Steel wire thread insert assembly detection system

Abstract

The invention discloses a steel wire thread insert assembly detection system, and belongs to the technical field of assembly detection. According to a preset assembly rotating speed curve of a current steel wire thread insert, first predicted time and second predicted time of the current steel wire thread insert are analyzed; the first predicted time and the second predicted time are the time of the current steel wire thread insert in a stable assembly stage and the time of the current steel wire thread insert in a thread insert tightening stage respectively, and then dividing the rotating speed change curve into a rotating speed stable trend time period and a rotating speed descending trend time period; the rotating speed stable trend time period and the rotating speed descending trend time period are compared with the first predicted time and the second predicted time respectively, whether the current assembly process of the wire thread insert is abnormal or not is evaluated, abnormal evaluation and judgment after assembly are achieved, the reliability of abnormal detection is improved, and then the assembly quality is guaranteed.

Description

Technical Field

[0001] The invention relates to the technical field of assembly detection, in particular to a wire screw assembly detection system. Background Art

[0002] In the automated assembly of wire thread inserts, the prior art only calibrates the parameters of the automated assembly tools to improve the assembly accuracy, but lacks abnormal evaluation and judgment after assembly, thus failing to ensure assembly quality. Summary of the invention

[0003] The present invention is to solve the technical problems existing in the prior art. The present invention provides a wire screw assembly detection system, comprising: The data acquisition module is used to collect the speed change curve of the current wire thread insert during the assembly process; An estimated time analysis module, used for analyzing a first estimated time and a second estimated time of the current wire thread insert according to a preset assembly speed curve of the current wire thread insert through a trained first deep learning module, wherein the first estimated time and the second estimated time are respectively the time taken by the current wire thread insert in a stable assembly stage and the time taken in a tightening stage of the thread insert; The abnormality analysis module is used to divide the speed change curve into a speed stable trend period and a speed decreasing trend period, and then compare the speed stable trend period and the speed decreasing trend period with the first estimated time and the second estimated time respectively to evaluate whether there is any abnormality in the current wire screw sleeve assembly process.

[0004] Furthermore, the speed change curve is divided into a speed stable trend period and a speed decreasing trend period, specifically: Using a trained second deep learning model, identifying a first curve segment belonging to a steady straight line fluctuation form and a second curve segment belonging to a descending curve fluctuation form in the speed change curve; The first curve segment is taken as the period of stable speed trend, and the second curve segment is taken as the period of decreasing speed trend.

[0005] Further, the speed steady trend period and the speed decreasing trend period are compared with the first estimated time and the second estimated time respectively to evaluate whether the current wire screw sleeve assembly process is abnormal, specifically: If the absolute value of the difference between the time taken during the stable speed trend period and the first estimated time taken is greater than or equal to the first preset value, or the absolute value of the difference between the time taken during the decreasing speed trend period and the second estimated time taken is greater than or equal to the second preset value, it is determined that an abnormality has occurred in the current assembly process of the wire screw sleeve.

[0006] Furthermore, the system also includes: An information acquisition module, used to acquire workpiece information of a workpiece to be assembled and screw sleeve information of a screw sleeve to be assembled; The thread insert recognition module is used to identify whether the current wire thread insert matches the currently assembled threaded hole based on the thread insert information and the workpiece information.

[0007] Furthermore, the screw sleeve identification module comprises: A screw thread image acquisition module is used to acquire a multi-view screw thread image of the current wire screw thread; An information analysis module is used to analyze the estimated information of the current wire thread insert according to the multi-view thread insert image, including the estimated diameter, estimated length and estimated thread width; The actual model matching module is used to analyze the actual screw sleeve model of the current wire screw sleeve according to the screw sleeve estimation information; The judgment module is used to judge whether the actual screw sleeve model of the current wire screw sleeve is the same as the matching screw sleeve model of the currently assembled threaded hole. If they are the same, the current wire screw sleeve matches the currently assembled threaded hole.

[0008] Furthermore, the multi-viewing screw sleeve image specifically includes a screw sleeve front view and a screw sleeve top view. The screw sleeve front view is an image taken directly facing the screw sleeve body, and the screw sleeve top view is an image taken directly facing the screw sleeve opening.

[0009] Furthermore, actual length reference marks are provided in both the front view and the top view of the screw sleeve.

[0010] Furthermore, the thread sleeve estimation information of the current wire thread sleeve is analyzed based on the multi-view thread sleeve image, specifically: Perform image preprocessing on the front view and top view of the screw sleeve; The thread sleeve texture features are extracted from the image through edge detection, and the thread sleeve estimation information of the current wire thread sleeve is analyzed based on the actual length reference mark through the thread sleeve texture features.

[0011] Furthermore, the actual screw sleeve model of the current wire screw sleeve is analyzed based on the screw sleeve estimation information, specifically: From the thread insert information, the actual caliber, actual length and actual thread width that are closest to the estimated caliber, estimated length and estimated thread width of the current wire thread insert are queried respectively, and the thread insert model corresponding to the closest actual caliber, actual length and actual thread width is used as the actual thread insert model of the current wire thread insert.

[0012] The present invention also provides a wire screw assembly detection method, comprising the following steps: Collect the speed change curve of the current wire thread insert during the assembly process; According to a preset assembly speed curve of the current wire thread insert, a first estimated time and a second estimated time of the current wire thread insert are analyzed by a trained first deep learning module, wherein the first estimated time and the second estimated time are respectively the time taken by the current wire thread insert in a stable assembly stage and the time taken in a tightening stage of the thread insert; The speed change curve is divided into a speed stable trend period and a speed decreasing trend period, and then the speed stable trend period and the speed decreasing trend period are compared with the first estimated time and the second estimated time respectively to evaluate whether there is any abnormality in the current assembly process of the wire screw sleeve.

[0013] Compared with the prior art, the present invention has the following beneficial effects: The present invention analyzes the first estimated time and the second estimated time of the current wire screw insert according to the preset assembly speed curve of the current wire screw insert, wherein the first estimated time and the second estimated time are respectively the time of the current wire screw insert in the stable assembly stage and the time of the screw insert in the tightening stage, and then divides the speed change curve into a speed stable trend period and a speed decreasing trend period, and compares the speed stable trend period and the speed decreasing trend period with the first estimated time and the second estimated time respectively, so as to evaluate whether the assembly process of the current wire screw insert is abnormal, realize abnormal evaluation and judgment after assembly, improve the reliability of abnormal detection and thus ensure assembly quality; Before abnormality detection, the present invention also analyzes the actual screw sleeve model of the current wire screw sleeve based on the screw sleeve estimation information, and determines whether the actual screw sleeve model of the current wire screw sleeve is the same as the matching screw sleeve model of the currently assembled threaded hole, completes the matching detection, and ensures the matching of the data used in subsequent abnormality detection, thereby ensuring the reliability of the abnormality detection results and guaranteeing the assembly quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention. In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0015] Figure 1 It is a structural diagram of a wire screw assembly detection system of the present invention. DETAILED DESCRIPTION

[0016] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0017] It should be noted that all directional indications (such as up, down, left, right, front, back, etc.) in the embodiments of the present invention are only used to explain the relative position relationship, movement status, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly.

[0018] In addition, the descriptions of "first", "second", etc. in the present invention are only used for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the ability of ordinary technicians in the field to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such a combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0019] Embodiment 1 See also Figure 1 As shown, the present invention provides a wire screw assembly detection system, which specifically includes: A data acquisition module, an estimated time analysis module and an abnormality analysis module, and a central processing unit that is connected to each module in communication.

[0020] The data acquisition module is used to collect the speed change curve of the current wire thread insert during the assembly process; The rotation speed variation curve is a curve with the rotation speed as the vertical axis and the time as the horizontal axis.

[0021] The speed variation curve of the current wire thread insert also represents the speed variation curve of the assembly tool.

[0022] In the automated wire screw assembly, the corresponding assembly speed curve will be set according to the screw insert model, which means that the time taken to assemble the same screw insert with the normal corresponding assembly speed curve is basically the same. The assembly is first performed at a stable speed, and this process is the steady assembly stage. When the assembly is almost completed, the speed will gradually decrease to zero, and this process is the screw insert tightening stage. The same screw insert is assembled with the normal corresponding assembly speed curve, and the time taken in the two stages is basically the same. If it is different, it means that the assembly is abnormal due to problems with the screw insert or the assembly tool, which may affect the assembly quality and efficiency.

[0023] The estimated time analysis module is used to analyze the first estimated time and the second estimated time of the current wire thread insert according to the preset assembly speed curve of the current wire thread insert through a trained first deep learning module. The first estimated time and the second estimated time are the time taken for the current wire thread insert in the stable assembly stage and the time taken for the tightening stage of the thread insert, respectively.

[0024] The first deep learning module is trained with a large number of different preset assembly speed curves as training samples. In the preset assembly speed curves used as training samples, labels for the stable assembly stage and the screw sleeve tightening stage are provided. The stable assembly stage and the screw sleeve tightening stage of the preset assembly speed curve are judged by identifying the label training, so as to identify the corresponding time of the two stages.

[0025] The abnormality analysis module is used to divide the speed change curve into a speed stable trend period and a speed decreasing trend period, and then compare the speed stable trend period and the speed decreasing trend period with the first estimated time and the second estimated time respectively to evaluate whether there is any abnormality in the current wire screw sleeve assembly process.

[0026] The speed change curve is divided into a speed stable trend period and a speed decreasing trend period, specifically: Using a trained second deep learning model, identifying a first curve segment belonging to a steady straight line fluctuation form and a second curve segment belonging to a descending curve fluctuation form in the speed change curve; The first curve segment is taken as the period of stable speed trend, and the second curve segment is taken as the period of decreasing speed trend.

[0027] The second deep learning model is trained with a large number of actual speed curves of wire thread sleeves as training samples, and morphological labels for smooth straight line fluctuation patterns and declining curve fluctuation patterns are provided in the actual speed curves used as training samples. During the training process, smooth straight line fluctuation pattern curves and declining curve fluctuation pattern curves are identified from the actual speed curves through the morphological labels, and then training is performed based on the fluctuation patterns corresponding to a large number of smooth straight line fluctuation pattern curves and declining curve fluctuation pattern curves, so as to obtain a second deep learning model that can analyze whether the curve belongs to a smooth straight line fluctuation pattern or a declining curve fluctuation pattern according to its fluctuation pattern.

[0028] The process of comparing the stable speed trend period and the decreasing speed trend period with the first estimated time and the second estimated time to evaluate whether the current wire screw sleeve assembly process is abnormal is as follows: If the absolute value of the difference between the time taken during the stable speed trend period and the first estimated time taken is greater than or equal to the first preset value, or the absolute value of the difference between the time taken during the decreasing speed trend period and the second estimated time taken is greater than or equal to the second preset value, it is determined that an abnormality has occurred in the current assembly process of the wire screw sleeve.

[0029] In some embodiments, the wire screw assembly detection system further includes: An information acquisition module, used to acquire workpiece information of a workpiece to be assembled and screw sleeve information of a screw sleeve to be assembled; The workpiece information includes: the number of threaded holes and the corresponding positions, hole diameters, thread depths in holes, thread widths in holes and matching thread insert models of each threaded hole; The screw sleeve information includes: screw sleeve model and corresponding actual diameter, actual length and actual thread width; It should be noted that the threaded holes in the workpiece are matched with different types of threaded sleeves according to their corresponding hole diameters, thread depths in the holes and thread widths in the holes, that is, the actual diameters, actual lengths and actual thread widths of the threaded sleeves are matched respectively.

[0030] A thread insert recognition module is used to identify whether the current wire thread insert matches the currently assembled threaded hole according to the thread insert information and the workpiece information; In some embodiments, the screw cap identification module includes: a screw cap image acquisition module, an information analysis module, an actual model matching module and a judgment module.

[0031] The thread sleeve image acquisition module is used to acquire multi-view thread sleeve images of the current wire thread sleeve; The information analysis module is used to analyze the estimated information of the current wire thread insert according to the multi-view thread insert image, including the estimated caliber, estimated length and estimated thread width; The actual model matching module is used to analyze the actual screw sleeve model of the current wire screw sleeve according to the screw sleeve estimation information; The judgment module is used to judge whether the actual screw sleeve model of the current wire screw sleeve is the same as the matching screw sleeve model of the currently assembled threaded hole. If they are the same, the current wire screw sleeve matches the currently assembled threaded hole.

[0032] The multi-view screw sleeve image specifically includes a screw sleeve front view and a screw sleeve top view, the screw sleeve front view is an image taken directly facing the screw sleeve body, and the screw sleeve top view is an image taken directly facing the screw sleeve mouth; Actual length reference marks are provided in both the front view and the top view of the screw sleeve. Specifically, when photographing the front view and the top view of the screw sleeve, a length measuring ruler is also photographed in the front view and the top view of the screw sleeve respectively as actual length reference marks.

[0033] The estimated information of the current wire screw insert is analyzed based on the multi-view screw insert image, including the estimated caliber, the estimated length and the estimated thread width, specifically: Perform image preprocessing on the front view and top view of the screw sleeve. Specifically, the functions provided by the image processing software library (such as OpenCV) can be used to perform grayscale, binarization, edge detection and other operations to remove image noise and highlight target features; The thread sleeve texture features are extracted from the image through edge detection, and the thread sleeve estimation information of the current wire thread sleeve is analyzed according to the actual length reference mark through the thread sleeve texture features, including the estimated diameter, estimated length and estimated thread width.

[0034] According to the estimated information of the screw sleeve, the actual screw sleeve model of the current wire screw sleeve is analyzed, specifically: From the thread insert information, the actual caliber, actual length and actual thread width that are closest to the estimated caliber, estimated length and estimated thread width of the current wire thread insert are queried respectively, and the thread insert model corresponding to the closest actual caliber, actual length and actual thread width is used as the actual thread insert model of the current wire thread insert.

[0035] Embodiment 2 The present invention also provides a wire screw assembly detection method, which specifically comprises the following steps: S1. Assembly abnormality identification steps: The assembly abnormality identification step comprises the following steps: T1, collecting the speed change curve of the current wire thread insert during the assembly process; T2, according to the preset assembly speed curve of the current wire thread insert, analyzing the first estimated time and the second estimated time of the current wire thread insert through the trained first deep learning module, wherein the first estimated time and the second estimated time are the time of the current wire thread insert in the stable assembly stage and the time of the screw insert tightening stage, respectively; T3. Divide the speed change curve into a speed stable trend period and a speed decreasing trend period, and then compare the speed stable trend period and the speed decreasing trend period with the first estimated time and the second estimated time respectively to evaluate whether there is any abnormality in the current assembly process of the wire screw sleeve.

[0036] The first deep learning module is trained with a large number of different preset assembly speed curves as training samples. In the preset assembly speed curves used as training samples, labels for the stable assembly stage and the screw sleeve tightening stage are provided. The stable assembly stage and the screw sleeve tightening stage of the preset assembly speed curve are judged by identifying the label training, so as to identify the corresponding time of the two stages.

[0037] The speed change curve is divided into a speed stable trend period and a speed decreasing trend period, specifically: Using a trained second deep learning model, identifying a first curve segment belonging to a steady straight line fluctuation form and a second curve segment belonging to a descending curve fluctuation form in the speed change curve; The first curve segment is taken as the period of stable speed trend, and the second curve segment is taken as the period of decreasing speed trend.

[0038] The second deep learning model is trained with a large number of actual speed curves of wire thread sleeves as training samples, and morphological labels for smooth straight line fluctuation patterns and declining curve fluctuation patterns are provided in the actual speed curves used as training samples. During the training process, smooth straight line fluctuation pattern curves and declining curve fluctuation pattern curves are identified from the actual speed curves through the morphological labels, and then training is performed based on the fluctuation patterns corresponding to a large number of smooth straight line fluctuation pattern curves and declining curve fluctuation pattern curves, so as to obtain a second deep learning model that can analyze whether the curve belongs to a smooth straight line fluctuation pattern or a declining curve fluctuation pattern according to its fluctuation pattern.

[0039] The process of comparing the stable speed trend period and the decreasing speed trend period with the first estimated time and the second estimated time to evaluate whether the current wire screw sleeve assembly process is abnormal is as follows: If the absolute value of the difference between the time taken during the stable speed trend period and the first estimated time taken is greater than or equal to the first preset value, or the absolute value of the difference between the time taken during the decreasing speed trend period and the second estimated time taken is greater than or equal to the second preset value, it is determined that an abnormality has occurred in the current assembly process of the wire screw sleeve.

[0040] Before step S1, the following step S0 is also included, namely, a screw sleeve matching identification step, which specifically includes the following steps: U1. Obtain workpiece information of a workpiece to be assembled and threaded sleeve information of a threaded sleeve to be assembled; The workpiece information includes: the number of threaded holes and the corresponding positions, hole diameters, thread depths in holes, thread widths in holes and matching thread insert models of each threaded hole; The screw sleeve information includes: screw sleeve model and corresponding actual diameter, actual length and actual thread width; U2. Identify whether the current wire thread insert matches the currently assembled threaded hole based on the thread insert information and the workpiece information.

[0041] Step U2 is specifically: Obtain multi-view thread insert images of the current wire thread insert; According to the multi-view thread insert image, the thread insert estimation information of the current wire thread insert is analyzed, including the estimated diameter, estimated length and estimated thread width; According to the estimated information of the thread insert, the actual thread insert model of the current wire thread insert is analyzed; It is determined whether the actual thread insert model of the current wire thread insert is the same as the matching thread insert model of the currently assembled threaded hole. If they are the same, the current wire thread insert matches the currently assembled threaded hole.

[0042] Embodiment 3 The present invention also provides an electronic device, including: a processor, a sending device, an input device, an output device and a memory. The processor can be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit, or one or more integrated circuits, and is used to execute relevant programs to implement the technical solution provided in the embodiment of the present application. The memory can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device or a random access memory (RAM), and is used to store computer program code. The computer program code includes computer instructions. When the processor executes the computer instructions, the electronic device executes a method as described in any of the above possible implementation methods.

[0043] Embodiment 4 The present invention also provides a computer-readable storage medium, in which a computer program is stored. The computer program includes program instructions. When the program instructions are executed by a processor of an electronic device, the processor executes a method as described in any possible implementation manner.

[0044] The beneficial effects of the present invention are: The present invention analyzes the first estimated time and the second estimated time of the current wire screw insert according to the preset assembly speed curve of the current wire screw insert, wherein the first estimated time and the second estimated time are respectively the time of the current wire screw insert in the stable assembly stage and the time of the screw insert in the tightening stage, and then divides the speed change curve into a speed stable trend period and a speed decreasing trend period, and compares the speed stable trend period and the speed decreasing trend period with the first estimated time and the second estimated time respectively, so as to evaluate whether the assembly process of the current wire screw insert is abnormal, realize abnormal evaluation and judgment after assembly, improve the reliability of abnormal detection and thus ensure assembly quality; Before abnormality detection, the present invention also analyzes the actual screw sleeve model of the current wire screw sleeve based on the screw sleeve estimation information, and determines whether the actual screw sleeve model of the current wire screw sleeve is the same as the matching screw sleeve model of the currently assembled threaded hole, completes the matching detection, and ensures the matching of the data used in subsequent abnormality detection, thereby ensuring the reliability of the abnormality detection results and guaranteeing the assembly quality.

[0045] In the description of the specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0046] In addition, each functional unit in each embodiment of the present application can be integrated into a processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of a software functional unit. If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including multiple instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method of each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, referred to as ROM), random access memory (RandomAccess Memory, referred to as RAM), disk or optical disk and other media that can store programs.

[0047] The foregoing is merely a specific embodiment of the present invention, which enables those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features claimed herein.

Claims

1. A wire screw assembly detection system, characterized in that: include: The data acquisition module is used to collect the speed change curve of the current wire thread insert during the assembly process; An estimated time analysis module, used for analyzing a first estimated time and a second estimated time of the current wire thread insert according to a preset assembly speed curve of the current wire thread insert through a trained first deep learning module, wherein the first estimated time and the second estimated time are respectively the time taken by the current wire thread insert in a stable assembly stage and the time taken in a tightening stage of the thread insert; The abnormality analysis module is used to divide the speed change curve into a speed stable trend period and a speed decreasing trend period, and then compare the speed stable trend period and the speed decreasing trend period with the first estimated time and the second estimated time respectively to evaluate whether there is any abnormality in the current wire screw sleeve assembly process.

2. The wire screw assembly detection system according to claim 1, characterized in that: The speed change curve is divided into a speed stable trend period and a speed decreasing trend period, specifically: Using a trained second deep learning model, identifying a first curve segment belonging to a steady straight line fluctuation form and a second curve segment belonging to a descending curve fluctuation form in the speed change curve; The first curve segment is taken as the period of stable speed trend, and the second curve segment is taken as the period of decreasing speed trend.

3. The wire screw assembly detection system according to claim 1, characterized in that: The process of comparing the stable speed trend period and the decreasing speed trend period with the first estimated time and the second estimated time to evaluate whether the current wire screw sleeve assembly process is abnormal is as follows: If the absolute value of the difference between the time taken during the stable speed trend period and the first estimated time taken is greater than or equal to the first preset value, or the absolute value of the difference between the time taken during the decreasing speed trend period and the second estimated time taken is greater than or equal to the second preset value, it is determined that an abnormality has occurred in the current assembly process of the wire screw sleeve.

4. The wire screw assembly detection system according to claim 1, characterized in that: The system also includes: An information acquisition module, used to acquire workpiece information of a workpiece to be assembled and screw sleeve information of a screw sleeve to be assembled; The thread insert recognition module is used to identify whether the current wire thread insert matches the currently assembled threaded hole based on the thread insert information and the workpiece information.

5. The wire screw assembly detection system according to claim 4, characterized in that: The screw sleeve identification module comprises: A screw thread image acquisition module is used to acquire a multi-view screw thread image of the current wire screw thread; An information analysis module is used to analyze the estimated information of the current wire thread insert according to the multi-view thread insert image, including the estimated diameter, estimated length and estimated thread width; The actual model matching module is used to analyze the actual screw sleeve model of the current wire screw sleeve according to the screw sleeve estimation information; The judgment module is used to judge whether the actual screw sleeve model of the current wire screw sleeve is the same as the matching screw sleeve model of the currently assembled threaded hole. If they are the same, the current wire screw sleeve matches the currently assembled threaded hole.

6. The wire screw assembly detection system according to claim 5, characterized in that: The multi-view screw sleeve image specifically includes a screw sleeve front view and a screw sleeve top view. The screw sleeve front view is an image taken directly facing the screw sleeve body, and the screw sleeve top view is an image taken directly facing the screw sleeve mouth.

7. The wire screw assembly detection system according to claim 6, characterized in that: Actual length reference marks are provided in the front view and top view of the screw sleeve.

8. The wire screw assembly detection system according to claim 7, characterized in that: The thread sleeve estimation information of the current wire thread sleeve is analyzed based on the multi-view thread sleeve image, specifically: Perform image preprocessing on the front view and top view of the screw sleeve; The thread sleeve texture features are extracted from the image through edge detection, and the thread sleeve estimation information of the current wire thread sleeve is analyzed based on the actual length reference mark through the thread sleeve texture features.

9. The wire screw assembly detection system according to claim 5, characterized in that: According to the estimated information of the screw sleeve, the actual screw sleeve model of the current wire screw sleeve is analyzed, specifically: From the thread insert information, the actual caliber, actual length and actual thread width that are closest to the estimated caliber, estimated length and estimated thread width of the current wire thread insert are queried respectively, and the thread insert model corresponding to the closest actual caliber, actual length and actual thread width is used as the actual thread insert model of the current wire thread insert.

10. A wire screw assembly detection method, applied to the wire screw assembly detection system according to any one of claims 1 to 9, characterized in that: The following steps are involved: Collect the speed change curve of the current wire thread insert during the assembly process; According to a preset assembly speed curve of the current wire thread insert, a first estimated time and a second estimated time of the current wire thread insert are analyzed by a trained first deep learning module, wherein the first estimated time and the second estimated time are respectively the time taken by the current wire thread insert in a stable assembly stage and the time taken in a tightening stage of the thread insert; The speed change curve is divided into a speed stable trend period and a speed decreasing trend period, and then the speed stable trend period and the speed decreasing trend period are compared with the first estimated time and the second estimated time respectively to evaluate whether there is any abnormality in the current assembly process of the wire screw sleeve.

Images