is referred to as being “connected to” another component, it may be directly connected to the other component, but it should be understood that other components may exist in between. On the other hand, when it is mentioned that a certain element is "directly connected" to another element, it should be understood that the other element does not exist in the middle. On the other hand, other expressions describing the relationship between elements, that is, "between" and "between" or "neighboring to" and "directly adjacent to", etc., should be interpreted similarly.

The singular expression is to be understood as including the plural expression unless the context clearly dictates otherwise, and terms such as "comprises" or "have" refer to the embodied feature, number, step, action, component, part or these It is intended to indicate that a combination exists, and it should be understood that it does not preclude the possibility of the existence or addition of one or more other features or numbers, steps, operations, components, parts, or combinations thereof.

In each step, identification numbers (eg, a, b, c, etc.) are used for convenience of description, and identification numbers do not describe the order of each step, and each step clearly indicates a specific order in context. Unless otherwise specified, it may occur in a different order from the specified order. That is, each step may occur in the same order as specified, may be performed substantially simultaneously, or may be performed in the reverse order.

The present invention can be embodied as computer-readable codes on a computer-readable recording medium, and the computer-readable recording medium includes all types of recording devices in which data readable by a computer system is stored. . Examples of the computer-readable recording medium include ROM, RAM, CD-ROM, magnetic tape, floppy disk, optical data storage device, and the like. In addition, the computer-readable recording medium is distributed in a computer system connected to a network, so that the computer-readable code can be stored and executed in a distributed manner.

All terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the present invention belongs, unless otherwise defined. Terms defined in general used in the dictionary should be interpreted as having the meaning consistent with the context of the related art, and cannot be interpreted as having an ideal or excessively formal meaning unless explicitly defined in the present application.

1 is a view for explaining a system for simultaneously monitoring a bearing and a tool state according to an embodiment of the present invention.

Referring to FIG. 1 , the bearing and tool condition simultaneous monitoring system 100 may include a device 130 for monitoring the condition of the bearing 111 and the tool 113 of the machine tool 110 .

The machine tool 110 is a machine for making various machines, and refers to a machine for processing such as metal cutting.

The device 130 for simultaneous monitoring of the bearing and tool status is implemented as a server corresponding to a computer or program capable of diagnosing the status of the bearing 111 and the tool 113 in real time by monitoring the cutting process of the machine tool 110 can be The device 130 for simultaneous monitoring of the bearing and tool state is a bearing diagnostic model that diagnoses the normality and damage of the bearing 111 based on the vibration generated when the machine tool 110 is operated, and the wear of the tool 113. A tool condition diagnosis model to diagnose may be generated, and the states of the bearing 111 and the tool 113 may be monitored based on the bearing diagnosis model and the tool condition diagnosis model.

FIG. 2 is a block diagram illustrating an apparatus for simultaneous monitoring of bearing and tool conditions in FIG. 1 .

Referring to FIG. 2 , the apparatus 130 for simultaneous monitoring of bearing and tool conditions includes a data measuring unit 210 , a bearing diagnosis model unit 230 , a tool condition diagnosis model unit 250 , a monitoring unit 270 , and a control unit. (290).

The data measurement unit 210 may measure vibration data generated when the machine tool 110 is operated. In one embodiment, the data measuring unit 210 may measure the vibration according to the spindle operation by attaching a 3-axis acceleration sensor to the spindle of the machine tool 110 . Here, the data measuring unit 210 may collect vibration data in each direction of the X-axis, Y-axis, and Z-axis using the 3-axis acceleration sensor.

The bearing diagnosis model unit 230 may generate a bearing diagnosis model by extracting characteristics of vibration data generated under normal bearing and damaged bearing conditions and composing learning data. In an embodiment, the bearing diagnosis model unit 230 may extract a characteristic of the vibration data measured using an empirical mode decomposition method.

The empirical mode decomposition method is a technique applying the Hilbert transform, and it can separate time and amplitude signals based on frequency, and this is called an intrinsic mode function. Abnormal data and normal data can be distinguished using the intrinsic mode function.

The bearing diagnosis model unit 230 may extract an intrinsic mode function by separating a frequency component from vibration data measured by applying an empirical mode decomposition method, and extract feature data from the extracted intrinsic mode function. Here, the characteristic data is a natural frequency component of a bearing defect, and represents kurtosis, skewness, standard deviation, and average values compared to normal data. The bearing diagnosis model unit 230 may generate a bearing diagnosis model through machine learning by selecting the feature data extracted through the selection criteria. In an embodiment, the bearing diagnosis model unit 230 may select feature data using a correlation function, and input the selected feature data into a support vector machine to diagnose bearing normality and abnormality. You can create a model.

The tool condition diagnosis model unit 250 may generate a tool condition diagnosis model by extracting characteristics of vibration data generated in a machining process using normal and worn tools and configuring learning data. In one embodiment, the tool state diagnosis model unit 250 extracts characteristic data through a continuous wavelet transformation technique for vibration data measured by a normal tool and vibration data measured by a worn tool, and characteristic data of abnormal data compared to normal data Through deep learning using a convolutional neural network by selecting

The monitoring unit 270 simultaneously monitors the bearing 111 and the tool 113 of the machine tool 110 through the bearing diagnosis model and the tool state diagnosis model based on the vibration data measured when the machine tool 110 is processed. by performing a quick diagnosis of the state of the bearing 111 and the tool 113 . In one embodiment, the monitoring unit 270 allows the replacement of the bearing 111 and the tool 113 at an appropriate time based on the diagnosis result of the bearing 111 and the tool 113 to thereby increase the productivity of the machine tool 110 . can provide improvement.

The control unit 290 controls the overall operation of the device 130 for simultaneous monitoring of the bearing and tool conditions, and the data measurement unit 210 , the bearing diagnosis model unit 230 , the tool condition diagnosis model unit 250 , and the monitoring unit It is possible to manage the control flow and data flow between the 270 .

3 is a flowchart for explaining a bearing diagnosis model generation process of the bearing diagnosis model unit of FIG. 2 .

In FIG. 3 , the bearing diagnosis model unit 230 collects vibration data generated under normal bearing and damaged bearing conditions (step S310 ). The bearing diagnosis model unit 230 may collect vibration data by measuring vibration generated when the machine tool 110 is operated using an acceleration sensor. The bearing diagnosis model unit 230 may collect vibration data generated when the bearing 111 of the machine tool 110 is normal and vibration data generated when the bearing 111 has a defect. For example, as shown in FIG. 4 , the bearing diagnosis model unit 230 collects vibration data generated in the normal bearing 420 and the defective bearing 430 using the acceleration sensor 410 .

4 is an exemplary view showing the configuration of a bearing diagnostic test apparatus according to an embodiment, and FIG. 5 is an exemplary view showing a bearing defect according to an exemplary embodiment.

As illustrated in FIG. 5, bearing defects occur in various ways, such as cage defects, smearing (stained state), and flaking (a phenomenon in which the surface is peeled off into thin pieces). Bearings have different vibration characteristics depending on the condition of the defect.

Again, returning to FIG. 3 , the bearing diagnosis model unit 230 extracts features from the collected vibration data (step S330 ). The bearing diagnosis model unit 230 separates a frequency component from the vibration data and extracts characteristic data for a bearing defect. In an embodiment, the bearing diagnosis model unit 230 extracts an intrinsic mode function of the vibration data using an empirical mode decomposition method, which is a signal processing technique, and extracts feature data from the extracted intrinsic mode function. Here, the feature data may include kurtosis, skewness, standard deviation, and average values. For example, as shown in FIG. 6A , the bearing diagnosis model unit 230 may extract the intrinsic mode function by separating the vibration data of amplitude and time based on frequency using an empirical mode decomposition method.

6A and 6B are exemplary diagrams illustrating characteristics of an intrinsic mode function extracted using an empirical mode decomposition method from vibration data according to normal and defective bearings according to an embodiment.

As illustrated in FIG. 6B , the amplitude of the intrinsic mode function of the vibration data of the abnormal bearing is larger than that of the intrinsic mode function of the normal vibration data. The intrinsic mode function of the vibration data of an ideal bearing has different amplitudes depending on the type of defect.

7 is an exemplary diagram illustrating a state in which feature data is displayed in a coordinate system according to an exemplary embodiment.

As illustrated in FIG. 7 , the bearing diagnosis model unit 230 may classify by displaying characteristic data according to the normal and defective types of the bearing in the Cartesian coordinate system. For example, the bearing diagnosis model unit 230 may classify the feature data extracted according to the classification criteria of the degree of asymmetry, standard deviation, mean, and root mean square by displaying it in a Cartesian coordinate system including the X-axis and the Y-axis. In an embodiment, the bearing diagnosis model unit 230 may classify the feature data by combining a plurality of classification criteria into different types by displaying the characteristic data in the Cartesian coordinate system. For example, the bearing diagnosis model unit 230 may classify the feature data by displaying the characteristic data in the Cartesian coordinate system based on the kurtosis value of the X-axis and the degree of asymmetry of the Y-axis as a classification criterion. As another example, the bearing diagnosis model unit 230 may classify the normal data and the abnormal data of the bearing by displaying them in the same Cartesian coordinate system based on the same classification criteria. In the case of FIG. 7, the bearing normal data (□) and defect-specific data (flaking (○), ball defect (▽), smearing (◇)) can be located in the same rectangular coordinate system according to a plurality of classification criteria.

Again, returning to FIG. 3 , the bearing diagnosis model unit 230 selects the extracted feature data to distinguish between normal and abnormal bearings (step S350 ). In an embodiment, the bearing diagnosis model unit 230 selects the feature data through cluster analysis using a correlation function. As shown in FIG. 8 , the bearing diagnosis model unit 230 clusters each classified individual characteristic data for each normal and defect of the bearing using a correlation function and selects the data based on the distance between the clusters.

8 is an exemplary diagram illustrating clustering of feature data using a data correlation function according to an embodiment.

As illustrated in FIG. 8 , the bearing diagnosis model unit 230 may form a first cluster composed of characteristic data of a normal bearing and a second cluster composed of characteristic data of a damaged bearing by using a correlation function.

The bearing diagnosis model unit 230 may calculate the dissimilarity through the following equation based on the distance between the first cluster and the second cluster, and select feature data that satisfies a specific criterion for the calculated dissimilarity.

[Equation]

Here, r _c1 is the radius of the cluster of normal data, r _c2 is the radius of the cluster of abnormal data, and D _c1,c2 is the distance between the centers of the two clusters.

If the dissimilarity (DSN _F ) calculated through the above equation satisfies the condition greater than "1", the bearing diagnosis model unit 230 is a case in which there is no overlapping feature between the normal data and the abnormal data of the bearing, which satisfies the condition. Select feature data.

The bearing diagnosis model unit 230 generates a bearing diagnosis model by performing machine learning with the selected feature data (step S370). In an embodiment, the bearing diagnosis model unit 230 may generate a bearing diagnosis model by inputting the selected feature data into a support vector machine.

FIG. 4 is a flowchart for explaining a process of generating a tool state diagnosis model of the tool state diagnosis model unit of FIG. 2 .

Referring to FIG. 4 , the tool state diagnosis model unit 250 collects tool vibration data (step S410 ). The tool state diagnosis model unit 250 may collect vibration data of a machining process using a worn tool and a normal tool through an acceleration sensor. As illustrated in FIG. 10 , the collected vibration data shows a size distribution over time in each of the X-axis, Y-axis, and Z-axis directions.

The tool state diagnosis model unit 250 extracts features from the collected vibration data (step S430). The tool state diagnosis model unit 250 may extract features by applying a continuous wavelet transformation technique to vibration data. The tool state diagnosis model unit 250 generates a tool state diagnosis model by inputting the extracted feature data into the neural network (step S440). The tool state diagnosis model unit 250 classifies normal and wear by inputting characteristic data into the input layer of the neural network structure illustrated in FIG. 11 and learning. The tool state diagnosis model unit 250 may display the classified normality and wear as a confusion matrix.

12 is an exemplary diagram illustrating a confusion matrix in which normal and wear of the tool state diagnosis model according to an embodiment are classified.

Referring to FIG. 12 , normal and wear classification rates of tools can be identified in the confusion matrix. For example, the unclassified data failed to classify 556 to 47 items for wear data and failed to classify 537 to 66 items for normal data.

13 is an exemplary view illustrating a simultaneous monitoring screen of a bearing and a tool state according to an embodiment.

Referring to FIG. 13 , the device 130 for simultaneous monitoring of bearing and tool status may simultaneously monitor vibration data measured through an acceleration sensor during machining through a bearing diagnostic model and a tool status diagnostic model, and bearing and tool status can be diagnosed

Although the above has been described with reference to preferred embodiments of the present invention, those skilled in the art can variously modify and change the present invention within the scope without departing from the spirit and scope of the present invention as set forth in the claims below. You will understand that it can be done.

100: Simultaneous monitoring system for bearing and tool condition
110: machine tool
111: bearing 113: tool
130: Device for simultaneous monitoring of bearing and tool condition
210: data measurement unit 230: bearing diagnostic model unit
250: tool state diagnosis model unit 270: monitoring unit
290: control unit
510: acceleration sensor 520: normal bearing
530: defective bearing

Claims (13)

a data measurement unit for measuring vibration data generated when the machine tool is operated;
a bearing diagnosis model unit that extracts characteristics of vibration data generated under normal bearing and damaged bearing conditions and constructs learning data to generate a bearing diagnosis model;
a tool condition diagnosis model unit for generating a tool condition diagnosis model by extracting characteristics of vibration data generated in a machining process using normal and worn tools and constructing learning data; and
A bearing and a tool comprising a monitoring unit for diagnosing the state of the bearing and the tool by simultaneously monitoring the bearing and the tool of the machine tool through the bearing diagnosis model and the tool condition diagnosis model based on the measured vibration data Device for simultaneous status monitoring.
The method of claim 1, wherein the data measuring unit
A device for simultaneous monitoring of bearing and tool status, characterized in that an acceleration sensor is attached to the spindle of the machine tool and vibration according to operation of the spindle is measured through the acceleration sensor.
According to claim 1, wherein the bearing diagnostic model unit
A device for simultaneous monitoring of bearing and tool condition, characterized by extracting characteristic data about the natural frequency of bearing defects compared to normal data by separating frequency components from vibration data generated in normal bearings and broken bearings through empirical mode decomposition.
The method of claim 3, wherein the bearing diagnosis model unit
A device for simultaneous monitoring of bearing and tool status, characterized in that the feature data extracted through the correlation function is selected and the selected feature data is input to generate a bearing diagnostic model that distinguishes between normal and abnormal bearings through machine learning.
5. The method of claim 4, wherein the bearing diagnosis model unit
The extracted characteristic data is clustered through a correlation function to form a first cluster consisting of characteristic data of a normal bearing and a second cluster consisting of characteristic data for each defect of a broken bearing, and the degree of dissimilarity between the first cluster and the second cluster Device for simultaneous monitoring of bearing and tool conditions, characterized in that the selection of the characteristic data based on the.
The method of claim 5, wherein the bearing diagnosis model unit
Device for simultaneous monitoring of bearing and tool conditions, characterized in that the dissimilarity is calculated according to the following [Equation].
[Equation]

Here, r _c1 is the radius of the cluster of normal data, r _c2 is the radius of the cluster of abnormal data, and D _c1,c2 is the distance between the centers of the two clusters.
5. The method of claim 4, wherein the bearing diagnosis model unit
A device for simultaneous monitoring of bearing and tool status, characterized in that the selected feature data is input to a support vector machine to generate a bearing diagnostic model.
According to claim 1, wherein the tool state diagnosis model unit
It collects vibration data of the machining process using a worn tool and a normal tool through the acceleration sensor, extracts features from the collected vibration data, and uses the extracted feature data as input to learn a neural network to classify normal and wear to create a tool condition diagnosis model A device for simultaneous monitoring of bearing and tool conditions, characterized in that.
The method of claim 8, wherein the tool state diagnosis model unit
Device for simultaneous monitoring of bearing and tool condition, characterized in that the classified normal and wear are displayed in a confusion matrix to check the normal and wear classification rate of the tool.
generating a bearing diagnosis model by extracting features based on vibrations generated under normal bearing and damaged bearing conditions and composing learning data;
generating a tool state diagnosis model by extracting features based on vibrations generated in a machining process using normal and abrasive tools and configuring learning data;
Measuring vibration data generated when the machine tool is operated; and
A bearing and a tool comprising the step of diagnosing the state of the bearing and the tool by simultaneously monitoring the bearing and the tool of the machine tool through the bearing diagnosis model and the tool state diagnosis model based on the measured vibration data A method for simultaneous status monitoring.
The method of claim 10, wherein the generating of the bearing diagnostic model comprises:
collecting vibration data generated under normal bearing and broken bearing conditions;
Separating the frequency component from the collected vibration data to extract the characteristic data for the natural frequency of the bearing defect compared to the normal data;
selecting the extracted feature data for identifying the abnormality of the bearing through a correlation function; and
A method for simultaneous monitoring of bearing and tool status, comprising the step of generating a bearing diagnostic model by performing machine learning with the selected feature data.
12. The method of claim 11, wherein the generating of the bearing diagnostic model comprises:
In the feature data selection process, the dissimilarity between the first cluster composed of the characteristic data of the normal bearing and the second cluster composed of the characteristic data for each defect of the damaged bearing is calculated through the following equation, and the calculated dissimilarity satisfies a specific criterion. Method for simultaneous monitoring of bearing and tool condition, characterized in that the data is screened.
[Equation]

Here, r _c1 is the radius of the cluster of normal data, r _c2 is the radius of the cluster of abnormal data, and D _c1,c2 is the distance between the centers of the two clusters.
The method of claim 10, wherein the generating of the tool state diagnosis model comprises:
collecting vibration data of a machining process using a worn tool and a normal tool;
extracting features from the collected vibration data; and
Method for simultaneous monitoring of bearing and tool condition comprising the step of generating a tool condition diagnosis model by classifying normal and wear by learning a neural network as an input of the extracted feature data.

Images