Intelligent tool changing decision control method and system

Abstract

The present invention relates to the field of data processing technology, and in particular to an intelligent tool change decision control method and system. The method comprises the steps of: collecting vibration data and temperature data, obtaining the degree of tool wear at each sampling moment according to the values ​​of temperature data and vibration data around each sampling moment; obtaining the correlation value of temperature data and vibration data at each sampling moment, obtaining a correlation sequence based on the correlation value, and obtaining the noise influence degree of tool wear at each sampling moment according to the correlation sequence; according to the noise influence degree of tool wear at each sampling moment, adaptively obtaining the abnormal threshold of tool wear at each sampling moment, and making abnormal judgment on tool wear at each sampling moment according to the abnormal threshold of tool wear at each sampling moment, so as to realize intelligent tool change decision control. The present invention improves the accuracy of intelligent tool change decision control.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to an intelligent tool changing decision control method and system. Background Art

[0002] In modern manufacturing, CNC machine tools are widely used in the processing of various materials, and tool changing is an indispensable part of the processing process. During the use of CNC machine tools, the tools may be damaged or worn. Therefore, it is necessary to replace the tools that are damaged or worn to a greater extent. In the prior art, the tools can be manually detected to remind the staff to replace them; or the damage and wear of the tools can be detected in real time in an intelligent way to remind the staff to replace them.

[0003] The degree of tool wear can be identified by machine vision. In addition, because tools with different degrees of wear exhibit different temperatures and amplitudes during work, the degree of tool wear can also be indirectly obtained by detecting the temperature and amplitude of the tool. Finally, the timing of tool replacement can be determined by detecting the degree of tool wear.

[0004] The patent application document with the current publication number CN116820040A discloses a method for online monitoring of product quality production to obtain a data set of six quality factors for each process, collect information in production, and distinguish this data set by the work order dimension; extract samples from the data set according to time series and production characteristics and calculate the confidence interval, use the confidence interval to set it as the control line of the control chart, and set the qualified line in the process as the alarm line of the control chart. The qualified line in the process refers to the upper and lower limits of the qualified lines of the manufacturing process parameters and environmental parameters of each process; select the model data set according to the time series, use XGBoost to build a prediction model, and perform ROC evaluation on the model; if an early warning is triggered, use the RRCF algorithm to detect abnormal variables, and perform abnormal extraction according to the set abnormal threshold.

[0005] Generally speaking, the Robust Random Cut Forest (RRCF) algorithm can be applied to the detection of tool temperature data and vibration data. The algorithm dynamically maintains the distribution of random segmentation trees on the data stream, and judges the degree of abnormality based on the impact of the insertion or deletion of new sample points on the complexity of the segmentation tree. For example, when an abnormal situation is detected, it is determined that there is a large change in the degree of wear of the tool. However, the RRCF algorithm often uses a fixed abnormal threshold method for abnormality detection. In actual working scenarios, due to the operating environment of CNC machine tools, there is noise in the collected temperature data and vibration data, and the degree of tool wear obtained using temperature data and vibration data is also affected by noise. Therefore, when using a fixed abnormal threshold method for abnormal detection of tool wear, normal data may be judged as abnormal, which leads to unnecessary tool changes in intelligent tool change decisions, resulting in a waste of production resources. Summary of the invention

[0006] In order to solve the technical problem that the RRCF algorithm may judge normal data as abnormal when using a fixed abnormal threshold to detect the abnormality of tool wear degree, thereby causing unnecessary tool changes in intelligent tool change decisions, the present invention provides an intelligent tool change decision control method and system.

[0007] In a first aspect, the present invention provides an intelligent tool change decision control method, which adopts the following technical solution:

[0008] An intelligent tool changing decision control method comprises the following steps:

[0009] Collect vibration data and temperature data during tool operation;

[0010] Calculating the noise impact of tool wear , where i is the serial number, indicating the sampling time, represents the noise influence degree of tool wear at sampling time i; Represents the correlation value between temperature data and vibration data at sampling time i; Representative The variance of multiple consecutive correlation values ​​centered at ; Represents the preset hyperparameter; exp() represents the exponential function with a natural constant as the base;

[0011] The abnormal threshold of tool wear degree is obtained, and the abnormal threshold is positively correlated with the noise influence degree of tool wear; the tool wear degree is judged abnormally according to the abnormal threshold of tool wear degree, so as to realize intelligent tool change decision control.

[0012] The innovation of the present invention lies in obtaining the noise influence degree of tool wear at each sampling moment according to the correlation between vibration data and temperature data, and making abnormal judgment on the tool wear degree at each sampling moment based on the abnormal threshold of the tool wear degree adaptively based on the noise influence degree, thereby reducing false alarms (misjudging normal data as abnormal data) and missed alarms (failing to detect real abnormalities), improving the accuracy of abnormality detection, reducing the waste of production resources caused by unnecessary tool changes in intelligent tool changing decisions, and improving the efficiency of intelligent tool changing decision control.

[0013] Preferably, the calculation process of the tool wear degree includes:

[0014] ;

[0015] In the formula, represents the tool wear degree at sampling time i; Represents the number of temperature data around sampling time i; Represents the value of the jth temperature data around sampling time i; Represents the number of vibration data around sampling time i; represents the value of the jth vibration data around sampling time i; tanh() represents the normalization function.

[0016] The degree of tool wear at each sampling moment is obtained based on the values ​​of the temperature data and vibration data around each sampling moment, which can accurately reflect the degree of tool wear at each sampling moment.

[0017] Preferably, obtaining the correlation value between the temperature and the amplitude includes:

[0018] ;

[0019] In the formula, Represents the correlation value between temperature data and vibration data at sampling time i; Represents the Pearson correlation coefficient between the temperature data around sampling time i and the vibration data around sampling time i.

[0020] The larger the correlation value is, the less the temperature data and vibration data at sampling time i are affected by noise, which facilitates the subsequent acquisition of the noise influence degree of tool wear at each sampling time according to the correlation value.

[0021] Preferably, the The acquisition of multiple continuous correlation values ​​centered on , including:

[0022] The correlation values ​​of the temperature data and the vibration data at each sampling moment are sorted in ascending order of the sampling moments to obtain a correlation sequence;

[0023] The number of correlation values ​​W is preset, and the first W correlation values ​​and the last W correlation values ​​of the correlation values ​​between the temperature data and the vibration data at the sampling time i in the correlation sequence are recorded as centered on a continuous set of multiple correlation values, Represents the correlation value between temperature data and vibration data at sampling time i.

[0024] Preferably, the step of obtaining the abnormal threshold value of tool wear degree includes:

[0025] ;

[0026] In the formula, represents the abnormal threshold of tool wear degree at sampling time i; represents the noise influence degree of tool wear at sampling time i; A fixed anomaly threshold representing the degree of tool wear at all sampling moments.

[0027] The abnormal threshold of tool wear degree at each sampling moment is adaptively obtained, making subsequent abnormality detection more accurate.

[0028] Preferably, the abnormality judgment of the tool wear degree is performed according to the abnormal threshold value of the tool wear degree to realize intelligent tool change decision control, including:

[0029] If the tool wear degree at any sampling moment is greater than the abnormal threshold of the tool wear degree at that sampling moment, the system automatically changes the tool.

[0030] Preferably, the collecting of the amplitude and temperature of the tool during operation includes:

[0031] The vibration sensor and temperature sensor are installed on the tool. The sampling time is every two seconds, and the amplitude and temperature of the tool during operation are collected each time.

[0032] Reduce the waste of production resources caused by unnecessary tool changes in intelligent tool change decisions, and improve the efficiency of intelligent tool change decision control.

[0033] In a second aspect, the present invention provides an intelligent tool change decision control system, which adopts the following technical solution:

[0034] An intelligent tool-changing decision control system comprises: a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the above-mentioned intelligent tool-changing decision control method is implemented.

[0035] By adopting the above technical solution, the above-mentioned intelligent tool changing decision control method is generated into a computer program and stored in a memory so as to be loaded and executed by a processor, thereby making a terminal device based on the memory and the processor for easy use.

[0036] The present invention has the following technical effects: the innovation of the present invention lies in obtaining the degree of noise influence of tool wear at each sampling moment based on the correlation between vibration data and temperature data, and making abnormal judgment on the degree of tool wear at each sampling moment based on the abnormal threshold of the degree of noise influence adaptively, thereby improving the accuracy of abnormal detection, reducing the waste of production resources caused by unnecessary tool changes in intelligent tool changing decisions, and improving the efficiency of intelligent tool changing decision control. Furthermore, the degree of tool wear at each sampling moment is obtained based on the sum of the values ​​of temperature data and vibration data around each sampling moment, which can accurately reflect the degree of tool wear at the current sampling moment. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] By reading the detailed description below with reference to the accompanying drawings, the above and other purposes, features and advantages of the exemplary embodiments of the present invention will become readily understood. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-restrictive manner, and the same or corresponding reference numerals represent the same or corresponding parts.

[0038] Figure 1 It is a method flow chart of an intelligent tool changing decision control method in an embodiment of the present invention. DETAILED DESCRIPTION

[0039] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0040] It should be understood that when the terms "first", "second", etc. are used in the claims, descriptions, and drawings of the present invention, they are only used to distinguish different objects, rather than to describe a specific order. The terms "include" and "comprise" used in the description and claims of the present invention indicate the presence of the described features, wholes, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their collections.

[0041] The embodiment of the present invention discloses an intelligent tool change decision control method, referring to Figure 1 , comprising steps S1 to S3:

[0042] S1: Collect vibration data and temperature data.

[0043] In an embodiment of the present invention, a vibration sensor and a temperature sensor are installed on the tool. A sampling time is set every two seconds. The amplitude and temperature of the tool during operation are collected each time as vibration data and temperature data. The data are collected for a total of five minutes to obtain all temperature data and vibration data.

[0044] S2: Obtain the degree of tool wear at each sampling moment based on the values ​​of the surrounding temperature data and the surrounding vibration data at each sampling moment; obtain the correlation value between the temperature data and the vibration data at each sampling moment, and obtain a correlation sequence based on the correlation value; obtain the degree of noise influence of tool wear at each sampling moment based on the correlation value and the correlation sequence between the temperature data and the vibration data at each sampling moment.

[0045] It should be noted that the RRCF algorithm often uses a fixed abnormality threshold method for anomaly detection. However, due to the operating environment of CNC machine tools, there is noise in the collected temperature data and vibration data. The fixed abnormality threshold method is easily affected by noise, which increases the false alarm rate and may misjudge normal data as abnormal. This will lead to unnecessary tool changes in intelligent tool change decisions, resulting in a waste of production resources.

[0046] Step S2 includes steps S20 and S21, which are specifically as follows:

[0047] S20: Obtain the tool wear degree at each sampling moment according to the values ​​of the ambient temperature data and the ambient vibration data at each sampling moment.

[0048] It should be noted that when a known tool wears during use, the contact area and friction between the tool and the workpiece will change, which will cause the vibration level and temperature of the tool to increase. Therefore, the degree of tool wear is positively correlated with the vibration level and temperature of the tool. Therefore, in the present invention, it is first necessary to obtain the degree of tool wear based on the collected temperature data and vibration data.

[0049] Get the tool wear degree at sampling time i, where i is the sequence number:

[0050] ;

[0051] In the formula, represents the tool wear degree at sampling time i; Represents the number of temperature data around sampling time i; Represents the value of the jth temperature data around sampling time i; Represents the number of vibration data around sampling time i; represents the value of the jth vibration data around sampling time i; tanh() represents the normalization function.

[0052] As an example, the number of sampling moments N is preset, and the temperature data of the N sampling moments before and after the sampling moment i is used as the temperature data around the sampling moment i; the vibration data of the N sampling moments before and after the sampling moment i is used as the vibration data around the sampling moment i; in this embodiment, the number of sampling moments N=40 is preset, and in other embodiments, the implementer can preset the value of the number of sampling moments N according to the specific implementation situation. It should be noted that if the number of sampling moments before or after the sampling moment i does not meet N, it can be discarded; and and The values ​​of are equal; The larger the value of , the greater the tool wear at sampling time i.

[0053] S21: Obtain the correlation value between the temperature data and the vibration data at each sampling moment, obtain the correlation sequence based on the correlation value, and obtain the noise influence degree of tool wear at each sampling moment according to the correlation value between the temperature data and the vibration data at each sampling moment and the correlation sequence.

[0054] It should be noted that when using the RRCF algorithm to detect the degree of tool wear at each sampling moment, the collected vibration data and temperature data will be affected by noise, so the degree of tool wear at each sampling moment will also be affected by noise. If the tool wear degree at each sampling moment is detected for abnormality based on a fixed abnormal threshold to control whether to change the tool, it may affect the timing of tool change. Therefore, when performing abnormal detection on the tool wear degree at each sampling moment, it is first necessary to obtain the degree of noise influence of tool wear at each sampling moment, and then adaptively obtain the abnormal threshold of the tool wear degree at each sampling moment based on the noise influence degree for abnormal detection.

[0055] It should be further explained that, since the faster the tool vibrates during its operation, more heat will be generated. Therefore, the collected temperature data and vibration data are positively correlated to a certain extent, and the positive correlation between the temperature data and the vibration data is stable within a shorter time range. Therefore, the present invention first needs to obtain the correlation value of the temperature data and the vibration data at each sampling moment based on the correlation between the temperature data around each sampling moment and the surrounding vibration data. Finally, according to the stability of the correlation value of the temperature data and the vibration data at any sampling moment within its local time range, the degree of noise influence of the tool wear at each sampling moment is obtained.

[0056] In this embodiment of the present invention, the correlation value between the temperature data and the vibration data at sampling time i is obtained:

[0057] ;

[0058] In the formula, Represents the correlation value between temperature data and vibration data at sampling time i; represents the Pearson correlation coefficient between the temperature data around sampling time i and the vibration data around sampling time i; The larger the value of , the greater the correlation value between the temperature data and the vibration data at sampling time i.

[0059] The correlation values ​​of the temperature data and the vibration data at each sampling moment are sorted in ascending order of the sampling moments to obtain a correlation sequence;

[0060] The number of correlation values ​​W is preset, and the first W correlation values ​​and the last W correlation values ​​of the correlation values ​​between the temperature data and the vibration data at the sampling time i in the correlation sequence are recorded as centered on a continuous set of multiple correlation values, represents the correlation value between the temperature data and the vibration data at the sampling time i; it should be noted that the preset number of correlation values ​​W=11, in other embodiments, the implementer may preset the value of the number of correlation values ​​W according to the specific implementation situation, and if any correlation value is at the edge position in the correlation sequence, and its front side correlation value or rear side correlation value in the correlation sequence does not satisfy W, it can be discarded;

[0061] In the embodiment of the present invention, the noise influence degree of tool wear at sampling time i is obtained:

[0062] ;

[0063] In the formula, represents the noise influence degree of tool wear at sampling time i; Represents the correlation value between temperature data and vibration data at sampling time i; Representative The variance of multiple consecutive correlation values ​​centered at ; Represents the preset hyperparameters, in order to prevent The value of is 0. In the embodiment of the present invention, B=0.01 is preset. In other embodiments, the implementer may preset the value of B according to the specific implementation situation. The larger it is, the more relevant the temperature data and vibration data are at sampling time i, and the smaller the noise impact of tool wear at sampling time i is. The larger the value of , the greater the fluctuation of the continuous correlation values ​​centered on the correlation value of the temperature data and the vibration data at the sampling time i, which means that the stability of the correlation value of the temperature data and the vibration data at the sampling time i in the local range of the time series is worse, and the influence of noise is greater at this time;

[0064] S3: According to the noise influence degree of tool wear at each sampling moment, the abnormal threshold of tool wear degree at each sampling moment is adaptively obtained, and the abnormality of tool wear degree at each sampling moment is judged according to the abnormal threshold of tool wear degree at each sampling moment to realize intelligent tool change decision control.

[0065] Step S3 includes steps S30 and S31, which are specifically as follows:

[0066] S30: adaptively obtaining an abnormal threshold of the tool wear degree at each sampling moment according to the noise influence degree of the tool wear at each sampling moment.

[0067] It should be noted that the degree of tool wear at each sampling moment is known to be affected by noise. If the degree of tool wear at each sampling moment is detected for abnormality based on a fixed abnormal threshold to control whether to change the tool, it may affect the timing of tool change. Therefore, if the noise impact of tool wear at each sampling moment is greater, the abnormal threshold of the tool wear degree at each sampling moment is increased, so that the subsequent abnormal detection of the tool wear degree at each sampling moment is more accurate.

[0068] In the embodiment of the present invention, a fixed abnormal threshold value R of the tool wear degree at all sampling moments is preset to be 0.6. In other embodiments, the implementer may preset the value of R according to the specific implementation situation.

[0069] Get the abnormal threshold of tool wear at each sampling moment:

[0070] ;

[0071] In the formula, represents the abnormal threshold of tool wear degree at sampling time i; represents the noise influence degree of tool wear at sampling time i; Represents the fixed abnormal threshold of the tool wear degree at all sampling moments; if the noise influence on the tool wear at sampling moment i is greater, then the acquisition of the tool wear degree at this sampling moment is affected by the noise data, and the abnormal threshold of the tool wear degree at this sampling moment should be larger.

[0072] S31: An abnormality judgment is made on the tool wear degree at each sampling moment according to the abnormal threshold of the tool wear degree at each sampling moment, so as to realize intelligent tool change decision control.

[0073] In an embodiment of the present invention, if the degree of tool wear at any sampling moment is greater than the abnormal threshold of the tool wear at the sampling moment, the tool at the sampling moment needs to be replaced, and the system automatically changes the tool to ensure that the tool is always in the best working condition, thereby improving processing accuracy and product quality.

[0074] An embodiment of the present invention further discloses an intelligent tool change decision control system, including a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, an intelligent tool change decision control method according to the present invention is implemented.

[0075] The above system also includes other components well known to those skilled in the art, such as a communication bus and a communication interface, and their configuration and functions are known in the art, so they will not be described in detail here.

[0076] In the present invention, the aforementioned memory may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. For example, a computer-readable storage medium may be any suitable magnetic storage medium or magneto-optical storage medium, such as a resistive random access memory, a dynamic random access memory, a static random access memory, an enhanced dynamic random access memory, a high bandwidth memory, a hybrid storage cube, etc., or any other medium that can be used to store the required information and can be accessed by an application, a module, or both. Any such computer storage medium may be part of the device or accessible or connectable to the device.

[0077] Although this specification has shown and described a number of embodiments of the present invention, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Those skilled in the art will conceive of many modifications, changes and alternatives without departing from the ideas and spirit of the present invention. It should be understood that in the practice of the present invention, various alternatives to the embodiments of the present invention described herein may be employed.

[0078] The above are all preferred embodiments of the present invention, and are not intended to limit the protection scope of the present invention. Therefore, any equivalent changes made based on the structure, shape, and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. An intelligent tool change decision control method, characterized in that: Includes steps: Collect vibration data and temperature data during tool operation; Calculating the noise impact of tool wear , where i is the serial number, indicating the sampling time, represents the noise influence degree of tool wear at sampling time i; Represents the correlation value between temperature data and vibration data at sampling time i; Representative The variance of multiple consecutive correlation values ​​centered at ; Represents the preset hyperparameter; exp() represents the exponential function with the natural constant e as the base; The abnormal threshold of tool wear degree is obtained, and the abnormal threshold is positively correlated with the noise influence degree of tool wear; the tool wear degree is judged abnormally according to the abnormal threshold of tool wear degree, so as to realize intelligent tool change decision control.

2. The intelligent tool change decision control method according to claim 1 is characterized in that: The calculation process of the tool wear degree includes: ； In the formula, represents the tool wear degree at sampling time i; Represents the number of temperature data around sampling time i; Represents the value of the jth temperature data around sampling time i; Represents the number of vibration data around sampling time i; represents the value of the jth vibration data around sampling time i; tanh() represents the normalization function.

3. The intelligent tool changing decision control method according to claim 1 is characterized in that: The acquisition of the correlation value between the temperature and the amplitude includes: ； In the formula, Represents the correlation value between temperature data and vibration data at sampling time i; Represents the Pearson correlation coefficient between the temperature data around sampling time i and the vibration data around sampling time i.

4. The intelligent tool change decision control method according to claim 1 is characterized in that: Said The acquisition of multiple continuous correlation values ​​centered on , including: The correlation values ​​of the temperature data and the vibration data at each sampling moment are sorted in ascending order of the sampling moments to obtain a correlation sequence; The number of correlation values ​​W is preset, and the first W correlation values ​​and the last W correlation values ​​of the correlation values ​​between the temperature data and the vibration data at the sampling time i in the correlation sequence are recorded as centered on a continuous set of multiple correlation values, Represents the correlation value between temperature data and vibration data at sampling time i.

5. The intelligent tool change decision control method according to claim 1 is characterized in that: The abnormal threshold value of tool wear degree is obtained, including: ； In the formula, represents the abnormal threshold of tool wear degree at sampling time i; represents the noise influence degree of tool wear at sampling time i; A fixed anomaly threshold representing the degree of tool wear at all sampling moments.

6. The intelligent tool change decision control method according to claim 1 is characterized in that: The abnormality judgment of the tool wear degree is performed according to the abnormal threshold value of the tool wear degree to realize intelligent tool change decision control, including: If the tool wear degree at any sampling moment is greater than the abnormal threshold of the tool wear degree at that sampling moment, the system automatically changes the tool.

7. The intelligent tool change decision control method according to claim 1 is characterized in that: The collecting of the amplitude and temperature of the tool during operation includes: The vibration sensor and temperature sensor are installed on the tool. The sampling time is every two seconds, and the amplitude and temperature of the tool during operation are collected each time.

8. An intelligent tool change decision control system, characterized in that: include: A processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, an intelligent tool change decision control method according to any one of claims 1 to 7 is implemented.

Images