Aluminum profile processing quality detection method and system

Abstract

The invention discloses an aluminum profile machining quality detection method and system. The method comprises the steps that multi-mode defect detection data and the quality acceptance requirement of a user are acquired; according to the quality acceptance requirement, carrying out inversion analysis on the multi-mode defect detection data; judging whether the quality acceptance requirement is met or not according to the analysis result, and if yes, judging that the quality detection result is qualified; otherwise, judging that the quality detection result is unqualified. The method is not only suitable for intelligent screening in batch detection, but also can provide a basis for quality pre-judgment and process feedback in a complex use scene, and has the advantages of high detection precision, strong adaptability, high intelligent degree and the like.

Description

Technical Field

[0001] The present invention relates to the technical field of quality inspection, and in particular to a method and system for inspecting the processing quality of aluminum profiles. Background Art

[0002] Aluminum profiles are widely used in construction, transportation, electronics, aerospace and other fields due to their light weight, high strength and good corrosion resistance. As the requirements for the application performance of aluminum profiles increase, quality control during the molding process becomes particularly important. During the processing of aluminum profiles, they are easily affected by factors such as process parameters, raw material defects, and uneven cooling rates, which can lead to defects such as cracks, pores, warping, and uneven wall thickness in the products. These defects may seriously affect their structural performance and service life. Traditional quality inspection methods mostly rely on manual sampling or surface visual inspection, which cannot fully evaluate the internal defects of the product and their impact on mechanical properties. They also have problems such as blind spots in detection, low efficiency, and inconsistent judgment standards.

[0003] With the development of nondestructive testing technology, multimodal testing methods such as ultrasonic testing, eddy current testing, optical scanning, and X-ray imaging have been gradually applied to the identification of aluminum profile defects. Although these technologies can achieve higher-precision data acquisition, they still face two challenges in actual engineering applications: first, the variety and dimensionality of the test data are diverse, and there is a lack of a unified data fusion and interpretation mechanism; second, there is a significant disconnect between the test results and the actual load-bearing capacity of the material, which cannot effectively support quality judgments based on "performance in use." In addition, faced with diverse usage requirements under different working conditions, how to combine test data with structural mechanical properties to achieve a feedforward assessment of quality risks has become an urgent problem to be solved. Summary of the Invention

[0004] In view of the above-mentioned problems, the present invention is proposed.

[0005] Therefore, the technical problem solved by the present invention is that the existing aluminum profile processing quality detection method cannot meet the requirements for the detection of performance during use.

[0006] To solve the above technical problems, the present invention provides the following technical solutions: a method for detecting the processing quality of aluminum profiles, comprising:

[0007] Obtain multimodal defect detection data and user's quality acceptance requirements;

[0008] performing an inversion analysis on the multimodal defect detection data according to the quality acceptance requirements;

[0009] The analysis results are used to determine whether the product meets the quality inspection requirements. If so, the product is deemed qualified; otherwise, it is deemed unqualified.

[0010] As a preferred solution of the aluminum profile processing quality inspection method described in the present invention, the multimodal defect detection data includes, for each quality defect type of the aluminum profile, using the corresponding detection means to perform defect detection and obtain the detection data under each detection means.

[0011] As a preferred solution of the aluminum profile processing quality inspection method of the present invention, wherein: the user's quality acceptance requirements include the user's minimum index for each quality defect inspection result and the user's usage requirements for the aluminum profile;

[0012] The quality defect detection results include identifying the quality defects of the aluminum profiles using the detection data under each detection method and generating quantifiable parameters for each defect;

[0013] The minimum index is a restriction on quantifiable parameters in the detection results of a single quality defect of an aluminum profile; if the detection result of any quality defect of the aluminum profile does not meet the restriction of the minimum index, the inversion analysis stage is skipped and the quality inspection result is directly output as qualified; if the detection results of each quality defect of the aluminum profile meet the restriction of the minimum index, an inversion analysis is performed based on the user's usage requirements for the aluminum profile and the detection data under each detection method.

[0014] As a preferred solution of the aluminum profile processing quality inspection method of the present invention, wherein: the user's use requirements for the aluminum profile include the user's requirements for the aluminum profile to be able to be used normally under working conditions of a specific purpose;

[0015] Among them, when setting the usage requirements, the user provides the limit conditions under each working condition;

[0016] The limit condition includes the maximum value of the working condition parameter, which is composed of two parameters: maximum pressure and minimum force area.

[0017] As a preferred embodiment of the aluminum profile processing quality inspection method of the present invention, the inverse analysis of the multi-modal defect detection data includes making an assumption about the aluminum profile: any position of the aluminum profile may serve as an action point under extreme conditions;

[0018] Under the above assumptions, the stress that may be generated at each point is simulated to obtain the ultimate stress at each point;

[0019] At each point of the aluminum profile, each type of test data is inverted and analyzed to obtain the stress threshold at each point;

[0020] By comparing the ultimate stress at each point with the stress threshold, it is determined whether each point can withstand the ultimate condition; when all points can withstand the ultimate condition, it is determined that the quality acceptance requirements are met.

[0021] As a preferred embodiment of the aluminum profile processing quality inspection method of the present invention, the three-dimensional geometric model of the aluminum profile is spatially discretized to construct a three-dimensional volume unit grid, where each grid node corresponds to a spatial coordinate point (x, y, z); wherein each grid point is regarded as an independent point position;

[0022] According to the limit conditions, a normal force is applied to any position of the aluminum profile, and the pressure is a quasi-static constant load; a finite element solver is used to perform a three-dimensional nonlinear mechanical simulation;

[0023] In the solution results of the force applied at each position, find the maximum equivalent stress point in the entire model; record the stress response values of all other points when the maximum point appears; and construct a three-dimensional stress propagation map with the maximum stress point as the core;

[0024] The ultimate stress is expressed as: {Z1, Z2, ..., Z n};

[0025] Among them, Z n =(σ max，n ,σ(S) n );Z n represents the ultimate stress at the nth applied position; n represents the number of applied positions; σ max，n Indicates the maximum stress value and the corresponding coordinate position of the maximum stress at the nth applied position; S represents the set of all points;

[0026] σ(S) n ={σ 1，n , σ 2，n ,...,σ f，n} represents the set of characteristic points under the n-th applied position; σ f，n It represents the stress magnitude at the fth coordinate position and the coordinate position under the nth applied position.

[0027] As a preferred embodiment of the aluminum profile processing quality detection method of the present invention, the inverse analysis includes obtaining the mean of the detection data of each mode at each point as the characteristic value T = {T1, T2, ..., T j}; Taking the characteristic value as input, using the Bayesian network to output the probability of occurrence of each defect at each point;

[0028] Using the typical test data pre-selected for each defect, calculate the comprehensive defect ratio at each point: For each defect pre-selected typical test data, match them in any proportion so that the matching result meets the constraints:

[0029] in, is embedded into the corresponding Q g Elements in, both appear at the same time; D g，i represents the g-th defect type, the characteristic value of the detection data i; T i Indicates the characteristic value of the detection data i at the point; i represents the index of the detection data type; j represents the number of detection data types; Q g represents the proportion of the g-th defect type; G represents the number of defect types; Indicates the proportional coefficient of the g-th defect type, which is not less than 0 and less than Indicates the maximum proportional coefficient of the g-th defect type;

[0030] Get all the matching sets B that satisfy the constraints e ={b1, b2, ..., b c}; b c Indicates the cth ratio, c indicates the number of ratios obtained, B e Represents the ratio set of the e-th point;

[0031] Assume: Q e，G Indicates the proportion of the Gth defect type at the eth point; b e，0 Represents the ratio of the probability components of the Bayesian network output at the e-th point; Denotes the embedding Q e，G The proportionality coefficient of

[0032] In the screening ratio set, with b e，0 The closest ratio is recorded as: Q e，1 :Q e，2 :...:Q e，G ;

[0033] In the selected ratio, for each element Q e，G Extract the scale factor embedded in

[0034] Use the pre-fitted function, input the proportional coefficient and defect type, and output the reduction rate of the maximum stress value;

[0035] Calculate the reduction rate of each defect type for each node, use the screened ratio as the weight coefficient, and perform weighted summation to obtain the actual reduction rate; use the actual reduction rate to reduce the standard maximum stress value of the node to obtain the stress threshold.

[0036] An aluminum profile processing quality inspection system, wherein: a detection unit obtains multi-modal defect detection data and user's quality acceptance requirements;

[0037] an analysis unit, performing inversion analysis on the multimodal defect detection data according to the quality acceptance requirements;

[0038] The judgment unit judges whether the quality inspection result meets the quality inspection requirements according to the analysis result. If so, the quality inspection result is judged to be qualified; otherwise, the quality inspection result is judged to be unqualified.

[0039] A computer device comprises: a memory and a processor; the memory stores a computer program, wherein: when the processor executes the computer program, the steps of any one of the methods of the present invention are implemented.

[0040] A computer-readable storage medium stores a computer program, wherein: when the computer program is executed by a processor, the steps of any one of the methods of the present invention are implemented.

[0041] Beneficial effects of the present invention: The aluminum profile processing quality detection method provided by the present invention can realize the coordinated analysis of multi-modal defect data and operating conditions, breaking through the limitations of traditional detection that only relies on surface results or fixed indicators to judge. By constructing a three-dimensional model and introducing full-field extreme working condition simulation, the potential failure points of aluminum profiles under any load path are effectively identified, thereby improving the comprehensiveness and reliability of structural safety assessment. Combining the Bayesian network with the ratio optimization algorithm, the quantitative inversion of the influence of multiple types of defects is realized, and the mechanical properties of the nodes are dynamically reduced according to the defect ratio to ensure that the evaluation results are closer to the actual service status. This method is not only suitable for intelligent screening in batch detection, but also provides a basis for quality prediction and process feedback in complex usage scenarios. It has the advantages of high detection accuracy, strong adaptability, and high degree of intelligence. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0043] Figure 1 This is an overall flow chart of a method for detecting the processing quality of aluminum profiles provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0044] To make the above-mentioned objects, features, and advantages of the present invention more clearly understood, the following detailed description of the specific embodiments of the present invention is given in conjunction with the accompanying drawings. It is obvious that the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in this field without creative work should fall within the scope of protection of the present invention.

[0045] Reference Figure 1 , as one embodiment of the present invention, provides a method for detecting the processing quality of aluminum profiles, comprising:

[0046] S1: Obtain multimodal defect detection data and user's quality acceptance requirements.

[0047] Multimodal defect detection data includes defect detection using corresponding detection methods for each type of quality defect in aluminum profiles, and the detection data obtained under each detection method. For crack defects, methods such as acoustic emission detection, ultrasonic detection, or eddy current detection are used to obtain high-frequency acoustic signals, ultrasonic echo time attenuation data, or eddy current impedance change values generated when cracks initiate or expand, and then extract characteristic parameters such as crack length, depth, and location. For internal pore defects, multi-frequency eddy current detection, X-ray digital imaging, or CT scanning are used to determine the size, density, and spatial distribution of pores through phase delay characteristics, image grayscale distribution, or voxel-level pore structure. For surface flatness anomalies, structured light projection and three-dimensional laser scanning are used to obtain point cloud data of the aluminum profile surface, and warping and concave-convex conditions are evaluated by calculating information such as local curvature and profile height difference. The raw data obtained by each detection method constitutes multimodal input, providing a data foundation for subsequent defect identification, feature extraction, and quality assessment.

[0048] The user's quality acceptance requirements include the user's minimum indicators for each quality defect detection result and the user's usage requirements for aluminum profiles. The quality defect detection results include the use of detection data under each detection method to identify the quality defects of aluminum profiles and generate quantifiable parameters for each defect; specifically, for crack defects, the generated quantifiable parameters include crack length, depth, number or acoustic emission energy value. For flatness defects, the generated quantifiable parameters include local curvature value, maximum height difference value, and warpage deviation value. For internal pore defects, the generated quantifiable parameters include maximum pore diameter, pore density per unit area, eddy current phase delay amplitude change, etc.

[0049] The minimum index is a restriction on quantifiable parameters in the detection results of a single quality defect of an aluminum profile; if the detection result of any quality defect of the aluminum profile does not meet the restriction of the minimum index, the inversion analysis stage is skipped and the quality inspection result is directly output as qualified; if the detection results of each quality defect of the aluminum profile meet the restriction of the minimum index, an inversion analysis is performed based on the user's usage requirements for the aluminum profile and the detection data under each detection method.

[0050] After acquiring multimodal defect data, an independent judgment threshold is first set for each quality defect type to quickly identify serious defects, thereby building a pre-judgment threshold in the system analysis. If any defect parameter in the test results does not reach the minimum index, it means that the defect can be ignored or does not pose an actual safety risk in the current usage scenario. At this time, there is no need to enter the subsequent complex inversion analysis stage, and it can be directly judged as qualified, which improves the efficiency and adaptability of the detection process; and when all defects reach the minimum index, that is, all defect parameters have potential impact risks, then enter the inversion analysis stage, through three-dimensional simulation and performance inversion, further combined with user needs to conduct a refined assessment of the overall structural safety. This mechanism realizes "defect pre-screening + graded judgment + intelligent diversion", which not only reduces the system's computing burden, but also improves the pertinence and engineering adaptability of the evaluation, reflecting the advantages of dynamic decision-making driven by data.

[0051] The user's requirements for the use of aluminum profiles include the user's requirements for the normal use of aluminum profiles under working conditions for specific purposes. Among them, when setting the usage requirements, the user provides the extreme conditions under each working condition. The extreme conditions include the maximum value of the working condition parameter; it is composed of two parameters: maximum pressure and minimum force area. Incorporating the user's actual usage scenario requirements for aluminum profiles into the quality inspection process, the inspection and evaluation results are not only based on standardized defect data judgment, but also better meet the safety requirements of specific application scenarios. By constructing a usage demand model based on the "working conditions" input by the user, the quality assessment is not only limited to the identification of defects in the material itself, but also focuses on its load-bearing capacity and service performance in the target application.

[0052] S2: Performing inversion analysis on the multimodal defect detection data according to the quality acceptance requirements.

[0053] The inverse analysis of the multimodal defect detection data involves assuming that any location on the aluminum profile could serve as a point of action under extreme conditions. Based on this assumption, the stresses that could potentially be generated at each location are simulated to determine the ultimate stress at each location.

[0054] At each point on the aluminum profile, inversion analysis is performed on each test data point to determine the stress threshold at each point. By comparing the ultimate stress at each point with the stress threshold, it is determined whether each point can withstand the extreme conditions. If all points can withstand the extreme conditions, it is determined to meet the quality acceptance requirements.

[0055] By assuming that each point of the aluminum profile is a potential limit load point, a comprehensive assessment under the most unfavorable working conditions can be achieved. Compared with the traditional method of performing local simulation only at a specific loading point, this method obtains the stress response value of each point under the maximum load through full structure traversal simulation, forming an "ultimate stress distribution map" to reflect potential weaknesses or vulnerable areas. At the same time, combined with the multimodal detection data corresponding to each point, the stress tolerance (i.e., stress threshold) of the material at that position under the current defect state is inferred to ensure that the evaluation results are not only based on theoretical calculations, but also fully reflect the impact of actual defects on structural strength. Finally, by comparing the ultimate stress with the stress threshold point by point, the overall stability of the structure under extreme working conditions is judged, and the integrated judgment standard of "structural integrity + defect tolerance" is realized. This design improves the rigor and adaptability of structural quality assessment, and effectively supports reliability screening and risk warning in key application scenarios.

[0056] The three-dimensional geometric model of the aluminum profile is spatially discretized to construct a three-dimensional volume unit grid. Each grid node corresponds to a spatial coordinate point (x, y, z); each grid point is regarded as an independent point.

[0057] Based on the limiting conditions, a normal force is applied to any position on the aluminum profile, using a quasi-static dead load. A finite element solver is used to perform a three-dimensional nonlinear mechanical simulation. This can be done by simulating several preset force application locations, or by randomly selecting multiple force application locations from the center of the position.

[0058] In the solution results of the force applied at each position, find the maximum equivalent stress point in the entire model; record the stress response values of all other points when the maximum point appears; and construct a three-dimensional stress propagation map with the maximum stress point as the core.

[0059] The ultimate stress is expressed as: {Z1, Z2, ..., Z n}.

[0060] Among them, Z n =(σ max，n ,σ(S) n );Z n represents the ultimate stress at the nth applied position; n represents the number of applied positions; σ max，n Indicates the maximum stress value and the corresponding coordinate position of the maximum stress at the nth applied position; S represents the set of all points. σ(S) n ={σ 1，n , σ 2，n ,...,σ f，n} represents the set of characteristic points under the n-th applied position; σ f，n It represents the stress magnitude at the fth coordinate position and the coordinate position under the nth applied position.

[0061] By establishing a three-dimensional discrete model of the aluminum profile structure and simulating loading at multiple possible force application points, a stress propagation map based on extreme working conditions is constructed, providing structural-level stress risk identification capabilities for quality inspection. By spatially discretizing the aluminum profile model, each grid point has a unique three-dimensional coordinate identity and can serve as an independent loading or response node, ensuring positional resolution for stress analysis. Using a finite element solver to apply quasi-static normal dead loads at several representative or randomly sampled force application locations effectively simulates the effects of common or extreme working conditions on the entire structure while avoiding the high computational cost of full-point loading. By extracting the maximum equivalent stress point under each loading condition and tracking the full-field response, a three-dimensional stress propagation map centered on the stress peak is obtained. This map reflects the diffusion and concentration of the internal stress state of the material due to the application of external forces, providing a basis for subsequent determination of whether each point meets its local stress threshold.

[0062] Furthermore, the inversion analysis includes obtaining the mean of the detection data of each mode at each point as the characteristic value T={T1, T2, ..., T j}; Taking the characteristic value as input, the Bayesian network is used to output the probability of occurrence of each defect at each point.

[0063] Using the typical test data pre-selected for each defect (a defect may be reflected in multiple test data), calculate the comprehensive defect ratio at each point: For each defect pre-selected typical test data, match them in any proportion so that the matching result meets the constraints:

[0064] in, is embedded into the corresponding Q g Elements in, both appear at the same time; D g，i represents the g-th defect type, the characteristic value of the detection data i; T i Indicates the characteristic value of the detection data i at the point; i represents the index of the detection data type; j represents the number of detection data types; Q g represents the proportion of the g-th defect type; G represents the number of defect types; Indicates the proportional coefficient of the g-th defect type, which is not less than 0 and less than Indicates the maximum proportional coefficient of the g-th defect type.

[0065] Get all the matching ratios B that satisfy the constraints e ={b1, b2, ..., b c}; b c Indicates the cth ratio, c indicates the number of ratios obtained, B e Represents the ratio set of the e-th point.

[0066] Assume: Q e，G Indicates the proportion of the Gth defect type at the eth point; b e，0 Represents the ratio of the probability components of the Bayesian network output at the e-th point; Denotes the embedding Q e，G The proportional coefficient.

[0067] In the screening ratio set, with b e，0 The closest ratio is: Q e，1 :Q e，2 :...:Q e，G .

[0068] In the selected ratio, for each element Q e，G Extract the scale factor embedded in

[0069] Based on multimodal defect detection data, a ratio analysis mechanism is established that can reversely infer the proportion of defect types. Taking into account that a certain type of defect (such as cracks or pores) may be reflected in multiple detection data, there is cross-sensitivity between different detection features. Therefore, relying solely on data from a single modality cannot accurately quantify the impact of the defect. To this end, the system pre-sets mapping samples between typical defects and their characteristic responses, and constructs multiple feasible defect ratio ratio sets based on the eigenvalues of different detection data dimensions. Under the premise of meeting specific constraints (such as the embedded features must appear synchronously and the proportion is within a reasonable range), the distance is minimized by matching with the probability ratio output by the Bayesian model to screen out the ratio result closest to the actual state.

[0070] Ultimately, the defect ratio coefficient is extracted from the optimal ratio and used to calculate the reduction effect of each defect type on the material's stress-bearing capacity, achieving a precise transformation from "detection signature" to "mechanical damage quantification." This method improves the fusion and utilization of multimodal data, addresses the assessment uncertainty caused by the mixing and mutual influence of defect types in complex scenarios, and enhances the interpretability and reliability of quality inspection results.

[0071] Furthermore, a pre-fitted function is used to input the proportional coefficient and defect type, and output the reduction rate of the maximum stress value. In this design, a quantitative relationship function between the proportional coefficient and the maximum stress of the material is established for each defect type, and a pre-fitted regression model or interpolation function is used to achieve the mapping from defect proportion to stress reduction rate. In engineering implementation, this function can be constructed based on a large amount of actual test or finite element simulation data through regression fitting, support vector regression (SVR), polynomial fitting or neural network model. For example, for crack defects, the influence curve can be obtained by fitting different crack lengths with material strength test data; for pore defects, the weakening effect of different pore densities on yield stress can be simulated to generate a data-driven mapping relationship.

[0072] In actual use, the system substitutes the input defect type and corresponding ratio as parameters into the function, quickly outputting the reduction rate of each defect on the material's mechanical properties. Because the function structure has been pre-fitted through offline training, online use requires only parameter substitution for calculation. This reduces computational effort and provides fast response, making it suitable for embedding into quality inspection systems for automated, real-time evaluation. Furthermore, the function model is scalable and can be retrained and adaptively updated based on product category, material type, or new detection features, ensuring continuous improvement in analysis accuracy and applicability.

[0073] Calculate the reduction rate of each defect type for each node, use the screened ratio as the weight coefficient, and perform weighted summation to obtain the actual reduction rate; use the actual reduction rate to reduce the standard maximum stress value of the node to obtain the stress threshold.

[0074] S3: Determine whether the analysis results meet the quality acceptance requirements. If yes, the quality inspection result is determined to be qualified; otherwise, the quality inspection result is determined to be unqualified.

[0075] On the other hand, this embodiment further provides an aluminum profile processing quality inspection system, which includes: a detection unit that obtains multi-modal defect detection data and user's quality acceptance requirements.

[0076] An analysis unit performs an inversion analysis on the multimodal defect detection data according to the quality acceptance requirements.

[0077] The judgment unit judges whether the quality inspection result meets the quality inspection requirements according to the analysis result. If so, the quality inspection result is judged to be qualified; otherwise, the quality inspection result is judged to be unqualified.

[0078] If the above functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, and other media that can store program code.

[0079] The logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing the logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (e.g., a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device). For purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0080] More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection with one or more wires (electronic devices), a portable computer disk cartridge (magnetic devices), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disc read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering, or processing in another suitable manner as necessary, and then stored in a computer memory.

[0081] It should be understood that various parts of the present invention can be implemented using hardware, software, firmware, or a combination thereof. In the above-described embodiments, multiple steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one or combination of the following technologies known in the art can be used: a discrete logic circuit having logic gate circuits for implementing logic functions on data signals, an application-specific integrated circuit having suitable combinational logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0082] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for detecting the processing quality of aluminum profiles, characterized in that: include: Obtain multimodal defect detection data and user's quality acceptance requirements; performing an inversion analysis on the multimodal defect detection data according to the quality acceptance requirements; Determine whether the analysis results meet the quality acceptance requirements. If so, the quality test results are considered qualified. Otherwise, the quality inspection result is judged to be unqualified.

2. The aluminum profile processing quality inspection method according to claim 1, wherein: The multimodal defect detection data includes, for each quality defect type of the aluminum profile, defect detection is performed using a corresponding detection means, and detection data obtained under each detection means.

3. The aluminum profile processing quality inspection method according to claim 2, characterized in that: The user's quality acceptance requirements include the user's minimum indicators for each quality defect detection result and the user's usage requirements for aluminum profiles; The quality defect detection results include identifying the quality defects of the aluminum profiles using the detection data under each detection method and generating quantifiable parameters for each defect; The minimum index is a restriction on quantifiable parameters in the detection results of a single quality defect of an aluminum profile; if the detection result of any quality defect of the aluminum profile does not meet the restriction of the minimum index, the inversion analysis stage is skipped and the quality inspection result is directly output as qualified; if the detection results of each quality defect of the aluminum profile meet the restriction of the minimum index, an inversion analysis is performed based on the user's usage requirements for the aluminum profile and the detection data under each detection method.

4. The aluminum profile processing quality inspection method according to claim 3, wherein: The user's requirements for the use of aluminum profiles include the user's requirements for the aluminum profiles to be able to be used normally under working conditions for specific purposes; Among them, when setting the usage requirements, the user provides the limit conditions under each working condition; The limit condition includes the maximum value of the working condition parameter, which is composed of two parameters: maximum pressure and minimum force area.

5. The aluminum profile processing quality inspection method according to claim 4, characterized in that: The inverse analysis of the multimodal defect detection data includes making an assumption about the aluminum profile: any position of the aluminum profile may serve as an action point under the extreme condition; Under the above assumptions, the stress that may be generated at each point is simulated to obtain the ultimate stress at each point; At each point of the aluminum profile, each type of test data is inversely analyzed to obtain the stress threshold at each point; By comparing the ultimate stress at each point with the stress threshold, it is determined whether each point can withstand the ultimate condition; when all points can withstand the ultimate condition, it is determined that the quality acceptance requirements are met.

6. The aluminum profile processing quality inspection method according to claim 5, characterized in that: Discretize the 3D geometric model of the aluminum profile in space and construct a 3D volume unit grid. Each grid node corresponds to a spatial coordinate point (x, y, z); each grid point is regarded as an independent point. According to the limit conditions, a normal force is applied to any position of the aluminum profile, and the pressure is a quasi-static constant load; a finite element solver is used to perform a three-dimensional nonlinear mechanical simulation; In the solution results of the force applied at each position, find the maximum equivalent stress point in the entire model; record the stress response values of all other points when the maximum point appears; and construct a three-dimensional stress propagation map with the maximum stress point as the core; The ultimate stress is expressed as: {Z1, Z2, ..., Z n }; Among them, Z n =(σ max ,n,σ(S) n );Z n represents the ultimate stress at the nth applied position; n represents the number of applied positions; σ max，n Indicates the maximum stress value and the corresponding coordinate position of the maximum stress at the nth applied position; S represents the set of all points; σ(S) n ={σ 1,n ,σ 2,n ,...,σ f，n } represents the set of characteristic points under the n-th applied position; σ f，n It represents the stress magnitude at the fth coordinate position and the coordinate position under the nth applied position.

7. The aluminum profile processing quality inspection method according to claim 6, characterized in that: The inverse analysis includes obtaining the mean value of the detection data of each mode at each point as the characteristic value T={T1, T2, ..., T j }; Taking the characteristic value as input, using the Bayesian network to output the probability of occurrence of each defect at each point; Using the typical test data pre-selected for each defect, calculate the comprehensive defect ratio at each point: For each defect pre-selected typical test data, match them in any proportion so that the matching result meets the constraints: in, is embedded into the corresponding Q g Elements in, both appear at the same time; D g，i represents the g-th defect type, the characteristic value of the detection data i; T i Indicates the characteristic value of the detection data i at the point; i represents the index of the detection data type; j represents the number of detection data types; Q g represents the proportion of the g-th defect type; G represents the number of defect types; Indicates the proportional coefficient of the g-th defect type, which is not less than 0 and less than Indicates the maximum proportional coefficient of the g-th defect type; Get all the matching sets B that satisfy the constraints e ={b1,b2,...,b c }; b c Indicates the cth ratio, c indicates the number of ratios obtained, B e Represents the ratio set of the e-th point; Assume: Q e，G Indicates the proportion of the Gth defect type at the eth point; b e,0 Represents the ratio of the probability components of the Bayesian network output at the e-th point; Denotes the embedding Q e,G The proportionality coefficient of In the screening ratio set, with b e，0 The closest ratio is recorded as: Q e,1 :Q e,2 :...:Q e,G ; In the selected ratio, for each element Q e，G Extract the scale factor embedded in Use the pre-fitted function, input the proportional coefficient and defect type, and output the reduction rate of the maximum stress value; Calculate the reduction rate of each defect type for each node, use the screened ratio as the weight coefficient, and perform weighted summation to obtain the actual reduction rate; use the actual reduction rate to reduce the standard maximum stress value of the node to obtain the stress threshold.

8. An aluminum profile processing quality inspection system using the method according to any one of claims 1 to 7, characterized in that: Inspection unit, which obtains multi-modal defect detection data and the user's quality acceptance requirements; an analysis unit, performing inversion analysis on the multimodal defect detection data according to the quality acceptance requirements; A judgment unit, which judges whether the quality inspection requirements are met based on the analysis results, and if so, judges the quality inspection result as qualified; Otherwise, the quality inspection result is judged to be unqualified.

9. A computer device comprising: A memory and a processor; the memory stores a computer program, wherein the processor implements the steps of the method according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images