Foreign matter particle material identification method and device and storage medium

Abstract

The embodiment of the invention relates to the technical field of acoustic detection, and discloses a foreign matter particle material identification method and device and a storage medium, the method comprises the following steps: obtaining a frequency spectrum signal corresponding to an acoustic signal of at least one acoustic sensor, the acoustic sensor being arranged on a to-be-detected product, in the process that the to-be-detected product is excited to generate mechanical vibration, the frequency spectrum signal corresponding to the acoustic signal of the acoustic sensor; the acoustic sensor acquires an acoustic signal; obtaining frequency band characteristics, signal-to-noise ratios of the frequency band characteristics, peak amplitude and duration of the frequency band characteristics except the frequency band of the environmental noise in the frequency spectrum signal; detecting whether foreign matter particles exist in the to-be-detected product or not according to the frequency band characteristics and the duration time of the frequency band characteristics; if the foreign matter particles exist in the to-be-detected product, the materials of the foreign matter particles are recognized according to the frequency band characteristics, the signal-to-noise ratio, the peak amplitude and the duration time, the material recognition result is output, and the materials comprise the metal material and the non-metal material. In this way, efficient, accurate and non-destructive foreign matter particle material recognition is achieved.

Description

Technical Field

[0001] This invention relates to the field of acoustic detection technology, specifically to a method, device, and storage medium for identifying foreign particle materials. Background Technology

[0002] Foreign particle detection is mainly used in various processes such as product welding and assembly to detect foreign particles inside the product in advance. For example, in the military and aerospace fields, precision instruments may contain various tiny foreign particles such as loose screws and detached welding slag. In the communications field, foreign particles may be present in the metal cavities of modules such as duplexers and filters inside 5G base stations. In the field of new energy vehicles, IGBT modules in the power battery control system also need to be detected for particles. If foreign particles are present inside the product, they will be activated and released when the product is operating under conditions such as ultra-high acceleration or severe impact. These particles will then move randomly and irregularly within the product cavity, either suspending within the cavity or falling onto certain components, posing a significant threat to the reliability of the product. At best, metallic particles can cause short circuits, pipe blockages, and jamming of moving parts; non-metallic particles can also cause pipe blockages and jamming of moving parts. At worst, they can lead to serious quality accidents such as explosions.

[0003] Currently, foreign object particle detection in high-end products such as electronic devices mainly suffers from the following technical limitations: 1. Traditional vibration detection methods use single-frequency vibration to determine the presence of foreign objects through sound signals, but cannot distinguish material types; 2. X-ray detection technology can detect metallic foreign objects, but has limited ability to identify non-metallic materials, and the equipment is expensive; 3. Optical detection methods require damaging the product packaging, resulting in low detection efficiency and the inability to identify internal foreign objects; 4. Simple acoustic detection can only determine the presence or absence of foreign particles, lacks material classification capabilities, and has a high false positive rate. Summary of the Invention

[0004] In view of the above problems, embodiments of the present invention provide an efficient, accurate and non-destructive method, device and storage medium for identifying foreign particle materials, so as to solve the problems existing in the prior art.

[0005] According to one aspect of the present invention, a method for identifying foreign particle material is provided, the method comprising: Acquire the spectral signal corresponding to the acoustic signal of at least one acoustic sensor, wherein the acoustic sensor is disposed on the product to be tested, and the acoustic sensor acquires the acoustic signal during the process of the product to be tested being excited to generate mechanical vibration. The spectrum signal is analyzed to obtain the frequency band characteristics of the spectrum signal excluding the frequency band of environmental noise, the signal-to-noise ratio, peak amplitude and duration of the frequency band characteristics; The presence of foreign particles in the product under test is detected based on the frequency band characteristics and the duration of the frequency band characteristics. If the foreign particles are present in the product to be tested, the material of the foreign particles is identified based on the frequency band characteristics, the signal-to-noise ratio, the peak amplitude, and the duration, and the material identification result is output. The material includes metallic and non-metallic materials.

[0006] In one optional approach, detecting the presence of foreign particles in the product to be detected based on the frequency band characteristics and the duration of the frequency band characteristics includes: Within a preset number of consecutive periods, analyze whether the same frequency band characteristics appear in each period, and analyze whether the frequency band characteristics in each period are all within a preset first frequency band range or are all within a second frequency band range. If the same frequency band feature appears in each cycle, and the frequency band feature in each cycle is either within a preset first frequency band range or within a second frequency band range, then it is determined that there are foreign particles in the product to be detected, and the frequency of the first frequency band range is greater than the frequency of the second frequency band range.

[0007] In one alternative approach, the first frequency band ranges from 19.2kHz to 21.4kHz, or from 29.4kHz to 32.1kHz, and the second frequency band ranges from 5.4kHz to 6.0kHz.

[0008] In one optional approach, if the foreign particles are present in the product to be detected, the material of the foreign particles is identified based on the frequency band characteristics, the signal-to-noise ratio, the peak amplitude, and the duration, and a material identification result is output, including: If the foreign particles are present in the product to be tested, and the frequency band characteristics of each cycle are all within the first frequency band range, then within the continuous cycle, the signal-to-noise ratio corresponding to the frequency band characteristics of each cycle is analyzed to see if it is greater than or equal to a preset signal-to-noise ratio threshold, and whether the peak amplitude is greater than or equal to a preset first peak threshold. If the analysis results are both yes, then the material of the foreign particles is identified as metal. If the foreign particles are present in the product to be tested, and the frequency band characteristics of each cycle are all within the second frequency band range, then within the continuous cycle, the signal-to-noise ratio corresponding to the frequency band characteristics of each cycle is analyzed to see if it is greater than or equal to the signal-to-noise ratio threshold, and whether the peak amplitude is greater than or equal to the preset second peak threshold. If the analysis results are both yes, then the material of the foreign particles is identified as non-metallic, and the second peak threshold is greater than the first peak threshold.

[0009] In one optional approach, if the foreign particles are present in the product to be detected, the material of the foreign particles is identified based on the frequency band characteristics, the signal-to-noise ratio, the peak amplitude, and the duration, and a material identification result is output, further including: If the foreign particles are present in the product to be tested, and the frequency band characteristics of each cycle are all within the second frequency band range, and within the continuous cycle, the signal-to-noise ratio corresponding to the frequency band characteristics of each cycle is greater than or equal to the signal-to-noise ratio threshold, and the peak amplitude is greater than or equal to the preset second peak threshold, then it is analyzed whether the frequency band characteristics of each cycle are all within the third frequency band range, where the third frequency band range is 5.6kHz-5.8kHz; If the frequency band characteristics of each cycle are all within the third frequency band range, then the material of the foreign object particle is identified as plastic.

[0010] In one optional approach, the continuous period is N, where N is an integer greater than or equal to 3. If the foreign matter particle is present in the product to be detected, the material of the foreign matter particle is identified based on the frequency band characteristics, the signal-to-noise ratio, the peak amplitude, and the duration, and a material identification result is output. This further includes: If the foreign particles are present in the product to be tested, and the frequency band characteristics of each period are within the range of the second frequency band, then within the first M periods of the continuous period N, it is analyzed whether the peak amplitude corresponding to the frequency band characteristics of each period is greater than or equal to k times the second peak threshold. If so, the material of the foreign particles is identified as non-metallic, where M is an integer less than N and k is an integer greater than 2.

[0011] In one alternative approach, the acoustic sensors include multiple sensors, and the acoustic signals acquired by each acoustic sensor are processed through a separate channel to obtain the corresponding spectral signals. In the analysis of the spectral signals of multiple channels, the first peak threshold, the second peak threshold, and the signal-to-noise ratio threshold corresponding to each channel are dynamically calculated according to a preset AI module.

[0012] In an alternative approach, the method further includes: Acquire sample data for each of the acoustic sensors, wherein the sample data includes at least peak amplitude, average amplitude, signal-to-noise ratio, fluctuation, and material identification results of foreign particles; The sample data and predetermined threshold algorithm corresponding to each acoustic sensor are stored in a preset database; The AI ​​agent module calls the pre-deployed AI module, which then executes the threshold algorithm on the sample data in the database. Based on the preset confidence level, the first peak threshold, the second peak threshold, and the signal-to-noise ratio threshold for each channel are calculated.

[0013] According to another aspect of the present invention, a computer device is provided, comprising: a processor, a memory, a communication interface, and a communication bus, wherein the processor, the memory, and the communication interface communicate with each other via the communication bus; the memory is used to store at least one executable instruction, wherein the executable instruction causes the processor to perform the method described above.

[0014] According to another aspect of the present invention, a computer-readable storage medium is provided, the storage medium storing at least one executable instruction, which, when executed on a computer device, causes the computer device to perform the method described above.

[0015] This invention first detects the presence of foreign particles in the product under test by using frequency band characteristics and the duration of those characteristics. If foreign particles are present, the signal-to-noise ratio and peak amplitude are combined to jointly determine the material of the foreign particles, achieving efficient and high-precision material identification of both metallic and non-metallic foreign particles. In particular, the identification accuracy of lightweight non-metallic foreign particles is significantly improved, with an overall material identification accuracy of over 95%. Moreover, it does not require damaging the product packaging, enabling non-destructive detection of foreign particles and material identification.

[0016] The above description is merely an overview of the technical solutions of the embodiments of the present invention. In order to better understand the technical means of the embodiments of the present invention and to implement them in accordance with the contents of the specification, and to make the above and other objects, features and advantages of the embodiments of the present invention more apparent and understandable, specific embodiments of the present invention are described below. Attached Figure Description

[0017] The accompanying drawings are for illustrative purposes only and are not intended to limit the invention. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings: Figure 1 This diagram illustrates the usage environment of the foreign particle material identification device provided in an embodiment of the present invention. Figure 2 A flowchart illustrating the foreign particle material identification method provided in an embodiment of the present invention is shown. Figure 3 A schematic diagram illustrating the identification of foreign particles as being made of metal according to an embodiment of the present invention is shown; Figure 4A schematic diagram illustrating the identification of non-metallic foreign particles according to an embodiment of the present invention is shown; Figure 5 A schematic diagram of the structure of the foreign particle material identification device provided in an embodiment of the present invention is shown; Figure 6 A schematic diagram of the structure of a computer device provided in an embodiment of the present invention is shown. Detailed Implementation

[0018] Exemplary embodiments of the invention will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the invention are shown in the drawings, it should be understood that the invention can be implemented in various forms and should not be limited to the embodiments set forth herein.

[0019] Figure 1 A schematic diagram of the usage environment of the foreign matter particle material identification device provided in an embodiment of the present invention is shown. This foreign matter particle material identification device performs the following foreign matter particle material identification method. Figure 1 As shown, the product under test is excited to generate mechanical vibration. This mechanical vibration causes excess foreign particles within the product to displace. This displacement is a random combination of sliding and impacting of the foreign particles relative to the product shell. During this process, stress elastic waves and sound waves are generated. These two waves propagate within the product shell and form a reverberant signal. Preferably, the product under test is excited by broadband mechanical vibration. The broadband frequency range can be 5Hz-500Hz, within which the frequency continuously changes. The product under test follows the vibration. Broadband mechanical vibration can effectively excite foreign particles of different masses and materials within the product, causing them to displace.

[0020] One or more acoustic sensors are disposed on the product to be tested. If multiple acoustic sensors are disposed at different locations on the product, they can collect acoustic signals at different locations during the mechanical vibration generated by the product. The acoustic sensors can be piezoelectric particle acoustic sensors to achieve acoustic-to-electric conversion. In one embodiment, the acoustic sensor is disposed at the bottom of the product to effectively collect the acoustic signal. When foreign particles are present inside the product, the particles are excited and generate a reverberation signal. This reverberation signal is transmitted to the acoustic sensor through the product structure. The acoustic sensor collects the acoustic signal formed by the ambient noise and the reverberation signal. When there are no foreign particles inside the product, the acoustic sensor collects the acoustic signal of only ambient noise. The acoustic sensor transmits the acoustic signal to the foreign particle material identification device.

[0021] The foreign particle material identification device processes acoustic signals to obtain spectral data. By analyzing the spectral data, it can detect whether there are foreign particles inside the product under test and identify the material of the foreign particles.

[0022] This invention can be used for non-destructive testing and material classification of foreign particles inside products in fields such as aviation, aerospace, military, communications, and new energy vehicles, including integrated circuits, transistors, capacitors, and other high-end equipment manufacturing equipment. Specifically, this invention can also be used for foreign particle detection and material classification of packaged products, aiming to detect the material of free foreign particles present within the device's packaging cavity, thereby improving product quality and reliability.

[0023] Figure 2 A flowchart of the foreign particle material identification method according to an embodiment of the present invention is shown, such as... Figure 2 As shown, the method includes the following steps: Step 10: Obtain the spectral signal corresponding to the acoustic signal of at least one acoustic sensor. The acoustic sensor is installed on the product to be tested. During the process of the product to be tested being excited to generate mechanical vibration, the acoustic sensor collects the acoustic signal.

[0024] One or more acoustic sensors can be set, corresponding to one or more acoustic signals acquired. By performing signal processing operations such as filtering, amplification, and wavelet transform on the acoustic signals, a clear spectral signal is obtained.

[0025] Step 20: Analyze the spectrum signal to obtain the frequency band characteristics of the spectrum signal excluding the frequency band of environmental noise, the signal-to-noise ratio, peak amplitude and duration of the frequency band characteristics.

[0026] The spectral signal is analyzed to obtain frequency band characteristics, which are those excluding the frequency band of ambient noise. In the foreign matter particle material identification environment of this embodiment, ambient noise serves as the sound benchmark. Other sounds besides ambient noise may be the sounds generated by the excitation of foreign matter particles inside the product to be detected. In this embodiment, ambient noise can be considered as the sound of mechanical vibration. In one implementation, the frequency band corresponding to the ambient noise is between 7.0kHz and 7.8kHz. After removing the frequency band characteristics of ambient noise, the remaining frequency band characteristics are included in the analysis to detect foreign matter particles and identify the material.

[0027] Step 30: Detect whether there are foreign particles in the product to be tested based on the frequency band characteristics and the duration of the frequency band characteristics.

[0028] This embodiment is based on broadband vibration excitation of the product under test, which can effectively excite foreign particles of different masses and materials in the product to continuously displace and / or collide and produce sound. If these frequency band characteristics exist and the frequency band characteristics appear continuously and stably, rather than suddenly, they can be considered as the frequency band characteristics corresponding to the displacement and / or vibration of foreign particles in the product under test, thereby determining that there are foreign particles in the product under test.

[0029] Further, detecting the presence of foreign particles in the product under test based on the frequency band characteristics and the duration of the frequency band characteristics includes: Within a preset number of consecutive periods, analyze whether the same frequency band characteristics appear in each period, and analyze whether the frequency band characteristics in each period are all within a preset first frequency band range or are all within a second frequency band range. If the same frequency band feature appears in each cycle, and the frequency band feature in each cycle is either within a preset first frequency band range or within a second frequency band range, then it is determined that there are foreign particles in the product to be detected, and the frequency of the first frequency band range is greater than the frequency of the second frequency band range.

[0030] Preferably, the first frequency band is a high-frequency band of 19.2kHz-21.4kHz or 29.4kHz-32.1kHz, and the second frequency band is a low-frequency band of 5.4kHz-6.0kHz. The frequency bands corresponding to the sounds produced when foreign particles of different masses and materials in the product under test are excited fall within the aforementioned first frequency band range or second frequency band range.

[0031] This embodiment determines whether there are foreign particles in the product under test by detecting the consistency of multi-periodic frequency band features. This detection of the consistency of multi-periodic frequency band features can effectively reduce the false judgment rate.

[0032] Step 40: If the foreign particles are present in the product to be tested, the material of the foreign particles is identified based on the frequency band characteristics, the signal-to-noise ratio, the peak amplitude, and the duration, and the material identification result is output. The material includes metallic and non-metallic materials.

[0033] If foreign particles are present in the product under test, the material of the foreign particles is further identified based on frequency band characteristics, signal-to-noise ratio, peak amplitude, and duration. Specifically, the sound produced when metallic foreign particles are excited generally corresponds to the high-frequency band, while the sound produced when non-metallic foreign particles are excited generally corresponds to the low-frequency band. These factors, combined with signal-to-noise ratio, peak amplitude, and duration, ensure accurate material identification.

[0034] like Figure 3 As shown, acoustic signals were collected using four acoustic sensors, corresponding to channels CH1, CH2, CH3, and CH4. Analysis revealed the presence of foreign particles in the product under test. Based on frequency band characteristics, signal-to-noise ratio, peak amplitude, and duration, the material of the foreign particles was identified as non-metallic. Similarly, as... Figure 4 As shown, the material of the foreign particles is identified as metal based on frequency band characteristics, signal-to-noise ratio, peak amplitude, and duration.

[0035] Furthermore, if the foreign particles are present in the product to be tested, the material of the foreign particles is identified based on the frequency band characteristics, the signal-to-noise ratio, the peak amplitude, and the duration, and a material identification result is output, including: If the foreign particles are present in the product to be tested, and the frequency band characteristics of each cycle are all within the first frequency band range, then within the continuous cycle, the signal-to-noise ratio corresponding to the frequency band characteristics of each cycle is analyzed to see if it is greater than or equal to a preset signal-to-noise ratio threshold, and whether the peak amplitude is greater than or equal to a preset first peak threshold. If the analysis results are both yes, then the material of the foreign particles is identified as metal. If the foreign particles are present in the product to be tested, and the frequency band characteristics of each cycle are all within the second frequency band range, then within the continuous cycle, the signal-to-noise ratio corresponding to the frequency band characteristics of each cycle is analyzed to see if it is greater than or equal to the signal-to-noise ratio threshold, and whether the peak amplitude is greater than or equal to the preset second peak threshold. If the analysis results are both yes, then the material of the foreign particles is identified as non-metallic, and the second peak threshold is greater than the first peak threshold.

[0036] Signal-to-noise ratio (SNR) is an indicator that measures the strength of an effective signal relative to the level of environmental noise fluctuation. It is used to accurately distinguish between the real signal and noise signal from foreign particles, and to determine that the real signal is not caused by environmental noise, but is non-accidental noise generated by the foreign particles. This embodiment distinguishes between metallic and non-metallic materials based on parameters such as frequency band characteristics, SNR, peak amplitude, and duration. The extraction and analysis of these subtle parameters must be based on the premise that the signal from the foreign particles themselves is real and reliable. If the SNR is too low, noise may severely distort or obscure these key features. For example, noise may cause misidentification of peak frequencies or make a weak non-metallic signal appear as a metallic signal. Only when the SNR is high enough can the signal features used for subsequent material analysis be guaranteed to be real, reliable, effective, or representative.

[0037] In this embodiment, the peak amplitude of metallic foreign particles is relatively small, while the peak amplitude of non-metallic foreign particles is correspondingly larger. Preferably, the first peak threshold can be set between 10mV and 15mV, and the second peak threshold can be set between 35mV and 60mV.

[0038] In one embodiment, if the foreign particles are present in the product to be tested, the material of the foreign particles is identified based on the frequency band characteristics, the signal-to-noise ratio, the peak amplitude, and the duration, and a material identification result is output. This further includes: If the foreign particles are present in the product to be tested, and the frequency band characteristics of each cycle are all within the second frequency band range, and within the continuous cycle, the signal-to-noise ratio corresponding to the frequency band characteristics of each cycle is greater than or equal to the signal-to-noise ratio threshold, and the peak amplitude is greater than or equal to the preset second peak threshold, then it is analyzed whether the frequency band characteristics of each cycle are all within the third frequency band range, where the third frequency band range is 5.6kHz-5.8kHz; If the frequency band characteristics of each cycle are all within the third frequency band range, then the material of the foreign object particle is identified as plastic.

[0039] In this embodiment, after identifying the foreign object particle as a non-metallic material, it is further possible to identify whether the non-metallic foreign object particle is plastic or not. Due to the specific characteristics of plastic material, its corresponding frequency band is the aforementioned third frequency band range of 5.6kHz-5.8kHz. After identifying the foreign object particle as a non-metallic material, this frequency band feature can be further enhanced for detection. If it is found that the frequency band feature of each cycle is within the 5.6kHz-5.8kHz range, then it can be determined that the material of the foreign object particle is plastic.

[0040] In one embodiment, the continuous period is N, where N is an integer greater than or equal to 3. If the foreign matter particle is present in the product to be detected, the material of the foreign matter particle is identified based on the frequency band characteristics, the signal-to-noise ratio, the peak amplitude, and the duration, and a material identification result is output. This further includes: If the foreign particles are present in the product to be tested, and the frequency band characteristics of each period are within the range of the second frequency band, then within the first M periods of the continuous period N, it is analyzed whether the peak amplitude corresponding to the frequency band characteristics of each period is greater than or equal to k times the second peak threshold. If so, the material of the foreign particles is identified as non-metallic, where M is an integer less than N and k is an integer greater than 2.

[0041] In this embodiment, after determining that there are foreign particles in the product to be tested, and that the frequency band characteristics of each cycle are within the second frequency band range, it is possible to directly determine whether the foreign particles are non-metallic by the peak amplitude in the first M cycles of the continuous period N. If the peak amplitude is significantly greater than the second peak threshold, that is, K times the second peak threshold, for example, 5 times the second peak threshold, then the material of the foreign particles is identified as non-metallic, and the foreign particles are large non-metallic particles. When such large non-metallic particles are excited, they can instantly generate a large signal with a significantly larger peak amplitude. This large signal can be used to directly identify them as large non-metallic particles.

[0042] This invention first detects the presence of foreign particles in the product under test by using frequency band characteristics and the duration of those characteristics. If foreign particles are present, the signal-to-noise ratio and peak amplitude are combined to jointly determine the material of the foreign particles, achieving efficient and high-precision material identification of both metallic and non-metallic foreign particles. In particular, the identification accuracy of lightweight non-metallic foreign particles is significantly improved, with an overall material identification accuracy of over 95%. Moreover, it does not require damaging the product packaging, enabling non-destructive detection of foreign particles and material identification.

[0043] In an optional embodiment, the acoustic sensors include multiple sensors. The acoustic signals acquired by each acoustic sensor are processed through a separate channel to obtain the corresponding spectral signal. In the analysis of the spectral signals of multiple channels, the first peak threshold, the second peak threshold, and the signal-to-noise ratio threshold corresponding to each channel are dynamically calculated according to a preset AI module. This consistency of multi-channel spectral signal analysis results can further improve the accuracy of foreign object particle material identification. At the same time, since the environmental noise level of different foreign object particle material identification environments is different, and the sensitivity of different acoustic sensors also has slight differences, and considering some products with high requirements for foreign object particle material identification, such as products in the aerospace field, it is necessary to dynamically and adaptively adjust the first peak threshold, the second peak threshold, and the signal-to-noise ratio threshold corresponding to each channel. The specific algorithm can be executed by the preset AI module, thereby further improving the accuracy of foreign object particle material identification, reducing the risk of false alarms, and helping to improve product quality.

[0044] Furthermore, methods for identifying the material composition of foreign particles also include: Acquire sample data for each of the acoustic sensors, wherein the sample data includes at least peak amplitude, average amplitude, signal-to-noise ratio, fluctuation, and material identification results of foreign particles; The sample data and predetermined threshold algorithm corresponding to each acoustic sensor are stored in a preset database; The AI ​​agent module calls the pre-deployed AI module, which then executes the threshold algorithm on the sample data in the database. Based on the preset confidence level, the first peak threshold, the second peak threshold, and the signal-to-noise ratio threshold for each channel are calculated.

[0045] In this embodiment, a sample dataset is first established for each acoustic sensor. Each time an object is detected, a data record is generated regardless of whether a foreign object is detected. A record is also generated based on the material identification result of the foreign object particle and stored in the database.

[0046] When the sample data accumulates to a certain amount (e.g., 5000 records), or when the confidence level of the material identification results continues to decline, the AI ​​agent module will invoke a pre-deployed AI module to automatically initiate the learning process. The AI ​​module can be a supervised learning model. It learns from the sample data, studying the complex, non-linear mapping between features such as peak amplitude, signal-to-noise ratio (SNR), and frequency, and the final material type. Next, the AI ​​module executes a thresholding algorithm. This algorithm doesn't simply aim to find an intermediate value, but rather to calculate a set of thresholds for each channel that achieves the highest recognition accuracy. The AI ​​module simulates using multiple different SNR thresholds, first peak thresholds, second peak thresholds, etc., to evaluate historical data and calculate the confidence level (e.g., material identification accuracy) for each set of thresholds. Finally, it selects the threshold combination with the highest confidence level as the new SNR threshold, first peak threshold, and second peak threshold for that channel.

[0047] The AI ​​module in this embodiment analyzes massive amounts of historical data to continuously summarize and discover the optimal threshold combinations for distinguishing particles of different materials. The threshold algorithm upgrades existing fixed threshold settings into a dynamic, intelligent, and adaptive decision-making system, which can greatly improve the accuracy and environmental adaptability of foreign particle material identification.

[0048] Figure 5 A schematic diagram of the structure of the foreign particle material identification device according to an embodiment of the present invention is shown. Figure 5 As shown, the device includes: The acquisition module 501 is used to acquire the spectrum signal corresponding to the acoustic signal of at least one acoustic sensor. The acoustic sensor is disposed on the product to be tested. During the process of the product to be tested being excited to generate mechanical vibration, the acoustic sensor acquires the acoustic signal. Analysis module 502 is used to analyze the spectrum signal and obtain the frequency band characteristics of the spectrum signal excluding the frequency band of environmental noise, the signal-to-noise ratio, peak amplitude and duration of the frequency band characteristics; The detection module 503 is used to detect whether there are foreign particles in the product to be detected based on the frequency band characteristics and the duration of the frequency band characteristics. The identification module 504 is used to identify the material of the foreign particles according to the frequency band characteristics, the signal-to-noise ratio, the peak amplitude and the duration if the foreign particles are present in the product to be detected, and output the material identification result, wherein the material includes metallic material and non-metallic material.

[0049] The embodiments of the foreign matter particle material identification device are basically the same as the embodiments of the foreign matter particle material identification method described above, and the embodiments described above can be referred to.

[0050] Figure 6 The diagram shows a structural schematic of an embodiment of the computer device of the present invention. The specific embodiments of the present invention do not limit the specific implementation of the computer device.

[0051] like Figure 6 As shown, the computer device may include: a processor 402, a communications interface 404, a memory 406, and a communications bus 408.

[0052] The processor 402, communication interface 404, and memory 406 communicate with each other via communication bus 408. Communication interface 404 is used to communicate with other computer devices, such as clients or other server network elements. The processor 402 executes program 410, specifically performing the relevant steps described above in the computer device embodiment.

[0053] Specifically, program 410 may include program code, which includes computer-executable instructions.

[0054] Processor 402 may be a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement embodiments of the present invention. The computer device includes one or more processors, which may be processors of the same type, such as one or more CPUs; or processors of different types, such as one or more CPUs and one or more ASICs.

[0055] Memory 406 is used to store program 410. Memory 406 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.

[0056] Specifically, program 410 can be called by processor 402 to cause the computer device to perform the following operations: Acquire the spectral signal corresponding to the acoustic signal of at least one acoustic sensor, wherein the acoustic sensor is disposed on the product to be tested, and the acoustic sensor acquires the acoustic signal during the process of the product to be tested being excited to generate mechanical vibration. The spectrum signal is analyzed to obtain the frequency band characteristics of the spectrum signal excluding the frequency band of environmental noise, the signal-to-noise ratio, peak amplitude and duration of the frequency band characteristics; The presence of foreign particles in the product under test is detected based on the frequency band characteristics and the duration of the frequency band characteristics. If the foreign particles are present in the product to be tested, the material of the foreign particles is identified based on the frequency band characteristics, the signal-to-noise ratio, the peak amplitude, and the duration, and the material identification result is output. The material includes metallic and non-metallic materials.

[0057] In one optional approach, detecting the presence of foreign particles in the product to be detected based on the frequency band characteristics and the duration of the frequency band characteristics includes: Within a preset number of consecutive periods, analyze whether the same frequency band characteristics appear in each period, and analyze whether the frequency band characteristics in each period are all within a preset first frequency band range or are all within a second frequency band range. If the same frequency band feature appears in each cycle, and the frequency band feature in each cycle is either within a preset first frequency band range or within a second frequency band range, then it is determined that there are foreign particles in the product to be detected, and the frequency of the first frequency band range is greater than the frequency of the second frequency band range.

[0058] In one alternative approach, the first frequency band ranges from 19.2kHz to 21.4kHz, or from 29.4kHz to 32.1kHz, and the second frequency band ranges from 5.4kHz to 6.0kHz.

[0059] In one optional approach, if the foreign particles are present in the product to be detected, the material of the foreign particles is identified based on the frequency band characteristics, the signal-to-noise ratio, the peak amplitude, and the duration, and a material identification result is output, including: If the foreign particles are present in the product to be tested, and the frequency band characteristics of each cycle are all within the first frequency band range, then within the continuous cycle, the signal-to-noise ratio corresponding to the frequency band characteristics of each cycle is analyzed to see if it is greater than or equal to a preset signal-to-noise ratio threshold, and whether the peak amplitude is greater than or equal to a preset first peak threshold. If the analysis results are both yes, then the material of the foreign particles is identified as metal. If the foreign particles are present in the product to be tested, and the frequency band characteristics of each cycle are all within the second frequency band range, then within the continuous cycle, the signal-to-noise ratio corresponding to the frequency band characteristics of each cycle is analyzed to see if it is greater than or equal to the signal-to-noise ratio threshold, and whether the peak amplitude is greater than or equal to the preset second peak threshold. If the analysis results are both yes, then the material of the foreign particles is identified as non-metallic, and the second peak threshold is greater than the first peak threshold.

[0060] In one optional approach, if the foreign particles are present in the product to be detected, the material of the foreign particles is identified based on the frequency band characteristics, the signal-to-noise ratio, the peak amplitude, and the duration, and a material identification result is output, further including: If the foreign particles are present in the product to be tested, and the frequency band characteristics of each cycle are all within the second frequency band range, and within the continuous cycle, the signal-to-noise ratio corresponding to the frequency band characteristics of each cycle is greater than or equal to the signal-to-noise ratio threshold, and the peak amplitude is greater than or equal to the preset second peak threshold, then it is analyzed whether the frequency band characteristics of each cycle are all within the third frequency band range, where the third frequency band range is 5.6kHz-5.8kHz; If the frequency band characteristics of each cycle are all within the third frequency band range, then the material of the foreign object particle is identified as plastic.

[0061] In one optional approach, the continuous period is N, where N is an integer greater than or equal to 3. If the foreign matter particle is present in the product to be detected, the material of the foreign matter particle is identified based on the frequency band characteristics, the signal-to-noise ratio, the peak amplitude, and the duration, and a material identification result is output. This further includes: If the foreign particles are present in the product to be tested, and the frequency band characteristics of each period are within the range of the second frequency band, then within the first M periods of the continuous period N, it is analyzed whether the peak amplitude corresponding to the frequency band characteristics of each period is greater than or equal to k times the second peak threshold. If so, the material of the foreign particles is identified as non-metallic, where M is an integer less than N and k is an integer greater than 2.

[0062] In one alternative approach, the acoustic sensors include multiple sensors, and the acoustic signals acquired by each acoustic sensor are processed through a separate channel to obtain the corresponding spectral signals. In the analysis of the spectral signals of multiple channels, the first peak threshold, the second peak threshold, and the signal-to-noise ratio threshold corresponding to each channel are dynamically calculated according to a preset AI module.

[0063] In an alternative approach, the method further includes: Acquire sample data for each of the acoustic sensors, wherein the sample data includes at least peak amplitude, average amplitude, signal-to-noise ratio, fluctuation, and material identification results of foreign particles; The sample data and predetermined threshold algorithm corresponding to each acoustic sensor are stored in a preset database; The AI ​​agent module calls the pre-deployed AI module, which then executes the threshold algorithm on the sample data in the database. Based on the preset confidence level, the first peak threshold, the second peak threshold, and the signal-to-noise ratio threshold for each channel are calculated.

[0064] This invention provides a computer-readable storage medium storing at least one executable instruction that, when executed on a computer device, causes the computer device to perform any of the above-described method embodiments.

[0065] This invention provides a computer program that can be invoked by a processor to cause a computer device to execute any of the above-described method embodiments.

[0066] This invention provides a computer program product, which includes a computer program stored on a computer-readable storage medium. The computer program includes program instructions that, when executed on a computer, cause the computer to perform any of the above-described method embodiments.

[0067] The algorithms or displays provided herein are not inherently related to any particular computer, virtual system, or other device. Various general-purpose systems can also be used in conjunction with the teachings herein. The required structure for constructing such systems is apparent from the above description. Furthermore, the embodiments of the present invention are not directed to any particular programming language. It should be understood that the content of the invention described herein can be implemented using various programming languages, and the above description of specific languages ​​is for the purpose of disclosing the best mode of implementation of the invention.

[0068] Numerous specific details are set forth in the specification provided herein. However, it will be understood that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures, and techniques have not been shown in detail so as not to obscure the understanding of this specification.

[0069] Similarly, it should be understood that, in order to streamline the invention and aid in understanding one or more of the various aspects of the invention, features of the embodiments of the invention are sometimes grouped together in a single embodiment, figure, or description thereof in the above description of exemplary embodiments of the invention. However, this disclosure should not be construed as reflecting an intention that the claimed invention requires more features than are expressly recited in each claim.

[0070] Those skilled in the art will understand that modules in the computer device of the embodiments can be adaptively modified and placed in one or more computer devices different from that embodiment. Modules, units, or components in the embodiments can be combined into a single module, unit, or component, and can be divided into multiple sub-modules, sub-units, or sub-components. Except where at least some of such features and / or processes or units are mutually exclusive, any combination can be used to combine all features disclosed in this specification (including the accompanying claims, abstract, and drawings) and all processes or units of any method or computer device so disclosed. Unless expressly stated otherwise, each feature disclosed in this specification (including the accompanying claims, abstract, and drawings) may be replaced by an alternative feature that serves the same, equivalent, or similar purpose.

[0071] It should be noted that the above embodiments are illustrative of the invention and not restrictive, and that those skilled in the art can devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses should not be construed as limiting the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention can be implemented by means of hardware comprising several different elements and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by the same item of hardware. The use of the words first, second, and third, etc., does not indicate any order. These words can be interpreted as names. The steps in the above embodiments, unless otherwise specified, should not be construed as limiting the order of execution.

Claims

1. A foreign particle material identification method characterized by comprising: The method comprises: obtaining a spectrum signal corresponding to an acoustic signal of at least one acoustic sensor arranged on a product to be detected, the acoustic sensor collecting the acoustic signal during a process in which the product to be detected is excited to generate mechanical vibration; analyzing the spectrum signal to obtain a frequency band feature of the spectrum signal except for an environmental noise frequency band, a signal-to-noise ratio of the frequency band feature, a peak amplitude, and a duration; detecting whether a foreign particle exists in the product to be detected according to the frequency band feature and the duration of the frequency band feature; if the foreign particle exists in the product to be detected, identifying a material of the foreign particle according to the frequency band feature, the signal-to-noise ratio, the peak amplitude, and the duration, and outputting a material identification result, the material including a metal material and a non-metal material.

2. The method of claim 1, wherein the detection of whether the foreign particle exists in the product to be detected according to the frequency band feature and the duration of the frequency band feature comprises: analyzing, in a preset number of consecutive periods, whether the same frequency band feature appears in each period and whether the frequency band feature in each period is a frequency band feature in a preset first frequency band range or a frequency band feature in a second frequency band range; if the same frequency band feature appears in each period and the frequency band feature in each period is a frequency band feature in the preset first frequency band range or a frequency band feature in the second frequency band range, it is determined that the foreign particle exists in the product to be detected, and a frequency of the first frequency band range is greater than a frequency of the second frequency band range.

3. The method of claim 2, wherein, The first frequency band range is 19.2 kHz-21.4 kHz or 29.4 kHz-32.1 kHz, and the second frequency band range is 5.4 kHz-6.0 kHz.

4. The method of claim 3, wherein, if the foreign particle exists in the product to be detected, the identification of the material of the foreign particle according to the frequency band feature, the signal-to-noise ratio, the peak amplitude, and the duration, and the output of the material identification result, comprises: if the foreign particle exists in the product to be detected and the frequency band feature in each period is a frequency band feature in the first frequency band range, in the consecutive periods, it is analyzed whether a signal-to-noise ratio corresponding to the frequency band feature in each period is greater than or equal to a preset signal-to-noise ratio threshold value and whether the peak amplitude is greater than or equal to a preset first peak threshold value, and if the analysis results are both yes, it is identified that the material of the foreign particle is metal; if the foreign particle exists in the product to be detected and the frequency band feature in each period is a frequency band feature in the second frequency band range, in the consecutive periods, it is analyzed whether a signal-to-noise ratio corresponding to the frequency band feature in each period is greater than or equal to the signal-to-noise ratio threshold value and whether the peak amplitude is greater than or equal to a preset second peak threshold value, and if the analysis results are both yes, it is identified that the material of the foreign particle is non-metal, and the second peak threshold value is greater than the first peak threshold value.

5. The method of claim 4, wherein, The material of the foreign particle is identified according to the frequency band feature, the signal-to-noise ratio, the peak amplitude and the duration if the foreign particle exists in the product to be detected, and a material identification result is output. If the foreign particle exists in the product to be detected, the frequency band feature of each period is in the second frequency band range, and in the continuous period, the signal-to-noise ratio corresponding to the frequency band feature of each period is greater than or equal to the signal-to-noise ratio threshold value, and the peak amplitude is greater than or equal to the preset second peak threshold value, then whether the frequency band feature of each period is in the third frequency band range is analyzed, and the third frequency band range is 5.6 kHz-5.8 kHz. If the frequency band feature of each period is in the third frequency band range, the material of the foreign particle is plastic.

6. The method of claim 4, wherein, The continuous period is N, N is an integer greater than or equal to 3, and the material of the foreign particle is identified according to the frequency band feature, the signal-to-noise ratio, the peak amplitude and the duration if the foreign particle exists in the product to be detected, and a material identification result is output. If the foreign particle exists in the product to be detected, the frequency band feature of each period is in the second frequency band range, and in the continuous period, the signal-to-noise ratio corresponding to the frequency band feature of each period is greater than or equal to the signal-to-noise ratio threshold value, and the peak amplitude is greater than or equal to the preset second peak threshold value, then whether the frequency band feature of each period is in the third frequency band range is analyzed, and the third frequency band range is 5.6 kHz-5.8 kHz.

7. The method according to any one of claims 1 to 6, characterized in that, The acoustic sensors include a plurality of, the acoustic signals collected by each acoustic sensor are processed through a separate channel to obtain the corresponding frequency spectrum signal, and in the analysis of the frequency spectrum signals of multiple channels, the first peak threshold value, the second peak threshold value and the signal-to-noise ratio threshold value corresponding to each channel are dynamically calculated according to a preset AI module.

8. The method of claim 7, wherein, The method further comprises: Obtaining sample data corresponding to each acoustic sensor, the sample data at least including peak amplitude, amplitude average, signal-to-noise ratio, fluctuation degree and material identification result of foreign particle; Storing the sample data corresponding to each acoustic sensor and the predetermined threshold algorithm in a preset database; Based on the preset AI agent module, the AI module deployed in advance is called, the threshold algorithm is executed on the sample data in the database through the AI module, and the first peak threshold value, the second peak threshold value and the signal-to-noise ratio threshold value corresponding to each channel are calculated based on the preset confidence.

9. A computer device, comprising: Comprise: A processor, a memory, a communication interface and a communication bus, the processor, the memory and the communication interface complete the communication among each other through the communication bus; The memory is used to store at least one executable instruction, and the executable instruction makes the processor execute the method in any one of claims 1-8.

10. A computer-readable storage medium, characterized in that, The storage medium has at least one executable instruction stored therein, and the executable instruction, when executed on the computer device, causes the computer device to perform the method according to any one of claims 1-8.

Images