Automatic riveting forming online quality detection method based on 3D line scanning camera

Abstract

The invention discloses an automatic riveting forming online quality detection method based on a 3D line scanning camera, and relates to the field of aviation riveting detection.The method comprises the steps that calibration operation is carried out on the 3D line scanning camera, and a unified measurement basis is established; performing optical measurement on the surface of the wall plate and the surface of the rivet in the adjacent area of the rivet for multiple times, and acquiring and recording a corresponding data set; sorting the wallboard area data set and the rivet top end data set according to measured values; selecting an intermediate value of the wallboard data set and an intermediate value of the rivet data set, and calculating an algebraic difference value of the two intermediate values as a rivet levelness evaluation result; and storing the evaluation results of the plurality of rivets in a database, and generating a structured quality detection report. According to the scheme, the precision, efficiency and consistency of riveting levelness detection can be remarkably improved, full-automatic online detection and full-coverage detection are achieved, the omission ratio and the misjudgment risk are greatly reduced, and meanwhile the good anti-interference capability and environment adaptability are achieved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of aviation riveting detection, in particular to an automatic riveting forming online quality detection method based on a 3D line scanning camera. BACKGROUND

[0002] With the continuous development of the aerospace industry towards high quality, high efficiency and high reliability, automatic drilling and riveting technology has become a key link in the process of aircraft manufacturing. Especially in the development of large passenger aircraft and fighter aircraft, the requirement for riveting forming quality is becoming more and more strict, and the detection precision and efficiency of flushness, as one of the core indicators for evaluating riveting quality, directly affect the performance and life of the overall structure. At present, artificial sampling inspection or traditional optical measurement methods are generally used in this field, which not only has low efficiency and is easily affected by subjective factors, but also is difficult to meet the demand for real-time full inspection of high-speed automatic production lines. In addition, the aviation components often involve various material combinations, complex profiles and surfaces with inconsistent reflection characteristics, which further increase the difficulty of accurate measurement.

[0003] The existing flushness detection method has several significant limitations. First, the traditional manual detection method has low efficiency, limited sampling rate, and cannot achieve full coverage. Moreover, the detection results are greatly affected by the experience of the operator, and the data consistency and reliability are insufficient. Second, common optical measurement equipment is easily disturbed by stray light, environmental vibration and instantaneous deformation when dealing with strong reflection, multi-material or complex topological surfaces, resulting in increased measurement error. Third, most existing systems lack real-time noise reduction and dynamic anti-interference mechanisms for high-speed production line environments, making it difficult to meet the production line beat requirements while ensuring detection accuracy. Finally, most methods do not achieve comprehensive digitization and data traceability of the detection process, which is not conducive to deep analysis of quality data and production optimization. Therefore, based on the above problems, the present application proposes an automatic riveting forming online quality detection method based on a 3D line scanning camera. SUMMARY

[0004] PURPOSE OF THE INVENTION In order to solve the above problems, the purpose of the present application is to provide an automatic riveting forming online quality detection method based on a 3D line scanning camera, which aims to solve the outstanding problems of flushness detection in precision, efficiency and anti-interference ability in the process of automatic riveting in the field of aerospace, and to ensure that high-precision, fully-automatic and real-time online detection can be achieved in high-speed automatic production line environments, in order to overcome the limitations of traditional manual sampling inspection and ordinary optical measurement methods in detection consistency, environmental adaptability and data traceability.

[0005] TECHNICAL SCHEME In order to achieve the above object, the present application provides an automatic riveting forming online quality detection method based on a 3D line scanning camera, which adopts a three-dimensional line scanning camera as a core measuring device, performs calibration, measures multiple times in the rivet and adjacent wallboard area respectively, sorts the collected data according to numerical value and extracts the median value, calculates the height difference as the evaluation result of the rivet flushness, integrates multiple noise reduction strategies, including outlier elimination and adaptive filtering processing, effectively suppresses mechanical vibration and surface reflection interference, finally realizes automatic recording, storage and report generation of detection data, and forms a complete and reliable online quality detection system.

[0006] In the first aspect, the present application provides an automatic riveting forming online quality detection method based on a 3D line scanning camera, comprising: Calibration operation is performed on the three-dimensional line scanning camera to establish a unified measurement reference; Multiple non-contact optical measurements are performed on the surface of the wallboard in the rivet adjacent area and the surface of the rivet top, and the corresponding data sets are acquired and recorded; The wallboard data set and the rivet top data set are sorted in ascending order according to the measurement value respectively; The middle value of the wallboard data set and the middle value of the rivet data set are selected, and the algebraic difference between the two middle values is calculated as the evaluation result of the rivet flushness; The evaluation results of multiple rivets are stored in the database, and a structured quality detection report is generated to realize full-process digital management and data traceability.

[0007] Further, the three-dimensional line scanning camera is a high-speed and high-precision optical measurement device, and the measurement process integrates multiple noise reduction processing strategies, identifies and removes outliers in the measurement data through statistical methods, and uses edge-preserving filtering algorithm to smooth the data surface, effectively suppresses environmental vibration and surface reflection interference, and improves detection consistency.

[0008] Further, the edge-preserving filtering algorithm includes adaptive bilateral filtering or Gaussian filtering, and further introduces a noise suppression mechanism based on real-time collected environmental vibration signals to dynamically adjust the filtering parameters, so as to enhance the adaptability and robustness of the system under complex working conditions.

[0009] Further, the noise suppression mechanism for dynamically adjusting the filtering parameters specifically adjusts the convolution kernel size or threshold parameter of the filtering algorithm according to the vibration frequency energy.

[0010] Further, the filtering algorithm further includes a wavelet threshold noise reduction method, which realizes high-frequency noise separation and effective signal enhancement by performing multi-scale decomposition and threshold reconstruction processing on the optical measurement signal.

[0011] Further, before data acquisition, the threshold parameters of each link in the multi-stage noise suppression strategy are pre-calibrated and adaptively initialized according to the optical reflection characteristics and structural complexity of the detected surface.

[0012] In a second aspect, the application further provides an automatic rivet forming online quality detection system based on a 3D line scanning camera, which is based on the method of the first aspect and comprises: a three-dimensional line scanning camera for performing optical scanning and data acquisition; a data acquisition and processing module configured to perform sorting of data sets, extraction of intermediate values and calculation of algebraic differences; a data storage module for storing detection data and associated information of the rivet; a report generation module for generating a quality detection report; a calibration module for performing calibration of the camera coordinate system and periodic precision rechecking.

[0013] Further, the detection path of the system is automatically calculated in real time based on the position and topological configuration of the rivet to be detected.

[0014] Further, the system is equipped with an adaptive operation control unit for sensing the state of interference sources during detection and deciding whether to start a rechecking mechanism; all sensor data and diagnostic logs are integrated into the same database to support quality traceability and production system linkage adjustment.

[0015] In a third aspect, the application further provides a computer readable storage medium having a computer program stored therein, wherein the computer program, when executed by a management platform, implements the above-mentioned automatic rivet forming online quality detection method based on a 3D line scanning camera.

[0016] The application uses a high-speed and high-precision three-dimensional line scanning camera as the core measurement device, performs camera calibration, and measures the rivet and the adjacent wall plate area multiple times, sorts the obtained data sets, extracts the median values, and calculates the height difference as the evaluation result of the rivet flushness. The system integrates multi-stage noise reduction and dynamic anti-interference mechanisms, including outlier rejection and adaptive filtering methods, effectively suppresses mechanical vibration, surface reflection and complex working condition interference, and finally realizes automatic recording, storage and report generation of detection data, forming a complete and reliable online quality detection system.

[0017] This solution significantly improves the accuracy, efficiency, and consistency of riveting flatness inspection, achieving fully automated online and comprehensive inspection, greatly reducing the rate of missed detections and the risk of misjudgment, while also possessing excellent anti-interference capabilities and environmental adaptability. The system generates fully digital quality reports, supporting end-to-end data traceability and in-depth analysis, making it particularly suitable for high-volume, high-speed automated production scenarios in high-precision fields such as aerospace, providing reliable data support for riveting quality evaluation and process optimization.

[0018] Beneficial effects By implementing the automatic online quality inspection method for riveting and forming based on a 3D line scan camera provided by the present invention, the following technical effects are achieved: (1) By using a three-dimensional line scan camera as the core measuring device, high-resolution capture and reconstruction of the surface morphology of rivets and wall panels can be achieved, effectively overcoming the problems of low efficiency and easy damage to the workpiece surface of traditional contact measurement, and significantly improving the automation level of detection and the accuracy of data acquisition.

[0019] (2) By taking multiple measurements and extracting intermediate values ​​from the dataset to calculate the height difference, this method can effectively resist random errors and instantaneous interference in the measurement process, improve the stability and reliability of the flatness assessment results, and avoid the negative impact of extreme values ​​on the detection results.

[0020] (3) The system integrates outlier removal, bilateral filtering, Gaussian filtering and vibration response adaptive filtering and other multi-level noise suppression methods to effectively deal with complex working conditions such as mechanical vibration, surface reflection and multi-material combination, and ensure that the detection system still has high robustness and accuracy in high-speed production line environment.

[0021] (4) By automatically recording the test results in the database and generating structured reports, the riveting quality data is fully digitized, queryable and analyzable, supporting quality traceability, production statistics and process optimization, and providing a data foundation and decision support for high-reliability manufacturing.

[0022] (5) By using a noise suppression mechanism that dynamically adjusts the filtering parameters based on real-time acquired environmental vibration signals, the real-time linkage optimization of the filtering parameters and environmental vibration is realized, which effectively suppresses the periodic interference caused by mechanical vibration and improves the system's adaptability and robustness in complex and variable industrial environments.

[0023] (6) Through the synergistic effect of outlier removal and signal smoothing in the multi-level noise reduction processing strategy, the signal-to-noise ratio of the original data and the consistency of the measurement are significantly improved, laying a data foundation for high-precision quantitative evaluation and further enhancing the detection reliability of the system under complex surface conditions such as strong reflection and multiple material combinations. Attached Figure Description

[0024] To make the above-described method for online quality inspection of automatic riveting forming based on a 3D line scan camera more obvious and understandable, the accompanying drawings used in the specific embodiments of the present invention will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0025] Figure 1 This is a flowchart illustrating the method described in this application; Figure 2 This is a schematic diagram illustrating the principle of this application; Figure 3 This describes the data processing and multi-level noise reduction strategy workflow. Detailed Implementation

[0026] Example 1: An automatic online quality inspection method for riveting forming based on a 3D line scan camera is provided. The method flow is as follows: Figure 1 As shown, the principle is as follows Figure 2 As shown, the process includes: calibrating the 3D line scan camera to establish a unified measurement benchmark; performing multiple non-contact optical measurements on the wall panel surface and the rivet tip surface in the vicinity of the rivet, acquiring and recording the corresponding datasets; sorting the wall panel area dataset and the rivet tip dataset in ascending order according to the measured values; selecting the median value of the wall panel dataset and the median value of the rivet dataset, and calculating the algebraic difference between the two median values ​​as the rivet flatness evaluation result; storing the evaluation results of multiple rivets in a database and generating a structured quality inspection report.

[0027] The details are as follows.

[0028] First, the hardware units of the inspection system are constructed. The 3D line scan camera is fixed to the end flange of a six-axis industrial robot via a high-rigidity mechanical bracket. This configuration gives the system great mobility in three-dimensional space, enabling it to accurately reach complex or narrow spaces within the riveting area and effectively avoid blind spots. Both the camera and robot control systems are integrated with the data acquisition and processing module in the host industrial computer via industrial Ethernet.

[0029] Before the testing process begins, a rigorous calibration procedure must be performed. Standard gauge blocks calibrated and certified by the National Institute of Metrology are used as reference pieces. A robot is controlled to drive a camera to scan the reference pieces from multiple angles and positions. The calibration module's built-in algorithm calculates the camera's intrinsic and extrinsic parameters and their transformation relationship with the robot's coordinate system, establishing a high-precision unified world coordinate system and calibrating the measurement accuracy to the micrometer level. This process ensures the consistency and traceability of the measurement reference throughout the entire lifecycle.

[0030] During formal testing, the robot positions itself along a preset path, ensuring the camera's optical axis is perpendicular to the rivet being tested and its surrounding panel area. For measuring a single rivet: the data acquisition and processing module controls the camera to trigger multiple measurements continuously on the panel area adjacent to the rivet. The specific number of measurements is dynamically configured based on the on-site signal-to-noise ratio, such as 6 times. Subsequently, multiple measurements are also performed on the top surface of the rivet, such as 4 times. Each measurement acquires a data frame containing a 3D point cloud.

[0031] Subsequently, the system executes the core median filtering and calculation process. The module sorts multiple measurement datasets from the panel area and the rivet tip in ascending order of Z-axis height values. Instead of averaging all points, it selects the median value from each of the two sorted datasets—the third value from the panel data and the second value from the rivet data. The algebraic difference between these two median values ​​is then calculated as the flatness assessment result for the rivet. This "median selection" strategy is highly effective against outlier interference caused by instantaneous vibrations, light intensity fluctuations, or tiny surface reflections.

[0032] To cope with the complex vibration environment of the production line, the system integrates multi-level noise reduction strategies, such as... Figure 3 As shown. First, in the data preprocessing stage, a statistical outlier removal algorithm is used to calculate the average distance between each point and its K nearest neighbors, removing points that exceed three times the standard deviation of the global average distance to eliminate significant noise. Second, an edge-preserving filtering algorithm is applied. This embodiment uses an adaptive bilateral filter, whose spatial domain kernel function is adaptively adjusted according to the point cloud density, while the color domain kernel function dynamically changes according to the laser line intensity information. This smooths the surface data while perfectly preserving the edge features of rivets and panels, preventing edge blurring from introducing calculation errors. Finally, the system uses a built-in accelerometer to collect environmental vibration signals in real time and dynamically adjusts the parameters of the filtering algorithm, such as the convolution kernel size, accordingly to achieve adaptive vibration suppression, significantly improving the system's robustness and measurement consistency under complex working conditions.

[0033] Ultimately, the flatness data of each rivet, along with its corresponding robot position coordinates, timestamp, batch number, and other information, are structured and stored in the data storage module. The report generation module extracts data from the database periodically or on demand, generating fully digital inspection reports that meet the requirements of the aviation quality system. It supports data traceability and quality trend analysis by aircraft location, part number, time period, etc., forming a complete technical closed loop from inspection to analysis.

[0034] The experimental subject was a panel assembly of a certain type of aircraft, containing 320 rivets. The experiment simulated the actual vibration and light change environment of the production line. Compared with traditional manual inspection using a handheld laser rangefinder, the sampling rate was 20%. The comparison results are shown in Table 1.

[0035] Table 1. Comparison of Automatic Riveting Forming Quality Inspection Method and Traditional Manual Inspection Results Performance indicators Automatic rivet forming quality detection method Traditional manual detection Effectiveness improvement Single-point average detection time 0.90±0.05 s 3.8±0.6 s Efficiency improved by about 4.2 times Flatness measurement accuracy (standard deviation) 0.018 mm 0.095 mm Significant improvement in measurement consistency Defect detection rate 99.6% 93.75% The system realizes full detection, and manual sampling detection of 64 rivets Stability under different working conditions Error increase <0.01 mm under conventional vibration environment Error increase about 0.06 mm under vibration environment The system has excellent anti-interference ability Data recording error rate 0.1% 6.2% The system automatically records to avoid human input errors Detectable rivet type coverage 98% Limited accessibility, about 85% The system can flexibly position rivets in complex areas Verification shows that, while achieving an average error similar to that of the above embodiments, this system significantly outperforms traditional manual inspection methods in terms of detection efficiency, measurement accuracy, defect detection capability, environmental adaptability, and data reliability. The system possesses excellent anti-interference performance and stability, enabling full-process digital quality data management and effectively supporting quality traceability and process optimization in high-precision manufacturing scenarios. It is particularly suitable for applications in aerospace manufacturing with extremely high quality requirements and fast production cycles, demonstrating significant technological advancements.

[0036] Example 2: The main difference between this embodiment and Embodiment 1 lies in the selection of the specific algorithm in the multi-level noise reduction strategy. The rest of the system structure and workflow are the same, which illustrates the flexibility of the technical solution of the present invention.

[0037] In the data denoising stage, this embodiment uses a wavelet transform-based noise suppression method instead of the adaptive bilateral filtering in Embodiment 1. Specifically, the data acquisition and processing module performs wavelet threshold denoising on the preprocessed point cloud data along the laser line direction. First, a suitable base wavelet representing the workpiece surface morphology is selected to decompose the signal into N layers, obtaining sub-bands of different frequencies. Subsequently, an adaptive threshold function is used to quantize each high-frequency detail coefficient. The determination of this threshold is related to the real-time acquired vibration frequency energy; when the vibration energy is high, a stricter threshold is used to suppress high-frequency noise. Finally, the processed wavelet coefficients are reconstructed to obtain the denoised smooth surface data.

[0038] This method can also effectively separate noise from real surface signals, performs well in environments with strong mechanical vibration interference, and achieves the same technical effects of edge feature preservation and dynamic anti-interference.

[0039] The same set of aircraft panel components with 320 rivets was used as test objects on a vibration platform simulating the environment of an aircraft manufacturing site. The same optical measurement data were processed by wavelet threshold denoising method and conventional Gaussian filtering method respectively. The comparison results are shown in Table 2.

[0040] Table 2. Comparison of wavelet threshold denoising method and conventional Gaussian filtering method Performance indicators Wavelet threshold denoising method Conventional Gaussian filtering method Effectiveness improvement Flatness measurement accuracy (standard deviation, mm) 0.015±0.002 0.028±0.004 Accuracy improved by 46.4% Error increment (mm) under strong vibration environment <0.008 0.022 Anti-interference ability improved by 64% Edge feature retention error (mm) 0.010 0.025 Edge retention ability improved by 60% Signal-to-noise ratio (dB) 28.5 22.3 Signal-to-noise ratio improved by 27.8% Single-point data processing time (ms) 12.5 8.2 Computing efficiency reduced by 34.4% Complex surface adaptability (pass rate%) 98.5% 89.0% Adaptability improved by 9.5% The wavelet thresholding denoising method effectively separates high-frequency noise from surface signals through multi-scale decomposition. Under vibration conditions, the error increment is only 0.008 mm, significantly better than Gaussian filtering's 0.022 mm. This is attributed to its adaptive thresholding mechanism and real-time linkage with vibration signals. The time-frequency localization characteristic of wavelet transform allows it to accurately preserve rivet edge features, while Gaussian filtering, due to global smoothing, leads to edge blurring and easily introduces flatness calculation errors. The wavelet thresholding denoising method has a 34.4% longer computation time than Gaussian filtering, but its adaptability to complex surfaces reaches 98.5%, making it more suitable for the high-precision requirements of aerospace riveting. The signal-to-noise ratio after wavelet thresholding denoising is 27.8% higher than that of Gaussian filtering, confirming its more effective noise suppression and preservation of effective signals. Experimental data shows that in the online inspection scenario of aerospace riveting, the wavelet thresholding denoising method significantly outperforms conventional Gaussian filtering in terms of measurement accuracy, vibration interference resistance, edge preservation, and adaptability to complex surfaces. Although its computational efficiency is slightly lower, its overall performance better meets the requirements of high-reliability manufacturing.

[0041] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable non-transitory storage media containing computer-usable program code.

[0042] The present invention can provide computer program instructions to a management platform of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing equipment to produce a machine, such that the instructions executed by the management platform of the computer or other programmable data processing equipment produce means for implementing the system.

[0043] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means that perform the functions of the system.

[0044] These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process, such that the instructions, which execute on the computer or other programmable apparatus, provide steps for implementing the functions of the system.

Claims

1. An automatic online quality inspection method for riveting and forming based on a 3D line scan camera, characterized in that, include: A calibration operation is performed on the 3D line scan camera to establish a unified measurement benchmark; Multiple optical measurements were performed on the wall panel surface and the rivet surface in the vicinity of the rivet to obtain and record the corresponding datasets. Sort the panel area dataset and the rivet tip dataset according to the measured values, respectively; Select the median value from the panel dataset and the median value from the rivet dataset, and calculate the algebraic difference between the two median values ​​as the flatness evaluation result of the rivets. The evaluation results of multiple rivets are stored in the database, and a structured quality inspection report is generated.

2. The method according to claim 1, characterized in that: The three-dimensional line scan camera is a high-speed, high-precision optical measurement device. During the measurement process, it integrates a multi-level noise reduction strategy, identifies and removes outliers in the measurement data through statistical methods, and uses an edge-preserving filtering algorithm to smooth the data surface.

3. The method according to claim 2, characterized in that: The edge-preserving filtering algorithm includes adaptive bilateral filtering or Gaussian filtering, and further introduces a noise suppression mechanism that dynamically adjusts the filtering parameters based on real-time acquired environmental vibration signals.

4. The method according to claim 3, characterized in that: The noise suppression mechanism that dynamically adjusts the filtering parameters specifically involves adaptively adjusting the convolution kernel size or threshold parameter of the filtering algorithm based on the vibration frequency energy.

5. The method according to claim 3, characterized in that: The filtering algorithm further includes a wavelet threshold denoising method, which achieves high-frequency noise separation and effective signal enhancement by performing multi-scale decomposition and threshold reconstruction on the optical measurement signal.

6. The method according to claim 2, characterized in that: Before data acquisition, the threshold parameters of each step in the multi-level noise suppression strategy are pre-calibrated and adapted based on the optical reflection characteristics and structural complexity of the surface under test.

7. An automated riveting forming online quality inspection system based on a 3D line scan camera, characterized in that: The system executes the method according to any one of claims 1-6 during operation, including: A 3D line scan camera is used to perform optical scanning and data acquisition; The data acquisition and processing module is configured to perform sorting of the dataset, extraction of intermediate values, and calculation of algebraic differences. The data storage module is used to store the rivet's detection data and related information; The report generation module is used to generate quality inspection reports; The calibration module is used to perform camera coordinate system calibration and periodic accuracy verification.

8. The system according to claim 7, characterized in that: The detection path of the system is automatically calculated in real time based on the position and topology of the rivet to be tested.

9. The system according to claim 7, characterized in that: The system is equipped with an adaptive operation control unit, which is used to sense the status of interference sources during the detection process and decide whether to initiate a re-inspection mechanism; all sensor data and diagnostic logs are integrated into the same database to support quality traceability and coordinated adjustment of the production system.

10. A computer-readable storage medium storing a computer program, characterized in that: The computer program is executed by the processor to perform the method according to any one of claims 1-6.

Images