Workpiece machining data processing method and system

Abstract

The invention relates to the technical field of data processing, in particular to a workpiece machining data processing method and system. The method comprises the following steps: acquiring data points in a historical operation data set of workpiece processing and a clustering center of each clustering cluster; obtaining an abnormal index of the cluster according to the ratio of the number of the data points in the cluster to the number of the data points in the maximum cluster, and obtaining the suspicious degree of the cluster according to the Euclidean distance between each data point in the cluster and the clustering center; taking the range value of the collection moment corresponding to the data points in the clustering cluster as the credibility of the suspicious degree to obtain the feature weight of the clustering cluster; the specific value of the local density of the data point to the feature weight of the clustering cluster where the data point is located is marked as the weighted local density of the data point, the outlier factor of the data point is obtained through calculation, workpiece machining data processing is achieved through the comparison result of the outlier factor and the preset threshold value, and the accuracy of workpiece machining anomaly monitoring is effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a workpiece processing data processing method and system. Background Art

[0002] Workpieces are used in many manufacturing industries such as wind power, chemical industry, and machinery. Their quality plays an important role in the performance and service life of related equipment. During the forging process, after the metal material is heated, it is plastically deformed by applying fixed pressure through a special press to produce high-strength and high-toughness workpieces. In order to ensure the quality of the workpiece, it is necessary to monitor the workpiece processing process.

[0003] Most of the existing technologies obtain monitoring results by collecting processing parameters in the workpiece production process and analyzing them. For example, the patent application document with publication number CN117495211A discloses an industrial machine tool workpiece quality prediction method based on adaptive cycle discovery. The method obtains a sample data set; randomly divides the sample data set into a training set, a validation set and a test set according to a set ratio; constructs a surface roughness prediction model for the workpiece; uses the training set to train the surface roughness prediction model for the workpiece; and uses the trained surface roughness prediction model for the workpiece to obtain a predicted value of the surface roughness of the workpiece, so as to predict the quality of the workpiece.

[0004] Although the above-mentioned existing technologies can improve the efficiency of obtaining workpiece quality results to a certain extent, in the actual processing process, due to factors such as internal friction of the machine tool and loose parts, the hydraulic system may generate continuous abnormal processing parameter data, and such abnormal data will affect the accuracy of workpiece quality prediction.

[0005] Based on this, how to accurately realize data monitoring during the workpiece processing is an urgent problem to be solved by technical personnel in this field. Summary of the invention

[0006] In order to solve the technical problem of how to accurately realize data monitoring during workpiece processing, the present invention provides a workpiece processing data processing method and system.

[0007] In a first aspect, the present invention provides a workpiece processing data processing method, which adopts the following technical solution: A workpiece processing data processing method comprises the steps of: A historical operation data set of workpiece processing is obtained, wherein the historical operation data set includes a number of data points composed of processing parameters, and the cluster center of each cluster in the historical operation data set is obtained by using an iterative self-organizing clustering algorithm; the abnormal index of the cluster is obtained by subtracting the ratio of the number of data points in a cluster to the number of data points in the largest cluster from 1, and the normalized value of the product of the Euclidean distance standard deviation of each data point in the cluster and the cluster center and the abnormal index is recorded as the suspicious degree of the cluster; the extreme difference value at the acquisition time corresponding to the data point in the cluster is used as the credibility of the suspicious degree to obtain the characteristic weight of the cluster; the local density of each data point is determined by using a local outlier factor algorithm, and the ratio of the local density of the data point to the characteristic weight of the cluster where the data point is located is recorded as the weighted local density of the data point; the outlier factor of the data point is obtained through the weighted local density of the data point, and the workpiece processing data processing is realized through the comparison result of the outlier factor with a preset threshold.

[0008] The present invention can obtain abnormal monitoring results of workpiece processing through the local outlier factor algorithm. In this process, the present invention takes into account that due to factors such as internal friction of the machine tool and loose parts, the hydraulic system may generate continuous abnormal processing parameter data, and the local outlier factor algorithm may identify such continuous abnormal data as normal data. Based on this, the present invention iteratively clusters the historical operation data, obtains the time span of the data points in the cluster cluster and the suspicious degree of the cluster cluster to determine its feature weight, and corrects the local density obtained by the local outlier factor algorithm through the feature weight, which can accurately identify the abnormal data in the operation data set, thereby effectively improving the accuracy of workpiece processing abnormal monitoring.

[0009] According to a workpiece processing data processing method provided by the present invention, the acquisition of the historical operation data set of the workpiece processing also includes: presetting the acquisition frequency, taking the value of each processing parameter obtained at each acquisition moment as a data point, and pre-processing all data points and arranging them in time series to obtain the historical operation data set.

[0010] The present invention can effectively improve the overall quality of the data by preprocessing the workpiece processing data, and prepare for subsequent data processing.

[0011] According to a workpiece processing data processing method provided by the present invention, the cluster center of each cluster in the historical operation data set is obtained by using an iterative self-organizing clustering algorithm, including: using an iterative self-organizing clustering algorithm to obtain the initial cluster in the historical operation data set, and obtaining the possibility of the latest data point belonging to each initial cluster through the degree of deviation between the processing parameters corresponding to the latest data point and the processing parameters corresponding to the cluster center of the initial cluster, and taking the initial cluster corresponding to the maximum possibility of the latest data point belonging to each cluster as the cluster where the data point is located, and determining the cluster center of each cluster.

[0012] The present invention takes into account the deviation between normal data and abnormal data in the workpiece processing data, but their local density performance may be similar. Therefore, the data set is divided into multiple initial clusters, and the latest data points are divided according to the degree of deviation between the latest data points and the initial clusters to obtain clusters, and the data characteristics in each cluster are analyzed to obtain its abnormality degree.

[0013] According to a workpiece processing data processing method provided by the present invention, the possibility degree of the latest data point belonging to each initial cluster satisfies the relationship: ; In the formula, Indicates that the i-th latest data point belongs to The probability of the initial clusters, Indicates the number of processing parameters corresponding to the data point, represents the value of the jth processing parameter in the i-th latest data point, Indicates The value of the jth processing parameter in the cluster center of the initial clusters, Indicates The standard deviation of the jth processing parameter of all data points in the initial clusters, represents the exponential function with base e, Represents the absolute value symbol.

[0014] According to a workpiece processing data processing method provided by the present invention, the extreme difference value at the collection time corresponding to the data point in the cluster is used as the credibility of the suspicious degree to obtain the feature weight of the cluster, including: taking the normalized value of the ratio of the suspicious degree of the cluster to its credibility as the feature weight of the cluster.

[0015] The present invention takes into account that the anomalies generated in the actual processing process appear as continuous abnormal data in the data set. Therefore, the continuous abnormal data generated in a shorter time span is more likely to be generated by the system itself, and appears as concentrated in a short time in the cluster. By combining the time span of the cluster with the degree of suspicion, the characteristic weight of the cluster can be accurately obtained.

[0016] According to a workpiece processing data processing method provided by the present invention, the outlier factor of the data point is obtained by the weighted local density of the data point, including: taking the ratio of the weighted local density mean of the data point and other data points in its k-neighborhood to the weighted local density of the data point as the outlier factor of the data point.

[0017] According to a workpiece processing data processing method provided by the present invention, the workpiece processing data processing is realized by comparing the outlier factor with the preset threshold, including: presetting the threshold; treating the data points corresponding to the outlier factor greater than the preset threshold as abnormal data points; treating the data points corresponding to the outlier factor not greater than the preset threshold as normal data points.

[0018] The present invention obtains abnormal data in the workpiece processing process by calculating the outlier factor, and can accurately process the processing data, thereby accurately obtaining the monitoring results of the data points.

[0019] In a second aspect, the present invention provides a workpiece processing data processing system, which adopts the following technical solution: A workpiece processing data processing system comprises: a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the workpiece processing data processing method mentioned above is implemented.

[0020] By adopting the above technical solution, the above-mentioned workpiece processing data processing method is generated into a computer program and stored in a memory so as to be loaded and executed by a processor, thereby making a terminal device based on the memory and the processor for easy use.

[0021] The present invention has the following technical effects: Based on the above technical scheme, when processing workpiece processing data, the present invention can obtain abnormal monitoring results of workpiece processing through the local outlier factor algorithm. In this process, the present invention iteratively clusters the historical operation data, determines its feature weight by obtaining the time span of the data points in the clustering cluster and the suspicious degree of the clustering cluster, and corrects the local density obtained by the local outlier factor algorithm through the feature weight. It can accurately identify abnormal data in the operating data set, reduce the influence of continuous abnormal processing parameter data generated by the hydraulic system on the monitoring results, and thus effectively improve the accuracy of workpiece processing abnormality monitoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] 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.

[0023] Figure 1 A schematic flow chart of a workpiece machining data processing method provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0024] 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.

[0025] 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.

[0026] It should be noted that workpieces are used in many manufacturing industries such as wind power, chemical industry, and machinery, and their quality plays an important role in the performance and service life of related equipment. During the forging process, after the metal material is heated, it is plastically deformed by applying fixed pressure through a special press to produce high-strength and high-toughness workpieces. In order to ensure the quality of the workpiece, it is necessary to monitor the abnormality of the workpiece processing process.

[0027] However, in the actual processing process, due to factors such as internal friction of the machine tool and loose parts, the hydraulic system may generate continuous abnormal processing parameter data. The local density of such abnormal processing parameter data is close to the local density of normal data. When processing, the conventional local outlier factor algorithm may regard the abnormal data as normal data because the local density of the abnormal data point is not obviously different from the local density of other data points in its neighborhood, which affects the accuracy of workpiece processing data.

[0028] Based on this, the embodiment of the present invention discloses a method for processing workpiece processing data, which obtains the abnormality of the clusters in the data set, evaluates the feature weights of the data points in the clusters in combination with the time span in the clusters, and weights the local density of the data points based on the feature weights, so as to accurately screen out abnormal data and improve the accuracy of workpiece processing data. Figure 1 As shown, Figure 1 A schematic flow chart of a method for processing workpiece machining data provided by an embodiment of the present invention, the method specifically comprises the following steps S1 to S5.

[0029] S1: Obtain the historical operation data set of workpiece processing, and use the iterative self-organizing clustering algorithm to obtain the cluster center of each cluster in the historical operation data set.

[0030] Among them, processing parameters may include pressure, speed, etc., which can be set according to actual needs.

[0031] By way of example, in an embodiment of the present invention, the processing parameters corresponding to each data point in the historical operation data set of workpiece processing are obtained, which also includes: presetting the acquisition frequency, taking the value of each processing parameter obtained at each acquisition moment as a data point, and pre-processing all data points and arranging them in time series to obtain the historical operation data set.

[0032] The acquisition frequency may be preset to be once per second, and may be specifically set according to actual needs, and the embodiment of the present invention does not impose too many restrictions on this.

[0033] For example, data preprocessing may be data cleaning, data format conversion, etc., which may be specifically configured according to actual needs, and the embodiments of the present invention do not impose excessive limitations thereon.

[0034] It should be noted that during the forging process of the workpiece, the processing parameter data will remain relatively stable under normal circumstances. However, due to the long-term use of the forging press, problems such as internal friction and loose parts of the machine tool may gradually appear, affecting the normal operation of the hydraulic system, resulting in continuous abnormalities in the monitored processing parameter data. Such abnormal data usually shows a certain deviation from the normal situation, but presents similar characteristics in its local area.

[0035] Based on this, the embodiment of the present invention iteratively clusters the historical operation data through an iterative self-organizing clustering algorithm, obtains different characteristic patterns in the distribution of historical data, compares the clustering results after each iteration, and analyzes the optimal clustering result after obtaining it.

[0036] By way of example, in an embodiment of the present invention, an iterative self-organizing clustering algorithm is used to obtain the cluster center of each cluster in a historical operation data set, including: using an iterative self-organizing clustering algorithm to obtain the initial cluster in the historical operation data set, and obtaining the possible degree to which the latest data point belongs to each initial cluster by the degree of deviation between the processing parameters corresponding to the latest data point and the processing parameters corresponding to the cluster center of the initial cluster, and taking the initial cluster corresponding to the maximum possible degree of the latest data point belonging to each cluster as the cluster where the data point is located, and determining the cluster center of each cluster.

[0037] The specific steps of obtaining the initial clusters in the historical operation data set by using the iterative self-organizing clustering algorithm can be implemented by the existing technology, and the embodiments of the present invention will not be described in detail here.

[0038] It can be understood that the cluster center of the cluster is also a data point, so it has corresponding values ​​of each processing parameter.

[0039] For example, in the embodiment of the present invention, the possibility of determining the latest data point belonging to each initial cluster cluster can be specifically referred to the following relationship: ; In the formula, Indicates that the i-th latest data point belongs to The probability of the initial clusters, Indicates the number of processing parameters corresponding to the data point, represents the value of the jth processing parameter in the i-th latest data point, Indicates The value of the jth processing parameter in the cluster center of the initial clusters, Indicates The standard deviation of the jth processing parameter of all data points in the initial clusters, represents the exponential function with base e, Represents the absolute value symbol.

[0040] In the above formula, Indicates the relationship between the i-th latest data point and the The cumulative sum of the differences in the processing parameters between the cluster centers of the initial clusters. The larger the value, the closer the difference between the i-th latest data point and the i-th latest data point is. The greater the difference between the cluster centers of the initial clusters, the farther the i-th latest data point is from the The cluster center of the initial cluster cluster, the corresponding data point belongs to the The smaller the value, the smaller the probability of the initial cluster; on the contrary, the smaller the value, the closer the i-th latest data point is to the i-th The smaller the difference between the cluster centers of the initial clusters, the closer the i-th latest data point is to the The cluster center of the initial cluster cluster, the corresponding data point belongs to the The greater the probability of the initial clusters.

[0041] Based on the above steps, data points with high similarity are divided into the same cluster, and the clusters are updated in real time according to the possibility that the latest data points belong to each initial cluster. In this way, as the latest data is continuously input, the patterns and structures in the data can be quickly identified to reflect the latest features of the data. Based on this clustering result, outliers or outliers that are significantly different from most data points can be identified, that is, continue to execute the following steps.

[0042] S2: The abnormal index of a cluster is obtained by subtracting the ratio of the number of data points in a cluster to the number of data points in the largest cluster from 1, and the normalized value of the product of the standard deviation of the Euclidean distance between each data point in the cluster and the cluster center and the abnormal index is recorded as the suspicious degree of the cluster.

[0043] After obtaining each cluster based on the above steps, the clusters that may have abnormalities can be determined based on the characteristics of the data points in each cluster. In the process of forging workpieces, in order to make the workpieces meet the relevant standard requirements, the corresponding processing parameters will be set according to the material standards, so that a large amount of normal data is generated during the production process and the processing parameters of normal data are relatively stable. If there is a problem inside the equipment that affects the normal operation of the hydraulic system, continuous abnormal data may be generated, and the distribution in the data set is unstable.

[0044] Based on this, the embodiment of the present invention determines the abnormality degree of the cluster by obtaining the relative size of each cluster and the standard deviation of the data in the cluster.

[0045] It can be understood that the size of the cluster is the number of data points contained in the cluster. The more data points contained in the cluster, the larger the cluster. The largest cluster is the cluster containing the largest number of data points.

[0046] For example, in the embodiment of the present invention, the suspicious degree of the cluster is determined, and the following relationship can be specifically referred to: ; In the formula, Indicates The suspiciousness of the clusters. Indicates The number of data points in a cluster, represents the number of data points in the largest cluster. Indicates The cluster centers of the clusters are The first The Euclidean distance between data points, Indicates The cluster centers of the clusters are The mean Euclidean distance between all data points in the clusters, Represents the normalization function.

[0047] In the above formula, It represents the abnormal index of the cluster. The smaller the cluster in the clustering result, the greater the possibility that the data in the cluster is abnormal discrete data. Therefore, The smaller the ratio of the number of data points in the first cluster to the number of data points in the largest cluster, the smaller the The fewer the number of data points in a cluster, the greater the abnormal index of the cluster.

[0048] Indicates The standard deviation of the Euclidean distance between each data point in a cluster and the cluster center. The larger the value, the greater the Euclidean distance between the data points in the cluster, and the more discrete the data points in the cluster are in spatial distribution.

[0049] In summary, the fewer the number of data points in a cluster and the more discrete the spatial distribution of the data points in the cluster, the greater the abnormality of the data points in the cluster, and the greater the suspiciousness of the corresponding cluster.

[0050] S3: Taking the extreme value of the collection time corresponding to the data point in the cluster as the credibility of the suspicious degree, so as to obtain the feature weight of the cluster.

[0051] It should be noted that the above steps cluster the processing parameters of each data point as samples to obtain the suspicious degree of the cluster. However, there is a time span between the sample processing parameter data, and the anomalies generated in the actual processing process appear as continuous abnormal data in the data set. Therefore, the abnormal data generated in a shorter time span is more likely to be generated by the system itself, and it appears in the cluster as concentrated occurrence in a short time.

[0052] Based on this, the embodiment of the present invention can more comprehensively evaluate the characteristics of each cluster by further obtaining the time span between data points in the cluster as the credibility of the suspicious degree of the cluster.

[0053] It can be understood that the range value of the collection time corresponding to the data points in the cluster is the time span in the cluster. The smaller the range value, the more concentrated the data points in the cluster appear in a short time.

[0054] By way of example, in an embodiment of the present invention, when determining the feature weight of a cluster, the range value of the cluster can be obtained by the difference between the maximum value and the minimum value at the collection time in the cluster, and the range value is used as the credibility of the suspicious degree; the normalized value of the ratio of the suspicious degree of the cluster to its credibility is used as the feature weight of the cluster.

[0055] Among them, if the time span of the data points in the cluster is more concentrated and the suspicious degree of the cluster is higher, it means that the cluster has generated a highly suspicious data cluster in a short period of time. When determining abnormal data based on the local outlier factor algorithm, compared with other clusters, the data features of this cluster need to be paid more attention, and the corresponding feature weight is also higher.

[0056] S4: Determine the local density of each data point using the local outlier factor algorithm, and record the ratio of the local density of the data point to the feature weight of the cluster where the data point is located as the weighted local density of the data point.

[0057] It should be noted that, based on the above steps, the data features and time spans in the clusters are respectively obtained, and the abnormal data set generated by the system abnormality can be accurately determined from each cluster. When the monitoring results of the data points are determined directly by the local density of the data points, such abnormal data may be regarded as normal data.

[0058] Based on this, the embodiment of the present invention performs weighted correction on the local density of data points in the clusters using the feature weights of each cluster obtained through the above steps, so that the final weighted local density takes into account both the local density distribution of the data points and the characteristics of the clusters in which the data points are located.

[0059] The specific step of determining the local density of each data point using the local outlier factor algorithm can be implemented by the existing technology, and will not be described in detail in the embodiment of the present invention.

[0060] For example, in the embodiment of the present invention, the weighted local density of the data point is determined, and the specific details can be referred to the following relationship: ; In the formula, represents the weighted local density of the ith data point, represents the local density of the ith data point, Represents the feature weight of the cluster where the i-th data point is located.

[0061] After weighted correction is performed on the local density of each data point based on the above steps, the abnormal data can be accurately obtained based on the corrected local density.

[0062] S5: Obtain the outlier factor of the data point through the weighted local density of the data point, and realize the workpiece processing data processing through the comparison result of the outlier factor and the preset threshold.

[0063] It should be noted that, by weighting the local density of each data point after weighted correction, the outlier factor of each data point can be accurately obtained, so that the continuous abnormal data and conventional abnormal data generated by the hydraulic system in the operating data set can be accurately obtained.

[0064] For example, in an embodiment of the present invention, the outlier factor of a data point is obtained by the weighted local density of the data point, including: taking the ratio of the weighted local density mean of the data point and other data points in its k-neighborhood to the weighted local density of the data point as the outlier factor of the data point.

[0065] Specifically, when obtaining other data points in the k-neighborhood of a data point, the k value can be preset to determine the Euclidean distance between the data point and other data points in the running data set, and the k data points with the smallest Euclidean distance are used as other data points in the k-neighborhood of the data point.

[0066] The k value may be set to 5; it may be set specifically according to actual needs, and the embodiment of the present invention does not impose too many restrictions on this.

[0067] By way of example, in an embodiment of the present invention, workpiece processing data processing is achieved by comparing the outlier factor with a preset threshold, including: a preset threshold; treating data points corresponding to outlier factors greater than the preset threshold as abnormal data points; and treating data points corresponding to outlier factors not greater than the preset threshold as normal data points.

[0068] The preset threshold value may be set to 1; it may be specifically set according to actual needs.

[0069] It can be understood that if the outlier factor of a data point is greater than a preset threshold, it means that the weighted local density of the data point is lower than the average weighted local density of other data points in its k-neighborhood, and the data point is an outlier abnormal data point.

[0070] Based on the above steps, each data point in the workpiece operation data set is processed to accurately obtain the abnormal monitoring results during the workpiece processing.

[0071] It can be seen that in an embodiment of the present invention, when processing workpiece processing data, a historical operation data set of workpiece processing can be obtained, the historical operation data set contains a number of data points composed of processing parameters, and the cluster center of each cluster in the historical operation data set is obtained by using an iterative self-organizing clustering algorithm; the abnormal index of the cluster is obtained by subtracting the ratio of the number of data points in a cluster to the number of data points in the largest cluster from 1, and the normalized value of the product of the Euclidean distance standard deviation of each data point in the cluster and the cluster center and the abnormal index is recorded as the suspicious degree of the cluster; the extreme difference value at the acquisition time corresponding to the data point in the cluster is used as the credibility of the suspicious degree to obtain the characteristic weight of the cluster; the local density of each data point is determined by using a local outlier factor algorithm, and the ratio of the local density of the data point to the characteristic weight of the cluster where the data point is located is recorded as the weighted local density of the data point; the outlier factor of the data point is obtained by the weighted local density of the data point, and the workpiece processing data is realized by comparing the outlier factor with the preset threshold.

[0072] In this way, the embodiment of the present invention can obtain the abnormal monitoring results of workpiece processing through the local outlier factor algorithm. In this process, the embodiment of the present invention takes into account that due to factors such as internal friction of the machine tool and loose parts, the hydraulic system may generate continuous abnormal processing parameter data, and the local outlier factor algorithm may identify such continuous abnormal data as normal data. Based on this, the embodiment of the present invention iteratively clusters the historical operation data, obtains the time span of the data points in the cluster cluster and the suspicious degree of the cluster cluster to determine its feature weight, and corrects the local density obtained by the local outlier factor algorithm through the feature weight, which can accurately identify the abnormal data in the operation data set, thereby effectively improving the accuracy of workpiece processing abnormality monitoring.

[0073] An embodiment of the present invention further discloses a workpiece processing data processing system, including a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, a workpiece processing data processing method provided by the present invention is implemented.

[0074] 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.

[0075] In the present invention, the aforementioned memory may be any tangible medium containing or storing a program that can be used by or in combination 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 RRAM, a dynamic random access memory DRAM, a static random access memory SRAM, an enhanced dynamic random access memory EDRAM, a high bandwidth memory HBM, a hybrid memory cube HMC, 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 a device or accessible or connectable to a device.

[0076] 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.

[0077] 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 workpiece processing data processing method, It is characterized in that include: Acquire a historical operation data set of workpiece processing, wherein the historical operation data set includes a number of data points composed of processing parameters, and use an iterative self-organizing clustering algorithm to obtain a cluster center of each cluster in the historical operation data set; The abnormal index of the cluster is obtained by subtracting the ratio of the number of data points in a cluster to the number of data points in the largest cluster from 1, and the normalized value of the product of the Euclidean distance standard deviation of each data point in the cluster and the cluster center and the abnormal index is recorded as the suspicious degree of the cluster; The extreme value of the collection time corresponding to the data point in the cluster is used as the credibility of the suspicious degree to obtain the feature weight of the cluster; The local density of each data point is determined using the local outlier factor algorithm, and the ratio of the local density of the data point to the feature weight of the cluster where the data point is located is recorded as the weighted local density of the data point; The outlier factor of the data point is obtained by the weighted local density of the data point, and the workpiece processing data is processed by comparing the outlier factor with the preset threshold.

2. A workpiece processing data processing method according to claim 1, It is characterized in that The acquisition of the historical operation data set of the workpiece processing also includes: The acquisition frequency is preset, and the value of each processing parameter obtained at each acquisition moment is taken as a data point. After preprocessing all data points, they are arranged in time series to obtain the historical operation data set.

3. A workpiece processing data processing method according to claim 2, It is characterized in that The method of obtaining the cluster center of each cluster in the historical operation data set by using an iterative self-organizing clustering algorithm includes: The iterative self-organizing clustering algorithm is used to obtain the initial clustering clusters in the historical operation data set. The degree of deviation between the processing parameters corresponding to the latest data point and the processing parameters corresponding to the cluster center of the initial clustering cluster is used to obtain the possibility that the latest data point belongs to each initial clustering cluster. The initial clustering cluster corresponding to the maximum possibility of the latest data point belonging to each clustering cluster is taken as the clustering cluster where the data point is located, and the cluster center of each clustering cluster is determined.

4. A workpiece processing data processing method according to claim 3, It is characterized in that The probability that the latest data point belongs to each initial cluster satisfies the relationship: ； In the formula, Indicates that the i-th latest data point belongs to The probability of the initial clusters, Indicates the number of processing parameters corresponding to the data point, represents the value of the jth processing parameter in the i-th latest data point, Indicates The value of the jth processing parameter in the cluster center of the initial clusters, Indicates The standard deviation of the jth processing parameter of all data points in the initial clusters, represents the exponential function with base e, Represents the absolute value symbol.

5. A workpiece processing data processing method according to claim 1, It is characterized in that The method of taking the extreme difference value of the collection time corresponding to the data point in the cluster as the credibility of the suspicious degree to obtain the feature weight of the cluster includes: The normalized value of the ratio of the suspicious degree of the cluster to its credibility is used as the feature weight of the cluster.

6. A workpiece processing data processing method according to claim 1, It is characterized in that The step of obtaining the outlier factor of the data point by weighted local density of the data point includes: The ratio of the weighted local density mean of the data point and other data points in its k-neighborhood to the weighted local density of the data point is taken as the outlier factor of the data point.

7. A workpiece processing data processing method according to claim 1, It is characterized in that The process of processing workpiece processing data by comparing the outlier factor with a preset threshold value includes: Preset threshold value; The data points whose outlier factors are greater than the preset threshold are regarded as abnormal data points; the data points whose outlier factors are not greater than the preset threshold are regarded as normal data points.

8. A workpiece processing data processing system, 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 workpiece processing data processing method according to any one of claims 1 to 7 is implemented.

Images