Fault detection method, electronic device, and storage medium

Abstract

The application discloses a fault detection method, an electronic device and a storage medium, and relates to the technical field of data processing. The method comprises the following steps: determining a first current integral according to a corresponding sampling current of screw assembly, and determining a first torque-to-position time of the screw assembly; determining a first dynamic envelope image corresponding to the screw, wherein the first dynamic envelope image represents an image point corresponding to a qualified screw assembly; determining a first image point corresponding to the screw according to the first torque-to-position time and the first current integral, wherein the first image point is in the same plane coordinate image as the first dynamic envelope image; in response to the first image point corresponding to the screw of a continuous preset number of screws not being in the first dynamic envelope image, determining that a screw assembly device has a fault, and outputting preset alarm information. The application improves the accuracy of fault detection.

Description

Technical Field

[0001] This application relates to the field of data processing technology, and in particular to fault detection methods, electronic devices, and storage media. Background Technology

[0002] With the development of industrial automation, screw assembly lines primarily utilize screw-making machines, such as electric tightening tools, for automated screw assembly. However, during the screw assembly process, screw assembly faults (such as stripped threads, wear, and jamming) can occur, affecting the assembly quality. Currently, fault detection in screw assembly equipment relies on a single current peak threshold. However, due to dynamic load changes during screw assembly, the accuracy of fault detection is low, leading to false alarms.

[0003] Therefore, improving the accuracy of fault detection has become an urgent problem to be solved.

[0004] The above content is only used to help understand the technical solution of this application and does not represent an admission that the above content is prior art. Summary of the Invention

[0005] The main objective of this application is to provide a fault detection method, electronic device, and storage medium, aiming to solve the technical problem of how to improve the accuracy of fault detection.

[0006] To achieve the above objectives, this application proposes a fault detection method applied to screw assembly equipment, comprising the following steps: The first current integral is determined based on the sampling current corresponding to the screw assembly, and the first torque arrival time for the screw assembly is determined. Determine the first dynamic envelope image corresponding to the screw, wherein the first dynamic envelope image represents the image of the image point corresponding to the screw that has been assembled successfully; The first image point corresponding to the screw is determined based on the first torque arrival time and the first current integral, wherein the first image point and the first dynamic envelope image are in the same plane coordinate image; If the first image point corresponding to a series of preset screws is not within the first dynamic envelope image, it is determined that there is a fault in the screw assembly equipment, and a preset alarm message is output.

[0007] In one embodiment, after determining the first image point corresponding to the screw based on the first torque arrival time and the first current integral, the method includes: The torque arrival time threshold range and the current integration threshold range are determined based on the first dynamic envelope image; If the first torque arrival time is greater than the maximum value of the torque arrival time threshold range and the first current integral is within the current integral threshold range, then it is determined that there is a stripped screw assembly fault. If the first torque arrival time is within the torque arrival time threshold range and the first current integral is greater than the maximum value of the current integral threshold range, then it is determined that there is a wear fault in the screw assembly. If the first torque arrival time is greater than the maximum value of the torque arrival time threshold range, and the first current integral is greater than the maximum value of the current integral threshold range, then it is determined that there is a jamming fault in the screw assembly.

[0008] In one embodiment, the step of determining the torque arrival time threshold range and the current integration threshold range based on the first dynamic envelope image includes: Determine all second image points contained in the first dynamic envelope image, wherein the second image points include torque arrival time and current integral; Determine the maximum and minimum torque arrival times among all second image points, and use the time interval between the minimum and maximum torque arrival times as the torque arrival time threshold interval. Determine the maximum and minimum current integrals for the current integrals at all points in the second image, and use the integration interval between the minimum and maximum current integrals as the current integral threshold interval.

[0009] In one embodiment, the step of determining the first current integral based on the sampling current corresponding to the screw assembly includes: Multiple current samples are taken at a preset sampling frequency within the first time window of screw assembly to obtain multiple sampled currents. The start time of the first time window is the screw assembly start time, and the end time is the screw assembly completion time. The first current integral is obtained by integrating multiple sampled currents.

[0010] In one embodiment, the step of determining the first dynamic envelope image corresponding to the screw includes: Determine the first screw specification and model; Based on the preset mapping relationship between screw specifications and dynamic envelope images, the dynamic envelope image that matches the first screw specification is determined as the first dynamic envelope image from among a plurality of preset dynamic envelope images.

[0011] In one embodiment, the fault detection method further includes: Obtain the third image point of multiple preset samples in a planar coordinate image representing torque arrival time and current integral, wherein the multiple samples are screws of the same specification and model that have been assembled and qualified. Determine the point cloud image containing each third image point in the planar coordinate image; Two-dimensional Gaussian kernel density is calculated based on the point cloud image to obtain the probability density surface; The dynamic envelope image in the planar coordinate image is determined based on the probability density surface.

[0012] In one embodiment, the step of calculating a two-dimensional Gaussian kernel density based on a point cloud image to obtain a probability density surface includes: Determine the first standard deviation and first interquartile range of all third image points in the first dimension characterizing torque arrival time, and determine the second standard deviation and second interquartile range of all third image points in the second dimension characterizing current integral. The bandwidth is obtained by adaptive bandwidth calculation based on the first standard deviation, the first interquartile range, the second standard deviation, and the second interquartile range. For each third image point in the point cloud image, calculate the Euclidean distance between the third image point and other third image points, and calculate the probability density value of the third image point using the Euclidean distance and bandwidth based on the preset two-dimensional Gaussian kernel density function. The point cloud image is updated based on the probability density values ​​of each third image point in the point cloud image to obtain the probability density surface.

[0013] In one embodiment, the step of determining the dynamic envelope image in a planar coordinate image based on a probability density surface includes: Contour lines are determined based on the probability density values ​​of each image point in the probability density surface; wherein, the probability density values ​​of image points within the image region enclosed by the contour lines in the probability density surface are greater than the probability density values ​​of image points outside the image region enclosed by the contour lines. The boundary lines in the point cloud image are determined based on the contour lines, and the image region contained within the boundary lines is used as the dynamic envelope image.

[0014] In addition, to achieve the above objectives, this application also proposes an electronic device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the fault detection method described above.

[0015] In addition, to achieve the above objectives, this application also proposes a storage medium, which is a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the steps of the fault detection method described above.

[0016] In this application, when performing fault detection on a screw assembly device, the first torque arrival time for screw assembly and the first current integral determined based on the sampling current corresponding to the screw assembly can be determined first. This allows for comprehensive consideration of the first torque arrival time, which indirectly reflects the mechanical resistance during screw tightening, and the first current integral, which reflects the work done by the motor in the screw assembly device. This avoids the low accuracy that often occurs when using only a single parameter for fault prediction. Furthermore, a first dynamic envelope image corresponding to the screw is determined, representing the image points corresponding to a properly assembled screw. This enables accurate and effective fault detection through the intuitive method of the dynamic envelope image. The system determines the first image point corresponding to the screw based on the first torque arrival time and the first current integral. This first image point and the first dynamic envelope image are located in the same plane coordinate image. This allows the system to fuse the two physically complementary features of torque arrival time and current integral during screw assembly to form the first image point. The system analyzes the position of the first image point relative to the first dynamic envelope image to determine if there is a fault in the screw assembly. To further improve the accuracy of fault detection in the screw assembly equipment, the system will also detect a fault in the screw assembly equipment if the first image point corresponding to a consecutive preset number of screws is not within the first dynamic envelope image, and output a preset alarm message. This can be achieved through multiple tests, with a fault in the screw assembly equipment only confirmed when the first image point corresponding to a consecutive preset number of screws is not within the first dynamic envelope image. This comprehensively considers the dynamic load changes during screw assembly, avoids false alarms, and improves the accuracy of fault detection. Attached Figure Description

[0017] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0018] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 This is a flowchart illustrating the first embodiment of the fault detection method in this application; Figure 2 This is a flowchart illustrating the second embodiment of the fault detection method in this application; Figure 3 This is a flowchart illustrating the third embodiment of the fault detection method in this application; Figure 4This is a schematic diagram of the overall process of the fault detection method in this application; Figure 5 This is a schematic diagram of the device structure of the hardware operating environment involved in the fault detection method in this application embodiment.

[0020] The purpose, features, and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0021] It should be understood that the specific embodiments described herein are merely illustrative of the technical solutions of this application and are not intended to limit this application.

[0022] To better understand the technical solution of this application, a detailed description will be provided below in conjunction with the accompanying drawings and specific implementation methods.

[0023] With the development of industrial automation, screw assembly lines are increasingly demanding higher reliability and automation levels from electric screwdrivers. Currently, fault detection for screw assembly using electric screwdrivers relies on a single current peak threshold for fault judgment. However, this method cannot distinguish between stripped screws and short-term hard connections, resulting in a high false alarm rate. Furthermore, the current peak value used varies depending on the screw specifications and requires manual adjustment, leading to a large workload for on-site maintenance.

[0024] Therefore, to avoid the above-mentioned defects, this application provides a fault detection method to avoid false alarms caused by using a single current peak threshold for fault detection, thereby improving the accuracy of fault detection. It can automatically detect faults in electric tightening tools without the need for manual adjustment of relevant parameters, and can automatically use different working conditions.

[0025] Optionally, in the embodiments of this application, an algorithm chain that allows for fault detection can be embedded in the intelligent electric screwdriver controller within the screw assembly equipment, such as screw machine equipment (e.g., electric tightening tool). The main loop of this algorithm chain is a 1kHz polling sampling built into the controller. No additional hardware is required; fault detection is achieved solely by existing current sampling and the rotational speed pulse of the electronic device. Furthermore, tightening faults can be determined based on dynamic envelope images, which is the fault determination of the screw assembly equipment.

[0026] Based on this, embodiments of this application provide a fault detection method, referring to... Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the fault detection method of this application.

[0027] In this embodiment, the fault detection method includes steps S10 to S40.

[0028] Step S10: Determine the first current integral based on the sampling current corresponding to the screw assembly, and determine the first torque arrival time for the screw assembly. Optionally, embodiments of this application can be applied to screw assembly equipment, which can be an electronic device, such as an electric tightening tool, capable of assembling screws, such as tightening them.

[0029] Alternatively, screw assembly can be the process of assembling screws into target positions using screw assembly equipment, such as the process of tightening screws (i.e., screws) to target positions using an electric screwdriver (i.e., screw assembly equipment).

[0030] Optionally, the first torque arrival time can be the length of time from when the tightening action jams to when the torque sensor or clutch sends an arrival signal (such as a falling edge timestamp) during the current screw assembly process, that is, the duration from the start time of screw assembly to the completion time of screw assembly.

[0031] Optionally, the sampling current can be the current value obtained by periodically sampling the current in the screw assembly equipment during the screw assembly process.

[0032] Optionally, the first current integral can be the current integral obtained by integrating the sampled current.

[0033] Optionally, during screw assembly using the screw assembly equipment, the motor current can be sampled and integrated for each screw assembly process to obtain the first current integral. Simultaneously, after the screw is assembled in place, the moment the torque is reached is recorded to obtain the first torque arrival time.

[0034] Optionally, steps S10-S40 can be performed when the screw assembly equipment assembles each screw.

[0035] Optionally, in step S10, the step of determining the first current integral based on the sampling current corresponding to the screw assembly includes steps a10-a20.

[0036] Step a10: Within the first time window of screw assembly, perform multiple current samplings at a preset sampling frequency to obtain multiple sampled currents; Step a20: Integrate the multiple sampled currents to obtain the first current integral.

[0037] It should be noted that the first time window starts at the time the screw assembly begins and ends at the time the screw assembly is completed. For example, the first time window is the time range from when the screw starts tightening to when the screw is tightened to the target position.

[0038] Optionally, the preset sampling frequency can be the frequency at which the motor current of the screw assembly equipment is sampled by analog-to-digital conversion, such as once per millisecond.

[0039] Optionally, when performing fault detection on screw assembly in screw assembly equipment, current sampling is performed on the complete screw assembly process of any screw, and current sampling can be performed at a preset sampling frequency to obtain multiple sampled current values, i.e., sampled current.

[0040] Optionally, the integral can be calculated according to Formula 1 below. For example, the screw assembly start time, screw assembly completion time and sampling current can be input into Formula 1 for calculation, and the first current integral can be output.

[0041] Formula 1; Where a1 is the screw assembly completion time, such as 0.3s, which can be the integration termination time; a2 is the screw assembly start time, such as 0, which can be the integration start moment, such as the instant the screw tightening starts. This is for continuous summation operations; dt is the sampled current, which is the instantaneous current function that changes with time (in A); dt is the time element, corresponding to the sampling period in the discrete implementation. Q is the current integral (e.g., the first current integral), representing the accumulated charge within the 0.3s tightening time window, which is positively correlated with the motor's output power.

[0042] In this embodiment, for each screw assembly, multiple current samples are taken at a preset frequency within a first time window from the start time to the completion time of the screw assembly to obtain multiple sampled currents. The multiple sampled currents are then integrated to obtain a first current integral. This ensures that the obtained first current integral can fully reflect the motor's work in the complete screw assembly process, thus guaranteeing the accuracy and effectiveness of the obtained first current integral.

[0043] Step S20: Determine the first dynamic envelope image corresponding to the screw; It should be noted that the first dynamic envelope image represents the image point corresponding to the screw that has been assembled successfully. Furthermore, the first dynamic envelope image contains the image points corresponding to the screws that have been assembled successfully. The first dynamic envelope image can be a pre-constructed dynamic envelope image, and it can be a closed region, such as a polygonal region, in a planar coordinate image representing the torque arrival time-current integral of the screw assembly. This region includes a safe assembly area under normal assembly conditions, meaning that the screw assembly process corresponding to the image points within this region is successful and without faults.

[0044] Optionally, in step S20, the step of determining the first dynamic envelope image corresponding to the screw includes steps b10-b20.

[0045] Step b10: Determine the first screw specification and model. Step b20: Based on the preset mapping relationship between screw specifications and dynamic envelope images, determine the dynamic envelope image that matches the first screw specification from among the preset multiple dynamic envelope images as the first dynamic envelope image.

[0046] Optionally, the first screw specification can be the specification identifier of the screw currently used in the screw assembly equipment, such as an M3x6 screw specification identifier. Different screw specifications correspond to different dynamic envelope images.

[0047] Optionally, dynamic envelope images associated with screw assembly can be pre-constructed for multiple screw specifications and models to establish a mapping relationship between screw specifications and models and dynamic envelope images, with different dynamic envelope images corresponding to different screw specifications and models.

[0048] Optionally, based on this mapping relationship, a search can be performed among multiple pre-stored dynamic envelope images to determine the dynamic envelope image that matches the specification of the first screw, and this image can be used as the first dynamic envelope image.

[0049] In this embodiment, by selecting the first dynamic envelope image corresponding to the first screw specification model corresponding to the screw currently assembled, and the mapping relationship between the screw specification model and the dynamic envelope image, the first dynamic envelope image corresponding to it is selected from a plurality of pre-stored dynamic envelope images. This enables the screw specification model to be comprehensively considered when performing fault detection, thus ensuring the accuracy of the obtained first dynamic envelope image.

[0050] Step S30: Determine the first image point corresponding to the screw based on the first torque arrival time and the first current integral; It should be noted that the first image and the first dynamic envelope image are located in the same planar coordinate image. Furthermore, this planar coordinate image can be a two-dimensional coordinate system planar image with the torque arrival time as one coordinate axis and the current integral as another coordinate axis.

[0051] Optionally, the first image point can be a coordinate in a planar coordinate image containing the first dynamic envelope image, and the corresponding horizontal and vertical coordinates can be the first torque arrival time and the first current integral, for example, the horizontal coordinate is the first torque arrival time and the vertical coordinate is the first current integral; or, the vertical coordinate is the first torque arrival time and the horizontal coordinate is the first current integral.

[0052] In step S40, in response to the fact that the first image point corresponding to a series of preset screws is not within the first dynamic envelope image, it is determined that there is a fault in the screw assembly equipment, and preset alarm information is output.

[0053] Optionally, the consecutive preset number can be a consecutive counting threshold, such as two consecutive numbers.

[0054] Optionally, the screw assembly equipment can perform fault detection on the current screw assembly, obtain the corresponding first image point, and detect whether the first image point is within the range of the first dynamic envelope image. If not, in order to avoid misjudgment, the screw assembly equipment can be detected multiple times in a row. Each time fault detection is performed, the selected first dynamic envelope image does not necessarily have to be the same dynamic envelope image. The dynamic envelope image can be filtered according to the screw specifications and models being assembled.

[0055] Optionally, if the screw assembly equipment performs screw assembly multiple times in a row and the corresponding first image points are not within the first dynamic envelope image, it can be determined that the screw assembly equipment has failed to assemble screws multiple times in a row (e.g., the screws assembled in two consecutive attempts are faulty), and the assembled screws are faulty. In this case, it can be determined that the screw assembly equipment is faulty, and a pre-set alarm message (e.g., voice prompt, flashing light, etc.) is output, and the screw assembly operation is stopped.

[0056] In this embodiment, when performing fault detection on the screw assembly equipment, the first torque arrival time for screw assembly and the first current integral determined based on the sampling current corresponding to the screw assembly can be determined first. This allows for comprehensive consideration of the first torque arrival time, which indirectly reflects the mechanical resistance during screw tightening, and the first current integral, which reflects the work done by the motor in the screw assembly equipment. This avoids the low accuracy that often occurs when using only a single parameter for fault prediction. Furthermore, a first dynamic envelope image corresponding to the screw is determined, representing the image point where a properly assembled screw is located. This enables accurate and effective fault detection through the intuitive method of the dynamic envelope image. The system determines the first image point corresponding to the screw based on the first torque arrival time and the first current integral. This first image point and the first dynamic envelope image are located in the same plane coordinate image. This allows the system to fuse the two physically complementary features of torque arrival time and current integral during screw assembly to form the first image point. The system analyzes the position of the first image point relative to the first dynamic envelope image to determine if there is a fault in the screw assembly. To further improve the accuracy of fault detection in the screw assembly equipment, the system will also detect a fault in the screw assembly equipment if the first image point corresponding to a consecutive preset number of screws is not within the first dynamic envelope image, and output a preset alarm message. This can be achieved through multiple tests, with a fault in the screw assembly equipment only confirmed when the first image point corresponding to a consecutive preset number of screws is not within the first dynamic envelope image. This comprehensively considers the dynamic load changes during screw assembly, avoids false alarms, and improves the accuracy of fault detection.

[0057] Based on the first embodiment of this application, a second embodiment of this application is proposed. In this second embodiment, content that is the same as or similar to the above embodiment can be referred to the above description, and will not be repeated hereafter. Based on this, refer to... Figure 2 After step S30, which determines the first image point corresponding to the screw based on the first torque arrival time and the first current integral, steps c10-c40 are also included.

[0058] Step c10: Determine the torque arrival time threshold range and the current integration threshold range based on the first dynamic envelope image; Optionally, the torque arrival time threshold range can be the time interval between the minimum and maximum values ​​of the torque arrival time in the first dynamic envelope image, representing the range of torque arrival time allowed for normal screw assembly using screw assembly equipment.

[0059] Optionally, the current integration threshold interval can be the current integration interval between the minimum and maximum values ​​of the current integration in the first dynamic envelope image, representing the allowable current integration range for normal screw assembly using a screw assembly device.

[0060] Optionally, step c10, which involves determining the torque arrival time threshold range and the current integration threshold range based on the first dynamic envelope image, includes steps c11-c13.

[0061] Step c11: Determine all second image points contained in the first dynamic envelope image; It should be noted that the second image point includes the torque arrival time and the current integral.

[0062] Optionally, in a planar coordinate image containing a first dynamic envelope image, all image points contained in the first dynamic envelope image are determined and used as second image points.

[0063] Optionally, the screw assembly process corresponding to the second image point is a screw assembly process that is normal and qualified.

[0064] Step c12: Determine the maximum torque arrival time and minimum torque arrival time among all second image points, and use the time interval between the minimum torque arrival time and the maximum torque arrival time as the torque arrival time threshold interval. Optionally, the second image point with the maximum torque arrival time and the second image point with the minimum torque arrival time can be determined among the various second image points. The maximum torque arrival time and the minimum torque arrival time can also be the maximum torque arrival time and the minimum torque arrival time in the first dynamic envelope image. Therefore, the time interval between the minimum torque arrival time and the maximum torque arrival time can be used as the torque arrival time threshold interval.

[0065] Step c13: Determine the maximum and minimum current integrals of the current integrals among all the second image points, and use the integration interval between the minimum and maximum current integrals as the current integration threshold interval.

[0066] Optionally, the second image point with the maximum current integral and the second image point with the minimum current integral can be determined among the various second image points. The maximum and minimum current integrals can be the maximum and minimum current integrals in the first dynamic envelope image. Therefore, the integration interval between the minimum and maximum current integrals can be used as the current integration threshold interval.

[0067] In this embodiment, during fault detection, the torque arrival time threshold range and the current integration threshold range can be determined first. The maximum torque arrival time and the minimum torque arrival time in each second image point within the first dynamic envelope image can be comprehensively considered to determine the torque arrival time threshold range. Similarly, the maximum current integration and the minimum current integration in each second image point within the first dynamic envelope image can be comprehensively considered to determine the current integration threshold range. This ensures the accuracy and effectiveness of the determined torque arrival time threshold range and current integration threshold range.

[0068] Step c20: In response to the first torque arrival time being greater than the maximum value of the torque arrival time threshold range, and the first current integral being within the current integral threshold range, it is determined that there is a stripped screw assembly fault. Step c30: In response to the first torque arrival time being within the torque arrival time threshold range and the first current integral being greater than the maximum value of the current integral threshold range, it is determined that there is a wear fault in the screw assembly. In step c40, in response to the first torque arrival time being greater than the maximum value of the torque arrival time threshold interval and the first current integral being greater than the maximum value of the current integral threshold interval, it is determined that there is a jamming fault in the screw assembly.

[0069] Alternatively, stripped thread failure may be caused by damage to the screw threads or loss of threads on the workpiece to which the screw is assembled, resulting in the screw not being able to be tightened effectively. For example, the time it takes for the screw to reach the target position is significantly extended, but the required current is small.

[0070] Alternatively, wear failure can be caused by wear on the screw head, which leads to increased friction on the contact surface and requires greater torque to tighten. The driving current will increase significantly, but the tightening time will not change much.

[0071] Optionally, a jamming failure could be caused by a screw, such as a screw getting stuck, resulting in severe obstruction during the screwing process.

[0072] Optionally, the screw assembly equipment can perform fault detection for each screw assembly to determine whether the assembly was successful. Taking the current screw assembly as an example, a comprehensive judgment can be made from two dimensions: the torque arrival time and the current integral dimension, to determine whether the screw assembly is faulty and the type of fault.

[0073] Optionally, the first torque arrival time obtained during the current screw assembly can be compared with a torque arrival time threshold range determined based on the first dynamic envelope image. Furthermore, the first current integral obtained during the current screw assembly can be compared with a current integral threshold range determined based on the first dynamic envelope image. If the first torque arrival time is not within the torque arrival time threshold range but is greater than the maximum torque arrival time (i.e., the maximum torque arrival time), and the first current integral is within the current integral threshold range, a torque arrival time fault in the current screw assembly can be determined. If the current integral is normal, a stripped thread fault can be determined. If the first current integral is not within the current integral threshold range but is greater than the maximum current integral (i.e., the maximum current integral), and the first torque arrival time is within the torque arrival time threshold range, a current integral fault in the current screw assembly can be determined. If the torque arrival time is normal, a wear fault can be determined. When the first torque arrival time is not within the torque arrival time threshold range and is greater than the maximum value of the torque arrival time threshold, i.e., the maximum torque arrival time, and the first current integral is not within the current integral threshold range and is greater than the maximum value of the current integral threshold range, i.e., the maximum current integral, it can be determined that the current integral and torque arrival time of the current screw assembly are both faulty. At this time, it can be determined that there is a jamming fault in the current screw assembly.

[0074] In this embodiment, by comparing the first torque arrival time obtained based on the current screw assembly with the torque arrival time threshold range determined based on the first dynamic envelope image, and by comparing the first current integral obtained based on the current screw assembly with the current integral threshold range determined based on the first dynamic envelope image, it is determined whether there is a fault in the current screw assembly and the corresponding fault type, such as stripped thread fault, wear fault and jammed screw fault, thereby ensuring the accuracy of fault detection.

[0075] Based on the first or second embodiment of this application, a third embodiment of this application is proposed. In this third embodiment, content that is the same as or similar to the above embodiments can be referred to the above description, and will not be repeated hereafter. Based on this, refer to... Figure 3 The fault detection method also includes steps d10-d40.

[0076] Step d10: Obtain the third image point of multiple preset samples in the planar coordinate image representing the torque arrival time and current integral; It should be noted that multiple samples are screws of the same specification and model that have been assembled and are qualified. Optionally, the planar coordinate image can be the same as the planar coordinate image in the first embodiment, where the horizontal and vertical axes can be the torque arrival time and the current integral, respectively. Optionally, multiple planar coordinate images can be set, for example, one planar coordinate image corresponding to each screw specification.

[0077] Optionally, the third image point can be a coordinate in a planar coordinate image, similar to the first and second image points, and its horizontal and vertical coordinates can be represented by the torque arrival time and current integral of the sample.

[0078] Optionally, each sample has a corresponding third image point in the planar coordinate image.

[0079] Optionally, a dynamic envelope image corresponding to the screw assembly can be constructed for each type of screw specification and model, and steps d10-d40 can be executed each time the dynamic envelope image is constructed.

[0080] Step d20: Determine the point cloud image containing each third image point in the planar coordinate image; It should be noted that point cloud images can be a special type of grid image. A grid image can be a regular array of points, i.e., a grid, covering each point in a third image on a planar coordinate image.

[0081] Optionally, the discrete point cloud shape formed by the third image points of each sample in the planar coordinate image can be used as the point cloud image.

[0082] Step d30: Calculate the two-dimensional Gaussian kernel density based on the point cloud image to obtain the probability density surface; Optionally, the probability density surface can be a three-dimensional surface or a two-dimensional surface overlaid on a planar coordinate image, transformed from a point cloud image using two-dimensional Gaussian kernel density calculation. Furthermore, when it is a three-dimensional surface, the height of each image point on the probability density surface can be the probability density value of that image point.

[0083] Optionally, step d30, which involves calculating the two-dimensional Gaussian kernel density based on the point cloud image to obtain the probability density surface, includes steps d31-d34.

[0084] Step d31: Determine the first standard deviation and first interquartile range of all third image points in the first dimension representing the torque arrival time, and determine the second standard deviation and second interquartile range of all third image points in the second dimension representing the current integral. Optionally, the first dimension characterizing the torque arrival time and the second dimension characterizing the current integral can be the dimensions corresponding to the horizontal and vertical axes in a planar coordinate image.

[0085] Optionally, the torque arrival time and current integral of each third image point can be determined, and the standard deviation of the torque arrival time of each third image point can be calculated to obtain the first standard deviation, and the standard deviation of the current integral of each third image point can be calculated to obtain the second standard deviation.

[0086] Optionally, the interquartile range (IQR) can be the quartile difference, which is a statistical measure of the dispersion of data. It is calculated from the difference between the third quartile (e.g., the 75th quartile) and the first quartile (e.g., the 25th quartile).

[0087] Optionally, the first quartile interval can be the quartile interval of the torque arrival time at each of the third image points. The second quartile interval can be the quartile interval of the current integral at each of the third image points.

[0088] Step d32: Perform adaptive bandwidth calculation based on the first standard deviation, the first interquartile range, the second standard deviation, and the second interquartile range to obtain the bandwidth; Optionally, the bandwidth can be a parameter used to determine the probability density surface. A larger bandwidth results in a smoother probability density surface.

[0089] Optionally, the bandwidth can be obtained through Silverman adaptive scaling. The Silverman adaptive bandwidth is not fixed during batch processing and can automatically scale with the sample distribution. The bandwidth can be calculated using the following formula 2.

[0090] Formula 2; Where h is the bandwidth; IQR is the interquartile range (75th quantile - 25th quantile); For containing at least one sample The standard deviation of the sample set; Q is the current integral; The torque arrival time is denoted by n. n represents the number of samples, which can be multiple, such as 10.

[0091] Optionally, a bandwidth calculation can be performed to characterize the torque arrival time in the first dimension. The first standard deviation and the first interquartile range are input into Formula 2 to calculate the first bandwidth. A bandwidth calculation can also be performed to characterize the current integral in the second dimension to obtain the second bandwidth. The final bandwidth can be determined based on the first and second bandwidths. For example, the average of the first and second bandwidths can be used as the bandwidth for determining the probability density surface, or the minimum value between the first and second bandwidths can be selected as the bandwidth for determining the probability density surface.

[0092] Step d33: For each third image point in the point cloud image, calculate the Euclidean distance between the third image point and other third image points, and calculate the probability density value of the third image point using the Euclidean distance and bandwidth based on the preset two-dimensional Gaussian kernel density function. Step d34: Update the point cloud image based on the probability density values ​​of each third image point in the point cloud image to obtain the probability density surface.

[0093] Optionally, the preset two-dimensional Gaussian kernel density function can be a pre-set two-dimensional Gaussian kernel density function, such as shown in Formula 3 below.

[0094] Formula 3; Where kde(z) is the probability density value; n is the number of samples; Let z be the third image point and z be the third image point. The Euclidean distance between them, where i is a positive integer and the maximum value of i is n; h is the bandwidth.

[0095] Optionally, Equation 3 can be used to calculate the probability density values ​​between each third image point and other third image points in the point cloud image. For example, the Euclidean distance and bandwidth can be input into a two-dimensional Gaussian kernel density function to calculate the probability density values.

[0096] Optionally, the probability density value of each third image point in the point cloud image can be determined and used as the coordinate of the height coordinate axis of the third image point to update the point cloud image, thereby obtaining a probability density surface. For example, the three-dimensional coordinates of any image point in the probability density surface can be the torque arrival time, the current integral, and the probability density value, respectively.

[0097] In this embodiment, when constructing the dynamic envelope image, a corresponding dynamic envelope image can be created for each screw specification. Furthermore, during the creation of the dynamic envelope image, the point cloud image can be determined based on the third image point of the assembled screw in the planar coordinate image. When calculating the two-dimensional Gaussian kernel density of the point cloud image, the bandwidth can first be determined based on its corresponding standard deviation and interquartile range. Then, using the two-dimensional Gaussian kernel density function, its bandwidth, and the Euclidean distance between each third image point and other third image points, the probability density value is calculated. Finally, the point cloud image is updated based on the calculated probability density values ​​corresponding to each third image point to obtain a probability density surface, thereby ensuring the accuracy and effectiveness of the obtained probability density surface.

[0098] Step d40: Determine the dynamic envelope image in the planar coordinate image based on the probability density surface.

[0099] Optionally, after obtaining the probability density surface, the point cloud image in the planar coordinate image can be updated based on the probability density surface to obtain a dynamic envelope image. For example, the boundary line of the dynamic envelope image can be determined based on the probability density values ​​of each image point in the probability density surface, and the image region enclosed by the boundary line can be used as the dynamic envelope image.

[0100] Optionally, step d40, which involves determining the dynamic envelope image in the planar coordinate image based on the probability density surface, includes steps d41-d42.

[0101] Step d41: Determine the contour lines based on the probability density values ​​of each image point in the probability density surface; Step d42: Determine the boundary lines in the point cloud image based on the contour lines, and use the image region contained within the boundary lines as the dynamic envelope image.

[0102] Optionally, the probability density value of image points within the image region enclosed by contour lines in the probability density surface is greater than the probability density value of image points outside the image region enclosed by contour lines. Optionally, a contour line can be a closed curve in a probability density surface that connects image points with a preset probability density value (which can be a pre-set probability density value, for example, the probability density values ​​can be sorted from largest to smallest and a probability density value containing a certain number of probability density values ​​can be selected as the preset probability density value). The probability density values ​​of all image points through which the contour line passes are equal, and it can also be considered as an isodense line.

[0103] Optionally, after constructing the probability density surface, contour lines can be determined based on the probability density values ​​corresponding to each image point on the probability density surface, such as contour lines with a probability density value of p=0.9. Then, third image points corresponding to the image points traversed by these contour lines in the planar coordinate image can be identified and connected to obtain boundary lines, such as the smallest closed boundary line containing 95% of the third image points. The image region contained within the boundary line can be used as a dynamic envelope image. Furthermore, the screw assembly corresponding to each image point (such as the third image point) in this dynamic envelope image can be considered normal and qualified.

[0104] Optionally, dynamic envelope images corresponding to each screw specification can be created, and the mapping relationship between each screw specification and its corresponding dynamic envelope image can be determined and stored, for example, in the form of a lookup table. This allows the screw assembly equipment to find the corresponding dynamic envelope image (e.g., the first dynamic envelope image) based on the actual screw specification and the stored dynamic envelope images corresponding to each screw specification when performing fault detection. Then, the first dynamic envelope image can be used to determine whether there is a fault in the current screw assembly and whether there is a fault in the screw assembly equipment. If a fault is found, corresponding alarm information can be output to promptly remind the user.

[0105] In this embodiment, when constructing the dynamic envelope image, a corresponding dynamic envelope image can be created for each screw specification and model. Furthermore, during the creation of the dynamic envelope image, a point cloud image can be determined based on the third image point of the assembled screw in the planar coordinate image. A two-dimensional Gaussian kernel density calculation is then performed on the point cloud image to determine the probability density surface. The dynamic envelope image in the planar coordinate image is then determined based on the probability density surface. The boundary lines in the voltage image can be determined based on the contour lines in the probability density surface. The image region contained within the boundary lines in the planar coordinate image is used as the dynamic envelope image, thereby ensuring the accuracy and effectiveness of the determined dynamic envelope image. This ensures the accuracy of fault prediction when using the dynamic envelope image for subsequent fault prediction.

[0106] In addition, to aid in understanding the principle of fault detection in this embodiment, examples are provided below.

[0107] For example, such as Figure 4As shown, the initial data acquisition for screw assembly can be performed first, including current sampling and torque arrival time capture, obtaining the sampled current and the first torque arrival time, respectively. During current sampling, it can be determined that current acquisition occurs within the first time window of the screw assembly action (e.g., tightening action). This first time window can be a 0.3s window. It is then determined whether the 0.3s window is fully completed, meaning whether a complete current acquisition was performed within the first time window, obtaining all sampled currents within that window. If not, for example, if only 0.1s of current acquisition is performed within the 0.3s window, leaving 0.2s without current acquisition, the fault detection process ends. If so, the current integral Q, or the first current integral, can be calculated based on the multiple sampled currents. A vector transformation is then performed based on the scalar first current integral and the first torque arrival time. Since the current integral Q of a single screw is only a cumulative current, it must be paired with the torque arrival time Δt (e.g., the first torque arrival time) to form an image point z=(Q, Δt). Q reflects the work done by the motor, and Δt reflects the mechanical resistance. The two complement each other. When the tooth strips, Δt increases sharply while Q is low. When there is wear, Q is large but Δt is normal. When the tooth is stuck, both parameters fail simultaneously.

[0108] Optionally, feature points can be constructed based on the first current integral and the first torque arrival time, such as first image points located in a planar coordinate image. Then, a dynamic envelope image can be loaded, such as a first screw envelope image corresponding to the screw specification and model being assembled. The dynamic envelope image can be constructed based on a point cloud image formed by the image points corresponding to the screws that are properly assembled in the planar coordinate image (this point cloud image can be a non-normally distributed image with irregular boundaries). For example, a two-dimensional Gaussian kernel density calculation can be performed on the point cloud image to obtain a probability density surface. Then, contour lines can be determined based on the probability density surface, such as extracting contour lines with a probability density value of 0.95. The dynamic envelope image in the planar coordinate image can then be determined based on the contour lines, such as a dynamic envelope image containing image points corresponding to 95% of the properly assembled screws.

[0109] Optionally, it can be determined whether the first image point is within the dynamic envelope image (e.g., the first dynamic envelope image). If so, Fault_cnt = 0, indicating that the screw assembly is normal. If not, Fault_cnt++, indicating a fault in the current screw assembly. It can also be determined whether Fault_cnt ≥ 2 exists. If so, Fault_ID = classify(z) and a fault code is sent to update the equipment parameters. In other words, if two consecutive screw assemblies fail, the screw assembly equipment is considered faulty and requires parameter updates.

[0110] Optionally, it can also detect whether the screw specifications have changed during subsequent screw assembly. If so, for example, the screw specifications have changed, a new or corresponding dynamic envelope image can be reconstructed for fault detection. Furthermore, when reconstructing the dynamic envelope image, the image points corresponding to the correctly assembled screws of the newly selected screw specifications can be used to reconstruct the dynamic envelope image. The sample number during dynamic envelope image construction will be updated, for example, updating the first 30 samples. The updated sample (i.e., the screw) will have the newly selected screw specifications, thus achieving zero manual parameter tuning. Specifically, it can perform a check if the sample number in the image is 30. If not, it can be determined that the screw specifications have changed, and the original first dynamic envelope image can continue to be used for fault detection until the end. If so, the dynamic envelope image can be reconstructed, and fault detection can be performed based on the reconstructed dynamic envelope image until the end.

[0111] In this embodiment, the "Q-Δt two-dimensional dynamic envelope" algorithm chain can run in parallel inside the electric screwdriver (i.e., screw assembly equipment) using the same current and speed signals as the source, without the need for additional sensors or manual parameter tuning. By using kernel density contour lines to distinguish between stripped threads, wear, and stuck screws in real time, the envelope can be updated automatically after changing specifications for 30 screws, reducing on-site maintenance to zero, the missed detection rate from 2.1% to 0.3%, and the false judgment rate to an order of magnitude lower. The average troubleshooting time is shortened from 2 hours to 15 minutes, significantly reducing production line downtime losses, while meeting the dual compliance requirements of auditing for fault traceability and lifespan predictability.

[0112] Furthermore, this application provides an electronic device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the fault detection method in Embodiment 1 above.

[0113] The following is for reference. Figure 5The figure illustrates a structural diagram of an electronic device suitable for implementing embodiments of this application. The electronic devices in the embodiments of this application may include, but are not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Description), PMPs (Portable Media Players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. The devices shown in the figure are merely examples and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0114] The electronic device may include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.) that can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage device 1003 into a random access memory (RAM) 1004. The RAM 1004 also stores various programs and data required for device operation. The processing unit 1001, ROM 1002, and RAM 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1006: input devices 1007 including, for example, touchscreens, touchpads, keyboards, mice, image sensors, microphones, accelerometers, gyroscopes, etc.; output devices 1008 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 1003 including, for example, magnetic tapes, hard disks, etc.; and communication devices 1009. Communication device 1009 allows electronic devices to communicate wirelessly or wiredly with other devices to exchange data. While electronic devices with various systems are shown in the figures, it should be understood that implementation or possession of all the systems shown is not required. More or fewer systems may be implemented alternatively.

[0115] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from ROM 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.

[0116] The electronic device provided in this application, employing the fault detection method in the above embodiments, can solve the technical problem of how to improve the accuracy of fault detection. Compared with the prior art, the beneficial effects of the electronic device provided in this application are the same as those of the fault detection method provided in the above embodiments, and other technical features of the electronic device are the same as those disclosed in the method of the previous embodiment, and will not be repeated here.

[0117] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0118] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0119] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, the computer-readable program instructions being used to execute the fault detection method in the above embodiments.

[0120] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0121] The aforementioned computer-readable storage medium may be included in an electronic device or may exist independently without being assembled into an electronic device.

[0122] The aforementioned computer-readable storage medium carries one or more programs, which, when executed by an electronic device, enable the electronic device to perform the steps in the aforementioned fault detection method.

[0123] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a Local Area Network (LAN) or a Wide Area Network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0124] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0125] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.

[0126] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the above-described fault detection method, thereby solving the technical problem of how to improve the accuracy of fault detection. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the fault detection method provided in the above embodiments, and will not be repeated here.

[0127] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the fault detection method described above.

[0128] The computer program product provided in this application can solve the technical problem of how to improve the accuracy of fault detection. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as those of the fault detection method provided in the above embodiments, and will not be repeated here.

[0129] The above are only some embodiments of this application and do not limit the patent scope of this application. All equivalent structural transformations made under the technical concept of this application and using the contents of the specification and drawings of this application, or direct / indirect applications in other related technical fields, are included in the patent protection scope of this application.

Claims

1. A fault detection method, characterized in that, The fault detection method is applied to screw assembly equipment and includes the following steps: The first current integral is determined based on the sampling current corresponding to the screw assembly, and the first torque arrival time for the screw assembly is determined. A first dynamic envelope image corresponding to the screw is determined, wherein the first dynamic envelope image represents the image of the image point corresponding to the screw that has been assembled successfully; The first image point corresponding to the screw is determined based on the first torque arrival time and the first current integral, wherein the first image point and the first dynamic envelope image are in the same plane coordinate image; In response to the fact that the first image point corresponding to a consecutive preset number of screws is not within the first dynamic envelope image, it is determined that there is a fault in the screw assembly equipment, and a preset alarm message is output.

2. The fault detection method as described in claim 1, characterized in that, After the step of determining the first image point corresponding to the screw based on the first torque arrival time and the first current integral, the method includes: The torque arrival time threshold range and the current integration threshold range are determined based on the first dynamic envelope image; If the first torque arrival time is greater than the maximum value of the torque arrival time threshold range, and the first current integral is located within the current integral threshold range, then it is determined that the screw assembly has a stripped thread fault. If the first torque arrival time is within the torque arrival time threshold range and the first current integral is greater than the maximum value of the current integral threshold range, then it is determined that the screw assembly has a wear fault. If the first torque arrival time is greater than the maximum value of the torque arrival time threshold range, and the first current integral is greater than the maximum value of the current integral threshold range, then it is determined that there is a jamming fault in the screw assembly.

3. The fault detection method as described in claim 2, characterized in that, The step of determining the torque arrival time threshold range and the current integration threshold range based on the first dynamic envelope image includes: Determine all second image points contained in the first dynamic envelope image, wherein the second image points include torque arrival time and current integral; Determine the maximum torque arrival time and the minimum torque arrival time among all the second image points, and use the time interval between the minimum torque arrival time and the maximum torque arrival time as the torque arrival time threshold interval; Determine the maximum and minimum current integrals among all the second image points, and use the integration interval between the minimum and maximum current integrals as the current integration threshold interval.

4. The fault detection method as described in claim 1, characterized in that, The step of determining the first current integral based on the sampling current corresponding to the screw assembly includes: Multiple current samples are taken at a preset sampling frequency within the first time window of screw assembly to obtain multiple sampled currents. The start time of the first time window is the screw assembly start time, and the end time is the screw assembly completion time. The first current integral is obtained by integrating the multiple sampled currents.

5. The fault detection method as described in claim 1, characterized in that, The step of determining the first dynamic envelope image corresponding to the screw includes: Determine the first screw specification model of the screw; Based on the preset mapping relationship between screw specifications and dynamic envelope images, the dynamic envelope image that matches the first screw specification is determined as the first dynamic envelope image from among a plurality of preset dynamic envelope images.

6. The fault detection method according to any one of claims 1-5, characterized in that, The fault detection method further includes: Obtain the third image point of multiple preset samples in a planar coordinate image representing torque arrival time and current integral, wherein the multiple samples are screws of the same specification and model that have been assembled successfully. Determine a point cloud image containing each of the third image points in the planar coordinate image; Based on the point cloud image, a two-dimensional Gaussian kernel density is calculated to obtain a probability density surface; The dynamic envelope image in the planar coordinate image is determined based on the probability density surface.

7. The fault detection method as described in claim 6, characterized in that, The step of calculating the two-dimensional Gaussian kernel density based on the point cloud image to obtain the probability density surface includes: Determine the first standard deviation and first interquartile range of all the third image points in the first dimension characterizing torque arrival time, and determine the second standard deviation and second interquartile range of all the third image points in the second dimension characterizing current integral. The bandwidth is obtained by adaptive bandwidth calculation based on the first standard deviation, the first interquartile range, the second standard deviation, and the second interquartile range; For each third image point in the point cloud image, the Euclidean distance between the third image point and other third image points is calculated, and the probability density value of the third image point is calculated using the Euclidean distance and the bandwidth according to the preset two-dimensional Gaussian kernel density function. The point cloud image is updated based on the probability density values ​​of each of the third image points in the point cloud image to obtain a probability density surface.

8. The fault detection method as described in claim 6, characterized in that, The step of determining the dynamic envelope image in the planar coordinate image based on the probability density surface includes: Contour lines are determined based on the probability density values ​​of each image point in the probability density surface; wherein, the probability density values ​​of image points within the image region enclosed by the contour lines in the probability density surface are greater than the probability density values ​​of image points located outside the image region enclosed by the contour lines. The boundary lines in the point cloud image are determined based on the contour lines, and the image region contained by the boundary lines is used as the dynamic envelope image.

9. An electronic device, characterized in that, The electronic device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the fault detection method as described in any one of claims 1 to 8.

10. A storage medium, characterized in that, The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, it implements the steps of the fault detection method as described in any one of claims 1 to 8.

Images