Titanium alloy forging process optimization method and system based on image processing

Abstract

The invention relates to the technical field of image processing, in particular to a titanium alloy forging process optimization method and system based on image processing.The method comprises the steps that an initial titanium ingot, a high-temperature camera, a high-temperature forging machine and an infrared imager are obtained, the started high-temperature forging machine is used for forging the initial titanium ingot, and forged titanium alloy is obtained; acquiring a high-temperature grayscale image and an infrared image of the forged titanium alloy by using a high-temperature camera and an infrared imager, constructing a target image area on a pre-constructed standard plane coordinate system by using the grayscale edge coordinate set and the temperature edge coordinate set, and performing forging evaluation operation on the high-temperature grayscale image and the infrared image based on the target image area. And the forging completion index, the forging uniformity and the forging defect degree are obtained till the forging time reaches the deadline or the forging completion index is larger than or equal to the forging completion threshold value, and optimization of the forging process of the titanium alloy is completed. According to the method, the automation degree and accuracy of parameter optimization in the forging process can be improved, and the product quality is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of image processing, and in particular to a titanium alloy forging process optimization method and system based on image processing. Background Art

[0002] As a material with excellent mechanical properties and corrosion resistance, titanium alloy is widely used in aerospace, military, chemical industry and other fields. The forging process of titanium alloy is one of the most important links in its manufacturing process.

[0003] At present, with the rapid development of image processing technology and infrared imaging technology, process control based on image and temperature monitoring has gradually become an important technical means in the field of advanced manufacturing. The application of high-temperature cameras and infrared imagers enables real-time monitoring of the temperature distribution and deformation of metals during the forging process, providing a new direction for the precise control of the forging process.

[0004] However, in the titanium alloy forging process, the existing technology lacks a comprehensive analysis and real-time optimization mechanism for high-temperature images and infrared images. The optimization of the forging process often relies on manual analysis of images. Therefore, there is an urgent need for a titanium alloy forging process optimization method based on image processing. The forging process can be optimized in real time through high-temperature images and infrared images, so as to improve the degree of automation of the titanium alloy forging process and improve product quality. Summary of the invention

[0005] The present invention provides a titanium alloy forging process optimization method based on image processing and a computer-readable storage medium, the main purpose of which is to improve the degree of automation and accuracy of optimizing parameters in the forging process and improve product quality.

[0006] To achieve the above object, the present invention provides a titanium alloy forging process optimization method based on image processing, comprising: Obtain an initial titanium ingot, a high temperature camera, a high temperature forging machine and an infrared imager, wherein the resolution of the high temperature camera is the same as that of the infrared imager; Starting the high temperature forging machine, taking the time of starting the high temperature forging machine as the starting point and recording the time in real time to obtain the forging time, and using the started high temperature forging machine to forge the initial titanium ingot to obtain the forged titanium alloy, wherein the initial forging frequency and initial forging temperature of the started high temperature forging machine for forging the initial titanium ingot are preset; Use a high-temperature camera and infrared imager to obtain high-temperature grayscale images and infrared images of forged titanium alloys; Perform grayscale edge analysis on the high temperature grayscale image to obtain a grayscale edge coordinate set, and perform temperature edge analysis on the infrared image to obtain a temperature edge coordinate set; A target image region is constructed on a pre-constructed standard plane coordinate system using a grayscale edge coordinate set and a temperature edge coordinate set. A forging evaluation operation is performed on the high-temperature grayscale image and the infrared image based on the target image region to obtain a forging completion index, forging uniformity, and forging defect degree. Comparing the forging completion index with a preset forging completion threshold, if the forging completion index is less than the forging completion threshold, performing a correction operation on the initial forging frequency and the initial forging temperature based on the forging uniformity and the forging defect degree, and obtaining an updated forging frequency and an updated forging temperature; The updated forging frequency is used as the initial forging frequency, the updated forging temperature is used as the initial forging temperature, and the forged titanium alloy is used as the initial titanium ingot. The process returns to the step of forging the initial titanium ingot using the started high-temperature forging machine until the forging time reaches the preset deadline or the forging completion index is greater than or equal to the forging completion threshold. The high-temperature forging machine is turned off and the forged titanium alloy is used as the target titanium alloy to complete the forging process optimization of the titanium alloy.

[0007] Optionally, the step of obtaining a high-temperature grayscale image and an infrared image of the forged titanium alloy using a high-temperature camera and an infrared imager includes: The forged titanium alloy is photographed by a high temperature camera to obtain a high temperature image, and the forged titanium alloy is photographed by an infrared imager to obtain an infrared image, wherein the position of the high temperature camera when photographing the forged titanium alloy is the same as the position of the infrared imager when photographing the forged titanium alloy, and the shooting direction of the high temperature camera when photographing the forged titanium alloy is the same as the shooting direction of the infrared imager when photographing the forged titanium alloy, wherein the infrared image includes: a plurality of infrared pixel points; A grayscale operation is performed on the high temperature image to obtain a high temperature grayscale image, wherein the high temperature grayscale image includes: a plurality of high temperature pixel points.

[0008] Optionally, performing grayscale edge analysis on the high temperature grayscale image to obtain a grayscale edge coordinate set includes: Identifying a high temperature image principal point in the high temperature grayscale image, wherein the high temperature image principal point is a high temperature pixel point located at a geometric center of the high temperature grayscale image; A first plane coordinate system is constructed in the high-temperature grayscale image with the principal point of the high-temperature image as the origin, wherein the direction from the first high-temperature pixel point in the upper left corner of the high-temperature grayscale image to the first high-temperature pixel point in the upper right corner of the high-temperature grayscale image is used as the positive horizontal axis direction of the first plane coordinate system, the direction from the first high-temperature pixel point in the upper left corner of the high-temperature grayscale image to the first high-temperature pixel point in the lower left corner of the high-temperature grayscale image is used as the positive vertical axis direction of the first plane coordinate system, and the length of the high-temperature pixel point is used as the unit length of the first plane coordinate system; The following operations are performed on each of the multiple high-temperature pixels: Confirm the high temperature gray value of the high temperature pixel point, and compare the high temperature gray value with the preset background gray threshold; If the high temperature grayscale value is less than the background grayscale threshold, the high temperature pixel point is recorded as a background pixel point; Summarize the background pixels to obtain multiple background pixels, and perform the following operations on each of the multiple background pixels: Confirm the background coordinates of the background pixel point in the first plane coordinate system, and calculate the first reference coordinates and the second reference coordinates based on the background coordinates. The calculation formula is as follows: , in, and are the horizontal and vertical coordinates of the background coordinates, and are the horizontal and vertical coordinates of the first reference coordinate, and are the abscissa and ordinate of the second reference coordinate respectively; Confirming a first reference pixel based on the first reference coordinates, the first plane coordinate system, and the high-temperature grayscale image, wherein the first reference pixel is a high-temperature pixel in the high-temperature grayscale image and the coordinates of the first reference pixel in the first plane coordinate system are the first reference coordinates; confirming a second reference pixel point based on the second reference coordinate, the first plane coordinate system, and the high temperature grayscale image; Confirming a first reference grayscale value of a first reference pixel, and confirming a second reference grayscale value of a second reference pixel; Calculate a reference grayscale difference value according to the first reference grayscale value and the second reference grayscale value, wherein the reference grayscale difference value is an absolute difference value between the first reference grayscale value and the second reference grayscale value; Comparing the reference grayscale difference value with a preset grayscale difference threshold; If the reference grayscale difference is greater than or equal to the grayscale difference threshold, the background pixel corresponding to the reference grayscale difference is recorded as the target pixel; Summarize the target pixel points to obtain multiple target pixel points; A grayscale edge coordinate set is obtained using a plurality of target pixel points and a first plane coordinate system.

[0009] Optionally, the acquiring a grayscale edge coordinate set by using a plurality of target pixel points and a first plane coordinate system includes: The target pixel points located in the first quadrant of the first plane coordinate system, the second quadrant of the first plane coordinate system, the third quadrant of the first plane coordinate system, and the fourth quadrant of the first plane coordinate system among the multiple target pixel points are respectively recorded as the first pixel point, the second pixel point, the third pixel point, and the fourth pixel point, and the first pixel point, the second pixel point, the third pixel point, and the fourth pixel point are respectively summarized to obtain a plurality of first pixel points, a plurality of second pixel points, a plurality of third pixel points, and a plurality of fourth pixel points; The following operation is performed on each of the plurality of first pixel points: Confirm the test pixel coordinates of the first pixel point on the first plane coordinate system, and calculate the Euclidean distance based on the test pixel coordinates. The calculation formula is as follows: , in, is the Euclidean distance, is the horizontal coordinate of the test pixel coordinate, is the ordinate of the test pixel coordinate; Summarize the Euclidean distances to obtain multiple Euclidean distances, record the largest Euclidean distance among the multiple Euclidean distances as the target distance, and record the first pixel point corresponding to the target distance as the first edge point; Acquire a second edge point based on a plurality of second pixel points and the first plane coordinate system, acquire a third edge point based on a plurality of third pixel points and the first plane coordinate system, and acquire a fourth edge point based on a plurality of fourth pixel points; Respectively confirming first pixel coordinates, second pixel coordinates, third pixel coordinates and fourth pixel coordinates of the first edge point, the second edge point, the third edge point and the fourth edge point on the first plane coordinate system; The first pixel coordinate, the second pixel coordinate, the third pixel coordinate, and the fourth pixel coordinate are aggregated to obtain a grayscale edge coordinate set.

[0010] Optionally, performing temperature edge analysis on the infrared image to obtain a temperature edge coordinate set includes: The second plane coordinate system is obtained based on the infrared image, and the following operations are performed on each of the multiple infrared pixel points: Identify the infrared temperature of the infrared pixel point and compare the infrared temperature with the preset forging temperature threshold; If the infrared temperature is less than the forging temperature threshold, the infrared pixel point is recorded as a background infrared point; The background infrared points are aggregated to obtain multiple background infrared points, and the following operations are performed on each of the multiple background infrared points: Acquire a first reference infrared point and a second reference infrared point based on the background infrared point, the second plane coordinate system and the infrared image; Identify a first reference temperature of a first reference infrared point, and identify a second reference temperature of a second reference infrared point; Calculating a reference temperature difference according to the first reference temperature and the second reference temperature, wherein the reference temperature difference is an absolute difference between the first reference temperature and the second reference temperature; comparing the reference temperature difference value with a preset reference temperature difference threshold; If the reference temperature difference is greater than or equal to the reference temperature difference threshold, the background infrared point corresponding to the reference temperature difference is taken as the target infrared point; Summarize the target infrared points to obtain multiple target infrared points; Acquire a first infrared coordinate, a second infrared coordinate, a third infrared coordinate, and a fourth infrared coordinate based on the plurality of target infrared points and the second plane coordinate system; The first infrared coordinate, the second infrared coordinate, the third infrared coordinate, and the fourth infrared coordinate are summarized to obtain a temperature edge coordinate set.

[0011] Optionally, constructing a target image region on a pre-constructed standard plane coordinate system using a grayscale edge coordinate set and a temperature edge coordinate set includes: A first reference point, a second reference point, a third reference point, and a fourth reference point are identified in the standard plane coordinate system based on the first pixel coordinate, the second pixel coordinate, the third pixel coordinate, and the fourth pixel coordinate in the grayscale edge coordinate set, wherein the coordinates of the first reference point, the second reference point, the third reference point, and the fourth reference point in the standard plane coordinate system are the first pixel coordinate, the second pixel coordinate, the third pixel coordinate, and the fourth pixel coordinate, respectively; Connecting the first reference point with the second reference point in the standard plane coordinate system to obtain a first line segment, connecting the second reference point with the third reference point in the standard plane coordinate system to obtain a second line segment, connecting the third reference point with the fourth reference point in the standard plane coordinate system to obtain a third line segment, and connecting the fourth reference point with the first reference point in the standard plane coordinate system to obtain a fourth line segment; Constructing a first standard area based on the first line segment, the second line segment, the third line segment and the fourth line segment in the standard plane coordinate system, wherein the first standard area is an area enclosed by the first line segment, the second line segment, the third line segment and the fourth line segment in the standard plane coordinate system; Acquire a second standard area based on the temperature edge coordinate set and the standard plane coordinate system; A target image region is determined based on the first standard region and the second standard region, wherein the target image region is an intersection of the first standard region and the second standard region.

[0012] Optionally, performing a forging evaluation operation on the high temperature grayscale image and the infrared image based on the target image area to obtain a forging completion index, a forging uniformity and a forging defect degree includes: The following operations are performed on each of the multiple high-temperature pixels in the high-temperature grayscale image: Confirm the high temperature coordinates of the high temperature pixel point in the first plane coordinate system, and confirm the high temperature corresponding point in the standard plane coordinate system based on the high temperature coordinates; Determine whether the high temperature corresponding point is located in the target image area. If the high temperature corresponding point is located in the target image area, record the high temperature pixel point corresponding to the high temperature corresponding point as the in-domain pixel point, and confirm the in-domain grayscale value of the in-domain pixel point. Summarize the pixel points in the domain to obtain multiple pixel points in the domain, summarize the grayscale values ​​in the domain to obtain multiple grayscale values ​​in the domain, and calculate the grayscale mean in the domain according to the multiple grayscale values ​​in the domain, wherein the grayscale mean in the domain is the average value of the multiple grayscale values ​​in the domain; Acquire multiple infrared points in the domain based on the infrared image, the second plane coordinate system, the standard plane coordinate system and the target image area; The following operations are performed on each of the multiple intra-domain infrared points: Identify the temperature of the infrared points in the domain; Summarize the temperatures in the domain to obtain multiple temperatures in the domain, and calculate the average temperature in the domain according to the multiple temperatures in the domain, wherein the average temperature in the domain is the average value of the multiple temperatures in the domain; The forging uniformity is calculated based on the grayscale mean value in the domain, the temperature mean value in the domain, multiple grayscale values ​​in the domain, and multiple temperatures in the domain. The calculation formula is as follows: , in, For forging uniformity, is the gray value in multiple domains Gray value in the domain, is the grayscale mean value in the domain, is the temperature in multiple domains The temperature in the domain, is the mean temperature in the domain, is the number of intra-domain grayscale values ​​among multiple intra-domain grayscale values, is the number of intra-domain temperatures in the plurality of intra-domain temperatures; The following operations are performed on each of the multiple in-domain pixels: The single-point difference is calculated based on the grayscale value in the domain corresponding to the pixel point in the domain and the grayscale mean in the domain. The calculation formula is as follows: , in, is the single point difference, is the gray value in the domain corresponding to the pixel point in the domain; Compare the single point difference with the preset defect threshold. If the single point difference is greater than the defect threshold, the pixel point in the domain corresponding to the single point difference is taken as the primary defect pixel point. A primary defect window is constructed in the high-temperature grayscale image based on the primary defect pixel point, wherein the size corresponding to the primary defect window is 3 pixels×3 pixels, and the primary defect pixel point is located at the geometric center of the primary defect window; Eliminate primary defect pixels from the primary defect window, and aggregate high-temperature pixels in the primary defect window after the primary defect pixels are eliminated to obtain a primary update point set; Confirming the grayscale value of each primary update point in the primary update point set to obtain multiple primary grayscale values; The following operations are performed on each of the plurality of primary grayscale values: Calculate the close grayscale difference value according to the primary grayscale value and the grayscale value in the domain, wherein the close grayscale difference value is the absolute difference between the primary grayscale value and the grayscale value in the domain; Summarize similar grayscale differences to obtain multiple similar grayscale differences, and use the primary update point with the smallest similar grayscale difference among the multiple primary update points as the intermediate defective pixel point; The intermediate difference is calculated based on the primary grayscale value corresponding to the intermediate defect pixel and the grayscale mean in the domain; Compare the intermediate difference with the defect threshold, if the intermediate difference is greater than the defect threshold, obtain the intermediate defect window based on the intermediate defect pixel point; Eliminate intermediate defect pixels and primary defect pixels from the intermediate defect window, and summarize the high-temperature pixels in the intermediate defect window after eliminating the intermediate defect pixels and primary defect pixels to obtain an intermediate update point set; Obtain high-level differences based on the intermediate update point set; Compare the high-level difference with the defect threshold. If the high-level difference is greater than the defect threshold, the pixel point in the domain corresponding to the high-level difference is taken as the target defect pixel point. The target defect pixel points are summarized to obtain multiple target defect pixel points. The forging defect degree is calculated based on the multiple target defect pixel points. The calculation formula is as follows: , in, is the forging defect degree, is the number of target defective pixels among multiple target defective pixels; The forging completion index is calculated based on the forging time, target image area, forging uniformity and forging defectivity.

[0013] Optionally, the forging completion index is calculated according to the forging time, the target image area, the forging uniformity and the forging defect degree, including: Confirm the area of ​​the target image region; The forging completion index is calculated based on the forging time, area, forging uniformity and forging defect degree. The calculation formula is as follows: , in, Forging completion index, Forging time, is the area of ​​the region, is the natural logarithm, is a natural constant.

[0014] Optionally, the performing of correction operation on the initial forging frequency and the initial forging temperature based on the forging uniformity and the forging defect degree to obtain the updated forging frequency and the updated forging temperature comprises: The updated forging frequency is calculated based on the forging uniformity and the initial forging frequency. The calculation formula is as follows: , in, To update the forging frequency, is the initial forging frequency, is the hyperbolic tangent function; The updated forging temperature is calculated based on the forging defect degree and the initial forging temperature. The calculation formula is as follows: , in, To update the forging temperature, is the initial forging temperature, The default standard defect degree.

[0015] To achieve the above object, the present invention also provides a titanium alloy forging process optimization system based on image processing, comprising: The initial titanium ingot forging module is used to obtain the initial titanium ingot, a high-temperature camera, a high-temperature forging machine and an infrared imager, wherein the resolution of the high-temperature camera is the same as that of the infrared imager, start the high-temperature forging machine, take the time of starting the high-temperature forging machine as the starting point and record the time in real time to obtain the forging time, and use the started high-temperature forging machine to forge the initial titanium ingot to obtain a forged titanium alloy, wherein the initial forging frequency and initial forging temperature of the started high-temperature forging machine for forging the initial titanium ingot are preset; A forging image analysis module is used to obtain a high-temperature grayscale image and an infrared image of a forged titanium alloy using a high-temperature camera and an infrared imager, perform grayscale edge analysis on the high-temperature grayscale image to obtain a grayscale edge coordinate set, and perform temperature edge analysis on the infrared image to obtain a temperature edge coordinate set; A forging defect assessment module is used to construct a target image area on a pre-constructed standard plane coordinate system using a grayscale edge coordinate set and a temperature edge coordinate set, and perform forging assessment operations on the high-temperature grayscale image and the infrared image based on the target image area to obtain a forging completion index, forging uniformity, and forging defect degree; The forging process optimization module is used to compare the forging completion index with the preset forging completion threshold. If the forging completion index is less than the forging completion threshold, the initial forging frequency and the initial forging temperature are corrected based on the forging uniformity and the forging defect degree to obtain the updated forging frequency and the updated forging temperature. The updated forging frequency is used as the initial forging frequency, the updated forging temperature is used as the initial forging temperature, and the forged titanium alloy is used as the initial titanium ingot. The module returns to the step of forging the initial titanium ingot using the started high-temperature forging machine until the forging time reaches the preset deadline or the forging completion index is greater than or equal to the forging completion threshold, the high-temperature forging machine is turned off, and the forged titanium alloy is used as the target titanium alloy to complete the forging process optimization of the titanium alloy.

[0016] In order to solve the above problem, the present invention further provides an electronic device, the electronic device comprising: A memory storing at least one instruction; and a processor, which executes the instructions stored in the memory to implement the titanium alloy forging process optimization method based on image processing as described above.

[0017] 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 titanium alloy forging process optimization method based on image processing.

[0018] The present invention solves the problems described in the background technology. The present invention obtains an initial titanium ingot, a high-temperature camera, a high-temperature forging machine and an infrared imager, wherein the resolution of the high-temperature camera is the same as that of the infrared imager. It can be seen that the embodiment of the present invention provides basic equipment for subsequently obtaining high-temperature grayscale images and infrared images of forged titanium alloys by obtaining the high-temperature camera and the infrared imager, and then starts the high-temperature forging machine, takes the time of starting the high-temperature forging machine as the starting point and records the time in real time to obtain the forging time, and uses the started high-temperature forging machine to forge the initial titanium ingot to obtain the forged titanium alloy, wherein the initial forging frequency and initial forging temperature of the high-temperature forging machine for forging the initial titanium ingot after starting are preset. It can be seen that the embodiment of the present invention records the forging time in real time, It is convenient to evaluate the degree of completion of forging according to the forging time later, use a high-temperature camera and an infrared imager to obtain a high-temperature grayscale image and an infrared image of the forged titanium alloy, perform grayscale edge analysis on the high-temperature grayscale image to obtain a grayscale edge coordinate set, and perform temperature edge analysis on the infrared image to obtain a temperature edge coordinate set. It can be seen that the embodiment of the present invention analyzes the position of the edge of the forged titanium alloy image in the high-temperature grayscale image through a sudden change in grayscale value, and analyzes the position of the edge of the forged titanium alloy image in the infrared image through a sudden change in temperature, which is convenient for the subsequent confirmation of the area of ​​the forged titanium alloy in the high-temperature grayscale image and the infrared image according to the position of the edge of the forged titanium alloy image, and uses the grayscale edge coordinate set and the temperature edge coordinate set to be in the pre-constructed standard A target image area is constructed on a quasi-plane coordinate system, and a forging evaluation operation is performed on the high-temperature grayscale image and the infrared image based on the target image area to obtain a forging completion index, forging uniformity, and forging defect degree. It can be seen that the embodiment of the present invention confirms the area where the forged titanium alloy is located in the high-temperature grayscale image and the infrared image by constructing a target image area, so that the image of the forged titanium alloy in the high-temperature grayscale image and the infrared image can be analyzed separately, and then the forging completion index, forging uniformity, and forging defect degree can be calculated, which is convenient for the subsequent optimization of the forging process according to the forging completion index, forging uniformity, and forging defect degree, improves the accuracy of optimizing the parameters in the forging process, compares the forging completion index with the preset forging completion threshold, and if the forging completion index is If the index is less than the forging completion threshold, the initial forging frequency and the initial forging temperature are corrected based on the forging uniformity and the forging defect degree to obtain an updated forging frequency and an updated forging temperature, and the updated forging frequency is used as the initial forging frequency, the updated forging temperature is used as the initial forging temperature, and the forged titanium alloy is used as the initial titanium ingot, and the process of forging the initial titanium ingot using the started high-temperature forging machine is returned to the step of forging the initial titanium ingot using the started high-temperature forging machine until the forging time reaches the preset deadline or the forging completion index is greater than or equal to the forging completion threshold, the high-temperature forging machine is turned off and the forged titanium alloy is used as the target titanium alloy to complete the forging process optimization of the titanium alloy. It can be seen that the embodiment of the present invention corrects the initial forging frequency and the initial forging temperature by forging uniformity and forging defect degree.This provides a more suitable forging environment for forging titanium alloys, improves the quality of the final product, and after correction, returns to the step of forging the initial titanium ingot using the high-temperature forging machine after startup, thereby adjusting the initial forging frequency and initial forging temperature in the forging process in stages and continuously cycling, thereby improving the automation level of optimizing the parameters in the forging process. Therefore, the present invention can improve the automation level and accuracy of optimizing the parameters in the forging process and improve product quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 A schematic diagram of a process flow of a titanium alloy forging process optimization method based on image processing provided by one embodiment of the present invention; Figure 2 A functional module diagram of a titanium alloy forging process optimization system based on image processing provided by one embodiment of the present invention; Figure 3 A schematic diagram of the structure of an electronic device for implementing the titanium alloy forging process optimization method based on image processing provided by one embodiment of the present invention.

[0020] Description of reference numerals: 1. Electronic device; 10. Processor; 11. Memory; 12. Bus.

[0021] 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

[0022] 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.

[0023] The embodiment of the present application provides a titanium alloy forging process optimization method based on image processing. The execution subject of the titanium alloy forging process optimization method based on image processing 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 by the embodiment of the present application. In other words, the titanium alloy forging process optimization method based on image processing 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.

[0024] Reference Figure 1 FIG. 1 is a flow chart of a titanium alloy forging process optimization method based on image processing provided by an embodiment of the present invention. In this embodiment, the titanium alloy forging process optimization method based on image processing includes: S1. Obtain an initial titanium ingot, a high temperature camera, a high temperature forging machine and an infrared imager, wherein the resolution of the high temperature camera is the same as that of the infrared imager.

[0025] It should be explained that the initial titanium ingot is a titanium ingot pre-produced by a titanium alloy manufacturing plant for forging titanium alloy. A high temperature camera is a camera that can photograph forged titanium alloy in an environment of 0 degrees Celsius to 70 degrees Celsius. An infrared imager is a photographing device that can detect infrared radiation from forged titanium alloys during shooting and perform imaging based on the infrared radiation. Optionally, a Baumer-VCXG-13M.I.XT industrial camera is used as a high temperature camera, and a FOTRIC-3610 expert digital thermal imager is used as an infrared imager.

[0026] For example, the resolution of the Baumer-VCXG-13M.I.XT industrial camera is 1280 pixels × 1024 pixels, and the resolution of the FOTRIC-3610 expert-level digital thermal imager is 1280 pixels × 1024 pixels. In this case, the resolution of the high-temperature camera is the same as the resolution of the infrared imager.

[0027] It should be understood that in the embodiment of the present invention, by limiting the resolution of the high-temperature camera to be the same as the resolution of the infrared imager, it is ensured that the subsequently obtained high-temperature image and the infrared image have the same image resolution, and because the position and shooting direction of the high-temperature camera when photographing the forged titanium alloy are the same as the position and shooting direction of the infrared imager when photographing the forged titanium alloy, the high-temperature pixel points in the high-temperature grayscale image correspond one-to-one with the infrared pixel points in the infrared image, and then the target image area can be obtained subsequently according to the intersection of the first standard area corresponding to the high-temperature grayscale image and the second standard area corresponding to the infrared image.

[0028] For example, when the resolution of the high-temperature camera is the same as the resolution of the infrared imager and the position and shooting direction of the high-temperature camera when photographing the forged titanium alloy are the same as the position and shooting direction of the infrared imager when photographing the forged titanium alloy, the following effect can be achieved: if the point corresponding to the high-temperature pixel point with coordinates (10, 10) in the first plane coordinate system is the geometric center of the side of the forged titanium alloy, then the point corresponding to the infrared pixel point with coordinates (10, 10) in the second plane coordinate system is also the geometric center of the side of the forged titanium alloy.

[0029] S2. Start the high temperature forging machine, take the time of starting the high temperature forging machine as the starting point and record the time in real time to obtain the forging time, and use the started high temperature forging machine to forge the initial titanium ingot to obtain the forged titanium alloy, wherein the initial forging frequency and initial forging temperature of the high temperature forging machine for forging the initial titanium ingot are preset.

[0030] It should be explained that a high temperature forging machine is a forging machine that can forge the initial titanium ingot. The specific forging process is determined by the forging process of the titanium alloy manufacturing plant. The initial forging frequency refers to the ratio of the number of times the high temperature forging machine strikes or hammers the workpiece to the unit time (usually per minute) when the high temperature forging machine forges the initial titanium ingot. The initial forging temperature refers to the temperature at which the high temperature forging machine heats the initial titanium ingot when forging it.

[0031] Preferably, the initial forging frequency is 30 times / minute and the initial forging temperature is 950 degrees Celsius.

[0032] The key point is that the forged titanium alloy refers to the initial titanium ingot in the forging process, not the initial titanium ingot after the forging is completed. That is, when the forged titanium alloy is subsequently photographed with a high-temperature camera and an infrared imager, the forged titanium alloy is always in the forging process.

[0033] For example, if the high temperature forging machine is started at 10:00, 10:00 is taken as the starting point and the time is recorded in real time. When it is 10:11, the forging time is 11 minutes.

[0034] S3. Use a high-temperature camera and an infrared imager to obtain a high-temperature grayscale image and an infrared image of the forged titanium alloy.

[0035] In detail, the method of obtaining a high-temperature grayscale image and an infrared image of the forged titanium alloy using a high-temperature camera and an infrared imager includes: The forged titanium alloy is photographed by a high temperature camera to obtain a high temperature image, and the forged titanium alloy is photographed by an infrared imager to obtain an infrared image, wherein the position of the high temperature camera when photographing the forged titanium alloy is the same as the position of the infrared imager when photographing the forged titanium alloy, and the shooting direction of the high temperature camera when photographing the forged titanium alloy is the same as the shooting direction of the infrared imager when photographing the forged titanium alloy, wherein the infrared image includes: a plurality of infrared pixel points; A grayscale operation is performed on the high temperature image to obtain a high temperature grayscale image, wherein the high temperature grayscale image includes: a plurality of high temperature pixel points.

[0036] It should be explained that the high temperature image is the image obtained when the high temperature camera takes pictures of the forged titanium alloy, and the infrared image is the thermal infrared image generated when the infrared imager takes pictures of the forged titanium alloy. Infrared pixel points refer to the pixel points in the infrared image, and high temperature pixel points refer to the pixel points in the high temperature grayscale image.

[0037] It should be understood that the grayscale operation performed on the high temperature image means grayscale each pixel in the high temperature image. The technology of performing the grayscale operation on the high temperature image to obtain the high temperature grayscale image is prior art and will not be described in detail here.

[0038] S4, performing grayscale edge analysis on the high temperature grayscale image to obtain a grayscale edge coordinate set, and performing temperature edge analysis on the infrared image to obtain a temperature edge coordinate set; In detail, the grayscale edge analysis is performed on the high temperature grayscale image to obtain a grayscale edge coordinate set, including: Identifying a high temperature image principal point in the high temperature grayscale image, wherein the high temperature image principal point is a high temperature pixel point located at a geometric center of the high temperature grayscale image; A first plane coordinate system is constructed in the high-temperature grayscale image with the principal point of the high-temperature image as the origin, wherein the direction from the first high-temperature pixel point in the upper left corner of the high-temperature grayscale image to the first high-temperature pixel point in the upper right corner of the high-temperature grayscale image is used as the positive horizontal axis direction of the first plane coordinate system, the direction from the first high-temperature pixel point in the upper left corner of the high-temperature grayscale image to the first high-temperature pixel point in the lower left corner of the high-temperature grayscale image is used as the positive vertical axis direction of the first plane coordinate system, and the length of the high-temperature pixel point is used as the unit length of the first plane coordinate system; The following operations are performed on each of the multiple high-temperature pixels: Confirm the high temperature gray value of the high temperature pixel point, and compare the high temperature gray value with the preset background gray threshold; If the high temperature grayscale value is less than the background grayscale threshold, the high temperature pixel point is recorded as a background pixel point; Summarize the background pixels to obtain multiple background pixels, and perform the following operations on each of the multiple background pixels: Confirm the background coordinates of the background pixel point in the first plane coordinate system, and calculate the first reference coordinates and the second reference coordinates based on the background coordinates. The calculation formula is as follows: , in, and are the horizontal and vertical coordinates of the background coordinates, and are the horizontal and vertical coordinates of the first reference coordinate, and are the abscissa and ordinate of the second reference coordinate respectively; Confirming a first reference pixel based on the first reference coordinates, the first plane coordinate system, and the high-temperature grayscale image, wherein the first reference pixel is a high-temperature pixel in the high-temperature grayscale image and the coordinates of the first reference pixel in the first plane coordinate system are the first reference coordinates; confirming a second reference pixel point based on the second reference coordinate, the first plane coordinate system, and the high temperature grayscale image; Confirming a first reference grayscale value of a first reference pixel, and confirming a second reference grayscale value of a second reference pixel; Calculate a reference grayscale difference value according to the first reference grayscale value and the second reference grayscale value, wherein the reference grayscale difference value is an absolute difference value between the first reference grayscale value and the second reference grayscale value; Comparing the reference grayscale difference value with a preset grayscale difference threshold; If the reference grayscale difference is greater than or equal to the grayscale difference threshold, the background pixel corresponding to the reference grayscale difference is recorded as the target pixel; Summarize the target pixel points to obtain multiple target pixel points; A grayscale edge coordinate set is obtained using a plurality of target pixel points and a first plane coordinate system.

[0039] It should be explained that the high temperature gray value refers to the gray value of the high temperature pixel. Optionally, the background gray threshold is a value set manually by the staff of the titanium alloy manufacturing plant, and optionally, the background gray threshold is 90. The background coordinates refer to the coordinates corresponding to the background pixel points on the first plane coordinate system.

[0040] It should be understood that the method for confirming the second reference pixel point based on the second reference coordinates, the first plane coordinate system and the high-temperature grayscale image is the same as the method for confirming the first reference pixel point based on the first reference coordinates, the first plane coordinate system and the high-temperature grayscale image, and will not be repeated here.

[0041] It should be explained that the first reference grayscale value and the second reference grayscale value refer to the grayscale value of the first reference pixel and the grayscale value of the second reference pixel, respectively. Optionally, the grayscale difference threshold is 20.

[0042] In detail, the step of obtaining a grayscale edge coordinate set using a plurality of target pixel points and a first plane coordinate system includes: The target pixel points located in the first quadrant of the first plane coordinate system, the second quadrant of the first plane coordinate system, the third quadrant of the first plane coordinate system, and the fourth quadrant of the first plane coordinate system among the multiple target pixel points are respectively recorded as the first pixel point, the second pixel point, the third pixel point, and the fourth pixel point, and the first pixel point, the second pixel point, the third pixel point, and the fourth pixel point are respectively summarized to obtain a plurality of first pixel points, a plurality of second pixel points, a plurality of third pixel points, and a plurality of fourth pixel points; The following operation is performed on each of the plurality of first pixel points: Confirm the test pixel coordinates of the first pixel point on the first plane coordinate system, and calculate the Euclidean distance based on the test pixel coordinates. The calculation formula is as follows: , in, is the Euclidean distance, is the horizontal coordinate of the test pixel coordinate, is the ordinate of the test pixel coordinate; Summarize the Euclidean distances to obtain multiple Euclidean distances, record the largest Euclidean distance among the multiple Euclidean distances as the target distance, and record the first pixel point corresponding to the target distance as the first edge point; Acquire a second edge point based on a plurality of second pixel points and the first plane coordinate system, acquire a third edge point based on a plurality of third pixel points and the first plane coordinate system, and acquire a fourth edge point based on a plurality of fourth pixel points; Respectively confirming first pixel coordinates, second pixel coordinates, third pixel coordinates and fourth pixel coordinates of the first edge point, the second edge point, the third edge point and the fourth edge point on the first plane coordinate system; The first pixel coordinate, the second pixel coordinate, the third pixel coordinate, and the fourth pixel coordinate are aggregated to obtain a grayscale edge coordinate set.

[0043] It should be explained that the test pixel coordinates refer to the coordinates corresponding to the first pixel point on the first plane coordinate system. The Euclidean distance refers to the distance between the first pixel point and the origin of the first plane coordinate system.

[0044] It should be understood that the method of obtaining the second edge point based on multiple second pixel points and the first plane coordinate system, the method of obtaining the third edge point based on multiple third pixel points and the first plane coordinate system, and the method of obtaining the fourth edge point based on multiple fourth pixel points are all the same as the method of obtaining the first edge point using multiple first pixel points and the first plane coordinate system, and will not be repeated here.

[0045] It should be explained that the first pixel coordinate, the second pixel coordinate, the third pixel coordinate and the fourth pixel coordinate respectively refer to the coordinates corresponding to the first edge point, the second edge point, the third edge point and the fourth edge point in the first plane coordinate system.

[0046] In detail, the temperature edge analysis of the infrared image is performed to obtain a temperature edge coordinate set, including: The second plane coordinate system is obtained based on the infrared image, and the following operations are performed on each of the multiple infrared pixel points: Identify the infrared temperature of the infrared pixel point and compare the infrared temperature with the preset forging temperature threshold; If the infrared temperature is less than the forging temperature threshold, the infrared pixel point is recorded as a background infrared point; The background infrared points are aggregated to obtain multiple background infrared points, and the following operations are performed on each of the multiple background infrared points: Acquire a first reference infrared point and a second reference infrared point based on the background infrared point, the second plane coordinate system and the infrared image; Identify a first reference temperature of a first reference infrared point, and identify a second reference temperature of a second reference infrared point; Calculating a reference temperature difference according to the first reference temperature and the second reference temperature, wherein the reference temperature difference is an absolute difference between the first reference temperature and the second reference temperature; comparing the reference temperature difference value with a preset reference temperature difference threshold; If the reference temperature difference is greater than or equal to the reference temperature difference threshold, the background infrared point corresponding to the reference temperature difference is taken as the target infrared point; Summarize the target infrared points to obtain multiple target infrared points; Acquire a first infrared coordinate, a second infrared coordinate, a third infrared coordinate, and a fourth infrared coordinate based on the plurality of target infrared points and the second plane coordinate system; The first infrared coordinate, the second infrared coordinate, the third infrared coordinate, and the fourth infrared coordinate are summarized to obtain a temperature edge coordinate set.

[0047] It is understandable that the method of obtaining the second plane coordinate system based on the infrared image is the same as the method of obtaining the first plane coordinate system using the high temperature grayscale image, which will not be repeated here. Preferably, the forging temperature threshold is 800 degrees Celsius, and the reference temperature difference threshold is 30 degrees Celsius.

[0048] It should be understood that the infrared temperature, the first reference temperature and the second reference temperature refer to the temperatures of the points corresponding to the infrared pixel point, the first reference infrared point and the second reference infrared point in reality, respectively. Since the intensity of infrared radiation is proportional to the temperature, when the infrared imager generates an infrared image according to the intensity of infrared radiation, each infrared pixel point in the infrared image corresponds to a temperature value, so the infrared temperature, the first reference temperature and the second reference temperature can be obtained through the infrared pixel point, the first reference infrared point and the second reference infrared point, and the technology for identifying the infrared temperature of the infrared pixel point, the technology for identifying the first reference temperature of the first reference infrared point and the technology for identifying the second reference temperature of the second reference infrared point are all prior arts and will not be described in detail here.

[0049] It can be understood that the method of acquiring the first reference infrared point and the second reference infrared point based on the background infrared point, the second plane coordinate system and the infrared image is the same as the method of confirming the first reference pixel point and the second reference pixel point using the background pixel point, the first plane coordinate system and the high-temperature grayscale image, and the method of acquiring the first infrared coordinate, the second infrared coordinate, the third infrared coordinate and the fourth infrared coordinate based on multiple target infrared points and the second plane coordinate system is the same as the method of acquiring the first pixel coordinate, the second pixel coordinate, the third pixel coordinate and the fourth pixel coordinate using multiple target pixel points and the first plane coordinate system, and they will not be repeated here.

[0050] S5. Use the grayscale edge coordinate set and the temperature edge coordinate set to construct a target image area on a pre-constructed standard plane coordinate system, and perform forging evaluation operations on the high-temperature grayscale image and the infrared image based on the target image area to obtain the forging completion index, forging uniformity and forging defect degree.

[0051] It should be explained that the standard plane coordinate system is a plane rectangular coordinate system.

[0052] In detail, the method of constructing a target image region on a pre-constructed standard plane coordinate system using a grayscale edge coordinate set and a temperature edge coordinate set includes: A first reference point, a second reference point, a third reference point, and a fourth reference point are identified in the standard plane coordinate system based on the first pixel coordinate, the second pixel coordinate, the third pixel coordinate, and the fourth pixel coordinate in the grayscale edge coordinate set, wherein the coordinates of the first reference point, the second reference point, the third reference point, and the fourth reference point in the standard plane coordinate system are the first pixel coordinate, the second pixel coordinate, the third pixel coordinate, and the fourth pixel coordinate, respectively; Connecting the first reference point with the second reference point in the standard plane coordinate system to obtain a first line segment, connecting the second reference point with the third reference point in the standard plane coordinate system to obtain a second line segment, connecting the third reference point with the fourth reference point in the standard plane coordinate system to obtain a third line segment, and connecting the fourth reference point with the first reference point in the standard plane coordinate system to obtain a fourth line segment; Constructing a first standard area based on the first line segment, the second line segment, the third line segment and the fourth line segment in the standard plane coordinate system, wherein the first standard area is an area enclosed by the first line segment, the second line segment, the third line segment and the fourth line segment in the standard plane coordinate system; Acquire a second standard area based on the temperature edge coordinate set and the standard plane coordinate system; A target image region is determined based on the first standard region and the second standard region, wherein the target image region is an intersection of the first standard region and the second standard region.

[0053] It should be understood that when taking a high-temperature image and an infrared image, it is impossible for the high-temperature image and the infrared image to contain only the image of the forged titanium alloy. There must also be an image of the device or background surrounding the forged titanium alloy (for example, a partial image of a high-temperature forging machine). At the junction of the image of the forged titanium alloy and the image of the device or background surrounding the forged titanium alloy, a sudden change in grayscale value will occur. Therefore, the embodiment of the present invention can confirm the approximate area where the image of the forged titanium alloy is located in the high-temperature image by performing grayscale edge analysis on the high-temperature grayscale image, that is, the first standard area reflects the area where the image of the forged titanium alloy is located in the high-temperature image, and the present invention In reality, a sudden temperature change will occur at the junction of the forged titanium alloy and the devices surrounding the forged titanium alloy. Therefore, the approximate area where the image of the forged titanium alloy is located in the infrared image can be confirmed by performing temperature edge analysis on the infrared image, that is, the second standard area reflects the area where the image of the forged titanium alloy is located in the infrared image. Since there may be interference such as noise in the high-temperature image and the infrared image, the intersection of the first standard area and the second standard area is used to further eliminate interference, narrow the range, and finally confirm the target image area, that is, the target image area reflects the area corresponding to the image of the forged titanium alloy in the standard plane coordinate system.

[0054] It should be explained that the first reference point, the second reference point, the third reference point and the fourth reference point are points whose coordinates in the standard plane coordinate system are the first pixel coordinate, the second pixel coordinate, the third pixel coordinate and the fourth pixel coordinate, respectively.

[0055] It should be understood that the method for obtaining the second standard area based on the temperature edge coordinate set and the standard plane coordinate system is the same as the method for obtaining the first standard area using the grayscale edge coordinate set and the standard plane coordinate system, and will not be repeated here.

[0056] In detail, the forging evaluation operation is performed on the high temperature grayscale image and the infrared image based on the target image area to obtain the forging completion index, forging uniformity and forging defect degree, including: The following operations are performed on each of the multiple high-temperature pixels in the high-temperature grayscale image: Confirm the high temperature coordinates of the high temperature pixel point in the first plane coordinate system, and confirm the high temperature corresponding point in the standard plane coordinate system based on the high temperature coordinates; Determine whether the high temperature corresponding point is located in the target image area. If the high temperature corresponding point is located in the target image area, record the high temperature pixel point corresponding to the high temperature corresponding point as the in-domain pixel point, and confirm the in-domain grayscale value of the in-domain pixel point. Summarize the pixel points in the domain to obtain multiple pixel points in the domain, summarize the grayscale values ​​in the domain to obtain multiple grayscale values ​​in the domain, and calculate the grayscale mean in the domain according to the multiple grayscale values ​​in the domain, wherein the grayscale mean in the domain is the average value of the multiple grayscale values ​​in the domain; Acquire multiple infrared points in the domain based on the infrared image, the second plane coordinate system, the standard plane coordinate system and the target image area; The following operations are performed on each of the multiple intra-domain infrared points: Identify the temperature of the infrared points in the domain; Summarize the temperatures in the domain to obtain multiple temperatures in the domain, and calculate the average temperature in the domain according to the multiple temperatures in the domain, wherein the average temperature in the domain is the average value of the multiple temperatures in the domain; The forging uniformity is calculated based on the grayscale mean value in the domain, the temperature mean value in the domain, multiple grayscale values ​​in the domain, and multiple temperatures in the domain. The calculation formula is as follows: , in, For forging uniformity, is the gray value in multiple domains Gray value in the domain, is the grayscale mean value in the domain, is the temperature in multiple domains The temperature in the domain, is the mean temperature in the domain, is the number of intra-domain grayscale values ​​among multiple intra-domain grayscale values, is the number of intra-domain temperatures in the plurality of intra-domain temperatures; The following operations are performed on each of the multiple in-domain pixels: The single-point difference is calculated based on the grayscale value in the domain corresponding to the pixel point in the domain and the grayscale mean in the domain. The calculation formula is as follows: , in, is the single point difference, is the gray value in the domain corresponding to the pixel point in the domain; Compare the single point difference with the preset defect threshold. If the single point difference is greater than the defect threshold, the pixel point in the domain corresponding to the single point difference is taken as the primary defect pixel point. A primary defect window is constructed in the high-temperature grayscale image based on the primary defect pixel point, wherein the size corresponding to the primary defect window is 3 pixels×3 pixels, and the primary defect pixel point is located at the geometric center of the primary defect window; Eliminate primary defect pixels from the primary defect window, and aggregate high-temperature pixels in the primary defect window after the primary defect pixels are eliminated to obtain a primary update point set; Confirming the grayscale value of each primary update point in the primary update point set to obtain multiple primary grayscale values; The following operations are performed on each of the plurality of primary grayscale values: Calculate the close grayscale difference value according to the primary grayscale value and the grayscale value in the domain, wherein the close grayscale difference value is the absolute difference between the primary grayscale value and the grayscale value in the domain; Summarize similar grayscale differences to obtain multiple similar grayscale differences, and use the primary update point with the smallest similar grayscale difference among the multiple primary update points as the intermediate defective pixel point; The intermediate difference is calculated based on the primary grayscale value corresponding to the intermediate defect pixel and the grayscale mean in the domain; Compare the intermediate difference with the defect threshold, if the intermediate difference is greater than the defect threshold, obtain the intermediate defect window based on the intermediate defect pixel point; Eliminate intermediate defect pixels and primary defect pixels from the intermediate defect window, and summarize the high-temperature pixels in the intermediate defect window after eliminating the intermediate defect pixels and primary defect pixels to obtain an intermediate update point set; Obtain high-level differences based on the intermediate update point set; Compare the high-level difference with the defect threshold. If the high-level difference is greater than the defect threshold, the pixel point in the domain corresponding to the high-level difference is taken as the target defect pixel point. The target defect pixel points are summarized to obtain multiple target defect pixel points. The forging defect degree is calculated based on the multiple target defect pixel points. The calculation formula is as follows: , in, is the forging defect degree, is the number of target defective pixels among multiple target defective pixels; The forging completion index is calculated based on the forging time, target image area, forging uniformity and forging defectivity.

[0057] It should be explained that the high temperature coordinates refer to the coordinates corresponding to the high temperature pixel points in the first plane coordinate system. The identification of the high temperature corresponding points in the standard plane coordinate system based on the high temperature coordinates refers to taking the points with the high temperature coordinates in the standard plane coordinate system as the high temperature corresponding points. The grayscale value within the domain is the grayscale value of the pixel points within the domain.

[0058] It should be understood that the method of obtaining multiple infrared points in the domain based on the infrared image, the second plane coordinate system, the standard plane coordinate system and the target image area is the same as the method of obtaining multiple pixel points in the domain using the high temperature grayscale image, the first plane coordinate system, the standard plane coordinate system and the target image area, and will not be repeated here. The method of identifying the temperature of the infrared point in the domain is the same as the method of identifying the infrared temperature of the infrared pixel point, and will not be repeated here.

[0059] It is understandable that the forging uniformity reflects the similarity of the states of various positions on the surface of the forged titanium alloy. The higher the forging uniformity, the higher the similarity of the states of various positions on the surface of the forged titanium alloy. The single point difference reflects the difference between the grayscale value of the pixel point in the domain and the grayscale mean value in the domain. The higher the single point difference, the greater the difference between the grayscale value of the pixel point in the domain and the grayscale mean value in the domain. Optionally, the defect threshold is 0.2.

[0060] It should be explained that the primary defect window is composed of the primary defect pixel and 8 high-temperature pixels adjacent to the primary defect pixel.

[0061] It should be understood that the primary update point set includes multiple primary update points, and the intermediate update point set includes multiple intermediate update points. The method of calculating the intermediate difference based on the primary grayscale value corresponding to the intermediate defective pixel and the grayscale mean in the domain is the same as the method of calculating the single-point difference based on the grayscale value in the domain corresponding to the pixel in the domain and the grayscale mean in the domain. The method of obtaining the intermediate defect window based on the intermediate defective pixel is the same as the method of obtaining the primary defect window using the primary defective pixel. The method of obtaining the high-level difference based on the intermediate update point set is the same as the method of obtaining the intermediate difference using the intermediate update point set, and will not be repeated here.

[0062] It can be understood that the embodiment of the present invention confirms intermediate defect pixels and high-level defect pixels through defect thresholds, primary defect windows and intermediate defect windows. If there are intermediate defect pixels and high-level defect pixels in the high-temperature pixels adjacent to the pixels in the domain, since the intermediate difference corresponding to the intermediate defect pixels and the high-level difference corresponding to the high-level defect pixels are both greater than the defect threshold, it means that the image composed of the pixels in the domain and the high-temperature pixels near the pixels in the domain may correspond to cracks and damage on the surface of the forged titanium alloy in reality. Therefore, the pixels in the domain are recorded as target defect pixels, and the target defect pixels are summarized at the end. The severity of the surface defects of the forged titanium alloy is evaluated by the number of target defect pixels in multiple target defect pixels. Therefore, the greater the forging defect degree, the more serious the surface defects of the forged titanium alloy.

[0063] In detail, the forging completion index is calculated according to the forging time, the target image area, the forging uniformity and the forging defect degree, including: Confirm the area of ​​the target image region; The forging completion index is calculated based on the forging time, area, forging uniformity and forging defect degree. The calculation formula is as follows: , in, Forging completion index, Forging time, is the area of ​​the region, is the natural logarithm, is a natural constant.

[0064] It should be understood that the area of ​​the region refers to the area of ​​the target image region. The forging completion index reflects the degree of completion of the forging process of the forged titanium alloy. The larger the forging completion index, the higher the degree of completion of the forging process of the forged titanium alloy.

[0065] It is understandable that during the forging process, the forged titanium alloy will be deformed under the forging of the high-temperature forging machine, and the height in the vertical direction will gradually decrease. Since the forged titanium alloy is often photographed on the side of the titanium alloy, the area of ​​the target image area corresponding to the forged titanium alloy will gradually decrease during the forging process. Therefore, the longer the forging time and the smaller the area, the greater the forging completion index.

[0066] S6. Compare the forging completion index with the preset forging completion threshold. If the forging completion index is less than the forging completion threshold, perform correction operations on the initial forging frequency and the initial forging temperature based on the forging time, forging uniformity and forging defect degree to obtain updated forging frequency and updated forging temperature.

[0067] Optionally, the staff of the titanium alloy manufacturing plant calculates an average value of the forging completion indexes of multiple titanium alloys that have passed forging in history as the forging completion threshold.

[0068] In detail, the performing of correction operation on the initial forging frequency and the initial forging temperature based on the forging uniformity and the forging defect degree to obtain the updated forging frequency and the updated forging temperature includes: The updated forging frequency is calculated based on the forging uniformity and the initial forging frequency. The calculation formula is as follows: , in, To update the forging frequency, is the initial forging frequency, is the hyperbolic tangent function; The updated forging temperature is calculated based on the forging defect degree and the initial forging temperature. The calculation formula is as follows: , in, To update the forging temperature, is the initial forging temperature, The default standard defect degree.

[0069] It should be explained that the main function of updating the forging frequency is to update the initial forging frequency when the high temperature forging machine forges the initial titanium ingot in the subsequent forging. The main function of updating the forging temperature is to update the initial forging temperature when the high temperature forging machine forges the initial titanium ingot in the subsequent forging. Optionally, the standard defectivity is 10%.

[0070] It should be understood that when the forging frequency is high, the stress generated by each forging can be transmitted to various parts of the forged titanium alloy more quickly, so that the stress distribution of the forged titanium alloy is more uniform. Therefore, when the forging uniformity is too low, the forging frequency can be updated by forging uniformity calculation, and the initial forging frequency can be updated with the updated forging frequency, so that the initial forging frequency can be appropriately increased, thereby improving the forging uniformity. When the forging temperature is too high, the excessively high temperature will increase the expansion stress on the surface of the forged titanium alloy, thereby forming cracks on the surface. At the same time, when the forging temperature is too high, the forged titanium alloy is more easily oxidized by air, thereby increasing the roughness of the surface, thereby increasing the forging defect degree. Therefore, when the forging defect degree is too high, the forging temperature can be updated by forging defect degree calculation, and the initial forging temperature can be updated with the updated forging temperature, thereby appropriately reducing the initial forging temperature, thereby improving the forging defect degree.

[0071] S7. Use the updated forging frequency as the initial forging frequency, the updated forging temperature as the initial forging temperature, and the forged titanium alloy as the initial titanium ingot, and return to the step of forging the initial titanium ingot using the started high-temperature forging machine until the forging time reaches the preset deadline or the forging completion index is greater than or equal to the forging completion threshold, turn off the high-temperature forging machine and use the forged titanium alloy as the target titanium alloy to complete the forging process optimization of the titanium alloy.

[0072] It should be explained that the target titanium alloy is the forged titanium alloy required by the titanium alloy manufacturing plant. The cut-off time is set by the staff of the titanium alloy factory according to the forging process of the titanium alloy, and optionally, the cut-off time is 1 hour.

[0073] The present invention solves the problems described in the background technology. The present invention obtains an initial titanium ingot, a high-temperature camera, a high-temperature forging machine and an infrared imager, wherein the resolution of the high-temperature camera is the same as that of the infrared imager. It can be seen that the embodiment of the present invention provides basic equipment for subsequently obtaining high-temperature grayscale images and infrared images of forged titanium alloys by obtaining the high-temperature camera and the infrared imager, and then starts the high-temperature forging machine, takes the time of starting the high-temperature forging machine as the starting point and records the time in real time to obtain the forging time, and uses the started high-temperature forging machine to forge the initial titanium ingot to obtain the forged titanium alloy, wherein the initial forging frequency and initial forging temperature of the high-temperature forging machine for forging the initial titanium ingot after starting are preset. It can be seen that the embodiment of the present invention records the forging time in real time, It is convenient to evaluate the degree of completion of forging according to the forging time later, use a high-temperature camera and an infrared imager to obtain a high-temperature grayscale image and an infrared image of the forged titanium alloy, perform grayscale edge analysis on the high-temperature grayscale image to obtain a grayscale edge coordinate set, and perform temperature edge analysis on the infrared image to obtain a temperature edge coordinate set. It can be seen that the embodiment of the present invention analyzes the position of the edge of the forged titanium alloy image in the high-temperature grayscale image through a sudden change in grayscale value, and analyzes the position of the edge of the forged titanium alloy image in the infrared image through a sudden change in temperature, which is convenient for the subsequent confirmation of the area of ​​the forged titanium alloy in the high-temperature grayscale image and the infrared image according to the position of the edge of the forged titanium alloy image, and uses the grayscale edge coordinate set and the temperature edge coordinate set to be in the pre-constructed standard A target image area is constructed on a quasi-plane coordinate system, and a forging evaluation operation is performed on the high-temperature grayscale image and the infrared image based on the target image area to obtain a forging completion index, forging uniformity, and forging defect degree. It can be seen that the embodiment of the present invention confirms the area where the forged titanium alloy is located in the high-temperature grayscale image and the infrared image by constructing a target image area, so that the image of the forged titanium alloy in the high-temperature grayscale image and the infrared image can be analyzed separately, and then the forging completion index, forging uniformity, and forging defect degree can be calculated, which is convenient for the subsequent optimization of the forging process according to the forging completion index, forging uniformity, and forging defect degree, improves the accuracy of optimizing the parameters in the forging process, compares the forging completion index with the preset forging completion threshold, and if the forging completion index is If the index is less than the forging completion threshold, the initial forging frequency and the initial forging temperature are corrected based on the forging uniformity and the forging defect degree to obtain an updated forging frequency and an updated forging temperature, and the updated forging frequency is used as the initial forging frequency, the updated forging temperature is used as the initial forging temperature, and the forged titanium alloy is used as the initial titanium ingot, and the process of forging the initial titanium ingot using the started high-temperature forging machine is returned to the step of forging the initial titanium ingot using the started high-temperature forging machine until the forging time reaches the preset deadline or the forging completion index is greater than or equal to the forging completion threshold, the high-temperature forging machine is turned off and the forged titanium alloy is used as the target titanium alloy to complete the forging process optimization of the titanium alloy. It can be seen that the embodiment of the present invention corrects the initial forging frequency and the initial forging temperature by forging uniformity and forging defect degree.This provides a more suitable forging environment for forging titanium alloys, improves the quality of the final product, and after correction, returns to the step of forging the initial titanium ingot using the high-temperature forging machine after startup, thereby adjusting the initial forging frequency and initial forging temperature in the forging process in stages and continuously cycling, thereby improving the automation level of optimizing the parameters in the forging process. Therefore, the present invention can improve the automation level and accuracy of optimizing the parameters in the forging process and improve product quality.

[0074] like Figure 2 , which is a functional module diagram of a titanium alloy forging process optimization system based on image processing provided by one embodiment of the present invention.

[0075] The titanium alloy forging process optimization system 100 based on image processing of the present invention can be installed in an electronic device. According to the functions to be implemented, the titanium alloy forging process optimization system 100 based on image processing can include an initial titanium ingot forging module 101, a forging image analysis module 102, a forging defect assessment module 103 and a forging process optimization module 104. The module of the present invention can also be referred to as 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.

[0076] The initial titanium ingot forging module 101 is used to obtain an initial titanium ingot, a high temperature camera, a high temperature forging machine and an infrared imager, wherein the resolution of the high temperature camera is the same as that of the infrared imager, start the high temperature forging machine, take the time of starting the high temperature forging machine as the starting point and record the time in real time to obtain the forging time, and use the started high temperature forging machine to forge the initial titanium ingot to obtain a forged titanium alloy, wherein the initial forging frequency and initial forging temperature of the started high temperature forging machine for forging the initial titanium ingot are preset; The forging image analysis module 102 is used to obtain a high-temperature grayscale image and an infrared image of the forged titanium alloy using a high-temperature camera and an infrared imager, perform grayscale edge analysis on the high-temperature grayscale image to obtain a grayscale edge coordinate set, and perform temperature edge analysis on the infrared image to obtain a temperature edge coordinate set; The forging defect assessment module 103 is used to construct a target image area on a pre-constructed standard plane coordinate system using a grayscale edge coordinate set and a temperature edge coordinate set, and perform a forging assessment operation on the high-temperature grayscale image and the infrared image based on the target image area to obtain a forging completion index, a forging uniformity, and a forging defect degree; The forging process optimization module 104 is used to compare the forging completion index with a preset forging completion threshold. If the forging completion index is less than the forging completion threshold, a correction operation is performed on the initial forging frequency and the initial forging temperature based on the forging uniformity and the forging defect degree to obtain an updated forging frequency and an updated forging temperature. The updated forging frequency is used as the initial forging frequency, the updated forging temperature is used as the initial forging temperature, and the forged titanium alloy is used as the initial titanium ingot. The module returns to the step of forging the initial titanium ingot using the started high-temperature forging machine until the forging time reaches the preset deadline or the forging completion index is greater than or equal to the forging completion threshold. The high-temperature forging machine is turned off and the forged titanium alloy is used as the target titanium alloy to complete the forging process optimization of the titanium alloy.

[0077] In detail, each module in the titanium alloy forging process optimization system 100 based on image processing in the embodiment of the present invention is used in the same manner as described above. Figure 1 The same technical means are used as the titanium alloy forging process optimization method based on image processing described in the text, and can produce the same technical effects, so they will not be repeated here.

[0078] like Figure 3 , which is a schematic diagram of the structure of an electronic device for implementing a titanium alloy forging process optimization method based on image processing provided by an embodiment of the present invention.

[0079] 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 alloy forging process optimization method program based on image processing.

[0080] 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 alloy forging process optimization method program based on image processing, but also can be used to temporarily store data that has been output or is to be output.

[0081] The processor 10 may be composed of an integrated circuit in some embodiments, 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 alloy forging process optimization method program based on image processing, etc.), and calls data stored in the memory 11 to execute various functions of the electronic device 1 and process data.

[0082] 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.

[0083] 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.

[0084] 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 device, so that the power management device can realize functions such as charging management, discharging management, and power consumption management. The power source may also include one or more DC or AC power sources, recharging devices, power failure detection circuits, power converters or inverters, power status indicators, and other arbitrary components. The electronic device 1 may also include a variety of sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be repeated here.

[0085] 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.

[0086] 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.

[0087] The titanium alloy forging process optimization method program based on image processing stored in the memory 11 of the electronic device 1 is a combination of multiple instructions. When running in the processor 10, it can achieve: Obtain an initial titanium ingot, a high temperature camera, a high temperature forging machine and an infrared imager, wherein the resolution of the high temperature camera is the same as that of the infrared imager; Starting the high temperature forging machine, taking the time of starting the high temperature forging machine as the starting point and recording the time in real time to obtain the forging time, and using the started high temperature forging machine to forge the initial titanium ingot to obtain the forged titanium alloy, wherein the initial forging frequency and initial forging temperature of the started high temperature forging machine for forging the initial titanium ingot are preset; Use a high-temperature camera and infrared imager to obtain high-temperature grayscale images and infrared images of forged titanium alloys; Perform grayscale edge analysis on the high temperature grayscale image to obtain a grayscale edge coordinate set, and perform temperature edge analysis on the infrared image to obtain a temperature edge coordinate set; A target image region is constructed on a pre-constructed standard plane coordinate system using a grayscale edge coordinate set and a temperature edge coordinate set. A forging evaluation operation is performed on the high-temperature grayscale image and the infrared image based on the target image region to obtain a forging completion index, forging uniformity, and forging defect degree. Comparing the forging completion index with a preset forging completion threshold, if the forging completion index is less than the forging completion threshold, performing a correction operation on the initial forging frequency and the initial forging temperature based on the forging uniformity and the forging defect degree, and obtaining an updated forging frequency and an updated forging temperature; The updated forging frequency is used as the initial forging frequency, the updated forging temperature is used as the initial forging temperature, and the forged titanium alloy is used as the initial titanium ingot. The process returns to the step of forging the initial titanium ingot using the started high-temperature forging machine until the forging time reaches the preset deadline or the forging completion index is greater than or equal to the forging completion threshold. The high-temperature forging machine is turned off and the forged titanium alloy is used as the target titanium alloy to complete the forging process optimization of the titanium alloy.

[0088] 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.

[0089] 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 device capable of carrying 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).

[0090] The present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor of an electronic device, the computer program can implement: Obtain an initial titanium ingot, a high temperature camera, a high temperature forging machine and an infrared imager, wherein the resolution of the high temperature camera is the same as that of the infrared imager; Starting the high temperature forging machine, taking the time of starting the high temperature forging machine as the starting point and recording the time in real time to obtain the forging time, and using the started high temperature forging machine to forge the initial titanium ingot to obtain the forged titanium alloy, wherein the initial forging frequency and initial forging temperature of the started high temperature forging machine for forging the initial titanium ingot are preset; Use a high-temperature camera and infrared imager to obtain high-temperature grayscale images and infrared images of forged titanium alloys; Perform grayscale edge analysis on the high temperature grayscale image to obtain a grayscale edge coordinate set, and perform temperature edge analysis on the infrared image to obtain a temperature edge coordinate set; A target image region is constructed on a pre-constructed standard plane coordinate system using a grayscale edge coordinate set and a temperature edge coordinate set. A forging evaluation operation is performed on the high-temperature grayscale image and the infrared image based on the target image region to obtain a forging completion index, forging uniformity, and forging defect degree. Comparing the forging completion index with a preset forging completion threshold, if the forging completion index is less than the forging completion threshold, performing a correction operation on the initial forging frequency and the initial forging temperature based on the forging uniformity and the forging defect degree, and obtaining an updated forging frequency and an updated forging temperature; The updated forging frequency is used as the initial forging frequency, the updated forging temperature is used as the initial forging temperature, and the forged titanium alloy is used as the initial titanium ingot. The process returns to the step of forging the initial titanium ingot using the started high-temperature forging machine until the forging time reaches the preset deadline or the forging completion index is greater than or equal to the forging completion threshold. The high-temperature forging machine is turned off and the forged titanium alloy is used as the target titanium alloy to complete the forging process optimization of the titanium alloy.

[0091] 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.

[0092] 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.

[0093] In addition, each functional module in each embodiment of the present invention may be integrated into one processing unit, or 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.

[0094] 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.

[0095] 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 titanium alloy forging process optimization method based on image processing, characterized in that: The method comprises: Obtain an initial titanium ingot, a high temperature camera, a high temperature forging machine and an infrared imager, wherein the resolution of the high temperature camera is the same as that of the infrared imager; Starting the high temperature forging machine, taking the time of starting the high temperature forging machine as the starting point and recording the time in real time to obtain the forging time, and using the started high temperature forging machine to forge the initial titanium ingot to obtain the forged titanium alloy, wherein the initial forging frequency and initial forging temperature of the started high temperature forging machine for forging the initial titanium ingot are preset; Use a high-temperature camera and infrared imager to obtain high-temperature grayscale images and infrared images of forged titanium alloys; Perform grayscale edge analysis on the high temperature grayscale image to obtain a grayscale edge coordinate set, and perform temperature edge analysis on the infrared image to obtain a temperature edge coordinate set; A target image region is constructed on a pre-constructed standard plane coordinate system using a grayscale edge coordinate set and a temperature edge coordinate set. A forging evaluation operation is performed on the high-temperature grayscale image and the infrared image based on the target image region to obtain a forging completion index, forging uniformity, and forging defect degree. Comparing the forging completion index with a preset forging completion threshold, if the forging completion index is less than the forging completion threshold, performing a correction operation on the initial forging frequency and the initial forging temperature based on the forging uniformity and the forging defect degree, and obtaining an updated forging frequency and an updated forging temperature; The updated forging frequency is used as the initial forging frequency, the updated forging temperature is used as the initial forging temperature, and the forged titanium alloy is used as the initial titanium ingot. The process returns to the step of forging the initial titanium ingot using the started high-temperature forging machine until the forging time reaches the preset deadline or the forging completion index is greater than or equal to the forging completion threshold. The high-temperature forging machine is turned off and the forged titanium alloy is used as the target titanium alloy to complete the forging process optimization of the titanium alloy.

2. The titanium alloy forging process optimization method based on image processing according to claim 1, characterized in that: The method of using a high temperature camera and an infrared imager to obtain a high temperature grayscale image and an infrared image of a forged titanium alloy includes: The forged titanium alloy is photographed by a high temperature camera to obtain a high temperature image, and the forged titanium alloy is photographed by an infrared imager to obtain an infrared image, wherein the position of the high temperature camera when photographing the forged titanium alloy is the same as the position of the infrared imager when photographing the forged titanium alloy, and the shooting direction of the high temperature camera when photographing the forged titanium alloy is the same as the shooting direction of the infrared imager when photographing the forged titanium alloy, wherein the infrared image includes: a plurality of infrared pixel points; A grayscale operation is performed on the high temperature image to obtain a high temperature grayscale image, wherein the high temperature grayscale image includes: a plurality of high temperature pixel points.

3. The titanium alloy forging process optimization method based on image processing according to claim 2, characterized in that: The grayscale edge analysis is performed on the high temperature grayscale image to obtain a grayscale edge coordinate set, including: Identifying a high temperature image principal point in the high temperature grayscale image, wherein the high temperature image principal point is a high temperature pixel point located at a geometric center of the high temperature grayscale image; A first plane coordinate system is constructed in the high-temperature grayscale image with the principal point of the high-temperature image as the origin, wherein the direction from the first high-temperature pixel point in the upper left corner of the high-temperature grayscale image to the first high-temperature pixel point in the upper right corner of the high-temperature grayscale image is used as the positive horizontal axis direction of the first plane coordinate system, the direction from the first high-temperature pixel point in the upper left corner of the high-temperature grayscale image to the first high-temperature pixel point in the lower left corner of the high-temperature grayscale image is used as the positive vertical axis direction of the first plane coordinate system, and the length of the high-temperature pixel point is used as the unit length of the first plane coordinate system; The following operations are performed on each of the multiple high-temperature pixels: Confirm the high temperature gray value of the high temperature pixel point, and compare the high temperature gray value with the preset background gray threshold; If the high temperature grayscale value is less than the background grayscale threshold, the high temperature pixel point is recorded as a background pixel point; Summarize the background pixels to obtain multiple background pixels, and perform the following operations on each of the multiple background pixels: Confirm the background coordinates of the background pixel point in the first plane coordinate system, and calculate the first reference coordinates and the second reference coordinates based on the background coordinates. The calculation formula is as follows: ， in, and are the horizontal and vertical coordinates of the background coordinates, and are the horizontal and vertical coordinates of the first reference coordinate, and are the abscissa and ordinate of the second reference coordinate respectively; Confirming a first reference pixel based on the first reference coordinates, the first plane coordinate system, and the high-temperature grayscale image, wherein the first reference pixel is a high-temperature pixel in the high-temperature grayscale image and the coordinates of the first reference pixel in the first plane coordinate system are the first reference coordinates; confirming a second reference pixel point based on the second reference coordinate, the first plane coordinate system, and the high temperature grayscale image; Confirming a first reference grayscale value of a first reference pixel, and confirming a second reference grayscale value of a second reference pixel; Calculate a reference grayscale difference value according to the first reference grayscale value and the second reference grayscale value, wherein the reference grayscale difference value is an absolute difference value between the first reference grayscale value and the second reference grayscale value; Comparing the reference grayscale difference value with a preset grayscale difference threshold; If the reference grayscale difference is greater than or equal to the grayscale difference threshold, the background pixel corresponding to the reference grayscale difference is recorded as the target pixel; Summarize the target pixel points to obtain multiple target pixel points; A grayscale edge coordinate set is obtained using a plurality of target pixel points and a first plane coordinate system.

4. The titanium alloy forging process optimization method based on image processing according to claim 3, characterized in that: The method of obtaining a grayscale edge coordinate set by using a plurality of target pixel points and a first plane coordinate system includes: The target pixel points located in the first quadrant of the first plane coordinate system, the second quadrant of the first plane coordinate system, the third quadrant of the first plane coordinate system, and the fourth quadrant of the first plane coordinate system among the multiple target pixel points are respectively recorded as the first pixel point, the second pixel point, the third pixel point, and the fourth pixel point, and the first pixel point, the second pixel point, the third pixel point, and the fourth pixel point are respectively summarized to obtain a plurality of first pixel points, a plurality of second pixel points, a plurality of third pixel points, and a plurality of fourth pixel points; The following operation is performed on each of the plurality of first pixel points: Confirm the test pixel coordinates of the first pixel point on the first plane coordinate system, and calculate the Euclidean distance based on the test pixel coordinates. The calculation formula is as follows: ， in, is the Euclidean distance, is the horizontal coordinate of the test pixel coordinate, is the ordinate of the test pixel coordinate; Summarize the Euclidean distances to obtain multiple Euclidean distances, record the largest Euclidean distance among the multiple Euclidean distances as the target distance, and record the first pixel point corresponding to the target distance as the first edge point; Acquire a second edge point based on a plurality of second pixel points and the first plane coordinate system, acquire a third edge point based on a plurality of third pixel points and the first plane coordinate system, and acquire a fourth edge point based on a plurality of fourth pixel points; Respectively confirming first pixel coordinates, second pixel coordinates, third pixel coordinates and fourth pixel coordinates of the first edge point, the second edge point, the third edge point and the fourth edge point on the first plane coordinate system; The first pixel coordinate, the second pixel coordinate, the third pixel coordinate, and the fourth pixel coordinate are aggregated to obtain a grayscale edge coordinate set.

5. The titanium alloy forging process optimization method based on image processing according to claim 4, characterized in that: The step of performing temperature edge analysis on the infrared image to obtain a temperature edge coordinate set includes: The second plane coordinate system is obtained based on the infrared image, and the following operations are performed on each of the multiple infrared pixel points: Identify the infrared temperature of the infrared pixel point and compare the infrared temperature with the preset forging temperature threshold; If the infrared temperature is less than the forging temperature threshold, the infrared pixel point is recorded as a background infrared point; The background infrared points are aggregated to obtain multiple background infrared points, and the following operations are performed on each of the multiple background infrared points: Acquire a first reference infrared point and a second reference infrared point based on the background infrared point, the second plane coordinate system and the infrared image; Identify a first reference temperature of a first reference infrared point, and identify a second reference temperature of a second reference infrared point; Calculating a reference temperature difference according to the first reference temperature and the second reference temperature, wherein the reference temperature difference is an absolute difference between the first reference temperature and the second reference temperature; comparing the reference temperature difference value with a preset reference temperature difference threshold; If the reference temperature difference is greater than or equal to the reference temperature difference threshold, the background infrared point corresponding to the reference temperature difference is taken as the target infrared point; Summarize the target infrared points to obtain multiple target infrared points; Acquire a first infrared coordinate, a second infrared coordinate, a third infrared coordinate, and a fourth infrared coordinate based on the plurality of target infrared points and the second plane coordinate system; The first infrared coordinate, the second infrared coordinate, the third infrared coordinate, and the fourth infrared coordinate are summarized to obtain a temperature edge coordinate set.

6. The titanium alloy forging process optimization method based on image processing according to claim 5, characterized in that: The method of constructing a target image region on a pre-constructed standard plane coordinate system using a grayscale edge coordinate set and a temperature edge coordinate set includes: A first reference point, a second reference point, a third reference point, and a fourth reference point are identified in the standard plane coordinate system based on the first pixel coordinate, the second pixel coordinate, the third pixel coordinate, and the fourth pixel coordinate in the grayscale edge coordinate set, wherein the coordinates of the first reference point, the second reference point, the third reference point, and the fourth reference point in the standard plane coordinate system are the first pixel coordinate, the second pixel coordinate, the third pixel coordinate, and the fourth pixel coordinate, respectively; Connecting the first reference point with the second reference point in the standard plane coordinate system to obtain a first line segment, connecting the second reference point with the third reference point in the standard plane coordinate system to obtain a second line segment, connecting the third reference point with the fourth reference point in the standard plane coordinate system to obtain a third line segment, and connecting the fourth reference point with the first reference point in the standard plane coordinate system to obtain a fourth line segment; Constructing a first standard area based on the first line segment, the second line segment, the third line segment and the fourth line segment in the standard plane coordinate system, wherein the first standard area is an area enclosed by the first line segment, the second line segment, the third line segment and the fourth line segment in the standard plane coordinate system; Acquire a second standard area based on the temperature edge coordinate set and the standard plane coordinate system; A target image region is determined based on the first standard region and the second standard region, wherein the target image region is an intersection of the first standard region and the second standard region.

7. The titanium alloy forging process optimization method based on image processing according to claim 6, characterized in that: The forging evaluation operation is performed on the high temperature grayscale image and the infrared image based on the target image area to obtain the forging completion index, forging uniformity and forging defect degree, including: The following operations are performed on each of the multiple high-temperature pixels in the high-temperature grayscale image: Confirm the high temperature coordinates of the high temperature pixel point in the first plane coordinate system, and confirm the high temperature corresponding point in the standard plane coordinate system based on the high temperature coordinates; Determine whether the high temperature corresponding point is located in the target image area. If the high temperature corresponding point is located in the target image area, record the high temperature pixel point corresponding to the high temperature corresponding point as the in-domain pixel point, and confirm the in-domain grayscale value of the in-domain pixel point. Summarize the pixels in the domain to obtain multiple pixels in the domain, summarize the grayscale values ​​in the domain to obtain multiple grayscale values ​​in the domain, and calculate the grayscale mean in the domain according to the multiple grayscale values ​​in the domain, wherein the grayscale mean in the domain is the average value of the multiple grayscale values ​​in the domain; Acquire multiple infrared points in the domain based on the infrared image, the second plane coordinate system, the standard plane coordinate system and the target image area; The following operations are performed on each of the multiple intra-domain infrared points: Identify the temperature of the infrared points in the domain; Summarize the temperatures in the domain to obtain multiple temperatures in the domain, and calculate the average temperature in the domain according to the multiple temperatures in the domain, wherein the average temperature in the domain is the average value of the multiple temperatures in the domain; The forging uniformity is calculated based on the grayscale mean value in the domain, the temperature mean value in the domain, multiple grayscale values ​​in the domain, and multiple temperatures in the domain. The calculation formula is as follows: ， in, For forging uniformity, is the gray value in multiple domains Gray value in the domain, is the grayscale mean in the domain, is the temperature in multiple domains The temperature in the domain, is the mean temperature in the domain, is the number of intra-domain grayscale values ​​among multiple intra-domain grayscale values, is the number of intra-domain temperatures in the plurality of intra-domain temperatures; The following operations are performed on each of the multiple in-domain pixels: The single-point difference is calculated based on the grayscale value in the domain corresponding to the pixel point in the domain and the grayscale mean in the domain. The calculation formula is as follows: ， in, is the single point difference, is the gray value in the domain corresponding to the pixel point in the domain; Compare the single point difference with the preset defect threshold. If the single point difference is greater than the defect threshold, the pixel point in the domain corresponding to the single point difference is taken as the primary defect pixel point. A primary defect window is constructed in the high-temperature grayscale image based on the primary defect pixel point, wherein the size corresponding to the primary defect window is 3 pixels×3 pixels, and the primary defect pixel point is located at the geometric center of the primary defect window; Eliminate primary defect pixels from the primary defect window, and aggregate high-temperature pixels in the primary defect window after the primary defect pixels are eliminated to obtain a primary update point set; Confirming the grayscale value of each primary update point in the primary update point set to obtain multiple primary grayscale values; The following operation is performed on each of the plurality of primary grayscale values: Calculate the approximate grayscale difference value according to the primary grayscale value and the grayscale value in the domain, wherein the approximate grayscale difference value is the absolute difference between the primary grayscale value and the grayscale value in the domain; Summarize similar grayscale differences to obtain multiple similar grayscale differences, and use the primary update point with the smallest similar grayscale difference among the multiple primary update points as the intermediate defective pixel point; The intermediate difference is calculated based on the primary grayscale value corresponding to the intermediate defect pixel and the grayscale mean in the domain; Compare the intermediate difference with the defect threshold, if the intermediate difference is greater than the defect threshold, obtain the intermediate defect window based on the intermediate defect pixel point; Eliminate intermediate defect pixels and primary defect pixels from the intermediate defect window, and summarize the high-temperature pixels in the intermediate defect window after eliminating the intermediate defect pixels and primary defect pixels to obtain an intermediate update point set; Obtain high-level differences based on the intermediate update point set; Compare the high-level difference with the defect threshold. If the high-level difference is greater than the defect threshold, the pixel point in the domain corresponding to the high-level difference is taken as the target defect pixel point. The target defect pixel points are summarized to obtain multiple target defect pixel points. The forging defect degree is calculated based on the multiple target defect pixel points. The calculation formula is as follows: ， in, is the forging defect degree, is the number of target defective pixels among multiple target defective pixels; The forging completion index is calculated based on the forging time, target image area, forging uniformity and forging defectivity.

8. The titanium alloy forging process optimization method based on image processing according to claim 7, characterized in that: The forging completion index is calculated according to the forging time, the target image area, the forging uniformity and the forging defect degree, including: Confirm the area of ​​the target image region; The forging completion index is calculated based on the forging time, area, forging uniformity and forging defect degree. The calculation formula is as follows: ， in, Forging completion index, Forging time, is the area of ​​the region, is the natural logarithm, is a natural constant.

9. The titanium alloy forging process optimization method based on image processing according to claim 8, characterized in that: The performing of correction operation on the initial forging frequency and the initial forging temperature based on the forging uniformity and the forging defect degree to obtain the updated forging frequency and the updated forging temperature comprises: The updated forging frequency is calculated based on the forging uniformity and the initial forging frequency. The calculation formula is as follows: ， in, To update the forging frequency, is the initial forging frequency, is the hyperbolic tangent function; The updated forging temperature is calculated based on the forging defect degree and the initial forging temperature. The calculation formula is as follows: ， in, To update the forging temperature, is the initial forging temperature, The default standard defect degree.

10. A titanium alloy forging process optimization system based on image processing, characterized in that: The system comprises: The initial titanium ingot forging module is used to obtain the initial titanium ingot, a high-temperature camera, a high-temperature forging machine and an infrared imager, wherein the resolution of the high-temperature camera is the same as that of the infrared imager, start the high-temperature forging machine, take the time of starting the high-temperature forging machine as the starting point and record the time in real time to obtain the forging time, and use the started high-temperature forging machine to forge the initial titanium ingot to obtain a forged titanium alloy, wherein the initial forging frequency and initial forging temperature of the started high-temperature forging machine for forging the initial titanium ingot are preset; A forging image analysis module is used to obtain a high-temperature grayscale image and an infrared image of a forged titanium alloy using a high-temperature camera and an infrared imager, perform grayscale edge analysis on the high-temperature grayscale image to obtain a grayscale edge coordinate set, and perform temperature edge analysis on the infrared image to obtain a temperature edge coordinate set; A forging defect assessment module is used to construct a target image area on a pre-constructed standard plane coordinate system using a grayscale edge coordinate set and a temperature edge coordinate set, and perform forging assessment operations on the high-temperature grayscale image and the infrared image based on the target image area to obtain a forging completion index, forging uniformity, and forging defect degree; The forging process optimization module is used to compare the forging completion index with the preset forging completion threshold. If the forging completion index is less than the forging completion threshold, the initial forging frequency and the initial forging temperature are corrected based on the forging uniformity and the forging defect degree to obtain the updated forging frequency and the updated forging temperature. The updated forging frequency is used as the initial forging frequency, the updated forging temperature is used as the initial forging temperature, and the forged titanium alloy is used as the initial titanium ingot. The module returns to the step of forging the initial titanium ingot using the started high-temperature forging machine until the forging time reaches the preset deadline or the forging completion index is greater than or equal to the forging completion threshold, the high-temperature forging machine is turned off, and the forged titanium alloy is used as the target titanium alloy to complete the forging process optimization of the titanium alloy.

Images