Method and apparatus for automatic measurement of material dimensions

Abstract

The application discloses a material size automatic measurement method and device, comprising: predicting product material sound wave reflection signal receiving effect as optimal sound wave emission parameters, obtaining sound wave reflection signal and corresponding timestamp information; identifying sound wave reflection source type of sound wave reflection signal, determining sound wave reflection source as frequency spectrum characteristics of product material sound wave reflection signal; identifying reasons for deviation of product material sound wave reflection signal; calculating non-homogeneous material non-homogeneous coefficient, correcting sound wave signal propagation speed in current non-homogeneous material, determining thickness size of single-layer product material and multi-layer combined material; evaluating whether production stability requirements have been reached after adjusting process parameters and production parameters. The application discloses a material size automatic measurement method and device, which enhances the intelligentization and automation level of product material detection, and meets the demand for high-precision, non-destructive detection and high-efficiency production.

Description

Technical Field

[0001] This invention relates to the field of automated measurement technology, and in particular to an automatic material size measurement method and apparatus. Background Technology

[0002] With the continuous improvement of automation in industrial manufacturing, the requirements for the precision and efficiency of product quality control are also increasing. In modern production, especially in the production and monitoring of high-precision parts, how to achieve rapid and accurate measurement of material dimensions and thickness has become a key issue. Traditional measurement methods mostly rely on contact tools, such as calipers and micrometers. These contact measurement methods are not only time-consuming but also susceptible to human error and environmental factors, making it difficult to meet the requirements of high efficiency and high precision. Currently, ultrasonic measurement technology, as a non-contact measurement method, has shown great application potential in material thickness measurement, quality inspection, and defect identification. Ultrasonic waves measure by utilizing the propagation characteristics of sound waves in materials, effectively avoiding the friction and damage caused by contact methods. However, existing ultrasonic measurement technologies still face some technical difficulties and challenges in practical applications. First, environmental factors have a significant impact on ultrasonic signals. The propagation of ultrasonic signals is affected by environmental conditions such as temperature, humidity, and air pressure, which can cause drift in signal frequency and amplitude, thus affecting the accuracy of measurement results. For example, the acoustic properties of materials may change under high or low temperature conditions, leading to variations in the propagation speed and reflection characteristics of ultrasonic signals. This makes it difficult for traditional ultrasonic measurement methods to guarantee consistency and reliability under different environments. Secondly, in existing thickness measurements of heterogeneous materials, such as composites containing different minerals, fibers, or particles, local density variations cause nonlinear changes in the sound wave propagation path, resulting in measurement errors. Different regions of heterogeneous materials, such as regions with higher or lower densities, cause sound waves to travel at different speeds during propagation, making the sound wave propagation path no longer a simple linear function. Traditional sound wave propagation models assume material homogeneity, but in practical applications, especially with complex heterogeneous materials, these assumptions often do not hold, making accurate measurement extremely difficult. In summary, existing ultrasonic measurement technologies have many problems in terms of accuracy, adaptability, environmental interference suppression, and measurement of multilayer composite materials, limiting their application in high-precision automated production lines and testing lines. How to solve these technical challenges and improve the adaptability of ultrasonic measurement technology in various complex environments has become a key issue urgently needing to be addressed in the current industrial measurement field. Summary of the Invention

[0003] To address the problems existing in the prior art, the present invention provides an automatic material size measurement method and apparatus.

[0004] A first aspect of the present invention provides an automatic material dimension measurement method, mainly comprising:

[0005] Based on the product materials and acoustic emission parameters of different specifications and standards, as well as the corresponding acoustic reflection signal reception effect, predict the acoustic emission parameters that are optimal for the acoustic reflection signal reception effect of the current product material, emit ultrasonic signals and acquire acoustic reflection signals and corresponding timestamp information.

[0006] The sound wave reflection signal is separated by an independent component analysis algorithm, and the type of sound wave reflection source is identified. The spectral characteristics of the sound wave reflection signal whose sound wave reflection source is the product material are determined.

[0007] Based on the spectral characteristics of the corrected acoustic wave reflection signal of the product material and the spectral characteristics of the reference acoustic wave reflection signal of the product material specification standard, the reasons for the deviation of the acoustic wave reflection signal of the product material are identified, and the process parameters of the production equipment are adjusted.

[0008] By comparing the acoustic wave reflection signals of the heterogeneous material with those of a known homogeneous reference sample, the heterogeneity coefficient of the heterogeneous material is determined, the propagation speed of the acoustic wave signal in the current heterogeneous material is corrected, and the thickness dimensions of single-layer product materials and multi-layer composite materials are calculated.

[0009] By using ultrasonic sensors to acquire the acoustic wave reflection signals of the product material after adjusting the process and production parameters, it can be determined whether the adjustment has met the production stability requirements, and the process and production parameters can be continuously adjusted.

[0010] Furthermore, the step of predicting the optimal acoustic wave emission parameters for the current product material based on different specifications of product materials and acoustic wave emission parameters, as well as the corresponding acoustic wave reflection signal reception effect, and then emitting ultrasonic signals and acquiring acoustic wave reflection signals and corresponding timestamp information includes:

[0011] An ultrasonic sensor is used to detect and receive ultrasonic signals from product materials of different specifications and standards. The ultrasonic wave emission parameters of the sensor are recorded, and the reception effect of the reflected sound signal is labeled. The specifications and standards include material type, size, thickness, number of layers, and density. The ultrasonic wave emission parameters include emission frequency, pulse width, and emission power. The reception effect is categorized as excellent, good, and poor. Based on the product materials of different specifications and standards, the ultrasonic wave emission parameters, and the corresponding reception effect of the reflected sound signal, a recurrent neural network is used to train a model to construct an ultrasonic wave emission parameter prediction model. This model determines the ultrasonic wave emission parameters that result in excellent reception of the reflected sound signal for the current product material, and sets the ultrasonic wave emission parameters for the ultrasonic sensor. According to the layout of the detection line, the position of the ultrasonic sensor is adjusted, and the ultrasonic sensor is installed above the detection line. An image of the product material on the detection line is acquired by a camera above the detection line. If the product material is directly below the ultrasonic sensor, the ultrasonic sensor emits ultrasonic signals to the product material on the detection line according to the set ultrasonic wave emission parameters and receives the reflected sound signal and corresponding timestamp information.

[0012] Furthermore, the step of separating the acoustic wave reflection signal using an independent component analysis algorithm, identifying the acoustic wave reflection source type, and determining the spectral characteristics of the acoustic wave reflection signal whose acoustic wave reflection source is the product material includes:

[0013] Based on the received acoustic wave reflection signals, the acoustic wave reflection signals are separated using an independent component analysis algorithm to obtain acoustic wave reflection signals from different acoustic wave reflection sources. A short-time Fourier transform algorithm is used to convert the time-domain audio signals of the acoustic wave reflection signals into frequency-domain data, extracting the spectral features of the acoustic wave reflection signals and saving them to the acoustic wave reflection monitoring database. The spectral features include frequency, peak frequency, and amplitude. Using the acoustic wave reflection signal monitoring database, the spectral features of acoustic wave reflection signals from different acoustic wave reflection sources are obtained, and the acoustic wave reflection source types are labeled. A random forest algorithm is used for model training to construct an acoustic wave reflection source identification model, identifying the acoustic wave reflection source type of the acoustic wave reflection signal. The spectral features of acoustic wave reflection signals from product materials are determined. Environmental data is acquired, and based on this data, frequency drift and amplitude drift are calculated to correct the frequency and amplitude of the acoustic wave reflection signals. The corrected spectral features of acoustic wave reflection signals from different acoustic wave reflection sources are obtained and saved to the acoustic wave reflection signal monitoring database. The environmental data includes temperature, humidity, and air pressure.

[0014] It also includes calculating frequency and amplitude drift based on environmental data to correct the frequency and amplitude of the reflected sound wave signal, specifically including:

[0015] Temperature, humidity, and air pressure data within the detection line are acquired in real time using temperature sensors, humidity sensors, and air pressure sensors installed on the detection line. The frequency drift calculation formula is then used. The frequency drift Δf under the current detection environment is determined, and the amplitude drift ΔA is determined using the amplitude drift calculation formula ΔA=A1·(n1·sin(T)+n2·H-n3·log(P)), where T is temperature, H is humidity, P is air pressure, f1 and A1 are the frequency and amplitude values ​​measured under standard conditions, respectively, l1, l2, and l3 are the influence coefficients of the detection environment on the frequency, and n1, n2, and n3 are the influence coefficients of the detection environment on the amplitude, which are obtained by experimental fitting through historical data. Based on the spectral characteristics, frequency drift, and amplitude drift of the sound wave reflection signal, the frequency and amplitude of the sound wave reflection signal are corrected.

[0016] Furthermore, the step of identifying the cause of the deviation in the acoustic wave reflection signal of the product material based on the spectral characteristics of the corrected acoustic wave reflection signal and the spectral characteristics of the reference acoustic wave reflection signal of the product material specification standard, and adjusting the process parameters of the production equipment, includes:

[0017] By using a sound wave reflection signal monitoring database, the spectral characteristics of sound wave reflection signals from different sound wave reflection sources after correction are obtained. The similarity between the spectral characteristics of the obtained product material's sound wave reflection signal and the spectral characteristics of the reference sound wave reflection signal of the product material specification standard is calculated using the cosine similarity method. If the similarity is lower than a preset similarity threshold, based on the obtained spectral characteristics of the product material's sound wave reflection signal and indicating the reasons for the deviation, a random forest algorithm is used to train the model, constructing a sound wave reflection signal deviation cause identification model to identify the reasons for the deviation in the product material's sound wave reflection signal. The reasons for the deviation include, but are not limited to, product material density deviation and shape defects, with shape defects including, but not limited to, cracks and pits. Based on the reasons for the deviation in the sound wave reflection signal, the process parameters of the production equipment are adjusted, including, but not limited to, temperature, cooling rate, injection pressure of the injection molding machine, injection speed, and injection volume.

[0018] Further, the process of determining the heterogeneity coefficient of the heterogeneous material using the acoustic wave reflection signal of the heterogeneous material and the acoustic wave reflection signal of a known homogeneous reference sample, correcting the propagation speed of the acoustic wave signal in the current heterogeneous material, and calculating the thickness dimensions of single-layer product materials and multi-layer composite materials includes:

[0019] If the material with density deviation is a heterogeneous material, the acoustic reflection signal of the corrected heterogeneous material and the acoustic reflection signal of a known homogeneous reference sample are obtained through an acoustic reflection signal monitoring database. The time-domain audio signal of the acoustic reflection signal is converted into frequency-domain data using a short-time Fourier transform algorithm. Heterogeneous materials include, but are not limited to, foamed plastics, carbon fiber composites, and glass fiber composites. The heterogeneity coefficient formula is then used. Calculate the heterogeneity coefficient H of the heterogeneous material, where S t and S r These are the acoustic wave reflection signal spectra of the heterogeneous material under test and the acoustic wave reflection signal spectra of a known homogeneous reference sample, respectively, Cov(S) t ,S r ) is the spectrum S t and S r covariance, For the spectrum S t standard deviation For the spectrum S r The standard deviation is calculated. Based on the frequency domain data of the acoustic wave reflection signals of the heterogeneous material and the known homogeneous reference sample, the main frequency phase difference between the acoustic wave reflection signal spectrum of the heterogeneous material and the spectrum of the known homogeneous reference sample is extracted. Based on this main frequency phase difference, the magnitude of the density of the heterogeneous material and the density of the known homogeneous reference sample is determined, and the velocity correction direction factor D is calculated. If the density of the heterogeneous material is greater than the density of the known homogeneous reference sample, D is 1; if the density of the heterogeneous material is less than the density of the known homogeneous reference sample, D is -1. Based on the heterogeneity coefficient and the velocity correction direction factor, the velocity correction formula is used to correct the propagation speed v of the acoustic wave signal in the current heterogeneous material. a Where v0 is the propagation speed of the acoustic signal in a known homogeneous reference sample; the propagation time difference ΔT between the sensor and the upper and lower surfaces is calculated using the timestamp information of the received ultrasonic signal; and the thickness is calculated using the formula... The thickness h of the product material is determined, where v0 is the propagation speed of the acoustic signal in a known homogeneous reference sample. Based on the heterogeneity coefficient of the heterogeneous material, it is determined whether there are local density direction change regions in the heterogeneous material. Based on the local heterogeneity coefficient and velocity correction direction factor of the heterogeneous material, the local thickness of the heterogeneous material is calculated, and the total thickness of the heterogeneous material is determined. If the product material is a multi-layer composite material, the propagation time difference between the signal from the sensor to the upper and lower surfaces of each layer is calculated using the timestamp information of the received ultrasonic signal. The thickness of each layer of the multi-layer composite material is calculated using the thickness calculation formula. The dimensional deviation between the product material size and the preset size, as well as the thickness deviation between the product material size and the preset thickness size, are calculated. If the dimensional deviation is greater than the preset dimensional deviation threshold or the thickness deviation exceeds the preset thickness deviation threshold, the thickness of the product material is corrected by adjusting the production parameters in the production process. The generated parameters include the precision of the production equipment, the gap of the mold, and the molding temperature.

[0020] It also includes determining whether there are local density direction variation regions in the heterogeneous material based on the heterogeneity coefficient, calculating the local thickness of the heterogeneous material based on the local heterogeneity coefficient and velocity correction direction factor, and determining the total thickness of the heterogeneous material. Specifically, this includes:

[0021] If the heterogeneity coefficient of the heterogeneous material is greater than a preset threshold, it is determined that there is a local density direction change region in the heterogeneous material. The echo signal of the heterogeneous material is then segmented into time segments according to a preset number of segments, and the main frequency phase difference of each segment is determined. The heterogeneity coefficient of the local heterogeneity of the heterogeneous material corresponding to each segment is calculated using the heterogeneity coefficient formula. Based on the main frequency phase difference of each segment, the density of the local heterogeneity of the echo signal corresponding to each segment is compared with the density of a known homogeneous reference sample, and the velocity correction direction factor D of the local heterogeneity of the echo signal corresponding to each segment is determined. Based on the heterogeneity coefficient and velocity correction direction factor of the local heterogeneity of the echo signal corresponding to each segment, the propagation speed of the echo signal in each local heterogeneous material is corrected using the velocity correction formula. The thickness of the local heterogeneity of the heterogeneous material is determined using the thickness calculation formula, and the total thickness of the heterogeneous material is calculated based on the thickness of the local heterogeneity of the heterogeneous material.

[0022] Furthermore, the step of acquiring the acoustic wave reflection signal of the product material after adjusting the process and production parameters using an ultrasonic sensor, determining whether the adjustment has met the production stability requirements, and continuously adjusting the process and production parameters includes:

[0023] The ultrasonic sensor acquires the acoustic wave reflection signal of the product material after adjusting the process parameters and production parameters, obtaining the new acoustic wave reflection signal spectrum characteristics and corresponding timestamp information. Based on the obtained new acoustic wave reflection signal spectrum characteristics and corresponding timestamp information, it is determined whether there is a deviation in the acoustic wave reflection signal, and whether the thickness of the product material deviates from the preset thickness size beyond the preset deviation threshold, to determine whether the production stability requirements have been met after adjustment. If the production stability requirements have not been met, the process parameters and production parameters are adjusted again until the production stability requirements are met.

[0024] A second aspect of the present invention provides an automatic material size measuring device, mainly comprising:

[0025] A processor and a memory; the memory stores at least one instruction, which is executed by the processor to cause the device to perform an automatic material size measurement method provided in the first aspect embodiment.

[0026] The technical solutions provided by the embodiments of the present invention may include the following beneficial effects:

[0027] This invention provides an automatic material dimension measurement method and apparatus. By optimizing acoustic wave emission parameters and real-time correcting ultrasonic signals, this invention effectively improves measurement accuracy and reliability. By analyzing acoustic wave reflection signals from different materials and dynamically adjusting based on production environment data, this invention overcomes the environmental influences of traditional measurement methods, ensuring signal stability under varying temperature, humidity, and air pressure conditions. Furthermore, by real-time monitoring of production environment changes and adaptive correction, this invention effectively eliminates measurement errors caused by process fluctuations, maintaining high stability and accuracy during production. This invention also possesses excellent capabilities for detecting the dimensions of heterogeneous materials. By calculating the heterogeneity coefficient of the heterogeneous material, it corrects the propagation speed of the acoustic wave signal within the heterogeneous material and accurately calculates the thickness dimension of the heterogeneous material based on the acoustic wave propagation time difference. It can also accurately measure the thickness dimensions of single-layer and multi-layer composite materials. This function is particularly suitable for the automated inspection of composite materials and complex structures, significantly improving production efficiency and reducing human measurement errors. This invention not only improves the accuracy and adaptability of ultrasonic measurement systems but also enhances the intelligence and automation level of product material inspection on the testing line, meeting the demands of modern manufacturing for high-precision, non-destructive testing and high-efficiency production. Attached Figure Description

[0028] Figure 1 This is a flowchart of an automatic material dimension measurement method and apparatus according to the present invention;

[0029] Figure 2 This is a schematic diagram of an automatic material dimension measurement method and apparatus according to the present invention;

[0030] Figure 3 This is another schematic diagram of an automatic material size measurement method and apparatus according to the present invention. Detailed Implementation

[0031] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be described in detail below with reference to the accompanying drawings and specific embodiments.

[0032] like Figure 1-3 This embodiment of an automatic material dimension measurement method and device may specifically include:

[0033] Step S101: Based on the product materials and acoustic emission parameters of different specifications and standards, as well as the corresponding acoustic reflection signal reception effect, predict the acoustic emission parameters that are optimal for the acoustic reflection signal reception effect of the current product material, emit ultrasonic signals and acquire acoustic reflection signals and corresponding timestamp information.

[0034] An ultrasonic sensor is used to detect and receive ultrasonic signals from product materials of different specifications and standards. The ultrasonic wave emission parameters of the sensor are recorded, and the reception effect of the reflected sound signal is labeled. Specifications and standards include material type, size, thickness, number of layers, and density. Ultrasonic wave emission parameters include emission frequency, pulse width, and emission power. Reception effects are categorized as excellent, good, and poor. Based on the different specifications and standards of product materials, ultrasonic wave emission parameters, and corresponding reception effects, a recurrent neural network is used to train a model to construct an ultrasonic wave emission parameter prediction model. This model determines the ultrasonic wave emission parameters that result in excellent reception of the reflected sound signal for the current product material, and sets the ultrasonic wave emission parameters for the ultrasonic sensor. The ultrasonic sensor is positioned according to the detection line layout and installed above the detection line. An image of the product material on the detection line is captured by a camera above the line. If the product material is directly below the ultrasonic sensor, the sensor emits ultrasonic signals to the product material on the detection line according to the set ultrasonic wave emission parameters and receives the reflected sound signal and corresponding timestamp information.

[0035] For example, on a testing line in a manufacturing plant, if the product material is foam plastic board, and the product has different specifications, specifically, the testing line produces foam plastic boards in three specifications: polyurethane (300mm x 200mm, 10mm thickness, 0.3g / cm³ density, 1 layer); polyvinyl chloride (250mm x 200mm, 15mm thickness, 0.5g / cm³ density, 2 layers); and polyethylene (500mm x 400mm, 20mm thickness, 0.4g / cm³ density, 3 layers). To ensure product quality and testing effectiveness, ultrasonic sensors are used to detect the thickness of these products and record the corresponding sound wave reflection signal reception. The ultrasonic sensor's sound wave emission parameters include a transmission frequency set to 5MHz, a pulse width of 2 microseconds, and a transmission power of 30dB. During the experiment, the ultrasonic sensor received reflected signals from different product materials according to the aforementioned specifications and emission parameters, and its reception performance was marked. For the first specification of polyurethane material, the reflected signal reception performance was rated as excellent; for the second specification of polyvinyl chloride material, the reception performance was rated as good; and for the third specification of polyethylene material, the reception performance was rated as poor. Based on these markings and product material specifications, a recurrent neural network was used to train a model, constructing a sound wave emission parameter prediction model to predict the impact of sound wave emission parameters of different specification standard materials on the reflected signal reception performance. After model training, the optimal sound wave emission parameters suitable for the detection line were obtained: a transmission frequency of 5MHz, a pulse width of 2 microseconds, and a transmission power of 30dB, ensuring excellent reflected signal reception performance. According to the layout of the detection line, the ultrasonic sensor was calibrated and precisely installed above the detection line to ensure that it could correctly irradiate the foam plastic board being produced. According to the layout of the inspection line, adjust the position of the ultrasonic sensor and install it above the inspection line. The position of the product is monitored in real time by a camera installed on the inspection line. When the camera detects that the product material is directly below the ultrasonic sensor, the ultrasonic sensor will emit a signal according to the previously set sound wave emission parameters. The ultrasonic signal is reflected back through the product material, and the sound wave reflection signal and timestamp information received by the ultrasonic sensor are recorded.

[0036] Step S102: Separate the acoustic wave reflection signal using an independent component analysis algorithm, identify the acoustic wave reflection source type of the acoustic wave reflection signal, and determine the spectral characteristics of the acoustic wave reflection signal from the product material as the acoustic wave reflection source.

[0037] Based on the received acoustic wave reflection signals, the acoustic wave reflection signals are separated using an independent component analysis algorithm to obtain acoustic wave reflection signals from different acoustic wave reflection sources. A short-time Fourier transform algorithm is used to convert the time-domain audio signals of the acoustic wave reflection signals into frequency-domain data, extracting the spectral features of the acoustic wave reflection signals and saving them to the acoustic wave reflection monitoring database. The spectral features include frequency, peak frequency, and amplitude. Using the acoustic wave reflection signal monitoring database, the spectral features of acoustic wave reflection signals from different acoustic wave reflection sources are obtained, and the acoustic wave reflection source types are labeled. A random forest algorithm is used for model training to construct an acoustic wave reflection source identification model, identifying the acoustic wave reflection source types of the acoustic wave reflection signals. The spectral features of acoustic wave reflection signals from product materials are then determined. Environmental data, including temperature, humidity, and air pressure, are acquired. Based on this data, frequency and amplitude drift are calculated to correct the frequency and amplitude of the acoustic wave reflection signals, obtaining the corrected spectral features of acoustic wave reflection signals from different acoustic wave reflection sources, which are then saved to the acoustic wave reflection signal monitoring database.

[0038] For example, on a certain detection line, the size of the foam plastic board currently being produced is 500mm x 300mm, the thickness is 20mm, and the density is 0.4g / cm³. During the production process, sensors receive sound wave reflection signals from different sources: reflection signals from the foam plastic board, reflection signals from production equipment such as metal bodies or robotic arms, and reflection signals from workshop walls or other objects, and these are saved to a sound wave reflection monitoring database. To effectively analyze and process these signals, an independent component analysis algorithm is first used to separate the received mixed sound wave signals, thereby extracting the sound wave reflection signals from different reflection sources. Short-time Fourier transform is used to convert these sound wave reflection signals from the time domain to the frequency domain. By performing Fourier transform on each separated signal, its spectral characteristics such as frequency, peak frequency, and amplitude are extracted, resulting in three types of sound wave reflection signals: a frequency of 5MHz with a peak frequency of 5.2MHz and an amplitude of 0.8; and a frequency of 6MHz with a peak frequency of 6.1MHz and an amplitude of 1.0. The spectral characteristics of three types of acoustic wave reflection signals—with a frequency of 4.5 MHz, a peak frequency of 4.7 MHz, and an amplitude of 0.4—were saved to the acoustic wave reflection monitoring database. Using this database, the spectral characteristics of acoustic wave reflection signals from different sources were obtained, and the source types were labeled, including reflections from foam boards, metal bodies or robotic arms, workshop walls, or other objects. A random forest algorithm was used to train the model, constructing an acoustic wave reflection source identification model to identify the acoustic wave reflection source type. The spectral characteristics of the acoustic wave reflection signal from the product material were determined to be a frequency of 5 MHz, a peak frequency of 5.2 MHz, and an amplitude of 0.8. In the production environment, environmental factors such as temperature, humidity, and air pressure may affect the propagation of ultrasonic signals, causing frequency and amplitude drift. For example, the current production environment has a temperature of 25℃, humidity of 60%, and air pressure of 1010 hPa. Based on this production environment data, the frequency and amplitude drift of the signal can be calculated. Using a relevant environmental correction model, it was found that an increase in temperature causes a frequency drift of 0.2 MHz and an amplitude drift of 0.1 MHz. To ensure measurement accuracy, these drifts were calculated and applied to correct each acoustic wave reflection signal. The corrected frequency of the acoustic wave reflection signal from the product material became 4.8 MHz, and the amplitude became 0.7 MHz. Finally, these corrected spectral characteristics were saved to the acoustic wave reflection monitoring database, providing a basis for subsequent production quality control and parameter adjustment.

[0039] Among them, based on the detection environment data, the frequency drift and amplitude drift are calculated, and the frequency and amplitude of the sound wave reflection signal are corrected.

[0040] Temperature, humidity, and air pressure data within the detection line are acquired in real time using temperature sensors, humidity sensors, and air pressure sensors installed on the detection line. The frequency drift calculation formula is then used. The frequency drift Δf under the current detection environment is determined, and the amplitude drift ΔA is calculated using the formula ΔA = A1·(n1·sin(T) + n2·H - n3·log(P)), where T is temperature, H is humidity, P is air pressure, f1 and A1 are the frequency and amplitude values ​​measured under standard conditions, respectively, l1, l2, and l3 are the influence coefficients of the detection environment on the frequency, and n1, n2, and n3 are the influence coefficients of the detection environment on the amplitude. These coefficients are obtained through experimental fitting using historical data. Based on the spectral characteristics, frequency drift, and amplitude drift of the sound wave reflection signal, the frequency and amplitude of the sound wave reflection signal are corrected.

[0041] For example, within the detection line, temperature, humidity, and barometric pressure sensors monitor the detection environment in real time, obtaining current temperatures of 30°C, humidity of 65%, and barometric pressure of 1012 hPa. Based on these environmental data and historical experimental data, the frequency drift calculation formula is used. The frequency and amplitude drift under the current detection environment are determined using the formula ΔA = A1·(n1·sin(T) + n2·H - n3·log(P)). If, under standard conditions of 25℃ temperature (T), 50% humidity (H), and 1010 hPa pressure (P), the measured frequency is 5 MHz and the amplitude is 1.0, then, according to the experimental fitting results, the influence coefficients of the detection environment on the frequency are l1 = 0.002, on humidity is l2 = 0.1, and on air pressure is l3 = 0.01, while the coefficients for amplitude drift are n1 = 0.05, n2 = 0.01, and n3 = 0.02. According to the formula for calculating frequency drift, the calculated frequency drift is 0.3806MHz. According to the formula for calculating amplitude drift, the calculated amplitude drift is 0.6149. After obtaining the frequency drift and amplitude drift, the frequency and amplitude of the sound wave reflection signal can be corrected. If the original frequency of the sound wave reflection signal is 5MHz and the amplitude is 1.0, the corrected frequency and amplitude are 5.3806MHz and 1.6149, respectively, based on the above calculations.

[0042] Step S103: Based on the spectral characteristics of the corrected product material acoustic wave reflection signal and the spectral characteristics of the reference acoustic wave reflection signal of the product material specification standard, identify the cause of the deviation in the product material acoustic wave reflection signal, and adjust the process parameters of the production equipment.

[0043] By using a sound wave reflection signal monitoring database, the spectral characteristics of sound wave reflection signals from different sound wave reflection sources are acquired after correction. The similarity between the acquired spectral characteristics of the product material's sound wave reflection signal and the spectral characteristics of the reference sound wave reflection signal of the product material specification standard is calculated using the cosine similarity method. If the similarity is lower than a preset similarity threshold, based on the acquired spectral characteristics of the product material's sound wave reflection signal and indicating the reasons for the deviation, a random forest algorithm is used to train a model to construct a sound wave reflection signal deviation cause identification model. The reasons for the deviation include, but are not limited to, product material density deviation and shape defects, including, but not limited to, cracks, bubbles, and pits. Based on the reasons for the sound wave reflection signal deviation, the process parameters of the production equipment are adjusted, including but not limited to temperature, cooling rate, injection pressure, injection speed, and injection volume of the injection molding machine.

[0044] For example, in a foam board inspection line, the standard product specifications are: polyurethane material, 300mm x 200mm in size, 10mm in thickness, and 0.3g / cm³ in density. During production, ultrasonic sensors collect the spectral characteristics of the acoustic reflection signals of the product material in real time through an acoustic reflection signal monitoring database. After correction, the spectral characteristics of the acoustic reflection signals of the product material include: a frequency of 5MHz, a peak frequency of 5.2MHz, and an amplitude of 0.8. Using a cosine similarity calculation method, the spectral characteristics of the current product material are compared with the spectral characteristics of the benchmark standard, resulting in a similarity value of 0.85, while the preset similarity threshold is 0.9. Since the calculated similarity value is lower than the preset 0.9, it indicates that there is a certain deviation in the currently produced product. Based on the acquired spectral characteristics, analysis reveals that the main reason for the deviation is the unevenness of the product material surface, and this shape defect is confirmed by annotating the signal. To further analyze the causes of the deviation, historical data and the reasons for the acoustic wave reflection signal deviation were used to train a model using the random forest algorithm, constructing an identification model for the causes of acoustic wave reflection signal deviation. Based on the trained model, surface unevenness and possible material density deviations were identified as the main causes of acoustic wave reflection signal deviation. To address this issue, the process parameters of the detection line were adjusted. First, the temperature control was fine-tuned to ensure the mold temperature remained stable at 185℃. Second, the cooling rate was adjusted to 1.2℃ / min to ensure uniform mold cooling. Simultaneously, the injection pressure of the injection molding machine was increased from 90MPa to 95MPa, the injection speed was maintained at 18mm / s, and the injection volume was adjusted to 120g to better fill the mold and reduce the occurrence of surface defects.

[0045] Step S104: Determine the heterogeneity coefficient of the heterogeneous material by using the acoustic wave reflection signal of the heterogeneous material and the acoustic wave reflection signal of the known homogeneous reference sample, correct the propagation speed of the acoustic wave signal in the current heterogeneous material, and calculate the thickness dimensions of the single-layer product material and the multi-layer composite material.

[0046] If the material with density deviation is a heterogeneous material, the acoustic reflection signal of the corrected heterogeneous material and the acoustic reflection signal of a known homogeneous reference sample are obtained through an acoustic reflection signal monitoring database. The time-domain audio signal of the acoustic reflection signal is then converted into frequency-domain data using a short-time Fourier transform algorithm. Heterogeneous materials include, but are not limited to, foamed plastics, carbon fiber composites, and glass fiber composites. The heterogeneity coefficient formula is used... Calculate the heterogeneity coefficient H of the heterogeneous material, where S t and S r These are the acoustic wave reflection signal spectra of the heterogeneous material under test and the acoustic wave reflection signal spectra of a known homogeneous reference sample, respectively, Cov(S) t ,S r ) is the spectrum S t and S r covariance, For the spectrum S t standard deviation For the spectrum S r The standard deviation is calculated. Based on the frequency domain data of the acoustic wave reflection signals of the heterogeneous material and the known homogeneous reference sample, the dominant frequency phase difference between the acoustic wave reflection signal spectrum of the heterogeneous material and the spectrum of the known homogeneous reference sample is extracted. Based on this dominant frequency phase difference, the magnitude of the density of the heterogeneous material and the density of the known homogeneous reference sample is determined, and the velocity correction direction factor D is calculated. If the density of the heterogeneous material is greater than the density of the known homogeneous reference sample, D is 1; if the density of the heterogeneous material is less than the density of the known homogeneous reference sample, D is -1. Based on the heterogeneity coefficient and the velocity correction direction factor, the velocity correction formula is used to correct the propagation speed v of the acoustic wave signal in the current heterogeneous material. a Where v0 is the propagation speed of the acoustic signal in a known homogeneous reference sample. The propagation time difference ΔT between the sensor and the upper and lower surfaces is calculated using the timestamp information of the received ultrasonic signals. The thickness is then calculated using the formula... The thickness h of the product material is determined, where v0 is the propagation speed of the acoustic signal in a known homogeneous reference sample. Based on the heterogeneity coefficient of the heterogeneous material, it is determined whether there are local density direction variation regions within the heterogeneous material. Based on the local heterogeneity coefficient and velocity correction direction factor, the thickness of the local heterogeneous material is calculated, and the total thickness of the heterogeneous material is determined. If the product material is a multi-layer composite material, the propagation time difference between the received ultrasonic signal and the upper and lower surfaces of each layer is calculated using the timestamp information. The thickness of each layer of the multi-layer composite material is then calculated using the thickness calculation formula. The dimensional deviation between the product material size and the preset size, as well as the thickness deviation between the product material size and the preset thickness size, are calculated. If the dimensional deviation is greater than the preset dimensional deviation threshold or the thickness deviation exceeds the preset thickness deviation threshold, the thickness of the product material is corrected by adjusting the production parameters during the production process. These parameters include the precision of the production equipment, the mold clearance, and the molding temperature.

[0047] For example, on a testing line, the thickness of a foamed plastic material is being measured and needs to be compared with a known homogeneous reference sample of foamed plastic. Using an existing database, the acoustic wave reflection signals of the foamed plastic and the known homogeneous reference sample are acquired. These signals are initially time-domain audio signals, which are converted into frequency-domain data using a short-time Fourier transform algorithm, allowing the extraction of the signal's spectral characteristics. If the spectrum of the foamed plastic and the spectrum of the reference sample are S... t and S r Calculate the covariance Cov(S) between the spectra of the foamed plastic and the reference sample. t ,S r ), and the standard deviation of the spectra of the foam plastic and the reference sample. and S t Based on the covariance between the spectra of the foam and the reference sample, and the standard deviation of their respective spectra, the heterogeneity coefficient formula is used. The heterogeneity coefficient H of the heterogeneous material is calculated. This number characterizes the degree of heterogeneity of the foam material. If the calculated value of H = 1.2, it indicates that the heterogeneity of the foam is relatively high. The phase difference of the dominant frequency is calculated based on the spectrum of the sound wave reflection signal of the foam and the spectrum of a known homogeneous reference sample. This operation aims to infer the density difference between the foam and the reference sample through the phase difference in the frequency domain. If the calculation result shows that the density of the foam is less than that of the reference sample, the dominant frequency phase difference indicates D = -1, meaning the density of the foam is low. If the calculation result shows that the density of the foam is greater than that of the reference sample, the dominant frequency phase difference indicates D = 1, meaning the density of the foam is high. Based on the heterogeneity coefficient H = 1.2 and the velocity correction direction factor D = -1, the velocity correction formula v is used. a = v0×(1+α·H·D), correcting the propagation speed of sound waves in foam plastic v a Where v0 is the propagation speed of the sound wave signal in a known homogeneous reference sample. If the propagation speed of the sound wave in the homogeneous reference sample is known to be v0 = 1500 m / s, the propagation speed of the sound wave in the foam plastic can be calculated using the velocity correction formula. a =1450m / s, indicating that the sound wave propagation speed of the foam plastic is slightly slower than that of the reference sample. Using the timestamp information of the received ultrasonic signal, the propagation time difference between the signal from the sensor to the upper and lower surfaces of the foam plastic is calculated. If the measured propagation time difference is Δt = 2ms, the thickness is calculated using the formula... The thickness of the foam plastic is calculated to be h = 10 mm. Based on the heterogeneity coefficient of the heterogeneous material, it is determined whether there are local density direction variation regions within the heterogeneous material. If the heterogeneity coefficient (1.2) is greater than the preset threshold (1.0), the local thickness of the heterogeneous material is calculated based on the local heterogeneity coefficient and velocity correction direction factor, and the total thickness of the heterogeneous material is determined. If the foam plastic is a multi-layer composite material, such as an outer layer of foam plastic and an inner layer of other materials, the propagation time difference between the received ultrasonic signal and the upper and lower surfaces of each layer is calculated using the timestamp information of the ultrasonic signal. The thickness of each layer is then calculated. If the calculated thickness of the outer foam plastic is 3 mm and the thickness of the inner material is 7 mm, then the total thickness of the foam plastic material is 10 mm. Finally, the deviation between the size of the foam plastic and the preset standard size is calculated. If the preset size is 10.5 mm and the actual measured thickness is 10 mm, the calculated size deviation is 0.5 mm. If the deviation exceeds the preset dimensional deviation threshold of 0.3mm, or the thickness dimensional deviation exceeds the preset thickness dimensional deviation threshold of 0.2mm, the production parameters in the production process will be automatically adjusted. The adjusted parameters may include the precision of the production equipment, the mold gap, or the molding temperature, to ensure that the thickness of the foam plastic material meets the predetermined standard.

[0048] Specifically, based on the heterogeneity coefficient of the heterogeneous material, it is determined whether there are local density direction change regions in the heterogeneous material. Based on the local heterogeneity coefficient and velocity correction direction factor of the heterogeneous material, the local thickness of the heterogeneous material is calculated, and the total thickness of the heterogeneous material is determined.

[0049] If the heterogeneity coefficient of the heterogeneous material is greater than a preset threshold, it is determined that there is a local density direction change region in the heterogeneous material. The echo signal of the heterogeneous material is then segmented into time segments according to a preset number of segments, and the dominant frequency phase difference of each segment is determined. The heterogeneity coefficient of the local heterogeneity of the heterogeneous material corresponding to each segment is calculated using the heterogeneity coefficient formula. Based on the dominant frequency phase difference of each segment, the density of the local heterogeneity of the echo signal corresponding to each segment is compared with the density of a known homogeneous reference sample, and the velocity correction direction factor D for the local heterogeneity of the echo signal corresponding to each segment is determined. Based on the heterogeneity coefficient and velocity correction direction factor of the local heterogeneity of the echo signal corresponding to each segment, the propagation velocity of the echo signal in each local heterogeneous material is corrected using the velocity correction formula. The thickness of the local heterogeneous material is determined using the thickness calculation formula, and the total thickness of the heterogeneous material is calculated based on the thickness of the local heterogeneous material.

[0050] For example, the thickness of a heterogeneous carbon fiber composite material is being measured, and it is known that the density of the echo signal varies at different locations. During production, the heterogeneity coefficient of the material was found to exceed a preset threshold of 1, thus requiring further analysis and correction of the thickness measurement. Based on ultrasonic signal data in the database, the calculated heterogeneity coefficient of the carbon fiber composite material is 1.2, which is greater than the preset threshold of 1.0. This indicates that the carbon fiber composite material has high non-uniformity and local density direction variation regions exist within it. Therefore, the echo signal is processed by time segmentation, such as dividing the signal into 5 segments, each representing the acoustic wave reflection information at different locations within the material. Each signal segment is analyzed to extract its dominant frequency phase difference. Spectral data was obtained through short-time Fourier transform, and the dominant frequency phase difference of each signal segment was calculated. If the dominant frequency phase difference of the first segment was 0.01 radians, the second 0.03 radians, the third 0.02 radians, the fourth 0.04 radians, and the fifth 0.05 radians, this dominant frequency phase difference reflects the local acoustic wave propagation characteristics in each signal segment, allowing for the assessment of material density differences in these regions. The local heterogeneity coefficient corresponding to each echo signal segment was calculated using the heterogeneity coefficient formula. If the heterogeneity coefficient was found to be 1.5 for the first segment, 2.0 for the second, 1.8 for the third, 2.2 for the fourth, and 2.5 for the fifth, these heterogeneity coefficients indicate that the heterogeneity of the material gradually increases as the echo signal progresses, especially in the later stages of the signal where the heterogeneity coefficient increases significantly. Based on the dominant frequency phase difference of each echo signal segment, it is further determined whether the local density of the heterogeneous material corresponding to each signal segment is greater than the density of a known homogeneous reference sample. If the density of the reference sample is 1500 kg / m³, in the first signal segment, the dominant frequency phase difference is 0.01 radians, indicating that the density of this region is less than the density of the reference sample. Therefore, the velocity correction direction factor D = -1 is determined for this segment. In the second signal segment, the dominant frequency phase difference is 0.03 radians, and the density is greater than the density of the reference sample. Therefore, the velocity correction direction factor D = 1 is determined for this segment. The determination results for the other segments are D = -1 for the third segment, D = 1 for the fourth segment, and D = 1 for the fifth segment. Based on the inhomogeneity coefficient and velocity correction direction factor corresponding to each echo signal segment, the velocity correction formula is used to correct the propagation velocity of the echo signal in each local region. It is known that the sound wave propagation velocity of the homogeneous reference sample is 1800 m / s. The propagation velocity of each signal segment is calculated by the correction formula. In the first signal segment, due to the low inhomogeneity coefficient and the velocity correction direction factor of -1, the corrected propagation velocity is 1700 m / s. In the second signal segment, the corrected propagation velocity is 1850 m / s, in the third segment it is 1750 m / s, in the fourth segment it is 1880 m / s, and in the fifth segment it is 1900 m / s.Using these corrected propagation velocities, the thickness can be calculated. If the propagation time difference of the first echo signal segment is 1.2 ms, the second 1.5 ms, the third 1.3 ms, the fourth 1.6 ms, and the fifth 1.7 ms, then based on the propagation time difference and the corrected propagation velocity, the local thickness of each segment can be calculated. For example, the local thickness calculated using the thickness calculation formula is 2.04 mm in the first segment, 2.78 mm in the second, 2.29 mm in the third, 3.01 mm in the fourth, and 3.23 mm in the fifth. Therefore, based on the local thickness dimensions of these five segments, the total thickness of the heterogeneous material is calculated to be 13.35 mm.

[0051] Step S105: Obtain the acoustic wave reflection signal of the product material after the process parameters and production parameters have been adjusted by the ultrasonic sensor, determine whether the production stability requirements have been met after the adjustment, and continue to adjust the process parameters and production parameters.

[0052] The ultrasonic sensor acquires the acoustic wave reflection signal of the product material after adjusting the process and production parameters, obtaining new spectral characteristics and corresponding timestamp information of the acoustic wave reflection signal. Based on the obtained new spectral characteristics and timestamp information, it is determined whether there is a deviation in the acoustic wave reflection signal, and whether the thickness of the product material deviates from the preset thickness beyond a preset deviation threshold, thus determining whether the production stability requirements have been met after adjustment. If the production stability requirements are still not met, the process and production parameters are adjusted again until the production stability requirements are met.

[0053] For example, on a certain testing line, the standard specifications for the produced foam boards are polyurethane material, with dimensions of 300mm x 200mm, a thickness of 10mm, and a density of 0.3g / cm³. To ensure product compliance, ultrasonic sensors are used to monitor the acoustic wave reflection signals in real time. During initial production, the measured spectral characteristics of the acoustic wave reflection signal show a frequency of 5MHz, a peak frequency of 5.2MHz, and an amplitude of 0.8. The ultrasonic signal propagation time difference is 0.012 seconds, and the calculated material thickness is 9mm, a deviation of 1mm. This deviation exceeds the preset threshold of 0.5mm, causing production to fail to meet stability requirements. Therefore, the production process and equipment parameters are adjusted, including improving the precision of the production equipment, adjusting the mold gap to a more precise 0.05mm, increasing the molding temperature to 185℃, and adjusting the cooling rate to 1.2℃ / min, to ensure effective control of material expansion and contraction during molding. After adjustments, the ultrasonic sensor continued to monitor the acoustic wave reflection signal of the new product. The new reflection signal spectrum characteristics showed a frequency of 5.05MHz, a peak frequency of 5.1MHz, and an amplitude of 0.85. The timestamp of the reflection signal showed a propagation time difference of 0.011 seconds, and the calculated product thickness was 9.8mm. At this point, the thickness deviation was 0.2mm, lower than the preset deviation threshold of 0.5mm. By comparing with the preset standard, the product material thickness and acoustic wave reflection signal spectrum characteristics were close to the preset requirements. After multiple rounds of adjustments and monitoring, the production process finally reached the stability requirements, ensuring that the product quality met the standards, and the acoustic wave reflection signal no longer showed deviation.

[0054] This embodiment of an automatic material dimension measuring device may specifically include:

[0055] A processor and a memory; the memory stores at least one instruction, which is executed by the processor to cause the device to perform the automatic material size measurement method as described in the above method embodiments.

[0056] The above description is merely a preferred embodiment of this application and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of the invention involved in this application is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the concept of this application. For example, technical solutions formed by substituting the above features with (but not limited to) technical features with similar functions disclosed in this application.

Claims

1. An automatic material dimension measurement method, characterized in that, The method includes: Based on the product materials and acoustic emission parameters of different specifications and standards, as well as the corresponding acoustic reflection signal reception effect, predict the acoustic emission parameters that are optimal for the acoustic reflection signal reception effect of the current product material, emit ultrasonic signals and acquire acoustic reflection signals and corresponding timestamp information. The sound wave reflection signal is separated by an independent component analysis algorithm, and the type of sound wave reflection source is identified. The spectral characteristics of the sound wave reflection signal whose sound wave reflection source is the product material are determined. Based on the spectral characteristics of the corrected acoustic wave reflection signal of the product material and the spectral characteristics of the reference acoustic wave reflection signal of the product material specification standard, the reasons for the deviation of the acoustic wave reflection signal of the product material are identified and used to guide the adjustment of the process parameters of the product production equipment. By using the acoustic wave reflection signals of heterogeneous materials and known homogeneous reference samples, the heterogeneity coefficient of heterogeneous materials is determined, the propagation speed of acoustic waves in the current heterogeneous material is corrected, and the thickness dimensions of single-layer product materials and multi-layer composite materials are calculated. By using ultrasonic sensors to acquire the acoustic wave reflection signals of the product material after adjusting the process and production parameters, it can be determined whether the production stability requirements have been met, and the process and production parameters can be continuously adjusted. The process of determining the heterogeneity coefficient of the heterogeneous material by comparing the acoustic wave reflection signal of the heterogeneous material with the acoustic wave reflection signal of a known homogeneous reference sample, correcting the propagation speed of the acoustic wave signal in the current heterogeneous material, and calculating the thickness dimensions of single-layer product materials and multi-layer composite materials includes: Through the formula for the coefficient of heterogeneity Calculate the heterogeneity coefficient H of the heterogeneous material, where and The images show the acoustic wave reflection signal spectra of the heterogeneous material under test and the acoustic wave reflection signal spectra of a known homogeneous reference sample, respectively. For the spectrum and covariance, For the spectrum standard deviation For the spectrum The standard deviation is calculated. Based on the frequency domain data of the acoustic wave reflection signals of the heterogeneous material and the known homogeneous reference sample, the dominant frequency phase difference between the acoustic wave reflection signal spectrum of the heterogeneous material and the acoustic wave reflection signal spectrum of the known homogeneous reference sample is extracted. Based on this dominant frequency phase difference, the magnitude of the density of the heterogeneous material and the density of the known homogeneous reference sample is determined, and the velocity correction direction factor D is determined. If the density of the heterogeneous material is greater than the density of the known homogeneous reference sample, then D is 1; if the density of the heterogeneous material is less than the density of the known homogeneous reference sample, then D is -1. Based on the heterogeneity coefficient and the velocity correction direction factor, the velocity correction formula is used. Correcting the propagation speed of sound waves in current heterogeneous materials ,in, Let be the propagation speed of the acoustic signal in a known homogeneous reference sample.

2. The automatic material dimension measurement method according to claim 1, wherein, The process involves predicting optimal acoustic emission parameters for the current product material based on different specifications of product materials and acoustic emission parameters, as well as the corresponding acoustic reflection signal reception effect. This includes emitting ultrasonic signals and acquiring acoustic reflection signals and corresponding timestamp information. An ultrasonic sensor emits ultrasonic signals to product materials of different specifications and standards, and receives the reflected sound waves. The ultrasonic sensor's emission parameters are recorded, and the reception effect of the reflected sound waves is labeled. Specifications include material type, thickness, number of layers, and density. Emission parameters include emission frequency, pulse width, and emission power. Reception effects are categorized as excellent, good, and poor. Based on the different specifications of the product materials, the ultrasonic emission parameters, and the corresponding reception effects, a recurrent neural network is used to train a model to construct an ultrasonic emission parameter prediction model. This model determines the ultrasonic emission parameters that result in excellent reception of the reflected sound waves for the current product material, and the ultrasonic sensor's emission parameters are then set. The ultrasonic sensor's position is adjusted, and it is installed above the detection line. An image of the product material on the detection line is acquired using a camera above the line. If the product material is directly below the ultrasonic sensor, the sensor emits ultrasonic signals to the material according to the set emission parameters and receives the reflected sound waves and corresponding timestamp information.

3. The automatic material dimension measurement method according to claim 1, wherein, The process of separating the acoustic wave reflection signal using an independent component analysis algorithm, identifying the acoustic wave reflection source type, and determining the spectral characteristics of the acoustic wave reflection signal from the product material as the acoustic wave reflection source includes: Based on the received acoustic wave reflection signals, the acoustic wave reflection signals are separated using an independent component analysis algorithm to obtain acoustic wave reflection signals from different acoustic wave reflection sources. A short-time Fourier transform algorithm is used to convert the time-domain audio signals of the acoustic wave reflection signals into frequency-domain data, extracting the spectral features of the acoustic wave reflection signals and saving them to the acoustic wave reflection monitoring database. The spectral features include frequency, peak frequency, and amplitude. Using the acoustic wave reflection signal monitoring database, the spectral features of acoustic wave reflection signals from different acoustic wave reflection sources are obtained, and the acoustic wave reflection source types are labeled. A random forest algorithm is used for model training to construct an acoustic wave reflection source identification model, identifying the acoustic wave reflection source type of the acoustic wave reflection signal. The spectral features of acoustic wave reflection signals from product materials are determined. Environmental data is acquired, and based on this data, frequency drift and amplitude drift are calculated to correct the frequency and amplitude of the acoustic wave reflection signals. The corrected spectral features of acoustic wave reflection signals from different acoustic wave reflection sources are obtained and saved to the acoustic wave reflection signal monitoring database. The environmental data includes temperature, humidity, and air pressure.

4. The automatic material dimension measurement method according to claim 3, wherein, The step of calculating frequency drift and amplitude drift based on environmental data, and correcting the frequency and amplitude of the reflected sound wave signal, includes: Temperature, humidity, and air pressure data within the detection line are acquired in real time using temperature sensors, humidity sensors, and air pressure sensors installed on the detection line. The frequency drift calculation formula is then used. Determine the frequency drift under the current detection environment. And use the amplitude drift calculation formula Determine the amplitude drift of the current detection environment. Where T is temperature, H is humidity, and P is air pressure. and These are the frequency value and amplitude value measured under standard conditions, respectively. , , It is the coefficient for detecting the influence of the environment on the frequency. , , It is the coefficient for detecting the influence of the environment on the amplitude, which is obtained by experimental fitting through historical data; based on the spectral characteristics, frequency drift, and amplitude drift of the sound wave reflection signal, the frequency and amplitude of the sound wave reflection signal are corrected.

5. The automatic material dimension measurement method according to claim 1, wherein, The process of identifying the cause of deviation in the acoustic wave reflection signal of the product material based on the spectral characteristics of the corrected acoustic wave reflection signal and the spectral characteristics of the reference acoustic wave reflection signal of the product material specification standard, and guiding the adjustment of the process parameters of the production equipment, includes: By using a sound wave reflection signal monitoring database, the spectral characteristics of sound wave reflection signals from different sound wave reflection sources after correction are obtained. The similarity between the spectral characteristics of the obtained product material's sound wave reflection signal and the spectral characteristics of the reference sound wave reflection signal of the product material specification standard is calculated using the cosine similarity method. If the similarity is lower than a preset similarity threshold, based on the obtained spectral characteristics of the product material's sound wave reflection signal and indicating the reasons for the deviation, a random forest algorithm is used to train the model, constructing a sound wave reflection signal deviation cause identification model to identify the reasons for the deviation in the product material's sound wave reflection signal. The reasons for the deviation include, but are not limited to, product material density deviation and shape defects, with shape defects including, but not limited to, cracks and pits. Based on the reasons for the deviation in the sound wave reflection signal, the process parameters of the production equipment are adjusted, including, but not limited to, temperature, cooling rate, injection pressure of the injection molding machine, injection speed, and injection volume.

6. The automatic material dimension measurement method according to claim 1, wherein, The process involves acquiring acoustic wave reflection signals from the product material after adjusting process and production parameters using an ultrasonic sensor, determining whether the adjustments have met production stability requirements, and continuously adjusting the process and production parameters, including: The ultrasonic sensor acquires the acoustic wave reflection signal of the product material after adjusting the process parameters and production parameters, obtaining the new acoustic wave reflection signal spectrum characteristics and corresponding timestamp information. Based on the obtained new acoustic wave reflection signal spectrum characteristics and corresponding timestamp information, it is determined whether there is a deviation in the acoustic wave reflection signal, and whether the thickness of the product material deviates from the preset thickness size beyond the preset deviation threshold, to determine whether the production stability requirements have been met after adjustment. If the production stability requirements have not been met, the process parameters and production parameters are adjusted again until the production stability requirements are met.

7. An automatic material dimension measuring device, characterized in that, The device includes: A processor and a memory; the memory stores at least one instruction, which is executed by the processor, causing the device to perform the automatic material dimension measurement method as described in any one of claims 1 to 6.

Images