CN111855397A - Nondestructive testing method and system - Google Patents
Nondestructive testing method and system Download PDFInfo
- Publication number
- CN111855397A CN111855397A CN201910339990.4A CN201910339990A CN111855397A CN 111855397 A CN111855397 A CN 111855397A CN 201910339990 A CN201910339990 A CN 201910339990A CN 111855397 A CN111855397 A CN 111855397A
- Authority
- CN
- China
- Prior art keywords
- stress
- data
- acoustic emission
- welding part
- stage
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 72
- 238000009659 non-destructive testing Methods 0.000 title claims abstract description 40
- 238000003466 welding Methods 0.000 claims abstract description 210
- 238000012360 testing method Methods 0.000 claims abstract description 108
- 238000001514 detection method Methods 0.000 claims abstract description 50
- 238000004422 calculation algorithm Methods 0.000 claims description 50
- 230000008569 process Effects 0.000 claims description 43
- 238000009864 tensile test Methods 0.000 claims description 37
- 208000010392 Bone Fractures Diseases 0.000 claims description 11
- 206010017076 Fracture Diseases 0.000 claims description 11
- 238000007689 inspection Methods 0.000 claims description 9
- 238000004140 cleaning Methods 0.000 claims description 8
- 238000012706 support-vector machine Methods 0.000 claims description 7
- 230000003321 amplification Effects 0.000 claims description 6
- 238000003066 decision tree Methods 0.000 claims description 6
- 238000007477 logistic regression Methods 0.000 claims description 6
- 238000003199 nucleic acid amplification method Methods 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 6
- 238000007637 random forest analysis Methods 0.000 claims description 6
- 230000001066 destructive effect Effects 0.000 claims 6
- 230000002787 reinforcement Effects 0.000 claims 2
- 238000004519 manufacturing process Methods 0.000 abstract description 24
- 239000000463 material Substances 0.000 description 24
- 238000005728 strengthening Methods 0.000 description 8
- 238000002591 computed tomography Methods 0.000 description 3
- 230000007547 defect Effects 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 230000009471 action Effects 0.000 description 2
- 230000008030 elimination Effects 0.000 description 2
- 238000003379 elimination reaction Methods 0.000 description 2
- 238000004021 metal welding Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 239000002699 waste material Substances 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 239000000758 substrate Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N29/00—Investigating or analysing materials by the use of ultrasonic, sonic or infrasonic waves; Visualisation of the interior of objects by transmitting ultrasonic or sonic waves through the object
- G01N29/14—Investigating or analysing materials by the use of ultrasonic, sonic or infrasonic waves; Visualisation of the interior of objects by transmitting ultrasonic or sonic waves through the object using acoustic emission techniques
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N3/00—Investigating strength properties of solid materials by application of mechanical stress
- G01N3/08—Investigating strength properties of solid materials by application of mechanical stress by applying steady tensile or compressive forces
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N2291/00—Indexing codes associated with group G01N29/00
- G01N2291/26—Scanned objects
- G01N2291/267—Welds
Landscapes
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Acoustics & Sound (AREA)
- Investigating Strength Of Materials By Application Of Mechanical Stress (AREA)
Abstract
The invention discloses a nondestructive testing method and a nondestructive testing system, wherein the nondestructive testing system comprises a first testing module, a determining module, a prediction model obtaining module, a judging module and at least one second testing module; the first detection module is used for acquiring first acoustic emission signal data, first stress data and first strain data corresponding to the sample welding part; the determining module is used for determining the stress stage of the sample welding part; the prediction model acquisition module is used for establishing a stress stage prediction model; the second testing module is used for acquiring target acoustic emission signal data, actual stress data and actual strain data corresponding to the target welding part; the prediction model acquisition module is also used for acquiring an actual stress stage; the judging module is used for judging whether the target welding part is a qualified product. The invention can realize nondestructive detection of the tiny workpiece, reduce the test rejection rate and reduce the production cost; meanwhile, the detection time is short, online detection can be realized, and the production efficiency is further improved.
Description
Technical Field
The invention relates to the technical field of equipment management, in particular to a nondestructive testing method and system.
Background
At present, after a tiny part in the 3C (electronic product) manufacturing industry is machined, a welding part is generally required to be welded and reinforced (such as laser welding). The strength of the welding part is mainly tested according to a certain proportion, such as welding of a mobile phone fixing stud, and the like, the welding part is scrapped due to the drawing and sampling inspection, so that great waste is caused, and the production cost is increased.
Conventional nondestructive testing methods include X-ray testing, industrial CT (computed tomography) testing, ultrasonic flaw detection methods, and the like. The product base material in the 3C industry is generally thin, the welding depth is shallow, and the welding seam is difficult to distinguish by adopting an X-ray detection method, so that the welding defect is difficult to distinguish; the welding line can be distinguished by adopting an industrial CT detection method, but the defects of extremely high cost, low detection efficiency, incapability of realizing online monitoring and the like exist; ultrasonic flaw detection is not suitable for detecting welds with too thin substrates.
Disclosure of Invention
The technical problems to be solved by the invention are that in the prior art, tensile force damage testing is carried out on a welding part, so that the welding part is easy to scrap, great waste is caused, and the production cost is increased; the traditional nondestructive testing method has the defects that the traditional nondestructive testing method is not suitable for testing tiny welding parts and the like in the 3C industry, and aims to provide a nondestructive testing method and a nondestructive testing system.
The invention solves the technical problems through the following technical scheme:
the invention provides a nondestructive testing system, which comprises a first testing module, a determining module, a prediction model obtaining module, a judging module and at least one second testing module, wherein the first testing module is used for detecting the first testing module;
when the sample welding piece is subjected to a tensile force test, the first detection module is used for acquiring first acoustic emission signal data, first stress data and first strain data which respectively correspond to the sample welding piece at different time points in the whole test process from the beginning of stress to the occurrence of fracture;
the determining module is used for determining the stress stage of the sample weldment according to the first acoustic emission signal data;
wherein the size of the first acoustic emission signal data is in positive correlation with the stress degree corresponding to the stress stage;
the prediction model acquisition module is used for taking the first acoustic emission signal data, the first stress data and the first stress data at the same time point as input, taking the stress stage as output, establishing a stress stage prediction model, and sending the stress stage prediction model to the second test module; (ii) a
The second testing module is used for acquiring target acoustic emission signal data, actual stress data and actual strain data which respectively correspond to the target welding part at different time points when the target welding part is subjected to tension testing, and calling the prediction model acquiring module;
the second testing module is further used for inputting the target acoustic emission signal data, the actual stress data and the actual strain data corresponding to the same time point as the stress stage prediction model, acquiring an actual stress stage corresponding to the target welding part, and sending the actual stress stage to the judging module;
the judging module is used for judging whether the actual stress stage reaches the yield stage or not in the process that the actual stress data reaches the preset tension value, if so, stopping the tension test on the target welding part, and determining that the target welding part is an unqualified product; otherwise, determining the target welding part as a qualified product.
Preferably, the first detection module comprises a tensile testing machine, a first extensometer, a first acoustic emission sensor, a first signal amplifier and a first high-frequency signal collector;
The tensile testing machine is used for applying mechanical force to the sample welding part and acquiring the first stress data corresponding to the sample welding part;
the extensometer is used for acquiring the first strain data corresponding to the sample welding piece when the tensile testing machine applies mechanical force to the sample welding piece;
the first acoustic emission sensor is used for acquiring acoustic emission signal data corresponding to the sample welding piece when the tensile testing machine applies mechanical force to the sample welding piece;
the first signal amplifier is used for amplifying the acoustic emission signal data;
the first high-frequency signal collector is used for collecting the high-frequency signals in the acoustic emission signal data after amplification processing.
Preferably, the second testing module comprises a preset tension value obtaining unit, a tension meter, a second extensometer, a second acoustic emission sensor, a second signal amplifier and a second high-frequency signal collector;
the preset tension value acquisition unit is used for acquiring the set preset tension value;
the tension meter is used for applying mechanical force to the target welding part and acquiring the actual stress data corresponding to the target welding part;
The second extensometer is used for acquiring the actual stress data corresponding to the target welding part when the tensile testing machine applies mechanical force to the target welding part;
the second sound emission sensor is used for acquiring target sound emission signal data corresponding to the target welding part when the tensile testing machine applies mechanical force to the target welding part;
the second signal amplifier is used for amplifying the target acoustic emission signal data;
the first high-frequency signal collector is used for collecting the high-frequency signals in the amplified target acoustic emission signal data.
Preferably, the prediction model obtaining module comprises a data acquisition unit and a model obtaining unit;
the data acquisition unit is used for acquiring the first acoustic emission signal data, the first stress data and the first strain data;
the model obtaining unit is used for adopting an SVM (support vector machine), a Decision Tree algorithm, an AdaBoost (iterative algorithm), a Random Forest algorithm, an Extra Trees (limit Tree algorithm), a Gradient Boosting algorithm, a Multiple layer perceptron algorithm, a KNN (proximity algorithm), a Logistic regression algorithm or a Linear discriminant analysis to input the first acoustic emission signal data, the first stress data and the first stress variable data at the same time point, and the stress stage is used as an output to establish a stress stage prediction model.
Preferably, the prediction model obtaining module further comprises a preprocessing unit;
the preprocessing unit is used for respectively cleaning the first acoustic emission signal data, the first stress data and the first stress data acquired by the first detection module; and/or the presence of a gas in the gas,
the prediction model acquisition module comprises an application program generation unit, and the second test module comprises an application program receiving unit;
the application program generating unit is used for generating an application program according to the stress stage prediction model established by the model acquiring unit and sending the application program to the application program receiving unit;
the application program receiving unit is used for receiving the application program, and acquiring an actual stress stage corresponding to the target welding part by taking the target acoustic emission signal data, the actual stress data and the actual strain data corresponding to the same time point as the input of the stress stage prediction model based on the application program. .
Preferably, the force-receiving stage comprises an elastic stage, a yielding stage, a strengthening stage or a breaking stage.
The invention also provides a nondestructive testing method, which is realized by using the nondestructive testing system and comprises the following steps:
When a sample welding piece is subjected to a tension test, the first detection module is adopted to obtain first acoustic emission signal data, first stress data and first strain data which respectively correspond to the sample welding piece at different time points in the whole test process from the beginning of stress to the occurrence of fracture;
determining the stress stage of the sample weldment according to the first acoustic emission signal data;
wherein the size of the first acoustic emission signal data is in positive correlation with the stress degree corresponding to the stress stage;
taking the first acoustic emission signal data, the first stress data and the first stress data of the same time point as input, taking the stress stage as output, establishing a stress stage prediction model, and sending the stress stage prediction model to the second test module;
when the second testing module is used for testing the tension of the target welding part, target acoustic emission signal data, actual stress data and actual strain data which respectively correspond to the target welding part at different time points are obtained;
the second testing module is adopted to take the target acoustic emission signal data, the actual stress data and the actual strain data corresponding to the same time point as the input of the stress stage prediction model, and the actual stress stage corresponding to the target welding part is obtained;
Judging whether the actual stress stage reaches a yield stage or not in the process that the actual stress data reaches a preset tension value, if so, stopping the tension test of the target welding piece, and determining that the target welding piece is an unqualified product; otherwise, determining the target welding part as a qualified product.
Preferably, the first detection module comprises a tensile testing machine, a first extensometer, a first acoustic emission sensor, a first signal amplifier and a first high-frequency signal collector;
when carrying out tensile test to sample welding spare, adopt first detection module obtains the whole testing process of sample welding spare from beginning atress to breaking off, the step that corresponds respectively at different time points first acoustic emission signal data, first stress data and first strain data includes:
applying mechanical force to the sample welding part by using the tensile testing machine, and acquiring the first stress data corresponding to the sample welding part;
when the extensometer is adopted to apply mechanical force to the sample welding part by the tensile testing machine, the first strain data corresponding to the sample welding part is obtained;
when the tensile testing machine applies mechanical force to the sample welding part, the first acoustic emission sensor is adopted to obtain acoustic emission signal data corresponding to the sample welding part;
Amplifying the acoustic emission signal data by using the first signal amplifier;
and collecting the high-frequency signals in the acoustic emission signal data after amplification by using the first high-frequency signal collector.
Preferably, the second testing module comprises a preset tension value obtaining unit, a tension meter, a second extensometer, a second acoustic emission sensor, a second signal amplifier and a second high-frequency signal collector;
when the second testing module is adopted to carry out tension testing on the target welding part, the step of acquiring the target acoustic emission signal data, the actual stress data and the actual strain data which respectively correspond to the target welding part at different time points further comprises the following steps:
acquiring the set preset tension value;
applying mechanical force to the target welding part by using the tension meter, and acquiring the actual stress data corresponding to the target welding part;
acquiring actual stress data corresponding to the target welding part by using the second extensometer when the tensile testing machine applies mechanical force to the target welding part;
when the tensile testing machine applies mechanical force to the target welding part, the second acoustic emission sensor is adopted to obtain target acoustic emission signal data corresponding to the target welding part;
Amplifying the target acoustic emission signal data by using the second signal amplifier;
and collecting the high-frequency signals in the amplified target acoustic emission signal data by using the second high-frequency signal collector.
Preferably, the step of establishing a stress phase prediction model by using the first acoustic emission signal data, the first stress data and the first stress data at the same time point as inputs and the stress phase as an output includes:
acquiring the first acoustic emission signal data, the first stress data and the first strain data; and adopting a support vector machine, a decision tree algorithm, AdaBoost, a random forest algorithm, a limit tree algorithm, a gradient lifting algorithm, a multilayer perceptron algorithm, a proximity algorithm, a logistic regression algorithm or a linear discrimination algorithm, taking the first acoustic emission signal data, the first stress data and the first stress data at the same time point as input, taking the stress phase as output, and establishing a stress phase prediction model.
Preferably, the step of acquiring the first acoustic emission signal data, the first stress data and the first strain data further comprises:
Cleaning the first acoustic emission signal data, the first stress data and the first stress data acquired by the first detection module respectively; and/or the presence of a gas in the gas,
the prediction model acquisition module comprises an application program generation unit, and the second test module comprises an application program receiving unit;
the step of sending the stress phase prediction model to the second test module comprises:
generating an application program by adopting the application program generating unit according to the established stress stage prediction model, and sending the application program to the application program receiving unit;
the step of acquiring the actual stress phase corresponding to the target welding part by using the second testing module to take the target acoustic emission signal data, the actual stress data and the actual strain data corresponding to the same time point as the input of the stress phase prediction model comprises the following steps:
and receiving the application program by adopting the application program receiving unit, and taking the target acoustic emission signal data, the actual stress data and the actual strain data corresponding to the same time point as the input of the stress stage prediction model based on the application program to obtain the actual stress stage corresponding to the target welding part.
Preferably, the force-receiving stage comprises an elastic stage, a yielding stage, a strengthening stage or a breaking stage.
The positive progress effects of the invention are as follows:
according to the method, a stress phase prediction model is established based on acoustic emission signal data and stress strain data of a sample welding part in a tension test process, so as to predict the corresponding actual stress phase of each target welding part after being applied with force to different degrees; in the process of adding the applied force to the preset tension value, if the target welding part does not reach the yield stage, determining that the target welding part is qualified; if the yield phenomenon occurs in the process, determining that the target welding part is unqualified, stopping detecting the target welding part, and performing rework or scrapping treatment on the target welding part according to an actual process, so that nondestructive detection on the tiny workpiece is realized, the test scrappage is reduced, and the production cost is reduced; meanwhile, the detection time is short, online detection can be realized, and the production efficiency is further improved.
Drawings
Fig. 1 is a schematic structural view of a nondestructive testing system of embodiment 1 of the present invention.
Fig. 2 is a schematic structural diagram of a nondestructive testing system of embodiment 2 of the present invention.
FIG. 3 is a flowchart of a nondestructive testing method in embodiment 3 of the present invention.
Detailed Description
The invention is further illustrated by the following examples, which are not intended to limit the scope of the invention.
Example 1
As shown in fig. 1, the nondestructive testing system of the present embodiment includes a first testing module 1, a determining module 2, a prediction model obtaining module 3, a judging module 4, and at least one second testing module 5.
The first detection module 1 is a detection device equipped in a laboratory or the like, and is mainly used for testing the whole process from the beginning of stress to the occurrence of fracture of a small amount of sample welding pieces.
The second testing module 5 is a testing device actually put into testing use in a factory, and a plurality of second testing modules 5 can be adopted to simultaneously and parallelly test. Compared with the first detection module 1, the second test module 5 has the advantages of small overall size, simple structure, low cost, high response speed and the like, and is suitable for detecting large-batch target welding pieces on line.
When a tensile test is performed on a sample welding piece, a first detection module 1 is used for acquiring first acoustic emission signal data, first stress data and first strain data which respectively correspond to the sample welding piece at different time points in the whole test process from the beginning of stress to the occurrence of fracture;
At this time, the first stress data and a stress-strain curve corresponding to the first stress data can be obtained, and the stress-strain curve is used for representing the deformation condition of the material of the sample welding piece along with the stress.
For a sample welding part (such as a metal welding part), when tensile force with different magnitudes is applied to the sample welding part, the internal structure of the sample welding part changes to different degrees, and an ultrahigh frequency stress wave pulse signal released by molecular lattices in the process of distortion and crack aggravation and plastic deformation of a material is an acoustic emission signal; in addition, the sample weld part may be deformed to different degrees in the process.
The determining module 2 is used for determining the stress stage of the sample welding part according to the first acoustic emission signal data;
the stress stage comprises an elastic stage, a yielding stage, a strengthening stage or a breaking stage, and the stress degree of the elastic stage, the yielding stage, the strengthening stage or the breaking stage is gradually increased.
Specifically, when the material is in an elastic stage, the material will recover to a state before stress application after stress relief, and at this time, the mechanical property of the material is not affected;
when the material is subjected to a yield stage or a strengthening stage, the mechanical properties of the material are influenced;
When the material reaches the fracture stage due to excessive stress, the material is completely scrapped.
The size of the first acoustic emission signal data is in positive correlation with the stress degree corresponding to the stress stage; the larger the first acoustic emission signal data is, the more serious the stress degree corresponding to the stress stage is.
The prediction model acquisition module 3 is used for taking the first acoustic emission signal data, the first stress data and the first stress data of the same time point as input and taking the stress stage as output, establishing a stress stage prediction model and sending the stress stage prediction model to the second test module 5;
the second testing module 5 is used for acquiring target acoustic emission signal data, actual stress data and actual strain data respectively corresponding to the target welding part at different time points when the target welding part is subjected to tension testing, and calling the prediction model acquiring module 3;
the method comprises the following steps of testing a target welding part by adopting a set standard force, namely testing a corresponding stress state of the force applied to the target welding part in the process of increasing to the standard force; different values of the standard force can be set for different materials.
The second testing module 5 is further configured to take the target acoustic emission signal data, the actual stress data and the actual strain data corresponding to the same time point as input of a stress phase prediction model, obtain an actual stress phase corresponding to the target weld assembly, and send the actual stress phase to the judging module;
Specifically, different second test modules 5 respectively call the prediction model acquisition module 3 to acquire actual stress stages corresponding to the target weld assembly; or, the prediction model obtaining module 3 is issued to each second testing module 5 in an application program manner, so that each second testing module 5 can calculate independently to obtain the actual stress stage corresponding to the target welding part.
The judging module 4 is used for judging whether the actual stress stage reaches the yield stage or not when the actual stress data reaches the preset tension value (namely the standard force), if so, stopping the tension test on the target welding part, and determining that the target welding part is an unqualified product; otherwise, determining the target welding part as a qualified product.
In addition, the nondestructive testing system in this embodiment is not limited to nondestructive testing of tiny parts (i.e., welded parts) in the 3C manufacturing industry, and may also be applied to nondestructive testing of other large parts, which is not described herein again.
In the embodiment, acoustic emission signal data and stress-strain data of a sample welding part in a tension testing process are obtained in advance through a first detection module, and a corresponding stress stage is determined according to the acoustic emission signal data; establishing a stress stage prediction model according to the data to predict the corresponding actual stress stage of each target welding piece after being applied with force of different degrees, and determining that the target welding piece is qualified if the target welding piece does not reach the yield stage in the process of adding the applied force to the preset tension value; if the yield phenomenon occurs in the process, determining that the target welding part is unqualified, stopping detecting the target welding part, and performing rework or scrapping treatment on the target welding part according to an actual process, so that nondestructive detection on the tiny workpiece is realized, the test scrappage is reduced, and the production cost is reduced; meanwhile, the detection time is short, online detection can be realized, and the production efficiency is further improved.
Example 2
As shown in fig. 2, the nondestructive testing system of the present embodiment is a further improvement of embodiment 1, specifically:
the prediction model obtaining module 3 runs on a central processing server, and specifically includes a data collecting unit 31, a preprocessing unit 32, a model obtaining unit 33, and an application generating unit 34.
The data acquisition unit 31 is used for acquiring first acoustic emission signal data, first stress data and first strain data;
the preprocessing unit 32 is configured to respectively perform cleaning processing on the first acoustic emission signal data, the first stress data, and the first stress data acquired by the first detection module, and store the preprocessed data by using the data acquisition unit 3.
Specifically, the cleaning treatment mainly comprises the treatment of abnormal values, and the elimination of other data collected by the nondestructive testing system when the sample welding part is not under the action of tensile force.
The model obtaining unit 33 is configured to use a support vector machine, a decision tree algorithm, AdaBoost, a random forest algorithm, a limit tree algorithm, a gradient boosting algorithm, a multi-layer perceptron algorithm, a proximity algorithm, a logistic regression algorithm, or a linear discrimination algorithm, to take the first acoustic emission signal data, the first stress data, and the first stress data at the same time point as inputs, and take the stress phase as an output, to establish a stress phase prediction model.
The method is not limited to the method for establishing the model by using the above listed algorithm, and other methods capable of realizing the establishment of the stress phase prediction model can be adopted.
The application generating unit 34 is configured to generate an application according to the stress phase prediction model established by the model obtaining unit.
The first detection module 1 comprises a tensile testing machine 11, a first extensometer 12, a first acoustic emission sensor 13, a first signal amplifier 14 and a first high-frequency signal collector 15.
The tensile testing machine 11 is used for applying mechanical force to the sample welding part and acquiring first stress data corresponding to the sample welding part;
the extensometer 12 is used for acquiring first strain data corresponding to the sample welding piece when the tensile testing machine applies mechanical force to the sample welding piece;
the first acoustic emission sensor 13 is used for acquiring acoustic emission signal data corresponding to the sample welding piece when the tensile testing machine applies mechanical force to the sample welding piece;
the first signal amplifier 14 is used for amplifying the acoustic emission signal data;
the first high-frequency signal collector 15 is configured to collect a high-frequency signal in the acoustic emission signal data after the amplification processing.
The second testing module 5 can operate on a low-cost stand-alone machine, and specifically includes a preset tension value acquiring unit 51, a tension meter 52, a second extensometer 53, a second acoustic emission sensor 54, a second signal amplifier 55, a second high-frequency signal collector 56, and an application receiving unit 57.
Of course, the second testing module 5 also includes other automated production modules, which are all in the prior art, and therefore, the detailed description thereof is omitted here.
The preset tension value obtaining unit 51 is configured to obtain a set preset tension value;
the tension meter 52 is used for applying mechanical force to the target welding part and acquiring actual stress data corresponding to the target welding part;
the second extensometer 53 is used for acquiring actual stress data corresponding to the target welding part when the tensile testing machine applies mechanical force to the target welding part;
the second acoustic emission sensor 54 is used for acquiring target acoustic emission signal data corresponding to the target welding part when the tensile testing machine applies mechanical force to the target welding part;
the second signal amplifier 55 is used for amplifying the target acoustic emission signal data;
the second high-frequency signal collector 56 is configured to collect a high-frequency signal in the amplified target acoustic emission signal data.
The application program receiving unit 57 is configured to receive the application program sent by the application program generating unit 34, and obtain an actual stress phase corresponding to the target weld assembly based on the application program by using the target acoustic emission signal data, the actual stress data, and the actual strain data as input of the stress phase prediction model.
In addition, in order to realize flexible production, the standard tension (i.e. the preset tension value) of the second testing module 5, the data type acquisition and the like can be optimally designed, set and adjusted according to different production materials, and further the production efficiency is ensured.
The following is illustrated with reference to specific examples:
taking the connecting stud of the mobile phone middle plate as an example, the diameter of the connecting stud is usually 1-2mm, the material of the middle plate is about 0.3mm, welding between the connecting stud of the middle plate and the middle plate is usually completed by laser spot welding, and the nondestructive testing system of the embodiment is used for performing standard force testing on the connecting stud enough for welding.
In the process of gradually increasing the force applied to the connecting stud, the stress stage where the connecting stud is located is obtained in real time through an application program, and when the situation that the mechanical property of the connecting stud is affected (namely the yield phenomenon occurs) does not occur before the force applied to the connecting stud reaches the standard force, the connecting stud is determined to be a qualified product; and when the connecting stud has a yield phenomenon before the force applied to the connecting stud reaches the standard force, determining that the connecting stud is an unqualified product, stopping detection, and performing rework or scrap treatment on the connecting stud according to an actual process.
In the embodiment, acoustic emission signal data and stress-strain data of a sample welding part in a tension testing process are obtained in advance through a first detection module, and a corresponding stress stage is determined according to the acoustic emission signal data; establishing a stress stage prediction model according to the data to predict the corresponding actual stress stage of each target welding piece after being applied with force of different degrees, and determining that the target welding piece is qualified if the target welding piece does not reach the yield stage in the process of adding the applied force to the preset tension value; if the yield phenomenon occurs in the process, determining that the target welding part is unqualified, stopping detecting the target welding part, and performing rework or scrapping treatment on the target welding part according to an actual process, so that nondestructive detection on the tiny workpiece is realized, the test scrappage is reduced, and the production cost is reduced; meanwhile, the detection time is short, online detection can be realized, and the production efficiency is further improved.
Example 3
As shown in fig. 3, the nondestructive testing method of the present embodiment is implemented by using the nondestructive testing system of embodiment 1, and includes:
s101, when a sample welding piece is subjected to a tensile force test, a first detection module is adopted to obtain first acoustic emission signal data, first stress data and first strain data which respectively correspond to the sample welding piece at different time points in the whole test process from the beginning of stress to the occurrence of fracture;
At this time, the first stress data and a stress-strain curve corresponding to the first stress data can be obtained, and the stress-strain curve is used for representing the deformation condition of the material of the sample welding piece along with the stress.
For a sample welding part (such as a metal welding part), when tensile force with different magnitudes is applied to the sample welding part, the internal structure of the sample welding part changes to different degrees, and an ultrahigh frequency stress wave pulse signal released by molecular lattices in the process of distortion and crack aggravation and plastic deformation of a material is an acoustic emission signal; in addition, the sample weld part may be deformed to different degrees in the process.
S102, determining a stress stage of a sample welding part according to the first acoustic emission signal data;
the stress stage comprises an elastic stage, a yielding stage, a strengthening stage or a breaking stage, and the stress degree of the elastic stage, the yielding stage, the strengthening stage or the breaking stage is gradually increased.
Specifically, when the material is in an elastic stage, the material will recover to a state before stress application after stress relief, and at this time, the mechanical property of the material is not affected;
when the material is subjected to a yield stage or a strengthening stage, the mechanical properties of the material are influenced;
When the material reaches the fracture stage due to excessive stress, the material is completely scrapped.
S103, taking the first acoustic emission signal data, the first stress data and the first stress data of the same time point as input, taking a stress stage as output, establishing a stress stage prediction model, and sending the stress stage prediction model to a second test module;
s104, when a second testing module is used for carrying out tension testing on the target welding part, acquiring target acoustic emission signal data, actual stress data and actual strain data which respectively correspond to the target welding part at different time points;
s105, a second testing module is adopted to take the target acoustic emission signal data, the actual stress data and the actual strain data as the input of a stress stage prediction model, and an actual stress stage corresponding to the target welding part is obtained;
specifically, different second test modules respectively call the prediction models to obtain actual stress stages corresponding to the target welding parts; or the prediction model is issued to each second test module in an application program mode, so that each second test module can conveniently and independently calculate to obtain the actual stress stage corresponding to the target welding part.
S106, in the process that the actual stress data reaches the preset tension value, judging whether the actual stress stage reaches the yield stage, if so, stopping the tension test on the target welding part, and determining the target welding part as an unqualified product; otherwise, determining the target welding part as a qualified product.
In addition, the nondestructive testing system in this embodiment is not limited to nondestructive testing of tiny parts (i.e., welded parts) in the 3C manufacturing industry, and may also be applied to nondestructive testing of other large parts, which is not described herein again. In the embodiment, acoustic emission signal data and stress-strain data of a sample welding part in a tension testing process are obtained in advance through a first detection module, and a corresponding stress stage is determined according to the acoustic emission signal data; establishing a stress stage prediction model according to the data to predict the corresponding actual stress stage of each target welding piece after being applied with force of different degrees, and determining that the target welding piece is qualified if the target welding piece does not reach the yield stage in the process of adding the applied force to the preset tension value; if the yield phenomenon occurs in the process, determining that the target welding part is unqualified, stopping detecting the target welding part, and performing rework or scrapping treatment on the target welding part according to an actual process, so that nondestructive detection on the tiny workpiece is realized, the test scrappage is reduced, and the production cost is reduced; meanwhile, the detection time is short, online detection can be realized, and the production efficiency is further improved.
Example 4
The nondestructive testing method of the present embodiment is implemented by using the nondestructive testing system in embodiment 2, specifically:
step S101 includes:
applying mechanical force to the sample welding part by using a tensile testing machine, and acquiring first stress data corresponding to the sample welding part;
when a mechanical force is applied to the sample welding part by the tensile testing machine, first strain data corresponding to the sample welding part are obtained by the extensometer;
the method comprises the steps that when a first acoustic emission sensor is adopted to apply mechanical force to a sample welding part through a tensile testing machine, acoustic emission signal data corresponding to the sample welding part are obtained;
amplifying the acoustic emission signal data by using a first signal amplifier;
and a first high-frequency signal collector is adopted to collect the high-frequency signals in the acoustic emission signal data after amplification processing.
Step S102 includes:
acquiring a set preset tension value;
applying mechanical force to the target welding part by using a tension meter, and acquiring actual stress data corresponding to the target welding part;
acquiring actual stress data corresponding to the target welding part when the second extensometer applies mechanical force to the target welding part by the tensile testing machine;
when a second sound emission sensor is adopted to apply mechanical force to the target welding part by the tensile testing machine, target sound emission signal data corresponding to the target welding part are obtained;
Amplifying the target acoustic emission signal data by adopting a second signal amplifier;
and collecting the high-frequency signals in the amplified target acoustic emission signal data by using a second high-frequency signal collector.
Step S103 includes:
acquiring first acoustic emission signal data, first stress data and first strain data;
and respectively cleaning the first acoustic emission signal data, the first stress data and the first stress data acquired by the first detection module, and storing the preprocessed data by adopting a data acquisition unit.
Specifically, the cleaning treatment mainly comprises the treatment of abnormal values, and the elimination of other data collected by the nondestructive testing system when the sample welding part is not under the action of tensile force.
The method comprises the steps of adopting a support vector machine, a decision tree algorithm, AdaBoost, a random forest algorithm, a limit tree algorithm, a gradient lifting algorithm, a multilayer perceptron algorithm, a proximity algorithm, a logistic regression algorithm or a linear discrimination algorithm, taking first acoustic emission signal data, first stress data and first stress data at the same time point as input, taking a stress phase as output, and establishing a stress phase prediction model.
The method is not limited to the method for establishing the model by using the above listed algorithm, and other methods capable of realizing the establishment of the stress phase prediction model can be adopted. The step of sending the stress phase prediction model to the second test module includes:
An application program generating unit is adopted to generate an application program according to the established stress stage prediction model, and the application program is sent to an application program receiving unit;
step S105 includes:
and receiving the application program by adopting an application program receiving unit, and taking the target acoustic emission signal data, the actual stress data and the actual strain data as the input of a stress stage prediction model based on the application program to obtain an actual stress stage corresponding to the target welding part.
In addition, in order to realize flexible production, the standard tension (namely the preset tension value) of the second test module, the data type acquisition and the like can be optimally designed, set and adjusted according to different production materials, and further the production efficiency is ensured.
The following is illustrated with reference to specific examples:
taking the connecting stud of the mobile phone middle plate as an example, the diameter of the connecting stud is usually 1-2mm, the material of the middle plate is about 0.3mm, welding between the connecting stud of the middle plate and the middle plate is usually completed by laser spot welding, and the nondestructive testing system of the embodiment is used for performing standard force testing on the connecting stud enough for welding.
In the process of gradually increasing the force applied to the connecting stud, the stress stage where the connecting stud is located is obtained in real time through an application program, and when the situation that the mechanical property of the connecting stud is influenced (namely the yield phenomenon does not occur) does not occur before the force applied to the connecting stud reaches the standard force, the connecting stud is determined to be a qualified product; and when the connecting stud has a yield phenomenon before the force applied to the connecting stud reaches the standard force, determining that the connecting stud is an unqualified product, stopping detection, and performing rework or scrap treatment on the connecting stud according to an actual process.
In the embodiment, acoustic emission signal data and stress-strain data of a sample welding part in a tension testing process are obtained in advance through a first detection module, and a corresponding stress stage is determined according to the acoustic emission signal data; establishing a stress stage prediction model according to the data to predict the corresponding actual stress stage of each target welding piece after being applied with force of different degrees, and determining that the target welding piece is qualified if the target welding piece does not reach the yield stage in the process of adding the applied force to the preset tension value; if the yield phenomenon occurs in the process, determining that the target welding part is unqualified, stopping detecting the target welding part, and performing rework or scrapping treatment on the target welding part according to an actual process, so that nondestructive detection on the tiny workpiece is realized, the test scrappage is reduced, and the production cost is reduced; meanwhile, the detection time is short, online detection can be realized, and the production efficiency is further improved.
While specific embodiments of the invention have been described above, it will be appreciated by those skilled in the art that these are by way of example only, and that the scope of the invention is defined by the appended claims. Various changes and modifications to these embodiments may be made by those skilled in the art without departing from the spirit and scope of the invention, and these changes and modifications are within the scope of the invention.
Claims (12)
1. A nondestructive testing system is characterized by comprising a first testing module, a determining module, a prediction model obtaining module, a judging module and at least one second testing module;
when the sample welding piece is subjected to a tensile force test, the first detection module is used for acquiring first acoustic emission signal data, first stress data and first strain data which respectively correspond to the sample welding piece at different time points in the whole test process from the beginning of stress to the occurrence of fracture;
the determining module is used for determining the stress stage of the sample weldment according to the first acoustic emission signal data;
wherein the size of the first acoustic emission signal data is in positive correlation with the stress degree corresponding to the stress stage;
the prediction model acquisition module is used for taking the first acoustic emission signal data, the first stress data and the first stress data at the same time point as input, taking the stress stage as output, establishing a stress stage prediction model, and sending the stress stage prediction model to the second test module;
the second testing module is used for acquiring target acoustic emission signal data, actual stress data and actual strain data which respectively correspond to the target welding part at different time points when the target welding part is subjected to tension testing;
The second testing module is further used for inputting the target acoustic emission signal data, the actual stress data and the actual strain data corresponding to the same time point as the stress stage prediction model, acquiring an actual stress stage corresponding to the target welding part, and sending the actual stress stage to the judging module;
the judging module is used for judging whether the actual stress stage reaches the yield stage or not in the process that the actual stress data reaches the preset tension value, if so, stopping the tension test on the target welding part, and determining that the target welding part is an unqualified product; otherwise, determining the target welding part as a qualified product.
2. The non-destructive inspection system of claim 1, wherein said first inspection module comprises a tensile tester, a first extensometer, a first acoustic emission sensor, a first signal amplifier, and a first high frequency signal collector;
the tensile testing machine is used for applying mechanical force to the sample welding part and acquiring the first stress data corresponding to the sample welding part;
the extensometer is used for acquiring the first strain data corresponding to the sample welding piece when the tensile testing machine applies mechanical force to the sample welding piece;
The first acoustic emission sensor is used for acquiring acoustic emission signal data corresponding to the sample welding piece when the tensile testing machine applies mechanical force to the sample welding piece;
the first signal amplifier is used for amplifying the acoustic emission signal data;
the first high-frequency signal collector is used for collecting the high-frequency signals in the acoustic emission signal data after amplification processing.
3. The nondestructive testing system of claim 1, wherein the second testing module comprises a preset tension value obtaining unit, a tension meter, a second extensometer, a second acoustic emission sensor, a second signal amplifier and a second high-frequency signal collector;
the preset tension value acquisition unit is used for acquiring the set preset tension value;
the tension meter is used for applying mechanical force to the target welding part and acquiring the actual stress data corresponding to the target welding part;
the second extensometer is used for acquiring the actual stress data corresponding to the target welding part when the tensile testing machine applies mechanical force to the target welding part;
the second sound emission sensor is used for acquiring target sound emission signal data corresponding to the target welding part when the tensile testing machine applies mechanical force to the target welding part;
The second signal amplifier is used for amplifying the target acoustic emission signal data;
the first high-frequency signal collector is used for collecting the high-frequency signals in the amplified target acoustic emission signal data.
4. The non-destructive inspection system of claim 1, wherein the predictive model acquisition module comprises a data acquisition unit and a model acquisition unit;
the data acquisition unit is used for acquiring the first acoustic emission signal data, the first stress data and the first strain data;
the model obtaining unit is used for adopting a support vector machine, a decision tree algorithm, AdaBoost, a random forest algorithm, a limit tree algorithm, a gradient lifting algorithm, a multilayer perceptron algorithm, a proximity algorithm, a logistic regression algorithm or a linear discrimination algorithm, taking the first acoustic emission signal data, the first stress data and the first stress data of the same time point as input, taking the stress stage as output, and establishing a stress stage prediction model.
5. The nondestructive inspection system of claim 4, wherein the predictive model acquisition module further comprises a preprocessing unit;
the preprocessing unit is used for respectively cleaning the first acoustic emission signal data, the first stress data and the first stress data acquired by the first detection module; and/or the presence of a gas in the gas,
The prediction model acquisition module comprises an application program generation unit, and the second test module comprises an application program receiving unit;
the application program generating unit is used for generating an application program according to the stress stage prediction model established by the model acquiring unit and sending the application program to the application program receiving unit;
the application program receiving unit is used for receiving the application program, and acquiring an actual stress stage corresponding to the target welding part by taking the target acoustic emission signal data, the actual stress data and the actual strain data corresponding to the same time point as the input of the stress stage prediction model based on the application program.
6. The non-destructive inspection system of claim 1, wherein the force-receiving stage comprises an elastic stage, a yield stage, a reinforcement stage, or a fracture stage.
7. A nondestructive testing method implemented by the nondestructive testing system of claim 1, the nondestructive testing method comprising:
when a sample welding piece is subjected to a tension test, the first detection module is adopted to obtain first acoustic emission signal data, first stress data and first strain data which respectively correspond to the sample welding piece at different time points in the whole test process from the beginning of stress to the occurrence of fracture;
Determining the stress stage of the sample weldment according to the first acoustic emission signal data;
wherein the size of the first acoustic emission signal data is in positive correlation with the stress degree corresponding to the stress stage;
taking the first acoustic emission signal data, the first stress data and the first stress data of the same time point as input, taking the stress stage as output, establishing a stress stage prediction model, and sending the stress stage prediction model to the second test module;
when the second testing module is used for testing the tension of the target welding part, target acoustic emission signal data, actual stress data and actual strain data which respectively correspond to the target welding part at different time points are obtained;
the second testing module is adopted to take the target acoustic emission signal data, the actual stress data and the actual strain data corresponding to the same time point as the input of the stress stage prediction model, and the actual stress stage corresponding to the target welding part is obtained;
judging whether the actual stress stage reaches a yield stage or not in the process that the actual stress data reaches a preset tension value, if so, stopping the tension test of the target welding piece, and determining that the target welding piece is an unqualified product; otherwise, determining the target welding part as a qualified product.
8. The non-destructive testing method of claim 7, wherein said first testing module comprises a tensile testing machine, a first extensometer, a first acoustic emission sensor, a first signal amplifier, and a first high frequency signal collector;
when carrying out tensile test to sample welding spare, adopt first detection module obtains the whole testing process of sample welding spare from beginning atress to breaking off, the step that corresponds respectively at different time points first acoustic emission signal data, first stress data and first strain data includes:
applying mechanical force to the sample welding part by using the tensile testing machine, and acquiring the first stress data corresponding to the sample welding part;
when the extensometer is adopted to apply mechanical force to the sample welding part by the tensile testing machine, the first strain data corresponding to the sample welding part is obtained;
when the tensile testing machine applies mechanical force to the sample welding part, the first acoustic emission sensor is adopted to obtain acoustic emission signal data corresponding to the sample welding part;
amplifying the acoustic emission signal data by using the first signal amplifier;
And collecting the high-frequency signals in the acoustic emission signal data after amplification by using the first high-frequency signal collector.
9. The nondestructive testing method of claim 7, wherein the second testing module comprises a preset tension value obtaining unit, a tension meter, a second extensometer, a second acoustic emission sensor, a second signal amplifier and a second high-frequency signal collector;
when the second testing module is adopted to carry out tension testing on the target welding part, the step of acquiring the target acoustic emission signal data, the actual stress data and the actual strain data which respectively correspond to the target welding part at different time points further comprises the following steps:
acquiring the set preset tension value;
applying mechanical force to the target welding part by using the tension meter, and acquiring the actual stress data corresponding to the target welding part;
acquiring actual stress data corresponding to the target welding part by using the second extensometer when the tensile testing machine applies mechanical force to the target welding part;
when the tensile testing machine applies mechanical force to the target welding part, the second acoustic emission sensor is adopted to obtain target acoustic emission signal data corresponding to the target welding part;
Amplifying the target acoustic emission signal data by using the second signal amplifier;
and collecting the high-frequency signals in the amplified target acoustic emission signal data by using the second high-frequency signal collector.
10. The non-destructive inspection method of claim 7, wherein said step of building a stress phase predictive model using said first acoustic emission signal data, said first stress data, and said first strain data at a same time as inputs and said stress phase as an output comprises:
acquiring the first acoustic emission signal data, the first stress data and the first strain data;
and adopting a support vector machine, a decision tree algorithm, AdaBoost, a random forest algorithm, a limit tree algorithm, a gradient lifting algorithm, a multilayer perceptron algorithm, a proximity algorithm, a logistic regression algorithm or a linear discrimination algorithm, taking the first acoustic emission signal data, the first stress data and the first stress data at the same time point as input, taking the stress phase as output, and establishing a stress phase prediction model.
11. The non-destructive inspection method of claim 10, wherein said step of acquiring said first acoustic emission signal data, said first stress data, and said first strain data is further followed by:
Cleaning the first acoustic emission signal data, the first stress data and the first stress data acquired by the first detection module respectively; and/or the presence of a gas in the gas,
the prediction model acquisition module comprises an application program generation unit, and the second test module comprises an application program receiving unit;
the step of sending the stress phase prediction model to the second test module comprises:
generating an application program by adopting the application program generating unit according to the established stress stage prediction model, and sending the application program to the application program receiving unit;
the step of acquiring the actual stress phase corresponding to the target welding part by using the second testing module to take the target acoustic emission signal data, the actual stress data and the actual strain data corresponding to the same time point as the input of the stress phase prediction model comprises the following steps:
and receiving the application program by adopting the application program receiving unit, and taking the target acoustic emission signal data, the actual stress data and the actual strain data corresponding to the same time point as the input of the stress stage prediction model based on the application program to obtain the actual stress stage corresponding to the target welding part.
12. The non-destructive inspection method of claim 7, wherein said force-receiving stage comprises an elastic stage, a yield stage, a reinforcement stage, or a fracture stage.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910339990.4A CN111855397A (en) | 2019-04-25 | 2019-04-25 | Nondestructive testing method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910339990.4A CN111855397A (en) | 2019-04-25 | 2019-04-25 | Nondestructive testing method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111855397A true CN111855397A (en) | 2020-10-30 |
Family
ID=72951469
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910339990.4A Pending CN111855397A (en) | 2019-04-25 | 2019-04-25 | Nondestructive testing method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111855397A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101566601A (en) * | 2009-05-04 | 2009-10-28 | 北京航空航天大学 | System for recognizing tensile damage state of 16Mn steel force-bearing part by adopting neural network and coupling iteration |
| CN101566541A (en) * | 2009-05-04 | 2009-10-28 | 北京航空航天大学 | System for evaluating tensile damage of in-service 16Mn steel force-bearing part by adopting catastrophic model |
| CN102109498A (en) * | 2009-12-28 | 2011-06-29 | 天津工业大学 | Nondestructive testing system and testing analysis method for three-dimensional braided composite material |
| CN102809611A (en) * | 2011-06-02 | 2012-12-05 | 中国人民解放军装甲兵工程学院 | System and method for detecting damage of metal component nondestructively |
| CN103018338A (en) * | 2012-12-05 | 2013-04-03 | 河海大学 | Concrete lossless detection method based on sound emission and neural network |
| CN106370730A (en) * | 2016-08-25 | 2017-02-01 | 中国科学院武汉岩土力学研究所 | Method of precisely measuring damage threshold value of brittle materials on the basis of acoustic emission technology |
-
2019
- 2019-04-25 CN CN201910339990.4A patent/CN111855397A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101566601A (en) * | 2009-05-04 | 2009-10-28 | 北京航空航天大学 | System for recognizing tensile damage state of 16Mn steel force-bearing part by adopting neural network and coupling iteration |
| CN101566541A (en) * | 2009-05-04 | 2009-10-28 | 北京航空航天大学 | System for evaluating tensile damage of in-service 16Mn steel force-bearing part by adopting catastrophic model |
| CN102109498A (en) * | 2009-12-28 | 2011-06-29 | 天津工业大学 | Nondestructive testing system and testing analysis method for three-dimensional braided composite material |
| CN102809611A (en) * | 2011-06-02 | 2012-12-05 | 中国人民解放军装甲兵工程学院 | System and method for detecting damage of metal component nondestructively |
| CN103018338A (en) * | 2012-12-05 | 2013-04-03 | 河海大学 | Concrete lossless detection method based on sound emission and neural network |
| CN106370730A (en) * | 2016-08-25 | 2017-02-01 | 中国科学院武汉岩土力学研究所 | Method of precisely measuring damage threshold value of brittle materials on the basis of acoustic emission technology |
Non-Patent Citations (1)
| Title |
|---|
| 刘同成 等: ""基于ARAMIS的铝合金拉伸过程声发射特性分析"", 《南昌大学学报（工科版）》, vol. 40, no. 2, pages 152 - 157 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109142547B (en) | Acoustic online nondestructive testing method based on convolutional neural network | |
| CN101806778B (en) | Method for non-linear ultrasonic online detection of early fatigue damage of metal material | |
| Fakih et al. | Detection and assessment of flaws in friction stir welded joints using ultrasonic guided waves: experimental and finite element analysis | |
| Ling et al. | Input electrical impedance as quality monitoring signature for characterizing resistance spot welding | |
| CN102809611A (en) | System and method for detecting damage of metal component nondestructively | |
| Summerville et al. | Nugget diameter in resistance spot welding: a comparison between a dynamic resistance based approach and ultrasound C-scan | |
| Rummel | Nondestructive inspection reliability history, status and future path | |
| CN110849973B (en) | High-frequency vibration system and method for nondestructive testing of micro-cracks on surface layer of small-size component | |
| CN111737848A (en) | Hoisting machinery main beam structure crack identification method based on time domain strain signal decomposition | |
| CN202083674U (en) | Large-scale thermal state casting and forging piece thermal treatment crack on-line detector | |
| Bashirov et al. | The technical condition assessment and the resource of safe operation of technological pipelines using electromagnetic-acoustic effect | |
| Harshitha et al. | Damage detection of structural members using internet of things (IoT) paradigm | |
| CN111855397A (en) | Nondestructive testing method and system | |
| CN111006755B (en) | Static detection method for mechanical vibration of ultrasonic welding head | |
| US8426771B2 (en) | Method of monitoring machine condition | |
| CN117191956A (en) | Acoustic emission-based titanium alloy stress corrosion damage classification method and apparatus | |
| CN109059813B (en) | Method for detecting corrosion strength of steel structure of hoisting machinery | |
| Souza et al. | Signal processing techniques for ultrasound automatic identification of flaws in steel welded joints–a comparative analysis | |
| Liang et al. | Fatigue Process Monitoring of Aluminum Alloy Materials Based on AE Technology | |
| JPS62114786A (en) | Method for monitoring processing condition | |
| CN205210025U (en) | Detect ultrasonic detection system of welding seam defect | |
| JP7459835B2 (en) | Evaluation method for steel pipe joints | |
| Qian et al. | Pattern recognition of fatigue damage acoustic emission signal | |
| KR101040926B1 (en) | Method for monitoring machine condition | |
| CN117233347B (en) | Carbon steel spheroidization grade measuring method, system and equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |