Evaluation method and system for bolt connection process of mechanical structure
Through the combination of machine vision and ultrasonic detection, the shortcomings in bolt connection process evaluation are solved, accurate control of preload force is achieved, and assembly quality and service safety are ensured.
Patent Information
- Application Number
- CN202510573532.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-04-30
- Publication Date
- 2025-08-15
AI Technical Summary
The existing bolt connection process lacks effective evaluation methods, resulting in insufficient preload control accuracy, affecting assembly quality and service safety.
Through machine vision, the contact area between bolts, nuts and connectors is detected, combined with ultrasonic detection of the stress status of bolts, the preload force is comprehensively calculated, and an evaluation report is formed to ensure the accuracy of preload force.
It has achieved scientific evaluation of the bolt connection process, improved the control accuracy of preload, and ensured assembly quality and service safety.
Smart Images

Figure CN120489424A_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the field of bolt preload evaluation, and in particular relates to an evaluation method and system for a mechanical structure bolt connection process. Background Art
[0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art.
[0003] Bolted connections are a common mechanical connection method, primarily used in machinery manufacturing, civil engineering, and other fields. Their high reliability, ease of disassembly, and convenient installation make them a crucial connection method. Bolted connections are primarily used to secure connected parts, prevent slippage or disengagement, and transmit static or dynamic forces. The essence of assembly tightening is to securely connect two components together through the axial preload of the bolt. This secure fastening is achieved through the self-locking force of the thread friction and various mating surface friction. Therefore, accurate control of the axial preload is essential for ensuring assembly quality.
[0004] There are many different tightening processes for bolt fasteners, with the main methods used for thread tightening including the torque method, the torque-angle method, and the yield point control method. The torque control method is based on the relationship T = K * D * F, where the bolt's axial preload is proportional to the tightening torque. Tightening is immediately stopped when the tightening torque reaches a set control value. This method is simple and easy to implement, but the K value is empirically set between 0.1 and 0.3. The thread surface roughness, the presence of lubricant, the tightening speed, the tightening tool, and the temperature during tightening all affect it, resulting in limited control accuracy for the preload, and a large dispersion in the bolt's axial preload. The torque-angle control method, developed based on the torque control method, uses the yield strength of the bolt material to initially tighten the bolt to a low torque and then, from this point, to a specified angle. This method further controls the bolt's axial extension and the compression of the connection by controlling the angle, thereby improving the control accuracy of the preload. However, this method requires expensive electric combination tightening tools with torque / angle control and monitoring capabilities and corresponding testing equipment, and is therefore less widely used. The yield point control method is also based on the phenomenon of bolt material yield. By continuously calculating and judging the slope of the torque / angle curve during the tightening process, the yield point is confirmed and tightening is stopped. This method can control the error of the preload force within a smaller range. This method is rarely used in large quantities in rail vehicle assembly.
[0005] In summary, the aforementioned bolt tightening processes are based on empirical calculations or the strength of the fasteners themselves, obtained through standard testing of a limited number of fasteners. However, the actual connected components and assembly conditions in the structure are rarely considered. Furthermore, existing testing methods mostly focus on tightening quality testing during the production process, while ignoring the scientific and reasonable evaluation of the construction process during the pre-production process planning stage. Furthermore, the current tightening process lacks effective assessment methods and standards, making it difficult to effectively guarantee the realization of preload. Summary of the Invention
[0006] In order to solve the above problems, the present invention proposes a method and system for evaluating the bolt connection process of mechanical structures. The present invention overcomes the limitations of a single detection method by detecting the appearance quality and preload of the bolt connection and cross-checking other modal data, thereby realizing effective evaluation of the tightening process and ensuring the realization of the preload.
[0007] According to some embodiments, the present invention adopts the following technical solutions:
[0008] A method for evaluating a mechanical structure bolt connection process comprises the following steps:
[0009] Acquire a plurality of images containing gaps between bolts, nuts, and connectors within a first set time period after a bolt connection operation of the mechanical structure, preprocess the images, and extract geometric features;
[0010] Based on the extracted geometric features, the contact area between the bolt, nut and connector is compared with the theoretical contact area, the contact ratio is calculated, the surface cracks are quantified, and the appearance inspection results are obtained;
[0011] Acquiring ultrasonic detection data within a second set time period after the mechanical structure bolt connection operation, determining the stress state of the bolt based on the ultrasonic detection data, calculating the preload force borne by the bolt, and obtaining an axial force detection result;
[0012] The appearance inspection results and axial force inspection results are integrated, and weights and physical constraints are introduced to determine the final inspection results. Based on the final inspection results, an evaluation report on the mechanical structure bolt connection process is formed.
[0013] As an optional embodiment, the preprocessing process includes denoising, enhancing and gray-scaling images of the contact surfaces of the bolts, nuts and connectors taken from multiple angles, and extracting the edges of the bolts, nuts and connectors.
[0014] As an optional implementation method, before comparing the contact area of the bolts, nuts and connectors with the theoretical contact area based on the extracted geometric features, an appearance inspection is performed first, specifically including: checking whether the size of the exposed thread of the nut meets the requirements, and whether there is mechanical damage on the exposed surface of the bolt and nut. If it does not meet the requirements or there is mechanical damage, the appearance inspection will fail.
[0015] As an optional implementation, based on the extracted geometric features, the contact area between the bolt, nut and connector is compared with the theoretical contact area, and the process of calculating the contact rate includes: the contact rate is:
[0016] Among them, e test is the coordinate of the edge point of the bolt head, e ref The edge template is in standard fitting state, D bolt is the nominal diameter of the bolt, N is the number of images, i represents the i-th image, a fitting rate of 0 indicates complete separation, and a fitting rate of 1 indicates perfect fit.
[0017] As an optional implementation, the process of performing surface crack quantification includes: using a surface crack quantification model, wherein the surface crack quantification model is:
[0018]
[0019] Among them, A crack is the crack area, A ref is the base area, d min is the shortest distance between the crack tip and the edge, and w is the attenuation coefficient.
[0020] As an optional implementation, the process of obtaining the appearance inspection result includes weighting the calculated values of the fitting rate and the surface crack quantification.
[0021] As an optional implementation method, in the process of obtaining ultrasonic detection data within a second set time period after the mechanical structure bolt connection operation, an ultrasonic generator is installed at one end of the bolt, and by measuring the time it takes for the reflected wave to return from the other end, the stress state of the bolt is obtained, and the preload force borne by the bolt is calculated.
[0022] As an optional implementation, the process of integrating the appearance inspection results and the axial force inspection results and introducing weights and physical constraints includes:
[0023] The comprehensive score is: Final_Score=∑w m x m ·Φ(ΔF p ,T), when the comprehensive score is lower than the set threshold, the evaluation is unqualified and an alarm is triggered;
[0024] Among them, w m is the weight, Φ is the physical constraint term, ΔF p is the deviation between the measured value and the design value, T is the torque design value, x m is the test result of different items. When m=1, it is the appearance test result. When m=2, it is the ultrasonic clamping force deviation, i.e. ΔF p / F design , ΔF p F is the deviation between the measured preload value and the design value, design is the design value of the preload force. When m=3, it is the fluctuation rate of the torque coefficient, that is: |KK nom ∣ / K nom , K is the measured torque coefficient, T=K×d×F p It is calculated that K nom is the design torque coefficient, F p is the measured preload value, and d is the bolt diameter.
[0025] As a further limited implementation method, the physical constraints are:
[0026]
[0027] When the preload force is within the set range, Φ = 1, otherwise, Φ decays according to the exponential function, and the penalty score is F design is the design value of preload force.
[0028] As an optional implementation, an evaluation report on the mechanical structure bolt connection process is formed based on the final inspection results and combined with the condition information of the mechanical structure bolt connection, wherein the condition information of the mechanical structure bolt connection includes: conditions related to the manufacturer, conditions related to the joint type, conditions related to the connecting parts, and conditions related to the bolts and nuts.
[0029] An evaluation system for a mechanical structure bolt connection process, comprising:
[0030] an image feature extraction module configured to acquire a plurality of images containing gaps between bolts, nuts, and connectors within a first set time period after a bolt connection operation of a mechanical structure, preprocess the images, and extract geometric features;
[0031] An appearance inspection module is configured to compare the contact area between the bolt, nut, and connector with the theoretical contact area based on the extracted geometric features, calculate the fit ratio, quantify surface cracks, and obtain appearance inspection results;
[0032] an axial force detection module configured to obtain ultrasonic detection data within a second set time period after the mechanical structure bolt connection operation, determine the stress state of the bolt based on the ultrasonic detection data, calculate the preload force borne by the bolt, and obtain an axial force detection result;
[0033] The comprehensive evaluation module is configured to integrate the appearance inspection results and the axial force inspection results, introduce weights and physical constraints, determine the final inspection results, and form an evaluation report on the mechanical structure bolt connection process based on the final inspection results.
[0034] Compared with the prior art, the present invention has the following beneficial effects:
[0035] The present invention detects the appearance quality of bolt connections based on machine vision and directly inspects and tests the pre-tightening force, thereby establishing a mathematical model for the bolt tightening quality. Furthermore, through cross-checking of torque, ultrasound, and visual data, the invention overcomes the limitations of a single detection method, supports the evaluation of the bolting construction process, overcomes the problem that the pre-tightening force quality of bolted joints is difficult to intuitively evaluate, supports the evaluation of the entire bolting construction process of the product, ensures the accuracy of the tightening process from the source, and guarantees the product manufacturing quality and service safety.
[0036] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS
[0037] The accompanying drawings, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.
[0038] Figure 1 The present invention is a flowchart of an evaluation method for a mechanical structure bolt connection process according to an embodiment. DETAILED DESCRIPTION
[0039] The present invention will be further described below with reference to the accompanying drawings and embodiments.
[0040] It should be noted that the following detailed descriptions are illustrative and intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which the present invention belongs.
[0041] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is intended to include the plural form. In addition, it should be understood that when the terms "comprise" and / or "include" are used in this specification, they indicate the presence of features, steps, operations, devices, components and / or combinations thereof.
[0042] In the absence of conflict, the embodiments and features in the embodiments of this application can be combined with each other.
[0043] Example 1
[0044] A method for evaluating the bolt connection process of mechanical structures, such as Figure 1 As shown, the following steps are included:
[0045] Acquire a plurality of images containing gaps between bolts, nuts, and connectors within a first set time period after a bolt connection operation of the mechanical structure, preprocess the images, and extract geometric features;
[0046] Based on the extracted geometric features, the contact area between the bolt, nut and connector is compared with the theoretical contact area, the contact ratio is calculated, the surface cracks are quantified, and the appearance inspection results are obtained;
[0047] Acquiring ultrasonic detection data within a second set time period after the mechanical structure bolt connection operation, determining the stress state of the bolt based on the ultrasonic detection data, calculating the preload force borne by the bolt, and obtaining an axial force detection result;
[0048] The appearance inspection results and axial force inspection results are integrated, and weights and physical constraints are introduced to determine the final inspection results. Based on the final inspection results, an evaluation report on the mechanical structure bolt connection process is formed.
[0049] First, information is collected. In this embodiment, according to the requirements of the design drawings, the parameters of the bolted joints are statistically summarized. The summarized information includes torque / preload requirements, connected materials, bolt information, nut information, washer information, anti-loosening method, lubricant and torque tools, etc.
[0050] Bolted joint analysis can be performed again. If the joint parameter information exceeds the approved range of the existing process assessment report, a process assessment test is required and the additional process assessment details required for the product are listed.
[0051] Then conduct the assessment test, obtain the results, and write an assessment report.
[0052] The following focuses on how to conduct process evaluation tests and calculate the results.
[0053] Of course, all process assessment tests can be based on samples of actual structures, so that the product structure (i.e. bolts, nuts / screw seats, gaskets and connected parts) and the specifications of each part, joint form, thread accuracy, lubrication conditions, connected parts materials, surface conditions, installation torque, tightening methods, lubricants, tightening tools and other construction conditions are consistent with actual operations.
[0054] Conduct an appearance inspection first.
[0055] Check that the exposed threads of the nuts should not be less than the standard requirements, and there should be no mechanical damage on the exposed surfaces of the bolts and nuts.
[0056] Next, a machine vision inspection system is used to detect the gap between the bolt head, nut and the connected parts.
[0057] In this embodiment, a high-resolution industrial camera can be used to capture clear images of bolts, nuts, and connectors. When capturing the images, it is ensured that the images are free of distortion and have sufficient depth of field.
[0058] When collecting images, you can also add a light source system, or ensure the lighting during collection. You can use a backlight to ensure uniform lighting and reduce shadow and reflection interference.
[0059] Alternatively, a lighting system with adjustable light brightness can be used to adapt to different materials and surfaces.
[0060] This embodiment uses a computer as an image processing unit and is equipped with image processing software to perform image analysis, feature extraction, and fitting rate calculation.
[0061] Of course, a mechanical adjustment mechanism may be added in some embodiments, and the industrial camera and / or light source system may be arranged on the mechanical adjustment mechanism to precisely align the camera and light source with the detection area, automatically adjust the position according to the situation, and adapt to workpieces of different sizes and shapes.
[0062] Use industrial cameras to capture the contact surfaces of bolts, nuts, and connectors from multiple angles, ensuring that each image is clear and covers all critical areas.
[0063] The collected images are pre-processed by denoising, enhancing, gray-scaling, etc. to improve the accuracy of subsequent analysis. Edge detection, contour extraction and other algorithms are used to identify the edges of bolts, nuts and connectors, and extract the geometric features of the contact surface, such as area and contour.
[0064] The contact rate is calculated by comparing the contact area between the bolt / nut and the connector with the theoretical contact area. The calculation formula for the contact rate is as follows:
[0065]
[0066] e testis the measured coordinate of the edge point of the bolt head;
[0067] e ref The edge template is in standard fitting state;
[0068] D bol is the nominal diameter of the bolt (unit: mm);
[0069] N is the total number of images.
[0070] A fit rate result of 0 indicates complete separation; a fit rate result of 1 indicates perfect fit.
[0071] Then use the surface crack quantification model to quantify the surface quality:
[0072]
[0073] A crack is the crack area;
[0074] A ref is the base area;
[0075] d min is the shortest distance between the crack tip and the edge;
[0076] w is the attenuation coefficient, which is 1 / 10 of the bolt diameter in this embodiment.
[0077] The appearance inspection result is the weighted sum of the two scores. The weight can be set according to the specific situation and needs.
[0078] In some embodiments, the detection results can be fed back to the user interface of the computer in real time.
[0079] Then, ultrasonic testing technology based on acoustic elasticity theory is used. An ultrasonic generator is installed at one end of the bolt. By accurately measuring the time it takes for the reflected wave to return from the other end, the stress state of the bolt is obtained, and the preload force borne by the bolt is calculated accordingly.
[0080] Of course, in some embodiments, multiple samples may be used for testing. For example, if there are a total of 6 samples, the average value of each sample meets the structural design load-bearing requirements, and no more than 2 samples have a single value that is not lower than the minimum structural design load-bearing requirements. Otherwise, the process is judged to be unqualified.
[0081] The ultrasonic detection system can use existing equipment and should be calibrated before detection.
[0082] Next, conduct a comprehensive rating of the tightening quality:
[0083] Final_Score=∑w m x m·Φ(ΔF p , T)
[0084] w m is the weight;
[0085] When m = 1, x is the visual comprehensive score, that is, the weighted result of Fit_Score and Crack_Score;
[0086] When m=2, the ultrasonic clamping force deviation ΔFp / F design , ΔFp is the deviation between the measured value and the design value, F design is the design value;
[0087] When m=3, the torque coefficient fluctuation rate is: |KK nom ∣ / K nom , K is the measured torque coefficient, which is calculated by T=K×d×Fp, K nom is the design torque coefficient, d is the bolt diameter, and T is the torque design value;
[0088] The physical constraints are:
[0089]
[0090] When the preload force is normal (i.e. Fp is within the design range): Φ = 1.
[0091] When the preload force is abnormal (i.e. Fp exceeds the limit value): Φ decays according to the exponential function and the penalty score is set. For example: Ultrasonic testing shows that Fp is only 80% of the design value, but the visual and torque data are normal: Φ = e -0.25 ≈0.78, Final_Score will be significantly lowered, forcing an alarm to be triggered to avoid missed detections due to failure of a single item.
[0092] When the final score Final_Score is lower than the threshold of 0.6, an alarm is triggered.
[0093] After the mechanical structure is bolted, if it passes the above test and meets the qualification requirements, the tightening process is approved.
[0094] The following conditions may also be considered during the evaluation process:
[0095] (1) Conditions related to manufacturers
[0096] The tightening process qualified by the manufacturer through the assessment test is valid for the same technology and quality control workshop of the manufacturer.
[0097] (2) Conditions related to connector type
[0098] The assessment is only valid for the type of bolted joint used for the process test.
[0099] The following conditions are met and can be considered to be the same connector type:
[0100] If there is no anti-loosening measure for the joint, it is recognized that there is anti-loosening measure.
[0101] (3) Conditions related to connectors
[0102] The process qualification is only valid for the type of connector material used in the test (steel / aluminum / copper / composite / plastic / rubber).
[0103] (4) Conditions related to bolts and nuts
[0104] Bolts and nuts are recognized to be of the same grade; when the bolt length is ≤100mm, the length difference is ≤15mm; when the bolt length is greater than 100mm, the length difference is ≤20mm, and they can be regarded as the same length.
[0105] (5) Conditions related to torque and tightening method
[0106] The assessment is only valid for the torque and tightening method used in the process test.
[0107] (6) Conditions related to the torque tightening process
[0108] The degree of automation, preset torque wrenches, tightening spindle type and electric torque wrenches are approved separately.
[0109] Lubricants: The assessment is only valid for the type of lubricant used in the process test.
[0110] Finally, a process assessment report is formed, which describes the evaluation results of each sample.
[0111] If no rejections or unsatisfactory test results are found, the process qualification report describing the results of the process qualification test piece is approved and signed.
[0112] It will be understood by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0113] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0114] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.
[0115] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.
[0116] The foregoing description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Those skilled in the art will readily appreciate that various modifications and variations of the present invention are possible. Any modifications, equivalent substitutions, or improvements made by those skilled in the art that fall within the spirit and principles of the present invention and do not require creative effort are intended to be within the scope of protection of the present invention.
Claims
1. A method for evaluating the bolt connection process of a mechanical structure, characterized in that: The following steps are involved: Acquire a plurality of images containing gaps between bolts, nuts, and connectors within a first set time period after a bolt connection operation of the mechanical structure, preprocess the images, and extract geometric features; Based on the extracted geometric features, the contact area between the bolt, nut and connector is compared with the theoretical contact area, the contact ratio is calculated, the surface cracks are quantified, and the appearance inspection results are obtained; Acquiring ultrasonic detection data within a second set time period after the mechanical structure bolt connection operation, determining the stress state of the bolt based on the ultrasonic detection data, calculating the preload force borne by the bolt, and obtaining an axial force detection result; The appearance inspection results and axial force inspection results are integrated, and weights and physical constraints are introduced to determine the final inspection results. Based on the final inspection results, an evaluation report on the mechanical structure bolt connection process is formed.
2. The method for evaluating a mechanical structure bolt connection process according to claim 1, wherein: The preprocessing process includes denoising, enhancing and graying images of the contact surfaces of bolts, nuts and connectors taken from multiple angles, and extracting the edges of the bolts, nuts and connectors.
3. The method for evaluating a mechanical structure bolt connection process according to claim 1, wherein: Before comparing the contact area of the bolts, nuts and connectors with the theoretical contact area based on the extracted geometric features, a visual inspection is performed first. Specifically, it includes checking whether the size of the exposed thread of the nut meets the requirements and whether there is mechanical damage on the exposed surface of the bolt and nut. If it does not meet the requirements or there is mechanical damage, the visual inspection will fail.
4. The method for evaluating a mechanical structure bolt connection process according to claim 1, wherein: Based on the extracted geometric features, the contact area between the bolt, nut and connector is compared with the theoretical contact area. The process of calculating the contact rate includes: Among them, e test is the coordinate of the edge point of the bolt head, e ref The edge template is in standard fitting state, D bolt is the nominal diameter of the bolt, N is the number of images, i represents the i-th image, a fitting rate of 0 indicates complete separation, and a fitting rate of 1 indicates perfect fit.
5. The method for evaluating a mechanical structure bolt connection process according to claim 1, wherein: The process of performing surface crack quantification includes: using a surface crack quantification model, wherein the surface crack quantification model is: Among them, A crack is the crack area, A ref is the base area, d min is the shortest distance between the crack tip and the edge, and w is the attenuation coefficient.
6. The method for evaluating a mechanical structure bolt connection process according to claim 1, wherein: The process of obtaining the appearance inspection results includes weighting the calculated values of the fit rate and the surface crack quantification.
7. The method for evaluating a mechanical structure bolt connection process according to claim 1, wherein: To obtain ultrasonic test data within the second set time period after a bolt connection operation on a mechanical structure, an ultrasonic generator is installed at one end of the bolt. By measuring the time it takes for the reflected wave to return from the other end, the stress state of the bolt is obtained and the preload force on the bolt is calculated.
8. The method for evaluating a mechanical structure bolt connection process according to claim 1, wherein: The process of introducing weights and physical constraints based on the appearance inspection results and axial force inspection results includes: The comprehensive score is: Final_Score=∑w m x m ·Φ(ΔF p ,T), when the comprehensive score is lower than the set threshold, the evaluation is unqualified and an alarm is triggered; Among them, w m is the weight, Φ is the physical constraint term, ΔF p is the deviation between the measured value and the design value, T is the torque design value, is the test result of different items, when m=1, it is the appearance test result, when m=2, it is the ultrasonic clamping force deviation, that is, ΔF p / F design , ΔF p F is the deviation between the measured preload value and the design value, design is the design value of the preload force. When m=3, it is the fluctuation rate of the torque coefficient, that is: |KK nom ∣ / K nom , K is the measured torque coefficient, T=K×d×F p It is calculated that K nom is the design torque coefficient, F p is the measured preload value, and d is the bolt diameter.
9. The method for evaluating a mechanical structure bolt connection process according to claim 1, wherein: The physical constraints are: When the preload force is within the set range, Φ = 1, otherwise, Φ decays according to the exponential function, and the penalty score is F design is the design value of preload force.
10. A system for evaluating a mechanical structure bolt connection process, comprising: an image feature extraction module configured to acquire a plurality of images containing gaps between bolts, nuts, and connectors within a first set time period after a bolt connection operation of a mechanical structure, preprocess the images, and extract geometric features; An appearance inspection module is configured to compare the contact area between the bolt, nut, and connector with the theoretical contact area based on the extracted geometric features, calculate the fit ratio, quantify surface cracks, and obtain appearance inspection results; an axial force detection module configured to obtain ultrasonic detection data within a second set time period after the mechanical structure bolt connection operation, determine the stress state of the bolt based on the ultrasonic detection data, calculate the preload force borne by the bolt, and obtain an axial force detection result; The comprehensive evaluation module is configured to integrate the appearance inspection results and the axial force inspection results, introduce weights and physical constraints, determine the final inspection results, and form an evaluation report on the mechanical structure bolt connection process based on the final inspection results.
Citation Information
Cited By
Intelligent torque gun with miniature camera and edge computing interface and method
CN121384292A
Fastener quality judgment method and system based on multi-source data fusion
CN122263030A