CN118150327A - Intelligent detection method and device for tensile properties of high temperature alloy ring forging blank - Google Patents

Abstract

The disclosure provides an intelligent detection method and device for tensile properties of a high-temperature alloy ring forging blank, relates to the technical field of industrial production, in particular to the technical fields of deep learning, image processing and the like, and can be applied to a scene of manufacturing an aviation ring forging. The specific implementation scheme comprises the following steps: detecting a blank to be detected through a tensile testing machine, and obtaining a target image of the blank to be detected; comparing the target image with a preset standard image, and determining the similarity between the target image and the preset standard image, wherein the preset standard image comprises a standard stress-strain curve; judging whether the similarity is larger than a preset similarity threshold value or not; if so, displaying first indication information, wherein the first indication information is used for indicating that the blank to be detected is a first blank; if not, displaying second indication information, wherein the second indication information is used for indicating that the blank to be detected is a second blank. The method and the device can improve accuracy and efficiency of detecting the tensile property of the blank to be detected.

Description

Intelligent detection method and device for tensile properties of high temperature alloy ring forging blank

Technical Field

The present disclosure relates to the field of industrial production technology, specifically to technical fields such as deep learning and image processing, and can be applied to the scenario of manufacturing aviation ring forgings, and in particular to an intelligent detection method and device for the tensile properties of high-temperature alloy ring forging blanks.

Background technique

Aviation ring forgings are an important manufacturing component in the aerospace industry. The manufacturing process of aviation ring forgings goes through multiple steps, including material selection, prefabricated billet heating, forging, processing, heat treatment and surface treatment. During the material selection step, it is necessary to conduct a metal tensile test on the alloy forging billet used to manufacture aviation ring forgings. The metal tensile test is the most basic test in mechanical properties, and it is also one of the important test items for inspecting metal materials and characterizing their intrinsic quality. The tensile properties of metals are an important indicator for evaluating metal materials, which can clearly reflect the elasticity, elastoplasticity and fracture characteristics of the material when subjected to tensile external forces. Therefore, when selecting materials, it is necessary to conduct a material tensile test on the alloy forging billet to detect whether the tensile properties of the alloy forging billet are qualified.

At present, the tensile properties of alloy forging billets mainly rely on manual operation.

However, the above method of manually testing the tensile properties of the alloy forging blank has low testing efficiency and low accuracy.

Summary of the invention

The present invention provides an intelligent detection method and device for the tensile properties of a high-temperature alloy ring forging blank, which can improve the accuracy and efficiency of the tensile properties detection of the blank to be detected.

According to a first aspect of the present disclosure, there is provided an intelligent detection method for the tensile properties of a high-temperature alloy ring forging blank, the method comprising: detecting the blank to be detected by a tensile testing machine to obtain a target image of the blank to be detected, the target image comprising a target stress-strain curve; comparing the target image with a preset standard image to determine the similarity between the target image and the preset standard image, the preset standard image comprising a standard stress-strain curve; judging whether the similarity is greater than a preset similarity threshold; if so, displaying a first indication information, the first indication information being used to indicate that the blank to be detected is a first blank and the tensile properties of the first blank are qualified; if not, displaying a second indication information, the second indication information being used to indicate that the blank to be detected is a second blank and the tensile properties of the second blank are unqualified.

According to a second aspect of the present disclosure, there is provided an intelligent detection device for tensile properties of a high-temperature alloy ring forging blank, the device comprising: an acquisition unit and a judgment unit.

The acquisition unit is specifically used to test the blank to be tested by a tensile testing machine, and obtain a target image of the blank to be tested, wherein the target image includes a target stress-strain curve.

The judgment unit is specifically used to compare the target image with a preset standard image to determine the similarity between the target image and the preset standard image, wherein the preset standard image includes a standard stress-strain curve; judge whether the similarity is greater than a preset similarity threshold; if so, display a first indication information, the first indication information is used to indicate that the blank to be detected is the first blank, and the tensile performance of the first blank is qualified; if not, display a second indication information, the second indication information is used to indicate that the blank to be detected is the second blank, and the tensile performance of the second blank is unqualified.

According to a third aspect of the present disclosure, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method of the first aspect.

According to a fourth aspect of the present disclosure, there is provided a non-transitory computer-readable storage medium storing computer instructions, the computer instructions being used to cause a computer to execute the method according to the first aspect.

According to a fifth aspect of the present disclosure, there is provided a computer program product, comprising a computer program, which implements the method according to the first aspect when executed by a processor.

It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description.

BRIEF DESCRIPTION OF THE DRAWINGS

The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure.

FIG1 is a schematic flow chart of an intelligent detection method for tensile properties of a high-temperature alloy ring forging blank provided in an embodiment of the present disclosure;

FIG2 is another schematic flow chart of the intelligent detection method for tensile properties of a high-temperature alloy ring forging blank provided by an embodiment of the present disclosure;

FIG3 is another schematic diagram of a process of an intelligent detection method for tensile properties of a high-temperature alloy ring forging blank provided in an embodiment of the present disclosure;

FIG4 is a schematic diagram of the composition of an intelligent detection device for tensile properties of a high-temperature alloy ring forging blank provided in an embodiment of the present disclosure;

FIG. 5 is a schematic block diagram of an exemplary electronic device 500 provided by an embodiment of the present disclosure and which can be used to implement an embodiment of the present disclosure.

Detailed ways

The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

It should be understood that in the embodiments of the present disclosure, the character "/" generally indicates that the objects associated with each other are in an "or" relationship. The terms "first", "second", etc. are used only for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features.

Aviation ring forgings are an important manufacturing component in the aerospace industry. The manufacturing process of aviation ring forgings goes through multiple steps, including material selection, prefabricated billet heating, forging, processing, heat treatment and surface treatment. During the material selection step, it is necessary to conduct a metal tensile test on the alloy forging billet used to manufacture aviation ring forgings. The metal tensile test is the most basic test in mechanical properties, and it is also one of the important test items for inspecting metal materials and characterizing their intrinsic quality. The tensile properties of metals are an important indicator for evaluating metal materials, which can clearly reflect the elasticity, elastoplasticity and fracture characteristics of the material when subjected to tensile external forces. Therefore, when selecting materials, it is necessary to conduct a material tensile test on the alloy forging billet to detect whether the tensile properties of the alloy forging billet are qualified.

Exemplarily, before the alloy forging blanks for producing aviation ring forgings are processed, they need to be subjected to metal tensile tests to verify that the tensile properties of the alloy forging blanks are qualified. For the same batch of alloy forging blanks, when the metal tensile test is carried out, several alloy forging blanks will be randomly selected for metal tensile tests, and a qualified rate threshold of the alloy forging blanks can be set. When the qualified rate of the selected several alloy forging blanks exceeds the qualified rate threshold, it can be indicated that this batch of alloy forging blanks is qualified, and this batch of alloy forging blanks can be used for casting aviation ring forgings. When the qualified rate of the selected several alloy forging blanks does not exceed the qualified rate threshold, it can be indicated that this batch of alloy forging blanks is unqualified, and this batch of alloy forging blanks cannot be used for casting aviation ring forgings.

For example, there are 100 alloy forgings in the same batch, and 10 of them are randomly selected for metal tensile testing, and the qualified rate threshold can be set as: 80%. When the qualified alloy forgings in the 10 randomly selected alloy forgings exceed 80%, it can be said that this batch of alloy forgings is qualified, and this batch of alloy forgings can be used for casting aviation ring forgings. When the qualified alloy forgings in the 10 randomly selected alloy forgings do not exceed 80%, it can be said that this batch of alloy forgings is unqualified, and this batch of alloy forgings cannot be used for casting aviation ring forgings.

At present, the tensile properties of alloy forging blanks mainly rely on manual operation.

Exemplarily, the testing of tensile properties of alloy forging blanks mainly includes the following steps: preparing test pieces, adjusting the testing machine, clamping the test pieces, inspecting and testing, conducting tests, removing the test pieces, and measuring and recording. During the testing process, manual operations are mainly relied upon.

For example, in the above-mentioned measurement and recording steps, the alloy forging blank after stretching is mainly measured and recorded manually.

However, the above method of manually testing the tensile properties of the alloy forging blank has low testing efficiency and low accuracy.

For example, manual measurement of alloy forging blanks after stretching may lead to inaccurate measurement results. Moreover, when conducting tensile property tests on a large number of alloy forging blanks, manual measurement and recording may lead to low work efficiency, affecting the production efficiency of aviation ring forgings.

Against this background, the present disclosure provides an intelligent detection method for the tensile properties of a high-temperature alloy ring forging blank, which can improve the accuracy and efficiency of the tensile properties detection of the blank to be detected.

For example, the execution subject of the intelligent detection method of the tensile properties of the high-temperature alloy ring forging blank may be a computer or a server, or may be other equipment with data processing capabilities. The execution subject of the method is not limited here.

In some embodiments, the server may be a single server, or a server cluster composed of multiple servers. In some implementations, the server cluster may also be a distributed cluster. The present disclosure does not limit the specific implementation of the server.

Fig. 1 is a schematic flow chart of an intelligent detection method for tensile properties of a high-temperature alloy ring forging blank provided in an embodiment of the present disclosure. As shown in Fig. 1, in some embodiments, the method may include steps S101-S105.

S101, testing a blank to be tested by a tensile testing machine to obtain a target image of the blank to be tested, wherein the target image includes a target stress-strain curve.

Exemplarily, the shape and size processing quality of the blank to be tested have a certain influence on the tensile test of the blank to be tested. When selecting the blank to be tested, blanks of various shapes and sizes can be selected. For example, plate (thin material) samples, bar samples, pipe samples, wire samples, profile samples, and casting samples can be selected. In order to facilitate the tensile performance test of the blank to be tested, each blank to be tested may include a clamping section, a transition section, and a parallel section. The transition section of the blank to be tested can use an arc shape so that the clamping section and the parallel section are smoothly connected; the parallel section must be kept smooth and uniform to ensure the unidirectional stress state on the surface of the blank to be tested, so as to eliminate the stress concentration of the blank to be tested. The equipment for performing the tensile performance test can be a tensile testing machine, wherein the tensile testing machine can include four parts: a tensile mechanism, a sample clamping mechanism, a recording mechanism, and a force measuring mechanism. When conducting a tensile test, a clamping mechanism can be used to clamp the clamping section of the blank to be tested. In order to ensure the stability of the clamping of the blank to be tested during the tensile performance test, a clamping section that matches the clamping mechanism can be set on the blank to be tested, for example, a clamping section of a cylindrical and rectangular chuck. The blank to be tested is fixed on a tensile testing machine, and the tensile mechanism provides a tensile force to stretch the blank to be tested to both sides, and an axial force is applied to the blank to be tested until the blank to be tested breaks. During this period, the data is input into the recording mechanism through the force measuring mechanism, and finally the target image of the blank to be tested is obtained through the recording mechanism of the tensile testing machine, wherein the target image may include a target stress-strain curve, and the parameters of the target stress-strain curve may include: tension and time.

For example, the shape of the blank to be tested is a plate (thin material) sample. The clamping section of the plate (thin material) sample can be clamped by the sample clamping mechanism in the tensile testing machine, and the plate (thin material) sample can be fixed on the tensile testing machine. The tensile mechanism provides tension to stretch the plate (thin material) sample to both sides, and applies axial force to the plate (thin material) sample until the plate (thin material) sample breaks. During this period, the data can be input into the recording mechanism through the force measuring mechanism, and finally the target image of the plate (thin material) sample can be obtained through the recording mechanism of the tensile testing machine.

S102: Compare the target image with a preset standard image to determine the similarity between the target image and the preset standard image, wherein the preset standard image includes a standard stress-strain curve.

Exemplarily, the target image and the preset standard image can be compared by determining the similarity between the target image and the preset standard image based on the similarity between the target stress-strain curve and the preset standard stress-strain curve or by using a pre-trained similarity judgment model.

S103: Determine whether the similarity is greater than a preset similarity threshold.

Exemplarily, different similarity thresholds may be used according to different similarity calculation methods.

For example, taking the similarity judgment model through pre-training as an example, the similarity threshold can be set to 90%. For another example, taking the similarity between the target stress-strain curve and the preset standard stress-strain curve as an example, the similarity threshold can be set to 70%. There is no restriction on the preset similarity here, and it can be determined according to the actual situation.

S104: If yes, display first indication information, where the first indication information is used to indicate that the blank to be tested is the first blank and the tensile property of the first blank is qualified.

Exemplarily, when the similarity between the target image and the preset standard image is greater than a preset similarity threshold, the blank to be detected currently being tested can be judged to be a qualified first blank. According to the qualified condition of the blank to be detected currently being tested, first information can be generated and displayed to indicate that the blank to be detected is a qualified first blank.

For example, the preset similarity threshold may be 5, and the similarity between the target image and the preset standard image may be 5.5. If the similarity between the target image and the preset standard image is greater than the preset similarity threshold, it indicates that the blank to be tested is a qualified blank.

S105. If not, display second indication information, where the second indication information is used to indicate that the blank to be tested is the second blank, and the tensile property of the second blank is unqualified.

For example, the preset similarity threshold may be 5, and the similarity between the target image and the preset standard image may be 4. If the similarity between the target image and the preset standard image is less than the preset similarity threshold, it indicates that the currently tested blank to be detected is an unqualified second blank. According to the qualified condition of the currently tested blank to be detected, the second information may be generated and displayed to indicate that the blank to be detected is an unqualified second blank.

The present disclosure ensures the comparability and compliance of the tensile test by selecting multiple types of blanks to be tested for tensile testing. By obtaining the target image of the blank to be tested, comparing the target image with the preset standard image, determining the similarity between the target image and the preset standard image, and determining whether the tensile performance of the blank to be tested is qualified based on the similarity, it can effectively evaluate whether the tensile performance of the blank to be tested meets the requirements, optimize the production process, and improve production efficiency.

Fig. 2 is another schematic flow diagram of the intelligent detection method for tensile properties of a high-temperature alloy ring forging blank provided by an embodiment of the present disclosure. As shown in Fig. 2, in some embodiments, step S102 may include steps S201-S202.

S201, extracting a target feature vector of a target image and a standard feature vector of a preset standard image.

Exemplarily, the target feature vector of the target stress-strain curve in the target image and the standard feature vector of the standard stress-strain curve in the preset standard image can be extracted by using a preset feature vector extraction model to extract the target stress-strain curve in the target image and the standard stress-strain curve in the preset standard image, respectively. For example, the curve can be used as input, the feature vector corresponding to the curve can be used as output, and the neural network can be trained to obtain a preset feature vector extraction model. The implementation of the feature vector extraction model is not limited here.

For another example, extracting the target feature vector of the target stress-strain curve in the target image and extracting the standard feature vector of the standard stress-strain curve in the preset standard image can be: respectively calculating some statistics of the target stress-strain curve in the target image and the standard stress-strain curve in the preset standard image, respectively performing Fourier transform on the target stress-strain curve in the target image and the standard stress-strain curve in the preset standard image, respectively performing curve fitting on the target stress-strain curve in the target image and the standard stress-strain curve in the preset standard image, etc., and the method of extracting the target feature vector of the target stress-strain curve in the target image and extracting the standard feature vector of the standard stress-strain curve in the preset standard image is not limited herein.

S202: Determine the similarity between the target image and a preset standard image according to the similarity between the target feature vector and the standard feature vector.

Exemplarily, the similarity between the target feature vector and the standard feature vector may be determined by cosine similarity, Euclidean distance, Manhattan distance, Pearson correlation coefficient, etc., and the similarity between the target feature vector and the standard feature vector may be determined based on the similarity between the target feature vector and the standard feature vector. The similarity between the target feature vector and the standard feature vector may be used as the similarity between the target stress-strain curve in the target image and the standard stress-strain curve in the preset standard image, or as the similarity between the target image and the preset standard image.

For example, the target feature vector can be The standard eigenvector can be The cosine similarity can be used to determine the similarity between the target feature vector and the standard feature vector, and the calculated result can be 80%. The calculated similarity of 80% between the target feature vector and the standard feature vector can be used as the similarity between the target stress-strain curve and the preset standard stress-strain curve, that is, the similarity between the target stress-strain curve and the preset standard stress-strain curve is 80%.

This embodiment extracts the target characteristic vector of the target stress-strain curve and the standard characteristic vector of the preset standard stress-strain curve, and determines the similarity between the target stress-strain curve and the preset standard stress-strain curve according to the similarity between the target characteristic vector and the standard characteristic vector. The similarity between the target stress-strain curve and the preset standard stress-strain curve can be quickly calculated, thereby determining whether the tensile properties of the corresponding blank to be tested are qualified.

In some embodiments, the intelligent detection method for the tensile properties of the high-temperature alloy ring forging blank may also include: inputting the target image into a pre-trained image classification model, outputting the classification result of the target image, the classification result being the probability that the target image is a standard image, and the pre-trained image classification model uses standard images and non-standard images as input, marks the standard image as 1, and marks the non-standard image as 0 as output, and trains the neural network.

Exemplarily, the classification result may be the probability that the target image is a standard image, and the probability that the target image is an image of a qualified blank may be used as the similarity between the target image and the preset standard image. The pre-trained image classification model may be to take a high-temperature alloy forging blank inspection image training set as input, the high-temperature alloy forging blank inspection image training set may include standard images and non-standard images, mark the standard image as 1, and mark the non-standard image as 0 as output, train the neural network, and obtain the pre-trained image classification model, and the implementation of the pre-trained image classification model is not limited here.

This embodiment can improve classification accuracy by inputting the target image into a pre-trained image classification model and outputting the classification result of the target image, and has good interpretability and visualization effects, thereby improving the scalability and flexibility of detecting the blank to be detected.

Fig. 3 is another flow chart of the intelligent detection method for tensile properties of high temperature alloy ring forging blank provided by the embodiment of the present disclosure. As shown in Fig. 3, in some embodiments, the preset standard image is selected from a standard image library, the standard image library includes standard images corresponding to at least two different types of blanks, and before comparing the target image with the preset standard image, the intelligent detection method for tensile properties of high temperature alloy ring forging blank further includes S301-S302.

S301, obtaining the target blank type of the blank to be inspected.

For example, the target blank types of the blank to be inspected may include: plate blanks, bar blanks, tube blanks, wire blanks, profile blanks, and casting blanks. Each target blank type of different shapes and sizes may correspond to a different standard stress-strain curve in the standard image library.

For example, the standard stress-strain curve of the plate blank may be curve A, and the standard stress-strain curve of the bar blank may be curve B. Before comparing the target stress-strain curve with the preset standard stress-strain curve, the target blank type of the blank to be tested needs to be obtained first.

S302 . Selecting a preset standard image corresponding to the target blank type from a standard image library according to the target blank type.

Exemplarily, the standard image library may contain all target blank types of different shapes and sizes. A preset standard image corresponding to the target blank type may be selected from the standard image library according to the target blank type.

For example, the standard image library may include three standard stress-strain curves, namely, curve A, curve B, and curve C, and the corresponding blank types are: plate blank, bar blank, and tube blank. When the target blank type of the blank to be detected is a plate blank, the preset standard image corresponding to the target blank type of the blank to be detected is determined to be curve A.

This embodiment can provide a more accurate basis by obtaining the target blank type of the blank to be tested and selecting a preset standard image corresponding to the target blank type from the standard image library according to the target blank type, which helps to improve the accuracy of tensile performance testing of the blank to be tested.

In some embodiments, the intelligent detection method for the tensile properties of the high-temperature alloy ring forging blank also includes: obtaining the yield strength, tensile strength, elongation and shrinkage of the first blank through a tensile testing machine, and judging whether the first blank is qualified based on the yield strength, tensile strength, elongation and shrinkage of the first blank.

Exemplarily, the yield strength of the first blank is a sign that the first blank begins to produce macroscopic plastic deformation when stretched, and the yield point expressed by tensile force is called yield strength. In the target stress-strain curve, the point before the first drop in force when the first blank yields is the upper yield point, the minimum force value during the yield period is called the lower yield point, and the tensile forces corresponding to the upper and lower yield points are called the upper and lower yield strengths. Since the value of the lower yield strength is relatively stable and has good reproducibility, the lower yield strength ReL can be selected as the yield strength. In addition, taking the yield strength as the standard, the calculation method of the allowable stress can be:

[σ]＝ReL/n Formula (1)

In formula (1), [σ] is the specified allowable stress, ReL is the yield strength of the first blank, and n is the safety factor, which can take a value of at least 2.

For another example, the tensile strength of the first blank is the critical value of the transition of the first blank from uniform plastic deformation to local concentrated plastic deformation, and is also the maximum bearing capacity of the first blank under static tensile conditions. The tensile strength can characterize the resistance to the maximum uniform plastic deformation of the first blank. Before the first blank is subjected to the maximum tensile stress, the deformation is uniform, but after the necking phenomenon occurs, the tensile strength will immediately decrease, and the necking phenomenon is the concentrated deformation stage. The maximum force value Fm of the tensile test process can be found in the target stress-strain curve, and the tensile strength Rm is obtained by dividing it by the original cross-sectional area So of the first blank. The calculation method of the tensile strength can be:

Rm＝Fm/So Formula (2)

In formula (2), Rm is the tensile strength, unit: MPa; Fm is the maximum tensile force that the first blank can withstand before breaking, unit: N; So is the original cross-sectional area of the first blank, unit: square millimeter.

For another example, in the target stress-strain curve, the abscissa is the elongation of the first blank, and the elongation after the first blank is broken can be used as an indicator for testing the elongation of the first blank.

For another example, the toughness and brittleness of the first blank are determined according to the amount of plastic deformation under certain conditions, and the shrinkage rate of the first blank can be calculated as follows:

Z＝(So-Su)/So×100％ Formula (3)

In formula (3), Z is the shrinkage rate of the first blank, So is the original cross-sectional area of the first blank, and Su is the minimum cross-sectional area of the first blank after fracture.

It can be stipulated that when the shrinkage rate of the first blank is less than 5%, it is a brittle fracture, otherwise it is a ductile material.

Corresponding qualified conditions can be set for the yield strength, tensile strength, elongation and shrinkage of the qualified first blank, respectively. When the yield strength, tensile strength, elongation and shrinkage of the qualified first blank are all qualified, the first blank can be determined to be qualified. When any one of the yield strength, tensile strength, elongation and shrinkage of the qualified first blank is unqualified, the first blank can be determined to be unqualified.

This embodiment can improve the quality of the first blank by judging whether the first blank is qualified according to the yield strength, tensile strength, elongation and shrinkage of the first blank, thereby improving the production quality of aviation ring forgings.

In some embodiments, the blank to be tested includes a clamping section, a transition section and a parallel section. The target image is obtained by testing the parallel section of the blank to be tested with a tensile testing machine. The length ratio relationship between the clamping section, the transition section and the parallel section is 3:2:5.

In this embodiment, the blank to be tested includes a clamping section, a transition section and a parallel section. The clamping section of the blank to be tested can be used for the tensile testing machine to clamp the blank to be tested; the transition section of the blank to be tested is used to smoothly transition the diameter or shape change of the clamping section and the parallel section to reduce the concentration of material stress; the parallel section of the blank to be tested is used for final processing or manufacturing and is the most important area in the blank to be tested. The length ratio relationship between the clamping section, the transition section and the parallel section is 3:2:5, which can improve the stability and accuracy of processing, reduce material waste, improve the processing process, and enhance the flexibility of the process.

In an exemplary embodiment, the present disclosure also provides an intelligent detection device for the tensile properties of a high-temperature alloy ring forging blank, which can be used to implement the intelligent detection method for the tensile properties of a high-temperature alloy ring forging blank as in the above-mentioned embodiment. FIG4 is a schematic diagram of the composition of the intelligent detection device for the tensile properties of a high-temperature alloy ring forging blank provided in an embodiment of the present disclosure. As shown in FIG4, the device may include: an acquisition unit 401 and a judgment unit 402.

The acquisition unit 401 is used to test the blank to be tested by a tensile testing machine, and acquire a target image of the blank to be tested, wherein the target image includes a target stress-strain curve.

The judgment unit 402 is used to compare the target image with the preset standard image to determine the similarity between the target image and the preset standard image, wherein the preset standard image includes a standard stress-strain curve; judge whether the similarity is greater than a preset similarity threshold; if so, display the first indication information, the first indication information is used to indicate that the blank to be detected is the first blank, and the tensile performance of the first blank is qualified; if not, display the second indication information, the second indication information is used to indicate that the blank to be detected is the second blank, and the tensile performance of the second blank is unqualified.

Optionally, the judgment unit 402 is specifically used to: extract a target characteristic vector of the target stress-strain curve and a standard characteristic vector of a preset standard stress-strain curve; and determine the similarity between the target characteristic vector and the standard characteristic vector and the preset standard stress-strain curve according to the similarity between the target characteristic vector and the standard characteristic vector.

Optionally, the judgment unit 402 is further configured to: input the target image into a pre-trained image classification model, and output a classification result of the target image.

Optionally, the preset standard image is selected from a standard image library. Before comparing the target image with the preset standard image, the judgment unit 402 is also used to: obtain the target blank type of the blank to be inspected; and select a preset standard image corresponding to the target blank type from the standard image library according to the target blank type.

Optionally, the judgment unit 402 is further used to: obtain the yield strength, tensile strength, elongation and shrinkage of the first blank through a tensile testing machine, and judge whether the blank to be tested is qualified according to the yield strength, tensile strength, elongation and shrinkage of the blank to be tested.

Optionally, the parameters of the target stress-strain curve include tension and time.

Optionally, the target billet type includes at least one of the following: plate billet, bar billet, tube billet, wire billet, profile billet, and casting billet.

Optionally, the blank to be inspected includes a clamping section, a transition section and a parallel section.

In the technical solution disclosed herein, the acquisition, storage and application of user personal information involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium, and a computer program product.

In an exemplary embodiment, an electronic device includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the method described in the above embodiments.

In an exemplary embodiment, the readable storage medium may be a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause a computer to execute the method according to the above embodiments.

In an exemplary embodiment, a computer program product includes a computer program, and when the computer program is executed by a processor, the method according to the above embodiments is implemented.

FIG5 shows a schematic block diagram of an example electronic device 500 that can be used to implement an embodiment of the present disclosure. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and/or required herein.

As shown in Figure 5, electronic device 500 includes a computing unit 501, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 502 or a computer program loaded from a storage unit 508 into a random access memory (RAM) 503. In RAM 503, various programs and data required for the operation of electronic device 500 can also be stored. Computing unit 501, ROM 502 and RAM 503 are connected to each other via bus 504. Input/output (I/O) interface 505 is also connected to bus 504.

A number of components in the electronic device 500 are connected to the I/O interface 505, including: an input unit 506, such as a keyboard, a mouse, etc.; an output unit 507, such as various types of displays, speakers, etc.; a storage unit 508, such as a disk, an optical disk, etc.; and a communication unit 509, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 509 allows the electronic device 500 to exchange information/data with other devices through a computer network such as the Internet and/or various telecommunication networks.

The computing unit 501 may be a variety of general and/or special processing components with processing and computing capabilities. Some examples of the computing unit 501 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 501 performs the various methods and processes described above, such as the intelligent detection method for the tensile properties of the high-temperature alloy ring forging blank. For example, in some embodiments, the intelligent detection method for the tensile properties of the high-temperature alloy ring forging blank may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 508. In some embodiments, part or all of the computer program may be loaded and/or installed on the electronic device 500 via the ROM 502 and/or the communication unit 509. When the computer program is loaded into the RAM 503 and executed by the computing unit 501, one or more steps of the intelligent detection method for the tensile properties of the high-temperature alloy ring forging blank described above may be performed. Alternatively, in other embodiments, the computing unit 501 may be configured to execute the intelligent detection method of the tensile properties of the high-temperature alloy ring forging blank by any other appropriate manner (for example, by means of firmware).

Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and/or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, implements the functions/operations specified in the flow chart and/or block diagram. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communications network). Examples of communications networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims (19)

1. An intelligent detection method for tensile properties of a high-temperature alloy ring forging blank, the method comprising: Testing the blank to be tested by a tensile testing machine to obtain a target image of the blank to be tested, wherein the target image includes a target stress-strain curve; Comparing the target image with a preset standard image to determine the similarity between the target image and the preset standard image, wherein the preset standard image includes a standard stress-strain curve; Determining whether the similarity is greater than a preset similarity threshold; If yes, first indication information is displayed, where the first indication information is used to indicate that the blank to be tested is the first blank, and the tensile performance of the first blank is qualified; If not, the second indication information is displayed, where the second indication information is used to indicate that the blank to be tested is the second blank, and the tensile performance of the second blank is unqualified. 2. The method according to claim 1, wherein comparing the target image with a preset standard image to determine the similarity between the target image and the preset standard image comprises: Extracting a target feature vector of the target image and a standard feature vector of the preset standard image; The similarity between the target image and the preset standard image is determined according to the similarity between the target feature vector and the standard feature vector. 3. The method according to claim 1, further comprising: The target image is input into a pre-trained image classification model, and a classification result of the target image is output, wherein the classification result is the probability that the target image is a standard image. The pre-trained image classification model is obtained by training a neural network by using standard images and non-standard images as inputs, marking standard images as 1 and marking non-standard images as 0 as outputs. 4. The method according to claim 1, wherein the preset standard image is selected from a standard image library, wherein the standard image library includes standard images corresponding to at least two different types of blanks, and before comparing the target image with the preset standard image, the method further comprises: Acquire the target blank type of the blank to be detected; The preset standard image corresponding to the target blank type is selected from a standard image library according to the target blank type. 5. The method according to any one of claims 1 to 5, further comprising: The yield strength, tensile strength, elongation and shrinkage of the first blank are obtained by the tensile testing machine, and whether the first blank is qualified is determined based on the yield strength, tensile strength, elongation and shrinkage of the first blank. The method according to claim 1 , wherein the parameters of the target stress-strain curve include tension and time. 7. The method according to claim 4, wherein the target billet type comprises at least one of the following: plate billet, bar billet, tube billet, wire billet, profile billet, and casting billet. 8. According to the method described in any one of claims 1 to 7, the blank to be tested includes a clamping section, a transition section and a parallel section, the target image is obtained by testing the parallel section of the blank to be tested by the tensile testing machine, and the length ratio relationship between the clamping section, the transition section and the parallel section is 3:2:5. 9. An intelligent detection device for tensile properties of a high-temperature alloy ring forging blank, the device comprising: An acquisition unit, specifically used to test the blank to be tested by a tensile testing machine, and acquire a target image of the blank to be tested, wherein the target image includes a target stress-strain curve; The judgment unit is specifically used to compare the target image with a preset standard image to determine the similarity between the target image and the preset standard image, wherein the preset standard image includes a standard stress-strain curve; judge whether the similarity is greater than a preset similarity threshold; if so, display a first indication information, wherein the first indication information is used to indicate that the blank to be detected is a first blank, and the tensile performance of the first blank is qualified; if not, display a second indication information, wherein the second indication information is used to indicate that the blank to be detected is a second blank, and the tensile performance of the second blank is unqualified. 10. The device according to claim 9, wherein the judging unit is specifically configured to: Extracting a target feature vector of the target image and a standard feature vector of the preset standard image; The similarity between the target image and the preset standard image is determined according to the similarity between the target feature vector and the standard feature vector. 11. The device according to claim 9, wherein the determining unit is further configured to: The target image is input into a pre-trained image classification model, and a classification result of the target image is output, wherein the classification result is the probability that the target image is a standard image. The pre-trained image classification model is obtained by training a neural network by using standard images and non-standard images as inputs, marking standard images as 1 and marking non-standard images as 0 as outputs. 12. The device according to claim 9, wherein the preset standard image is selected from a standard image library, wherein the standard image library includes standard images corresponding to at least two different types of blanks, and before comparing the target image with the preset standard image, the judgment unit is further configured to: Acquire the target blank type of the blank to be detected; The preset standard image corresponding to the target blank type is selected from a standard image library according to the target blank type. 13. The device according to any one of claims 9 to 12, wherein the judging unit is further configured to: The yield strength, tensile strength, elongation and shrinkage of the first blank are obtained by the tensile testing machine, and whether the first blank is qualified is determined based on the yield strength, tensile strength, elongation and shrinkage of the first blank. 14. The device according to claim 9, wherein the parameters of the target stress-strain curve include tension and time. 15 . The device according to claim 12 , wherein the target billet type comprises at least one of the following: a plate billet, a bar billet, a tube billet, a wire billet, a profile billet, and a casting billet. 16. According to the device according to any one of claims 9 to 15, the blank to be tested includes a clamping section, a transition section and a parallel section, the target image is obtained by detecting the parallel section of the blank to be tested by the tensile testing machine, and the length ratio relationship between the clamping section, the transition section and the parallel section is 3:2:5. 17. An electronic device comprising: at least one processor; and a memory communicatively connected to the at least one processor; The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method according to any one of claims 1 to 8. 18. A non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause a computer to execute the method according to any one of claims 1 to 8. 19. A computer program product, comprising a computer program, which, when executed by a processor, implements the method according to any one of claims 1 to 8.