A method and system for monitoring abnormal operation status of a high-precision numerical control machine tool

Abstract

The present invention relates to the technical field of data processing. More specifically, the present invention relates to a method and system for monitoring abnormal operating states of a high-precision numerical control machine tool. The method includes: determining a plurality of initial clustering clusters when clustering a pre-acquired target sequence using the ISODATA algorithm. During subsequent iterative clustering, the reliability of each sampling point in each initial clustering cluster is used as a weight to perform a weighted sum of the positions of all sampling points in the corresponding initial clustering cluster, obtaining a plurality of weighted cluster centers for the current clustering until the clustering result converges, obtaining a plurality of clustering clusters, and monitoring the abnormal operating state of the numerical control machine tool according to the comparison result between the normalized value of the distance between each sampling point in each clustering cluster and the clustering center of the corresponding clustering cluster and a preset threshold. The present invention can improve the accuracy of monitoring the abnormal operating state of the numerical control machine tool.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing. More specifically, the present invention relates to a method and system for monitoring abnormal operating states of high-precision numerical control machine tools. Background Art

[0002] As an automated device with a program control system, a numerical control machine tool plays an important role in the manufacturing industry and can achieve high-precision and high-efficiency machining of parts. When the operating state of a numerical control machine tool is abnormal, the relevant operating data will also be abnormal. Therefore, by monitoring the state of the operating data, the abnormal operating state of the numerical control machine tool can be effectively identified, enabling potential problems to be discovered in a timely manner and ensuring the stability of the production process and the quality of products.

[0003] In the related art, as disclosed in the patent application document with the publication number CN117131425A, a method and system for monitoring the machining state of a numerical control machine tool based on feedback data are disclosed. The method includes: obtaining a fault data set according to the basic information of the numerical control machine tool, performing feature reduction on the fault samples, and using the reduced features for classification to obtain a low-dimensional fault feature set. Screening multi-dimensional feature parameters under different working conditions to generate fault feedback data including working condition features. Constructing a machining state monitoring model to identify the current working condition of the numerical control machine tool and make a fault decision. Finally, tracing the root cause of the fault according to the fault decision result and determining the operation and maintenance direction of the numerical control machine tool.

[0004] However, in the above solution, when extracting the low-dimensional fault feature set, it is necessary to first obtain the fault data set, then perform feature reduction and classification on it, and a large amount of labeled information is required during the classification process, resulting in a large time cost, lack of real-time performance, and failure to consider the influence of noise data. Therefore, to a certain extent, it may lead to the inability to accurately monitor the abnormal state of the numerical control machine tool. Summary of the Invention

[0005] To solve the problem of being unable to accurately monitor the abnormal state of a numerical control machine tool, the present invention provides a method and system for monitoring abnormal operating states of high-precision numerical control machine tools.

[0006] According to a first aspect of the present invention, there is provided a method for monitoring abnormal operating states of high-precision numerical control machine tools, including:

[0007] Obtaining various operating data of each sampling point of the numerical control machine tool within the current time period to obtain a target sequence;

[0008] Using the ISODATA algorithm to perform iterative clustering on the target sequence. During each clustering process, taking the reliability of the sampling points in each clustering cluster as a weight, performing weighted summation on the positions of all sampling points in the corresponding clustering cluster to obtain multiple weighted cluster centers during the current clustering until the positions of all clustering clusters converge, obtaining multiple target clustering clusters;

[0009] Monitor the abnormal operating state of the CNC machine tool according to the comparison result between the normalized value of the distance between each sampling point in each target clustering cluster and the weighted cluster center of the corresponding target clustering cluster and a preset threshold value.

[0010] Among them, the reliability , is the degree of fluctuation abnormality of the target sequence, and the degree of fluctuation abnormality reflects the abnormality of the fluctuation of the operation data in the target sequence. is the degree of change abnormality of the th sampling point in the target sequence, and the degree of change abnormality reflects the abnormality of the change trend of the operation data at this sampling point.

[0011] The clustering method of the target sequence in the present invention can effectively distinguish different operating states during the operation of the CNC machine tool, and during the clustering process, it can reduce the weight of sampling points with low reliability, ensuring the accuracy of the cluster center determined in each iterative clustering process, thereby ensuring the accuracy of the obtained clustering result, and further accurately identifying the abnormal operating state of the CNC machine tool based on the clustering result with high accuracy.

[0012] Preferably, the method for obtaining the degree of fluctuation abnormality of the target sequence includes:

[0013] Obtain various operation data of each sampling point of the CNC machine tool in multiple historical time periods to obtain a plurality of reference sequences. The length of the reference sequence is the same as that of the target sequence, and the type of operation data in the reference sequence is the same as that in the target sequence.

[0014] Calculate the difference between the variance of each operation data in the target sequence and the variance of the corresponding operation data in all reference sequences, and take the mean value of the normalized difference as the degree of fluctuation abnormality of the target sequence.

[0015] Preferably, the degree of fluctuation abnormality satisfies the following relational expression:

[0016] ;

[0017] In the formula, is the degree of fluctuation abnormality of the target sequence; is the variance of the th type of operation data in the target sequence; is the variance of the th type of operation data in the th reference sequence; is the absolute value function; is the normalization function; is the number of reference sequences; is the number of types of operation data; is the summation symbol.

[0018] The present invention limits the range of the fluctuation anomaly degree of the target sequence to within 0-1, which can reduce the calculation difficulty.

[0019] Preferably, the change anomaly degree satisfies the following relational expression:

[0020] ;

[0021] In the formula, is the change anomaly degree of the th sampling point in the target sequence; is the difference between the th sampling point in the target sequence and the th type of operation data of the previous sampling point; is the difference between the th sampling point and the previous sampling point in the th reference sequence for the th type of operation data; is the absolute value of the Pearson correlation coefficient between the th type of operation data in the target sequence and the th type of operation data in the th reference sequence, is the normalization function, is the number of reference sequences, is the number of types of operation data, is the absolute value symbol; is the summation symbol.

[0022] The present invention determines the change anomaly degree of each sampling point in the target sequence by integrating various aspects of data, which can ensure the accuracy of the determined change anomaly degree.

[0023] Preferably, the method further includes:

[0024] Using the function to map the reliability of the sampling points in each clustering cluster during the current clustering process to values whose sum is 1.

[0025] The present invention can reduce the computational amount required to determine the weighted cluster center during the iterative clustering process.

[0026] Preferably, according to the comparison result between the normalized value of the distance between each sampling point in each target clustering cluster and the weighted cluster center of the corresponding target clustering cluster and a preset threshold, monitor the abnormal operation state of the numerically controlled machine tool, including:

[0027] Obtain the preset threshold;

[0028] When the normalized value of the distance between any sampling point in any cluster and the cluster center of any cluster is greater than a preset threshold, it is determined that the operation data of any sampling point is abnormal.

[0029] The present invention can accurately monitor the abnormal operation state of a numerically controlled machine tool.

[0030] According to a second aspect of the present invention, there is provided a system for monitoring abnormal operation states of a high-precision numerically controlled machine tool. The system for monitoring abnormal operation states of a high-precision numerically controlled machine tool includes a memory and a processor. A computer program is stored on the memory, and the processor executes the computer program to implement the steps of the first aspect of the present invention.

[0031] The present invention has the following effects:

[0032] When the present invention performs iterative clustering on a target sequence using the ISODATA algorithm, taking the reliability of sampling points as weights can reduce the influence of noise, so that in each iterative clustering, the determined weighted cluster center can approach the actual cluster center, thereby ensuring the accuracy of the clustering result. Furthermore, based on the relatively accurate clustering result, abnormal sampling points can be identified to monitor the abnormal operation state of the numerically controlled machine tool. And when determining the reliability of sampling points, the abnormal conditions of the change trend of the operation data of the sampling points and the abnormal fluctuations of the operation data in the target sequence are combined, and the influence of noise can be considered from multiple aspects, ensuring the accuracy of the determined reliability. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] By reading the following detailed description with reference to the accompanying drawings, the above and other objects, features, and advantages of the exemplary embodiments of the present invention will become readily understood. In the drawings, several embodiments of the present invention are shown by way of illustration and not limitation, and like or corresponding reference numerals represent like or corresponding parts, wherein:

[0034] Figure 1 is a schematic flow chart of the steps of a method for monitoring abnormal operation states of a high-precision numerically controlled machine tool according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0035] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0036] The following will describe in detail the specific embodiments of the present invention with reference to the accompanying drawings.

[0037] Refer to Figure 1, a method for monitoring abnormal operation status of a high-precision numerical control machine tool, including steps S1 - S3, specifically as follows:

[0038] S1: Obtain various operation data of each sampling point of the numerical control machine tool within the current time period to obtain a target sequence.

[0039] In an exemplary embodiment of the present invention, the current time period refers to the time period composed of the current moment and several previous moments; the operation data refers to the data that can affect the performance of the numerical control machine tool; the target sequence refers to the set of various operation data collected at each moment within the current time period.

[0040] In an exemplary embodiment of the present invention, the operation data includes spindle speed data, spindle vibration data, spindle temperature data, feed speed data, feed displacement data, guide rail temperature data, and guide rail vibration data.

[0041] Among them, the feed speed data refers to the moving speed of the workbench or the tool in the feed direction; the feed displacement data refers to the moving distance of the workbench or the tool in the feed direction. Specifically, an encoder can be installed on the motor shaft or the lead screw of the feed system, and the feed speed data can be obtained by measuring the rotation angle of the motor or the rotation angle and pitch of the lead screw; a laser displacement sensor can be installed at a fixed position of the machine tool, and the feed displacement data can be obtained by emitting a laser beam and measuring the intensity of the reflected light.

[0042] A magnetoelectric sensor can be fixedly installed near the spindle on the spindle box housing, and the spindle speed data can be obtained by measuring the frequency of the induced electromotive force; an acceleration sensor can be arranged above the spindle, and the sum of the absolute values of the vibration accelerations of the spindle in three directions is used as the spindle vibration data; a temperature sensor can be installed inside the spindle box to collect the spindle temperature data.

[0043] A temperature sensor can be arranged on the surface of the guide rail to obtain the guide rail temperature data; an acceleration sensor can be arranged on the surface of the guide rail to obtain the guide rail vibration data.

[0044] Furthermore, the sampling frequency of all sensors can be set to 10Hz, and the operation data during the operation of the numerical control machine tool can be collected in real time, and the spindle speed data, spindle vibration data, spindle temperature data, feed speed data, feed displacement data, guide rail temperature data, and guide rail vibration data collected at each moment within the current time period are used as the target sequence. The length of the target sequence in this embodiment is not particularly limited.

[0045] S2: Use the ISODATA algorithm to iteratively cluster the target sequence. In each clustering process, the reliability of the sampling points in each cluster is used as the weight, and the positions of all sampling points in the corresponding cluster are weighted and summed to obtain multiple weighted cluster centers for the current clustering, until the positions of all clusters converge to obtain multiple target clusters.

[0046] It should be noted that when performing abnormal monitoring on the operating status of CNC machine tools, it is difficult to determine how many different operating states exist in the data due to the changeable states of CNC machine tools during operation. ISODATA (Iterative Self-organizing Data Analysis Techniques Algorithm) can automatically adjust the number of clusters according to the distribution of data without pre-specifying the number of clusters. Therefore, using this algorithm to cluster the target sequence can effectively distinguish the different operating states of CNC machine tools during operation.

[0047] It should be further explained that various operation data in the target sequence may be affected by noise during the collection process, resulting in a certain deviation between the obtained cluster center and the actual cluster center during the iterative clustering of the target sequence using the algorithm, making the clustering result less accurate. Therefore, the present invention improves the way the algorithm determines the cluster center during each iterative clustering to ensure that the obtained weighted cluster center is close to the actual cluster center, thereby improving the accuracy of the clustering result. The present invention only improves the way the algorithm determines the cluster center during the iterative clustering process, and does not improve other processes of the algorithm.

[0048] In an exemplary embodiment of the present invention, reliability refers to data that measures the degree to which the sampling points in each cluster are affected by noise, and is used as a weight to reduce the influence of the sampling points that are more likely to be affected by noise on the clustering results. For example, when any sampling point in the target sequence is more likely to be affected by noise, it means that the reliability of the sampling point is low. When the target sequence is iteratively clustered using the ISODATA algorithm, the weight of the sampling point needs to be reduced to obtain the weighted cluster center of the cluster where the sampling point is located, so as to avoid deviation between the obtained cluster center and the actual cluster center, and ensure the accuracy of the clustering results.

[0049] Specifically, calculating the reliability of any sampling point in the target sequence includes the following steps:

[0050] Step 1: Determine the degree of abnormal fluctuation of the target sequence;

[0051] In an exemplary embodiment of the present invention, the determination of the degree of abnormal fluctuation of the target sequence can be achieved by the following steps:

[0052] (1) Obtain various operation data of each sampling point of the CNC machine tool in multiple historical time periods to obtain multiple reference sequences. The length of the reference sequence is the same as that of the target sequence, and the categories of the operation data in the reference sequence are the same as those of the operation data in the target sequence;

[0053] Optionally, a certain number, such as 100 historical time periods, can be selected, and then the spindle speed data, spindle vibration data, spindle temperature data, feed speed data, feed displacement data, guide rail temperature data, and guide rail vibration data collected at each moment within the selected historical time periods are used as reference sequences, so as to obtain multiple reference sequences. In this embodiment, the length of the reference sequence is not particularly limited, as long as it is the same as the length of the target sequence.

[0054] (2) Calculate the difference between the variance of each operation data in the target sequence and the variance of the corresponding operation data in all reference sequences, and use the mean value of the normalized difference as the fluctuation abnormality degree of the target sequence.

[0055] Specifically, the fluctuation abnormality degree of the target sequence satisfies the following relational expression:

[0056] ;

[0057] In the formula, is the fluctuation abnormality degree of the target sequence; is the variance of the th kind of operation data in the target sequence; is the th reference sequence and the th kind of operation data; is the absolute value function; is the normalization function; is the number of reference sequences; is the number of types of operation data; is the summation symbol.

[0058] Among them, reflects the difference between the variance of the th kind of operation data in the target sequence and the variance of the th reference sequence and the th kind of operation data. The larger this value is, the more abnormal the fluctuation of the operation data in the target sequence is, and the greater the fluctuation abnormality degree of the corresponding target sequence is.

[0059] In another embodiment, other methods can also be used for normalization, such as normalization through a deformed exponential function. In this embodiment, the normalization method used is not particularly limited.

[0060] Step 2: Determine the degree of abnormal change of each sampling point in the target sequence.

[0061] Specifically, the degree of abnormal change of any sampling point in the target sequence satisfies the following relational expression:

[0062] ;

[0063] In the formula, is the degree of abnormal change of the th sampling point in the target sequence; is the difference between the th sampling point in the target sequence and the th type of operating data of the previous sampling point; is the difference between the th sampling point and the previous sampling point in the th reference sequence for the th type of operating data; is the absolute value of the Pearson correlation coefficient between the th type of operating data in the target sequence and the th sampling point in the th reference sequence for the is the normalization function, is the number of reference sequences, is the number of types of operating data, is the absolute value symbol; is the summation symbol.

[0064] Among them, reflects the difference in the change trend of the th type of operating data at the th sampling point in the target sequence and the change trend of the th sampling point in the th type of operating data in the th reference sequence. The larger this value is, the greater the influence of noise on the th type of operating data at this sampling point. And when the similarity between the th type of operating data in the target sequence and the th type of operating data in this reference sequence is relatively large, the influence of noise on the th type of operating data at this sampling point is relatively greater.

[0065] Step 3: Combine the degree of abnormal change of any sampling point in the target sequence and the degree of abnormal fluctuation of the target sequence to calculate the reliability of this sampling point.

[0066] Specifically, the reliability of any sampling point in the target sequence satisfies the following relational expression:

[0067] ;

[0068] In the formula, is the reliability of the th sampling point in the target sequence; is the degree of fluctuation abnormality of the target sequence; is the degree of change abnormality of the th sampling point in the target sequence.

[0069] Among them, the specific process of iteratively clustering the target sequence using the ISODATA algorithm is as follows: First, randomly select multiple, such as 5 sampling points from the target sequence as the initial clustering centers, and then determine the Manhattan distance between each sampling point in the target sequence and each initial clustering center, and divide each sampling point into the corresponding initial clustering center with the smallest Manhattan distance to obtain multiple initial clustering clusters. It should be noted that in order to avoid the distribution of each type of running data in the target sequence being too sparse in space, in this embodiment, the Manhattan distance is used to measure the distance between each sampling point and each initial clustering center. Of course, a suitable measurement method can also be selected according to specific situations, and this embodiment does not make a special limitation here.

[0070] Then, in the second clustering process, use the function to map the reliability of all sampling points in each initial clustering cluster to values whose sum is 1, and then use the reliability of each sampling point in each initial clustering cluster as the weight to perform weighted summation on the positions of all sampling points in the corresponding initial clustering cluster to obtain multiple weighted cluster centers in the second clustering, and so on until the positions of all clustering clusters converge to obtain multiple target clustering clusters.

[0071] For example, in any clustering process, if any clustering cluster contains sample point 1 (0, 1, 1) and sample point 2 (2, 0, 1), and the weights of sample point 1 and sample point 2 are 0.2 and 0.8 respectively, then the weighted cluster center of this clustering cluster is: (0×0.2 + 2×0.8, 1×0.2 + 0×0.8, 1×0.2 + 1×0.8), that is, (1.6, 0.2, 1). It should be noted that the process of iteratively clustering data using the ISODATA algorithm to obtain multiple clustering clusters is a prior art, and this embodiment does not elaborate on it here.

[0072] Optionally, using the reliability to determine the weighted cluster center in each clustering process can reduce the influence of noise data, thereby improving the accuracy of the obtained clustering results, and further accurately identifying the abnormal operating state of the CNC machine tool.

[0073] S3: Monitor the abnormal operating state of the CNC machine tool according to the comparison result between the normalized value of the distance between each sampling point in each target clustering cluster and the weighted cluster center of the corresponding target clustering cluster and a preset threshold.

[0074] In an exemplary embodiment of the present invention, the monitoring of the abnormal operating state of the CNC machine tool can be achieved through the following steps:

[0075] Obtain a preset threshold; when the normalized value of the distance between any sampling point in any target clustering cluster and the weighted cluster center of any target clustering cluster is greater than the preset threshold, it is determined that the operating data of any sampling point is abnormal.

[0076] Optionally, the distance between any sampling point in any target clustering cluster and the weighted cluster center of the target clustering cluster can be the Manhattan distance or the Euclidean distance. This embodiment does not make a special limitation on the type of distance adopted.

[0077] Optionally, the threshold can be set to 0.8 according to the empirical value. When the normalized value of the distance between any sampling point in any target clustering cluster and the weighted cluster center of the target clustering cluster is greater than 0.8, it is determined that the operating data of the sampling point is abnormal, and the sampling point can be marked as abnormal, thereby completing the abnormal monitoring of the operating state of the CNC machine tool.

[0078] The present invention also provides a system for monitoring the abnormal operating state of a high-precision CNC machine tool. The system includes a memory and a processor, and a computer program is stored on the memory. The computer program integrates the functions of a method for monitoring the abnormal operating state of a high-precision CNC machine tool. When the computer program is executed, the accuracy of monitoring the abnormal operating state of the CNC machine tool can be improved through a method for monitoring the abnormal operating state of a high-precision CNC machine tool.

[0079] In the description of this specification, the meanings of "a plurality" and "several" are at least two, such as two, three or more, etc., unless otherwise clearly and specifically defined.

[0080] Although this specification has shown and described multiple embodiments of the present invention, it is obvious to those skilled in the art that such embodiments are provided only by way of example. Those skilled in the art will think of many changes, alterations and alternative ways without departing from the spirit and idea of the present invention. It should be understood that various alternative solutions to the embodiments of the present invention described herein can be adopted in the process of practicing the present invention.

Claims

1. A method for monitoring abnormal operation status of a high-precision CNC machine tool, characterized in that: include: Obtain various operating data of the CNC machine tool at each sampling point in the current time period to obtain the target sequence; The target sequence is iteratively clustered using the ISODATA algorithm. In each clustering process, the reliability of the sampling points in each cluster is used as the weight, and the positions of all sampling points in the corresponding cluster are weighted and summed to obtain multiple weighted cluster centers for the current clustering, until the positions of all clusters converge to obtain multiple target clusters; Monitoring the abnormal operation state of the CNC machine tool according to the normalized value of the distance between each sampling point in each of the target clusters and the weighted cluster center of the corresponding target cluster and the comparison result of the preset threshold value; Among them, the reliability , is the degree of abnormal fluctuation of the target sequence, which reflects the abnormal fluctuation of the operating data in the target sequence; The target sequence The abnormal degree of change of a sampling point reflects the abnormality of the change trend of the operation data of the sampling point; The method for obtaining the degree of abnormal fluctuation of the target sequence includes: Acquire multiple operating data of each sampling point of the CNC machine tool in multiple historical time periods to obtain multiple reference sequences, wherein the length of the reference sequence is the same as the length of the target sequence, and the category of the operating data in the reference sequence is the same as the category of the operating data in the target sequence; Calculate the variance of each running data in the target sequence and the difference between the variance of the corresponding running data in all reference sequences, and use the normalized mean of the differences as the degree of fluctuation anomaly of the target sequence; The abnormal degree of the change satisfies the following relationship: ； In the formula, The target sequence The degree of abnormality of changes at each sampling point; The target sequence The sampling point is the same as the previous sampling point. The difference of running data; For the The first The sampling point is the same as the previous sampling point. The difference of the running data; The target sequence Type of operation data, The first The absolute value of the Pearson correlation coefficient between the running data, is the normalization function, is the number of reference sequences, is the number of types of operating data, is the absolute value symbol; is the summation symbol.

2. A method for monitoring abnormal operation status of a high-precision CNC machine tool according to claim 1, characterized in that: The degree of abnormal fluctuation satisfies the following relationship: ； In the formula, is the degree of abnormal fluctuation of the target sequence; The target sequence The variance of the running data; For the The reference sequence The variance of the running data; is the absolute value function; is the normalization function; is the number of reference sequences; is the number of types of operating data; is the summation symbol.

3. The method for monitoring abnormal operation status of a high-precision CNC machine tool according to claim 1, characterized in that: The method further comprises: use Function, which maps the reliability of the sampling points of each cluster in the clustering process to a value whose sum is 1.

4. The method for monitoring abnormal operation status of a high-precision CNC machine tool according to claim 1, characterized in that: The monitoring of the abnormal operation state of the CNC machine tool according to the comparison result of the normalized value of the distance between each sampling point in each target cluster and the weighted cluster center of the corresponding target cluster and the preset threshold comprises: Get the preset threshold value; When the normalized value of the distance between any sampling point in any target cluster and the weighted cluster center of any target cluster is greater than the preset threshold, it is determined that the operating data of any sampling point is abnormal.

5. The method for monitoring abnormal operation status of a high-precision CNC machine tool according to claim 1, characterized in that: The operation data includes spindle speed data, spindle vibration data, spindle temperature data, feed speed data, feed displacement data, guide rail temperature data and guide rail vibration data.

6. A high-precision CNC machine tool operation status abnormality monitoring system, characterized in that: The high-precision CNC machine tool operating status abnormality monitoring system includes a memory and a processor, the memory stores a computer program, and the processor executes the computer program to implement the steps of the method as described in any one of claims 1-5.

Images