Material detection method and system based on big data

Abstract

The application provides a material detection method and system based on big data, relates to the field of material quality detection, and solves the technical problems of insufficient detection accuracy and poor supply chain quality control linkage in the existing material detection method. The method comprises the following steps: emitting a sweep frequency sound wave to the warehouse-in material of the terminal warehouse by using a sound wave emitting device; collecting vibration velocity spectrum data and sound pressure gradient data of the warehouse-in material after receiving the sweep frequency sound wave; calculating a defect index of the warehouse-in material according to the vibration velocity spectrum data and the sound pressure gradient data; when the defect index is greater than a preset threshold, marking the warehouse-in material as a defective material, and sending a traceability detection instruction to the previous node warehouse to start a hierarchical detection process of the previous node warehouse. The application is used for the warehouse-in detection, quality traceability and whole-chain control process of materials in the supply chain.

Description

Technical Field

[0001] This invention belongs to the field of material quality inspection, specifically a material inspection method and system based on big data. Background Technology

[0002] In supply chain management, material quality inspection is a crucial step in ensuring the stable operation of the supply chain and preventing defective materials from entering end-use or sales stages. However, existing material inspection methods typically combine manual visual inspection with traditional instrument sampling, which is prone to insufficient accuracy due to technical limitations: manual visual inspection is limited by the resolution of the human eye, making it insufficient for identifying microscopic defects such as microcracks below the millimeter level and uneven material density, easily misjudging defects at the critical state as acceptable; traditional instruments mostly rely on preset thresholds for judgment, making it difficult to capture minute grayscale differences or structural stress changes on the material surface, resulting in low accuracy in identifying quality fluctuations on the edge of acceptable levels; the limited sample size of sampling means that local inspection results cannot reflect the true quality level of the entire batch, especially when the defect distribution is discrete, it is very easy to miss detections due to sample bias, resulting in a significant deviation between inspection accuracy and actual quality status. Summary of the Invention

[0003] This application provides a material inspection method and system based on big data, which solves the technical problem of insufficient inspection accuracy in the prior art.

[0004] To achieve the above objectives, this application adopts the following technical solution: Firstly, a material inspection method based on big data is provided, including: A sweeping sound wave is emitted to the incoming goods in the terminal warehouse using a sound wave transmitting device; The vibration velocity spectrum data and sound pressure gradient data of the materials received after receiving the frequency sweeping sound wave are collected; the vibration velocity spectrum data represents the distribution of vibration velocity at each point on the surface of the materials as a function of frequency, and the sound pressure gradient data represents the rate of change of sound pressure value on the surface of the materials as a function of spatial location. The defect index of the incoming materials is calculated based on the vibration velocity spectrum data and sound pressure gradient data. When the defect index is greater than a preset threshold, the incoming materials are marked as defective materials, and a traceability detection instruction is sent to the upstream warehouse. The traceability detection instruction is used to initiate the hierarchical detection process of the upstream warehouse.

[0005] Based on the above technical solution, the material inspection method based on big data provided in this application achieves high-precision defect screening of incoming materials by combining acoustic wave detection with big data analysis. Specifically, by collecting vibration velocity spectrum data and sound pressure gradient data, the physical characteristics of materials are characterized from different angles, which helps to accurately identify material defects. When the defect index exceeds a preset threshold, the defective material is immediately marked and a traceability inspection command is triggered, ensuring that problematic materials can be processed in a timely manner, thereby improving the efficiency and accuracy of material quality control and providing a guarantee for the stable operation of the supply chain.

[0006] Furthermore, the vibration velocity spectrum data is acquired using a laser Doppler vibrometer, and the sound pressure gradient data is collected using a distributed microphone array, with both having the same sampling frequency.

[0007] Furthermore, the calculation of the defect index of the target material based on vibration velocity spectrum data and sound pressure gradient data includes: The vibration velocity spectrum data is subjected to bandpass filtering and denoising to obtain the preprocessed velocity spectrum data v(f); Extract the velocity spectrum data from the preprocessed data that corresponds to the reference spectrum v ref (f) refers to the abnormal frequency band where the deviation value is greater than the preset deviation threshold, and the vibration abnormal zone is obtained; the reference spectrum represents the vibration velocity spectrum data of the same type of standard material; Extract the spatial regions in the sound pressure gradient data whose gradient values ​​are greater than a preset gradient threshold to obtain the sound pressure anomaly region; The intersection of the abnormal vibration zone and the abnormal sound pressure zone is marked as the abnormal vibration zone; The defect index of the target material is obtained according to the defect index calculation formula; the defect index calculation formula is used to characterize the preprocessed velocity spectrum data v(f) and the reference spectrum v. ref (f) and the relationship between the abnormal vibration zone.

[0008] Furthermore, the formula for calculating the defect index satisfies: Where DI represents the defect index, Ω represents the frequency range of the swept-frequency sound wave, and A hs σ represents the area of ​​the abnormal vibration zone, σ represents the standard deviation of the reference spectrum, and f represents the frequency of the swept sound wave.

[0009] Furthermore, prior to the graded detection, the risk area division of the previous node warehouse is performed, including: Obtain the supplier code S and production batch L based on the defective materials; Filter the associated material set Q in the database of the previous node warehouse; the associated material set has the same supplier code as the defective material, and the production date of the production batch is within a preset time window; Calculate the risk coefficient of materials within the associated material set; Cluster analysis was performed based on the spatial location of the warehouse at the previous node according to the risk coefficient, resulting in multiple risk areas.

[0010] Furthermore, the formula for calculating the risk coefficient is: λ i =α×δ i +β×e -kΔTi ; where λ i δ represents the risk coefficient of the i-th associated material in the associated material set. i The process similarity between the i-th associated material and the defective material is represented by ΔTi, which is obtained by calculating the proportion of the number of identical production equipment used by the i-th material and the defective material to the total number of production equipment used by the defective material. ΔTi represents the time difference between the production dates of the i-th associated material and the defective material, k represents the attenuation coefficient, and α and β represent the weighting coefficients of each item, which are determined through experimental experience.

[0011] Furthermore, the cluster analysis includes: Get the 3D model of the previous node's warehouse; Based on the aforementioned 3D model, a spatial mapping of materials is performed, creating a tuple for each material containing spatial coordinates (x, y, z), supplier code, production batch, and risk coefficient λ; where, if material w If the associated material set Q is given, then the risk coefficient λ w =0; Using spatial clustering algorithms, the tuples of the material point set are spatially clustered to obtain the risk region set {Z}. k |k=1,2,…,K}, where Z k Let K represent the k-th risk area, where K represents the number of risk areas.

[0012] Furthermore, the hierarchical detection process of the previous node warehouse includes: Calculate the average risk coefficient of all related materials in the k-th risk area. ; when When the time is greater than T1, mark the risk area as a Level 1 risk area and perform Level 1 detection: Frequency sweeping waves are sequentially emitted to all materials in the first-level risk area. The defect index of each material in the first-level risk area is calculated based on the vibration velocity spectrum data and sound pressure gradient data of the materials. When the defect index is greater than the preset threshold, the target material is marked as a defective material. When T2 < When the value is ≤T1, the risk area is marked as a secondary risk area, and secondary detection is performed: All materials in the Level 2 risk area are randomly selected at a first ratio to obtain the first sampled materials; Frequency sweeping waves are sequentially emitted to the first sampled material, and the defect index of each sampled material is calculated based on the vibration velocity spectrum data and sound pressure gradient data of the material; when the defect index is greater than the preset threshold, the target material is marked as a defective material. If the proportion of defective materials in the first sample exceeds the preset ratio, the secondary risk area will be marked as a primary risk area, and the primary inspection will be performed. when When the risk level is ≤T2, the risk area is marked as a level 3 risk area, and level 3 detection is performed: All materials in the Level 3 risk area are randomly selected at the second ratio to obtain the second sampled materials; The second sampled material is sequentially emitted with a sweeping radio wave. The defect index of each sampled material is calculated based on the vibration velocity spectrum data and sound pressure gradient data of the material. When the defect index is greater than the preset threshold, the target material is marked as a defective material. If the proportion of defective materials in the second sample exceeds the preset ratio, the level 3 risk area will be marked as a level 2 risk area, and the level 2 inspection will be performed.

[0013] Furthermore, when performing the hierarchical detection in the previous node warehouse: If a new defective material is detected in the previous node warehouse, a traceability detection instruction is sent to the parent node warehouse of the previous node warehouse, and the risk area division and the graded detection process are executed in the parent node warehouse.

[0014] Secondly, this application provides a material inspection system based on big data, comprising: a sound wave emitting module, a data acquisition module, and a data analysis module; wherein, The sound wave transmitting module is used to transmit frequency-sweeping sound waves to the incoming materials in the terminal warehouse using a sound wave transmitting device. The data acquisition module is used to collect vibration velocity spectrum data and sound pressure gradient data of the materials after they are received by the frequency sweeping sound wave; the vibration velocity spectrum data represents the distribution of vibration velocity at each point on the surface of the materials as a function of frequency, and the sound pressure gradient data represents the rate of change of sound pressure value on the surface of the materials as a function of spatial position. The data analysis module is used to calculate the defect index of the target material based on the vibration velocity spectrum data and sound pressure gradient data. When the defect index is greater than a preset threshold, the material entering the warehouse is marked as defective material, and a traceability detection command is sent to the upstream warehouse. The traceability detection command is used to start the graded detection process of the upstream warehouse.

[0015] Thirdly, a material detection device based on big data is provided, comprising: a communication unit and a processing unit; wherein, The communication unit is used to transmit data and communicate with the acoustic wave transmitting device, the data acquisition device, and the previous node warehouse. The processing unit is used to control the sound wave emitting device to emit frequency-sweeping sound waves, process the collected vibration velocity spectrum data and sound pressure gradient data, calculate the defect index of the target material, determine whether the material has defects based on the defect index, and generate and send traceability detection instructions when defects exist.

[0016] Fourthly, this application provides a big data-based material inspection device, comprising: a processor and a storage medium; the storage medium includes instructions, and the processor is used to execute the instructions to implement the method described in the first aspect and any possible implementation thereof. This big data-based material inspection device can be an electronic device or a chip within an electronic device.

[0017] Fifthly, this application provides a computer-readable storage medium storing instructions that, when executed on a big data-based material inspection device, cause the big data-based material inspection device to perform the methods described in the first aspect and any possible implementation thereof.

[0018] Sixthly, this application provides a computer program product containing instructions that, when run on a big data-based material inspection device, cause the big data-based material inspection device to perform the methods described in the first aspect and any possible implementation thereof.

[0019] This application provides a material inspection method and system based on big data. It achieves high-precision defect identification through a multi-dimensional collaborative detection mechanism and enhances supply chain quality control efficiency by combining traceability testing. For defect detection, a laser Doppler vibrometer and a distributed microphone array are used to simultaneously collect vibration velocity spectrum data and sound pressure gradient data. After bandpass filtering and noise reduction, vibration anomaly areas are extracted by comparing with a reference spectrum. The intersection of this data with spatial sound pressure gradient anomaly areas determines the abnormal vibration region. Finally, a defect index is calculated using a quantification formula, which improves the accuracy of defect identification.

[0020] In terms of defect tracing, a risk area division, tiered detection, and multi-level linkage tracing analysis mechanism has been constructed: Based on the supplier code and production batch of defective materials, a set of related materials is screened; risk coefficients are calculated by combining process similarity and production date difference; and risk areas are divided by spatial clustering based on a 3D warehouse model. Tiered detection is implemented according to the average risk coefficient, dynamically adjusting from full inspection to sampling inspection. When a problem is detected at one node, tracing back to the next higher node forms a progressively layered tracing network. This mechanism can quickly locate the source of risk, providing end-to-end assurance for supply chain quality control.

[0021] It should be understood that the descriptions of technical features, technical solutions, beneficial effects, or similar language in this application do not imply that all features and advantages can be achieved in any single embodiment. Rather, it is understood that the description of a feature or beneficial effect means that a specific technical feature, technical solution, or beneficial effect is included in at least one embodiment. Therefore, the descriptions of technical features, technical solutions, or beneficial effects in this specification do not necessarily refer to the same embodiment. Furthermore, the technical features, technical solutions, and beneficial effects described in this embodiment can be combined in any suitable manner. Those skilled in the art will understand that embodiments can be implemented without one or more specific technical features, technical solutions, or beneficial effects of a particular embodiment. In other embodiments, additional technical features and beneficial effects may be identified in specific embodiments that do not embody all embodiments. Attached Figure Description

[0022] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0023] Figure 1 A system architecture diagram of a big data-based material inspection system provided for embodiments of this application; Figure 2 A flowchart illustrating a material inspection method based on big data, provided for an embodiment of this application; Figure 3 A flowchart illustrating another material inspection method based on big data provided in this application embodiment; Figure 4 A flowchart illustrating another material inspection method based on big data provided in this application embodiment; Figure 5 A schematic diagram of a material detection device based on big data provided in this application embodiment; Figure 6 This is a schematic diagram of the hardware structure of a material detection device based on big data, provided in an embodiment of this application. Detailed Implementation

[0024] In the description of this application, unless otherwise stated, " / " means "or," for example, A / B can mean A or B. The "and / or" in this document is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, and B alone. Furthermore, "at least one" means one or more, and "multiple" means two or more. The terms "first," "second," etc., do not limit the quantity or order of execution, and "first," "second," etc., do not necessarily imply differences.

[0025] It should be noted that, in this application, the terms "exemplary" or "for example" are used to indicate that something is being described as an example, illustration, or illustration. Any embodiment or design described as "exemplary" or "for example" in this application should not be construed as being more preferred or advantageous than other embodiments or design solutions. Specifically, the use of terms such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner.

[0026] The material detection method based on big data provided in this application can be applied to, for example... Figure 1 The material inspection system based on big data shown below, such as Figure 1 As shown, the communication system includes: a sound wave transmitting module, a data acquisition module, and a data analysis module; wherein, The acoustic wave transmitting module is used to transmit frequency-sweeping acoustic waves to incoming materials in the terminal warehouse using an acoustic wave transmitting device. The data acquisition module is used to collect vibration velocity spectrum data and sound pressure gradient data of the materials after they are received by the frequency sweep sound wave. The vibration velocity spectrum data represents the distribution of vibration velocity at each point on the surface of the materials as a function of frequency, and the sound pressure gradient data represents the rate of change of the sound pressure value on the surface of the materials as a function of spatial location. The data analysis module is used to calculate the defect index of the target material based on vibration velocity spectrum data and sound pressure gradient data. When the defect index is greater than the preset threshold, the material entering the warehouse is marked as defective material, and a traceability detection command is sent to the upper node warehouse. The traceability detection command is used to start the graded detection process of the upper node warehouse.

[0027] To address the technical problems of low accuracy in material inspection and poor coordination in supply chain quality control in existing technologies, this application provides a material inspection method and system based on big data. The method includes: A sweeping sound wave is emitted to the incoming goods in the terminal warehouse using a sound wave transmitting device; The vibration velocity spectrum data and sound pressure gradient data of the materials received after receiving the frequency sweep sound wave are collected; the vibration velocity spectrum data represents the distribution of vibration velocity at each point on the surface of the materials as a function of frequency, and the sound pressure gradient data represents the rate of change of the sound pressure value on the surface of the materials as a function of spatial location. The defect index of the incoming materials is calculated based on the vibration velocity spectrum data and sound pressure gradient data. When the defect index exceeds the preset threshold, the incoming materials are marked as defective materials, and a traceability inspection command is sent to the upstream warehouse. The traceability inspection command is used to initiate the graded inspection process of the upstream warehouse.

[0028] like Figure 2 As shown in the embodiments of this application, the material detection method based on big data includes: S1. Use a sound wave transmitting device to transmit frequency sweeping sound waves to the incoming materials in the terminal warehouse.

[0029] Among them, the end-point warehouse refers to the warehouse at the end of the supply chain, directly connected to end-user demand, used to temporarily store incoming materials that are about to be distributed to the end user. Sweep frequency sound waves are used to excite the incoming materials to vibrate, and the internal or surface defects of the materials are reflected by the vibration response and sound field changes. The frequency range is usually 20Hz-1MHz (covering the audio to ultrasonic bands, which can be adjusted according to the material and testing requirements).

[0030] In some implementations, the sound wave emitting device can be a loudspeaker, an ultrasonic transducer, etc., and the sweep rate (such as linear or logarithmic sweep) can be adjusted by a control device to ensure that the sound wave covers the frequency range in which the material may resonate.

[0031] It should be noted that the transmission of frequency sweep acoustic waves should be kept stable to avoid interference with the acquisition of vibration response of materials due to vibration of the device itself or external noise.

[0032] For example, for metallic materials, a sweeping sound wave of 50kHz-500kHz can be used to more easily excite abnormal vibrations at internal defects.

[0033] S2. Collect vibration velocity spectrum data and sound pressure gradient data of the materials received after receiving the sweep frequency sound wave.

[0034] Among them, the vibration velocity spectrum data represents the distribution of vibration velocity at each point on the material surface as a function of frequency, and the sound pressure gradient data represents the rate of change of sound pressure value on the material surface as a function of spatial location.

[0035] In some implementations, vibration velocity spectrum data can be acquired by vibration sensors (VS), such as piezoelectric vibration sensor arrays; sound pressure gradient data can be acquired by microphone arrays (MA), and the rate of change of sound pressure with position can be calculated by the spatial distribution of multiple microphones.

[0036] It should be noted that the vibration sensor and microphone array should be deployed to cover key areas of the material surface, and their sampling frequencies should be consistent (e.g., 1kHz-100kHz) to ensure data matching in the time dimension.

[0037] S3. Calculate the defect index of the materials entering the warehouse based on the vibration velocity spectrum data and sound pressure gradient data.

[0038] The defect index is used to characterize the likelihood and severity of defects in incoming materials; the higher the value, the greater the risk of defects.

[0039] In some implementations, the defect index can be calculated using data fusion algorithms. For example, the proportion of frequency components deviating from the normal range in the vibration velocity spectrum data and the area proportion of abnormal gradient regions in the sound pressure gradient data can be weighted and summed, and the weights of the weighted summation can be dynamically adjusted according to the type of materials.

[0040] It should be noted that healthy objects exhibit a uniform vibration velocity distribution and a symmetrical sound field during resonance. However, once a crack exists, a stress concentration zone forms at the crack tip, leading to three anomalies: abrupt changes in local vibration velocity, phase shifts in vibration modes, and distortion of the sound pressure gradient. Therefore, using vibration velocity spectrum data and sound pressure gradient data to determine the defects in incoming materials, and combining the anomaly characteristics of both datasets, can effectively reduce the false positive rate of detection based on a single data source.

[0041] For example, if 30% of the frequency components in the vibration velocity spectrum data deviate from the normal range, and 20% of the region in the sound pressure gradient data has an abnormal gradient, and the vibration weight is set to 0.6 and the sound pressure weight is set to 0.4, then the defect index can be calculated as 30%×0.6+20%×0.4=26%.

[0042] S4. When the defect index is greater than the preset threshold, mark the incoming materials as defective materials and send a traceability detection instruction to the upstream warehouse.

[0043] Among them, the traceability detection command is used to initiate the hierarchical detection process of the previous node warehouse.

[0044] In some implementation methods, the tiered testing process can be: dividing the testing scope according to the risk level of the materials, such as full inspection of high-risk areas, sampling inspection of medium-risk areas, and routine inspection of low-risk areas.

[0045] It should be noted that the preset threshold needs to be determined by statistical analysis of historical data on materials judged as defective by human intervention, combined with an acceptable false judgment rate (such as 5%). For example, the mean or 90th percentile of the defect index of historical defective materials can be used as the initial threshold, and then dynamically optimized through actual application.

[0046] For example, if the average defect index of historical defective materials is 40%, the preset threshold can be set to 35%. When a material is detected to have a defect index of 42%, it is marked as a defective material and a traceability instruction is sent.

[0047] Based on the above technical solution, the material inspection method based on big data provided in this application excites material vibration by sweeping frequency sound waves and collects multi-dimensional response data. Combined with the defect index, the material quality is quantitatively evaluated, realizing accurate inspection from the end warehouse entry stage. At the same time, by sending traceability instructions to the upstream warehouse, the collaborative management of each node in the supply chain is promoted, effectively improving the comprehensiveness of material quality inspection and the traceability efficiency of supply chain quality problems, and providing technical support for the stable operation of the supply chain.

[0048] In one possible implementation of this application embodiment, the above-mentioned S1 can be specifically implemented by the following S101, S102, and S103, which are described in detail below: S101. Determine the transmission parameters of the swept frequency sound wave, including the frequency range, sweep method, and sampling frequency.

[0049] The frequency range must cover the frequency band that can excite the vibration response of the materials entering the warehouse. The frequency sweep method is used to control the frequency change pattern. The sampling frequency must be consistent with the equipment used to collect vibration velocity spectrum data and sound pressure gradient data later.

[0050] In some implementations, the frequency range can be determined according to the material of the material. For example, 20kHz-1MHz can be selected for metallic materials, and 20Hz-20kHz can be selected for non-metallic materials. The frequency sweeping method can be linear frequency sweep (frequency changes linearly with time) or logarithmic frequency sweep (frequency changes logarithmically with time). The sampling frequency is determined by matching the parameters of the laser Doppler vibrometer and the distributed microphone array.

[0051] It should be noted that the sampling frequency should be set to be higher than twice the highest frequency of the swept sound wave, that is, in accordance with the Nyquist sampling theorem, in order to avoid signal aliasing from affecting the accuracy of subsequent data.

[0052] For example, if a certain plastic material is being inspected upon entering the warehouse, and the frequency range is determined to be 50Hz-10kHz, a linear frequency sweep method is used, and the sampling frequency of the laser Doppler vibrometer is 20kHz, then the sampling frequency of the frequency sweep sound wave is set to 20kHz.

[0053] S102. Input the determined transmission parameters into the control module of the acoustic wave transmitting device to complete the device debugging.

[0054] The control module is used to receive parameters and regulate the operating status of the acoustic wave transmitting device to ensure that the transmission parameters are executed accurately.

[0055] In some implementations, the control module can be implemented using a programmable logic controller (PLC) or a microprocessor, supporting real-time modification and storage of parameters, facilitating rapid parameter switching when testing different batches of materials.

[0056] It should be noted that during the debugging process, the output power stability of the sound wave emitting device needs to be checked to avoid inconsistent vibration response of materials due to power fluctuations.

[0057] For example, the sweep rate is set to 1kHz / s (i.e., the frequency increases by 1kHz per second) by the control module, and the power detection function is activated to ensure that the output power fluctuation range does not exceed ±5%.

[0058] S103. Control the sound wave emitting device to emit frequency sweeping sound waves with set parameters to the incoming materials in the terminal warehouse.

[0059] During the launch process, it is necessary to ensure that the sound waves cover the key inspection areas of the materials, such as vulnerable parts of the surface and areas of concentrated structural stress.

[0060] In some implementations, the excitation effect of sound waves on materials can be improved by adjusting the installation position of the sound wave emitting device, such as making it at a 30°-60° angle with the surface of the material, or by increasing the number of emitting devices, such as using multiple emitting devices arranged in an array.

[0061] For example, for rectangular prism-shaped materials entering the warehouse, one sound wave emitting device is deployed on each of its two opposite sides to simultaneously emit sweeping sound waves, ensuring that the entire material can be effectively excited.

[0062] Based on the above technical solution, by clearly defining the step-by-step operation of parameter setting, device debugging and precise transmission, it is ensured that the frequency sweeping sound wave can stably and effectively excite the vibration response of the materials entering the warehouse, laying the foundation for the accurate acquisition of subsequent vibration velocity spectrum data and sound pressure gradient data, and improving the reliability of the early data for material defect detection.

[0063] In one possible implementation of this application embodiment, the above-mentioned S2 can be specifically implemented by the following S201, S202 and S203, which are described in detail below: S201. Deploy vibration velocity spectrum data acquisition equipment and sound pressure gradient data acquisition equipment, and align them with the material inspection area of ​​the terminal warehouse.

[0064] Among them, the vibration velocity spectrum data acquisition equipment uses a laser Doppler vibrometer (LDV) to measure the vibration velocity at various points on the surface of the material in a non-contact manner; the sound pressure gradient data acquisition equipment uses a distributed microphone array (DMA), which consists of multiple microphones arranged at preset spatial intervals to collect the spatial distribution of sound pressure around the material.

[0065] In some implementations, a laser Doppler vibrometer can be installed on a three-axis displacement platform, and the scanning range can be adjusted by program control to ensure coverage of key areas on the material surface, such as corners and seams; a distributed microphone array can be fixed within a 1-3 meter range around the material, arranged in a circle or rectangle, and the number of microphones can be set according to the detection accuracy requirements, usually 8-64.

[0066] It should be noted that the equipment should be deployed in a way that avoids obstruction, ensuring that the laser beam of the laser Doppler vibrometer is incident vertically or nearly vertically onto the surface of the material, and that the microphone array is pointing towards the material to reduce signal attenuation.

[0067] It should be noted that in this application, the sound wave emitting device is used to induce forced vibration on the surface of a material through air or structural conduction. Resonance occurs when the sound wave frequency matches the natural frequency of the material, and defects in the area can cause local stiffness changes, resulting in abnormal vibration responses. The "vibration velocity spectrum data" generated by the sound wave-induced vibration of the material is obtained using a laser Doppler vibrometer. That is, when a laser beam irradiates the surface of a vibrating object, the frequency of the reflected light will undergo a Doppler frequency shift due to the object's vibration. By measuring this frequency shift, the vibration velocity of the object can be calculated.

[0068] For example, for inbound materials with a surface area of ​​2m×1m, the scanning step of the laser Doppler vibration meter is set to 5mm to cover the entire surface of the materials; 16 microphones are deployed around the materials to form a 32-channel distributed array, with the distance between adjacent microphones being 30cm.

[0069] S202. Set the sampling parameters of the acquisition device and perform time synchronization calibration.

[0070] The sampling parameters include sampling frequency and sampling duration. It is necessary to ensure that the sampling frequency of the laser Doppler vibrometer and the distributed microphone array are the same, and the sampling duration is not shorter than the transmission duration of the swept frequency sound wave, so as to fully record the response of the material throughout the entire swept frequency process.

[0071] In some implementations, a high-precision clock synchronization module, such as Global Positioning System (GPS) synchronization or IEEE 1588 Precision Time Protocol, is used to calibrate the time of the two devices to ensure that the timestamp error of the data acquisition does not exceed 10 microseconds.

[0072] It should be noted that the sampling frequency setting must match the highest frequency of the swept sound wave, usually 2-5 times the highest frequency of the swept wave, in order to satisfy the Nyquist sampling theorem and avoid signal aliasing.

[0073] For example, if the highest frequency of the swept sound wave is 1MHz, the sampling frequency is uniformly set to 2MHz, and the sampling duration is set to the sweep duration plus 2 seconds to ensure that the attenuated vibration signal after the sweep ends is included.

[0074] S203. Simultaneously with the transmission of the sweeping sound wave, the acquisition equipment is activated to synchronously acquire the vibration velocity spectrum data and sound pressure gradient data of the materials entering the warehouse.

[0075] In some implementations, the acquisition device can be connected to a data caching server to store the real-time acquired data in a time series, generating a data segment every second for easy subsequent verification and traceability.

[0076] It should be noted that unnecessary noise sources (such as broadcasts and fans) in the warehouse should be turned off during the data collection process, and the interference of environmental noise on the microphone array should be reduced by using soundproof covers or sound-absorbing materials to ensure that the signal-to-noise ratio of the sound pressure gradient data is not less than 20dB.

[0077] For example, when the sound wave emitting device starts emitting frequency sweeping sound waves, it triggers the synchronous start signal of the acquisition device. The laser Doppler vibrometer scans the surface of the material point by point with a step size of 5mm, and collects 1024 data samples at each point. The distributed microphone array synchronously records the sound pressure signal, with each microphone generating 2 million sampling points per second, and continues to collect until 1 second after the frequency sweep ends.

[0078] Based on the above technical solution, the accuracy, synchronization and integrity of vibration velocity spectrum data and sound pressure gradient data are ensured, providing reliable raw data support for subsequent calculation of the defect index, and improving the effectiveness of data correlation analysis.

[0079] In one possible implementation of the embodiments of this application, combined with Figure 2 ,like Figure 3 As shown, the above S3 can be implemented through the following S301, S302 and S303, which are explained in detail below: S301. Preprocess the vibration velocity spectrum data to obtain the preprocessed velocity spectrum data.

[0080] The preprocessing includes bandpass filtering and noise reduction, which aims to remove irrelevant signals such as environmental noise and equipment interference, and retain effective vibration information related to material defects.

[0081] In some implementations, bandpass filtering can be performed using a Butterworth filter or a Chebyshev filter, with the filtering frequency band set according to the resonant frequency range corresponding to the material. For example, for metallic materials, the frequency band can be set to 10kHz-500kHz. Denoising can be performed using wavelet transform denoising, mean filtering, or median filtering algorithms to reduce the impact of random noise on the data.

[0082] For example, the collected vibration velocity spectrum data is filtered using an 8th-order Butterworth bandpass filter (passband 100kHz-300kHz), and then noise is removed by wavelet transform (using db4 wavelet basis, decomposed into 3 layers) to obtain smooth preprocessed velocity spectrum data v(f).

[0083] S302. Extract the abnormal vibration area and the abnormal sound pressure area, and determine the intersection of the two as the abnormal vibration area.

[0084] Among them, the vibration anomaly zone refers to the frequency band in the preprocessed velocity spectrum data that deviates from the reference spectrum by more than a preset threshold; the sound pressure anomaly zone refers to the spatial region in the sound pressure gradient data where the gradient value exceeds a preset gradient threshold; the abnormal vibration zone is the intersection of the two, used to focus on areas where defects may exist. The reference spectrum (RS) refers to the vibration velocity spectrum data of standard materials of the same type (without defects), which can be obtained by averaging the values ​​after testing multiple standard materials in the early stage.

[0085] In some implementations, the preset deviation threshold can be determined by statistically analyzing the deviation of the velocity spectrum between historical standard materials and defective materials (e.g., set to 30%); the preset gradient threshold can be set according to the spatial sound pressure gradient distribution range of the same type of standard materials (e.g., take 1.2 times the maximum gradient value of the standard materials).

[0086] It should be noted that the reference spectrum v ref (f) It needs to be updated regularly, such as recalculating after each batch of standard materials is tested, to avoid deviations in the benchmark due to minor changes in the production process; the extraction of the sound pressure abnormality area needs to be combined with the spatial coordinates of the materials to ensure the accuracy of the area positioning.

[0087] For example, the vibration velocity of the reference spectrum v0(f) of a certain type of standard material in the 100kHz frequency band is 0.5m / s. After preprocessing, the v(f) of a certain material entering the warehouse is 0.8m / s in the same frequency band, with a deviation of 60% (exceeding the 30% preset threshold). Therefore, the 100kHz frequency band is marked as an abnormal vibration zone. In the sound pressure gradient data, if the gradient value of a 20cm×20cm area on the surface of the material exceeds 5Pa / m (the preset gradient threshold is 3Pa / m), then this area is an abnormal sound pressure zone. The intersection of the two is the abnormal vibration zone.

[0088] It should be noted that the intersection of frequency bands and regions is not a direct dimensional intersection, but rather refers to the overlap and correlation of "vibration anomalies corresponding to a specific abnormal frequency band" and "sound pressure anomalies in a specific spatial region" in terms of materials. That is, the spatial region simultaneously exhibits vibration anomalies and sound pressure gradient anomalies under the abnormal frequency band.

[0089] Specifically, the vibration anomaly zone is defined by the frequency dimension—when the vibration velocity spectrum data of a certain frequency band deviates from the reference spectrum by more than a preset threshold, it indicates that the vibration of the material at that frequency is abnormal; while the sound pressure anomaly zone is defined by the spatial dimension—when the sound pressure gradient value of a certain spatial area exceeds a preset threshold, it indicates that the sound field distribution in that area is abnormal.

[0090] In actual testing, if a material has defects (such as cracks), it will cause local vibration anomalies at a specific frequency (corresponding to a certain abnormal frequency band). At the same time, the spatial region where the defect is located will experience sound pressure gradient distortion due to stress concentration (corresponding to a certain spatial sound pressure anomaly region). Therefore, "intersection" refers to the fact that within the abnormal frequency band, a certain spatial region on the surface of the material simultaneously exhibits abnormal vibration velocity and sound pressure gradient, that is, the vibration and sound field of this region at this frequency band both show abnormal characteristics.

[0091] In the exemplary scenario, the 100kHz frequency band is the vibration anomaly zone, indicating that the material vibrates abnormally at 100kHz; the 20cm×20cm area is the sound pressure anomaly zone, indicating that the sound pressure gradient in this area is abnormal. The intersection of the two is that "at 100kHz, the 20cm×20cm area simultaneously exhibits abnormal vibration velocity and abnormal sound pressure gradient," thus identifying this area as an abnormal vibration zone, i.e., an area where defects may exist.

[0092] S303. Calculate the defect index of the incoming materials according to the defect index calculation formula.

[0093] The defect index calculation formula is used to quantify the correlation between the characteristics of the abnormal vibration zone and the degree of deviation of the velocity spectrum, characterizing the severity of material defects. The formula involves the preprocessed velocity spectrum data v(f) and the reference spectrum. (f) and parameters such as the area A of the abnormal vibration zone.

[0094] In some implementations, the defect index DI is calculated using the following formula: Where Ω represents the frequency range of the swept-frequency sound wave, and A hs The area of ​​the abnormal vibration zone is represented by σ, and the standard deviation of the reference spectrum is represented by v. ref (f) represents the reference spectrum.

[0095] In some implementations, the standard deviation σ of the reference spectrum can be obtained by including the following steps: First, vibration velocity spectrum data of standard materials of the same type are collected. In this application, the reference spectrum can be obtained by collecting vibration velocity spectra of at least three defect-free standard materials of the same type using a laser Doppler vibrometer (each material is collected 5-10 times, with a total sample size of ≥15 sets). For example, for a batch of standard metal parts, the surface of each material is scanned at 5mm steps within the 100kHz-300kHz frequency band to obtain the vibration velocity-frequency curves at each point.

[0096] Then, the standard deviation at a single frequency point is calculated. For each frequency point f, the vibration velocity values ​​{v} of all standard samples at that frequency are extracted. 01 (f),v 02 (f),…,v 0n (f)}, calculate the standard deviation of a single frequency point using the population standard deviation formula: ; where μ(f) is the mean value at that frequency point, and n is the total number of standard samples.

[0097] Finally, a frequency-standard deviation mapping table is constructed. σ(f) at each frequency point is associated with the corresponding frequency f to form the standard deviation distribution of the reference spectrum, covering the entire frequency band of the swept-frequency sound wave. This mapping table serves as the benchmark parameter for calculating the defect index, used to quantify the degree of dispersion between the vibration velocity spectrum of the material under test and the standard spectrum.

[0098] It should be noted that the frequency range F in the formula must be consistent with the frequency range of the swept-frequency sound wave in S1, and the area A must be calculated based on the actual dimensions of the material surface, such as through spatial coordinate conversion, to ensure that the physical meaning of the value is clear. Furthermore, the standard deviation σ must be calculated separately for each material model to avoid confusion between different model benchmarks.

[0099] It should be noted that this application collects vibration velocity spectrum data and sound pressure gradient data of the materials after receiving the frequency sweep sound wave. First, the vibration velocity spectrum data is preprocessed by bandpass filtering and noise reduction. Then, the preprocessed velocity spectrum data is compared with the vibration velocity spectrum data of the same type of standard material (i.e., the reference spectrum). The frequency bands where the deviation between the two is greater than the preset deviation threshold are selected as vibration anomaly areas. In this process, the reference spectrum is a dedicated reference established based on the vibration characteristics of the same type of defect-free material. Even if the material under test has uneven surface or uneven texture, its vibration law in the defect-free state will be consistent with that of the same type of standard material. Therefore, by comparing the deviation with the reference spectrum, the vibration anomaly caused by defects in the material under test can be accurately captured, rather than being affected by the non-uniformity of the material itself.

[0100] Simultaneously, this application analyzes the collected sound pressure gradient data and, in conjunction with a preset gradient threshold set based on the spatial sound pressure gradient distribution range of standard materials of the same type, locates spatial areas where the sound pressure gradient value exceeds the threshold as sound pressure anomaly zones. The preset gradient threshold is not a uniform and fixed standard, but is determined based on the sound pressure distribution characteristics of materials of the same type under normal conditions. It can adapt to the natural sound pressure gradient differences of materials with different structures and materials, and only identifies sound pressure gradient distortion caused by defects.

[0101] Based on this, this application defines the intersection of the abnormal vibration zone and the abnormal sound pressure zone as the abnormal vibration zone. Combining the deviation of the preprocessed velocity spectrum data from the reference spectrum, the standard deviation of the reference spectrum, and the area of ​​the abnormal vibration zone, a defect index is calculated using a quantitative formula to determine whether the material has defects. The entire detection logic does not depend on whether the material surface is smooth or uniform in texture. It only needs to use the characteristics of a standard material of the same type as a reference to achieve defect detection for various types of materials. Whether the material has a regular, uniform surface or an irregular surface and uneven texture, as long as the reference data of a standard material of the same type can be obtained, defects can be accurately identified using this method.

[0102] Based on the above technical solution, step S3 improves signal quality through data preprocessing, focuses on potential defect areas by accurately locating abnormal areas, and calculates the defect index through a quantitative formula, realizing the transformation from raw data to the quantification of defect degree. This provides objective and comparable indicators for subsequent defect judgment, and can improve the accuracy and consistency of material defect detection.

[0103] In one possible implementation of the embodiments of this application, combined with Figure 2 ,like Figure 4 As shown, the above S4 specifically includes the following S401 to S403: S401. Compare the calculated defect index of the incoming materials with a preset threshold. If the defect index is greater than the preset threshold, mark the incoming materials as defective materials.

[0104] The preset threshold is a critical value used to define whether materials have defects. Its setting is based on the detection data of historical defective materials to ensure that normal materials can be effectively distinguished from defective materials.

[0105] In some implementation methods, the preset threshold can be determined by statistical analysis of the defect index of defective materials that have been manually verified in the past. For example, the 75th percentile of the defect index of historical defective materials can be taken as the initial threshold, and then dynamically adjusted according to the false judgment rate in actual detection (such as controlling the false judgment rate within 5%).

[0106] It should be noted that the preset thresholds need to be set separately according to the type of material. Due to differences in physical properties, the defect index range of different materials and models is different and cannot be used interchangeably (for example, the threshold for metal materials is usually higher than that for plastic materials).

[0107] For example, in historical data, the average defect index of a certain type of metal material is 60, and the 75th percentile is 70. After testing, the false judgment rate is 3% when the threshold is set to 65. Therefore, the preset threshold for this type of material is determined to be 65. If the defect index of a certain metal material entering the warehouse is 72 (greater than 65), it is marked as a defective material.

[0108] S402. Generate traceability and inspection instructions based on the information of defective materials.

[0109] The traceability and detection instructions must contain key information sufficient to initiate the warehouse tiered detection process of the previous node, providing a basis for the risk area division and detection operation of the previous node.

[0110] In some implementations, the traceability and detection instructions may include information such as the supplier code (S), production batch (L), defect index, and abnormal vibration zone characteristics (such as area and corresponding frequency range) of the defective materials. This information is obtained by retrieving the database of the materials management system.

[0111] For example, if a defective material has a supplier code of "S001", a production batch of "L202305", a defect index of 72, an abnormal vibration zone area of ​​0.04m², and a corresponding frequency of 100kHz-150kHz, then the traceability and detection instruction will explicitly include this information. This information will then be generated using a structured data format (such as JSON) for use by the previous node's warehouse.

[0112] S403. After receiving the instruction, the previous node warehouse performs risk area delineation, specifically including: (1) Screening related material set: Based on the supplier code S and production batch L of the defective material, filter out materials with the same supplier code and production date within a preset time window (e.g. ±15 days) from the database of the previous node to form a related material set.

[0113] (2) Calculate the risk coefficient: For the i-th material in the associated material cluster, calculate the risk coefficient λ according to the formula. i =α×δ i +β×e -kΔTi , where δ i The process similarity between the material and the defective material is calculated by the proportion of the number of production equipment used by the i-th material and the defective material to the total number of production equipment of the defective material. ΔTi is the time difference between the production dates of the i-th related material and the defective material, k is the attenuation coefficient, usually taken as 0.1, and α and β represent the weight coefficients of each item.

[0114] (3) Divide risk areas by spatial clustering: Obtain the three-dimensional model of the previous node warehouse; create a tuple containing spatial coordinates, supplier code, production batch and risk coefficient for each related material; use density clustering algorithm, such as DBSCAN, to perform spatial clustering on the tuple, and divide materials with spatial distance less than the preset neighborhood radius and risk coefficient difference within the preset range into the same risk area.

[0115] It should be noted that the values ​​of α and β can be determined through experimental experience. For example, for materials with high production process stability and significant equipment impact on quality (such as precision mechanical parts), the weight of process similarity is higher, and α=0.6 and β=0.4 can be set; for materials with strong time sensitivity and large fluctuations with production time (such as electronic components), the weight of production date difference is higher, and α=0.4 and β=0.6 can be set. Simultaneously, α and β must satisfy α+β=1 to ensure the risk coefficient λ. i The value range is between 0 and 1, which facilitates horizontal comparison of risk levels of different materials. The preset neighborhood radius is set according to the warehouse storage density (e.g., 1-3 meters) to ensure that materials with similar physical locations are included in the same analysis unit; the risk coefficient difference range (e.g., ±0.1) is used to screen materials with similar risk levels, so that materials in the same area have similar quality risk characteristics.

[0116] S404, The previous node warehouse performs a graded detection process based on the risk area: (1) Calculate the average risk coefficient of all materials in the k-th risk area. =(λ1+λ2+...+λ n ) / n, where n is the quantity of materials in the area, and the risk coefficient of non-related materials is 0.

[0117] (2) According to λ kThe results of comparison with thresholds T1 and T2 (T1>T2) are used for graded detection: like >T1 (e.g., T1=0.6) is marked as a Level 1 risk area, and all materials are subject to full inspection. The inspection method is as described in the first part. If T2 < If the defect rate is ≤T1 (e.g., T2=0.3), it is marked as a level 2 risk area and sampled for inspection at the first proportion (e.g., 30%). If the defect rate exceeds the preset proportion (e.g., 10%), it is upgraded to level 1 inspection. like If the defect rate is ≤T2, it is marked as a Level 3 risk area and sampled for testing at the second rate (e.g., 10%). If the defect rate exceeds the preset rate, it is upgraded to Level 2 testing.

[0118] In some implementations, T1 and T2 are preset grading thresholds, determined by statistical analysis of the defect rate in historical risk areas; for example, T1 is set to a value that makes the defect detection rate of the first-level area ≥95%; the sampling ratio (including the first ratio and the second ratio) is adjusted according to the area size, and the ratio can be appropriately reduced for larger areas.

[0119] It should be noted that when a defective material is detected at the previous node, a traceability command needs to be sent to the next higher node to form a multi-level linkage.

[0120] For example, the average risk coefficient of risk area Z1 =0.5 (T1=0.6, T2=0.3), which is determined to be a level 2 risk area. 10 items are sampled at a rate of 30%. If 2 of them are defective (accounting for 20% > 10%), Z1 will be upgraded to a level 1 area and a full inspection will be carried out.

[0121] Based on the above technical solution, step S4 achieves end-to-end quality traceability from the end warehouse to the previous node through defect marking, traceability instruction generation, risk area division, and graded detection. This ensures that defective materials do not flow downstream through precise marking, and promotes targeted detection at the previous node through traceability instructions, reducing ineffective detection costs and improving the synergy and efficiency of supply chain quality control. It also provides support for the rapid location and resolution of quality problems across the entire chain.

[0122] It should be noted that this application uses a step-by-step upward tracing method from the end warehouse to locate defects in order to accurately assign responsibility and distinguish whether the cause of the material defect is an original quality problem provided by the supplier or damage that occurs during the flow of the material in the supply chain (such as transportation, handling, and storage).

[0123] Specifically, if the defect originates from a supplier's quality issue, related materials from the same production batch or with similar processes will typically share common defects. Tracing back to the previous node from the end warehouse, filtering related material sets based on supplier codes and production batches, calculating risk coefficients, and dividing risk areas will reveal defects across multiple nodes' related material sets. The tracing process will extend upwards level by level, ultimately pinpointing the initial supplier node. If the defect is caused by transportation or manual handling, this type of damage is usually accidental, existing only in a few materials at a specific stage of the flow. In this case, tracing back to the previous node reveals that the risk coefficients of the related material sets are generally low, and the number of defective materials in the tiered inspection is small. The tracing process will stop at a certain node warehouse and will not continue upwards.

[0124] Therefore, the test results of the end warehouse can drive upstream quality control through the traceability mechanism. As the last checkpoint before the end, it can extend quality assurance to the front end of actual application and sales, which not only meets the actual needs of quality control at the end of the supply chain, but also provides a guarantee for the application and sales of products in the market.

[0125] The above primarily describes the solutions of the embodiments of this application from the perspective of device implementation. It is understood that each device, such as a big data-based material inspection device, includes at least one of the hardware structures and software modules corresponding to each function in order to achieve the above-mentioned functions. Those skilled in the art should readily recognize that, in conjunction with the units and algorithm steps of the various examples described in the embodiments disclosed herein, this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed by hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0126] This application embodiment can divide the big data-based material inspection device into functional units according to the above method example. For example, each function can be divided into separate functional units, or two or more functions can be integrated into one processing unit. The integrated unit can be implemented in hardware or as a software functional unit. It should be noted that the unit division in this application embodiment is illustrative and only represents one logical functional division; other division methods may be used in actual implementation.

[0127] When using integrated units, Figure 5A possible structural schematic diagram of the big data-based material inspection device (referred to as big data-based material inspection device 50) involved in the above embodiments is shown. The big data-based material inspection device 50 includes a processing unit 501 and a communication unit 502, and may also include a storage unit 503. Figure 5 The structural diagram shown can be used to illustrate the structure of the big data-based material detection device involved in the above embodiments.

[0128] when Figure 5 The schematic diagram shown illustrates the structure of the big data-based material inspection device involved in the above embodiments. The processing unit 501 is used to control and manage the operation of the big data-based material inspection device, the communication unit 502 is used for the big data-based material inspection device to communicate with other devices, and the storage unit 503 is used to store the program code and data of the big data-based material inspection device.

[0129] For example, the communication unit 502 is used to receive vibration velocity spectrum data and sound pressure gradient data, send traceability detection commands to the upper node warehouse, and interact with the sound wave emitting device and data acquisition equipment.

[0130] The processing unit 501 is used to control the sound wave emitting device to emit frequency sweep sound waves to the materials entering the warehouse, process the collected vibration velocity spectrum data and sound pressure gradient data to calculate the defect index, determine whether the materials are defective materials based on the defect index, and generate a traceability detection command when the materials are determined to be defective materials.

[0131] In one possible implementation, the processing unit 501 is further configured to preprocess the vibration velocity spectrum data, extract abnormal vibration areas and abnormal sound pressure areas and determine abnormal vibration areas, as well as divide risk areas according to risk coefficients and execute graded detection processes.

[0132] In one possible implementation, the communication unit 502 is further configured to receive the graded detection results fed back from the previous node warehouse; the processing unit 501 is further configured to adjust the preset threshold and risk coefficient calculation parameters according to the feedback results, and optimize the subsequent detection process.

[0133] Storage unit 503 is used to store benchmark spectrum data of standard materials of the same model, historical defective material data, preset thresholds, program code, and three-dimensional model information of each node warehouse, providing data support for data analysis and decision-making of the processing unit.

[0134] The processing unit 501 can be a processor or a controller, and the communication unit 502 can be a communication interface, transceiver, transceiver circuit, transceiver device, etc. The term "communication interface" is a general term and may include one or more interfaces. The storage unit 503 can be a memory. When the big data-based material detection device 50 is a chip, the processing unit 501 can be a processor or a controller, and the communication unit 502 can be an input interface and / or an output interface, pins, or circuits, etc. The storage unit 503 can be a storage unit within the chip (e.g., a register, cache, etc.) or a storage unit located outside the chip (e.g., read-only memory (ROM), random access memory (RAM, etc.)).

[0135] The communication unit can also be called a transceiver unit. The antenna and control circuit with transceiver functions in the big data-based material inspection device 50 can be considered as the communication unit 502 of the big data-based material inspection device 50, and the processor with processing functions can be considered as the processing unit 501 of the big data-based material inspection device 50. Optionally, the device in the communication unit 502 used to implement the receiving function can be considered as a communication unit, which is used to execute the receiving steps in the embodiments of this application. The communication unit can be a receiver, a receiver circuit, etc. The device in the communication unit 502 used to implement the transmitting function can be considered as a transmitting unit, which is used to execute the transmitting steps in the embodiments of this application. The transmitting unit can be a transmitter, a transmitter, a transmitting circuit, etc.

[0136] Figure 5 If the integrated units in the process are implemented as software functional modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the embodiments of this application, in essence, or the parts that contribute to the prior art, or all or part of the technical solutions, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor to execute all or part of the steps of the methods described in the various embodiments of this application. Storage media for storing computer software products include various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory, random access memory, magnetic disks, or optical disks.

[0137] Figure 5 The units in the process can also be called modules; for example, a processing unit can be called a processing module.

[0138] This application embodiment also provides a hardware structure diagram of a big data-based material inspection device (referred to as big data-based material inspection device 60), see [link to diagram]. Figure 6 The big data-based material detection device 60 includes a processor 601, and optionally, a memory 602 connected to the processor 601.

[0139] In the first possible implementation, see Figure 6 The material inspection device 60 based on big data also includes a transceiver 603. The processor 601, memory 602, and transceiver 603 are connected via a bus. The transceiver 603 is used to communicate with other devices or communication networks. Optionally, the transceiver 603 may include a transmitter and a receiver. The device in the transceiver 603 that implements the receiving function can be considered as a receiver, which is used to perform the receiving steps in the embodiments of this application. The device in the transceiver 603 that implements the transmitting function can be considered as a transmitter, which is used to perform the transmitting steps in the embodiments of this application.

[0140] Based on the first possible implementation method Figure 6 The structural diagram shown can be used to illustrate the structure of the big data-based material detection device involved in the above embodiments.

[0141] in, Figure 6 This can also be illustrated by the system chip in a big data-based material inspection device. In this case, the actions performed by the aforementioned big data-based material inspection device can be implemented by this system chip. The specific actions performed can be found above and will not be repeated here.

[0142] In implementation, each step of the method provided in this embodiment can be completed by integrated logic circuits in the processor or by instructions in software form. The steps of the method disclosed in the embodiments of this application can be directly manifested as being executed by a hardware processor, or being executed by a combination of hardware and software modules in the processor.

[0143] The processor in this application may include, but is not limited to, at least one of the following: a central processing unit (CPU), a microprocessor, a digital signal processor (DSP), a microcontroller unit (MCU), or an artificial intelligence processor, etc., which are various computing devices that run software. Each computing device may include one or more cores for executing software instructions to perform calculations or processing. The processor may be a separate semiconductor chip or integrated with other circuits into a single semiconductor chip. For example, it may be integrated with other circuits (such as encoding / decoding circuits, hardware acceleration circuits, or various bus and interface circuits) to form a SoC (System-on-a-Chip), or it may be integrated as a built-in processor within an ASIC. The ASIC with the integrated processor may be packaged separately or together with other circuits. In addition to the cores for executing software instructions to perform calculations or processing, the processor may further include necessary hardware accelerators, such as field-programmable gate arrays (FPGAs), PLDs (programmable logic devices), or logic circuits that implement dedicated logic operations.

[0144] The memory in the embodiments of this application may include at least one of the following types: read-only memory (ROM) or other types of static storage devices capable of storing static information and instructions; random access memory (RAM) or other types of dynamic storage devices capable of storing information and instructions; or electrically erasable programmable-only memory (EEPROM). In some scenarios, the memory may also be a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media, or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures that can be accessed by a computer, but is not limited thereto.

[0145] This application also provides a computer-readable storage medium including instructions that, when run on a computer, cause the computer to perform any of the methods described above.

[0146] This application also provides a computer program product containing instructions that, when run on a computer, cause the computer to perform any of the methods described above.

[0147] This application also provides a chip including a processor and an interface circuit. The interface circuit is coupled to the processor. The processor is used to run computer programs or instructions to implement the above-described method. The interface circuit is used to communicate with other modules outside the chip.

[0148] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented using software programs, implementation can be, in whole or in part, in the form of a computer program product. This computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium accessible to a computer or a data storage device containing one or more servers, data centers, etc., that can be integrated with the medium. The available media can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media (e.g., solid-state disks (SSDs)).

[0149] Although this application has been described herein in conjunction with various embodiments, those skilled in the art, by reviewing the accompanying drawings, disclosure, and appended claims, will understand and implement other variations of the disclosed embodiments in carrying out the claimed application. In the claims, the word "comprising" does not exclude other components or steps, and "a" or "an" does not exclude multiple instances. A single processor or other unit can implement several functions listed in the claims. While different dependent claims may recite certain measures, this does not mean that these measures cannot be combined to produce good results.

[0150] Although this application has been described in conjunction with specific features and embodiments, it is obvious that various modifications and combinations can be made thereto without departing from the spirit and scope of this application. Accordingly, this specification and drawings are merely illustrative descriptions of the application as defined by the appended claims, and are considered to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Clearly, those skilled in the art can make various alterations and modifications to this application without departing from the spirit and scope of this application. Thus, if such modifications and variations of this application fall within the scope of the claims of this application and their equivalents, this application is also intended to include such modifications and variations.

Claims

1. A material inspection method based on big data, characterized in that, include: A sweeping sound wave is emitted to the incoming goods in the terminal warehouse using a sound wave transmitting device; The vibration velocity spectrum data and sound pressure gradient data of the materials received after receiving the frequency sweeping sound wave are collected; the vibration velocity spectrum data represents the distribution of vibration velocity at each point on the surface of the materials as a function of frequency, and the sound pressure gradient data represents the set of rates of change of sound pressure values ​​at spatial locations on the surface of the materials in the sound field. The defect index of the incoming materials is calculated based on the vibration velocity spectrum data and sound pressure gradient data. When the defect index is greater than a preset threshold, the incoming materials are marked as defective materials, and a traceability inspection instruction is sent to the upstream node warehouse; the traceability inspection instruction is used to instruct the node warehouse to perform a graded inspection process. The calculation of the defect index of the target material based on vibration velocity spectrum data and sound pressure gradient data includes: The vibration velocity spectrum data is subjected to bandpass filtering and denoising to obtain the preprocessed velocity spectrum data v(f); Extract the velocity spectrum data from the preprocessed data that corresponds to the reference spectrum v ref (f) refers to the abnormal frequency band where the deviation value is greater than the preset deviation threshold, and the vibration abnormal zone is obtained; the reference spectrum represents the vibration velocity spectrum data of the same type of standard material; Extract the spatial regions in the sound pressure gradient data whose gradient values ​​are greater than a preset gradient threshold to obtain the sound pressure anomaly region; The intersection of the abnormal vibration zone and the abnormal sound pressure zone is marked as the abnormal vibration zone; specifically, if a certain spatial region on the surface of a material exhibits both abnormal vibration velocity and abnormal sound pressure gradient within the abnormal frequency band, then that spatial region is marked as the abnormal vibration zone. The defect index of the target material is obtained according to the defect index calculation formula; the defect index calculation formula satisfies: Where DI represents the defect index, Ω represents the frequency range of the swept-frequency sound wave, and A hs σ represents the area of ​​the abnormal vibration zone, σ represents the standard deviation of the reference spectrum, and f represents the frequency of the swept sound wave.

2. The material inspection method based on big data according to claim 1, characterized in that, The graded testing process includes: Obtain the supplier code S and production batch L based on the defective materials; Filter the associated material set Q in the database of the previous node warehouse; the associated material set has the same supplier code as the defective material, and the production date of the production batch is within a preset time window; Calculate the risk coefficient of materials within the associated material set; Cluster analysis is performed based on the spatial location of the warehouse at the previous node according to the risk coefficient to obtain multiple risk areas; Multiple risk areas are subject to tiered testing.

3. The material inspection method based on big data according to claim 2, characterized in that, The formula for calculating the risk coefficient is: λ i =α×δ i +β×e -kΔTi ; where λ i δ represents the risk coefficient of the i-th associated material in the associated material set. i The process similarity between the i-th associated material and the defective material is represented by the ratio of the number of identical production equipment used by the i-th material and the defective material to the total number of production equipment used by the defective material. ΔTi represents the time difference between the production dates of the i-th associated material and the defective material, k represents the attenuation coefficient, and α and β represent the weight coefficients of each item.

4. The material inspection method based on big data according to claim 2, characterized in that, The cluster analysis includes: Get the 3D model of the previous node's warehouse; Based on the aforementioned 3D model, a spatial mapping of materials is performed, creating a tuple for each material containing spatial coordinates (x, y, z), supplier code, production batch, and risk coefficient λ; where, if material w If the associated material set Q is given, then the risk coefficient λ w =0; Using spatial clustering algorithms, the tuples of the material point set are spatially clustered to obtain the risk region set {Z}. k |k=1,2,…,K}, where Z k Let K represent the k-th risk area, where K represents the number of risk areas.

5. The material inspection method based on big data according to claim 3, characterized in that, The tiered detection of multiple risk areas includes: Calculate the average risk coefficient of all related materials in the k-th risk area. ; when When the value is greater than T1, the risk area is marked as a first-level risk area and a first-level detection is performed. The first-level detection includes: sequentially transmitting frequency sweeping radio waves to all materials in the first-level risk area, calculating the defect index of each material in the first-level risk area based on the vibration velocity spectrum data and sound pressure gradient data of the materials; when the defect index is greater than a preset threshold, the target material is marked as a defective material. When T2 < When the value is ≤T1, the risk area is marked as a secondary risk area, and secondary detection is performed. The secondary detection includes: All materials in the Level 2 risk area are randomly selected at a first ratio to obtain the first sampled materials; Frequency sweeping waves are sequentially emitted to the first sampled material, and the defect index of each sampled material is calculated based on the vibration velocity spectrum data and sound pressure gradient data of the material; when the defect index is greater than the preset threshold, the target material is marked as a defective material. If the proportion of defective materials in the first sample exceeds the preset ratio, the secondary risk area will be marked as a primary risk area, and the primary inspection will be performed. when When the risk level is ≤T2, the risk area is marked as a level 3 risk area, and level 3 detection is performed. The level 3 detection includes: All materials in the Level 3 risk area are randomly selected at a second ratio to obtain the second sampled materials; and the second ratio is less than the first ratio. The second sampled material is sequentially emitted with a sweeping radio wave. The defect index of each sampled material is calculated based on the vibration velocity spectrum data and sound pressure gradient data of the material. When the defect index is greater than the preset threshold, the target material is marked as a defective material. If the proportion of defective materials in the second sample exceeds the preset ratio, the level 3 risk area will be marked as a level 2 risk area, and the level 2 inspection will be performed.

6. The material inspection method based on big data according to claim 5, characterized in that, When performing the hierarchical detection in the previous node warehouse: If new defective materials are detected during the graded detection of multiple risk areas, a traceability detection instruction is sent to the superior node warehouse of the previous node warehouse, and the risk area division and graded detection process are executed in the superior node warehouse.

7. The material inspection method based on big data according to claim 1, characterized in that, The vibration velocity spectrum data is acquired using a laser Doppler vibrometer, and the sound pressure gradient data is collected using a distributed microphone array. The sampling frequencies of the vibration velocity spectrum data and the sound pressure gradient data are the same.

8. A material inspection system based on big data, characterized in that, include: The system comprises a sound wave emission module, a data acquisition module, and a data analysis module; among which, The sound wave transmitting module is used to transmit frequency-sweeping sound waves to the incoming materials in the terminal warehouse using a sound wave transmitting device. The data acquisition module is used to collect vibration velocity spectrum data and sound pressure gradient data of the materials after they are received by the frequency sweeping sound wave; the vibration velocity spectrum data represents the distribution of vibration velocity at each point on the surface of the materials as a function of frequency, and the sound pressure gradient data represents the rate of change of the sound pressure value on the surface of the materials as a function of spatial position. The data analysis module is used to calculate the defect index of the target material based on the vibration velocity spectrum data and sound pressure gradient data. When the defect index is greater than a preset threshold, the material entering the warehouse is marked as defective material, and a source detection command is sent to the upstream warehouse. The source detection command is used to start the graded detection process of the upstream warehouse. The calculation of the defect index of the target material based on vibration velocity spectrum data and sound pressure gradient data includes: The vibration velocity spectrum data is subjected to bandpass filtering and denoising to obtain the preprocessed velocity spectrum data v(f); Extract the velocity spectrum data from the preprocessed data that corresponds to the reference spectrum v ref (f) refers to the abnormal frequency band where the deviation value is greater than the preset deviation threshold, and the vibration abnormal zone is obtained; the reference spectrum represents the vibration velocity spectrum data of the same type of standard material; Extract the spatial regions in the sound pressure gradient data whose gradient values ​​are greater than a preset gradient threshold to obtain the sound pressure anomaly region; The intersection of the abnormal vibration zone and the abnormal sound pressure zone is marked as the abnormal vibration zone; specifically, if a certain spatial region on the surface of a material exhibits both abnormal vibration velocity and abnormal sound pressure gradient within the abnormal frequency band, then that spatial region is marked as the abnormal vibration zone. The defect index of the target material is obtained according to the defect index calculation formula; the defect index calculation formula satisfies: Where DI represents the defect index, Ω represents the frequency range of the swept-frequency sound wave, and A hs σ represents the area of ​​the abnormal vibration zone, σ represents the standard deviation of the reference spectrum, and f represents the frequency of the swept sound wave.

Images