KR20220157168A - System for artificial intelligence-based cutting tool wear management and method thereof - Google Patents

Abstract

The present invention relates to a system for managing wear of a cutting tool based on artificial intelligence and a method thereof. More specifically, the system comprises: a cutting machine equipped with a cutting tool to perform cutting; a sensor module installed in the cutting machine to measure the moving value, the spindle torque value, and the like of the cutting tool; a terminal module connected to the sensor module and provided to perform input and output of measured data; an embedded computer for receiving the measured data from the sensor module and determining whether the cutting tool is worn by predicting machining defects resulting from the service life of the cutting tool through an artificial intelligence analysis algorithm; and an alarm module for generating an alarm when the embedded computer determines that the cutting tool is worn. Therefore, the system can prevent damage to machine tools and prevent the occurrence of mass defects.

Description

Artificial intelligence-based cutting tool wear management system and method {System for artificial intelligence-based cutting tool wear management and method thereof}

The present invention relates to an artificial intelligence-based cutting tool wear management system and method thereof, and more particularly, artificial intelligence capable of accurately identifying the progress of wear and monitoring the state of cutting tools to prevent damage so that cutting tools can be replaced at the right time Based cutting tool wear management system and method.

Cutting is a method of cutting and processing materials, and this cutting process inevitably uses a cutting tool.

In the production system using machine tools, cutting tools inevitably wear and break tools due to friction on the contact surface of processing parts, which leads to inaccuracy, lowered reliability, waste of time due to cutting tool replacement, and requiring the machine to stop. Problems such as frequent replacement of

In the production system, most of the cutting tools depend on a uniform replacement according to a visual inspection method and use time for replacement, and automation is required.

The wear and tear of cutting tools resulting from the limitations of these traditional visual inspection methods can cause serious problems in work safety and loss of processing time as well as deterioration in performance and product quality. A monitoring system is needed to accurately grasp the progress of wear and prevent damage.

Republic of Korea Patent No. 10-0979032 (2010.08.24.)

The purpose of the present invention is

Artificial intelligence-based cutting tool wear management system to prevent immediate damage to machine tools and mass defects in the event of an abnormality of cutting tools by collecting real-time data on the use of cutting tools and using them to analyze the state of wear of cutting tools, and to provide that way.

The objects of the present invention are not limited to the above-mentioned objects, and other objects not mentioned will be clearly understood by those skilled in the art from the following description.

In order to achieve the above object, the artificial intelligence-based cutting tool wear management system according to the present invention is a cutting machine equipped with a cutting tool to perform cutting, a value installed in the cutting machine and moving the cutting tool, and a spindle torque A sensor module that measures values, etc., a terminal module connected to the sensor module and provided to perform input and output of the measured data, and receiving the measured data from the sensor module and using an artificial intelligence analysis algorithm to determine the lifespan of the cutting tool. It includes an embedded computer that determines whether the cutting tool is worn by predicting machining defects, and an alarm module that generates an alarm when the embedded computer determines that the cutting tool is in a worn state.

In addition, the embedded computer includes a data collection unit that collects measurement data including a cutting tool movement value and a spindle torque value from the sensor module, and processes the measurement data into meaningful values for application to the artificial intelligence analysis algorithm. A data pre-processing unit that receives the processed data from the data pre-processing unit and a data learning unit that learns a prediction model to predict machining defects according to the life of the cutting tool, and AI analysis after completion of learning in the data learning unit It is characterized in that it includes a data analysis unit that determines whether the cutting tool is normal or worn through an algorithm.

In addition, the embedded computer may include a monitoring unit that visually provides measurement data collected from the sensor module through signal processing so that a user can check work progress information in real time.

In addition, the artificial intelligence analysis algorithm is characterized in that it is an XGBoost (eXtreme Gradient Boosting, XGB) algorithm that creates a strong prediction model by putting weights on learning errors of weak prediction models and sequentially reflecting them in the next prediction model.

On the other hand, the artificial intelligence-based cutting tool wear management method according to another aspect of the present invention is an artificial intelligence-based cutting tool wear management method performed by a computer, the value of moving the cutting tool from the sensor module in the data collection unit, the spindle torque value Collecting measurement data including, etc., processing the data into meaningful values for applying the measured data collected by the data pre-processing unit to the artificial intelligence analysis algorithm, and processing data from the data pre-processing unit in the data learning unit. Learning a predictive model to predict machining defects according to the life of the cutting tool by receiving input, and after completing learning in the data learning unit in the data analysis unit, determining whether the cutting tool is normal or worn through an artificial intelligence analysis algorithm and generating, by an alarm module, a warning alarm when it is determined that the cutting tool is worn in the step of determining wear.

In addition, the step of processing the data includes receiving raw data measured in real time from a sensor module, and processing the raw data first to reduce meaningless values, omissions, and errors based on the raw data; Classifying the data values that have been primarily processed through the primary processing step, identifying characteristics and performing secondary processing in order to learn them in a predictive model.

In addition, the artificial intelligence analysis algorithm is characterized in that it is an XGBoost (eXtreme Gradient Boosting, XGB) algorithm that creates a strong prediction model by putting weights on learning errors of weak prediction models and sequentially reflecting them in the next prediction model.

Artificial intelligence-based cutting tool wear management system and method according to the present invention, when an abnormality occurs in a cutting tool, enables a manager or operator to check through an immediate alarm, induces quick action on the occurrence of an abnormality, and thereby prevents damage to the machine tool And mass defects can be prevented.

In addition, by providing accurate conditions for cutting tool wear, there is an effect of reducing costs due to the use of optimal tool life, improving productivity of companies, and securing corporate competitiveness in terms of quality.

1 is a block diagram showing an artificial intelligence-based cutting tool wear management system according to the present invention.
2 is a block diagram showing an embedded computer constituting an artificial intelligence-based cutting tool wear management system according to the present invention.
3 is a flowchart showing the overall flow of the artificial intelligence-based cutting tool wear management method according to the present invention.
4 is an exemplary diagram for explaining signal characteristics for each type for determining the wear state of a cutting tool according to the artificial intelligence-based cutting tool wear management method according to the present invention.

Advantages and features of the present invention, and methods of achieving them, will become clear with reference to the detailed description of the following embodiments taken in conjunction with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below, but will be implemented in various different forms, only these embodiments make the disclosure of the present invention complete, and common knowledge in the art to which the present invention belongs. It is provided to fully inform the holder of the scope of the invention, and the present invention is only defined by the scope of the claims.

With reference to the accompanying drawings below, specific details for the practice of the present invention will be described in detail. Like reference numbers refer to like elements, regardless of drawing, and "and/or" includes each and every combination of one or more of the recited items.

Terminology used in this specification is for describing the embodiments, and is not intended to limit the present invention. In this specification, singular forms also include plural forms unless specifically stated otherwise in a phrase. As used herein, "comprises" and/or "comprising" does not exclude the presence or addition of one or more other elements other than the recited elements.

Unless otherwise defined, all terms (including technical and scientific terms) used in this specification may be used in a meaning commonly understood by those of ordinary skill in the art to which the present invention belongs. In addition, terms defined in commonly used dictionaries are not interpreted ideally or excessively unless explicitly specifically defined.

Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings.

1 is a block diagram showing an artificial intelligence-based cutting tool wear management system according to the present invention.

Referring to FIG. 1, the artificial intelligence-based cutting tool wear management system largely includes a cutting machine 100, a sensor module 200, a terminal module 300, an embedded computer 400, and an alarm module 500. .

First, the cutting machine 100 means a machine tool that performs cutting using a cutting tool, and may generally mean a CNC (Computerized Numerical Control) lathe or a machining center (Machining Center, MCT), which is limited thereto. It is not.

Next, the sensor module 200 is a sensor that measures the actual moving value of the cutting tool compared to the set value provided by the cutting machine 100, the current and voltage data of the cutting machine 100, the torque value of the spindle, and the like. It may consist of, but is not limited thereto. Here, it goes without saying that each sensor may be installed at a separate location in the cutting machine 100 to measure each data or value.

Next, the terminal module 300 is a device connected to the sensor module 200 to transmit measured data or to receive an output, and is provided to perform input/output of measured data.

As shown in FIG. 1, the terminal module 300 may include a terminal unit 300a for outputting data and a master unit 300b for receiving outputted data, and the terminal unit 300a Of course, one or more may be provided depending on the position where each sensor is provided.

Next, the embedded computer 400 means a computer that receives the data measured from the sensor module 200 and determines whether the cutting tool is worn by predicting machining defects according to the life of the cutting tool through an artificial intelligence analysis algorithm. .

Here, the embedded computer 400 may refer to an industrial embedded computer having a built-in microprocessor capable of implementing computer functions, and is not limited thereto, and a general personal computer (PC) may be substituted. Of course.

2 is a block diagram showing an embedded computer constituting an artificial intelligence-based cutting tool wear management system according to the present invention.

Referring to FIG. 2, to describe the embedded computer 400 in more detail, the embedded computer 400 includes a data collection unit 410, a data pre-processing unit 420, a data learning unit 430 and data The analysis unit 440 may be included.

First, the data collection unit 410 serves to collect the measurement data including a moving value of a cutting tool and a spindle torque value from the sensor module 200 .

Preferably, the data collection unit 410 receives measurement data output from the terminal unit 300a through the master unit 300b provided on the side of the embedded computer 400 and collects the data.

Next, the data pre-processing unit 420 serves to process the data into meaningful values for application to the artificial intelligence analysis algorithm. Meaningful values here mean that measured values generated in actual processes may have errors, noise values, abnormal data, etc., and these data can be interpreted as meaningless values, and values excluding these values It can be interpreted as a meaningful value.

Such meaningless, omissions, or errors occur to reduce the quality (or accuracy) of data. In data analysis, performing preprocessing with the meaningful values to improve the quality is one of the most important steps in data analysis. can mean

In addition, the data pre-processing unit 420 may be configured to undergo first and second pre-processing of measurement data collected from the sensor module 200, that is, raw data.

The first preprocessing process may refer to a process of identifying an index of raw data and improving a quality index of low-quality data that deteriorates quality due to the collected raw data.

The second pre-processing process may refer to a process of converting the first processed data processed through the first pre-processing process into data for learning in a predictive model to be described later, and attribute values necessary for learning to the predictive model. It may refer to a process of filtering, discarding unnecessary data, and leaving only data for actual use.

Next, the data learning unit 430 receives the processed data from the data pre-processing unit 420 and serves to learn a prediction model to predict machining defects according to the lifespan of the cutting tool.

Next, the data analysis unit 440 serves to determine whether the cutting tool is normal or worn through an artificial intelligence analysis algorithm after the learning is completed in the data learning unit 430.

The artificial intelligence analysis algorithm classifies and defines the signal patterns for the moving values (eg, X, Y, Z axes) and spindle torque values of the cutting tools collected from the sensor module 200 by type to determine the degree of wear of the cutting tools. , It means an algorithm that compares the current signal and the normal signal to diagnose the wear condition and analyzes the wear degree of the cutting tool. This may be understood as determining the wear condition when the wear value of the current cutting tool is equal to or higher than a preset reference value.

Here, the artificial intelligence analysis algorithm may refer to an XGBoost (eXtreme Gradient Boosting, XGB) algorithm that weights learning errors of weak prediction models and sequentially reflects them to the next prediction model to create a strong prediction model. Of course, the prediction model described in the data learning unit 430 may also correspond to this.

The XGBoost algorithm may have excellent predictive performance in classification and regression domains, overfitting regulation, and the effect of reducing the number of divisions by pruning divisions without positive gains in determining the degree of wear of cutting tools.

In addition, cross-validation is performed internally at each iteration so that it has an optimized number of iterations, and if the evaluation value of the evaluation dataset is optimized through the cross-validation instead of the specified number of iterations, the iteration can be stopped in the middle, thereby shortening the process. There are advantages to reducing it.

Meanwhile, the embedded computer 400 may further include a monitoring unit 450 that visually provides measurement data collected from the sensor module through signal processing so that the user can check work progress information in real time. .

The monitoring unit 450 may be formed in the form of a generally configured touch display, and a detailed description thereof will be omitted.

Next, the alarm module 500 generates an alarm when it is determined that the cutting tool is worn in the embedded computer 400, which may mean an industrial warning light.

The alarm module 500 is connected to the embedded computer 400 to set the entire warning range for complete wear of cutting tools so as to effectively prepare for work stoppage. The alarm module 500 warns or alarms Through this, there is an effect that the manager or operator can promptly induce a response to the wear of the cutting tool.

Hereinafter, an artificial intelligence-based cutting tool wear management method using the artificial intelligence-based cutting tool wear management system according to the present invention will be described.

3 is a flowchart showing the overall flow of the artificial intelligence-based cutting tool wear management method according to the present invention.

Referring to FIG. 3, to describe the artificial intelligence-based cutting tool wear management method according to the present invention, in the artificial intelligence-based cutting tool wear management method performed by a computer (or embedded computer), first, a data collection unit ( In step 410, measurement data including a cutting tool movement value, a spindle torque value, and the like is collected from the sensor module 200 (S110).

Next, a step of processing the data into meaningful values for applying the measurement data collected by the data pre-processing unit 420 to the artificial intelligence analysis algorithm is performed (S120).

The processing of the data (S120) includes receiving raw data measured in real time from the sensor module 200, and primary processing of the raw data to reduce meaningless values, omissions, and errors based on the raw data. It may be configured to perform a step of performing secondary processing by identifying characteristics in order to classify the data values that have been primarily processed through the step of performing the primary processing and to learn them in a predictive model.

In the first processing step, an index of the raw data is identified, and a process of improving the quality index of low-quality data that deteriorates the quality due to the collected raw data is performed.

Thereafter, the secondary processing step is a step of converting the data processed through the primary processing step into data for learning in a predictive model to be described later based on the primary processed data, filtering attribute values required for learning in the predictive model, A process of discarding unnecessary data and leaving only data for actual use is performed.

Next, the data learning unit 430 receives the processed data from the data pre-processing unit 420 and learns a prediction model to predict machining defects according to the lifespan of the cutting tool (S130).

Next, the data analysis unit performs a step of determining whether the cutting tool is normal or worn through an artificial intelligence analysis algorithm after learning is completed in the data learning unit (S140).

To explain this as an example, the artificial intelligence analysis algorithm is a signal pattern for the moving values (eg, X, Y, Z axes) and spindle torque values of the cutting tool collected from the sensor module 200 to determine the degree of wear of the cutting tool. It is possible to analyze the degree of wear of cutting tools by categorizing and defining by type, comparing the current signal and normal signal to diagnose the state of wear.

4 is an exemplary diagram for explaining signal characteristics for each type for determining the wear state of a cutting tool according to the artificial intelligence-based cutting tool wear management method according to the present invention.

To further explain with reference to FIG. 4, (a) of FIG. 4 shows a signal pattern indicating an initial setting state, and wear limit lines (red lines) 1 and 2 mean wear limit lines. In addition, the breakage limit lines (green lines) 4 and 5 are limit lines specifying the normal range of the cutting tool, and if the cutting tool is normal, a signal is located between the wear limit line and the breakage limit line.

(b) of FIG. 4 shows a signal pattern for the wear state of the cutting tool, and when the wear limit line is reached, it is determined that the wear state is reached. That is, when the wear value of the current cutting tool is equal to or higher than a preset reference value, it can be understood that the wear state is determined.

Figure 4 (c) shows the signal pattern for the broken state of the cutting tool, which may mean an abnormal pattern signal, and if it does not reach (exceed) the range of the normal breakage limit line, it can be judged as the broken state of the cutting tool. .

In this way, the artificial intelligence analysis algorithm for determining the wear state of the cutting tool is an XGBoost (eXtreme Gradient Boosting, XGB) algorithm that creates a strong prediction model by weighting the learning errors of weak prediction models and sequentially reflecting them in the next prediction model. may be used, and refer to the XGBoost (eXtreme Gradient Boosting, XGB) algorithm described above through the artificial intelligence-based cutting tool wear management system according to the present invention, and a detailed description thereof will be omitted.

When it is determined that the cutting tool is worn in the step of determining whether or not to be worn, the alarm module 500 generates an alarm (S150).

The alarm module 500 may generate a work stop alarm and a warning alarm, and the step of generating the alarm (S150) sets a warning range before the work stop alarm to efficiently prepare for work stop. It can be configured to generate. Here, the work stop alarm refers to an alarm for a situation in which equipment (work) must be stopped, and the warning alarm warns of a point in time when machining precision is reduced due to wear, and a manager (operator) sends a warning alarm. It can induce a quick response to the wear of the cutting tool.

Meanwhile, in the step of determining whether the cutting tool is normal or worn (S140), when the result of the determination is that the cutting tool is normal, the step of collecting the measurement data (S110) is repeated.

Therefore, the artificial intelligence-based cutting tool wear management system and method according to the present invention is made to monitor the wear progress (normal, replacement required) of the cutting tool in real time so that the cutting tool can be replaced at the right time, so that the work It has the effect of preventing serious problems in performance and product quality deterioration as well as loss of safety and processing time.

Although the embodiments of the present invention have been described with reference to the above and accompanying drawings, those skilled in the art to which the present invention pertains can implement the present invention in other specific forms without changing the technical spirit or essential features. You will understand that there is Therefore, it should be understood that the embodiments described above are illustrative in all respects and not restrictive.

100: cutting machine
200: sensor module
300: terminal module
400: embedded computer
410: data collection unit
420: data pre-processing unit
430: data learning unit
440: data analysis unit
450: monitoring unit
500: alarm module

Claims (7)

A cutting machine equipped with a cutting tool to perform cutting;
a sensor module installed in the cutting machine to measure a moving value of the cutting tool, a spindle torque value, and the like;
a terminal module connected to the sensor module and provided to perform input/output of measured data;
An embedded computer that receives the data measured from the sensor module and determines whether or not the cutting tool is worn by predicting machining defects according to the life of the cutting tool through an artificial intelligence analysis algorithm; and
An artificial intelligence-based cutting tool wear management system comprising an alarm module for generating an alarm when the embedded computer determines that the cutting tool is in a worn state. According to claim 1,
The embedded computer,
A data collection unit for collecting measurement data including a moving value of the cutting tool and a spindle torque value from the sensor module;
A data pre-processor for processing the measurement data into meaningful values for application to the artificial intelligence analysis algorithm;
A data learning unit that receives the processed data from the data pre-processing unit and learns a prediction model to predict machining defects according to the life of the cutting tool;
Artificial intelligence-based cutting tool wear management system, characterized in that it comprises a data analysis unit for determining whether the cutting tool is normal or worn through an artificial intelligence analysis algorithm after completion of learning in the data learning unit. According to claim 1,
The embedded computer,
Artificial intelligence-based cutting tool wear management system comprising a monitoring unit that visually provides the measurement data collected from the sensor module through signal processing so that the user can check work progress information in real time. According to claim 1,
The artificial intelligence analysis algorithm,
An artificial intelligence-based cutting tool wear management system characterized by an XGBoost (eXtreme Gradient Boosting, XGB) algorithm that weights the learning errors of weak prediction models and sequentially reflects them to the next prediction model to create a strong prediction model. In the artificial intelligence-based cutting tool wear management method performed by a computer,
Collecting measurement data including a cutting tool movement value, a spindle torque value, and the like from a sensor module in a data collection unit;
Processing the data into meaningful values for applying the measurement data collected by the data pre-processing unit to the artificial intelligence analysis algorithm;
learning a predictive model in order to predict machining defects according to the lifespan of a cutting tool by receiving processed data from the data pre-processing unit in a data learning unit;
After completing learning in the data learning unit in the data analysis unit, determining whether the cutting tool is normal or worn through an artificial intelligence analysis algorithm; and
An artificial intelligence-based cutting tool wear management method comprising: generating a warning alarm by an alarm module when it is determined that the wear of the cutting tool is determined in the step of determining whether the wear is present. According to claim 5,
Processing the data is
Receiving raw data measured in real time from the sensor module;
Primary processing of raw data to reduce meaningless values, omissions, and errors based on the raw data;
Artificial intelligence-based cutting tool wear management method comprising the step of classifying the primary processed data values through the primary processing step to identify characteristics and secondary processing to learn in a predictive model. . According to claim 5,
The artificial intelligence analysis algorithm,
An artificial intelligence-based cutting tool wear management method characterized in that it is an XGBoost (eXtreme Gradient Boosting, XGB) algorithm that weights the learning errors of weak prediction models and sequentially reflects them to the next prediction model to create a strong prediction model.

Images