Long material defect detection method, device, electronic equipment and storage medium

Abstract

The present invention provides a long material defect detection method, device, electronic device and storage medium, belonging to the field of metallurgical technology. The method comprises: determining the expected defect area and defect appearance information of the long material in the appearance image of the long material; determining the detection area for the tapping test on the long material based on the expected defect type and expected defect area corresponding to the production process of the long material; determining the defect volume of the long material based on the vibration response signal generated by the long material after the tapping test; determining the three-dimensional defect information of the long material based on the expected defect type, defect appearance information and defect volume, so as to grind the long material based on the three-dimensional defect information. The present invention can perform non-destructive detection of defect information inside the long material and improve the accuracy of defect detection.

Description

Technical Field

[0001] The present invention relates to the technical field of long material defect detection, and in particular to a long material defect detection method, device, electronic equipment and storage medium. Background Art

[0002] As a key raw material in industrial production, the quality of long products directly affects the performance of the final product. By detecting defects in long products, unqualified products can be discovered and handled in a timely manner to ensure that product quality meets standard requirements. For defects that can be repaired, such as small cracks or holes, grinding can be considered and continued normal use after proper disposal.

[0003] At present, non-destructive testing of defects in long materials mainly focuses on surface defects. It is difficult to identify internal defects and tiny appearance defects, and it is also difficult to identify the depth of surface defects. The detection method for internal defects in long materials requires the use of complex technology or destructive testing. The process is complicated and costly, which is not conducive to comprehensive implementation, resulting in the current inaccurate defect detection effect on long materials. Summary of the invention

[0004] The embodiments of the present invention provide a method, device, electronic device and storage medium for detecting defects in long materials, so as to solve the problem that the defect detection effect of long materials is not accurate enough.

[0005] In a first aspect, an embodiment of the present invention provides a method for detecting defects in a long material, comprising:

[0006] Determining the expected defect area and defect appearance information of the long material in the appearance image of the long material;

[0007] Determine the detection area for the tap test on the long product based on the expected defect type and expected defect area corresponding to the production process of the long product;

[0008] Determining the defect volume of the long material based on the vibration response signal generated by the long material after the tapping test;

[0009] Based on the expected defect type, defect appearance information and defect volume, the three-dimensional defect information of the long material is determined, so as to grind the long material based on the three-dimensional defect information.

[0010] In a possible implementation, determining a detection area for performing a tapping test on the long material based on an expected defect type and an expected defect area corresponding to a production process of the long material includes:

[0011] Based on the expected defect type and expected defect area corresponding to the production process of the long material, a preset defect detection area comparison table is searched to obtain the detection area for the tapping test on the long material.

[0012] In a possible implementation, before determining the detection area for performing a knock test on the long material based on the expected defect type and the expected defect area corresponding to the production process of the long material, the method further includes:

[0013] Acquire vibration response signals of a plurality of long materials; wherein each long material has different defect types and defect areas, each long material corresponds to a plurality of vibration response signals, and each vibration response signal corresponding to each long material is obtained by performing a tapping test on a different area of ​​the long material;

[0014] For each defect type and defect area, the vibration response signals corresponding to the defect type and defect area are grouped according to the knocking test area, and the average linearity of the vibration response signals in each group is calculated. The knocking test area where the group with the largest average linearity is located is used as the detection area corresponding to the defect type and defect area;

[0015] The defect types and the detection areas corresponding to the defect areas are combined to obtain a defect detection area comparison table.

[0016] In a possible implementation, determining the defect volume of the long material based on a vibration response signal generated by the long material after a tapping test includes:

[0017] Separate the overlapping signals of the vibration response signals generated by the long material after the knocking test to obtain the main vibration signal and the defect vibration signal;

[0018] Based on the ratio of the signal energies of the main vibration signal and the defect vibration signal, the volume ratio of the defect part to the main part is determined, and the defect volume of the long material is determined based on the volume ratio.

[0019] In a possible implementation, de-overlapping the vibration response signal to separate it into a main vibration signal and a defect vibration signal includes:

[0020] Performing subspace separation on the vibration response signal to obtain each subspace corresponding to the vibration response signal;

[0021] Determine a separation matrix of the vibration response signal according to mutual information values ​​corresponding to each subspace and the vibration response signal;

[0022] Separating the vibration response signal according to the separation matrix to obtain at least two vibration signal components;

[0023] The vibration signal component with the largest signal energy is taken as the main vibration signal, and the remaining vibration signal components are taken as defect vibration signals.

[0024] In a possible implementation, based on the expected defect type, defect appearance information, and defect volume, three-dimensional defect information of the long material is determined, including:

[0025] Searching for multiple defect shapes matching the expected defect type and defect appearance information in a preset defect shape library;

[0026] For each defect shape, adjusting the size of the defect shape based on the defect volume and the preset volume of the defect shape, and determining the endpoint coordinates of the defect shape;

[0027] Each adjusted defect shape is superimposed below the defect surface of the long material as the defect area of ​​the long material, and the end point coordinates of the defect area are used as the three-dimensional defect information of the long material.

[0028] In a second aspect, an embodiment of the present invention provides a long material defect detection device, comprising:

[0029] An appearance inspection module, used to determine the expected defect area and defect appearance information of the long material in the appearance image of the long material;

[0030] A test positioning module, used to determine the detection area for the percussion test on the long material based on the expected defect type and expected defect area corresponding to the production process of the long material;

[0031] A volume detection module, for determining the defect volume of the long material based on a vibration response signal generated by the long material after the tapping test;

[0032] The three-dimensional prediction module is used to determine the three-dimensional defect information of the long material based on the expected defect type, defect appearance information and defect volume, so as to grind the long material based on the three-dimensional defect information.

[0033] In a third aspect, an embodiment of the present invention provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the processor implements the steps of the method described in the first aspect or any possible implementation manner of the first aspect.

[0034] In a fourth aspect, an embodiment of the present invention 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, the steps of the method described in the first aspect or any possible implementation of the first aspect are implemented.

[0035] The embodiment of the present invention provides a method, device, electronic device and storage medium for detecting defects in long materials. The appearance and location of defects are estimated through the appearance image of the long materials, and a suitable knocking test area is selected in combination with the possible defect types. The defect volume is estimated through the vibration response signal, and the appearance information of the defect and the defect volume are combined to estimate the three-dimensional information of the internal defects of the long materials. The present invention introduces the vibration response signal on the basis of image detection, which can perform non-destructive detection of the defect information inside the long materials and improve the accuracy of defect detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0037] Figure 1 is a flow chart of a method for detecting defects in long materials provided by an embodiment of the present invention;

[0038] Figure 2 It is a structural schematic diagram of a long material defect detection device provided by an embodiment of the present invention;

[0039] Figure 3 It is a schematic diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0040] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present invention. However, it should be clear to those skilled in the art that the present invention may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present invention.

[0041] In order to make the purpose, technical solutions and advantages of the present invention more clear, specific embodiments will be described below in conjunction with the accompanying drawings.

[0042] See also Figure 1 , which shows a flow chart of the implementation of the long material defect detection method provided by an embodiment of the present invention, and is described in detail as follows:

[0043] Step 101: determining an expected defect region and defect appearance information of the long material in an appearance image of the long material.

[0044] In this embodiment, the present invention is specifically used for long products with smooth surfaces, including seamless steel pipes and bars. In order to ensure the performance and reliability of the product, it is necessary to detect the defects of the long products after production, and to grind the long products with repair value to improve the yield rate.

[0045] The defects of long products mainly include cracks, rust, pits, pores, segregation, oxide scale, etc. These defects are reflected to a certain extent in the appearance of long products. The location of the defects on the surface of the long products, as well as the shape, color, size, etc. of the defective part on the surface of the long products can be identified through the appearance image. The shape, color, size, etc. of the defective part on the surface of the long products belong to the defect appearance information.

[0046] Partitioning the long material, for example, into n equal-length segments, each segment being a region, can simplify the defect detection process. After partitioning, the region where the defect is located on the surface of the long material is the defect region of the long material. In addition, since the location of the defect in this step is only based on the appearance of the long material, it may not be accurate, so the determined defect region is called the expected defect region.

[0047] Step 102: determining a detection area for performing a tapping test on the long material based on the expected defect type and expected defect area corresponding to the production process of the long material.

[0048] In this embodiment, the tapping test is a commonly used non-destructive testing method, which can be used to detect whether there are defects such as cracks, slag inclusions, pores, etc. inside the material. Selecting a suitable tapping position is of great significance to the effect of the tapping test.

[0049] Specifically, the knocking test is to analyze the vibration response signal of the long material after knocking. The vibration response signal is mainly composed of the response signal generated by the normal part of the long material and the response signal generated by the defective part. According to the two types of response signals in the vibration response signal, the specific information of the long material defect can be determined. Therefore, the detection area can be selected according to the difficulty of analyzing the vibration response signal. The defect type and defect area are the influencing factors of the vibration response signal parameters.

[0050] Expected defect types refer to the types of defects that may exist in long products, which are usually related to the production process. Therefore, the corresponding expected defect types can be found based on the production process.

[0051] Step 103: determining the defect volume of the long material based on the vibration response signal generated by the long material after the tapping test.

[0052] In this embodiment, the vibration response signal is composed of a main vibration signal and a defect vibration signal, wherein the main vibration signal is generated by the defect-free part of the long material, and the defect vibration signal is generated by the defective part of the long material. The characteristics of the vibration response signal are affected by parameters such as the composition, density, shape and volume of the object. Since the defect-free part and the defective part of the long material differ in many aspects, although the volume of the defective part cannot be directly determined using the vibration response signal, the relationship between the characteristics of the vibration response signal and the volume of the object can be used. For example, for a given excitation, an object with a larger volume may have a smaller amplitude because of its larger mass and inertia. However, due to its large volume, even if the amplitude is small, the total vibration energy may be larger. By analyzing the relationship between the main vibration signal and the defect vibration signal and converting it into the relationship between the volume of the defect-free part and the defective part of the long material, the defective volume of the long material can be identified.

[0053] Step 104 , based on the expected defect type, defect appearance information and defect volume, determine the three-dimensional defect information of the long material, so as to perform grinding on the long material based on the three-dimensional defect information.

[0054] In this embodiment, based on the defect type and defect appearance information, the shape of the defect inside the long material can be estimated. By adding the defect volume on this basis, the three-dimensional size of the defect inside the long material can be estimated, that is, the three-dimensional defect information of the long material.

[0055] In order to increase the output and utilization rate of long products, long products with repair value can be ground to remove the defective parts of the long products. Accurately determining the three-dimensional information of the defects of the long products can improve the grinding effect of the long products.

[0056] The embodiment of the present invention estimates the appearance of defects and the location of defects through the appearance image of the long material, selects a suitable knocking test area based on the possible defect types, estimates the defect volume through the vibration response signal, and then combines the appearance information of the defect with the defect volume to estimate the three-dimensional information of the internal defects of the long material. The present invention introduces the vibration response signal on the basis of image detection, which can perform non-destructive detection of the defect information inside the long material and improve the accuracy of defect detection.

[0057] In a possible implementation, determining a detection area for performing a tapping test on the long material based on an expected defect type and an expected defect area corresponding to a production process of the long material includes:

[0058] Based on the expected defect type and expected defect area corresponding to the production process of the long material, a preset defect detection area comparison table is searched to obtain the detection area for the tapping test on the long material.

[0059] In this embodiment, the defect detection area comparison table contains the most suitable detection area for each defect type and defect area, and can be directly searched based on this information of the long material.

[0060] In a possible implementation, before determining the detection area for performing a knock test on the long material based on the expected defect type and the expected defect area corresponding to the production process of the long material, the method further includes:

[0061] Acquire vibration response signals of a plurality of long materials; wherein each long material has different defect types and defect areas, each long material corresponds to a plurality of vibration response signals, and each vibration response signal corresponding to each long material is obtained by performing a tapping test on a different area of ​​the long material;

[0062] For each defect type and defect area, the vibration response signals corresponding to the defect type and defect area are grouped according to the knocking test area, and the average linearity of the vibration response signals in each group is calculated. The knocking test area where the group with the largest average linearity is located is used as the detection area corresponding to the defect type and defect area;

[0063] The defect types and the detection areas corresponding to the defect areas are combined to obtain a defect detection area comparison table.

[0064] In this embodiment, the defect detection area comparison table is pre-constructed according to the knocking vibration response characteristics of the long material. Specifically, a variety of long materials of different materials can be selected, and knocking tests can be performed separately to record the vibration response signals. After the recording is completed, the long materials are subjected to cross-sectional inspection to accurately determine the defect type and defect area of ​​the long materials. After the data is collected, the optimal detection position corresponding to each defect type and defect area is determined according to the linearity of the vibration response signal. Among them, the linearity of the vibration response signal is the linearity of the amplitude and the knocking force. The higher the linearity of the vibration response signal, the higher the response degree of the position to the knocking detection, and the more suitable it is as a detection area for the knocking test.

[0065] In a possible implementation, determining the defect volume of the long material based on a vibration response signal generated by the long material after a tapping test includes:

[0066] Separate the overlapping signals of the vibration response signals generated by the long material after the knocking test to obtain the main vibration signal and the defect vibration signal;

[0067] Based on the ratio of the signal energies of the main vibration signal and the defect vibration signal, the volume ratio of the defect part to the main part is determined, and the defect volume of the long material is determined based on the volume ratio.

[0068] In this embodiment, the main vibration signal is generated by the non-defective portion of the long material, and the defect vibration signal is generated by the defective portion of the long material.

[0069] Signal energy refers to the energy distribution of the signal in time and frequency. The energy of the vibration signal can reflect the intensity or activity of the object's vibration. Therefore, the ratio of the signal energy of the main vibration signal and the defect vibration signal can be used to represent the vibration intensity ratio of the main part and the defect part, and converted into the volume ratio of the defect part to the main part. Based on this, the defect volume can be determined in combination with the overall volume of the long material.

[0070] In a possible implementation, de-overlapping the vibration response signal to separate it into a main vibration signal and a defect vibration signal includes:

[0071] Performing subspace separation on the vibration response signal to obtain each subspace corresponding to the vibration response signal;

[0072] Determine a separation matrix of the vibration response signal according to mutual information values ​​corresponding to each subspace and the vibration response signal;

[0073] Separating the vibration response signal according to the separation matrix to obtain at least two vibration signal components;

[0074] The vibration signal component with the largest signal energy is taken as the main vibration signal, and the remaining vibration signal components are taken as defect vibration signals.

[0075] In this embodiment, subspace signal separation can separate multiple source signals from the mixed signal. The volume of the defective part of the long material is usually much smaller than the volume of the non-defective part, so the signal energy of the defective vibration signal will also be much smaller than the signal energy of the main vibration signal. The vibration signal component with the largest signal energy can be used as the main vibration signal, and the remaining vibration signal components can be used as defective vibration signals.

[0076] In a possible implementation, based on the expected defect type, defect appearance information, and defect volume, three-dimensional defect information of the long material is determined, including:

[0077] Searching for multiple defect shapes matching the expected defect type and defect appearance information in a preset defect shape library;

[0078] For each defect shape, adjusting the size of the defect shape based on the defect volume and the preset volume of the defect shape, and determining the endpoint coordinates of the defect shape;

[0079] Each adjusted defect shape is superimposed below the defect surface of the long material as the defect area of ​​the long material, and the end point coordinates of the defect area are used as the three-dimensional defect information of the long material.

[0080] In this embodiment, the defect shape library contains a variety of defect shapes, which can be collected by destructive testing of the long material. Among the various defect shapes that match the expected defect type and defect appearance information, there is a high probability that the defect shape inside the current long material is included. Combined with the defect volume determined in the above steps, each defect shape can be scaled to make the defect shape closer to the defect inside the current long material.

[0081] In this embodiment, there is no need to further determine the specific defect shape, but all the matched defect shapes are superimposed and integrated. The superimposed shape combination can basically cover the defect area inside the current long material, and the part exceeding the defect area inside the current long material is small, which can be used for long material grinding.

[0082] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.

[0083] The following is an embodiment of the device of the present invention. For details not described in detail therein, reference may be made to the corresponding method embodiment described above.

[0084] Figure 2 The schematic diagram of the structure of the long material defect detection device provided by the embodiment of the present invention is shown. For the convenience of explanation, only the part related to the embodiment of the present invention is shown, which is described in detail as follows:

[0085] like Figure 2 As shown, the long material defect detection device 2 includes:

[0086] An appearance detection module 21 is used to determine the expected defect area and defect appearance information of the long material in the appearance image of the long material;

[0087] A test positioning module 22, for determining a detection area for performing a knock test on the long material based on an expected defect type and an expected defect area corresponding to a production process of the long material;

[0088] A volume detection module 23, for determining the defect volume of the long material based on a vibration response signal generated by the long material after the tapping test;

[0089] The three-dimensional prediction module 24 is used to determine the three-dimensional defect information of the long material based on the expected defect type, defect appearance information and defect volume, so as to perform grinding on the long material based on the three-dimensional defect information.

[0090] In a possible implementation, the test positioning module 22 is specifically used for:

[0091] Based on the expected defect type and expected defect area corresponding to the production process of the long material, a preset defect detection area comparison table is searched to obtain the detection area for the tapping test on the long material.

[0092] In a possible implementation, the test positioning module 22 is further configured to:

[0093] Before determining the detection area for the tapping test on the long material based on the expected defect type and expected defect area corresponding to the production process of the long material, a plurality of vibration response signals of the long materials are obtained; wherein each long material has different defect types and defect areas, each long material corresponds to a plurality of vibration response signals, and each vibration response signal corresponding to each long material is obtained by performing a tapping test on a different area of ​​the long material;

[0094] For each defect type and defect area, the vibration response signals corresponding to the defect type and defect area are grouped according to the knocking test area, and the average linearity of the vibration response signals in each group is calculated. The knocking test area where the group with the largest average linearity is located is used as the detection area corresponding to the defect type and defect area;

[0095] The defect types and the detection areas corresponding to the defect areas are combined to obtain a defect detection area comparison table.

[0096] In a possible implementation, the volume detection module 23 is specifically used to:

[0097] Separate the overlapping signals of the vibration response signals generated by the long material after the knocking test to obtain the main vibration signal and the defect vibration signal;

[0098] Based on the ratio of the signal energies of the main vibration signal and the defect vibration signal, the volume ratio of the defect part to the main part is determined, and the defect volume of the long material is determined based on the volume ratio.

[0099] In a possible implementation, the volume detection module 23 is specifically used to:

[0100] Performing subspace separation on the vibration response signal to obtain each subspace corresponding to the vibration response signal;

[0101] Determine a separation matrix of the vibration response signal according to mutual information values ​​corresponding to each subspace and the vibration response signal;

[0102] Separating the vibration response signal according to the separation matrix to obtain at least two vibration signal components;

[0103] The vibration signal component with the largest signal energy is taken as the main vibration signal, and the remaining vibration signal components are taken as defect vibration signals.

[0104] In a possible implementation, the three-dimensional prediction module 24 is specifically used for:

[0105] Searching for multiple defect shapes matching the expected defect type and defect appearance information in a preset defect shape library;

[0106] For each defect shape, adjusting the size of the defect shape based on the defect volume and the preset volume of the defect shape, and determining the endpoint coordinates of the defect shape;

[0107] Each adjusted defect shape is superimposed below the defect surface of the long material as the defect area of ​​the long material, and the end point coordinates of the defect area are used as the three-dimensional defect information of the long material.

[0108] The embodiment of the present invention estimates the appearance of defects and the location of defects through the appearance image of the long material, selects a suitable knocking test area based on the possible defect types, estimates the defect volume through the vibration response signal, and then combines the appearance information of the defect with the defect volume to estimate the three-dimensional information of the internal defects of the long material. The present invention introduces the vibration response signal on the basis of image detection, which can perform non-destructive detection of the defect information inside the long material and improve the accuracy of defect detection.

[0109] Figure 3 Schematic diagram of an electronic device provided by an embodiment of the present invention. Figure 3 As shown, the electronic device 3 of this embodiment includes: a processor 30, a memory 31, and a computer program 32 stored in the memory 31 and executable on the processor 30. When the processor 30 executes the computer program 32, the steps in the above-mentioned long material defect detection method embodiments are implemented. Alternatively, when the processor 30 executes the computer program 32, the functions of the modules / units in the above-mentioned device embodiments are implemented.

[0110] Exemplarily, the computer program 32 may be divided into one or more modules / units, which are stored in the memory 31 and executed by the processor 30 to implement the present invention. The one or more modules / units may be a series of computer program instruction segments capable of implementing specific functions, which are used to describe the execution process of the computer program 32 in the electronic device 3.

[0111] The electronic device 3 may be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server. The electronic device 3 may include, but is not limited to, a processor 30 and a memory 31. Those skilled in the art will appreciate that Figure 3It is only an example of the electronic device 3 and does not constitute a limitation of the electronic device 3. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the electronic device may also include input and output devices, network access devices, buses, etc.

[0112] The processor 30 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0113] The memory 31 may be an internal storage unit of the electronic device 3, such as a hard disk or memory of the electronic device 3. The memory 31 may also be an external storage device of the electronic device 3, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the electronic device 3. Further, the memory 31 may also include both an internal storage unit and an external storage device of the electronic device 3. The memory 31 is used to store the computer program and other programs and data required by the electronic device. The memory 31 may also be used to temporarily store data that has been output or is to be output.

[0114] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0115] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0116] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0117] In the embodiments provided by the present invention, it should be understood that the disclosed devices / electronic devices and methods can be implemented in other ways. For example, the device / electronic device embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0118] The units described as separate components may or may not be physically separated, and the components shown as units 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 units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0119] In addition, each functional unit 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 software functional units.

[0120] If the integrated module / unit 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. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned various long material defect detection method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device that can carry the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0121] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A method for detecting defects in long materials, characterized in that: include: Determining the expected defect area and defect appearance information of the long material in the appearance image of the long material; Determining a detection area for performing a tapping test on the long material based on the expected defect type and the expected defect area corresponding to the production process of the long material; Determining a defect volume of the long material based on a vibration response signal generated by the long material after the tapping test; Based on the expected defect type, the defect appearance information and the defect volume, three-dimensional defect information of the long material is determined, so as to grind the long material based on the three-dimensional defect information.

2. The method according to claim 1, characterized in that The determining of a detection area for performing a knock test on the long material based on the expected defect type and the expected defect area corresponding to the production process of the long material comprises: Based on the expected defect type and the expected defect area corresponding to the production process of the long material, a search is performed in a preset defect detection area comparison table to obtain a detection area for performing a tapping test on the long material.

3. The method according to claim 2, characterized in that Before determining the detection area for performing a knock test on the long material based on the expected defect type and the expected defect area corresponding to the production process of the long material, the method further includes: Acquire vibration response signals of a plurality of long materials; wherein each long material has different defect types and defect areas, each long material corresponds to a plurality of vibration response signals, and each vibration response signal corresponding to each long material is obtained by performing a tapping test on a different area of ​​the long material; For each defect type and defect area, the vibration response signals corresponding to the defect type and defect area are grouped according to the knocking test area, and the average linearity of the vibration response signals in each group is calculated. The knocking test area where the group with the largest average linearity is located is used as the detection area corresponding to the defect type and defect area; The defect detection area comparison table is obtained by combining the detection areas corresponding to the defect types and defect areas.

4. The method according to claim 1, characterized in that: The step of determining the defect volume of the long material based on the vibration response signal generated by the long material after the tapping test comprises: Separating overlapping signals of the vibration response signal generated by the long material after the knocking test to obtain a main vibration signal and a defect vibration signal; Based on the ratio of the signal energies of the main body vibration signal and the defect vibration signal, the volume ratio of the defect portion to the main body portion is determined, and based on the volume ratio, the defect volume of the long material is determined.

5. The method according to claim 4, characterized in that The de-overlapping process of the vibration response signal to separate it into a main vibration signal and a defect vibration signal includes: Performing subspace separation on the vibration response signal to obtain subspaces corresponding to the vibration response signal; Determine a separation matrix of the vibration response signal according to mutual information values ​​corresponding to each subspace and the vibration response signal; Separating the vibration response signal according to the separation matrix to obtain at least two vibration signal components; The vibration signal component with the largest signal energy is taken as the main vibration signal, and the remaining vibration signal components are taken as defect vibration signals.

6. The method according to claim 1, characterized in that The determining of the three-dimensional defect information of the long material based on the expected defect type, the defect appearance information and the defect volume includes: Searching for multiple defect shapes matching the expected defect type and the defect appearance information in a preset defect shape library; For each defect shape, adjusting the size of the defect shape based on the defect volume and the preset volume of the defect shape, and determining the endpoint coordinates of the defect shape; Each adjusted defect shape is superimposed below the defect surface of the long material as a defect area of ​​the long material, and the end point coordinates of the defect area are used as three-dimensional defect information of the long material.

7. A long material defect detection device, characterized in that: include: An appearance detection module, used to determine the expected defect area and defect appearance information of the long material in the appearance image of the long material; A test positioning module, used to determine a detection area for performing a knock test on the long material based on the expected defect type and the expected defect area corresponding to the production process of the long material; A volume detection module, used to determine the defect volume of the long material based on the vibration response signal generated by the long material after the knocking test; A three-dimensional prediction module is used to determine the three-dimensional defect information of the long material based on the expected defect type, the defect appearance information and the defect volume, so as to grind the long material based on the three-dimensional defect information.

8. The long material defect detection device according to claim 7, characterized in that: The test positioning module is specifically used for: Based on the expected defect type and the expected defect area corresponding to the production process of the long material, a search is performed in a preset defect detection area comparison table to obtain a detection area for performing a tapping test on the long material.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images