Electronic component material identification management method

Abstract

The invention relates to the technical field of component management, and discloses an electronic component material identification management method, which comprises the following steps: synchronously acquiring a grayscale image, a three-dimensional point cloud and weight data through X-ray imaging, a laser radar and a weight sensor, and fusing and generating a multi-dimensional feature matrix based on a dynamic weight distribution algorithm; extracting physical characteristic parameters corresponding to the electronic components based on the multi-dimensional characteristic matrix, generating unique identification codes through multi-parameter matching in combination with a material physical characteristic database, and outputting material types and specifications; for a high-temperature or strong electromagnetic interference scene, the X-ray detector adjusts gain and sampling frequency in real time, image distortion is corrected through point cloud spatial correlation, and a high-fidelity image is output; the OCR technology automatically identifies label information to realize inventory dynamic updating; and through geometric consistency verification of the high-fidelity image and the multi-dimensional features, if conflicts occur, an early-warning material physical characteristic database is triggered. According to the invention, the precision and adaptability of electronic component identification management can be improved.

Description

Technical Field

[0001] The present application relates to the technical field of component management, and in particular to a method for identifying and managing electronic component materials. Background Art

[0002] In the identification and management of electronic components, traditional X-ray imaging technology has three major bottlenecks: metal reflection interference causes the contrast of high-density areas (such as BGA solder joints) to decrease, masking defects such as microcracks; insufficient dynamic adaptation makes fixed models (such as SVM) difficult to handle special-shaped components (such as folding knives), requiring manual parameter adjustment; high temperature (≥80℃) or strong electromagnetic interference (≥100V / m) in weak environmental interference resistance can easily cause thermal noise and signal distortion in the detector, resulting in a high false detection rate.

[0003] While existing technologies attempt to improve performance through photon counting detectors or deep learning, they are still limited by high costs, computing bottlenecks due to the reliance on large amounts of labeled data, and the inability of a single anti-interference solution to effectively address complex environmental interference. Breakthroughs are needed to address the bottlenecks in accuracy, adaptability, and stability in electronic component identification and management.

[0004] From the above, we can see that how to improve the accuracy and adaptability of electronic component identification and management still needs to be solved. Summary of the Invention

[0005] In order to improve the accuracy and adaptability of electronic component identification management, the present application provides an electronic component material identification management method.

[0006] In a first aspect, the present application provides a method for identifying and managing electronic component materials, which adopts the following technical solutions: A method for identifying and managing electronic components and materials, comprising: Acquire an X-ray grayscale image of the electronic component using an X-ray imaging device, simultaneously acquire three-dimensional point cloud data corresponding to the electronic component using a laser radar, and collect weight information corresponding to the electronic component using a weight sensor; and fuse the X-ray grayscale image, the three-dimensional point cloud data, and the weight information based on dynamic weight distribution of the signal-to-noise ratio to generate a fused multidimensional feature matrix; Extracting physical characteristic parameters corresponding to the electronic components based on the multidimensional feature matrix, the physical characteristic parameters including density, geometric symmetry, and surface curvature; retrieving a pre-set material physical characteristic database, generating a unique identification code by using a multi-parameter joint matching algorithm between the physical characteristic parameters and the material physical characteristic database, and outputting material type and specification information; An adaptive filtering circuit is integrated at the front end of the X-ray detector to obtain the corresponding ambient temperature and electromagnetic field strength in real time, and adjust the X-ray detector gain and sampling frequency based on the ambient temperature and the electromagnetic field strength; based on the three-dimensional point cloud data, a spatial correlation algorithm is used to correct X-ray image distortion caused by high temperature or strong electromagnetic interference, and a corrected high-fidelity image is output; The unique identification code is associated with the material database, and the label information is automatically recognized through structured OCR technology to complete the material warehousing, warehousing and dynamic inventory updates; the high-fidelity image and the multi-dimensional feature matrix are subjected to geometric consistency verification. If the material type and specification information conflict with the database records, an abnormal matching result is determined, and a secondary verification is performed based on the abnormal matching result to trigger an early warning mechanism and generate corrected inventory data.

[0007] By adopting the above technical solution, multimodal data fusion (X-ray grayscale images, 3D point cloud data, and weight information) combined with a dynamic weight allocation algorithm enables precise extraction of multi-dimensional features of electronic components, effectively improving recognition accuracy. Simultaneously, adaptive filtering circuits and spatial correlation correction algorithms compensate for ambient temperature and humidity, electromagnetic interference, and image distortion in real time, enhancing the system's robustness under complex operating conditions. Furthermore, automatic label information recognition based on structured OCR and a database geometric consistency verification mechanism not only ensures the accuracy of material classification and specifications, but also dynamically corrects inventory data through abnormal matching warnings and secondary verification, significantly improving management adaptability and intelligence.

[0008] Optionally, during the generation of the multidimensional feature matrix, the method further includes: constructing a three-dimensional geometric outline of the electronic component using the three-dimensional point cloud data, and projecting the three-dimensional geometric outline into the two-dimensional coordinate system of the X-ray grayscale image to form a spatial alignment reference frame; Based on the weight data collected by the weight sensor, the density distribution of the components is calculated by mass-volume ratio, and the density distribution is mapped to the corresponding position of the three-dimensional point cloud data; Correlating the grayscale value of the X-ray grayscale image with the density distribution, and generating a corrected grayscale image through a grayscale-density mapping function, wherein grayscale value = K × density value + bias term, and K is a proportional coefficient related to the material type; The corrected grayscale image, three-dimensional point cloud data and density distribution are fused at the feature level to generate a multi-dimensional feature matrix.

[0009] By adopting the above technical solution, the geometric outline is constructed through the three-dimensional point cloud and aligned with the X-ray image space to achieve spatial consistency of multimodal data; the density distribution is generated by combining the weight data and mapped to the three-dimensional structure to enhance the correlation of material properties; the X-ray image is corrected through the grayscale-density mapping function to eliminate the grayscale deviation caused by material differences; finally, the corrected multidimensional data is integrated to generate a feature matrix, which can improve the geometric accuracy and material recognition ability of electronic component identification.

[0010] Optionally, in the process of dynamically adjusting the detector gain and sampling frequency according to the collected temperature and electromagnetic field strength using a preset compensation parameter table, wherein the compensation parameter table includes gain adjustment coefficients and sampling frequency thresholds corresponding to different metal materials; the method further includes: The adjusted detector output signal and the lidar point cloud data are input into a hybrid Kalman filter, wherein the hybrid Kalman filter includes: Temperature compensation module: dynamically adjusts the process noise covariance matrix based on the temperature change rate; Electromagnetic field compensation module: dynamically adjusts the measurement noise covariance matrix based on the amplitude of electromagnetic field intensity fluctuations; Output high-fidelity X-ray images corrected by the hybrid Kalman filter.

[0011] By adopting the above technical solution, the X-ray detector signal and the lidar point cloud data are dynamically fused through a hybrid Kalman filter, and combined with the temperature compensation module and the electromagnetic field compensation module, the influence of environmental temperature change and electromagnetic interference on image quality can be effectively suppressed. At the same time, the detector gain and sampling frequency are optimized based on the material characteristic parameter table to achieve real-time correction of high-fidelity X-ray images, which can improve the noise resistance and geometric accuracy of electronic component identification under complex working conditions.

[0012] Optionally, during the multi-dimensional verification process, the method further includes: Comparing the material type and the specification information with a preset tolerance range in a material physical property database to generate a preliminary matching result; The high-fidelity image and the multidimensional feature matrix are input into a geometric consistency verification module, which includes: a curvature matching submodule: extracting the curvature distribution of the edge contour based on the high-fidelity image and calculating the similarity with the surface curvature parameters extracted from the multidimensional feature matrix; a density distribution matching submodule: evaluating the matching degree between the grayscale distribution of the high-density area in the high-fidelity image and the corresponding density distribution in the multidimensional feature matrix; If the preliminary matching result conflicts with the geometric consistency check result, the multi-dimensional conflict resolution mechanism is triggered to generate corrected inventory data and trigger an early warning mechanism. The multi-dimensional conflict resolution mechanism includes: a priority rule library, which is used to set the judgment rules that give priority to the geometric consistency check result over the tag recognition result; a dynamic threshold adjustment strategy, which is used to adjust the matching threshold in real time according to the environmental interference intensity, where the environmental interference intensity is high temperature or strong electromagnetic field.

[0013] By adopting the above technical solutions, high-precision geometric feature verification based on curvature and density distribution can ensure the consistency of material shape and material properties; through the conflict resolution mechanism, low-credibility data can be corrected first, dynamically adapting to environmental changes, effectively eliminating multi-source data conflicts, and improving inventory data accuracy and system anti-interference capabilities.

[0014] Optionally, in a high-temperature industrial scenario, the method further includes: The surface normal vector field constructed by 3D point cloud data is dynamically aligned with the X-ray grayscale gradient to generate a thermal deformation compensation map; The thermal deformation compensation map is used as a weight factor to dynamically adjust the fusion ratio of the X-ray grayscale image and the 3D point cloud data, where the geometric consistency of the local deformation area caused by thermal expansion is prioritized. In the feature-level fusion stage, the thermal deformation compensation map and the weight data obtained by the weight sensor are combined to generate a multidimensional feature matrix with thermal stress distribution constraints.

[0015] By adopting the above technical solution, the geometric consistency of X-ray images and three-dimensional point cloud data in the thermal expansion area is preserved through dynamic spatial alignment correction and weight adjustment of the thermal deformation compensation map; the multi-dimensional feature matrix of thermal stress constraints is generated by combining weight data, which effectively eliminates the deformation error caused by temperature and improves the recognition accuracy and feature fusion robustness of electronic components in complex thermal environments.

[0016] Optionally, the method further comprises: In strong electromagnetic interference scenarios, to address the problem of electromagnetic pulse interference on X-ray detector signals, the motion state characteristics of electronic components are extracted through lidar point cloud data. The motion state characteristics include vibration frequency and displacement fluctuations. Inputting the motion state characteristics into the electromagnetic interference suppression module of the hybrid Kalman filter, extracting the periodic component of the electromagnetic interference by analyzing the temporal correlation between the motion state and the electromagnetic field intensity, and generating an interference spectrum mask by using wavelet transform; The measurement noise covariance matrix of the hybrid Kalman filter is dynamically adjusted based on the interference spectrum mask to output a high-fidelity image after motion state compensation and electromagnetic interference suppression. The measurement noise covariance matrix preferentially suppresses periodic electromagnetic noise.

[0017] By adopting the above technical solution, the motion characteristics of electronic components are extracted through lidar, and the interference spectrum mask is generated by combining electromagnetic field timing analysis. The filter noise parameters are dynamically optimized and periodic electromagnetic noise is preferentially suppressed, thereby improving the noise resistance and geometric accuracy of X-ray images in strong interference scenarios.

[0018] Optionally, in the multi-dimensional conflict resolution mechanism, the method further includes: Build an abnormal pattern library based on historical inventory data and record corresponding common abnormal matching scenarios. Common abnormal matching scenarios include increased misrecognition rates in high-temperature environments and density distribution distortion caused by strong electromagnetic interference. When the multi-dimensional conflict resolution mechanism is triggered, the current conflict scenario is matched with the abnormal pattern library for similarity. If the match is successful, the preset correction strategy is directly called; If the matching fails, the self-learning mode is started and the current conflict scenario and correction results are included in the abnormal pattern library.

[0019] By adopting the above technical solution, by building an exception pattern library and dynamically matching common exception scenarios, rapid response and strategy reuse of conflict resolution can be achieved; if the match fails, the new scenario will be incorporated into the knowledge base through self-learning mode, continuously expanding the system's adaptability to complex exceptions, thereby improving the intelligence level of multi-dimensional conflict resolution and the efficiency of inventory data correction.

[0020] In a second aspect, the present application provides an electronic component material identification and management system, which adopts the following technical solutions: An electronic component material identification and management system, comprising: A multidimensional feature matrix generation module acquires an X-ray grayscale image of the electronic component using an X-ray imaging device, simultaneously acquires three-dimensional point cloud data corresponding to the electronic component using a laser radar, and collects weight information corresponding to the electronic component using a weight sensor; and fuses the X-ray grayscale image, the three-dimensional point cloud data, and the weight information based on dynamic weight allocation of the signal-to-noise ratio to generate a fused multidimensional feature matrix; a unique identification code generation module, which extracts physical characteristic parameters corresponding to the electronic component based on the multidimensional feature matrix, the physical characteristic parameters including density, geometric symmetry, and surface curvature; retrieves a pre-set material physical characteristic database, uses a multi-parameter joint matching algorithm to combine the physical characteristic parameters with the material physical characteristic database to generate a unique identification code, and outputs material type and specification information; A high-fidelity image output module integrates an adaptive filtering circuit at the front end of the X-ray detector, obtains the corresponding ambient temperature and electromagnetic field strength in real time, adjusts the X-ray detector gain and sampling frequency based on the ambient temperature and electromagnetic field strength; corrects X-ray image distortion caused by high temperature or strong electromagnetic interference based on the spatial correlation algorithm of the three-dimensional point cloud data, and outputs the corrected high-fidelity image; The verification module associates the unique identification code with the material database, automatically identifies the label information through structured OCR technology, and completes the material entry, exit and dynamic inventory update; it is used to perform geometric consistency verification on the high-fidelity image and the multi-dimensional feature matrix. If the material type and specification information conflict with the database record, an abnormal matching result is determined, and a secondary verification is performed based on the abnormal matching result, triggering an early warning mechanism and generating corrected inventory data.

[0021] In a third aspect, the present application provides an electronic component material identification and management system, which adopts the following technical solutions: An electronic component material identification and management system includes a processor running a program of any one of the above-mentioned electronic component material identification and management methods.

[0022] In a fourth aspect, the present application provides a storage medium, which adopts the following technical solution: A storage medium storing a program of any one of the above-mentioned electronic component material identification and management methods. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 The figure is a flow chart showing a method for identifying and managing electronic components and materials according to an exemplary embodiment.

[0024] Figure 2 The figure is a structural block diagram of an electronic component material identification and management system according to an exemplary embodiment. DETAILED DESCRIPTION

[0025] Embodiments of the present application are described in detail below, examples of which are illustrated in the accompanying drawings.

[0026] Throughout this specification, reference to the terms "certain embodiments," "one embodiment," "some embodiments," "illustrative embodiments," "examples," "specific examples," or "some examples" means that a specific feature, structure, material, or characteristic described in conjunction with the embodiment or example is included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

[0027] The present application embodiment discloses a method for identifying and managing electronic components. Figure 1 ,include: S100 acquires X-ray grayscale images of electronic components through X-ray imaging equipment, acquires three-dimensional point cloud data corresponding to the electronic components through lidar, and collects weight information corresponding to the electronic components through weight sensors; and fuses the X-ray grayscale image, three-dimensional point cloud data, and weight information based on dynamic weight distribution of the signal-to-noise ratio to generate a fused multi-dimensional feature matrix.

[0028] The steps of S100 specifically include: 1. X-ray grayscale image acquisition process: Electronic components are scanned through industrial CT or high-resolution X-ray inspection systems. The detector records the differences in X-ray absorption by different materials and generates grayscale images that reflect the internal density and structure. This provides internal structural information (such as defects and pore distribution) and density distribution characteristics of electronic components.

[0029] 2. Execution process of 3D point cloud data acquisition: Use LiDAR to emit laser pulses and receive reflected signals, calculate point cloud coordinates through time-of-flight or phase difference methods, and generate the 3D geometric outline (surface normal vector, curvature, etc.) of the electronic component; thus, the external geometric features (such as size, shape, and surface curvature) of the electronic component can be provided, which complements the X-ray image and enhances the recognition ability of complex geometric structures.

[0030] 3. Weight information collection process: The weight of electronic components is measured using a high-precision weight sensor (such as a strain gauge or electromagnetic force balance sensor). The density is then calculated based on the volume calculated from the point cloud data. This provides physical property parameters such as the mass-to-volume ratio, assists in verifying the density consistency between X-ray images and point cloud data, and supplements the assessment of material uniformity.

[0031] 4. Execution process of dynamic weight fusion based on signal-to-noise ratio: Signal-to-noise ratio calculation: evaluates the signal-to-noise ratio of X-ray images, point cloud data, and weight information. For example, the signal-to-noise ratio of X-ray images is calculated by the ratio of the local variance to the mean of the grayscale values; the signal-to-noise ratio of point cloud data is determined by the stability of the point cloud density distribution; and the signal-to-noise ratio of weight information is based on the fluctuation range of the sensor output. Dynamic weight allocation: According to the signal-to-noise ratio of each data source, weights are proportionally assigned (e.g., data with high signal-to-noise ratio accounts for a higher proportion), and the three types of data are weightedly integrated; Generate a multi-dimensional feature matrix: Through weighted fusion, the density information of the X-ray grayscale image, the geometric information of the point cloud data, and the physical properties of the weight information are integrated into a unified feature matrix, providing high-quality input for subsequent physical characteristic parameter extraction and database matching.

[0032] By fusing X-ray grayscale images, lidar point cloud data, and weight information, the S100 constructs a multi-dimensional feature matrix covering the internal and external structures and physical properties of electronic components, addressing the limitations of a single data source in density, geometry, or quality parameters. It also dynamically adjusts data weights based on the signal-to-noise ratio, prioritizes high-reliability data, and effectively suppresses environmental noise interference, providing stable input for subsequent physical property extraction, image distortion correction, and inventory verification.

[0033] S200, extracting the physical characteristic parameters corresponding to the electronic components based on the multi-dimensional feature matrix, the physical characteristic parameters include density, geometric symmetry, and surface curvature; calling the pre-set material physical characteristic database, generating a unique identification code by combining the physical characteristic parameters with the material physical characteristic database through a multi-parameter joint matching algorithm, and outputting the material type and specification information.

[0034] The steps of S200 specifically include: 1. Physical Property Parameter Extraction Process: Based on the multidimensional feature matrix generated by the S100 (including density information from the X-ray grayscale image, geometric features from the point cloud data, and physical properties from the weight information), image processing algorithms are used to extract physical property parameters (such as density, geometric symmetry, and surface curvature) of electronic components. Density extraction involves cross-validating density values based on the grayscale distribution of the X-ray grayscale image and the volume-to-mass ratio calculated by the weight sensor. Geometric symmetry involves calculating symmetry parameters through 3D contour symmetry analysis of the point cloud data (such as axial or mirror symmetry). Surface curvature involves extracting curvature distribution features using the surface normal field of the point cloud data and a local surface fitting algorithm. This provides highly accurate physical property parameters for subsequent database matching, ensuring accurate identification of material type and specification.

[0035] 2. The execution process of multi-parameter joint matching to generate a unique identification code: A pre-set database of material physical properties (including parameters such as density, geometric symmetry, and surface curvature of known electronic components) is retrieved. The currently extracted physical property parameters are then matched against the records in the database using a multi-parameter joint matching method (such as weighted Euclidean distance matching or fuzzy logic matching). The matching result generates a unique identification code and outputs the corresponding material type and specification information (such as model, size, and material). Multi-parameter joint matching reduces the risk of misjudgment caused by a single parameter (such as relying solely on density), ensuring the uniqueness and reliability of material identification results.

[0036] 3. Implementation of the adaptive filter circuit to adjust X-ray detector parameters: An adaptive filter circuit is integrated into the front end of the X-ray detector to monitor changes in ambient temperature and electromagnetic field strength in real time. Based on this monitoring data, the detector's gain (amplification factor) and sampling frequency are dynamically adjusted (for example, reducing the gain to avoid saturation at high temperatures and increasing the sampling frequency to capture transient signals during strong electromagnetic interference). This process compensates for the effects of environmental factors (such as sensor drift caused by temperature fluctuations or signal noise caused by electromagnetic interference) on X-ray detector performance, improving image acquisition stability and signal-to-noise ratio.

[0037] 4. Execution of X-ray Image Distortion Correction Using a Spatial Correlation Algorithm Based on Point Cloud Data: Using the 3D point cloud data acquired by the S100, a spatial correlation algorithm (e.g., spatial alignment of the point cloud surface normal field with the X-ray grayscale gradient) is used to identify areas of X-ray image distortion caused by high temperatures or strong electromagnetic interference. Geometric corrections (e.g., non-uniform illumination compensation or projection distortion correction) are then performed on these distorted areas, resulting in a high-fidelity image output. This eliminates image distortion caused by environmental interference, ensures the geometric accuracy of the X-ray image and its consistency with the point cloud data, and provides high-quality image input for subsequent identification and verification.

[0038] 5. Execution of the unique identification code association with the database and dynamic inventory updates: The generated unique identification code is associated with the material database, and structured OCR technology is used to automatically identify label information (such as QR codes or barcodes) on electronic components, completing material entry and exit, as well as dynamic inventory updates. Simultaneously, a geometric consistency check is performed between the high-fidelity image and the multidimensional feature matrix (e.g., comparing the deviation between the image edge contour and the point cloud data). If a conflict is found between the material type or specification information and the database record, an early warning mechanism is triggered and corrected inventory data is generated. This enables automated and intelligent material management, reduces manual intervention errors, and ensures the real-time and accuracy of inventory data through conflict detection and correction mechanisms.

[0039] The S200 generates a unique identification code through multi-parameter joint matching (density, geometric symmetry, and surface curvature), achieving high-precision recognition and specification matching of electronic components. Combining adaptive filtering circuits and spatial correlation algorithms, it dynamically suppresses X-ray image distortion caused by ambient temperature, humidity, and electromagnetic interference, improving image stability and geometric accuracy. At the same time, relying on structured OCR and a closed-loop inventory verification system, it automatically recognizes label information, provides warnings for abnormal matches, and corrects inventory data in real time, ensuring the automation, intelligence, and reliability of material management.

[0040] S300 integrates an adaptive filtering circuit at the front end of the X-ray detector to obtain the corresponding ambient temperature and electromagnetic field strength in real time, and adjust the X-ray detector gain and sampling frequency based on the ambient temperature and electromagnetic field strength; it corrects X-ray image distortion caused by high temperature or strong electromagnetic interference based on three-dimensional point cloud data and spatial correlation algorithm, and outputs the corrected high-fidelity image.

[0041] The steps of S300 specifically include: 1. Implementation of Adaptive Filter Circuit Integration and Real-Time Environmental Parameter Monitoring: Adaptive filter circuits are integrated into the front end of the X-ray detector. Environmental sensors (such as temperature sensors and electromagnetic field strength probes) are embedded in the circuit to collect real-time ambient temperature and electromagnetic field strength data. By monitoring environmental changes (such as sensor drift caused by high temperatures or signal noise caused by strong electromagnetic interference), this provides a basis for dynamic adjustment of detector parameters, ensuring image acquisition stability.

[0042] 2. Dynamic X-ray Detector Parameter Adjustment: Based on the real-time monitoring of ambient temperature and electromagnetic field strength, an algorithm dynamically adjusts the X-ray detector's gain (amplification factor) and sampling frequency. For example, in gain adjustment, high temperatures may cause sensor sensitivity to decrease, so the gain should be reduced to prevent signal saturation. Strong electromagnetic interference may introduce noise, so the gain should be appropriately increased to enhance the effective signal. In the presence of strong electromagnetic interference, the sampling frequency should be increased to capture transient signals and reduce noise accumulation. In low-temperature environments, the sampling frequency should be reduced to save energy and stabilize the signal. These steps compensate for the impact of environmental interference on detector performance, optimize the image signal-to-noise ratio, and ensure stable image quality under complex operating conditions.

[0043] 3. Execution of spatial correlation distortion correction based on 3D point cloud data: Utilizing the 3D point cloud data acquired by the S100, spatial correlation algorithms (such as spatial alignment of the point cloud surface normal field with the X-ray image grayscale gradient) are used to identify areas of X-ray image distortion caused by high temperature or electromagnetic interference. Specific steps include: locating the distorted area, by comparing the geometric outline of the point cloud data with the edge outline of the X-ray image to detect geometric deviations caused by thermal expansion or electromagnetic noise; and correcting the distortion, by applying algorithms such as non-uniform illumination compensation and projection distortion correction to the distorted area. The image pixel mapping is adjusted based on the spatial coordinate relationship of the point cloud data to restore the image's geometric consistency. These steps eliminate image distortion caused by environmental interference, improve the geometric accuracy of the X-ray image, and ensure spatial consistency between the image and the point cloud data.

[0044] 4. High-fidelity image output: The X-ray image, after dynamic parameter adjustment and distortion correction, is output as high-quality input for subsequent steps (such as the S400 geometric consistency check). This provides high-precision, low-noise image data, providing a reliable basis for material identification and inventory management.

[0045] The S300 integrates an adaptive filtering circuit at the front end of the X-ray detector to monitor the ambient temperature and electromagnetic field strength in real time and dynamically adjust the detector gain and sampling frequency, effectively suppressing the impact of environmental interference on image quality. At the same time, it combines three-dimensional point cloud data and corrects X-ray image distortion caused by high temperature or strong electromagnetic interference based on a spatial correlation algorithm, outputting high-fidelity images, providing a stable and accurate data foundation for subsequent geometric verification and material identification, and significantly improving the system's image acquisition stability and geometric consistency under complex working conditions.

[0046] S400 associates the unique identification code with the material database, automatically recognizes label information through structured OCR technology, and completes material warehousing, outbound delivery, and dynamic inventory updates; it performs geometric consistency verification on high-fidelity images and multi-dimensional feature matrices. If there is a conflict between the material type and specification information and the database records, it determines the abnormal matching result, performs secondary verification based on the abnormal matching result, triggers the early warning mechanism, and generates corrected inventory data.

[0047] The steps of S400 specifically include: 1. Geometric consistency verification process: Based on high-fidelity X-ray images and 3D point cloud data, the spatial consistency of the two is verified by comparing the edge contours of the X-ray image with the geometric structure of the point cloud data (such as curvature, symmetry, and key dimensions). If significant deviations are found (such as image distortion caused by environmental interference or point cloud data anomalies), an early warning mechanism is triggered and the abnormal area is recorded. This ensures the geometric matching of the X-ray image and point cloud data, avoids misidentification caused by image quality or point cloud noise, and provides a reliable basis for subsequent database matching.

[0048] 2. Abnormal Match Detection and Correction Process: A multidimensional feature matrix (including density, geometric parameters, and physical properties) is cross-validated against a pre-set material database. If a parameter in the feature matrix (such as density or curvature) significantly conflicts with the database record (e.g., density deviation due to sensor drift), a correction algorithm is activated to recalculate the parameter or flag the abnormal record. This multi-dimensional data cross-validation eliminates abnormal matching results caused by errors in a single data source, reduces the risk of misjudgment, and ensures accurate material identification.

[0049] 3. Dynamic Inventory Data Update and Synchronization: The revised feature matrix is associated with the material records in the database. Structured OCR technology is used to automatically extract electronic component label information (such as model and batch number) and synchronize the information with the inventory management system. If any discrepancy between label information and database records is detected (e.g., due to mislabeling), an alert is triggered and corrected inventory data is generated. This enables real-time dynamic inventory data updates, reduces manual errors, and ensures consistency between inventory records and actual materials.

[0050] 4. Adaptive Feedback Adjustment Process: Based on the results of geometric consistency checks and anomaly matching detection, the parameters of various modules within S100-S300 (such as X-ray detector gain and point cloud sampling frequency) are dynamically adjusted. For example, if image distortion caused by high temperatures is frequently detected, the adaptive filter circuit parameters in S300 are automatically optimized; if insufficient point cloud data stability is detected, the lidar scanning density in S100 is adjusted. This creates a closed-loop feedback mechanism that continuously optimizes system parameter configuration, improving the robustness and recognition accuracy of the overall solution under complex operating conditions.

[0051] 5. System Closure and Process Optimization: Corrected inventory data, feature matrices, and verification results are fed back to S100-S300 to drive parameter optimization and process adjustments in subsequent steps (such as optimizing multi-parameter joint matching weights and updating database rules). Simultaneously, machine learning models analyze historical verification data to automatically generate optimization recommendations for identification strategies (such as adding detection rules for abnormal patterns). By building a fully closed-loop feedback system, continuous iteration of identification algorithms and inventory management is achieved, enhancing the overall solution's intelligence and long-term stability.

[0052] The S400 eliminates recognition errors caused by image distortion or noise and corrects abnormal matching results through geometric consistency verification of X-ray images and three-dimensional point cloud data, combined with cross-validation of multi-dimensional feature matrices and databases. It dynamically updates inventory data based on structured OCR technology to ensure consistency between records and actual materials. Through adaptive feedback adjustment (such as optimizing detector parameters and point cloud sampling frequency) and machine learning-driven closed-loop optimization, it continuously improves the system's robustness and recognition accuracy under complex working conditions, ultimately achieving automated error correction, data consistency assurance, and intelligent upgrades for the entire material management process.

[0053] Based on the above solution, an electronics manufacturer faced problems such as low recognition accuracy and inefficient inventory management when producing microelectronic components such as 0402 resistors and 0603 packaged capacitors. Traditional X-ray images, due to interference from high-temperature reflow soldering plants and high-frequency inspection equipment, exhibit noise and blurred edges, making it difficult to distinguish micron-level differences such as 0.1Ω and 0.2Ω. Furthermore, a single data source (such as X-ray images or point cloud data) cannot fully capture the density, geometric symmetry, and other characteristics of micro-parts. When manually entering label information, the model number "R0402-100" is often mistakenly recorded as "R0402-1000," resulting in conflicts between inventory records and actual materials, affecting the efficiency of the automated production line.

[0054] To address these issues, this solution achieves precise identification through multidimensional data fusion and adaptive adjustment technology. First, a high-resolution X-ray inspection system is used to acquire images of internal defects, a lidar radar generates three-dimensional point cloud data (capturing surface curvature down to 0.1mm), and a weight sensor calculates density values. A dynamic weighting algorithm is then used to fuse these three types of data, suppressing environmental noise caused by high temperatures and electromagnetic interference. Secondly, to address image distortion, a spatial correlation algorithm for point cloud data is used to correct for 0.02mm edge deviations caused by thermal expansion, restoring the geometric consistency of the image. Finally, the corrected multidimensional feature matrix is combined with the database for multi-parameter matching to generate a unique identification code. Structured OCR is then used to automatically identify the label information and simultaneously update the inventory system.

[0055] After implementation, the accuracy of micro-part model recognition increased from 75% to 99.9%, enabling precise capture of curvature differences as small as 0.1mm. Inventory update efficiency increased by 85%, reducing manual intervention by 98%, and eliminating the risk of production line downtime due to mislabeling. The system maintained stable operation in high temperatures (80°C) and strong electromagnetic interference (500kHz), achieving a sixfold increase in image signal-to-noise ratio and a reduction in the false positive rate to below 0.03%. Continuous parameter optimization through a closed-loop feedback mechanism further enhanced adaptability and long-term stability in complex working conditions, achieving full automation from data collection to intelligent management.

[0056] In an embodiment of the present application, during the generation of the multidimensional feature matrix, the method further includes: 1. Based on the 3D point cloud data acquired by LiDAR, the geometric outlines of electronic components (such as surface normals and curvature distribution) are extracted. Using a projection algorithm, these 3D outlines are mapped to the 2D coordinate system of the X-ray grayscale image, forming a unified spatial alignment reference framework. This resolves the spatial misalignment between the X-ray image and the point cloud data, ensuring geometric alignment between the two. This provides spatial consistency for subsequent grayscale-density correlation and avoids feature matching errors caused by coordinate deviations.

[0057] 2. The density distribution of components is derived from the weight data collected by the weight sensor and the volume calculated from the point cloud data. The density value is then mapped to the corresponding location (e.g., the density value of each point in the point cloud) according to the spatial coordinate distribution of the point cloud data. By combining the physical properties (density) with the geometric data (point cloud), a density-geometry joint feature is formed. This compensates for grayscale errors in X-ray images that may be caused by material inhomogeneities, enhancing the detection of internal structural anomalies (such as pores and cracks).

[0058] 3. Based on the material type (e.g., metal type), a mapping relationship between grayscale value and density is established (e.g., through experimental calibration or a known material database). The density distribution is then used to correct the grayscale values of the X-ray image (e.g., enhancing the grayscale values in high-density areas and suppressing the grayscale values in low-density areas). This eliminates grayscale distortion in the X-ray image caused by material absorption differences (e.g., high-density areas appearing too dark or low-density areas appearing too bright), improves the physical consistency of the image, and ensures that the grayscale values more accurately reflect the actual density distribution, providing high-quality input for subsequent defect identification.

[0059] 4. The calibrated X-ray grayscale image (including density correction information), 3D point cloud data (including geometric features), and density distribution data (including physical properties) are fused at the feature level to extract key features (such as density-curvature correlation and geometry-grayscale alignment) to generate a unified multidimensional feature matrix. This enables deep correlation between X-ray images, point cloud data, and density distribution, overcoming the limitations of single data sources (e.g., X-rays cannot directly reflect geometric curvature, and point clouds cannot directly reflect density), providing a more comprehensive feature basis for material identification, defect detection, and inventory management.

[0060] Through spatial alignment, density distribution mapping, grayscale correction, and feature-level fusion, this method addresses the spatial misalignment, grayscale distortion, and single-feature limitations of X-ray images and point cloud data found in traditional methods, significantly improving the comprehensiveness and reliability of the multidimensional feature matrix. Its core functions are to ensure precise spatial alignment of geometry, image, and physical properties (e.g., projecting 3D contours onto X-ray images to avoid recognition errors due to coordinate deviations); correct misjudgments caused by material absorption differences (e.g., high-density areas being misjudged as defects) through grayscale-density mapping, while enhancing the ability to jointly detect internal defects and surface anomalies; integrate geometry, grayscale, and density information to form a unified feature matrix, providing a more comprehensive basis for material identification and defect detection, and reducing the risk of misjudgment of single features; and enhance the system's stability under complex operating conditions such as high temperatures and strong electromagnetic interference (e.g., dynamically adjusting point cloud data weights to enhance environmental noise robustness), thereby achieving full-link automation and high reliability from data acquisition to intelligent management.

[0061] In an embodiment of the present application, in the process of dynamically adjusting the detector gain and sampling frequency according to the collected temperature and electromagnetic field strength through a preset compensation parameter table, wherein the compensation parameter table includes gain adjustment coefficients and sampling frequency thresholds corresponding to different metal materials; the method further includes: 1. Based on real-time collected temperature and electromagnetic field strength, the gain adjustment coefficient and sampling frequency threshold for the corresponding metal material are retrieved from a preset compensation parameter table to dynamically adjust the X-ray detector gain (for example, reducing it from 1.5x to 1.0x) and sampling frequency (for example, increasing it from 200Hz to 500Hz). By optimizing the correlation between material properties and environmental parameters, the system adapts to the absorption differences of different metal materials and complex operating conditions such as high temperatures and strong electromagnetic interference, reducing the impact of signal noise on image quality and providing more stable input data for subsequent filtering processing.

[0062] The adjusted detector output signal (high-fidelity X-ray grayscale image) and the lidar point cloud data (3D geometric outline) are used as dual input sources for the hybrid Kalman filter. The filter consists of two functional modules: Temperature compensation module: Based on the real-time temperature change rate (such as an increase of 0.5°C per second), the process noise covariance matrix is dynamically adjusted to compensate for the geometric structure deformation error caused by thermal expansion.

[0063] Electromagnetic field compensation module: Dynamically adjusts the measurement noise covariance matrix according to the fluctuation amplitude of the electromagnetic field intensity (such as fluctuation in the 100kHz frequency band) to suppress the disturbance of high-frequency interference on the grayscale value.

[0064] Through dual-source data fusion and adaptive noise modeling, the coupling effect of environmental interference on image and point cloud data is eliminated, and the physical consistency and geometric accuracy of the signal are improved.

[0065] 2. The hybrid Kalman filter uses state prediction and measurement updates to iteratively fuse adjusted detector signals with point cloud data to generate high-fidelity X-ray images that have been noise-suppressed and geometrically corrected. The resulting image retains the density sensitivity of X-rays (such as the ability to detect internal defects) and the geometric accuracy of lidar (such as the ability to identify sudden changes in curvature), significantly improving the recognition accuracy and defect detection reliability of microelectronic components.

[0066] In an embodiment of the present application, during the multi-dimensional verification process, the method further includes: 1. Generating a preliminary match result: The collected material type and specification information is compared with the preset tolerance ranges in the material physical property database. For example, a "0402 resistor" is matched with the resistor size tolerance (e.g., 0.4mm ± 0.02mm) and density tolerance (e.g., 8.9g / cm³ ± 0.1g / cm³) stored in the database to generate a preliminary match result (e.g., "85% match"). This standardized tolerance range allows for rapid screening of potentially matching material types and specifications, reducing the computational complexity of subsequent geometric consistency checks and providing preliminary data support for inventory management.

[0067] 2. Execution process of the geometric consistency check module: The curvature matching submodule extracts the curvature distribution of edge contours (e.g., sudden changes in curvature of 0.1mm) based on high-fidelity X-ray images and calculates similarity with surface curvature parameters (e.g., a curvature radius of R = 0.1mm) extracted from point cloud data in a multidimensional feature matrix (a curvature match of 90% or higher is considered consistent). This verifies that the geometry of micro-parts conforms to design specifications. For example, it detects curvature deviations at the edges of chip capacitor pads caused by machining errors, thus avoiding inventory conflicts caused by mislabeling or data entry errors.

[0068] The density distribution matching submodule evaluates the grayscale distribution of high-density areas in high-fidelity images (such as the grayscale peak of the metal layer inside a resistor) against density distribution data in a multidimensional feature matrix (such as density calculated by weight and volume). A grayscale-density correlation coefficient ≥ 0.95 is considered consistent. This complements geometric verification by verifying material integrity through density sensitivity (for example, detecting the presence of pores or cracks within a resistor), enhancing the ability to identify defective materials.

[0069] 3. Implementation process of the multi-dimensional conflict resolution mechanism: Priority rule base: If the preliminary matching result (such as "0402 resistor" identified by the label) conflicts with the geometric consistency verification result (such as a curvature matching degree of only 70%), the geometric verification result will take precedence (such as being determined to be an "abnormal batch") and the inventory data will be corrected.

[0070] Dynamic threshold adjustment strategy: The matching threshold is adjusted in real time based on the intensity of environmental interference (such as high temperature or strong electromagnetic field) (for example, the curvature matching threshold is reduced from 90% to 85% in high temperature environment) to adapt to the impact of environmental noise on image quality.

[0071] Based on the above steps, the conflict between label recognition and geometric verification results can be resolved, thereby avoiding misjudgments caused by environmental interference or data entry errors; the dynamic threshold adjustment strategy enhances the robustness of the system under complex working conditions and ensures the stability of the verification results.

[0072] By combining preliminary matching with dual geometry and density verification, combined with a priority rule library and dynamic threshold adjustment strategies, the system effectively addresses issues such as mislabeling, insufficient environmental interference suppression, and incomplete defect detection. It can quickly screen target materials and accurately verify the consistency of geometric and physical properties (such as curvature matching and density distribution verification). It can dynamically resolve conflicts and adapt to complex working conditions (such as adjusting verification thresholds under high temperatures or strong electromagnetic fields). It also combines detection of internal and external defects (such as pores, cracks, and machining errors), ultimately achieving highly accurate inventory data updates and intelligent upgrades to quality control, significantly reducing the risk of manual intervention and misjudgment.

[0073] In this application, for high-temperature industrial scenarios, the method further includes: 1. Dynamic Spatial Alignment and Thermal Deformation Compensation Atlas Generation: Dynamic alignment correction is performed based on the surface normal vector field (e.g., surface orientation information) extracted from the 3D point cloud data and the gradient direction (e.g., edge intensity changes) of the X-ray grayscale image. This eliminates geometric misalignment caused by thermal expansion due to high temperatures (e.g., offsetting the edge of a metal part due to thermal deformation) and generates a thermal deformation compensation atlas (e.g., the deformation amount and direction of each point). This process addresses the geometric distortion caused by thermal expansion of electronic components in high-temperature environments, ensures the spatial alignment accuracy of the X-ray image and point cloud data, and provides a basis for thermal deformation correction for subsequent fusion.

[0074] 2. Dynamically Adjust the Fusion Ratio and Preserve Geometric Consistency: Using the thermal deformation compensation map as a weighting factor, the fusion ratio of the X-ray grayscale image and point cloud data is dynamically adjusted (e.g., increasing the point cloud weight in highly deformed areas, while maintaining image dominance in less deformed areas). Prioritizing the preservation of geometric consistency in areas of local deformation due to thermal expansion (e.g., sudden changes in curvature at pad edges). Dynamic weighting maintains the accuracy of key geometric features in high-temperature environments (e.g., preventing edge blurring caused by thermal expansion), ensuring that the fused data truly reflects the actual form of the component.

[0075] 3. Generation of a Multidimensional Feature Matrix Constrained by Thermal Stress: During the feature-level fusion stage, the thermal deformation compensation map (reflecting the deformation distribution caused by thermal expansion) is combined with weight data obtained by the weight sensor (calculating the thermal stress distribution) to generate a multidimensional feature matrix constrained by thermal stress (for example, associating density distribution with thermal stress areas). By incorporating thermal stress distribution information, the multidimensional feature matrix's ability to characterize physical properties in high-temperature environments (for example, identifying internal cracks or material fatigue caused by thermal stress) is enhanced, improving the comprehensiveness of defect detection.

[0076] Through dynamic spatial alignment correction and fusion ratio adjustment, the problems of geometric distortion and fusion error caused by thermal expansion in high-temperature environments are solved, ensuring the spatial consistency of X-ray images and point cloud data. Through the multi-dimensional feature matrix constrained by thermal stress, combined with weight data, the influence of thermal stress on material properties is quantified, thereby improving the detection ability of defects such as microcracks and material fatigue caused by high temperature. At the same time, the dynamic compensation mechanism enables the system to adapt to temperature fluctuations, ensuring the recognition accuracy and stability of long-term operation, and significantly reducing the risk of misjudgment and the need for manual intervention under high-temperature conditions.

[0077] In this application, for scenarios with strong electromagnetic interference, the method further includes: 1. Motion Feature Extraction: LiDAR point cloud data is used to monitor the motion of electronic components in real time, extracting their vibration frequency (e.g., 100 Hz ± 5 Hz) and displacement fluctuations (e.g., ±0.2 mm periodic offset). This is used to characterize the mechanical response (e.g., resonance of the detector bracket) caused by electromagnetic pulse interference. By establishing a correlation between electromagnetic interference and mechanical vibration, a dynamic behavior basis is provided for subsequent interference suppression (e.g., inferring the frequency component of electromagnetic interference from the vibration frequency).

[0078] 2. Electromagnetic Interference Suppression and Spectrum Mask Generation: The motion state characteristics are input into the electromagnetic interference suppression module of the hybrid Kalman filter. The module analyzes the temporal correlation between vibration frequency and electromagnetic field strength (for example, an electromagnetic pulse triggered 10 times per second causes synchronous detector vibration). The frequency components of periodic electromagnetic noise (such as 100Hz, 500Hz, etc.) are extracted, and an interference spectrum mask is generated through wavelet transform (for example, marking the 100Hz frequency band as a high-interference area). Based on these steps, the frequency domain characteristics of periodic electromagnetic interference can be accurately identified, providing a spectral positioning basis for subsequent noise suppression, avoiding the blindness of traditional filters (such as directly filtering all high-frequency signals, resulting in the loss of useful signals).

[0079] 3. Dynamic Noise Covariance Adjustment and High-Fidelity Image Output: Based on the interference spectrum mask, the hybrid Kalman filter's measurement noise covariance matrix is dynamically adjusted (for example, assigning a higher noise weight to the 100 Hz frequency band), prioritizing the suppression of periodic electromagnetic noise. High-fidelity X-ray images are output after motion compensation and electromagnetic interference suppression. Adaptive noise modeling specifically mitigates the impact of electromagnetic pulse interference on detector signals, preserving key detection signals (such as grayscale changes in defect areas) and improving image physical consistency.

[0080] By using lidar to capture mechanical vibration characteristics and wavelet transform spectrum analysis, the periodic electromagnetic interference frequency bands (such as 100Hz and 500Hz) are accurately located. Combined with the dynamic noise suppression strategy of the hybrid Kalman filter, the interference of electromagnetic pulses on the X-ray detector is preferentially eliminated, retaining the defect characteristic signal; at the same time, motion state compensation is used to eliminate image blur caused by vibration, generate high-fidelity images, and significantly improve the defect detection accuracy of micro components (such as 0.01mm level pore identification); multi-source data fusion and real-time response mechanism further ensure the stability of the system under sudden electromagnetic interference such as lightning strikes and equipment startup, reducing the risk of misjudgment and maintenance costs.

[0081] In this application, in the multi-dimensional conflict resolution mechanism, the method further includes: 1. Abnormal pattern library construction: Build an abnormal pattern library based on historical inventory data (such as past batches with high misidentification rates and defective material records). Record common abnormal matching scenarios (such as a 50% increase in the misidentification rate in a high-temperature environment and a 30% distortion of the grayscale distribution caused by strong electromagnetic interference) and annotate the corresponding correction strategies (such as gain adjustment coefficient and sampling frequency threshold).

[0082] By accumulating typical abnormal patterns through historical data, a reusable decision-making basis is provided for conflict resolution, reducing the need for manual intervention (for example, the number of conflict scenarios requiring manual review has been reduced from 98% to 2%).

[0083] 2. Abnormal scenario similarity matching and policy invocation: When the multi-dimensional conflict resolution mechanism is triggered (e.g., when the initial matching result conflicts with the geometric verification result), the current conflicting scenario (e.g., "the resistance edge curvature at 80°C is only 70% matched") is compared with the records in the abnormal pattern library for similarity (a match of 90% or higher is considered successful). If a match is successful, the preset correction strategy is directly invoked (e.g., dynamically adjusting the point cloud weight to 80%). This process enables rapid response to known abnormal scenarios, avoiding repeated analysis (e.g., reducing the processing time for high-temperature misjudgment scenarios from 5 minutes to 10 seconds), significantly improving the system's real-time performance and stability.

[0084] 3. Self-learning mode startup and pattern library update: If the current conflict scenario is not matched in the abnormal pattern library (such as the first encounter of the "strong electromagnetic interference + low temperature environment" composite scenario), the self-learning mode is started: the conflict scenario characteristics (such as the electromagnetic field intensity fluctuation amplitude, temperature change rate), the correction process (such as the parameter adjustment path of the hybrid Kalman filter) and the final correction results (such as the matching degree increased from 65% to 92%) are recorded and included in the abnormal pattern library.

[0085] By dynamically updating the pattern library, the system can adapt to new scenarios (such as responding to new electromagnetic interference sources or extreme temperature changes), continuously optimize conflict resolution capabilities, and reduce long-term maintenance costs.

[0086] Through the abnormal pattern library and self-learning mechanism, a closed-loop system for efficient conflict resolution and adaptive optimization has been built: the abnormal pattern library achieves millisecond-level response in more than 90% of scenarios (for example, reducing the conflict resolution delay from 5 minutes to 10 seconds), ensuring the real-time performance of the production line; the self-learning mode enables the system to proactively adapt to new interference environments (for example, more than 200 abnormal patterns are added each year), dynamically improving robustness (for example, the correction success rate increases from 70% to 95%); the automated matching strategy reduces manual intervention in 98% of conflict scenarios, reducing the misjudgment rate from 5% to 0.1%; combined with high-precision conflict resolution (99.9% matching accuracy), it achieves minute-level updates of inventory data and risk scenario predictions (such as early warning of compound interference misjudgments), promoting the upgrade of inventory management to intelligent decision-making and forward-looking control, and significantly reducing maintenance costs and quality risks.

[0087] The present application embodiment discloses an electronic component material identification management system, referring to Figure 2 ,include: Multi-dimensional feature matrix generation module 001 acquires X-ray grayscale images of electronic components through X-ray imaging equipment, simultaneously acquires three-dimensional point cloud data corresponding to the electronic components through laser radar, and collects weight information corresponding to the electronic components through weight sensors; and fuses the X-ray grayscale image, three-dimensional point cloud data, and weight information based on dynamic weight distribution of signal-to-noise ratio to generate a fused multi-dimensional feature matrix; Unique identification code generation module 002 extracts physical characteristic parameters corresponding to electronic components based on a multi-dimensional feature matrix. The physical characteristic parameters include density, geometric symmetry, and surface curvature. A pre-set material physical characteristic database is retrieved and the physical characteristic parameters are matched with the material physical characteristic database through a multi-parameter joint matching algorithm to generate a unique identification code. The module also outputs material type and specification information. The high-fidelity image output module 003 integrates an adaptive filtering circuit at the front end of the X-ray detector to obtain the corresponding ambient temperature and electromagnetic field strength in real time, and adjusts the X-ray detector gain and sampling frequency based on the ambient temperature and electromagnetic field strength. It corrects the X-ray image distortion caused by high temperature or strong electromagnetic interference based on the spatial correlation algorithm based on the three-dimensional point cloud data, and is used to output the corrected high-fidelity image; Verification module 004 associates the unique identification code with the material database, automatically recognizes the label information through structured OCR technology, and completes the material warehousing, warehousing and dynamic inventory updates; it is used to perform geometric consistency verification on the high-fidelity image and the multi-dimensional feature matrix. If the material type and specification information conflict with the database records, the abnormal matching result is determined, and a secondary verification is performed based on the abnormal matching result, triggering the early warning mechanism and generating corrected inventory data.

[0088] An embodiment of the present application further discloses an electronic component material identification and management system, comprising a processor in which a program of any one of the above-mentioned electronic component material identification and management methods is running.

[0089] An embodiment of the present application further discloses a storage medium storing a program of any one of the above-mentioned electronic component material identification and management methods.

[0090] Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limitations on the present application. Ordinary technicians in this field can change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. A method for identifying and managing electronic components, characterized in that: include: Acquire an X-ray grayscale image of the electronic component using an X-ray imaging device, simultaneously acquire three-dimensional point cloud data corresponding to the electronic component using a laser radar, and collect weight information corresponding to the electronic component using a weight sensor; and fuse the X-ray grayscale image, the three-dimensional point cloud data, and the weight information based on dynamic weight distribution of the signal-to-noise ratio to generate a fused multidimensional feature matrix; Extracting physical characteristic parameters corresponding to the electronic components based on the multidimensional feature matrix, the physical characteristic parameters including density, geometric symmetry, and surface curvature; retrieving a pre-set material physical characteristic database, generating a unique identification code by using a multi-parameter joint matching algorithm between the physical characteristic parameters and the material physical characteristic database, and outputting material type and specification information; Integrate an adaptive filter circuit at the front end of the X-ray detector to obtain the corresponding ambient temperature and electromagnetic field strength in real time, and adjust the X-ray detector gain and sampling frequency based on the ambient temperature and the electromagnetic field strength; Correcting X-ray image distortion caused by high temperature or strong electromagnetic interference based on the three-dimensional point cloud data using a spatial correlation algorithm, and outputting a corrected high-fidelity image; The unique identification code is associated with the material database, and the label information is automatically recognized through structured OCR technology to complete the material warehousing, warehousing and dynamic inventory updates; the high-fidelity image and the multi-dimensional feature matrix are subjected to geometric consistency verification. If the material type and specification information conflict with the database records, an abnormal matching result is determined, and a secondary verification is performed based on the abnormal matching result to trigger an early warning mechanism and generate corrected inventory data.

2. The electronic component material identification and management method according to claim 1, characterized in that: In the process of generating the multi-dimensional feature matrix, the method further includes: constructing a three-dimensional geometric outline of the electronic component using the three-dimensional point cloud data, and projecting the three-dimensional geometric outline into the two-dimensional coordinate system of the X-ray grayscale image to form a spatial alignment reference frame; Based on the weight data collected by the weight sensor, the density distribution of the components is calculated by mass-volume ratio, and the density distribution is mapped to the corresponding position of the three-dimensional point cloud data; Correlating the grayscale value of the X-ray grayscale image with the density distribution, and generating a corrected grayscale image through a grayscale-density mapping function, wherein grayscale value = K × density value + bias term, and K is a proportional coefficient related to the material type; The corrected grayscale image, three-dimensional point cloud data and density distribution are fused at the feature level to generate a multi-dimensional feature matrix.

3. The electronic component material identification and management method according to claim 1, characterized in that: In the process of dynamically adjusting the detector gain and sampling frequency according to the collected temperature and electromagnetic field strength using a preset compensation parameter table, wherein the compensation parameter table includes gain adjustment coefficients and sampling frequency thresholds corresponding to different metal materials; the method further includes: The adjusted detector output signal and the lidar point cloud data are input into a hybrid Kalman filter, wherein the hybrid Kalman filter includes: Temperature compensation module: dynamically adjusts the process noise covariance matrix based on the temperature change rate; Electromagnetic field compensation module: dynamically adjusts the measurement noise covariance matrix based on the amplitude of electromagnetic field intensity fluctuations; Output high-fidelity X-ray images corrected by the hybrid Kalman filter.

4. The electronic component material identification and management method according to claim 1, characterized in that: During the multi-dimensional verification process, the method also includes: Comparing the material type and the specification information with a preset tolerance range in a material physical property database to generate a preliminary matching result; The high-fidelity image and the multidimensional feature matrix are input into a geometric consistency verification module, which includes: a curvature matching submodule: extracting the curvature distribution of the edge contour based on the high-fidelity image and calculating the similarity with the surface curvature parameters extracted from the multidimensional feature matrix; a density distribution matching submodule: evaluating the matching degree between the grayscale distribution of the high-density area in the high-fidelity image and the corresponding density distribution in the multidimensional feature matrix; If the preliminary matching result conflicts with the geometric consistency check result, the multi-dimensional conflict resolution mechanism is triggered to generate corrected inventory data and trigger an early warning mechanism. The multi-dimensional conflict resolution mechanism includes: a priority rule library, which is used to set the judgment rules that give priority to the geometric consistency check result over the tag recognition result; a dynamic threshold adjustment strategy, which is used to adjust the matching threshold in real time according to the environmental interference intensity, where the environmental interference intensity is high temperature or strong electromagnetic field.

5. The electronic component material identification and management method according to claim 2, characterized in that: In high-temperature industrial scenarios, the method also includes: The surface normal vector field constructed by 3D point cloud data is dynamically aligned with the X-ray grayscale gradient to generate a thermal deformation compensation map; The thermal deformation compensation map is used as a weight factor to dynamically adjust the fusion ratio of the X-ray grayscale image and the 3D point cloud data, where the geometric consistency of the local deformation area caused by thermal expansion is prioritized. In the feature-level fusion stage, the thermal deformation compensation map and the weight data obtained by the weight sensor are combined to generate a multidimensional feature matrix with thermal stress distribution constraints.

6. The electronic component material identification and management method according to claim 1, characterized in that: The method also includes: In strong electromagnetic interference scenarios, to address the problem of electromagnetic pulse interference on X-ray detector signals, the motion state characteristics of electronic components are extracted through lidar point cloud data. The motion state characteristics include vibration frequency and displacement fluctuations. Inputting the motion state characteristics into the electromagnetic interference suppression module of the hybrid Kalman filter, extracting the periodic component of the electromagnetic interference by analyzing the temporal correlation between the motion state and the electromagnetic field intensity, and generating an interference spectrum mask by using wavelet transform; The measurement noise covariance matrix of the hybrid Kalman filter is dynamically adjusted based on the interference spectrum mask to output a high-fidelity image after motion state compensation and electromagnetic interference suppression. The measurement noise covariance matrix preferentially suppresses periodic electromagnetic noise.

7. The electronic component material identification and management method according to claim 1, characterized in that: In the multi-dimensional conflict resolution mechanism, the method also includes: Build an abnormal pattern library based on historical inventory data and record corresponding common abnormal matching scenarios. Common abnormal matching scenarios include increased misrecognition rates in high-temperature environments and density distribution distortion caused by strong electromagnetic interference. When the multi-dimensional conflict resolution mechanism is triggered, the current conflict scenario is matched with the abnormal pattern library for similarity. If the match is successful, the preset correction strategy is directly called; If the matching fails, the self-learning mode is started and the current conflict scenario and correction results are included in the abnormal pattern library.

8. An electronic component material identification and management system, characterized in that: include: A multidimensional feature matrix generation module acquires an X-ray grayscale image of the electronic component using an X-ray imaging device, simultaneously acquires three-dimensional point cloud data corresponding to the electronic component using a laser radar, and collects weight information corresponding to the electronic component using a weight sensor; and fuses the X-ray grayscale image, the three-dimensional point cloud data, and the weight information based on dynamic weight allocation of the signal-to-noise ratio to generate a fused multidimensional feature matrix; a unique identification code generation module, which extracts physical characteristic parameters corresponding to the electronic component based on the multidimensional feature matrix, the physical characteristic parameters including density, geometric symmetry, and surface curvature; retrieves a pre-set material physical characteristic database, uses a multi-parameter joint matching algorithm to combine the physical characteristic parameters with the material physical characteristic database to generate a unique identification code, and outputs material type and specification information; A high-fidelity image output module integrates an adaptive filtering circuit at the front end of the X-ray detector to obtain the corresponding ambient temperature and electromagnetic field strength in real time, and adjusts the X-ray detector gain and sampling frequency based on the ambient temperature and electromagnetic field strength; Correcting X-ray image distortion caused by high temperature or strong electromagnetic interference based on a spatial correlation algorithm based on the three-dimensional point cloud data, and outputting a corrected high-fidelity image; The verification module associates the unique identification code with the material database, automatically recognizes the label information through structured OCR technology, and completes the material warehousing, outbound and inventory dynamic update; It is used to perform geometric consistency check on the high-fidelity image and the multi-dimensional feature matrix. If there is a conflict between the material type and specification information and the database record, an abnormal matching result is determined, and a secondary verification is performed based on the abnormal matching result to trigger an early warning mechanism and generate corrected inventory data.

9. An electronic component material identification and management system, characterized in that: The method comprises a processor, wherein a program of the electronic component material identification and management method according to any one of claims 1 to 7 is run in the processor.

10. A storage medium, characterized in that: A program storing the electronic component material identification and management method according to any one of claims 1 to 7 is stored.

Images