Data-driven numerical control machine tool temperature compensation method and system

Abstract

The invention relates to the technical field of numerical control machine tool control, in particular to a data-driven numerical control machine tool temperature compensation method and system, and the method comprises the steps: comparing the variation trend of temperature data and the difference of the amplitude between a temperature measurement point and a homologous measurement point; obtaining a temperature interference degree by combining the similarity of the autocorrelation degree of the temperature data between the temperature measuring point and the homologous measuring point, and determining a temperature weight coefficient by combining the correlation degree between the displacement data of the main shaft of the numerical control machine tool in the main direction and the temperature data of any homologous measuring point of each temperature measuring point at all acquisition moments; and compensating the temperature of the numerical control machine tool at the current moment. The invention aims to improve the precision of temperature compensation of the numerical control machine tool.

Description

Technical Field

[0001] The present application relates to the technical field of CNC machine tool control, and in particular to a data-driven CNC machine tool temperature compensation method and system. Background Art

[0002] CNC machine tools are automated machine tools equipped with program control systems and are an important part of industrial control systems. They can automatically complete workpiece processing tasks according to pre-programmed programs, achieve precise control of machine tool movement, and thus improve workpiece production efficiency and processing quality.

[0003] CNC machine tools generate a lot of heat during the processing process. This heat will cause the temperature of various parts of the machine tool to rise and cause thermal deformation. Since the various parts of the machine tool have different thermal expansion coefficients, temperature changes will cause changes in the geometric shape of the machine tool, which will affect the processing accuracy of the workpiece. Therefore, a temperature compensation method is needed to reduce the impact of thermal deformation of the machine tool on the overall processing accuracy of the workpiece. The traditional CNC machine tool temperature compensation method is to obtain temperature values ​​at multiple positions on the CNC machine tool and calculate the temperature compensation result based on the average of all the obtained temperature values. However, this method does not take into account the different effects of temperature changes at different positions in the CNC machine tool on the thermal deformation of the machine tool and the influence of external interference that the temperature may receive during the data acquisition process. As a result, the average of all the obtained temperature values ​​cannot accurately reflect the thermal deformation of the machine tool, which in turn affects the accuracy of the temperature compensation result of the machine tool. Summary of the invention

[0004] In order to solve the above technical problems, the purpose of this application is to provide a data-driven CNC machine tool temperature compensation method and system, and the technical solutions adopted are as follows:

[0005] In a first aspect, an embodiment of the present application provides a data-driven temperature compensation method for a CNC machine tool, the method comprising the following steps:

[0006] Set multiple temperature measuring points on the CNC machine tool, obtain the temperature data of each temperature measuring point at the current moment and all the acquisition moments within a preset time period before, and the displacement data of the spindle of the CNC machine tool in all directions;

[0007] All temperature measurement points are clustered, and all temperature measurement points in the cluster where each temperature measurement point is located are recorded as the homologous measurement points of each temperature measurement point. Before the current moment, the differences between all temperature data in the neighborhood at each acquisition moment and each homologous measurement point are compared, as well as the differences between the extreme distribution of all temperature data and each homologous measurement point, to evaluate the degree of temperature synchronization of each temperature measurement point at each acquisition moment;

[0008] Analyze the autocorrelation degree of all temperature data in the neighborhood at each acquisition time and the similarity between each temperature measurement point and its homologous measurement points, determine the temperature correlation of each temperature measurement point at each acquisition time, and combine the temperature synchronization degree to obtain the temperature interference degree of each temperature measurement point at each acquisition time;

[0009] Compare the change trends of all displacement data of the spindle of the CNC machine tool in various directions to determine the main direction of the spindle of the CNC machine tool; comprehensively analyze the temperature interference of any homologous measuring point of each temperature measuring point at all acquisition times before the current moment to obtain the reliability of any homologous measuring point of each temperature measuring point, and combine the correlation between the displacement data of the spindle of the CNC machine tool in the main direction at all acquisition times and the temperature data of any homologous measuring point of each temperature measuring point to construct the temperature sensitivity of each temperature measuring point at the current moment; determine the temperature weight coefficient of each temperature measuring point at the current moment based on the temperature interference and temperature sensitivity;

[0010] Based on the temperature data and temperature weight coefficient of each temperature measuring point at the current moment, the temperature of the CNC machine tool at the current moment is compensated.

[0011] Preferably, the expression of the temperature synchronization degree of each temperature measuring point at each acquisition time is: In the formula, S i,j Indicates the degree of temperature synchronization of the jth temperature measurement point at the i-th acquisition time; g i,j represents the mean value of the difference between the temperature data of all acquisition moments in the neighborhood of the i-th acquisition moment and all its homologous measurement points; h i,j It represents the mean of the difference between the range of the temperature data of all the acquisition moments in the neighborhood of the i-th acquisition moment and the j-th temperature measurement point and all its homologous measurement points; exp() represents an exponential function with a natural constant as the base.

[0012] Preferably, the method for determining the temperature correlation of each temperature measurement point at each acquisition time is:

[0013] Obtain the autocorrelation sequence of the temperature data of each temperature measuring point at all the acquisition times in the neighborhood of each acquisition time, recorded as the autocorrelation sequence of each temperature measuring point at each acquisition time;

[0014] The mean of the similarity of the autocorrelation sequences between each temperature measurement point and all its homologous measurement points at each acquisition time is calculated as the temperature correlation of each temperature measurement point at each acquisition time.

[0015] Preferably, the temperature interference degree of each temperature measuring point at each collection moment is the reciprocal of the average of the temperature synchronization degree and the temperature correlation degree of each temperature measuring point at each collection moment.

[0016] Preferably, the method for determining the main direction of the spindle of the CNC machine tool is:

[0017] The displacement data of the spindle of the CNC machine tool at all acquisition times in each direction are fitted to obtain the fitting straight line of the spindle of the CNC machine tool in each direction, and the absolute value of the slope of the fitting straight line in all directions is calculated. The direction with the largest absolute value of the slope is taken as the main direction of the spindle of the CNC machine tool.

[0018] Preferably, the reliability of any homologous measuring point of each temperature measuring point is a normalized value of the inverse of the cumulative sum of temperature interferences of any homologous measuring point of each temperature measuring point at all acquisition moments.

[0019] Preferably, the expression of the temperature sensitivity of each temperature measuring point at the current moment is: Where D j Indicates the temperature sensitivity of the temperature measuring point j at the current moment; Ph j,z represents the reliability of the zth homologous measurement point of temperature measurement point j; dh j,z It represents the correlation between the displacement data of the main axis of the CNC machine tool in the main direction at all acquisition moments before the current moment and the temperature data of the zth homologous measurement point of temperature measurement point j; Z j Represents the number of all homologous measurement points of temperature measurement point j.

[0020] Preferably, the method for determining the temperature weight coefficient of each temperature measuring point at the current moment is:

[0021] The average value of the temperature interference of each temperature measuring point at all acquisition moments before the current moment is calculated, and the ratio of the temperature sensitivity to the average value of the temperature interference is normalized as the temperature weight coefficient of each temperature measuring point at the current moment.

[0022] Preferably, compensating the temperature of the CNC machine tool at the current moment includes:

[0023] The expression of the temperature compensation data R of the CNC machine tool at the current moment is: In the formula, a j Represents the temperature data of the jth temperature measurement point at the current moment; Q j represents the temperature weight coefficient of the jth temperature measuring point at the current moment; N represents the number of all temperature measuring points on the CNC machine tool.

[0024] In the second aspect, an embodiment of the present application also provides a data-driven temperature compensation system for CNC machine tools, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, wherein when the processor executes the computer program, the steps of any one of the above-mentioned data-driven temperature compensation methods for CNC machine tools are implemented.

[0025] This application has at least the following beneficial effects:

[0026] The present application constructs a temperature interference degree by analyzing the difference in the change trend and the difference in the amplitude between the temperature data of a temperature measuring point and its homologous measuring point, and combining the similarity between the degree of autocorrelation of the temperature data of the temperature measuring point and its homologous measuring point, which can more accurately evaluate the degree to which the temperature data of each temperature measuring point is interfered by noise, and help to reduce the influence of noise data on the evaluation of thermal deformation error of the temperature measuring point, thereby improving the accuracy of temperature compensation for CNC machine tools; further, by analyzing the correlation between the displacement data of the CNC machine tool and the temperature data of the temperature measuring point, and combining the temperature interference degree, a temperature sensitivity is constructed, which reflects the sensitivity of the temperature measuring point to the thermal deformation error of the CNC machine tool, which helps to identify the temperature measuring point with a greater influence on the thermal deformation error, and can more comprehensively evaluate the sensitivity of the temperature measuring point, thereby improving the accuracy of temperature compensation for CNC machine tools; further, by combining the temperature interference degree and the temperature sensitivity, a temperature weight coefficient is constructed, and the influence of each temperature measuring point data on the thermal deformation error of the CNC machine tool helps to determine the temperature measuring point that is most critical to temperature compensation, more effectively compensates the temperature of the CNC machine tool, and improves the accuracy of temperature compensation for CNC machine tools. The present application uses a data-driven temperature compensation method to more accurately compensate for the thermal deformation error of a CNC machine tool, thereby improving the accuracy of temperature compensation for the CNC machine tool. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present application or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0028] Figure 1 A flowchart of a method for temperature compensation of a CNC machine tool using data drive provided in one embodiment of the present application;

[0029] Figure 2 A schematic diagram of a temperature interference degree acquisition process provided by an embodiment of the present application;

[0030] Figure 3 A schematic diagram of a temperature weight coefficient extraction framework provided for one embodiment of the present application. DETAILED DESCRIPTION

[0031] In order to further explain the technical means and effects adopted by the present application to achieve the predetermined invention purpose, the following is a detailed description of the data-driven CNC machine tool temperature compensation method and system proposed in the present application, its specific implementation method, structure, features and effects, in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0032] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.

[0033] The following is a detailed description of a data-driven CNC machine tool temperature compensation method and system provided in the present application in conjunction with the accompanying drawings.

[0034] See also Figure 1 , which shows a flowchart of a method for temperature compensation of a CNC machine tool using data drive provided by an embodiment of the present application, the method comprising the following steps:

[0035] Step S1: multiple temperature measuring points are set on the CNC machine tool, and the temperature data of each temperature measuring point at the current moment and all acquisition moments within a preset time period before the current moment are obtained, as well as the displacement data of the spindle of the CNC machine tool in each direction.

[0036] N temperature measuring points are set in the CNC machine tool, and the temperature data of each temperature measuring point at all collection times within a preset time length t before the current time is collected by a temperature sensor, and the displacement data of the spindle of the CNC machine tool in the X, Y, and Z directions within the preset time length t before the current time are collected by a displacement sensor, wherein the data collection frequency is set to f, the X direction represents the forward direction parallel to the spindle, the Y direction represents the lateral movement direction parallel to the CNC machine tool main console and perpendicular to the forward direction, and the Z direction represents the up and down movement direction perpendicular to the CNC machine tool main console.

[0037] It should be noted that the number N of temperature measurement points, the preset time t, and the data acquisition frequency f are all manually set. In this embodiment, the number N of temperature measurement points is 20, the preset time t is 5 minutes, and the data acquisition frequency f is 10 Hz. The implementer can also set them according to the specific situation. This embodiment does not impose any special restrictions.

[0038] Step S2: cluster all temperature measurement points, record all temperature measurement points in the cluster where each temperature measurement point is located as the homologous measurement points of each temperature measurement point, and before the current moment, respectively compare the differences between each temperature measurement point and its homologous measurement points for all temperature data in the neighborhood at each acquisition moment, as well as the differences between each temperature measurement point and its homologous measurement points for the extreme distribution of all temperature data, to evaluate the temperature synchronization degree of each temperature measurement point at each acquisition moment; analyze the similarity between each temperature measurement point and its homologous measurement points for the autocorrelation degree of all temperature data in the neighborhood at each acquisition moment, determine the temperature correlation degree of each temperature measurement point at each acquisition moment, and obtain the temperature interference degree of each temperature measurement point at each acquisition moment in combination with the temperature synchronization degree.

[0039] Since the heat sources of CNC machine tools mainly come from motors, thermal friction, coolants, and ambient temperature, the temperature changes at different positions of CNC machine tools are usually the result of thermal coupling of multiple heat sources. For temperature measurement points with similar heat source coupling results, their temperature changes usually show synchronization in time, that is, in the same time period, these temperature measurement points have similar temperature change trends and amplitudes, and their temperature data usually have similar autocorrelation distributions in time. When the temperature data collected by the temperature measurement point at a certain moment is disturbed by noise, due to the randomness of the noise, this synchronization and autocorrelation distribution are usually destroyed. Therefore, in order to improve the accuracy of evaluating the degree of influence of the temperature data of a certain temperature measurement point on the thermal deformation error of the CNC machine tool, the temperature interference degree of each temperature measurement point at each acquisition time is evaluated by comparing the difference in the change trend and amplitude of the temperature data between the temperature measurement point and its homologous measurement point, and combining the similarity of the autocorrelation degree of the temperature data between the temperature measurement point and the homologous measurement point, specifically:

[0040] (1) All temperature measurement points on the CNC machine tool are clustered, where the DTW distance of the temperature data at all acquisition times between different temperature measurement points is used as the clustering distance to obtain multiple clusters. All temperature measurement points in the cluster where each temperature measurement point is located are recorded as the homologous measurement points of each temperature measurement point.

[0041] It should be noted that there are many commonly used clustering algorithms. In this embodiment, the k-means clustering algorithm is used to cluster all temperature measurement points at the current moment. The implementer can also use other clustering methods such as DPC density mean clustering. Regarding the selection of clustering methods, this embodiment does not make any special restrictions.

[0042] The clustering principle of the k-means clustering algorithm and the calculation process of DTW are both well-known technologies, and the specific clustering process and calculation process are not described in detail.

[0043] (2) Further, before the current moment, for each temperature measurement point, a neighborhood W is divided with each collection moment as the center, wherein the radius of the neighborhood W is manually set. In this embodiment, the radius of the neighborhood W is 7. The implementer can also set it according to the specific situation. This embodiment does not impose any special restrictions.

[0044] (3) Furthermore, before the current moment, the differences between all temperature data and their extreme distribution in the neighborhood at each acquisition moment and each temperature measurement point and its homologous measurement point are compared to evaluate the degree of temperature synchronization of each temperature measurement point at each acquisition moment, specifically:

[0045] The degree of temperature synchronization S of the jth temperature measurement point at the i-th acquisition time i,j The expression is: In the formula, g i,j represents the mean value of the difference between the temperature data of all acquisition moments in the neighborhood of the i-th acquisition moment and all its homologous measurement points; h i,j It represents the mean of the difference between the range of the temperature data of all the acquisition moments in the neighborhood of the i-th acquisition moment and the j-th temperature measurement point and all its homologous measurement points; exp() represents an exponential function with a natural constant as the base.

[0046] According to the degree of temperature synchronization of each temperature measuring point at each acquisition time, it can be understood that if the mean value of the difference between the temperature data at the i-th acquisition time and all the acquisition times in its neighborhood at the j-th temperature measuring point and all the homologous measuring points is larger, it means that the similarity of the temperature change trend between the j-th temperature measuring point and all the homologous measuring points is smaller; and the mean value of the difference between the range of the temperature data at the i-th acquisition time and all the acquisition times in its neighborhood at the j-th temperature measuring point and all the homologous measuring points is larger, it means that the difference in temperature amplitude between the j-th temperature measuring point and all the homologous measuring points is larger, and the degree of temperature synchronization is smaller;

[0047] On the contrary, if the mean of the difference between the temperature data at the i-th acquisition time and all the acquisition times in its neighborhood at the j-th temperature measurement point and all the homologous measurement points is smaller, and the mean of the difference between the range of the temperature data at the i-th acquisition time and all the acquisition times in its neighborhood at the j-th temperature measurement point and all the homologous measurement points is smaller, it means that the difference in temperature amplitude between the j-th temperature measurement point and its homologous measurement points is smaller, and the degree of temperature synchronization is greater.

[0048] (4) further, obtaining the autocorrelation sequence of the temperature data of each temperature measuring point at all the acquisition times in the neighborhood of each acquisition time as the autocorrelation sequence of each temperature measuring point at each acquisition time;

[0049] The method for obtaining the autocorrelation sequence is a well-known technique, and the specific acquisition process will not be described in detail.

[0050] The mean of the similarity of the autocorrelation sequences between each temperature measurement point and all its homologous measurement points at each acquisition time is calculated as the temperature correlation of each temperature measurement point at each acquisition time.

[0051] It should be noted that there are many methods for measuring the similarity between sequences. In this embodiment, the cosine similarity of the autocorrelation sequences between each temperature measurement point and all its homologous measurement points at each acquisition time is calculated to measure the similarity of the autocorrelation sequences between the temperature measurement point and its homologous measurement points. The implementer may also use other methods for measuring the similarity between sequences, such as the Jaccard similarity coefficient or the inverse of the Euclidean distance. This embodiment does not impose any special restrictions on the selection of the method for measuring the similarity between sequences.

[0052] The calculation process of cosine similarity is a well-known technology, and its specific calculation steps are not repeated here.

[0053] (5) Furthermore, before the current moment, the reciprocal of the average of the temperature synchronization degree and the temperature correlation degree of each temperature measuring point at each collection moment is used as the temperature interference degree of each temperature measuring point at each collection moment.

[0054] According to the temperature interference degree of each temperature measuring point at each acquisition time, it can be understood that if the temperature correlation is greater, it means that the similarity between the autocorrelation of the temperature measuring point and its homologous measuring point is greater, that is, the greater the similarity of the temperature change trend between the temperature measuring point and the homologous measuring point, the smaller the influence of noise on the thermal deformation error of the CNC machine tool, and the smaller the possibility of being interfered by noise; and the greater the temperature synchronization degree, the greater the similarity of the temperature change trend between the temperature measuring point and the homologous measuring point, and the smaller the final temperature interference degree, which means that the influence of noise on the thermal deformation error of the CNC machine tool is smaller;

[0055] On the contrary, if the temperature correlation is smaller, it means that the similarity between the autocorrelation of the temperature measuring point and its homologous measuring point is smaller, that is, the similarity of the temperature change trend between the temperature measuring point and the homologous measuring point is smaller, which means that the influence of noise on the thermal deformation error of the CNC machine tool is greater, and the possibility of being interfered by noise is greater. The smaller the temperature synchronization is, the smaller the similarity of the temperature change trend between the temperature measuring point and the homologous measuring point is, and the greater the final temperature interference is, which means that the influence of noise on the thermal deformation error of the CNC machine tool is greater.

[0056] Preferably, the temperature interference degree acquisition process diagram provided in this embodiment is as follows: Figure 2 shown.

[0057] Step S3: compare the change trends of all displacement data of the spindle of the CNC machine tool in various directions to determine the main direction of the spindle of the CNC machine tool; comprehensively analyze the temperature interference of any homologous measuring point of each temperature measuring point at all acquisition times before the current moment to obtain the reliability of any homologous measuring point of each temperature measuring point, and combine the correlation between the displacement data of the spindle of the CNC machine tool in the main direction at all acquisition times and the temperature data of any homologous measuring point of each temperature measuring point to construct the temperature sensitivity of each temperature measuring point at the current moment; determine the temperature weight coefficient of each temperature measuring point at the current moment based on the temperature interference and temperature sensitivity.

[0058] (1) First, since the thermal deformation error of a CNC machine tool is usually the result of the combined influence of thermal deformation at various positions, in order to improve the evaluation accuracy of the sensitivity of each temperature measurement point of the CNC machine tool to the thermal deformation error of the CNC machine tool, the displacement data of the spindle of the CNC machine tool at all acquisition times in each direction are fitted to obtain the fitting straight line of the spindle of the CNC machine tool in each direction, and the absolute value of the slope of the fitting curve of the spindle of the CNC machine tool in all directions is calculated, and the direction with the largest absolute value of the slope is recorded as the main direction.

[0059] It should be noted that the reason why the direction with the largest absolute value of the slope is taken as the main direction is that in the direction with the largest absolute value of the slope, the displacement change caused by temperature change is most significant, that is, this direction is most sensitive to temperature change. Therefore, the thermal deformation in this direction has the greatest impact on the overall accuracy of the CNC machine tool. Therefore, the degree of influence of thermal deformation in this direction on temperature compensation is analyzed.

[0060] (2) Secondly, in CNC machine tools, for temperature measurement points with similar heat source coupling results, their sensitivity to the thermal deformation error of the CNC machine tool is usually similar. Therefore, by analyzing the correlation between the displacement data of the CNC machine tool and the temperature data of the homologous measurement points of each temperature measurement point, and combining the temperature interference, the temperature sensitivity of each temperature measurement point at the current moment is determined, specifically:

[0061] Calculate the cumulative sum of the temperature interference of any homologous measuring point of each temperature measuring point at all acquisition moments, and use the normalized value of the reciprocal of the cumulative sum as the reliability of any homologous measuring point of each temperature measuring point;

[0062] Further, based on the correlation between the displacement data of the spindle of the CNC machine tool in the main direction at all acquisition moments and the temperature data of any homologous measuring point of each temperature measuring point, and in combination with the reliability, the temperature sensitivity of each temperature measuring point at the current moment is determined, specifically:

[0063] The temperature sensitivity D of the jth temperature measurement point at the current moment j The expression is: Where Ph j,z represents the reliability of the zth homologous measurement point of temperature measurement point j; dh j,z It represents the correlation between the displacement data of the main axis of the CNC machine tool in the main direction at all acquisition moments before the current moment and the temperature data of the zth homologous measurement point of temperature measurement point j; Z j Represents the number of all homologous measurement points of temperature measurement point j.

[0064] It should be noted that there are many methods for measuring the degree of correlation between data groups. In this embodiment, the Pearson correlation coefficient between the displacement data of the spindle of the CNC machine tool in the main direction at all acquisition moments before the current moment and the temperature data of the zth homologous measuring point of the jth temperature measuring point is calculated to measure the degree of correlation between the displacement data and the temperature data. The implementer may also use other methods for measuring the degree of correlation between data groups, such as the Kendall correlation coefficient or the Spearman correlation coefficient. Regarding the selection of the method for measuring the degree of correlation between data groups, this embodiment does not impose any special restrictions.

[0065] The calculation process of the Pearson correlation coefficient is a well-known technique, and the specific calculation steps are not described in detail.

[0066] Further, according to the temperature sensitivity of each temperature measuring point at the current moment, it can be understood that if the reliability of the zth homologous measuring point of the jth temperature measuring point is greater, it means that the sensitivity of the jth temperature measuring point to the thermal deformation error of the CNC machine tool is more reliable, and this sensitivity can better represent the sensitivity of other temperature measuring points with similar heat source influences to the thermal deformation error of the CNC machine tool; and the greater the correlation between the displacement data and the temperature data, it means that the change trends between the displacement data and the temperature data are the same, the size of the displacement data changes in the same direction with the change of the temperature data, and the greater the obtained temperature sensitivity, it means that the jth temperature measuring point is more sensitive to the thermal deformation error of the CNC machine tool;

[0067] On the contrary, if the reliability of the zth homologous measuring point of the jth temperature measuring point is greater, it means that the jth temperature measuring point is less sensitive to the thermal deformation error of the CNC machine tool; and the smaller the correlation between the displacement data and the temperature data, the smaller the similarity of the change trends between the displacement data and the temperature data, and the smaller the obtained temperature sensitivity, which means that the jth temperature measuring point is less sensitive to the thermal deformation error of the CNC machine tool.

[0068] (3) Then, based on the temperature interference and temperature sensitivity, the temperature weight coefficient of each temperature measurement point at the current moment is determined, specifically:

[0069] The average value of the temperature interference of each temperature measuring point at all acquisition moments before the current moment is calculated, and the ratio of the temperature sensitivity to the average value of the temperature interference is normalized as the temperature weight coefficient of each temperature measuring point at the current moment.

[0070] According to the temperature weight coefficient of each temperature measuring point at the current moment, it can be understood that the greater the sensitivity of the temperature measuring point to the thermal deformation error of the CNC machine tool, that is, the greater the temperature sensitivity, and the smaller the mean value of the temperature interference of the temperature measuring point, the more the temperature data at the current moment can reflect the thermal deformation of the CNC machine tool at the current moment, and the greater the temperature weight coefficient of the temperature measuring point, the more the temperature data of the temperature measuring point at the current moment can reflect the thermal deformation of the CNC machine tool at the current moment;

[0071] On the contrary, the less sensitive the temperature measuring point is to the thermal deformation error of the CNC machine tool, that is, the smaller the temperature sensitivity, and the larger the mean value of the temperature interference of the temperature measuring point, the less the temperature data at the current moment can reflect the thermal deformation of the CNC machine tool at the current moment, and the smaller the temperature weight coefficient of the temperature measuring point, the less the temperature data of the temperature measuring point at the current moment can reflect the thermal deformation of the CNC machine tool at the current moment.

[0072] Preferably, the temperature weight coefficient extraction framework schematic diagram provided in this embodiment is as follows Figure 3 shown.

[0073] Step S4: Based on the temperature data and temperature weight coefficient of each temperature measuring point at the current moment, the temperature of the CNC machine tool at the current moment is compensated.

[0074] Based on the temperature weight coefficient obtained in step S3, the temperature of the CNC machine tool at the current moment is compensated based on the temperature weight coefficient and the temperature data of all temperature measurement points at the current moment, specifically:

[0075] The expression of the temperature compensation data R of the CNC machine tool at the current moment is: In the formula, a j Represents the temperature data of the jth temperature measurement point at the current moment; Q j represents the temperature weight coefficient of the jth temperature measuring point at the current moment; N represents the number of all temperature measuring points on the CNC machine tool.

[0076] So far, this embodiment constructs the temperature interference degree by analyzing the distribution characteristics of the temperature data between the temperature measuring points with similar heat source coupling results in the CNC machine tool, and can more accurately distinguish the noise interference degree of the temperature data of each temperature measuring point of the CNC machine tool; by analyzing the sensitivity of the temperature measuring points with similar heat source coupling results in the CNC machine tool to the thermal deformation error of the CNC machine tool, and combining the correlation between the temperature data and the displacement data and the noise interference degree, the temperature sensitivity is constructed, which can more accurately evaluate the evaluation accuracy of the sensitivity of each temperature measuring point in the CNC machine tool to the thermal deformation error of the CNC machine tool; finally, the temperature sensitivity and the temperature interference degree are combined to construct the temperature weight coefficient, and the temperature compensation result of the CNC machine tool is calculated according to the temperature weight coefficient, which reduces the method of calculating the temperature compensation result in the traditional CNC machine tool because it does not consider the different effects of temperature changes at different positions in the CNC machine tool on the thermal deformation of the machine tool, and the interference of external noise that the temperature data may be subjected to during the acquisition process, and can more accurately calculate the temperature compensation result of the CNC machine tool, thereby achieving more precise control of the movement of the CNC machine tool.

[0077] Based on the same inventive concept as the above method, an embodiment of the present application also provides a data-driven CNC machine tool temperature compensation system, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor implements the steps of any one of the above-mentioned data-driven CNC machine tool temperature compensation methods when executing the computer program.

[0078] It should be noted that the above sequence of the embodiments of the present application is for description only and does not represent the advantages and disadvantages of the embodiments. The above is a description of a specific embodiment of this specification. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0079] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

[0080] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the principles of the present application should be included in the protection scope of the present application.

Claims

1. A data-driven CNC machine tool temperature compensation method, characterized in that: The method comprises the following steps: Set multiple temperature measuring points on the CNC machine tool, obtain the temperature data of each temperature measuring point at the current moment and all the acquisition moments before the preset time length, and the displacement data of the spindle of the CNC machine tool in all directions; All temperature measurement points are clustered, and all temperature measurement points in the cluster where each temperature measurement point is located are recorded as the homologous measurement points of each temperature measurement point. Before the current moment, the differences between all temperature data in the neighborhood at each acquisition moment and each homologous measurement point are compared, as well as the differences between the extreme distribution of all temperature data and each homologous measurement point, to evaluate the degree of temperature synchronization of each temperature measurement point at each acquisition moment; Analyze the autocorrelation degree of all temperature data in the neighborhood at each acquisition time and the similarity between each temperature measurement point and its homologous measurement points, determine the temperature correlation of each temperature measurement point at each acquisition time, and combine the temperature synchronization degree to obtain the temperature interference degree of each temperature measurement point at each acquisition time; Compare the change trends of all displacement data of the spindle of the CNC machine tool in various directions to determine the main direction of the spindle of the CNC machine tool; comprehensively analyze the temperature interference of any homologous measuring point of each temperature measuring point at all acquisition times before the current moment to obtain the reliability of any homologous measuring point of each temperature measuring point, and combine the correlation between the displacement data of the spindle of the CNC machine tool in the main direction at all acquisition times and the temperature data of any homologous measuring point of each temperature measuring point to construct the temperature sensitivity of each temperature measuring point at the current moment; determine the temperature weight coefficient of each temperature measuring point at the current moment based on the temperature interference and temperature sensitivity; Based on the temperature data and temperature weight coefficient of each temperature measuring point at the current moment, the temperature of the CNC machine tool at the current moment is compensated.

2. A data-driven CNC machine tool temperature compensation method as claimed in claim 1, characterized in that: The expression of the temperature synchronization degree of each temperature measuring point at each acquisition time is: In the formula, S i,j Indicates the degree of temperature synchronization of the jth temperature measurement point at the i-th acquisition time; g i,j represents the mean value of the difference between the temperature data of all acquisition moments in the neighborhood of the i-th acquisition moment and all its homologous measurement points; h i,j It represents the mean of the difference between the range of the temperature data of all the acquisition moments in the neighborhood of the i-th acquisition moment and the j-th temperature measurement point and all its homologous measurement points; exp() represents an exponential function with a natural constant as the base.

3. A data-driven temperature compensation method for CNC machine tools as claimed in claim 1, characterized in that: The method for determining the temperature correlation of each temperature measurement point at each acquisition time is: Obtain the autocorrelation sequence of the temperature data of each temperature measuring point at all the acquisition times in the neighborhood of each acquisition time, recorded as the autocorrelation sequence of each temperature measuring point at each acquisition time; The mean of the similarity of the autocorrelation sequences between each temperature measurement point and all its homologous measurement points at each acquisition time is calculated as the temperature correlation of each temperature measurement point at each acquisition time.

4. A data-driven temperature compensation method for CNC machine tools as claimed in claim 1, characterized in that: The temperature interference degree of each temperature measurement point at each acquisition moment is the reciprocal of the average of the temperature synchronization degree and the temperature correlation degree of each temperature measurement point at each acquisition moment.

5. The data-driven temperature compensation method for a CNC machine tool according to claim 1, characterized in that: The method for determining the main direction of the spindle of the CNC machine tool is: The displacement data of the spindle of the CNC machine tool at all acquisition times in each direction are fitted to obtain the fitting straight line of the spindle of the CNC machine tool in each direction, and the absolute value of the slope of the fitting straight line in all directions is calculated. The direction with the largest absolute value of the slope is taken as the main direction of the spindle of the CNC machine tool.

6. A data-driven CNC machine tool temperature compensation method as claimed in claim 1, characterized in that: The reliability of any homologous measuring point of each temperature measuring point is a normalized value of the inverse of the cumulative sum of temperature interferences of any homologous measuring point of each temperature measuring point at all acquisition moments.

7. A data-driven temperature compensation method for a CNC machine tool as claimed in claim 1, characterized in that: The expression of the temperature sensitivity of each temperature measuring point at the current moment is: Where D j Indicates the temperature sensitivity of the temperature measuring point j at the current moment; Ph j,z represents the reliability of the zth homologous measurement point of temperature measurement point j; dh j,z It represents the correlation between the displacement data of the main axis of the CNC machine tool in the main direction at all acquisition moments before the current moment and the temperature data of the zth homologous measurement point of temperature measurement point j; Z j Represents the number of all homologous measurement points of temperature measurement point j.

8. A data-driven temperature compensation method for a CNC machine tool as claimed in claim 1, characterized in that: The method for determining the temperature weight coefficient of each temperature measuring point at the current moment is: The average value of the temperature interference of each temperature measuring point at all acquisition moments before the current moment is calculated, and the ratio of the temperature sensitivity to the average value of the temperature interference is normalized as the temperature weight coefficient of each temperature measuring point at the current moment.

9. A data-driven temperature compensation method for a CNC machine tool as claimed in claim 1, characterized in that: The compensating the temperature of the CNC machine tool at the current moment includes: The expression of the temperature compensation data R of the CNC machine tool at the current moment is: In the formula, a j Represents the temperature data of the jth temperature measurement point at the current moment; Q j represents the temperature weight coefficient of the jth temperature measuring point at the current moment; N represents the number of all temperature measuring points on the CNC machine tool.

10. A data-driven temperature compensation system for a numerically controlled machine tool, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the steps of a data-driven temperature compensation method for a CNC machine tool as described in any one of claims 1 to 9 are implemented.

Images