Numerical control machine tool networking monitoring system and method based on data platform

Abstract

The invention relates to the technical field of numerical control machine tool monitoring, and discloses a numerical control machine tool networking monitoring system and method based on a data platform, and the system comprises a detection part which is disposed in a numerical control machine tool, and the detection part comprises a vibration sensor, a temperature sensor, a noise detection sensor, and a data collection module. The monitoring part is electrically connected with the detection part, and the monitoring part comprises an acquisition module, an evaluation module and a communication module. According to the method, clustering and difference analysis are performed through multi-sensor data acquisition and Gaussian mixture model analysis in combination with the model and operation data of the numerical control machine tool, so that efficient and accurate abnormal data detection and real-time early warning are realized, and the monitoring precision and fault response capability of the numerical control machine tool are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of CNC machine tool monitoring, and in particular to a CNC machine tool networking monitoring system and method based on a data platform. Background Art

[0002] With the rapid development of Industry 4.0 and intelligent manufacturing, CNC machine tools, as core equipment of industrial production, have become the key link in improving production efficiency and equipment reliability in terms of operating status monitoring and management. Traditional CNC machine tool monitoring mainly relies on regular inspections and manual maintenance, but this method cannot detect potential faults in equipment operation in a timely manner, which can easily lead to unexpected downtime and high maintenance costs. In addition, with the diversification of types and models of CNC machine tools, their operating status has significant individual differences, which makes unified fault monitoring and management more complicated.

[0003] At present, many CNC machine tool monitoring systems use single sensor data or fixed rules for fault judgment, which makes it difficult to fully capture the multi-dimensional information of machine tool operation, especially under the combined effects of multiple factors such as vibration, temperature, and noise, the accuracy of identifying abnormal behavior of equipment is low. In addition, existing systems generally lack in-depth analysis of the operating characteristics of machine tools of different models, and fail to establish adaptive models based on the operating characteristics of various types of machine tools, resulting in insufficient sensitivity and robustness of anomaly detection. At the same time, the early warning information transmission and response mechanism after anomaly detection is not efficient enough to meet the needs of smart factories for real-time monitoring and rapid fault handling.

[0004] Therefore, there is an urgent need to invent a unified supervision technology for CNC machine tools to solve the problems that the existing CNC machine tool monitoring system is difficult to comprehensively capture multi-dimensional operation information, lacks adaptive analysis of the characteristics of machine tools of different models, has insufficient accuracy and robustness in anomaly detection, and the early warning information transmission and response mechanism is not efficient enough. Summary of the invention

[0005] In view of this, the present invention proposes a networked monitoring system and method for CNC machine tools based on a data platform, aiming to solve the problems that the existing CNC machine tool monitoring system is difficult to comprehensively capture multi-dimensional operation information, lacks adaptive analysis of the characteristics of machine tools of different models, has insufficient accuracy and robustness in anomaly detection, and the early warning information transmission and response mechanism is not efficient enough.

[0006] The present invention proposes a networked monitoring system for CNC machine tools based on a data platform, comprising:

[0007] A detection unit is arranged inside the CNC machine tool, and the detection unit includes a vibration sensor, a temperature sensor, a noise detection sensor and a data acquisition module;

[0008] A monitoring unit, electrically connected to the detection unit, the monitoring unit comprising an acquisition module, an evaluation module and a communication module;

[0009] The acquisition module is respectively connected to the vibration sensor, the temperature sensor, the noise detection sensor and the operation data acquisition module based on the communication module, and the acquisition module is configured to acquire the operation data set detected by the detection unit when each of the CNC machine tools is in operation, wherein the operation data set includes the mechanical operation data and the electrical operation data detected by each sensor when the CNC machine tool is in operation;

[0010] An evaluation module is electrically connected to the communication module and the acquisition module, respectively, and the evaluation module is configured to cluster each of the CNC machine tools according to the model information of each of the CNC machine tools, determine the preset operation data in each cluster according to the operation data set of each of the CNC machine tools in the cluster, and determine the difference data between each of the CNC machine tools according to the relationship between the preset operation data and the operation data; the evaluation module is also configured to obtain the difference data threshold, filter each of the difference data according to the difference data threshold, obtain the abnormal value of the filtered data based on the Gaussian mixture model, and determine the abnormal data according to the abnormal value;

[0011] The communication module is communicatively connected to the detection platform, and the communication module is configured to send the comparison result between the abnormal data and the preset operation data to the detection platform and issue a message warning.

[0012] Furthermore, the evaluation module is further configured to obtain the difference data threshold, including:

[0013] The evaluation module is further configured to obtain the historical normal operation data of the CNC machine tool based on the communication module, and substitute the historical normal operation data into Formula I to obtain the difference data threshold, wherein Formula I is as follows:

[0014]

[0015] Among them, Y represents the difference data threshold, Represents the difference mean of historical normal operation data, represents the standard deviation of the historical normal operation data, and k represents the adjustment factor, where:

[0016] ;

[0017] ;

[0018] ;

[0019] Where Wt represents the data difference value of historical normal operation data, represents the operating data of the sensor at time t, represents the operating data of the sensor at time t-1, and N represents the number of historical normal operating data.

[0020] Further, the evaluation module is configured to cluster the CNC machine tools according to the model information of the CNC machine tools, and determine the preset operation data sets in each cluster according to the operation data sets of the CNC machine tools in the cluster, including:

[0021] Acquire the specifications and types of each of the CNC machine tools, and establish information association formulas for each of the CNC machine tools according to the specifications and types;

[0022] Obtaining a distance metric between each of the information association equations, and constructing a distance matrix according to the distance metric;

[0023] Iteratively clustering the information association formulas according to the distance matrix, and determining the information association formulas after iterative clustering as the types of the numerically controlled machine tools;

[0024] The operation data of each of the types of the numerically controlled machine tools is acquired, and the operation data set is established according to each of the operation data.

[0025] Furthermore, when the evaluation module establishes the operation data set according to each of the operation data, it includes:

[0026] The duplicate data in each of the operation data are removed, and each of the operation data after the duplicate data are removed is clustered, wherein:

[0027] Obtaining the maintenance time in the operation data, and determining clustered indicator data according to the relationship between the maintenance time and the preset time configured by the evaluation module;

[0028] When the maintenance time is less than or equal to the preset time, the evaluation module determines that the operation data is the indicator data;

[0029] When the maintenance duration is greater than the preset duration, the evaluation module determines that the operation data is not the indicator data;

[0030] The evaluation module is further configured to obtain a linear axis in each of the indicator data, and determine a median value of the linear axis as preset operation data of the type of the CNC machine tool;

[0031] The evaluation module is further configured to establish the operation data set according to preset operation data of each type of the CNC machine tools.

[0032] Furthermore, when the evaluation module determines the difference data between the numerically controlled machine tools according to the relationship between the preset operating data and the operating data, it includes:

[0033] The evaluation module is further configured to compare the operation data of the CNC machine tool with the preset operation data, and determine the difference data according to the comparison result;

[0034] When the operating data is consistent with the preset operating data, the evaluation module determines that the operating data is not the difference data;

[0035] When the operating data is inconsistent with the preset operating data, the evaluation module determines that the operating data is the difference data.

[0036] Furthermore, when the evaluation module screens each of the difference data according to the difference data threshold, it includes:

[0037] Compare the difference data with the difference data threshold, and remove small difference data;

[0038] When the difference data is greater than the difference data threshold, the evaluation module retains the difference data;

[0039] When the difference data is less than or equal to the difference data threshold, the evaluation module determines the difference data as small difference data and removes the difference data.

[0040] Furthermore, when obtaining outliers of the filtered data based on the Gaussian mixture model and determining the abnormal data according to the outliers, it includes:

[0041] Calculate the outlier value of each filtered data based on the Gaussian mixture model:

[0042] ;

[0043] in, Represents the outlier value of data x, K is the number of Gaussian components, π k Expressed as the mixing coefficient of the kth component, It is expressed as the probability density of data x belonging to a certain Gaussian component;

[0044] When the abnormal value of the screened data is greater than 0.8, the data is determined to be the abnormal data, and the numerical control machine tool corresponding to the abnormal data is identified.

[0045] Further, when the communication module is configured to send the comparison result between the abnormal data and the preset operation data to the detection platform, it includes:

[0046] The communication module is further configured to obtain difference data between the abnormal data and the preset operation data, and determine an alarm score of the abnormal data according to the difference data;

[0047] ;

[0048] Wherein, S is the alarm score of the abnormal data, N is the total number of the difference data, wi is the weight coefficient of the i-th difference data, Di is the i-th indicator data in the abnormal data, and di is the i-th indicator data in the preset operation data;

[0049] The communication module is also configured to determine an alarm level according to the alarm score, and generate alarm information according to the alarm level and difference data, and send the alarm information to the detection platform.

[0050] Further, the communication module is further configured to determine the alarm level according to the alarm score, including:

[0051] The communication module is further configured to determine the alarm level according to a relationship between the alarm score and a first preset alarm score and a second preset alarm score preconfigured in the communication module;

[0052] When the alarm score is less than the first preset alarm score, the communication module determines that the alarm level is a first warning level;

[0053] When the alarm score is greater than or equal to the first preset alarm score, and the alarm score is less than the second preset alarm score, the communication module determines that the alarm level is the second warning level;

[0054] When the alarm score is greater than or equal to the second preset alarm score, the communication module determines that the alarm level is the third warning level;

[0055] The first preset alarm score is less than the second preset alarm score, and the first warning level is lower than the second warning level and lower than the third warning level.

[0056] Compared with the prior art, the beneficial effect of the present invention is that multi-dimensional operation data including vibration, temperature, noise, etc. are collected through multi-sensor fusion technology, covering two important areas of mechanical operation and electrical operation, forming a comprehensive and detailed data foundation. The system uses efficient communication between the acquisition module and the sensor and data acquisition module to ensure the integrity and accuracy of real-time data. By associating the operation data set with the CNC machine tool model information, the evaluation module can perform cluster analysis on machine tools of different models, generate preset operation data in each cluster, and provide a reliable benchmark for subsequent anomaly detection. This data-driven approach makes up for the limitations of traditional methods and effectively improves the adaptability of the monitoring system to diversified equipment. In addition, the evaluation module performs outlier analysis on the screened difference data through a Gaussian mixture model, thereby accurately capturing abnormal patterns in complex and multi-dimensional data. The evaluation module eliminates non-critical data by screening the difference data threshold and focuses on key characteristics, thereby improving the accuracy and computational efficiency of anomaly detection. The communication module further enhances the applicability of the system. It can transmit the comparison results of abnormal data with the preset operating benchmark to the detection platform in a timely manner, and generate real-time warning information to help operators quickly identify and handle faults.

[0057] On the other hand, the present application also provides a CNC machine tool networking monitoring method based on a data platform, comprising:

[0058] Acquire an operation data set of the CNC machine tools detected when each of the CNC machine tools is in operation, wherein the operation data set includes mechanical operation data and electrical operation data detected by each sensor when the CNC machine tools are in operation;

[0059] Clustering the CNC machine tools according to the model information of the CNC machine tools, and determining the preset operation data in each cluster according to the operation data set of each CNC machine tool in the cluster;

[0060] Determining difference data between the numerically controlled machine tools according to the relationship between the preset operating data and the operating data;

[0061] Obtaining the difference data threshold, screening each difference data according to the difference data threshold, obtaining an outlier value of the screened data based on a Gaussian mixture model, and determining the outlier data according to the outlier value;

[0062] The comparison result between the abnormal data and the preset operation data is sent to the detection platform, and a message warning is issued.

[0063] It can be understood that the data platform-based networking monitoring system and method for CNC machine tools in the above-mentioned embodiments of the present invention have the same beneficial effects and will not be described in detail. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present invention. Moreover, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0065] Figure 1 A functional block diagram of a CNC machine tool networking monitoring system based on a data platform provided in an embodiment of the present invention;

[0066] Figure 2 A flowchart of a data platform-based CNC machine tool networking monitoring method provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0067] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided in order to enable a more thorough understanding of the present disclosure and to be able to fully convey the scope of the present disclosure to those skilled in the art. It should be noted that, in the absence of conflict, the embodiments of the present invention and the features described in the embodiments can be combined with each other. The present invention will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0068] like Figure 1 As shown, in some embodiments of the present application, this embodiment provides a networked monitoring system for CNC machine tools based on a data platform, including: a detection unit and a monitoring unit.

[0069] Specifically, the detection unit is arranged inside the CNC machine tool, and the detection unit includes a vibration sensor, a temperature sensor, a noise detection sensor and a data acquisition module. The monitoring unit is electrically connected to the detection unit, and the monitoring unit includes an acquisition module, an evaluation module and a communication module. The acquisition module is respectively connected to the vibration sensor, the temperature sensor, the noise detection sensor and the operation data acquisition module based on the communication module for communication, and the acquisition module is configured to acquire the operation data set detected by the detection unit when each CNC machine tool is running, wherein the operation data set includes the mechanical operation data and the electrical operation data when each sensor detects the operation of the CNC machine tool. The evaluation module is electrically connected to the communication module and the acquisition module respectively, and the evaluation module is configured to cluster each CNC machine tool according to the model information of each CNC machine tool, determine the preset operation data in each cluster according to the operation data set of each CNC machine tool in the cluster, and determine the difference data between each CNC machine tool according to the relationship between the preset operation data and the operation data. The evaluation module is also configured to obtain a difference data threshold, filter each difference data according to the difference data threshold, obtain the abnormal value of the filtered data based on the Gaussian mixture model, and determine the abnormal data according to the abnormal value. The communication module is connected to the detection platform for communication. The communication module is configured to send the comparison result between the abnormal data and the preset operation data to the detection platform and issue a message warning.

[0070] It can be seen that by integrating vibration sensors, temperature sensors, noise detection sensors and data acquisition modules inside the detection unit, the mechanical operation data and electrical operation data of the CNC machine tool during operation can be captured in real time. The sensors and data acquisition modules work together to ensure the comprehensiveness and accuracy of the operation data, overcoming the limitations of traditional single sensor monitoring. Secondly, the monitoring unit communicates with the sensors of the detection unit through the acquisition module to ensure the real-time acquisition of the operation data set of the CNC machine tool. Based on these data, the evaluation module combines the model information of the machine tool and groups the machine tools with similar operation characteristics through cluster analysis technology. This process generates preset operation benchmark data in different clusters, thereby realizing personalized monitoring of machine tools of different models. In this way, the evaluation module can analyze the specific operation characteristics of different machine tools without relying on a unified standard model, which improves the adaptability and accuracy of the system. In addition, the evaluation module calculates the difference data of each machine tool by comparing the operation data with the preset operation data, and screens the key data features based on the difference data threshold to eliminate redundant information. This not only reduces the complexity of data processing, but also improves the efficiency of anomaly detection. Furthermore, the evaluation module uses a Gaussian mixture model to detect outliers on the filtered data. The Gaussian mixture model is a probability-based unsupervised learning algorithm that can effectively capture potential abnormal patterns in the data. In this way, the system can accurately identify abnormal behaviors in machine tool operation and prevent the occurrence of potential faults. Finally, the comparison results of the abnormal data identified by the evaluation module and the preset operating benchmark are sent to the detection platform through the communication module, and early warning information is generated in real time. This real-time communication and early warning mechanism can not only promptly notify operators of potential machine tool failures, but also provide data support for subsequent maintenance decisions. Through this mechanism, the system greatly shortens the fault response time and reduces the risk of production interruption due to equipment abnormalities.

[0071] It is understandable that through multi-sensor fusion technology, the machine tool operation data is fully collected, including mechanical operation data (such as vibration, noise) and electrical operation data (such as temperature, etc.), to achieve real-time and accurate monitoring of the machine tool operation status. By acquiring efficient communication connections between the module and the sensor, the system can obtain complete and accurate operation data sets in real time, providing a reliable basis for subsequent analysis. The evaluation module uses cluster analysis to group machine tools of different models, and generates preset operation benchmarks based on the data within the group, accurately adapting to the operation characteristics of machine tools of different models, significantly improving the adaptability and accuracy of data analysis, thereby effectively improving the reliability and sensitivity of anomaly detection. In addition, by using the Gaussian mixture model to detect outliers on the screened difference data, potential operation anomalies can be accurately identified, greatly improving the system's fault warning capability. The communication module sends the detection results and abnormal information to the detection platform in real time, and generates message warnings to ensure that operators can respond quickly to potential problems and reduce production risks that may be caused by equipment failures.

[0072] Specifically, when the evaluation module is further configured to obtain a difference data threshold, the evaluation module includes: the evaluation module is further configured to obtain historical normal operation data of the CNC machine tool based on the communication module, and substitute the historical normal operation data into Formula I to obtain the difference data threshold, wherein Formula I is as follows:

[0073] ;

[0074] Among them, Y represents the difference data threshold, Represents the difference mean of historical normal operation data, represents the standard deviation of the historical normal operation data, and k represents the adjustment factor, where:

[0075] ;

[0076] ;

[0077] ;

[0078] Where Wt represents the data difference value of historical normal operation data, represents the operating data of the sensor at time t, represents the operating data of the sensor at time t-1, and N represents the number of historical normal operating data.

[0079] It is understandable that the evaluation module obtains the historical normal operation data of the CNC machine tool through the communication module, and uses these historical data to calculate the mean and standard deviation of the difference data. Specifically, the threshold value Y of the difference data is obtained by combining the difference mean and difference standard deviation of the historical normal operation data with the adjustment factor k. The adjustment factor can be adjusted according to the actual situation to ensure the adaptability and flexibility of the difference data threshold, and adapt to the changes of different machine tool types and operating conditions. Through this method, the evaluation module can dynamically determine the threshold value of the difference data based on historical data, and effectively compare it with the real-time operation data. When the real-time data deviates from the preset threshold, the system can quickly identify the anomaly and issue an early warning. The calculation of the difference data depends on the difference values ​​in the historical operation data, which are obtained by comparing the difference between the sensor data at each time point and the data at the previous moment, thereby effectively capturing the changes in the operating state of the machine tool.

[0080] Specifically, the evaluation module is configured to cluster each CNC machine tool according to the model information of each CNC machine tool, and determine the preset operation data set in each cluster according to the operation data set of each CNC machine tool in the cluster, including: obtaining the specifications and types of each CNC machine tool, and establishing the information association formula of each CNC machine tool according to the specifications and types. Obtaining the distance metric between each information association formula, and constructing a distance matrix according to the distance metric. Iteratively clustering each information association formula according to the distance matrix, and determining each information association formula after iterative clustering as the type of each CNC machine tool. Obtaining the operation data of each CNC machine tool in the type of CNC machine tool, and establishing an operation data set according to each operation data.

[0081] Specifically, when the evaluation module establishes an operation data set based on each operation data, it includes: clearing duplicate data in each operation data, and clustering each operation data after clearing duplicate data, wherein: obtaining the time to be maintained in the operation data, and determining the clustered indicator data based on the relationship between the time to be maintained and the preset time configured by the evaluation module: when the time to be maintained is less than or equal to the preset time, the evaluation module determines that the operation data is indicator data. When the maintenance time is greater than the preset time, the evaluation module determines that the operation data is not indicator data. The evaluation module is also configured to obtain the linear axis in each indicator data, and determine the median of the linear axis as the preset operation data of the type of CNC machine tool. The evaluation module is also configured to establish an operation data set based on the preset operation data of each type of CNC machine tool.

[0082] It can be understood that the evaluation module establishes information associations according to the specifications and types of CNC machine tools, calculates the similarity between each information association through distance measurement, and then constructs a distance matrix for iterative clustering. This process groups machine tools with similar characteristics, thereby realizing the identification and classification of different types of machine tools. In this way, the evaluation module can establish a preset operation data set that is more in line with the actual situation for different types of CNC machine tools, thereby improving the adaptability and accuracy of the operation data. In addition, the evaluation module also establishes an indicator data set based on the operation data of the CNC machine tools. In this process, the module first removes duplicate data in the operation data and clusters them according to the relationship between the maintenance time and the preset time. When the maintenance time meets the preset conditions, the relevant data will be marked as indicator data for further analysis. The evaluation module pays special attention to the linear axis data and sets the preset operation data for each type of CNC machine tool by determining its value. This not only ensures that the operation data of different types of machine tools can accurately reflect their status, but also enables the system to perform more effective anomaly detection and prediction based on these data, thereby improving the monitoring accuracy and decision support capabilities of the system.

[0083] Specifically, when the evaluation module determines the difference data between each CNC machine tool according to the relationship between the preset operation data and the operation data, it includes: the evaluation module is also configured to compare the operation data of the CNC machine tool with the preset operation data, and determine the difference data according to the comparison result: when the operation data is consistent with the preset operation data, the evaluation module determines that the operation data is not difference data. When the operation data is inconsistent with the preset operation data, the evaluation module determines that the operation data is difference data.

[0084] Specifically, when the evaluation module screens each difference data according to the difference data threshold, it includes: comparing the difference data with the difference data threshold and eliminating small difference data: when the difference data is greater than the difference data threshold, the evaluation module retains the difference data. When the difference data is less than or equal to the difference data threshold, the evaluation module determines the difference data as small difference data and eliminates the difference data.

[0085] Specifically, obtaining the outlier value of the filtered data based on the Gaussian mixture model and determining the abnormal data according to the outlier value includes: calculating the outlier value of each filtered data based on the Gaussian mixture model:

[0086] .

[0087] in, represents the outlier value of data x, K is the number of Gaussian components, πk represents the mixing coefficient of the kth component, It is expressed as the probability density of data x belonging to a certain Gaussian component. When the outlier value of the filtered data is greater than 0.8, the data is determined to be abnormal data, and the CNC machine tool corresponding to the abnormal data is identified.

[0088] It can be understood that the evaluation module compares the difference data with the preset difference data threshold. When the difference data is greater than the threshold, the difference data is retained; if it is less than or equal to the threshold, the data is considered to be small difference data and is eliminated. The purpose of this screening process is to reduce the noise in subsequent analysis by removing small or unimportant difference data, ensuring that the remaining data more accurately reflects the operating status of the machine tool. Next, based on the Gaussian mixture model (GMM), the evaluation module calculates the outliers of the filtered data. The Gaussian mixture model models the distribution of data through a combination of multiple Gaussian components. The probability density of each data point belonging to a Gaussian component is expressed as , where K is the number of components and πk is the mixing coefficient. By calculating the outlier value of each data point, if its outlier value is greater than 0.8, it is judged as abnormal data. This method effectively identifies abnormal data that is significantly different from the normal operating mode through statistical modeling, thereby achieving accurate anomaly detection of CNC machine tools.

[0089] Specifically, when the communication module is configured to send the comparison result between the abnormal data and the preset operation data to the detection platform, it includes: the communication module is also configured to obtain the difference data between the abnormal data and the preset operation data, and determine the alarm score of the abnormal data according to the difference data.

[0090] .

[0091] Among them, S is the alarm score of abnormal data, N is the total number of difference data, wi is the weight coefficient of the ith difference data, Di is the ith indicator data in the abnormal data, and di is the ith indicator data in the preset operation data. The communication module is also configured to determine the alarm level according to the alarm score, and generate alarm information according to the alarm level and the difference data, and send it to the detection platform.

[0092] Specifically, when the communication module is also configured to determine the alarm level according to the alarm score, it includes: the communication module is also configured to determine the alarm level according to the relationship between the alarm score and the first preset alarm score and the second preset alarm score pre-configured by the communication module: when the alarm score is less than the first preset alarm score, the communication module determines the alarm level to be the first warning level. When the alarm score is greater than or equal to the first preset alarm score, and the alarm score is less than the second preset alarm score, the communication module determines the alarm level to be the second warning level. When the alarm score is greater than or equal to the second preset alarm score, the communication module determines the alarm level to be the third warning level. Among them, the first preset alarm score is less than the second preset alarm score, and the first warning level is lower than the second warning level and lower than the third warning level.

[0093] It can be understood that the alarm score of the abnormal data is generated by calculating the difference data between the abnormal data and the preset operation data. The communication module calculates the alarm score of the abnormal data according to the weight coefficient of each type of difference data and the difference of the specific indicators. The weight coefficient wi in the formula is combined with the difference data Di and di to quantify the abnormal degree of each indicator, and calculate the final alarm score S according to the total amount of difference data N. In this way, the communication module can assign a quantitative alarm score to each abnormal data, thereby effectively distinguishing abnormalities of different degrees. Next, the communication module determines the alarm level according to the relationship between the alarm score and the preset alarm score threshold. This process sets predefined alarm levels for abnormal situations of different levels. When the alarm score is less than the first preset threshold, the alarm level is low; when the alarm score is between the two preset thresholds, the alarm level is medium; and when the alarm score is greater than the second threshold, the alarm level is the highest. This hierarchical mechanism enables the detection platform to take different response measures according to the alarm level and difference data, ensuring timely handling of abnormal conditions that may affect the operation of CNC machine tools, thereby improving the intelligence and response efficiency of the machine tool monitoring system.

[0094] In the above embodiment, multi-dimensional operation data including vibration, temperature, noise, etc. are collected through multi-sensor fusion technology, covering two important areas of mechanical operation and electrical operation, forming a comprehensive and detailed data foundation. The system uses efficient communication between the acquisition module and the sensor and data acquisition module to ensure the integrity and accuracy of real-time data. By associating the operation data set with the CNC machine tool model information, the evaluation module can perform cluster analysis on machine tools of different models, generate preset operation data in each cluster, and provide a reliable benchmark for subsequent abnormal detection. This data-driven approach makes up for the limitations of traditional methods and effectively improves the adaptability of the monitoring system to diversified equipment. In addition, the evaluation module performs outlier analysis on the screened difference data through a Gaussian mixture model, thereby accurately capturing abnormal patterns in complex and multi-dimensional data. The evaluation module eliminates non-critical data by screening the difference data threshold and focuses on key characteristics, thereby improving the accuracy and computational efficiency of abnormal detection. The communication module further enhances the applicability of the system, and can transmit the comparison results of abnormal data with the preset operation benchmark to the detection platform in a timely manner, and generate real-time warning information to help operators quickly identify and handle faults.

[0095] In another preferred embodiment based on the above embodiment, Figure 2 As shown, this embodiment provides a CNC machine tool networking monitoring method based on a data platform, including:

[0096] Step S100, obtaining an operation data set of each CNC machine tool detected when each CNC machine tool is in operation, wherein the operation data set includes mechanical operation data and electrical operation data detected by each sensor when the CNC machine tool is in operation.

[0097] Step S200: clustering the CNC machine tools according to the model information of the CNC machine tools, and determining the preset operation data in each cluster according to the operation data set of each CNC machine tool in the cluster.

[0098] Step S300: Determine the difference data between the numerically controlled machine tools according to the relationship between the preset operating data and the operating data.

[0099] Step S400: obtaining a difference data threshold, screening each difference data according to the difference data threshold, obtaining an outlier value of the screened data based on a Gaussian mixture model, and determining the abnormal data according to the outlier value.

[0100] Step S500: Send the comparison result between the abnormal data and the preset operation data to the detection platform, and issue a message warning.

[0101] It can be understood that the data platform-based networking monitoring system and method for CNC machine tools in the above-mentioned embodiments of the present invention have the same beneficial effects and will not be described in detail.

[0102] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0103] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems) and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0104] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0105] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0106] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A CNC machine tool networking monitoring system based on a data platform, characterized in that: include: A detection unit is arranged inside the CNC machine tool, and the detection unit includes a vibration sensor, a temperature sensor, a noise detection sensor and a data acquisition module; A monitoring unit, electrically connected to the detection unit, the monitoring unit comprising an acquisition module, an evaluation module and a communication module; The acquisition module is respectively connected to the vibration sensor, the temperature sensor, the noise detection sensor and the operation data acquisition module based on the communication module, and the acquisition module is configured to acquire the operation data set detected by the detection unit when each of the CNC machine tools is in operation, wherein the operation data set includes the mechanical operation data and the electrical operation data detected by each sensor when the CNC machine tool is in operation; An evaluation module is electrically connected to the communication module and the acquisition module, respectively, and the evaluation module is configured to cluster each of the CNC machine tools according to the model information of each of the CNC machine tools, determine the preset operation data in each cluster according to the operation data set of each of the CNC machine tools in the cluster, and determine the difference data between each of the CNC machine tools according to the relationship between the preset operation data and the operation data; the evaluation module is also configured to obtain the difference data threshold, filter each of the difference data according to the difference data threshold, obtain the abnormal value of the filtered data based on the Gaussian mixture model, and determine the abnormal data according to the abnormal value; The communication module is communicatively connected to the detection platform, and the communication module is configured to send the comparison result between the abnormal data and the preset operation data to the detection platform and issue a message warning.

2. The CNC machine tool networking monitoring system based on a data platform as claimed in claim 1, characterized in that: The evaluation module is further configured to obtain the difference data threshold, including: The evaluation module is further configured to obtain the historical normal operation data of the CNC machine tool based on the communication module, and substitute the historical normal operation data into Formula I to obtain the difference data threshold, wherein Formula I is as follows: ； Among them, Y represents the difference data threshold, Represents the difference mean of historical normal operation data, represents the standard deviation of the historical normal operation data, and k represents the adjustment factor, where: ； ； ； Where Wt represents the data difference value of historical normal operation data, represents the operating data of the sensor at time t, represents the operating data of the sensor at time t-1, and N represents the number of historical normal operating data.

3. The CNC machine tool networking monitoring system based on a data platform as claimed in claim 1, characterized in that: The evaluation module is configured to cluster the CNC machine tools according to the model information of the CNC machine tools, and determine the preset operation data sets in each cluster according to the operation data sets of the CNC machine tools in the cluster, including: Acquire the specifications and types of each of the CNC machine tools, and establish information association formulas for each of the CNC machine tools according to the specifications and types; Obtaining a distance metric between each of the information association equations, and constructing a distance matrix according to the distance metric; Iteratively clustering the information association formulas according to the distance matrix, and determining the information association formulas after iterative clustering as the types of the numerically controlled machine tools; The operation data of each of the types of the numerically controlled machine tools is acquired, and the operation data set is established according to each of the operation data.

4. The CNC machine tool networking monitoring system based on a data platform as claimed in claim 3 is characterized in that: When the evaluation module establishes the operation data set according to each of the operation data, it includes: The duplicate data in each of the operation data are removed, and each of the operation data after the duplicate data are removed is clustered, wherein: Obtain the maintenance time in the operation data, and determine clustered indicator data according to the relationship between the maintenance time and the preset time configured by the evaluation module: When the maintenance time is less than or equal to the preset time, the evaluation module determines that the operation data is the indicator data; When the maintenance duration is greater than the preset duration, the evaluation module determines that the operation data is not the indicator data; The evaluation module is further configured to obtain a linear axis in each of the indicator data, and determine a median value of the linear axis as preset operation data of the type of the CNC machine tool; The evaluation module is further configured to establish the operation data set according to preset operation data of each type of the CNC machine tools.

5. The data platform-based CNC machine tool networking monitoring system according to claim 4, characterized in that: When the evaluation module determines the difference data between the numerically controlled machine tools according to the relationship between the preset operation data and the operation data, it includes: The evaluation module is further configured to compare the operation data of the CNC machine tool with the preset operation data, and determine the difference data according to the comparison result: When the operating data is consistent with the preset operating data, the evaluation module determines that the operating data is not the difference data; When the operating data is inconsistent with the preset operating data, the evaluation module determines that the operating data is the difference data.

6. The data platform-based CNC machine tool networking monitoring system according to claim 5, characterized in that: When the evaluation module screens each of the difference data according to the difference data threshold, it includes: Compare the difference data with the difference data threshold, and remove small difference data: When the difference data is greater than the difference data threshold, the evaluation module retains the difference data; When the difference data is less than or equal to the difference data threshold, the evaluation module determines the difference data as small difference data and removes the difference data.

7. The data platform-based CNC machine tool networking monitoring system according to claim 6, characterized in that: Obtaining outliers of the filtered data based on the Gaussian mixture model, and determining the abnormal data according to the outliers, including: Calculate the outlier value of each filtered data based on the Gaussian mixture model: ； in, Represents the outlier value of data x, K is the number of Gaussian components, π k Expressed as the mixing coefficient of the kth component, It is expressed as the probability density of data x belonging to a certain Gaussian component; When the abnormal value of the screened data is greater than 0.8, the data is determined to be the abnormal data, and the numerical control machine tool corresponding to the abnormal data is identified.

8. The data platform-based CNC machine tool networking monitoring system according to claim 7, characterized in that: When the communication module is configured to send the comparison result between the abnormal data and the preset operation data to the detection platform, it includes: The communication module is further configured to obtain difference data between the abnormal data and the preset operation data, and determine an alarm score of the abnormal data according to the difference data; ； Wherein, S is the alarm score of the abnormal data, N is the total number of the difference data, wi is the weight coefficient of the i-th difference data, Di is the i-th indicator data in the abnormal data, and di is the i-th indicator data in the preset operation data; The communication module is also configured to determine an alarm level according to the alarm score, and generate alarm information according to the alarm level and difference data, and send the alarm information to the detection platform.

9. The data platform-based CNC machine tool networking monitoring system according to claim 8, characterized in that: The communication module is further configured to determine the alarm level according to the alarm score, including: The communication module is further configured to determine the alarm level according to a relationship between the alarm score and a first preset alarm score and a second preset alarm score preconfigured in the communication module: When the alarm score is less than the first preset alarm score, the communication module determines that the alarm level is a first warning level; When the alarm score is greater than or equal to the first preset alarm score, and the alarm score is less than the second preset alarm score, the communication module determines that the alarm level is the second warning level; When the alarm score is greater than or equal to the second preset alarm score, the communication module determines that the alarm level is the third warning level; The first preset alarm score is less than the second preset alarm score, and the first warning level is lower than the second warning level and lower than the third warning level.

10. A method for monitoring a CNC machine tool network based on a data platform, applicable to a CNC machine tool network monitoring system based on a data platform as claimed in any one of claims 1 to 9, characterized in that: include: Acquire an operation data set of the numerically controlled machine tools detected when each of the numerically controlled machine tools is in operation, wherein the operation data set includes mechanical operation data and electrical operation data detected by each sensor when the numerically controlled machine tools are in operation; Clustering the CNC machine tools according to the model information of the CNC machine tools, and determining the preset operation data in each cluster according to the operation data set of each CNC machine tool in the cluster; Determining difference data between the numerically controlled machine tools according to the relationship between the preset operating data and the operating data; Obtaining the difference data threshold, screening each difference data according to the difference data threshold, obtaining an outlier value of the screened data based on a Gaussian mixture model, and determining the outlier data according to the outlier value; The comparison result between the abnormal data and the preset operation data is sent to the detection platform, and a message warning is issued.

Images