An Online Torque Detection Method and System for Screwdrivers

Abstract

The present application provides an online screwdriver torque detection method and system, which monitors the torque data of the screwdriver in real time during the screw tightening process; performs spatial conversion on the torque data according to preset spatial parameters to obtain a screw torque sequence, evaluates the neighborhood perturbation of the screw torque sequence to obtain multiple inter-window perturbation factors; generates a torque characteristic curve during the screw tightening process through the torque data, determines a predicted torque sequence during the screw tightening process based on the torque characteristic curve, and determines the data divergence degree of each torque data point in the torque data based on the predicted torque sequence; uses all the inter-window perturbation factors and the data divergence degree of each torque data point to determine all abnormal torque data points, and generates an abnormal torque detection report according to all the abnormal torque data points. By adopting the above solution, it is possible to monitor the abnormalities in the torque data in real time during the screw tightening process, achieve timely and reliable screw torque detection, and improve the production quality of products.

Description

Technical Field

[0001] This application relates to the technical field of torque monitoring. More specifically, this application relates to an online screwdriver torque detection method and system. Background Art

[0002] In modern industrial production, screwdrivers are widely used in various automated assembly lines to fasten components together to ensure the structural stability and reliability of products. Torque is one of the most important parameters in the screw tightening process, which is directly related to the assembly quality, service life, and safety of products. Therefore, online screwdriver torque detection has become an important part of quality control. The core objective of this system is to monitor the tightening torque data in real time during the operation of the screwdriver, ensure that it meets the preset process standards, and alarm or adjust in a timely manner when abnormalities occur, thereby improving production efficiency and reducing defective products.

[0003] However, in practical applications, the torque sensor must be able to measure the tightening torque in real time and accurately, while avoiding being affected by environmental interferences such as temperature changes, vibrations, electromagnetic interferences, etc. In addition, during the operation of the screwdriver, the torque data often changes dynamically, and high-speed rotation and impact forces may cause data fluctuations. Therefore, high-frequency data acquisition and intelligent algorithms are required to filter out noise to ensure the stability and reliability of the data. Therefore, how to monitor abnormalities in torque data in real time during the screw tightening process and achieve timely and reliable screw torque detection to improve the production quality of products is a problem faced by the industry. Summary of the Invention

[0004] This application provides an online screwdriver torque detection method and system, which can monitor abnormalities in torque data in real time during the screw tightening process, achieve timely and reliable screw torque detection, and improve the production quality of products.

[0005] In a first aspect, this application provides an online screwdriver torque detection method, and the detection method includes the following steps:

[0006] Monitor the torque data of the screwdriver in real time during the screw tightening process;

[0007] Perform spatial transformation on the torque data according to preset spatial parameters to obtain a screw torque sequence, and perform neighborhood perturbation evaluation on the screw torque sequence to obtain multiple inter-window perturbation factors during the screw tightening process;

[0008] Generate a torque characteristic curve during the screw tightening process through the torque data, determine a predicted torque sequence during the screw tightening process based on the torque characteristic curve, and determine the data anomaly trend of each torque data point in the torque data based on the predicted torque sequence;

[0009] Determine all abnormal torque data points during the screw tightening process using all the inter-window perturbation factors and the data heteroscedasticity of each torque data point, and generate an abnormal torque detection report based on all the abnormal torque data points.

[0010] Preferably, the torque data during the screw tightening process of the screwdriver is monitored in real time by a torque sensor.

[0011] Preferably, the spatial transformation of the torque data is performed according to preset spatial parameters to obtain the screw torque sequence, which specifically includes:

[0012] Determine the torque level and torque fluctuation during the screw tightening process based on the torque data;

[0013] Perform spatial mapping on the torque data using the torque level, the torque fluctuation, and the preset spatial parameters, and then obtain the screw torque sequence.

[0014] Preferably, perform neighborhood perturbation evaluation on the screw torque sequence to obtain multiple inter-window perturbation factors during the screw tightening process, which specifically includes:

[0015] Obtain a set data sliding window;

[0016] Determine the torque dependence based on the screw torque sequence;

[0017] Determine the screw torque data points included in each data sliding window in the screw torque sequence;

[0018] Perform neighborhood perturbation evaluation on the data sliding window based on the torque dependence, the screw torque data points included in the data sliding window, and the screw torque data points included in the adjacent data sliding window to obtain the inter-window perturbation factor of the data sliding window during the screw tightening process, and then obtain multiple inter-window perturbation factors during the screw tightening process.

[0019] Preferably, generate a torque characteristic curve during the screw tightening process from the torque data by using an exponential curve fitting algorithm to fit the torque data, and then generate a torque characteristic curve during the screw tightening process.

[0020] Preferably, determine the data heteroscedasticity of each torque data point in the torque data based on the predicted torque sequence, which specifically includes:

[0021] For each torque data point in the torque data, obtain the predicted torque corresponding to the torque data point in the predicted torque sequence;

[0022] Determine the data heteroscedasticity of the torque data point through the predicted torque, and then obtain the data heteroscedasticity of each torque data point in the torque data.

[0023] Preferably, all the abnormal torque data points during the screw tightening process are determined using all the inter-window disturbance factors and the data divergence of each torque data point, specifically including:

[0024] For each torque data point in the torque data, determine the inter-window disturbance factor corresponding to the torque data point;

[0025] Determine the data anomaly coefficient of the torque data point through the inter-window disturbance factor and the data divergence of the torque data point, and then obtain the data anomaly coefficients of each torque data point;

[0026] Take the torque data points with data anomaly coefficients greater than the set threshold as abnormal torque data points, and then obtain all the abnormal torque data points during the screw tightening process.

[0027] In a second aspect, the present application provides an on-line screw machine torque detection system for implementing an on-line screw machine torque detection method. The on-line screw machine torque detection system includes an anomaly detection unit, and the anomaly detection unit includes:

[0028] A torque monitoring module for real-time monitoring of the torque data of the screw machine during the screw tightening process;

[0029] A disturbance evaluation module for performing spatial conversion on the torque data according to preset spatial parameters to obtain a screw torque sequence, and performing neighborhood disturbance evaluation on the screw torque sequence, and then obtaining a plurality of inter-window disturbance factors during the screw tightening process;

[0030] An anomaly determination module for generating a torque characteristic curve during the screw tightening process through the torque data, determining a predicted torque sequence during the screw tightening process based on the torque characteristic curve, and determining the data divergence of each torque data point in the torque data based on the predicted torque sequence;

[0031] A report generation module for determining all the abnormal torque data points during the screw tightening process using all the inter-window disturbance factors and the data divergence of each torque data point, and generating an abnormal torque detection report according to all the abnormal torque data points.

[0032] In a third aspect, the present application provides a computer device, which includes a memory and a processor. The memory is used to store a computer program, and the processor is used to call and run the computer program from the memory, so that the computer device executes the above-mentioned on-line screw machine torque detection method.

[0033] Fourthly, the present application provides a computer-readable storage medium, in which instructions or codes are stored. When the instructions or codes run on a computer, the computer is enabled to execute the above-mentioned online screwdriver torque detection method when executed.

[0034] The technical solutions provided by the disclosed embodiments of the present application have the following beneficial effects:

[0035] In an online screwdriver torque detection method and system provided by the present application, torque data during the screw tightening process of the screwdriver is monitored in real time; the torque data is subjected to spatial conversion according to preset spatial parameters to obtain a screw torque sequence, and the neighborhood perturbation evaluation is performed on the screw torque sequence to obtain multiple window perturbation factors during the screw tightening process; a torque characteristic curve during the screw tightening process is generated through the torque data, a predicted torque sequence during the screw tightening process is determined based on the torque characteristic curve, and the data divergence degree of each torque data point in the torque data is determined based on the predicted torque sequence; all window perturbation factors and the data divergence degree of each torque data point are used to determine all abnormal torque data points during the screw tightening process, and an abnormal torque detection report is generated according to all the abnormal torque data points.

[0036] It can be seen that in the present application, firstly, the screw torque data is subjected to spatial conversion according to preset spatial parameters to obtain a screw torque sequence, and the window perturbation factor is calculated through neighborhood perturbation evaluation, which can help to more accurately capture abnormal fluctuations during the tightening process. By quantifying the local fluctuations of the torque data, the occurrence of torque abnormalities can be identified in a timely manner; secondly, by generating a torque characteristic curve during the screw tightening process and predicting the torque sequence based on this, the torque change trend during the normal tightening process can be accurately captured, and the data divergence degree of each torque data point is determined through the torque data and the predicted torque sequence, and abnormal fluctuations can be found in a timely manner; finally, by combining the window perturbation factor and the data divergence degree, the abnormal torque data points that occur during the screw tightening process can be detected more accurately, and then a detailed abnormal torque detection report is generated, providing effective support for quality control in the production process, being able to identify and correct abnormalities in a timely manner, avoiding the expansion of quality problems, and thus improving the overall production efficiency, product quality, and stability of equipment operation.

[0037] In summary, the technical solution adopted by the present application can monitor abnormalities in torque data in real time during the screw tightening process, realize timely and reliable screw torque detection, and improve the production quality of products. Brief Description of the Drawings

[0038] To more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0039] Figure 1 is an exemplary flowchart of an online screwdriver torque detection method according to some embodiments of the present application;

[0040] Figure 2 is an exemplary flowchart of determining the data divergence degree of each torque data point in the torque data according to some embodiments of the present application;

[0041] Figure 3 is an exemplary flowchart of determining all abnormal torque data points during the screw tightening process according to some embodiments of the present application;

[0042] Figure 4 is a schematic diagram of an exemplary hardware and / or software of an anomaly detection unit according to some embodiments of the present application;

[0043] Figure 5 is a schematic diagram of the structure of a computer device for implementing the online screwdriver torque detection method according to some embodiments of the present application. Detailed implementation manners

[0044] The following will clearly and completely describe the technical solutions in the embodiments of the present application in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, rather than all embodiments. Based on the embodiments of the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present application.

[0045] The embodiment of the present application provides an online screwdriver torque detection method and system. The core is to monitor the torque data of the screwdriver in real time during the screw tightening process; perform spatial transformation on the torque data according to preset spatial parameters to obtain a screw torque sequence, evaluate the neighborhood perturbation of the screw torque sequence, and then obtain multiple window perturbation factors during the screw tightening process; generate a torque characteristic curve during the screw tightening process through the torque data, determine a predicted torque sequence during the screw tightening process based on the torque characteristic curve, and determine the data divergence degree of each torque data point in the torque data based on the predicted torque sequence; use all the window perturbation factors and the data divergence degree of each torque data point to determine all abnormal torque data points during the screw tightening process, and generate an abnormal torque detection report according to all the abnormal torque data points. By adopting the above scheme, abnormalities in the torque data can be monitored in real time during the screw tightening process, and timely and reliable screw torque detection can be realized to improve the production quality of products.

[0046] To better understand the above technical solution, the following will describe the above technical solution in detail in combination with the accompanying drawings of the specification and specific implementation manners. Refer to Figure 1 , which is an exemplary flowchart of an online screwdriver torque detection method shown according to some embodiments of the present application. The online screwdriver torque detection method 100 mainly includes the following steps:

[0047] In step 101, the torque data of the screwdriver during the screw tightening process is monitored in real time.

[0048] Specifically, the torque data of the screwdriver during the screw tightening process can be monitored in real time through a torque sensor; in the present application, an automatic screwdriver is equipped with a radio frequency identification (RFID) tag or unit to uniquely identify each screwdriver. The RFID reading device installed in the detection system can scan the ID information of each screwdriver to ensure that the detected data matches the corresponding screwdriver. The torque sensor is installed on the screw hole to measure the torque during the screw tightening process in real time. When the screwdriver is working, the RFID reader will identify the ID information of the screwdriver, and at the same time, the torque sensor will monitor the tightening force of the screw in real time, that is, the torque data during the screw tightening process is obtained.

[0049] In step 102, perform spatial transformation on the torque data according to preset spatial parameters to obtain a screw torque sequence, evaluate the neighborhood perturbation of the screw torque sequence, and then obtain multiple window perturbation factors during the screw tightening process.

[0050] In some embodiments, performing spatial transformation on the torque data according to preset spatial parameters to obtain a screw torque sequence can be specifically implemented in the following manner, that is:

[0051] Determine the torque level and torque fluctuation degree during the screw tightening process according to the torque data;

[0052] Perform spatial mapping on the torque data using the torque level, the torque fluctuation degree, and a preset spatial parameter, and then obtain the screw torque sequence.

[0053] Specifically, first, the torque level and torque fluctuation degree during the screw tightening process can be determined according to the torque data. Among them, the torque level represents the average torque magnitude during the screw tightening process, and the torque fluctuation degree is an index indicating the degree of torque data fluctuation during the screw tightening process. In actual implementation, the average value of all torque data points in the torque data can be used as the torque level during the screw tightening process, and the standard deviation of all torque data points in the torque data can be used as the torque fluctuation degree during the screw tightening process. Then, the torque data can be spatially mapped using the torque level, the torque fluctuation degree, and a preset spatial parameter to obtain the screw torque sequence. Among them, the screw torque sequence is the representation of the torque data in a low-dimensional space, and this spatial parameter is a parameter used to control the degree of spatial mapping. In actual implementation, the spatial mapping can be represented in the following manner:

[0054] ;

[0055] Among them, represents the screw torque sequence, represents the torque data, represents the torque level, represents the torque fluctuation degree, k represents a preset spatial parameter, represents taking a specific value in the low-dimensional space. Through the above method, the spatial mapping can be completed, and then the screw torque sequence can be obtained.

[0056] In some embodiments, perform a neighborhood perturbation evaluation on the screw torque sequence to obtain multiple inter-window perturbation factors during the screw tightening process. Specifically, the following method can be adopted, that is:

[0057] Obtain a set data sliding window;

[0058] Determine the torque dependence according to the screw torque sequence;

[0059] Determine the screw torque data points included in each data sliding window in the screw torque sequence;

[0060] Based on the torque dependence, the screw torque data points included in the data sliding window and the screw torque data points included in the adjacent data sliding window, perform a neighborhood perturbation evaluation on the data sliding window to obtain the inter-window perturbation factor of the data sliding window during the screw tightening process, and then obtain multiple inter-window perturbation factors during the screw tightening process.

[0061] In specific implementation, first, a data sliding window needs to be defined. The data sliding window is a time window. In this application, the data sliding window contains n screw torque data points. The sliding step of the data sliding window is 1. In actual implementation, the sliding step of the data sliding window can also be set to other values, which is not limited here. Then, the torque dependence can be determined according to the screw torque sequence. Among them, the torque dependence represents the mutual dependence degree between the screw torque data points in the screw torque sequence. The covariance of all screw torque data points in the screw torque sequence can be used as the torque dependence. Furthermore, the screw torque data points included in each data sliding window in the screw torque sequence can be determined, that is, the screw torque data points included in the corresponding data sliding window in the screw torque sequence can be determined according to the position of each data sliding window. Finally, the neighborhood perturbation evaluation of the data sliding window can be carried out based on the torque dependence, the screw torque data points included in the data sliding window, and the screw torque data points included in the adjacent data sliding window, so as to obtain the window - to - window perturbation factor during the screw tightening process. Among them, the window - to - window perturbation factor represents the data perturbation degree between adjacent data sliding windows during the screw tightening process. In actual implementation, the window - to - window perturbation factor can be determined by the following formula: ;

[0062] Among them, represents the window - to - window perturbation factor during the screw tightening process of the data sliding window, n represents the total number of screw torque data points included in the data sliding window represents the j - th screw torque data point included in the data sliding window

[0063] represents the j - th screw torque data point included in the data sliding window, v represents the torque level of the screw torque sequence,

[0064] represents the torque dependence. Through the above method, the window - to - window perturbation factor corresponding to each data sliding window can be obtained, that is, multiple window - to - window perturbation factors during the screw tightening process can be obtained.

[0063] It should be noted that performing spatial transformation on the screw torque data according to the preset spatial parameters to obtain the screw torque sequence and calculating the window - to - window perturbation factor through neighborhood perturbation evaluation can help capture abnormal fluctuations during the tightening process more accurately. By quantifying the local fluctuations of the torque data, the occurrence of torque anomalies, such as too high or too low torque, can be identified in a timely manner, so as to provide real - time feedback.

[0064] In step 103, a torque characteristic curve during the screw tightening process is generated from the torque data. Based on the torque characteristic curve, a predicted torque sequence during the screw tightening process is determined. Based on the predicted torque sequence, the data divergence degree of each torque data point in the torque data is determined.

[0065] In some embodiments, generating a torque characteristic curve during the screw tightening process from the torque data is to fit the torque data using an exponential curve fitting algorithm, thereby generating a torque characteristic curve during the screw tightening process. Specifically, when implemented, a torque characteristic curve during the screw tightening process is generated by fitting. This torque characteristic curve can reflect the trend of torque change during the screw tightening process, especially the torque increase in the initial tightening stage, the stable stage in the middle of tightening, and the torque peak in the locking stage, etc. It can not only provide accurate prediction for the tightening process but also help detect abnormalities in the process in a timely manner.

[0066] In some embodiments, determining the predicted torque sequence during the screw tightening process based on the torque characteristic curve can be specifically implemented in the following manner, that is:

[0067] Each torque data point in the torque data is respectively input into the torque characteristic curve for prediction, and then the predicted torque corresponding to each torque data point is obtained;

[0068] A predicted torque sequence during the screw tightening process is constructed through the predicted torques corresponding to all torque data points.

[0069] Specifically, when implemented, first, each torque data point in the torque data can be respectively input into the torque characteristic curve for prediction, so as to obtain the predicted torque corresponding to each torque data point. In actual implementation, the predicted torque can be determined in the following manner: Among them, represents the predicted torque corresponding to the torque data point ; represents the i-th torque data point in the torque data, and A, B, and C represent the exponential fitting parameters of the torque characteristic curve. Through the above method, the predicted torque corresponding to each torque data point can be obtained. In actual implementation, the exponential fitting parameters can be set through historical experiments, which will not be elaborated here; then, a predicted torque sequence during the screw tightening process can be constructed through the predicted torques corresponding to all torque data points, that is, the predicted torques corresponding to all torque data points are arranged according to the time stamp, so as to obtain a predicted torque sequence during the screw tightening process.

[0070] Preferably, in some embodiments, referring to Figure 2As shown, this figure is an exemplary flowchart for determining the data divergence degree of each torque data point in the torque data in some embodiments of the present application. In this embodiment, determining the data divergence degree of each torque data point in the torque data based on the predicted torque sequence can be implemented by the following steps:

[0071] In step 1031, for each torque data point in the torque data, obtain the predicted torque corresponding to the torque data point in the predicted torque sequence;

[0072] In step 1032, determine the data divergence degree of the torque data point through the predicted torque, and then obtain the data divergence degree of each torque data point in the torque data.

[0073] Specifically, first, for each torque data point in the torque data, the predicted torque corresponding to the torque data point can be obtained in the predicted torque sequence by traversing; then, the data divergence degree of the torque data point can be determined through the predicted torque, where the data divergence degree represents the degree to which the torque data point tends to be abnormal. In actual implementation, the absolute value of the difference between the torque data point and its corresponding predicted torque can be calculated, and the result can be used as the data divergence degree of the torque data point. Through the above method, the data divergence degree of each torque data point in the torque data can be obtained.

[0074] It should be noted that by generating the torque characteristic curve during the screw tightening process and based on this predicted torque sequence, the torque change trend during the normal tightening process can be accurately captured. By determining the data divergence degree of each torque data point through the torque data and the predicted torque sequence, abnormal fluctuations can be detected in a timely manner, and problems such as too high or too low torque can be identified.

[0075] In step 104, use all the window disturbance factors and the data divergence degree of each torque data point to determine all the abnormal torque data points during the screw tightening process, and generate an abnormal torque detection report based on all the abnormal torque data points.

[0076] Preferably, in some embodiments, refer to Figure 3 As shown, this figure is an exemplary flowchart for determining all the abnormal torque data points during the screw tightening process in some embodiments of the present application. In this embodiment, using all the window disturbance factors and the data divergence degree of each torque data point to determine all the abnormal torque data points during the screw tightening process can be implemented by the following steps:

[0077] In step 1041, for each torque data point in the torque data, determine the window disturbance factor corresponding to the torque data point;

[0078] In step 1042, the data anomaly coefficient of the torque data point is determined by the data divergence degree between the window interval perturbation factor and the torque data point, and then the data anomaly coefficients of all torque data points are obtained;

[0079] In step 1043, the torque data points with data anomaly coefficients greater than the set threshold are taken as abnormal torque data points, and then all abnormal torque data points during the screw tightening process are obtained.

[0080] Specifically, when implemented, first, for each torque data point in the torque data, the window interval perturbation factor corresponding to the torque data point can be determined, that is, a data sliding window with this torque data point as the window center is determined, and the window interval perturbation factor corresponding to this data sliding window is taken as the window interval perturbation factor corresponding to this torque data point; then, the data anomaly coefficient of the torque data point can be determined by the window interval perturbation factor and the data divergence degree of the torque data point. Among them, this data anomaly coefficient represents the possible degree that the torque data point is abnormal data during the screw tightening process. The product of the data divergence degree of this torque data point and its corresponding window interval perturbation factor can be taken as the data anomaly coefficient of this torque data point. Through the above method, the data anomaly coefficients of all torque data points can be obtained; finally, the torque data points with data anomaly coefficients greater than the set threshold can be taken as abnormal torque data points. Among them, the threshold can be set according to historical experience and data analysis, which will not be elaborated here. Through the above method, all abnormal torque data points during the screw tightening process can be obtained.

[0081] In some embodiments, an abnormal torque detection report is generated according to all the abnormal torque data points; when specifically implemented, according to all the torque data points marked as abnormal, an abnormal torque detection report can be generated. Among them, this abnormal torque detection report includes:

[0082] List of abnormal data points: List all the torque data points marked as abnormal, as well as their corresponding time, torque value, window interval perturbation factor, and data divergence degree.

[0083] Analysis of abnormal causes: Based on the analysis of divergence degree and perturbation factor, possible abnormal causes are given, such as equipment failure, improper process, operation error, etc.

[0084] Impact assessment: Analyze the impact of abnormal data points on the overall production process or product quality, and evaluate whether it will lead to unqualified products.

[0085] Recommended measures: Put forward suggestions for the detected abnormal situations, such as adjusting the tightening process, checking the equipment, optimizing production parameters, etc.

[0086] Trend analysis: Analyze the abnormal trends during the tightening process to help identify potential systematic problems.

[0087] It should be noted that by combining the window disturbance factor and the data deviation degree, abnormal torque data points that occur during the screw tightening process can be detected more accurately, and then a detailed abnormal torque detection report can be generated, providing effective support for quality control in the production process, enabling timely identification and correction of abnormalities, avoiding the expansion of quality problems, and thus improving the overall production efficiency, product quality, and stability of equipment operation.

[0088] It can be seen that in this application, first, the screw torque data is spatially transformed according to preset spatial parameters to obtain a screw torque sequence, and the window disturbance factor is calculated through neighborhood disturbance evaluation, which can help capture abnormal fluctuations during the tightening process more accurately. By quantifying the local fluctuations of torque data, the occurrence of torque abnormalities can be identified in a timely manner; then, by generating a torque characteristic curve during the screw tightening process and predicting the torque sequence based on this, the torque change trend during the normal tightening process can be accurately captured. By determining the data deviation degree of each torque data point through the torque data and the predicted torque sequence, abnormal fluctuations can be discovered in a timely manner; finally, by combining the window disturbance factor and the data deviation degree, abnormal torque data points that occur during the screw tightening process can be detected more precisely, and then a detailed abnormal torque detection report can be generated, providing effective support for quality control in the production process, enabling timely identification and correction of abnormalities, avoiding the expansion of quality problems, and thus improving the overall production efficiency, product quality, and stability of equipment operation.

[0089] In summary, the technical solution adopted in this application can monitor abnormalities in torque data in real time during the screw tightening process, achieve timely and reliable screw torque detection, and improve the production quality of products.

[0090] In addition, on the other hand of this application, in some embodiments, this application provides an on-line screw machine torque detection system. The on-line screw machine torque detection system includes an abnormality detection unit. Refer to Figure 4 , this figure is a schematic diagram of exemplary hardware and / or software of the abnormality detection unit shown in some embodiments of this application. The abnormality detection unit 400 includes: a torque monitoring module 401, a disturbance evaluation module 402, an abnormality determination module 403, and a report generation module 404, which are described as follows:

[0091] The torque monitoring module 401. In this application, the torque monitoring module 401 is mainly used to monitor the torque data of the screw machine in real time during the screw tightening process;

[0092] The disturbance evaluation module 402. In this application, the disturbance evaluation module 402 is mainly used to perform spatial transformation on the torque data according to preset spatial parameters to obtain a screw torque sequence, and perform neighborhood disturbance evaluation on the screw torque sequence, and then obtain multiple window disturbance factors during the screw tightening process;

[0093] Anomaly determination module 403. In this application, the anomaly determination module 403 is mainly used to generate a torque characteristic curve during the screw tightening process through the torque data, determine a predicted torque sequence during the screw tightening process based on the torque characteristic curve, and determine the data divergence degree of each torque data point in the torque data based on the predicted torque sequence.

[0094] Report generation module 404. In this application, the report generation module 404 is mainly used to determine all abnormal torque data points during the screw tightening process using all the inter-window disturbance factors and the data divergence degree of each torque data point, and generate an abnormal torque detection report based on all the abnormal torque data points.

[0095] The above has introduced in detail the examples of the online screw machine torque detection method and system provided by the embodiments of this application. It can be understood that, in order to implement the above functions, the corresponding device includes the corresponding hardware structure and / or software module for executing each function. Those skilled in the art should easily realize that, combining the units and algorithm steps of each example described in the embodiments disclosed in this article, this application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a certain function is executed in the way of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this application.

[0096] In some embodiments, this application also provides a computer device, which includes a memory and a processor. The memory is used to store a computer program, and the processor is used to call and run the computer program from the memory, so that the computer device executes the above-mentioned online screw machine torque detection method.

[0097] In some embodiments, refer to Figure 5 , the dashed line in this figure indicates that this unit or module is optional. This figure is a schematic structural diagram of a computer device for the online screw machine torque detection method provided by the embodiments of this application. The online screw machine torque detection method described in the above embodiments can be implemented by Figure 5 the computer device shown. The computer device 500 includes at least one processor 501, a memory 502, and at least one communication unit 505. The computer device 500 can be a terminal device, a server, or a chip.

[0098] The processor 501 can be a general-purpose processor or a special-purpose processor. For example, the processor 501 can be a central processing unit (CPU), and the CPU can be used to control the computer device 500, execute software programs, and process the data of the software programs. The computer device 500 can also include a communication unit 505 for implementing signal input (reception) and output (transmission).

[0099] For example, the computer device 500 can be a chip, and the communication unit 505 can be the input and / or output circuit of the chip, or the communication unit 505 can be the communication interface of the chip, and the chip can be a component of a terminal device, a network device, or other devices.

[0100] For another example, the computer device 500 can be a terminal device or a server, and the communication unit 505 can be the transceiver of the terminal device or the server, or the communication unit 505 can be the transceiver circuit of the terminal device or the server.

[0101] The computer device 500 can include one or more memories 502, on which a program 504 is stored. The program 504 can be run by the processor 501 to generate instructions 503, enabling the processor 501 to execute the methods described in the above method embodiments according to the instructions 503. Optionally, data (such as a target audit model) can also be stored in the memory 502. Optionally, the processor 501 can also read the data stored in the memory 502, and this data can be stored at the same storage address as the program 504, or it can be stored at a different storage address from the program 504.

[0102] The processor 501 and the memory 502 can be set separately or integrated together. For example, they can be integrated on a system on chip (SOC) of a terminal device.

[0103] It should be understood that the steps of the above method embodiments can be completed by the logic circuit in hardware form or the instructions in software form in the processor 501. The processor 501 can be a central processor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), or other programmable logic devices. For example, discrete gate, transistor logic devices, or discrete hardware components.

[0104] Those skilled in the art should understand that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memory, CD-ROM, optical memory, etc.) containing computer-usable program code.

[0105] For example, in some embodiments, the present application also provides a computer-readable storage medium storing instructions or code, which, when run on a computer, cause the computer to implement the above-mentioned online screwdriver torque detection method.

[0106] Although the preferred embodiments of the present application have been described, those skilled in the art can make additional changes and modifications to these embodiments once they learn the basic creative concept. Therefore, the appended claims are intended to be construed as including the preferred embodiments as well as all changes and modifications falling within the scope of the present application.

[0107] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalent technologies, the present application is also intended to include these modifications and variations.

Claims

1. An online screw machine torque detection method, characterized in that: The detection method comprises the following steps: Real-time monitoring of the torque data of the screw machine during the screw tightening process; Performing spatial transformation on the torque data according to preset spatial parameters to obtain a screw torque sequence, performing neighborhood disturbance evaluation on the screw torque sequence, and then obtaining a plurality of inter-window disturbance factors during the screw tightening process; Generate a torque characteristic curve during the screw tightening process through the torque data, determine a predicted torque sequence during the screw tightening process according to the torque characteristic curve, and determine the data anomaly of each torque data point in the torque data based on the predicted torque sequence; All the inter-window disturbance factors and the data anomalies of each torque data point are used to determine all the abnormal torque data points during the screw tightening process, and an abnormal torque detection report is generated based on all the abnormal torque data points; Among them, the neighborhood disturbance evaluation is performed on the screw torque sequence to obtain multiple inter-window disturbance factors during the screw tightening process, which specifically include: Get the set data sliding window; determining a torque dependency according to the screw torque sequence; Determining the screw torque data points contained in each data sliding window in the screw torque sequence; Performing neighborhood disturbance evaluation on the data sliding window according to the torque dependence, the screw torque data points contained in the data sliding window and the screw torque data points contained in the adjacent data sliding window, obtaining an inter-window disturbance factor of the data sliding window during the screw tightening process, and then obtaining multiple inter-window disturbance factors during the screw tightening process, wherein the inter-window disturbance factor represents the degree of data disturbance between adjacent data sliding windows during the screw tightening process; Among them, all the abnormal torque data points in the screw tightening process are determined by using all the inter-window disturbance factors and the data anomaly of each torque data point, including: For each torque data point in the torque data, determining an inter-window disturbance factor corresponding to the torque data point; Determining the data anomaly coefficient of the torque data point by the inter-window disturbance factor and the data anomaly degree of the torque data point, wherein the product of the data anomaly degree of the torque data point and the corresponding inter-window disturbance factor is used as the data anomaly coefficient of the torque data point, thereby obtaining the data anomaly coefficient of each torque data point; The torque data points whose data abnormality coefficient is greater than the set threshold are taken as abnormal torque data points, and then all abnormal torque data points in the screw tightening process are obtained.

2. An online screw machine torque detection method as claimed in claim 1, characterized in that: The torque data of the screw machine during the screw tightening process is monitored in real time through the torque sensor.

3. The method for detecting torque of an online screw machine according to claim 1, characterized in that: The torque data is spatially transformed according to preset spatial parameters to obtain the screw torque sequence, which specifically includes: Determining the torque level and torque fluctuation during the screw tightening process according to the torque data; The torque level, the torque fluctuation and the preset spatial parameters are used to perform spatial mapping on the torque data, thereby obtaining a screw torque sequence.

4. The method for detecting torque of an online screw machine according to claim 1, characterized in that: Generating a torque characteristic curve during the screw tightening process through the torque data is to fit the torque data using an exponential curve fitting algorithm, thereby generating the torque characteristic curve during the screw tightening process.

5. The method for detecting torque of an online screw machine according to claim 1, characterized in that: Determining the data anomaly of each torque data point in the torque data based on the predicted torque sequence specifically includes: For each torque data point in the torque data, obtaining a predicted torque corresponding to the torque data point in the predicted torque sequence; The data anomaly of the torque data point is determined by the predicted torque, and then the data anomaly of each torque data point in the torque data is obtained.

6. An online screw machine torque detection system, used to perform an online screw machine torque detection method as claimed in any one of claims 1 to 5, the online screw machine torque detection system comprising an abnormality detection unit, characterized in that: The abnormality detection unit comprises: Torque monitoring module, used to monitor the torque data of the screw machine in real time during the screw tightening process; A disturbance evaluation module, used to perform spatial transformation on the torque data according to preset spatial parameters to obtain a screw torque sequence, perform neighborhood disturbance evaluation on the screw torque sequence, and further obtain multiple inter-window disturbance factors during the screw tightening process; an abnormality determination module, used to generate a torque characteristic curve in the screw tightening process through the torque data, determine a predicted torque sequence in the screw tightening process according to the torque characteristic curve, and determine the data anomaly of each torque data point in the torque data based on the predicted torque sequence; The report generation module is used to determine all abnormal torque data points in the screw tightening process using all inter-window disturbance factors and data anomalies of each torque data point, and generate an abnormal torque detection report based on all abnormal torque data points.

7. A computer device, characterized in that: The computer device includes a memory and a processor, the memory is used to store a computer program, and the processor is used to call and run the computer program from the memory, so that the computer device executes the online screw machine torque detection method described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores instructions or codes, and when the instructions or codes are executed on a computer, the computer implements the online screw machine torque detection method as described in any one of claims 1 to 5.

Images