Titanium plate structure performance prediction method and system based on surface defect analysis

Abstract

The invention relates to the technical field of titanium plate defect analysis, in particular to a titanium plate structure performance prediction method and system based on surface defect analysis, and the method comprises the steps: carrying out image shooting on a to-be-detected titanium plate sample by using a shooting probe to obtain an original titanium plate image, and carrying out sound wave monitoring on the to-be-detected titanium plate sample by using a sound wave probe to obtain an original sound wave signal set; obtaining an original damage process factor according to the original sound wave signal set, carrying out gray enhancement conversion on the original titanium plate image to obtain a titanium plate crack set, obtaining a segmented titanium plate image set according to the titanium plate crack set, carrying out titanium plate gray feature extraction based on the segmented titanium plate image set to obtain a titanium plate gray feature value, and obtaining a titanium plate gray feature value according to the titanium plate crack set; the target damage process factor and the titanium plate gray feature value are used for titanium plate structure performance prediction, and the titanium plate structure performance prediction accuracy and efficiency can be improved.

Description

Technical Field

[0001] The invention relates to the technical field of titanium plate defect analysis, and in particular to a titanium plate structure performance prediction method and system based on surface defect analysis. Background Art

[0002] Titanium plates have high strength and low density, as well as good corrosion resistance and high temperature resistance, which makes them important in actual industrial production. For example, titanium plates are important in the manufacture of aircraft structures, engine components, and spacecraft components. The microstructure and properties of titanium plates greatly affect their application in actual industrial production. Therefore, it is extremely important to predict the microstructure and properties of titanium plates in actual titanium plate applications.

[0003] At present, the prediction of the microstructure and performance of titanium plates is mainly achieved by obtaining the material data of titanium plates. Although this method can complete the prediction of the microstructure and performance of titanium plates, obtaining the material data of titanium plates requires pressure tests on titanium plates. During this process, the microstructure of titanium plates may change, resulting in inaccurate prediction results. At the same time, the prediction process of this method progresses slowly, reducing the efficiency of the prediction of the microstructure and performance of titanium plates. Summary of the invention

[0004] The present invention provides a titanium plate structure performance prediction method and system based on surface defect analysis, the main purpose of which is to improve the accuracy and efficiency of the titanium plate structure performance prediction.

[0005] To achieve the above-mentioned purpose, the present invention provides a method for predicting the microstructure and performance of a titanium plate based on surface defect analysis, comprising: receiving a titanium plate performance prediction instruction, and starting a shooting probe based on the titanium plate performance prediction instruction, wherein the shooting probe is installed in a titanium plate defect analysis platform, and the titanium plate defect analysis platform also includes: a probe holder, a titanium plate sample to be tested, a gel coupling agent, and an acoustic wave probe; using the shooting probe to shoot an image of the titanium plate sample to be tested to obtain an original titanium plate image, wherein the shooting probe is installed directly above the titanium plate sample to be tested, and the shooting probe is connected to the probe holder; after obtaining the original titanium plate image, starting the acoustic wave probe and using the acoustic wave probe to perform acoustic wave monitoring on the titanium plate sample to be tested to obtain an original acoustic wave signal set, wherein the acoustic wave probe is connected to the gel coupling agent, and the other end of the gel coupling agent is connected to the titanium plate sample to be tested; performing internal damage analysis of the titanium plate according to the original acoustic wave signal set to obtain an original damage process factor; performing grayscale enhancement conversion on the original titanium plate image , obtain a grayscale titanium plate image, perform crack identification in the grayscale titanium plate image, and obtain a titanium plate crack group set; according to the titanium plate crack group set, perform image segmentation on the grayscale titanium plate image to obtain a segmented titanium plate image set, wherein the number of segmented titanium plate images in the segmented titanium plate image set is the same as the number of titanium plate crack groups in the titanium plate crack group set, and different segmented titanium plate images may overlap in space; perform titanium plate grayscale feature extraction based on the segmented titanium plate image set to obtain a titanium plate grayscale feature value, perform surface defect weighting on the original damage process factor according to the titanium plate crack group set to obtain a target damage process factor, wherein the target damage process factor includes: an expansion damage process factor and a reduction damage process factor; transmit the target damage process factor and the titanium plate grayscale feature value to a pre-built titanium plate performance prediction platform, and based on the titanium plate performance prediction platform, complete the titanium plate tissue performance prediction based on surface defect analysis, wherein the titanium plate performance prediction platform has a built-in deep learning model for predicting the tissue performance of titanium plates.

[0006] Optionally, the method of using the acoustic wave probe to perform acoustic wave monitoring on the titanium plate sample to be tested to obtain an original acoustic wave signal group set includes: dividing the titanium plate sample to be tested into detection areas to obtain a titanium plate detection area set, and sequentially extracting titanium plate detection areas from the titanium plate detection area set, wherein different titanium plate detection areas in the titanium plate detection area set overlap in space; according to a preset detection acoustic wave amplitude, using the acoustic wave probe to transmit acoustic waves to the titanium plate detection area, and waiting for the titanium plate sample to be tested to reflect acoustic waves to the acoustic wave probe; after receiving the reflected acoustic wave reflected by the titanium plate sample to be tested, , record the reflection time of the reflected sound wave and identify the reflection amplitude of the reflected sound wave, wherein the reflection time is the time difference between the moment when the sound wave probe transmits the sound wave and the moment when the reflected sound wave is received; perform key-value pairing on the reflected sound wave, the reflection time and the reflected signal to obtain an original sound wave signal group, and return to the step of emitting sound waves to the titanium plate detection area using the sound wave probe according to the preset detection sound wave amplitude, until the number of the obtained original sound wave signal groups is not less than the preset reference sound wave number; summarize the original sound wave signal groups to obtain an original sound wave signal group set.

[0007] Optionally, the internal damage analysis of the titanium plate is performed according to the original acoustic wave signal set to obtain the original damage process factor, including: classifying the detection area in the original acoustic wave signal set to obtain multiple same-family acoustic wave signal sets, wherein the same-family acoustic wave signal sets in the same same-family acoustic wave signal set are from the same titanium plate detection area; performing the following operations on each of the multiple same-family acoustic wave signal sets: sequentially extracting the same-family acoustic wave signal sets in the same-family acoustic wave signal set to obtain the same-family reflection duration and the same-family reflection amplitude of the same-family acoustic wave signal set; judging whether the same-family reflection amplitude is within a preset standard reflection amplitude range; if the same-family reflection amplitude is within the standard reflection amplitude range, recording the same-family reflection amplitude as the effective reflection amplitude; If the same-family reflection amplitude is not within the standard reflection amplitude range, it is determined whether the same-family reflection duration is less than the preset standard reflection duration; if the same-family reflection duration is less than the standard reflection duration, the post-position sound wave signal group of the same-family sound wave signal group is obtained in the same-family sound wave signal group set, and the post-position reflection amplitude of the post-position sound wave signal group is extracted; then according to the post-position reflection amplitude and the same-family reflection amplitude, the effective reflection amplitude is calculated, wherein the effective reflection amplitude is the sum of the post-position reflection amplitude and the same-family reflection amplitude; the effective reflection amplitude is summarized to obtain an effective reflection amplitude set, and the average effective amplitude of the effective reflection amplitude set is calculated, and the original damage factor is calculated according to the average effective amplitude and the detected sound wave amplitude, wherein the average effective amplitude and the original damage factor are respectively expressed as: ,in, represents the average effective amplitude, Represents the number of effective reflection amplitudes in the effective reflection amplitude set, represents the i-th effective reflection amplitude, represents the original damage factor, Indicates the detected sound wave amplitude, represents the absolute value symbol; summing up the original damage factors to obtain an original damage factor set, extracting the maximum damage factor in the original damage factor set, and using the maximum damage factor as the original damage process factor.

[0008] Optionally, performing grayscale enhancement conversion on the original titanium plate image to obtain a grayscale titanium plate image includes: extracting original titanium plate pixels in the original titanium plate image in sequence, obtaining RGB pixel values ​​of the original titanium plate pixels, and performing grayscale conversion on the RGB pixel values ​​according to preset red coefficients, green coefficients, and blue coefficients to obtain grayscale pixel values, wherein the RGB pixel values ​​and the grayscale pixel values ​​are respectively expressed as: ,in, Represents RGB pixel value, represents the red pixel value, represents the green pixel value, represents the blue pixel value, represents the grayscale pixel value, represents the red coefficient, represents the green coefficient, Represents a blue coefficient; summarizes the grayscale pixel values ​​to obtain a grayscale pixel value set, draws a grayscale histogram of the grayscale pixel value set, and sets grayscale frequency maximums, wherein the grayscale frequency maximums are the maximum frequency and the minimum frequency; according to the grayscale histogram, grayscale enhancement is performed on the original titanium plate image to obtain a grayscale titanium plate image.

[0009] Optionally, the grayscale enhancement of the original titanium plate image is performed according to the grayscale histogram to obtain a grayscale titanium plate image, including: extracting grayscale pixel values ​​in the grayscale pixel value set in turn to obtain grayscale pixel points of the grayscale pixel values, identifying the grayscale frequency of the grayscale pixel values ​​in the grayscale histogram, and judging whether the grayscale frequency is less than the maximum frequency; if the grayscale frequency is not less than the maximum frequency, updating the grayscale pixel value with a preset maximum pixel value to obtain an updated pixel value, and updating the grayscale pixel point with the updated pixel value to obtain an updated pixel point; if the grayscale frequency is less than the maximum frequency, judging Determine whether the grayscale frequency is greater than the minimum frequency; if the grayscale frequency is not greater than the minimum frequency, update the grayscale pixel value with a preset minimum pixel value to obtain an updated pixel value, and update the grayscale pixel point with the updated pixel value to obtain an updated pixel point; if the grayscale frequency is greater than the minimum frequency, update the grayscale pixel value in frequency proportion to obtain an updated pixel value, and update the grayscale pixel point with the updated pixel value to obtain an updated pixel point; summarize the updated pixel points to obtain an updated pixel point set, and use the updated pixel point set to update the original titanium plate image to obtain a grayscale titanium plate image.

[0010] Optionally, the updating the grayscale pixel value in frequency ratio to obtain an updated pixel value includes: updating the grayscale pixel value according to the grayscale frequency, the minimum pixel value, the maximum pixel value, the minimum frequency and the maximum frequency to obtain an updated pixel value, wherein the updated pixel value is expressed as: ,in, Indicates updating pixel value, represents the grayscale frequency, represents the minimum frequency, represents the maximum pixel value, represents the minimum pixel value, Indicates the maximum frequency.

[0011] Optionally, the crack identification is performed in the grayscale titanium plate image to obtain a titanium plate crack group set, including: performing noise filtering on the grayscale titanium plate image to obtain a denoised titanium plate image, wherein the noise filtering method is a Gaussian filtering method; using a preset morphological gradient transformation method to perform morphological gradient transformation on the denoised titanium plate image to obtain a cracked titanium plate image, performing crack extraction in the cracked titanium plate image to obtain an original crack set, wherein the cracked titanium plate image contains a clear crack image; extracting original cracks in the original crack set in turn, identifying the original crack length of the original crack, performing key-value pairing on the original crack length and the original crack to obtain a titanium plate crack group, and summarizing the titanium plate crack groups to obtain a titanium plate crack group set.

[0012] Optionally, the grayscale feature extraction of the titanium plate based on the segmented titanium plate image set to obtain the grayscale feature value of the titanium plate includes: extracting segmented titanium plate images in the segmented titanium plate image set in sequence, identifying the number of cracks in the segmented titanium plate images, extracting segmented pixel point sets of the segmented titanium plate images, and obtaining segmented grayscale value sets corresponding to the segmented pixel point sets; calculating the segmented grayscale difference of the segmented grayscale value set, wherein the segmented grayscale difference is expressed as: ,in, Represents the segmentation grayscale difference, Represents the number of segmentation gray values ​​in the segmentation gray value set, represents the jth segmentation grayscale value; the crack number and segmentation grayscale difference are summarized to obtain a crack number set and a segmentation grayscale difference set; according to the crack number set and the segmentation grayscale difference set, the grayscale characteristic value of the titanium plate is calculated using the following formula: ,in, represents the grayscale eigenvalue of the titanium plate, represents the number of segmented titanium plate images in the segmented titanium plate image set, Indicates Number of cracks, Indicates Number of cracks, Indicates Segmentation grayscale difference.

[0013] Optionally, the surface defect weighting of the original damage progress factor according to the titanium plate crack group to obtain the target damage progress factor includes: obtaining the total length of the titanium plate cracks of the titanium plate crack group, and based on the original damage progress factor, querying the standard total crack length in a pre-constructed damage progress crack table, wherein the damage progress crack table is a relationship table between the damage progress factor and the crack length; judging whether the total length of the titanium plate cracks is greater than the standard total crack length; if the total length of the titanium plate cracks is greater than the standard total crack length, performing process expansion processing on the original damage progress factor to obtain an expanded damage progress factor, wherein the expanded damage progress factor is expressed as: ,in, represents the factor for expanding the damage process, represents the original damage progression factor, represents the logarithmic function, represents the total length of the titanium plate crack, represents the total length of the standard crack; if the total length of the titanium plate crack is not greater than the total length of the standard crack, the original damage process factor is subjected to a process reduction process to obtain a reduced damage process factor, wherein the reduced damage process factor is expressed as: in, Represents the reduction of damage progression factor.

[0014] To achieve the above-mentioned purpose, the present invention also provides a titanium plate tissue performance prediction system based on surface defect analysis, comprising: an original image shooting module, used to receive a titanium plate performance prediction instruction, and start a shooting probe based on the titanium plate performance prediction instruction, wherein the shooting probe is installed in a titanium plate defect analysis platform, and the titanium plate defect analysis platform also includes: a probe bracket, a titanium plate sample to be tested, a gel coupling agent and an acoustic wave probe, and the shooting probe is used to shoot an image of the titanium plate sample to be tested to obtain an original titanium plate image, wherein the shooting probe is installed directly above the titanium plate sample to be tested, and the shooting probe is connected to the probe bracket; a damage process calculation module, used to start the acoustic wave probe after the original titanium plate image is obtained and use the acoustic wave probe to perform acoustic wave monitoring on the titanium plate sample to be tested to obtain an original acoustic wave signal set, wherein the acoustic wave probe is connected to the gel coupling agent, and the other end of the gel coupling agent is connected to the titanium plate sample to be tested, and the internal damage analysis of the titanium plate is performed according to the original acoustic wave signal set to obtain an original damage process factor; a titanium plate crack identification module, used to identify the original titanium plate cracks. The plate image is grayscale enhanced and converted to obtain a grayscale titanium plate image, cracks are identified in the grayscale titanium plate image to obtain a titanium plate crack group set, and the grayscale titanium plate image is segmented according to the titanium plate crack group set to obtain a segmented titanium plate image set, wherein the number of segmented titanium plate images in the segmented titanium plate image set is the same as the number of titanium plate crack groups in the titanium plate crack group set, and different segmented titanium plate images may overlap in space; a titanium plate performance prediction module is used to extract titanium plate grayscale features based on the segmented titanium plate image set to obtain titanium plate grayscale feature values, and the original damage process factor is weighted by surface defects according to the titanium plate crack group set to obtain a target damage process factor, wherein the target damage process factor includes: an expansion damage process factor and a reduction damage process factor, and the target damage process factor and the titanium plate grayscale feature value are transmitted to a pre-constructed titanium plate performance prediction platform, and based on the titanium plate performance prediction platform, the titanium plate tissue performance prediction based on surface defect analysis is completed, wherein the titanium plate performance prediction platform has a built-in deep learning model for predicting the tissue performance of titanium plates.

[0015] In order to solve the above problems, the present invention also provides an electronic device, comprising: a memory storing at least one instruction; and a processor executing the instructions stored in the memory to implement the above-mentioned method for predicting titanium plate structure properties based on surface defect analysis.

[0016] In order to solve the above problems, the present invention also provides a computer-readable storage medium, in which at least one instruction is stored. The at least one instruction is executed by a processor in an electronic device to implement the above-mentioned method for predicting titanium plate structure properties based on surface defect analysis.

[0017] In order to solve the problem described in the background technology, the present invention first receives a titanium plate performance prediction instruction, starts a shooting probe based on the titanium plate performance prediction instruction, and uses the shooting probe to shoot an image of the titanium plate sample to be tested to obtain an original titanium plate image, completes the correct installation of the shooting probe and obtains the original image of the titanium plate sample to be tested, providing original conditions for subsequent surface defect analysis, and at the same time uses the shooting probe to shoot images to avoid direct contact with the titanium plate sample to be tested, so that the subsequent titanium plate tissue performance prediction has higher accuracy. After obtaining the original titanium plate image, the acoustic wave probe is started and the acoustic wave probe is used to perform acoustic wave monitoring on the titanium plate sample to be tested to obtain an original acoustic wave signal set. In this step, the original acoustic wave signals inside the titanium plate are obtained through acoustic wave monitoring. These signals can reflect the damage inside the titanium plate, providing data support for the subsequent titanium plate internal damage analysis. Then, the titanium plate internal damage analysis is performed according to the original acoustic wave signal set to obtain the original damage process factor. The calculation of the original damage process factor enables the internal damage of the titanium plate to have an intuitive representation of data, and then the original titanium plate image is grayscale enhanced and converted to obtain a grayscale titanium plate image, and then the grayscale titanium plate image is converted to grayscale. Crack identification is performed in the grayscale titanium plate image to obtain the titanium plate crack group set. This step completes the acquisition of surface cracks on the titanium plate sample to be tested, providing basic data for subsequent surface defect analysis. According to the titanium plate crack group set, the grayscale titanium plate image is segmented to obtain the segmented titanium plate image set, and the titanium plate grayscale feature extraction is performed based on the segmented titanium plate image set to obtain the titanium plate grayscale eigenvalue. The acquisition of the titanium plate grayscale eigenvalue makes the surface defects of the titanium plate sample to be tested have a numerical intuitive representation, which speeds up the process of predicting the microstructure and performance of the titanium plate. The original damage process factor is extracted through the titanium plate crack set. Surface defects are weighted to obtain the target damage process factor. This step combines the surface defects of the titanium plate sample to be tested with the internal damage, so that the obtained target damage process factor is more in line with the actual situation, and the accuracy of the prediction of the titanium plate structure performance is improved. Finally, the target damage process factor and the grayscale characteristic value of the titanium plate are transmitted to the titanium plate performance prediction platform. The titanium plate performance prediction platform is used to predict the titanium plate structure performance. By using the deep learning method to predict the titanium plate structure performance, the efficiency of the entire prediction is improved. At the same time, the support of big data also makes the prediction of the titanium plate structure performance more accurate. Therefore, the present invention can improve the accuracy and efficiency of the prediction of the titanium plate structure performance. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 A schematic flow chart of a method for predicting the microstructure and properties of a titanium plate based on surface defect analysis provided in one embodiment of the present invention; Figure 2 A functional module diagram of a titanium plate structure performance prediction system based on surface defect analysis provided by an embodiment of the present invention; Figure 3A schematic diagram of the structure of an electronic device for implementing the titanium plate structure performance prediction method based on surface defect analysis provided in one embodiment of the present invention.

[0019] Explanation of the reference numerals: 1. electronic device; 10. processor; 11. memory; 12. bus.

[0020] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0021] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0022] The embodiment of the present application provides a method for predicting the microstructure and properties of a titanium plate based on surface defect analysis. The execution subject of the method for predicting the microstructure and properties of a titanium plate based on surface defect analysis includes but is not limited to at least one of the electronic devices such as a server and a terminal that can be configured to execute the method provided in the embodiment of the present application. In other words, the method for predicting the microstructure and properties of a titanium plate based on surface defect analysis can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc.

[0023] Reference Figure 1 The figure is a flow chart of a titanium plate structure performance prediction method based on surface defect analysis provided by an embodiment of the present invention. In this embodiment, the titanium plate structure performance prediction method based on surface defect analysis includes: S1, receiving a titanium plate performance prediction instruction, and starting a shooting probe based on the titanium plate performance prediction instruction, wherein the shooting probe is installed in a titanium plate defect analysis platform, and the titanium plate defect analysis platform also includes: a probe bracket, a titanium plate sample to be tested, a gel coupling agent, and an acoustic wave probe.

[0024] It can be understood that the titanium plate performance prediction instruction refers to an instruction initiated manually to perform performance prediction on the titanium plate sample to be tested, and the shooting probe refers to a device with image shooting function and signal instruction receiving function, which is mounted above the titanium plate defect analysis platform by the probe bracket structure so as to shoot the titanium plate sample to be tested. The shooting probe can be a camera equipped with a signal receiver and a CCD sensor. The titanium plate defect analysis platform refers to an operating platform for performing performance prediction on the titanium plate sample to be tested. The titanium plate defect analysis platform is a metal plane, and the probe bracket refers to a long strip bracket connected to the shooting probe, one end of the probe bracket is connected to the titanium plate defect analysis platform, and the other end is connected to the shooting probe.

[0025] It can be understood that the titanium plate sample to be tested refers to the target titanium plate for which the microstructure and performance of the titanium plate need to be predicted. The titanium plate sample to be tested is a rectangular flat plate, which is placed horizontally in the titanium plate defect analysis platform. The gel coupling agent refers to a filler that connects the acoustic wave probe and the titanium plate sample to be tested. The gel coupling agent is in a gel state and can be directly applied to the titanium plate sample to be tested. It can fill the gap between the acoustic wave probe and the titanium plate sample to be tested. The acoustic wave probe refers to a device that can emit and receive sound waves. The acoustic wave probe has an acoustic wave transmitting unit and an acoustic wave receiving unit, wherein the acoustic wave transmitting unit is used to emit sound waves to the titanium plate sample to be tested, and the acoustic wave receiving unit is used to receive the acoustic wave signal reflected back by the titanium plate sample to be tested.

[0026] It should be noted that before the image of the titanium plate sample to be tested is captured by the shooting probe, the titanium plate sample to be tested is not connected to the acoustic wave probe to prevent the acoustic wave probe and the gel coupling agent from affecting the image captured by the shooting probe.

[0027] For example, Xiao Zhang is a staff member of a titanium plate processing factory. One day, Xiao Zhang wants to predict the titanium plate microstructure and performance of a titanium plate, so Xiao Zhang cuts a rectangular titanium plate sample from the titanium plate and uses the rectangular titanium plate sample as the titanium plate sample to be tested. He fixes the titanium plate sample to be tested in the titanium plate defect analysis platform and uses the control software to send a titanium plate performance prediction instruction to the shooting probe. When the shooting probe receives the titanium plate performance prediction instruction, the startup is completed.

[0028] S2. Use the shooting probe to shoot an image of the titanium plate sample to be tested to obtain an original titanium plate image, wherein the shooting probe is installed directly above the titanium plate sample to be tested, and the shooting probe is connected to the probe bracket.

[0029] It is understandable that the original titanium plate image refers to the image of the titanium plate sample to be tested obtained by photographing with a photographing probe. When the photographing probe is started, it is necessary to adjust the position according to the position of the titanium plate sample to be tested in the titanium plate defect analysis platform so that the photographing probe can capture a complete image of the titanium plate sample to be tested, wherein the position adjustment method is to change the height or direction of the probe bracket connected to the photographing probe to change the height and direction of the photographing probe, and the adjustment of the connecting probe can be manual or adjusted using a pre-set program.

[0030] For example, when the shooting probe is started, Xiao Zhang adjusts the connecting bracket according to the position of the titanium plate sample to be tested, and observes the position of the titanium plate sample to be tested in the shooting probe. When Xiao Zhang observes that the titanium plate sample to be tested can appear completely and clearly in the shooting probe, he fixes the connecting bracket and the shooting probe, and issues a shooting command. After receiving the shooting command, the shooting probe shoots the titanium plate sample to be tested and obtains multiple images. Xiao Zhang selects the clearest image from the multiple images as the original titanium plate image.

[0031] S3. After the original titanium plate image is obtained, the acoustic wave probe is started and the acoustic wave probe is used to perform acoustic wave monitoring on the titanium plate sample to be tested to obtain an original acoustic wave signal set, wherein the acoustic wave probe is connected to the gel coupling agent, and the other end of the gel coupling agent is connected to the titanium plate sample to be tested.

[0032] It can be understood that the original acoustic wave signal set refers to the acoustic wave electrical signal received by the acoustic wave probe from the titanium plate sample to be tested. The original acoustic wave signal groups in the original acoustic wave signal set are sorted according to the time of acquisition, and the original acoustic wave signal set contains the signal size of the original acoustic wave signal. Since the acoustic wave probe receives an electrical signal, the signal size is a voltage amplitude.

[0033] In detail, the method of using the acoustic wave probe to perform acoustic wave monitoring on the titanium plate sample to be tested to obtain an original acoustic wave signal group set includes: dividing the titanium plate sample to be tested into detection areas to obtain a titanium plate detection area set, and sequentially extracting titanium plate detection areas in the titanium plate detection area set, wherein different titanium plate detection areas in the titanium plate detection area set overlap in space; according to a preset detection acoustic wave amplitude, using the acoustic wave probe to transmit acoustic waves to the titanium plate detection area, and waiting for the titanium plate sample to be tested to reflect acoustic waves to the acoustic wave probe; after receiving the reflected acoustic wave reflected by the titanium plate sample to be tested, , record the reflection time of the reflected sound wave and identify the reflection amplitude of the reflected sound wave, wherein the reflection time is the time difference between the moment when the sound wave probe transmits the sound wave and the moment when the reflected sound wave is received; perform key-value pairing on the reflected sound wave, the reflection time and the reflected signal to obtain an original sound wave signal group, and return to the step of emitting sound waves to the titanium plate detection area using the sound wave probe according to the preset detection sound wave amplitude, until the number of the obtained original sound wave signal groups is not less than the preset reference sound wave number; summarize the original sound wave signal groups to obtain an original sound wave signal group set.

[0034] It can be understood that the titanium plate detection area set refers to the set of titanium plate samples to be tested after division, wherein the division method is artificial division, the detection sound wave amplitude refers to the artificially set sound wave voltage size, the sound wave probe will transmit sound waves to the titanium plate detection area with the detection sound wave amplitude, and the reflected sound wave refers to the first time the sound wave probe receives the sound wave from the titanium plate detection area after receiving the reflected sound wave last time. If the sound wave probe has not received any reflected sound waves from the titanium plate detection area before, then the reflected sound wave refers to the first sound wave received from the titanium plate detection area after the sound wave probe transmits the sound wave to the titanium plate detection area. The reflection time refers to the time difference between the moment when the sound wave probe transmits the detection sound wave and the moment when the reflected sound wave is received, and the reflected amplitude refers to the voltage size of the reflected sound wave. The reference sound wave number is an artificially set constant.

[0035] Exemplarily, after completing the acquisition of the original titanium plate image, Xiao Zhang selects multiple titanium plate detection areas on the titanium plate sample to be tested, and applies gel coupling agent on one of the titanium plate detection areas, and places the acoustic wave probe on the titanium plate detection area, sets the reference acoustic wave number to 10, starts the acoustic wave probe and uses the acoustic wave probe to emit acoustic waves to the titanium plate detection area, and after 0.1s, the acoustic wave probe receives the reflected acoustic wave reflected by the titanium plate detection area, that is, the reflection time is 0.1s, and the electrical signal size of the reflected acoustic wave is 1V, that is, the reflection amplitude is 1V, and the reflection time, reflection amplitude and reflected acoustic wave are key-paired to obtain the original acoustic wave signal group, and the above steps are repeated until the number of original acoustic wave signal groups obtained is 10, at which time the acoustic wave probe is moved to another adjacent titanium plate detection area, and the acoustic wave detection is continued until all titanium plate detection areas are inspected.

[0036] S4. Perform internal damage analysis on the titanium plate according to the original acoustic wave signal set to obtain an original damage progression factor.

[0037] It can be understood that the original damage progress factor refers to a numerical value used to represent the degree of damage in the titanium plate sample to be tested. When the acoustic wave probe transmits the acoustic wave to the titanium plate sample to be tested, the acoustic wave will be transmitted in the titanium plate sample to be tested. When encountering an obstacle, it will be reflected, and the reflected sound wave will be received by the acoustic wave probe. The obstacle is, for example, cracks inside the titanium plate sample to be tested. The more cracks there are in the titanium plate sample to be tested, the more obstacles the acoustic wave will encounter when transmitting in the titanium plate sample to be tested. These obstacles will further disperse the energy of the acoustic wave, making the amplitude of the returned acoustic wave smaller than that when it was transmitted. Therefore, the damage analysis of the inside of the titanium plate can be performed through the original acoustic wave signal set to obtain the original damage progress factor.

[0038] In detail, the internal damage analysis of the titanium plate is performed according to the original acoustic wave signal set to obtain the original damage process factor, including: classifying the detection area in the original acoustic wave signal set to obtain multiple same-family acoustic wave signal sets, wherein the same-family acoustic wave signal sets in the same same-family acoustic wave signal set are from the same titanium plate detection area; performing the following operations on each of the multiple same-family acoustic wave signal sets: sequentially extracting the same-family acoustic wave signal sets in the same-family acoustic wave signal set to obtain the same-family reflection duration and the same-family reflection amplitude of the same-family acoustic wave signal set; judging whether the same-family reflection amplitude is within a preset standard reflection amplitude range; if the same-family reflection amplitude is within the standard reflection amplitude range, recording the same-family reflection amplitude as the effective reflection amplitude; If the same-family reflection amplitude is not within the standard reflection amplitude range, it is determined whether the same-family reflection duration is less than the preset standard reflection duration; if the same-family reflection duration is less than the standard reflection duration, the post-position sound wave signal group of the same-family sound wave signal group is obtained in the same-family sound wave signal group set, and the post-position reflection amplitude of the post-position sound wave signal group is extracted; then according to the post-position reflection amplitude and the same-family reflection amplitude, the effective reflection amplitude is calculated, wherein the effective reflection amplitude is the sum of the post-position reflection amplitude and the same-family reflection amplitude; the effective reflection amplitude is summarized to obtain an effective reflection amplitude set, and the average effective amplitude of the effective reflection amplitude set is calculated, and the original damage factor is calculated according to the average effective amplitude and the detected sound wave amplitude, wherein the average effective amplitude and the original damage factor are respectively expressed as: ,in, represents the average effective amplitude, Represents the number of effective reflection amplitudes in the effective reflection amplitude set, represents the i-th effective reflection amplitude, represents the original damage factor, Indicates the detected sound wave amplitude, represents the absolute value symbol; summing up the original damage factors to obtain an original damage factor set, extracting the maximum damage factor in the original damage factor set, and using the maximum damage factor as the original damage process factor.

[0039] It is understandable that the same family reflection duration refers to the reflection duration in the same family sound wave signal group, the same family reflection amplitude refers to the reflection amplitude in the same family sound wave signal group, and the standard reflection amplitude range refers to the artificially set reflection amplitude range. The setting of the standard reflection amplitude range is to filter the noise in the process of the sound wave probe receiving the reflected sound wave. The sound wave signal amplitude generated by these noises is often not within the standard reflection amplitude range. The standard emission amplitude range can be obtained by the pre-experiment. The post-position sound wave signal group refers to the original sound wave signal group adjacent to the same family sound wave signal group in the acquisition time. For example, a is the same family sound wave signal group, and the original sound wave signal group obtained for the first time after obtaining a is b, then b is the post-position sound wave signal group of the same family sound wave signal group.

[0040] It should be explained that the post-reflection amplitude refers to the reflection amplitude in the post-reflection sound wave signal group, and the standard reflection duration refers to an artificially set time interval. When the same-family reflection duration is extremely small, it means that the interval between the same-family reflection amplitude and the post-reflection amplitude is extremely close, and they can be regarded as being reflected by the same obstacle. Therefore, the same-family reflection amplitude and the post-reflection amplitude at this time can be superimposed to obtain the effective reflection amplitude.

[0041] S5, performing grayscale enhancement conversion on the original titanium plate image to obtain a grayscale titanium plate image, and performing crack identification in the grayscale titanium plate image to obtain a titanium plate crack group.

[0042] It can be understood that the grayscale titanium plate image refers to the original titanium plate image after grayscale conversion, and the titanium plate crack group refers to the set of fine cracks on the titanium plate sample to be tested after crack identification.

[0043] In detail, the grayscale enhancement conversion of the original titanium plate image to obtain the grayscale titanium plate image includes: extracting original titanium plate pixels in the original titanium plate image in sequence, obtaining RGB pixel values ​​of the original titanium plate pixels, and grayscale conversion of the RGB pixel values ​​according to preset red coefficients, green coefficients, and blue coefficients to obtain grayscale pixel values, wherein the RGB pixel values ​​and the grayscale pixel values ​​are respectively expressed as: ,in, Represents RGB pixel value, represents the red pixel value, represents the green pixel value, represents the blue pixel value, represents the grayscale pixel value, represents the red coefficient, represents the green coefficient, Represents a blue coefficient; summarizes the grayscale pixel values ​​to obtain a grayscale pixel value set, draws a grayscale histogram of the grayscale pixel value set, and sets grayscale frequency maximums, wherein the grayscale frequency maximums are the maximum frequency and the minimum frequency; according to the grayscale histogram, grayscale enhancement is performed on the original titanium plate image to obtain a grayscale titanium plate image.

[0044] It should be explained that the red coefficient, green coefficient and blue coefficient refer to the sensitivity coefficients of the human eye to red, green and blue respectively, which are used to calculate the gray value of the pixel point. The red coefficient, green coefficient and blue coefficient can be obtained by consulting relevant literature, or can be set manually. The grayscale histogram refers to an image used to represent the frequency of occurrence of grayscale pixel values. In the grayscale histogram, the horizontal axis represents the grayscale pixel value, and the vertical axis represents the frequency of occurrence of the grayscale pixel value corresponding to the horizontal axis in the grayscale pixel value set. The maximum frequency and minimum frequency refer to the maximum occurrence frequency and minimum occurrence frequency of the grayscale pixel value set manually, respectively. The setting of the maximum frequency and the minimum frequency can determine the grayscale complexity of the grayscale titanium plate image, and the maximum frequency does not exceed the maximum vertical axis value in the grayscale histogram, and the minimum frequency does not exceed the minimum vertical axis value in the grayscale histogram.

[0045] In detail, the grayscale enhancement of the original titanium plate image is performed according to the grayscale histogram to obtain a grayscale titanium plate image, including: extracting grayscale pixel values ​​in the grayscale pixel value set in turn to obtain grayscale pixel points of the grayscale pixel values, identifying the grayscale frequency of the grayscale pixel values ​​in the grayscale histogram, and judging whether the grayscale frequency is less than the maximum frequency; if the grayscale frequency is not less than the maximum frequency, updating the grayscale pixel value with a preset maximum pixel value to obtain an updated pixel value, and updating the grayscale pixel point with the updated pixel value to obtain an updated pixel point; if the grayscale frequency is less than the maximum frequency, judging Determine whether the grayscale frequency is greater than the minimum frequency; if the grayscale frequency is not greater than the minimum frequency, update the grayscale pixel value with a preset minimum pixel value to obtain an updated pixel value, and update the grayscale pixel point with the updated pixel value to obtain an updated pixel point; if the grayscale frequency is greater than the minimum frequency, update the grayscale pixel value in frequency proportion to obtain an updated pixel value, and update the grayscale pixel point with the updated pixel value to obtain an updated pixel point; summarize the updated pixel points to obtain an updated pixel point set, and use the updated pixel point set to update the original titanium plate image to obtain a grayscale titanium plate image.

[0046] It can be understood that the grayscale frequency refers to the vertical coordinate of the grayscale pixel value in the grayscale histogram, and the maximum pixel value and the minimum pixel value both refer to artificially set constants.

[0047] In detail, the grayscale pixel value is updated in frequency ratio to obtain an updated pixel value, including: updating the grayscale pixel value according to the grayscale frequency, the minimum pixel value, the maximum pixel value, the minimum frequency and the maximum frequency to obtain an updated pixel value, wherein the updated pixel value is expressed as: ,in, Indicates updating pixel value, represents the grayscale frequency, represents the minimum frequency, represents the maximum pixel value, represents the minimum pixel value, Indicates the maximum frequency.

[0048] It should be explained that the proportion update refers to the process of recalculating the grayscale pixel value using the difference ratio between the grayscale frequency and the minimum frequency and the maximum frequency.

[0049] In detail, the method of performing crack identification in the grayscale titanium plate image to obtain a titanium plate crack group set includes: performing noise filtering on the grayscale titanium plate image to obtain a denoised titanium plate image, wherein the noise filtering method is a Gaussian filtering method; using a preset morphological gradient transformation method to perform morphological gradient transformation on the denoised titanium plate image to obtain a cracked titanium plate image, performing crack extraction on the cracked titanium plate image to obtain an original crack set, wherein the cracked titanium plate image contains a clear crack image; extracting original cracks in the original crack set in turn, identifying the original crack length of the original crack, performing key-value pairing on the original crack length and the original crack to obtain a titanium plate crack group, and summarizing the titanium plate crack groups to obtain a titanium plate crack group set.

[0050] It can be understood that the denoised titanium plate image refers to a grayscale titanium plate image after noise filtering, the morphological gradient change method refers to an image processing technology used to enhance image edge features, and the cracked titanium plate image refers to a denoised titanium plate image after morphological gradient transformation. In this cracked titanium plate image, the titanium plate crack will appear brighter so that the titanium plate crack can be identified.

[0051] S6. Perform image segmentation on the grayscale titanium plate image according to the titanium plate crack group set to obtain a segmented titanium plate image set, wherein the number of segmented titanium plate images in the segmented titanium plate image set is the same as the number of titanium plate crack groups in the titanium plate crack group set, and different segmented titanium plate images may overlap in space.

[0052] It should be explained that the segmented titanium plate image set refers to a set of grayscale titanium plate images after image segmentation, wherein the segmented titanium plate image is a rectangular image, and each segmented titanium plate image contains at least one titanium plate crack. If multiple titanium plate cracks intersect with each other, the segmented titanium plate image contains at least one complete titanium plate crack.

[0053] S7. Extract grayscale features of the titanium plate based on the segmented titanium plate image set to obtain grayscale feature values ​​of the titanium plate, and perform surface defect weighting on the original damage progression factor according to the titanium plate crack group set to obtain a target damage progression factor, wherein the target damage progression factor includes: an expansion damage progression factor and a reduction damage progression factor.

[0054] It can be understood that the titanium plate grayscale feature value refers to the numerical value used to represent the grayscale feature in the grayscale titanium plate image. Since there are multiple titanium plate cracks in the grayscale titanium plate image, and the lengths of different titanium plate cracks are different, their grayscale value changes for the segmented titanium plate image are different. Therefore, it is necessary to perform grayscale value analysis on each segmented titanium plate image, and weight the grayscale features of the entire grayscale titanium plate image according to the analysis results, so as to obtain the titanium plate grayscale feature value of the entire grayscale titanium plate image.

[0055] It can be understood that the target damage progression factor refers to a numerical value used to represent the degree of damage inside the titanium plate sample to be tested. The difference between the target damage progression factor and the original damage progression factor is that the original damage progression factor is only obtained through ultrasonic detection, while the target damage progression factor is obtained after combining the surface defect analysis of the titanium plate sample to be tested.

[0056] In detail, the grayscale feature extraction of the titanium plate based on the segmented titanium plate image set to obtain the grayscale feature value of the titanium plate includes: extracting the segmented titanium plate images in the segmented titanium plate image set in sequence, identifying the number of cracks in the segmented titanium plate images, extracting the segmented pixel point set of the segmented titanium plate images, and obtaining the segmented grayscale value set corresponding to the segmented pixel point set; calculating the segmented grayscale difference of the segmented grayscale value set, wherein the segmented grayscale difference is expressed as: ,in, Represents the segmentation grayscale difference, Represents the number of segmentation gray values ​​in the segmentation gray value set, represents the jth segmentation grayscale value; the crack number and segmentation grayscale difference are summarized to obtain a crack number set and a segmentation grayscale difference set; according to the crack number set and the segmentation grayscale difference set, the grayscale characteristic value of the titanium plate is calculated using the following formula: ,in, represents the grayscale eigenvalue of the titanium plate, represents the number of segmented titanium plate images in the segmented titanium plate image set, Indicates Number of cracks, Indicates Number of cracks, Indicates Segmentation grayscale difference.

[0057] It can be understood that the number of cracks refers to the number of cracks in the titanium plate in the segmented titanium plate image, the segmented pixel point set refers to the set of all pixel points in the segmented titanium plate image, the segmented grayscale value set refers to the set of grayscale values ​​of each pixel point in the segmented pixel point set, and the segmented grayscale difference refers to the variance of all segmented grayscales in the segmented grayscale value set.

[0058] In detail, the surface defect weighting of the original damage progress factor according to the titanium plate crack group to obtain the target damage progress factor includes: obtaining the total length of the titanium plate cracks of the titanium plate crack group, and based on the original damage progress factor, querying the standard total crack length in the pre-constructed damage progress crack table, wherein the damage progress crack table is a relationship table between the damage progress factor and the crack length; judging whether the total length of the titanium plate cracks is greater than the standard total crack length; if the total length of the titanium plate cracks is greater than the standard total crack length, the original damage progress factor is processed by process expansion to obtain the expanded damage progress factor, wherein the expanded damage progress factor is expressed as: ,in, represents the factor for expanding the damage process, represents the original damage progression factor, represents the logarithmic function, represents the total length of the titanium plate crack, represents the total length of the standard crack; if the total length of the titanium plate crack is not greater than the total length of the standard crack, the original damage process factor is subjected to a process reduction process to obtain a reduced damage process factor, wherein the reduced damage process factor is expressed as: ,in, Represents the reduction of damage progression factor.

[0059] It should be explained that the total length of the titanium plate crack refers to the total length of all the titanium plate cracks in the titanium plate crack group, and its calculation method is to accumulate all the original crack lengths in the titanium plate crack group. The damage process crack table refers to the relationship table between the artificially set damage process and crack length, and the damage process crack table can be obtained through preliminary experiments. The standard total crack length refers to the crack length under the original damage process factor.

[0060] For example, Xiao Wang is an operator in a titanium plate processing plant. In order to obtain a damage process crack table of a certain model of titanium plate, Xiao Wang obtained a titanium plate of this model, detected the damage process of the titanium plate through an ultrasonic probe, and then used image recognition to detect the crack length of the titanium plate. He obtained a large number of the above-mentioned damage processes and crack lengths, and drew a damage process crack table of this model of titanium plate based on a large number of damage processes and crack lengths.

[0061] S8. The target damage process factor and the grayscale characteristic value of the titanium plate are transmitted to a pre-built titanium plate performance prediction platform, and based on the titanium plate performance prediction platform, the titanium plate tissue performance prediction based on the surface defect analysis is completed, wherein the titanium plate performance prediction platform has a built-in deep learning model for predicting the tissue performance of the titanium plate.

[0062] It can be understood that the titanium plate performance prediction platform refers to a data processing center that processes data on damage process factors and grayscale eigenvalues ​​of titanium plates, for example: a computer processing platform that includes a deep learning algorithm. The deep learning model has been trained with a large amount of damage process factor and titanium plate grayscale eigenvalue data. It can perform performance prediction on the titanium plate sample to be tested based on the input target damage process factor and titanium plate grayscale eigenvalue to obtain a performance prediction value. The deep learning model is, for example: a deep neural network, a random forest model, etc., wherein the performance prediction values ​​include: predicted hardness value, predicted toughness value and predicted conductivity value.

[0063] For example, Xiao Li is a technician in a titanium plate processing factory. One day, Xiao Li wants to build a deep learning model for a certain model of titanium plate. So Xiao Li obtains multiple groups of titanium plates of this model, and obtains multiple groups of target damage process factors and grayscale characteristic values ​​of titanium plates of this model through the titanium plate defect analysis platform. After a period of time, he measures their hardness values, toughness values ​​and conductivity values, marks the target damage process factors and grayscale characteristic values ​​of titanium plates with hardness values, toughness values ​​and conductivity values, and trains the selected deep learning network with the marked damage process factors and grayscale characteristic values ​​of titanium plates to obtain a deep learning model for predicting the microstructure properties of this model of titanium plates.

[0064] In order to solve the problem described in the background technology, the present invention first receives a titanium plate performance prediction instruction, starts a shooting probe based on the titanium plate performance prediction instruction, and uses the shooting probe to shoot an image of the titanium plate sample to be tested to obtain an original titanium plate image, completes the correct installation of the shooting probe and obtains the original image of the titanium plate sample to be tested, providing original conditions for subsequent surface defect analysis, and at the same time uses the shooting probe to shoot images to avoid direct contact with the titanium plate sample to be tested, so that the subsequent titanium plate tissue performance prediction has higher accuracy. After obtaining the original titanium plate image, the acoustic wave probe is started and the acoustic wave probe is used to perform acoustic wave monitoring on the titanium plate sample to be tested to obtain an original acoustic wave signal set. In this step, the original acoustic wave signals inside the titanium plate are obtained through acoustic wave monitoring. These signals can reflect the damage inside the titanium plate, providing data support for the subsequent titanium plate internal damage analysis. Then, the titanium plate internal damage analysis is performed according to the original acoustic wave signal set to obtain the original damage process factor. The calculation of the original damage process factor enables the internal damage of the titanium plate to have an intuitive representation of data, and then the original titanium plate image is grayscale enhanced and converted to obtain a grayscale titanium plate image, and then the grayscale titanium plate image is converted to grayscale. Crack identification is performed in the grayscale titanium plate image to obtain the titanium plate crack group set. This step completes the acquisition of surface cracks on the titanium plate sample to be tested, providing basic data for subsequent surface defect analysis. According to the titanium plate crack group set, the grayscale titanium plate image is segmented to obtain the segmented titanium plate image set, and the titanium plate grayscale feature extraction is performed based on the segmented titanium plate image set to obtain the titanium plate grayscale eigenvalue. The acquisition of the titanium plate grayscale eigenvalue makes the surface defects of the titanium plate sample to be tested have a numerical intuitive representation, which speeds up the process of predicting the microstructure and performance of the titanium plate. The original damage process factor is extracted through the titanium plate crack set. Surface defects are weighted to obtain the target damage process factor. This step combines the surface defects of the titanium plate sample to be tested with the internal damage, so that the obtained target damage process factor is more in line with the actual situation, and the accuracy of the prediction of the titanium plate structure performance is improved. Finally, the target damage process factor and the grayscale characteristic value of the titanium plate are transmitted to the titanium plate performance prediction platform. The titanium plate performance prediction platform is used to predict the titanium plate structure performance. By using the deep learning method to predict the titanium plate structure performance, the efficiency of the entire prediction is improved. At the same time, the support of big data also makes the prediction of the titanium plate structure performance more accurate. Therefore, the present invention can improve the accuracy and efficiency of the prediction of the titanium plate structure performance.

[0065] like Figure 2 , which is a functional module diagram of a titanium plate structure performance prediction system based on surface defect analysis provided by an embodiment of the present invention.

[0066] The titanium plate structure performance prediction system 100 based on surface defect analysis of the present invention can be installed in an electronic device. According to the functions implemented, the titanium plate structure performance prediction system 100 based on surface defect analysis can include an original image shooting module 101, a damage process calculation module 102, a titanium plate crack identification module 103 and a titanium plate performance prediction module 104. The module of the present invention can also be called a unit, which refers to a series of computer program segments that can be executed by an electronic device processor and can complete fixed functions, which are stored in the memory of the electronic device.

[0067] The original image shooting module 101 is used to receive a titanium plate performance prediction instruction, and start a shooting probe based on the titanium plate performance prediction instruction, wherein the shooting probe is installed in a titanium plate defect analysis platform, and the titanium plate defect analysis platform also includes: a probe bracket, a titanium plate sample to be tested, a gel coupling agent and an acoustic wave probe, and the shooting probe is used to shoot an image of the titanium plate sample to be tested to obtain an original titanium plate image, wherein the shooting probe is installed directly above the titanium plate sample to be tested, and the shooting probe is connected to the probe bracket; the damage process calculation module 102 is used to start the acoustic wave probe after the original titanium plate image is acquired and use the acoustic wave probe to perform acoustic wave monitoring on the titanium plate sample to be tested to obtain an original acoustic wave signal set, wherein the acoustic wave probe is connected to the gel coupling agent, and the other end of the gel coupling agent is connected to the titanium plate sample to be tested, and the internal damage analysis of the titanium plate is performed according to the original acoustic wave signal set to obtain an original damage process factor; the titanium plate crack identification module 103 is used to perform grayscale enhancement conversion on the original titanium plate image to obtain a grayscale image. a titanium plate image, performing crack identification in the grayscale titanium plate image to obtain a titanium plate crack group set, performing image segmentation on the grayscale titanium plate image according to the titanium plate crack group set to obtain a segmented titanium plate image set, wherein the number of segmented titanium plate images in the segmented titanium plate image set is the same as the number of titanium plate crack groups in the titanium plate crack group set, and different segmented titanium plate images may overlap in space; the titanium plate performance prediction module 104 is used to extract grayscale features of the titanium plate based on the segmented titanium plate image set to obtain a grayscale eigenvalue of the titanium plate, performing surface defect weighting on the original damage process factor according to the titanium plate crack group set to obtain a target damage process factor, wherein the target damage process factor includes: an expansion damage process factor and a reduction damage process factor, transmitting the target damage process factor and the titanium plate grayscale eigenvalue to a pre-constructed titanium plate performance prediction platform, and completing the titanium plate tissue performance prediction based on the surface defect analysis based on the titanium plate performance prediction platform, wherein the titanium plate performance prediction platform has a built-in deep learning model for predicting the tissue performance of the titanium plate.

[0068] In detail, the modules in the titanium plate structure performance prediction system 100 based on surface defect analysis in the embodiment of the present invention are used in the same manner as described above. Figure 1 The same technical means are used as the titanium plate microstructure performance prediction method based on surface defect analysis described in the text, and can produce the same technical effects, so they will not be repeated here.

[0069] like Figure 3 , which is a schematic diagram of the structure of an electronic device for implementing a method for predicting titanium plate structure properties based on surface defect analysis provided by an embodiment of the present invention.

[0070] The electronic device 1 may include a processor 10, a memory 11 and a bus 12, and may also include a computer program stored in the memory 11 and executable on the processor 10, such as a titanium plate structure performance prediction method program based on surface defect analysis.

[0071] Among them, the memory 11 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, mobile hard disk, multimedia card, card-type memory (for example: SD or DX memory, etc.), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 11 can be an internal storage unit of the electronic device 1, such as a mobile hard disk of the electronic device 1. In other embodiments, the memory 11 can also be an external storage device of the electronic device 1, such as a plug-in mobile hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device 1. Further, the memory 11 also includes an internal storage unit of the electronic device 1 and an external storage device. The memory 11 can not only be used to store application software and various types of data installed in the electronic device 1, such as the code of the titanium plate structure performance prediction method program based on surface defect analysis, but also can be used to temporarily store data that has been output or is to be output.

[0072] In some embodiments, the processor 10 may be composed of an integrated circuit, for example, a single packaged integrated circuit, or a plurality of packaged integrated circuits with the same or different functions, including one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and combinations of various control chips, etc. The processor 10 is the control core (Control Unit) of the electronic device, and uses various interfaces and lines to connect various components of the entire electronic device, and executes or executes programs or modules stored in the memory 11 (such as a titanium plate structure performance prediction method program based on surface defect analysis, etc.), and calls data stored in the memory 11 to execute various functions of the electronic device 1 and process data.

[0073] The bus 12 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus 12 may be divided into an address bus, a data bus, a control bus, etc. The bus 12 is configured to realize connection and communication between the memory 11 and at least one processor 10, etc.

[0074] Figure 3 Only an electronic device with components is shown, and those skilled in the art will understand that Figure 3 The structure shown does not constitute a limitation on the electronic device 1, and may include fewer or more components than shown in the figure, or combine certain components, or arrange the components differently.

[0075] For example, although not shown, the electronic device 1 may also include a power source (such as a battery) for supplying power to various components. Preferably, the power source may be logically connected to the at least one processor 10 through a power management system, so that the power management system can realize functions such as charging management, discharging management, and power consumption management. The power source may also include any components such as one or more DC or AC power sources, recharging systems, power failure detection circuits, power converters or inverters, and power status indicators. The electronic device 1 may also include a variety of sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be repeated here.

[0076] Furthermore, the electronic device 1 may also include a network interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is generally used to establish a communication connection between the electronic device 1 and other electronic devices.

[0077] Optionally, the electronic device 1 may further include a user interface, which may be a display, an input unit (such as a keyboard), or a standard wired interface or a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, and an OLED (Organic Light-Emitting Diode) touch device. The display may also be appropriately referred to as a display screen or a display unit, which is used to display information processed in the electronic device 1 and to display a visual user interface.

[0078] The titanium plate structure performance prediction method program based on surface defect analysis stored in the memory 11 in the electronic device 1 is a combination of multiple instructions. When running in the processor 10, it can achieve: receiving a titanium plate performance prediction instruction, starting a shooting probe based on the titanium plate performance prediction instruction, wherein the shooting probe is installed in a titanium plate defect analysis platform, and the titanium plate defect analysis platform also includes: a probe bracket, a titanium plate sample to be tested, a gel coupling agent and an acoustic wave probe; using the shooting probe to shoot an image of the titanium plate sample to be tested to obtain an original titanium plate image, wherein the shooting probe is installed directly above the titanium plate sample to be tested, and the shooting probe is connected to the probe bracket; after obtaining the original titanium plate image, starting the acoustic wave probe and using the acoustic wave probe to perform acoustic wave monitoring on the titanium plate sample to be tested to obtain an original acoustic wave signal set, wherein the acoustic wave probe is connected to the gel coupling agent, and the other end of the gel coupling agent is connected to the titanium plate sample to be tested; performing internal damage analysis of the titanium plate according to the original acoustic wave signal set to obtain an original damage process factor; The original titanium plate image is subjected to grayscale enhancement conversion to obtain a grayscale titanium plate image, crack identification is performed in the grayscale titanium plate image to obtain a titanium plate crack group set; according to the titanium plate crack group set, the grayscale titanium plate image is segmented to obtain a segmented titanium plate image set, wherein the number of segmented titanium plate images in the segmented titanium plate image set is the same as the number of titanium plate crack groups in the titanium plate crack group set, and different segmented titanium plate images may overlap in space; grayscale feature extraction of the titanium plate is performed based on the segmented titanium plate image set to obtain a grayscale eigenvalue of the titanium plate, surface defect weighting is performed on the original damage process factor according to the titanium plate crack group set to obtain a target damage process factor, wherein the target damage process factor includes: an expansion damage process factor and a reduction damage process factor; the target damage process factor and the titanium plate grayscale eigenvalue are transmitted to a pre-built titanium plate performance prediction platform, and based on the titanium plate performance prediction platform, the titanium plate microstructure performance prediction based on surface defect analysis is completed, wherein the titanium plate performance prediction platform has a built-in deep learning model for microstructure performance prediction of titanium plates.

[0079] Specifically, the specific implementation method of the processor 10 for the above instructions can refer to Figures 1 to 3 The description of the relevant steps in the corresponding embodiments will not be repeated here.

[0080] Furthermore, if the module / unit integrated in the electronic device 1 is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. The computer-readable storage medium can be volatile or non-volatile. For example, the computer-readable medium can include: any entity or system that can carry the computer program code, a recording medium, a USB flash drive, a mobile hard disk, a magnetic disk, an optical disk, a computer memory, and a read-only memory (ROM).

[0081] The present invention also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor of an electronic device, it can achieve: receiving a titanium plate performance prediction instruction, starting a shooting probe based on the titanium plate performance prediction instruction, wherein the shooting probe is installed in a titanium plate defect analysis platform, and the titanium plate defect analysis platform also includes: a probe bracket, a titanium plate sample to be tested, a gel coupling agent and an acoustic wave probe; using the shooting probe to shoot an image of the titanium plate sample to be tested to obtain an original titanium plate image, wherein the shooting probe is installed directly above the titanium plate sample to be tested, and the shooting probe is connected to the probe bracket; after obtaining the original titanium plate image, starting the acoustic wave probe and using the acoustic wave probe to perform acoustic wave monitoring on the titanium plate sample to be tested to obtain an original acoustic wave signal set, wherein the acoustic wave probe is connected to the gel coupling agent, and the other end of the gel coupling agent is connected to the titanium plate sample to be tested; performing internal damage analysis of the titanium plate according to the original acoustic wave signal set to obtain an original damage process factor; and using the original titanium plate to shoot an image of the titanium plate sample to be tested to obtain an original damage process factor. The plate image is subjected to grayscale enhancement conversion to obtain a grayscale titanium plate image, cracks are identified in the grayscale titanium plate image to obtain a titanium plate crack group set; according to the titanium plate crack group set, the grayscale titanium plate image is segmented to obtain a segmented titanium plate image set, wherein the number of segmented titanium plate images in the segmented titanium plate image set is the same as the number of titanium plate crack groups in the titanium plate crack group set, and different segmented titanium plate images may overlap in space; grayscale feature extraction of the titanium plate is performed based on the segmented titanium plate image set to obtain a grayscale feature value of the titanium plate, surface defect weighting is performed on the original damage process factor according to the titanium plate crack group set to obtain a target damage process factor, wherein the target damage process factor includes: an expansion damage process factor and a reduction damage process factor; the target damage process factor and the titanium plate grayscale feature value are transmitted to a pre-built titanium plate performance prediction platform, and based on the titanium plate performance prediction platform, the titanium plate microstructure performance prediction based on surface defect analysis is completed, wherein the titanium plate performance prediction platform has a built-in deep learning model for microstructure performance prediction of titanium plates.

[0082] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, systems and methods can be implemented in other ways. For example, the system embodiments described above are only illustrative, and actual implementation may have other division methods.

[0083] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0084] In addition, each functional module in each embodiment of the present invention may be integrated into one processing unit, each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0085] It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0086] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention.

Claims

1. A method for predicting the microstructure and properties of titanium plates based on surface defect analysis, characterized in that: The method comprises: receiving a titanium plate performance prediction instruction, starting a shooting probe based on the titanium plate performance prediction instruction, wherein the shooting probe is installed in a titanium plate defect analysis platform, and the titanium plate defect analysis platform further comprises: a probe bracket, a titanium plate sample to be tested, a gel coupling agent and an acoustic wave probe; using the shooting probe to shoot an image of the titanium plate sample to be tested to obtain an original titanium plate image, wherein the shooting probe is installed directly above the titanium plate sample to be tested, and the shooting probe is connected to the probe bracket; after obtaining the original titanium plate image, starting the acoustic wave probe and using the acoustic wave probe to perform acoustic wave monitoring on the titanium plate sample to be tested to obtain an original acoustic wave signal set, wherein the acoustic wave probe is connected to the gel coupling agent, and the other end of the gel coupling agent is connected to the titanium plate sample to be tested; performing internal damage analysis on the titanium plate according to the original acoustic wave signal set to obtain an original damage process factor; performing grayscale enhancement conversion on the original titanium plate image to obtain a grayscale titanium plate image, and performing grayscale titanium plate image acquisition on the grayscale titanium plate image. Crack identification is performed in the plate image to obtain a titanium plate crack group set; based on the titanium plate crack group set, the grayscale titanium plate image is segmented to obtain a segmented titanium plate image set, wherein the number of segmented titanium plate images in the segmented titanium plate image set is the same as the number of titanium plate crack groups in the titanium plate crack group set, and different segmented titanium plate images may overlap in space; grayscale feature extraction of the titanium plate is performed based on the segmented titanium plate image set to obtain a titanium plate grayscale eigenvalue, and surface defect weighting is performed on the original damage process factor according to the titanium plate crack group set to obtain a target damage process factor, wherein the target damage process factor includes: an expansion damage process factor and a reduction damage process factor; the target damage process factor and the titanium plate grayscale eigenvalue are transmitted to a pre-built titanium plate performance prediction platform, and based on the titanium plate performance prediction platform, the titanium plate tissue performance prediction based on surface defect analysis is completed, wherein the titanium plate performance prediction platform has a built-in deep learning model for predicting the tissue performance of the titanium plate.

2. The titanium plate microstructure and performance prediction method based on surface defect analysis according to claim 1, characterized in that: The method uses the acoustic wave probe to perform acoustic wave monitoring on the titanium plate sample to be tested to obtain an original acoustic wave signal group set, including: dividing the titanium plate sample to be tested into detection areas to obtain a titanium plate detection area set, and sequentially extracting titanium plate detection areas in the titanium plate detection area set, wherein different titanium plate detection areas in the titanium plate detection area set overlap in space; according to a preset detection acoustic wave amplitude, using the acoustic wave probe to transmit acoustic waves to the titanium plate detection area, and waiting for the titanium plate sample to be tested to reflect acoustic waves to the acoustic wave probe; after receiving the reflected acoustic wave reflected by the titanium plate sample to be tested, recording Record the reflection duration of the reflected sound wave and identify the reflection amplitude of the reflected sound wave, wherein the reflection duration is the time difference between the moment when the sound wave probe transmits the sound wave and the moment when the reflected sound wave is received; perform key-value pairing on the reflected sound wave, the reflection duration and the reflected signal to obtain an original sound wave signal group, and return to the step of emitting sound waves to the titanium plate detection area using the sound wave probe according to the preset detection sound wave amplitude, until the number of the obtained original sound wave signal groups is not less than the preset reference sound wave number; summarize the original sound wave signal groups to obtain an original sound wave signal group set.

3. The titanium plate microstructure and performance prediction method based on surface defect analysis according to claim 2, characterized in that: The method of analyzing the internal damage of the titanium plate according to the original acoustic wave signal set to obtain the original damage process factor includes: classifying the detection area in the original acoustic wave signal set to obtain multiple acoustic wave signal sets of the same family, wherein the acoustic wave signal groups of the same family in the same acoustic wave signal set are from the same titanium plate detection area; performing the following operations on each of the multiple acoustic wave signal sets of the same family: extracting the acoustic wave signal groups of the same family in the acoustic wave signal set in turn to obtain the same reflection duration and the same reflection amplitude of the same family of acoustic wave signal groups; judging whether the same reflection amplitude is within a preset standard reflection amplitude range; if the same reflection amplitude is within the standard reflection amplitude range, recording the same reflection amplitude as the effective reflection amplitude; if the If the same-family reflection amplitude is not within the standard reflection amplitude range, it is determined whether the same-family reflection duration is less than the preset standard reflection duration; if the same-family reflection duration is less than the standard reflection duration, the post-position sound wave signal group of the same-family sound wave signal group is obtained in the same-family sound wave signal group set, and the post-position reflection amplitude of the post-position sound wave signal group is extracted; then according to the post-position reflection amplitude and the same-family reflection amplitude, the effective reflection amplitude is calculated, wherein the effective reflection amplitude is the sum of the post-position reflection amplitude and the same-family reflection amplitude; the effective reflection amplitude is summarized to obtain an effective reflection amplitude set, and the average effective amplitude of the effective reflection amplitude set is calculated, and the original damage factor is calculated according to the average effective amplitude and the detected sound wave amplitude, wherein the average effective amplitude and the original damage factor are respectively expressed as: ,in, represents the average effective amplitude, Represents the number of effective reflection amplitudes in the effective reflection amplitude set, represents the i-th effective reflection amplitude, represents the original damage factor, Indicates the detected sound wave amplitude, represents the absolute value symbol; summing up the original damage factors to obtain an original damage factor set, extracting the maximum damage factor in the original damage factor set, and using the maximum damage factor as the original damage process factor.

4. The titanium plate microstructure and performance prediction method based on surface defect analysis according to claim 3, characterized in that: The grayscale enhancement conversion of the original titanium plate image to obtain the grayscale titanium plate image includes: extracting original titanium plate pixels in the original titanium plate image in sequence, obtaining RGB pixel values ​​of the original titanium plate pixels, and grayscale conversion of the RGB pixel values ​​according to preset red coefficients, green coefficients, and blue coefficients to obtain grayscale pixel values, wherein the RGB pixel values ​​and the grayscale pixel values ​​are respectively expressed as: ,in, Represents RGB pixel value, represents the red pixel value, represents the green pixel value, represents the blue pixel value, represents the grayscale pixel value, represents the red coefficient, represents the green coefficient, Represents a blue coefficient; summarizes the grayscale pixel values ​​to obtain a grayscale pixel value set, draws a grayscale histogram of the grayscale pixel value set, and sets grayscale frequency maximums, wherein the grayscale frequency maximums are the maximum frequency and the minimum frequency; according to the grayscale histogram, grayscale enhancement is performed on the original titanium plate image to obtain a grayscale titanium plate image.

5. The titanium plate microstructure and performance prediction method based on surface defect analysis according to claim 4, characterized in that: The grayscale enhancement of the original titanium plate image is performed according to the grayscale histogram to obtain a grayscale titanium plate image, including: extracting grayscale pixel values ​​in the grayscale pixel value set in turn, obtaining grayscale pixel points of the grayscale pixel values, identifying the grayscale frequency of the grayscale pixel values ​​in the grayscale histogram, and judging whether the grayscale frequency is less than the maximum frequency; if the grayscale frequency is not less than the maximum frequency, updating the grayscale pixel value with a preset maximum pixel value to obtain an updated pixel value, and updating the grayscale pixel point with the updated pixel value to obtain an updated pixel point; if the grayscale frequency is less than the maximum frequency, judging Whether the grayscale frequency is greater than the minimum frequency; if the grayscale frequency is not greater than the minimum frequency, the grayscale pixel value is updated by using the preset minimum pixel value to obtain the updated pixel value, and the grayscale pixel point is updated by using the updated pixel value to obtain the updated pixel point; if the grayscale frequency is greater than the minimum frequency, the grayscale pixel value is updated in frequency proportion to obtain the updated pixel value, and the grayscale pixel point is updated by using the updated pixel value to obtain the updated pixel point; the updated pixel points are summarized to obtain an updated pixel point set, and the original titanium plate image is updated by using the updated pixel point set to obtain a grayscale titanium plate image.

6. The titanium plate microstructure and performance prediction method based on surface defect analysis according to claim 5, characterized in that: The updating of the grayscale pixel value by frequency ratio to obtain an updated pixel value includes: updating the grayscale pixel value according to the grayscale frequency, the minimum pixel value, the maximum pixel value, the minimum frequency and the maximum frequency to obtain an updated pixel value, wherein the updated pixel value is expressed as: ,in, Indicates updating pixel value. represents the grayscale frequency, represents the minimum frequency, represents the maximum pixel value, represents the minimum pixel value, Indicates the maximum frequency.

7. The titanium plate microstructure and performance prediction method based on surface defect analysis according to claim 6, characterized in that: The method of performing crack identification in the grayscale titanium plate image to obtain a titanium plate crack group set includes: performing noise filtering on the grayscale titanium plate image to obtain a denoised titanium plate image, wherein the noise filtering method is a Gaussian filtering method; performing morphological gradient transformation on the denoised titanium plate image using a preset morphological gradient transformation method to obtain a cracked titanium plate image, performing crack extraction in the cracked titanium plate image to obtain an original crack set, wherein the cracked titanium plate image contains a clear crack image; extracting original cracks in the original crack set in turn, identifying the original crack length of the original crack, performing key-value pairing on the original crack length and the original crack to obtain a titanium plate crack group, and summarizing the titanium plate crack groups to obtain a titanium plate crack group set.

8. The titanium plate microstructure and performance prediction method based on surface defect analysis according to claim 7, characterized in that: The method of extracting grayscale features of titanium plates based on the segmented titanium plate image set to obtain grayscale feature values ​​of titanium plates includes: extracting segmented titanium plate images in the segmented titanium plate image set in sequence, identifying the number of cracks in the segmented titanium plate images, extracting segmented pixel point sets of the segmented titanium plate images, and obtaining segmented grayscale value sets corresponding to the segmented pixel point sets; and calculating the segmented grayscale difference of the segmented grayscale value set, wherein the segmented grayscale difference is expressed as: ,in, Represents the segmentation grayscale difference, Represents the number of segmentation grayscale values ​​in the segmentation grayscale value set, represents the jth segmentation grayscale value; the crack number and segmentation grayscale difference are summarized to obtain a crack number set and a segmentation grayscale difference set; according to the crack number set and the segmentation grayscale difference set, the grayscale characteristic value of the titanium plate is calculated using the following formula: ,in, represents the grayscale eigenvalue of the titanium plate, represents the number of segmented titanium plate images in the segmented titanium plate image set, Indicates Number of cracks, Indicates Number of cracks, Indicates Segmentation grayscale difference.

9. The titanium plate microstructure and performance prediction method based on surface defect analysis according to claim 8, characterized in that: The method of weighting the original damage process factor by surface defects according to the titanium plate crack group to obtain the target damage process factor includes: obtaining the total length of the titanium plate cracks of the titanium plate crack group, and querying the standard total crack length in a pre-constructed damage process crack table based on the original damage process factor, wherein the damage process crack table is a relationship table between the damage process factor and the crack length; judging whether the total length of the titanium plate cracks is greater than the standard total crack length; if the total length of the titanium plate cracks is greater than the standard total crack length, performing process expansion processing on the original damage process factor to obtain an expanded damage process factor, wherein the expanded damage process factor is expressed as: ,in, represents the factor for expanding the damage process, represents the original damage progression factor, represents the logarithmic function, represents the total length of the titanium plate crack, represents the total length of the standard crack; if the total length of the titanium plate crack is not greater than the total length of the standard crack, the original damage process factor is subjected to a process reduction process to obtain a reduced damage process factor, wherein the reduced damage process factor is expressed as: ,in, Represents the reduction of damage progression factor.

10. A titanium plate structure performance prediction system based on surface defect analysis, characterized in that: The system includes: an original image shooting module, which is used to receive a titanium plate performance prediction instruction, and start a shooting probe based on the titanium plate performance prediction instruction, wherein the shooting probe is installed in a titanium plate defect analysis platform, and the titanium plate defect analysis platform also includes: a probe bracket, a titanium plate sample to be tested, a gel coupling agent and an acoustic wave probe, and the shooting probe is used to shoot an image of the titanium plate sample to be tested to obtain an original titanium plate image, wherein the shooting probe is installed directly above the titanium plate sample to be tested, and the shooting probe is connected to the probe bracket; a damage process calculation module, which is used to start the acoustic wave probe after the original titanium plate image is acquired and use the acoustic wave probe to perform acoustic wave monitoring on the titanium plate sample to be tested to obtain an original acoustic wave signal set, wherein the acoustic wave probe is connected to the gel coupling agent, and the other end of the gel coupling agent is connected to the titanium plate sample to be tested, and the internal damage analysis of the titanium plate is performed according to the original acoustic wave signal set to obtain an original damage process factor; a titanium plate crack recognition module, which is used to perform grayscale enhancement conversion on the original titanium plate image to obtain a grayscale A titanium plate image, crack identification is performed in the grayscale titanium plate image to obtain a titanium plate crack group set, and image segmentation is performed on the grayscale titanium plate image according to the titanium plate crack group set to obtain a segmented titanium plate image set, wherein the number of segmented titanium plate images in the segmented titanium plate image set is the same as the number of titanium plate crack groups in the titanium plate crack group set, and different segmented titanium plate images may overlap in space; a titanium plate performance prediction module, for performing grayscale feature extraction of the titanium plate based on the segmented titanium plate image set to obtain a grayscale eigenvalue of the titanium plate, performing surface defect weighting on the original damage process factor according to the titanium plate crack group set to obtain a target damage process factor, wherein the target damage process factor includes: an expansion damage process factor and a reduction damage process factor, transmitting the target damage process factor and the titanium plate grayscale eigenvalue to a pre-built titanium plate performance prediction platform, and completing titanium plate tissue performance prediction based on surface defect analysis based on the titanium plate performance prediction platform, wherein the titanium plate performance prediction platform has a built-in deep learning model for predicting the tissue performance of the titanium plate.

Images