Temperature monitoring method and system for numerical control machine tool
By performing characteristic analysis of the temperature and speed data of CNC machine tools, redefining the similarity degree and noise possibility of temperature data, the problem of the reduction of accuracy in temperature data detection is solved, and more accurate abnormality detection is achieved, which improves the Safety and reliability of machine tools.
Patent Information
- Application Number
- CN202411595113.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-11-11
- Publication Date
- 2024-12-06
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
The existing DBSCAN algorithm reduces accuracy due to noise interference in the abnormal detection of temperature data of CNC machine tools, and may identify abnormal data as normal data.
By analyzing the change characteristics of the temperature data and speed data of CNC machine tools, redefining the distance measurement method of the temperature data when determining the number of neighborhood data, obtaining the similarity and noise possibility between the temperature data, correcting the similarity, and then Achieve more accurate abnormality detection.
It improves the accuracy of abnormal detection, can detect potential problems in a timely manner, and improves the safety and reliability of the machine tool.
Smart Images

Figure CN119077435A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of data processing, and in particular to a temperature monitoring method and system for a numerically controlled machine tool. Background Art
[0002] As the market's requirements for product quality continue to increase, temperature changes will affect the machining accuracy and product quality of machine tools. Different materials will expand or contract when the temperature changes. This change may cause the relative position of the machine tool parts to change, thereby affecting the machining accuracy. Therefore, temperature monitoring has become an important means to improve product consistency and quality. In this solution, by real-time monitoring of the temperature data on the machine tool, it is easy to detect abnormalities in a timely manner, which can reduce the probability of equipment failure, reduce maintenance costs, and improve production efficiency.
[0003] The patent application document with the publication number CN117633677A discloses a distribution network measurement data anomaly detection method based on a streaming DBSCAN clustering algorithm. Step 1: construct a distribution network measurement data anomaly detection model; Step 2: based on the distribution network measurement data anomaly detection model constructed in step 1, perform anomaly detection on the distribution network measurement data.
[0004] When collecting temperature data of CNC machine tools, electromagnetic interference from other devices or power supplies around the CNC machine tools may cause the temperature sensor output to be unstable, resulting in noise in the temperature data, which may cause abnormal data in the temperature data to fluctuate or be reduced to false normal data. The existing DBSCAN algorithm realizes data anomaly detection based on the number of neighboring data of each data, and the determination of the number of neighboring data of each data is based on the analysis of the numerical value and sampling interval difference between the two data. Therefore, the presence of noise reduces the accuracy of anomaly detection of temperature data using the DBSCAN algorithm, and may identify abnormal data in the temperature data as normal data. Summary of the invention
[0005] In order to solve the technical problem that the existence of noise causes the accuracy of abnormality detection of temperature data using the DBSCAN algorithm to decrease, and abnormal data in the temperature data may be identified as normal data, the present invention provides a temperature monitoring method and system for a CNC machine tool.
[0006] In a first aspect, the present invention provides a temperature monitoring method for a CNC machine tool, which adopts the following technical solution: A temperature monitoring method for a CNC machine tool comprises the steps of: Collect temperature data; obtain the primary similarity between two temperature data; obtain the noise probability of each temperature data; Get the similarity between two temperature data , Represents the primary similarity between two temperature data; represents the noise probability of the first temperature data; represents the noise probability of the second temperature data; Represents the second hyperparameter; norm() represents the normalization function; According to the similarity between the two temperature data, the neighborhood data of each temperature data is obtained to achieve anomaly detection.
[0007] The innovation of the present invention lies in that by analyzing the change characteristics of the temperature data and speed data of the CNC machine tool, the distance measurement method of each temperature data when determining the number of neighborhood data is redefined, which can more comprehensively analyze the similarity between the temperature data, help distinguish abnormal data from normal data, and make the calculation of the similarity more in line with the actual situation, thereby improving the accuracy of anomaly detection, realizing real-time monitoring of the machine tool status, timely discovering potential problems, and improving the safety and reliability of the machine tool.
[0008] Preferably, obtaining the primary similarity between two temperature data includes: Get the numerical performance factor of each temperature data; ; In the formula, Represents the primary similarity between two temperature data; The numerical representation factor representing the first temperature data; A numerical representation factor representing the second temperature data; represents the first hyperparameter; Represents the sampling time interval between the first temperature data and the second temperature data; exp() represents an exponential function with a natural constant as the base.
[0009] The greater the primary similarity between the temperature data, the more similar the two temperature data are.
[0010] Preferably, obtaining the numerical expression factor of each temperature data includes: The surrounding data of each temperature data is obtained; the product of the average of the absolute values of the differences of all adjacent surrounding data of the i-th temperature data and the value of the i-th temperature data is used as the numerical expression factor of the i-th temperature data.
[0011] This facilitates obtaining the primary similarity between the temperature data based on the differences in the numerical expression factors between the temperature data.
[0012] Preferably, the obtaining of the noise probability of each temperature data includes: ; In the formula, Represents the noise possibility of the i-th temperature data; Represents the value of the i-th temperature data; Represents the minimum temperature value in the surrounding data of the i-th temperature data; represents the difference between the maximum temperature and the minimum temperature in the surrounding data of the i-th temperature data; Represents the value of the speed data at the sampling time corresponding to the i-th temperature data; represents the minimum speed value of all speed data in the sampling time period corresponding to the surrounding data of the i-th temperature data; Represents the difference between the maximum speed and the minimum speed in all speed data in the sampling time period corresponding to the surrounding data of the i-th temperature data; norm() represents the normalization function.
[0013] This facilitates the subsequent correction of the initial similarity between the temperature data according to the difference in noise possibilities between the temperature data, so as to obtain the similarity between the two temperature data.
[0014] Preferably, the process of acquiring neighborhood data of each temperature data according to the similarity between the two temperature data, thereby realizing anomaly detection, includes: A neighbor parameter u and a threshold parameter T are preset. For any temperature data in the temperature data sequence, the neighborhood data of the temperature data is obtained, and the neighborhood data of the temperature data is within the neighborhood range of the temperature data, and the similarity between the neighborhood data and the temperature data is greater than the threshold parameter T; the core point in the temperature data sequence is obtained, and the number of neighborhood data of the core point is greater than or equal to the neighbor parameter u; all abnormal data in the temperature data sequence are obtained, and the number of neighborhood data of the abnormal data is less than the neighbor parameter u and does not belong to the neighborhood data of other core points.
[0015] Make the obtained abnormal data more accurate.
[0016] Preferably, the step of obtaining surrounding data of each temperature data includes: The number of surrounding data N is preset, and the first N temperature data and the last N temperature data of the i-th temperature data are used as the surrounding data of the i-th temperature data.
[0017] Preferably, the collecting temperature data includes: A temperature sensor is installed on the CNC machine tool, and a sampling time is preset every two minutes. Temperature data is collected in sequence each time for a total of three hours.
[0018] In a second aspect, the present invention provides a temperature monitoring system for a CNC machine tool, which adopts the following technical solution: A temperature monitoring system for a numerically controlled machine tool 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 temperature monitoring method for a numerically controlled machine tool is implemented.
[0019] By adopting the above technical solution, the above-mentioned temperature monitoring method for CNC machine tools 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.
[0020] The present invention has the following technical effects: The purpose of the present invention is to redefine the distance measurement method for each temperature data when determining the number of neighborhood data by analyzing the change characteristics of the temperature data and speed data of a CNC machine tool, so as to more comprehensively analyze the similarity between the temperature data, help distinguish abnormal data from normal data, and make the calculation of the similarity more in line with the actual situation, thereby improving the accuracy of anomaly detection, realizing real-time monitoring of the machine tool status, timely discovering potential problems, and improving the safety and reliability of the machine tool. BRIEF DESCRIPTION OF THE DRAWINGS
[0021] 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.
[0022] Figure 1 The present invention is a flow chart of a method for temperature monitoring of a numerically controlled machine tool according to an embodiment of the present invention. DETAILED DESCRIPTION
[0023] 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.
[0024] 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.
[0025] The embodiment of the present invention discloses a temperature monitoring method for a CNC machine tool, referring to Figure 1 , comprising steps S1 to S3: S1: Collect temperature data and speed data.
[0026] In an embodiment of the present invention, a temperature sensor and a speed sensor are installed on a CNC machine tool, and a sampling moment is preset every two minutes. Temperature data and speed data are collected in turn each time, and the collection is done for a total of three hours; the temperature data at each sampling moment is used as a temperature data sequence; and the speed data at each sampling moment is used as a speed data sequence.
[0027] S2: Obtain the numerical expression factor of each temperature data, and obtain the primary similarity between two temperature data according to the numerical expression factor of each temperature data; obtain the noise possibility of each temperature data according to the connection between the corresponding temperature data and the speed data at the sampling time.
[0028] It should be noted that when collecting temperature data of a CNC machine tool, electromagnetic interference from other devices or power supplies around the CNC machine tool may cause the temperature sensor output to be unstable, resulting in noise in the temperature data. This may cause abnormal data in the temperature data to fluctuate or be reduced to false normal data. The existing DBSCAN algorithm realizes data anomaly detection based on the number of neighborhood data of each data, and the determination of the number of neighborhood data of each data is based on the analysis of the numerical value and sampling interval difference between the two data. Therefore, the presence of noise leads to a decrease in the accuracy of anomaly detection of temperature data using the DBSCAN algorithm, and abnormal data in the temperature data may be identified as normal data. Therefore, the present invention improves the DBSCAN algorithm and redefines the distance measurement method for each temperature data when determining the number of its neighborhood data during the anomaly detection process, so that abnormal data affected by noise can be detected.
[0029] Step S2 includes steps S20 and S21, which are specifically as follows: S20: Obtain a numerical expression factor of each temperature data, and obtain a primary similarity between two temperature data according to the numerical expression factor of each temperature data.
[0030] It should be noted that when redefining the distance measurement method for each temperature data in determining the number of its neighborhood data, it is necessary to analyze the numerical performance between the temperature data and the sampling time interval between the temperature data to obtain the initial similarity between the temperature data. If the numerical difference between the two temperature data is smaller, the change characteristics of the surrounding data of the two temperature data are closer, and the sampling time interval between the two temperature data is smaller, it means that the primary similarity between the two temperature data is greater.
[0031] In an embodiment of the present invention, the number of surrounding data N is preset, and the first N temperature data and the last N temperature data of the i-th temperature data are used as the surrounding data of the i-th temperature data. In the present embodiment, the preset number of surrounding data N=30. In other embodiments, the implementer can preset the value of the number of surrounding data N according to the specific implementation situation.
[0032] The product of the mean of the absolute values of the differences of all adjacent surrounding data of the i-th temperature data and the value of the i-th temperature data is used as the numerical expression factor of the i-th temperature data; Get the primary similarity between two temperature data: ; In the formula, Represents the primary similarity between two temperature data; The numerical representation factor representing the first temperature data; A numerical representation factor representing the second temperature data; represents the first hyperparameter. In the embodiment of the present invention, the first hyperparameter is preset , in order to avoid the difference between the numerical expression factors of the first temperature data and the second temperature data being 0; Represents the sampling time interval between the first temperature data and the second temperature data; exp() represents an exponential function with a natural constant as the base; The smaller the value is, the closer the two temperature data are in terms of their own numerical performance and the change characteristics of the surrounding data, which means that the primary similarity between the two temperature data is greater; The smaller the value is, the greater the reference value of the two temperature data to each other, and the more consistent the working conditions of the CNC machine tools reflected by the two temperature data are. That is, the closer the two temperature data are in terms of their own numerical performance and the change characteristics of the surrounding data, the greater the credibility, and the greater the primary similarity between the two temperature data.
[0033] S21: Get the noise probability of each temperature data.
[0034] It should be noted that the initial similarity between the two temperature data is obtained, but this index is obtained by analyzing the numerical value and sampling time interval between the temperature data. In this way, it can only be simply judged whether the two temperature data are similar enough from the two levels of numerical value and sampling time interval. However, since noise may cause abnormal data in the temperature data to fluctuate or actively reduce to normal data, the initial similarity between the two temperature data cannot solve the interference of noise well; In addition, in the scenario corresponding to this scheme, there is a positive correlation between the cutting speed and temperature of the CNC machine tool, where the higher the cutting speed, the greater the relative speed between the cutting tool and the workpiece, resulting in increased friction and cutting deformation energy, thereby generating more heat, which will cause the surface temperature of the tool and the workpiece to rise. Therefore, the change characteristics of the speed data and the temperature data at the corresponding moment are combined for analysis to obtain the noise possibility of each temperature data. The stronger the correlation between the changes in the two data at the corresponding moment, the lower the noise possibility of the temperature data at the corresponding moment.
[0035] In this embodiment of the present invention, the noise probability of each temperature data is obtained: ; In the formula, Represents the noise possibility of the i-th temperature data; Represents the value of the i-th temperature data; Represents the minimum temperature value in the surrounding data of the i-th temperature data; represents the difference between the maximum temperature and the minimum temperature in the surrounding data of the i-th temperature data; Represents the value of the speed data at the sampling time corresponding to the i-th temperature data; represents the minimum speed value of all speed data in the sampling time period corresponding to the surrounding data of the i-th temperature data; represents the difference between the maximum speed and the minimum speed in all speed data in the sampling period corresponding to the surrounding data of the i-th temperature data; norm() represents the normalization function; Represents the relative value of the i-th temperature data in its surrounding data; Represents the relative value of the speed data at the sampling time corresponding to the i-th temperature data in its surrounding data; The larger the value is, the worse the connection between the temperature data and the speed data at the sampling time corresponding to the i-th temperature data is. Then the i-th temperature is more likely to be affected by noise, and the noise possibility of the i-th temperature data is greater.
[0036] S3: According to the noise possibility of each temperature data, the initial similarity between the two temperature data is corrected to obtain the similarity between the two temperature data; according to the similarity between the two temperature data, the neighborhood data of each temperature data is obtained to achieve anomaly detection.
[0037] Step S3 includes steps S30 and S31, which are specifically as follows: S30: Correcting the initial similarity between the two temperature data according to the noise possibility of each temperature data to obtain the similarity between the two temperature data.
[0038] It should be noted that, if the difference in noise possibility between the two temperature data is smaller, the similarity between the two temperature data is greater; if the difference in noise possibility between the two temperature data is greater, the similarity between the two temperature data is smaller. Therefore, the initial similarity between the two temperature data is corrected according to the difference in noise possibility between the two temperature data to obtain the similarity between the two temperature data.
[0039] In this embodiment of the present invention, the similarity between two temperature data is obtained: ; In the formula, Represents the similarity between two temperature data; Represents the primary similarity between two temperature data; represents the noise probability of the first temperature data; represents the noise probability of the second temperature data; represents the second hyperparameter. In the embodiment of the present invention, the second hyperparameter is preset , in order to avoid the difference of the noise possibility between the first temperature data and the second temperature data being 0; The larger the value of is, the greater the similarity between the two temperature data is. The smaller the value is, the smaller the difference in the noise possibility between the two temperature data is, which means that the sampling authenticity of the two temperature data is closer, then the reference value between the two temperature data is greater, and the similarity between the two temperature data is greater.
[0040] S31: According to the similarity between the two temperature data, the neighborhood data of each temperature data is obtained to achieve anomaly detection.
[0041] It should be noted that the known existing DBSCAN algorithm realizes data anomaly detection based on the number of neighborhood data of each data, and the determination of the number of neighborhood data of each data is based on the analysis of the numerical values and sampling interval differences between the two data. Therefore, the presence of noise leads to a decrease in the accuracy of anomaly detection of temperature data using the DBSCAN algorithm. Therefore, the present invention analyzes the similarity between the two temperature data when determining the number of neighborhood data of each data, and can detect abnormal data affected by noise. Therefore, the present invention obtains the neighborhood data of each temperature data according to the similarity between the temperatures, thereby realizing anomaly detection.
[0042] In the embodiment of the present invention, a neighbor parameter is preset. , a neighborhood parameter and a threshold parameter , for the i-th temperature data, replace the The sequence of temperature data is recorded as the neighborhood range of the i-th temperature data; for any temperature data in the neighborhood range of the i-th temperature data, if the similarity between the temperature data and the i-th temperature data is greater than the threshold parameter , record the temperature data as the neighborhood data of the i-th temperature data; if the number of neighborhood data of the i-th temperature data is greater than or equal to the neighbor parameter , record the i-th temperature data as the core point; if the number of neighboring data of the i-th temperature data is less than the neighbor parameter , but when the i-th temperature data belongs to the neighborhood data of other core points, the i-th temperature data is recorded as a boundary point; if the number of neighborhood data of the i-th temperature data is less than the neighbor parameter , and the i-th temperature data does not belong to the neighborhood data of other core points, the i-th temperature data point is recorded as abnormal data; Through the above method, all core points and boundary points in the temperature data sequence are divided into clusters, and all abnormal points in the temperature sequence are divided into outliers; all outliers are regarded as abnormal data of the temperature data sequence.
[0043] An embodiment of the present invention further discloses a temperature monitoring system for a CNC machine tool, comprising a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, a temperature monitoring method for a CNC machine tool according to the present invention is implemented.
[0044] 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.
[0045] 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.
[0046] 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.
[0047] 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. A temperature monitoring method for a CNC machine tool, It is characterized in that Includes steps: Collect temperature data; obtain the primary similarity between two temperature data; obtain the noise probability of each temperature data; Get the similarity between two temperature data , Represents the primary similarity between two temperature data; represents the noise probability of the first temperature data; represents the noise probability of the second temperature data; Represents the second hyperparameter; norm() represents the normalization function; According to the similarity between the two temperature data, the neighborhood data of each temperature data is obtained to achieve anomaly detection.
2. A temperature monitoring method for a CNC machine tool according to claim 1, It is characterized in that The step of obtaining the primary similarity between two temperature data includes: Get the numerical performance factor of each temperature data; ; In the formula, Represents the primary similarity between two temperature data; The numerical representation factor representing the first temperature data; A numerical representation factor representing the second temperature data; represents the first hyperparameter; Represents the sampling time interval between the first temperature data and the second temperature data; exp() represents an exponential function with a natural constant as the base.
3. A temperature monitoring method for a CNC machine tool according to claim 2, It is characterized in that The step of obtaining the numerical expression factor of each temperature data includes: The surrounding data of each temperature data is obtained; the product of the average of the absolute values of the differences of all adjacent surrounding data of the i-th temperature data and the value of the i-th temperature data is used as the numerical expression factor of the i-th temperature data.
4. A temperature monitoring method for a CNC machine tool according to claim 1, It is characterized in that The noise possibility of obtaining each temperature data includes: ; In the formula, Represents the noise possibility of the i-th temperature data; Represents the value of the i-th temperature data; Represents the minimum temperature value in the surrounding data of the i-th temperature data; represents the difference between the maximum temperature and the minimum temperature in the surrounding data of the i-th temperature data; Represents the value of the speed data at the sampling time corresponding to the i-th temperature data; represents the minimum speed value of all speed data in the sampling time period corresponding to the surrounding data of the i-th temperature data; Represents the difference between the maximum speed and the minimum speed in all speed data in the sampling time period corresponding to the surrounding data of the i-th temperature data; norm() represents the normalization function.
5. A temperature monitoring method for a CNC machine tool according to claim 1, It is characterized in that The method of acquiring the neighborhood data of each temperature data according to the similarity between the two temperature data, thereby realizing anomaly detection, includes: A neighbor parameter u and a threshold parameter T are preset. For any temperature data in the temperature data sequence, the neighborhood data of the temperature data is obtained, and the neighborhood data of the temperature data is within the neighborhood range of the temperature data, and the similarity between the neighborhood data and the temperature data is greater than the threshold parameter T; the core point in the temperature data sequence is obtained, and the number of neighborhood data of the core point is greater than or equal to the neighbor parameter u; all abnormal data in the temperature data sequence are obtained, and the number of neighborhood data of the abnormal data is less than the neighbor parameter u and does not belong to the neighborhood data of other core points.
6. A temperature monitoring method for a CNC machine tool according to claim 3, It is characterized in that The step of obtaining surrounding data of each temperature data comprises: The number of surrounding data N is preset, and the first N temperature data and the last N temperature data of the i-th temperature data are used as the surrounding data of the i-th temperature data.
7. A temperature monitoring method for a CNC machine tool according to claim 1, It is characterized in that The collecting of temperature data comprises: A temperature sensor is installed on the CNC machine tool, and a sampling time is preset every two minutes. Temperature data is collected in sequence each time for a total of three hours.
8. A temperature monitoring system for CNC machine tools, It is 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, a temperature monitoring method for a numerically controlled machine tool according to any one of claims 1 to 7 is implemented.
Citation Information
Patent Citations
Novel numerical control machine tool fault diagnosis system and method
CN102478827A
Abnormality determination apparatus, abnormality determination system, abnormality determination method and storage medium
CN110103073A
Intelligent monitoring method and system for numerical control machine tool
CN115220396A
Method for monitoring operation state of numerical control machine tool
CN117798744A
Cold chain storage temperature monitoring method and system
CN118585012A
Cited By
Metal alloy current detection resistor detection data processing method and system
CN119474915A
