CN114910553A - Memory, and identification method, device and equipment for hydrogen induced cracking process - Google Patents
Memory, and identification method, device and equipment for hydrogen induced cracking process Download PDFInfo
- Publication number
- CN114910553A CN114910553A CN202110172982.2A CN202110172982A CN114910553A CN 114910553 A CN114910553 A CN 114910553A CN 202110172982 A CN202110172982 A CN 202110172982A CN 114910553 A CN114910553 A CN 114910553A
- Authority
- CN
- China
- Prior art keywords
- hydrogen induced
- induced cracking
- cracking process
- acoustic emission
- hydrogen
- 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
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
- 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
- G01N29/04—Analysing solids
-
- 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
- G01N29/44—Processing the detected response signal, e.g. electronic circuits specially adapted therefor
- G01N29/4472—Mathematical theories or simulation
-
- 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
- G01N29/44—Processing the detected response signal, e.g. electronic circuits specially adapted therefor
- G01N29/4481—Neural networks
-
- 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
- G01N2291/02—Indexing codes associated with the analysed material
- G01N2291/023—Solids
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Pathology (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- Immunology (AREA)
- Engineering & Computer Science (AREA)
- Acoustics & Sound (AREA)
- Signal Processing (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Algebra (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Mathematical Physics (AREA)
- Pure & Applied Mathematics (AREA)
- Investigating Or Analyzing Materials By The Use Of Ultrasonic Waves (AREA)
Abstract
The invention discloses a method and a device for identifying a hydrogen induced cracking process, wherein the method comprises the following steps: A. when a hydrogen induced cracking process of a metal tensile test piece is monitored under the constant load and temperature-controlled hydrogen charging experimental conditions, acoustic emission signals of the whole process are collected; B. performing cluster analysis by taking the time domain parameters extracted from the acoustic emission signals and the wavelet energy spectrum coefficient obtained by calculation as input variables to obtain cluster categories respectively corresponding to three stages of bubble generation and breakage, material surface cracking and separation and hydrogen induced crack growth; C. taking time domain parameters and wavelet energy spectrum coefficients of different regions in the clustering category as input, taking acoustic emission sources of three stages as output, and training a hydrogen induced cracking process recognition model; D. and identifying three stages of the hydrogen induced cracking process corresponding to different acoustic emission signals through the trained hydrogen induced cracking process identification model. The method and the device can quickly and effectively process and analyze acoustic emission signals under different modes in the hydrogen induced cracking process, and provide a theoretical basis for the field monitoring of hydrogen induced cracking of the hydrogen-contacting pressure vessel.
Description
Technical Field
The invention relates to the technical field of monitoring of hydrogen-induced pressure vessels, in particular to a method and a device for identifying and evaluating a hydrogen-induced cracking process.
Background
Hydrogen induced cracking is a destructive phenomenon of a hydrogen-contacting pressure vessel with high occurrence frequency and serious consequences. The application of the hydrogen pressure vessel in petrochemical enterprises is very wide, the hydrogen pressure vessel mostly operates under severe working conditions of high temperature, high pressure, strong corrosivity and the like, the medium of the hydrogen pressure vessel is often flammable and explosive or has corrosive and toxic substances, and once leakage or explosion occurs, the hydrogen pressure vessel is directly related to the safety of people's lives and properties, the national economy and safe operation and the social stability. Therefore, it is an important research topic to effectively perform online real-time monitoring on the hydrogen pressure vessel.
The acoustic emission detection technology is used as a dynamic nondestructive detection method, can effectively represent the internal damage evolution information of the material by monitoring the elastic wave generated by energy release in the material, and is widely applied to the damage detection of various types of materials. The damage mode and the damage process of the material which is cracked by hydrogen are very complicated, and a large number of acoustic emission signals are generated in the damage process. Therefore, fast and effective processing and analysis of hydrogen induced cracking signals is the key to realizing on-line monitoring.
The method for identifying the damage of the fiber braided layer of the composite material based on the acoustic emission means is disclosed in Chinese patent application CN110376289A, belongs to the technical field of nondestructive detection, monitors the damage conditions of different fiber braided layers of the fiber reinforced composite material by using the acoustic emission nondestructive detection means, combines the acoustic emission technology with the wavelet analysis means for analyzing signals in multiple scales and the effective mode identification technology, and can realize effective, accurate and real-time online nondestructive detection on different fiber braided layers of the fiber reinforced composite material structure. The scheme comprises the following steps: establishing a damage characteristic analysis table of the monitored material; and establishing an acoustic emission online monitoring system according to the obtained damage characteristic analysis table. The method can improve the detection accuracy, and has more detailed detection on the damage of the composite material and more reliable evaluation on the damage.
How to effectively identify acoustic emission signals, acquire qualitative and quantitative information of an acoustic emission source from the acoustic signals, extract characteristic parameters of principal components and have important significance on realizing online real-time monitoring of the hydrogen pressure vessel. At present, the more accurate identification of the hydrogen induced cracking process is still needed to be deeply researched, so that different modal conditions of the hydrogen induced cracking process are researched by testing under laboratory conditions and integrating multi-source information such as visual observation, electrochemistry, mechanics, acoustics and the like, corresponding characteristic parameters are extracted, and theoretical basis and technical support are provided for the online monitoring of the hydrogen-contacting pressure vessel.
The information disclosed in this background section is only for enhancement of understanding of the general background of the invention and should not be taken as an acknowledgement or any form of suggestion that this information forms the prior art already known to a person skilled in the art.
Disclosure of Invention
The invention aims to provide a method and a device for identifying a hydrogen induced cracking process, which can be used for carrying out a hydrogen induced cracking test under a laboratory condition, can quickly and effectively process and analyze acoustic emission signals under different modes in the hydrogen induced cracking process, and provides a theoretical basis for on-site monitoring of hydrogen induced cracking by using a hydrogen pressure vessel.
To achieve the above object, according to a first aspect of the present invention, there is provided a method of identifying a hydrogen induced cracking process, comprising the steps of: A. when a hydrogen induced cracking process of a metal tensile test piece is monitored under the constant load and temperature-controlled hydrogen charging experimental conditions, acoustic emission signals of the whole process are collected; B. performing cluster analysis by taking time domain parameters extracted from the acoustic emission signals and wavelet energy spectrum coefficients obtained by calculation as input variables to obtain cluster categories respectively corresponding to three stages of bubble generation and breakage, material surface cracking and separation and hydrogen induced crack growth; C. taking time domain parameters and wavelet energy spectrum coefficients of different regions in the clustering category as input, taking an acoustic emission source in three stages as output, and training a hydrogen induced cracking process identification model; D. and identifying three stages of the hydrogen induced cracking process corresponding to different acoustic emission signals through the trained hydrogen induced cracking process identification model.
Further, in the foregoing technical solution, the time-domain parameter may include: rise time, amplitude, energy, count, and duration of the acoustic emission signal.
Further, in the above technical solution, the calculating of the wavelet energy spectrum coefficient may specifically include: calculating a wavelet decomposition scale for determining the level number of wavelet decomposition; calculating energy values and total energy values in all levels of the waveform function according to the levels of wavelet decomposition; and calculating the wavelet energy spectrum coefficient through the energy values in each stage and the total energy value.
Further, in the above technical solution, a calculation formula of the wavelet decomposition scale is:
wherein f is s Is the sampling frequency, L f Is the filter length, N is the sample length;
the waveform function is embodied as:
f(t)＝f 0 (t)+f 1 (t)+…+f j (t) formula (2);
wherein, f 0 (t)，f 1 (t)，…，f j (t) stages for decomposing the signal;
the energy in each stage is:
the total energy is:
the calculation formula of the wavelet energy spectrum coefficient of each level under the wavelet scale is as follows:
R (j) (t)＝E (j) (t)/E (T) (t) formula (5).
Further, in the above technical solution, the clustering analysis in step B is based on a k-means algorithm to perform iterative computation, and specifically includes: taking the time domain parameters and the wavelet energy spectrum coefficients after normalization processing as the input of the k-means, classifying the acoustic emission signals of the three stages by using weighted Euclidean distances, and acquiring clustering centers corresponding to the three stages respectively; and performing enhancement processing on the marginal data of each cluster center through a compensation algorithm to obtain a cluster type with a clear limit.
Further, in the above technical solution, in the process of obtaining the clustering centers corresponding to the three stages respectively, the condition for determining that clustering is effective is: the Euclidean distance is used as the numerical value of the similarity measure between the acoustic emission signals and is larger than a preset threshold value; the similarity measure formula is:
wherein a (1) represents the average distance between the ith point and other points in the same class; b (1, k) is a vector representing the average distance of the 1 st point from each point in the different classes.
Further, in the above technical solution, the strengthening processing of the marginalized data by the compensation algorithm may specifically be: selecting a cluster center generated by clustering as an anchor point, taking the cluster center as a circle center, taking the maximum value of Euclidean distance as a radius, segmenting the Euclidean distance, dividing a clustering signal in a classification mode into a plurality of regions, compensating different regions to different degrees, and obtaining corresponding compensation coefficients based on a dichotomy so that the marginal data of each region is equal to the clustering center.
Further, in the above technical solution, the hydrogen induced cracking process identification model in step C may be an algorithm model based on a BP neural network.
Further, in the above technical scheme, in the process of establishing the hydrogen induced cracking process identification model, the compensation coefficient can be added into the algorithm of the connection weight of the hydrogen induced cracking process identification model.
To achieve the above object, according to a second aspect of the present invention, there is provided an identification device for a hydrogen induced cracking process, comprising: the acoustic emission signal acquisition module is used for acquiring an acoustic emission signal of the whole process when the hydrogen induced cracking process of the metal tensile test piece is monitored under the constant load and temperature-controlled hydrogen charging experimental conditions; the clustering analysis module is used for performing clustering analysis by taking the time domain parameters extracted from the acoustic emission signals and the wavelet energy spectrum coefficient obtained by calculation as input variables to obtain clustering categories respectively corresponding to three stages of bubble generation and breakage, material surface cracking and separation and hydrogen induced crack growth; the model training module is used for training the hydrogen induced cracking process recognition model by taking time domain parameters and wavelet energy spectrum coefficients of different regions in the clustering category as input and taking an acoustic emission source in three stages as output; and the process identification module is used for identifying three stages of the hydrogen induced cracking process corresponding to different acoustic emission signals through the trained hydrogen induced cracking process identification model.
To achieve the above object, according to a third aspect of the present invention, there is provided a memory including an instruction set adapted to a processor for executing the steps of the method for identifying a hydrogen induced cracking process as described above.
To achieve the above object, according to a fourth aspect of the present invention, there is provided an identification apparatus for hydrogen induced cracking process, comprising a bus, an input device, an output device, a processor and a memory as mentioned above; the bus is used for connecting the memory, the input device, the output device and the processor; the input device and the output device are used for realizing interaction with a user; the processor is configured to execute the set of instructions in the memory.
Compared with the prior art, the invention has the following beneficial effects:
1) according to the invention, the characteristic parameters of the hydrogen induced cracking process identification model can be more effectively represented through the time domain parameters of the five acoustic emission signals and the wavelet energy spectrum coefficient obtained through calculation, and the identification accuracy is higher;
2) in the clustering analysis process, a compensation algorithm is added, and data at the edge of each clustering center can be subjected to enhanced processing, so that the boundaries of clustering categories are clearer, and errors in classification and identification are avoided to the maximum extent;
3) the invention can provide direct basis for the research on damage evolution and failure mechanism in the process of hydrogen induced cracking of the material;
4) the hydrogen induced cracking acoustic emission signal can be effectively identified through a hydrogen induced cracking process identification model established based on a BP neural network, so that the property of the acoustic emission signal source is determined, namely the failure mechanism of the material is judged;
5) the method can be used for judging different stages of hydrogen induced cracking of the material, and has great significance for real-time monitoring of in-service hydrogen pressure vessels.
Other features and aspects of the present invention will become apparent from the following detailed description of exemplary embodiments, which proceeds with reference to the accompanying drawings.
Drawings
One or more embodiments are illustrated by way of example in the accompanying drawings, which correspond to the figures in which like reference numerals refer to similar elements and which are not to scale unless otherwise specified.
FIG. 1 is a schematic flow chart of a method for identifying a hydrogen induced cracking process in embodiment 1 of the present invention;
FIG. 2 is a schematic structural diagram of an identification device for hydrogen induced cracking in embodiment 2 of the present invention;
fig. 3 is a schematic structural diagram of an identification device for a hydrogen induced cracking process in embodiment 4 of the present invention.
Detailed Description
The following detailed description of the present invention is provided in conjunction with the accompanying drawings, but it should be understood that the scope of the present invention is not limited to the specific embodiments.
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be obtained by a person skilled in the art without making any creative effort based on the embodiments in the present invention, belong to the protection scope of the present invention. Throughout the specification and claims, unless explicitly stated otherwise, the term "comprise" or variations such as "comprises" or "comprising", etc., will be understood to imply the inclusion of a stated element or component but not the exclusion of any other element or component.
The word "exemplary" is used exclusively herein to mean "serving as an example, embodiment, or illustration. Any embodiment described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other embodiments.
Furthermore, in the following detailed description, numerous specific details are set forth in order to provide a better understanding of the invention. It will be understood by those skilled in the art that the present invention may be practiced without some of these specific details. In some instances, methods, means, elements well known to those skilled in the art have not been described in detail so as not to obscure the present invention.
Example 1
As shown in fig. 1, embodiment 1 of the identification method for hydrogen induced cracking process of the present invention specifically includes the following steps:
step S101, when a hydrogen induced cracking process of the metal tensile test piece is monitored under the constant load and temperature-controlled hydrogen charging experimental conditions, acoustic emission signals of the whole process are collected. Specifically, a metal material tensile test piece is prepared, the experiment conditions meet the requirements of using a constant load and temperature control hydrogen charging environment, the process of hydrogen induced cracking of a target material test piece under different constant loads and high temperature environments is measured, a PCI-2 full digital acoustic emission instrument can be adopted to collect acoustic emission signals in the whole experiment process, and the whole hydrogen induced cracking process mainly comprises three different stages of bubble generation and cracking in electrolytic hydrogen charging, material surface cracking and separation and hydrogen induced crack growth.
And step S102, recording experimental data. In the whole experiment process, observing an acoustic emission correlation diagram obtained from an acoustic emission instrument in the whole process, observing the rising and the breaking of bubbles in an environment box and the change of a corrosion layer on the surface of a target material test piece by naked eyes, and recording the phenomenon that the target material test piece changes; the experiment can provide acoustic sample data of three different stages of the whole process of hydrogen induced cracking of the metal material under different loading conditions, different temperatures and different hydrogen concentration conditions.
And step S103, extracting time domain parameters from the acquired acoustic emission signals and calculating to obtain wavelet energy spectrum coefficients. Specifically, the time domain parameters of the acoustic emission signal are extracted from the acoustic emission correlation diagram in step S102, and mainly include five feature parameters of the rise time, the amplitude, the energy, the count, and the duration of the acoustic emission signal. And meanwhile, db wavelet decomposition and reconstruction are carried out on the acoustic emission signals obtained through the experiment to obtain a reconstructed acoustic emission waveform signal and a spectrogram, and wavelet energy spectrum coefficients of typical signals of the three types (namely three stages of the hydrogen induced cracking overall process) of the acoustic emission source are calculated. And normalizing the six characteristic parameters by adopting a mean variance normalization method.
The calculation of the wavelet energy spectrum coefficient may specifically include the following steps: firstly, calculating a wavelet decomposition scale for determining the level number of wavelet decomposition; secondly, calculating energy values and total energy values in all levels of the wave function according to the levels of wavelet decomposition; and calculating the wavelet energy spectrum coefficient through the energy values in each stage and the total energy value. The calculation formula of the wavelet decomposition scale can be specifically expressed as follows:
wherein f is s For the sampling frequency, L f Is the filter length and N is the sample length.
The waveform function may be embodied as:
f(t)＝f 0 (t)+f 1 (t)+…+f j (t) formula (2);
wherein, f 0 (t)，f 1 (t)，…，f j (t) represents each stage of the decomposed signal.
The energy in each stage of the waveform function is:
total energy is expressed as:
the calculation formula of the wavelet energy spectrum coefficient of each level under the wavelet scale can be expressed as follows:
R (j) (t)＝E (j) (t)/E (T) (t) formula (5).
As can be seen from equation (5), the wavelet energy spectrum coefficient can be calculated by the ratio of the energy value in each stage of the wave function to the total energy value. The wavelet energy spectrum coefficient obtained by calculation is used as an acoustic emission signal characteristic parameter for identifying a hydrogen induced cracking damage mode of the material, and can be used as an input parameter of subsequent clustering analysis together with other five time domain parameters. Before cluster analysis, normalization processing needs to be carried out on the six characteristic parameters. In this embodiment, normalization processing of the characteristic parameters of the acoustic emission signal is performed by using a mean-square-variance normalization method, and specifically, standard normal distribution transformation is performed on data with a mean value of 0 and a standard deviation of 1. That is, for a sample having n acoustic emission signals, the calculation of the mean-squared-variance normalization can be performed by:
wherein x i Is the original signal parameter;
is the mean value of the original signal parameter; x' i Is a normalized signal parameter; σ is the standard deviation.
And step S104, performing cluster analysis by taking the six characteristic parameters after the normalization processing as input variables to obtain cluster categories respectively corresponding to three stages of bubble generation and breakage, material surface cracking and separation and hydrogen induced crack growth. Specifically, the clustering analysis may be based on a k-means algorithm to perform iterative computation, and the computation process may specifically include:
firstly, a time domain parameter and a wavelet energy spectrum coefficient after normalization processing are used as input of k-means, acoustic emission signals in three stages can be classified by using weighted Euclidean distances in a k-means algorithm iteration process and a sample dividing process, and clustering centers corresponding to the three stages respectively are obtained. In the embodiment, an acoustic emission signal clustering analysis method based on unsupervised pattern recognition is adopted, and acoustic emission signals with similar categories are classified into one category according to a specific similarity measurement method and a clustering algorithm in a certain parameter by selecting characteristic parameters under the condition that a damage pattern and each signal category are unknown. The method specifically comprises the following steps: predefining a classification number k, and selecting k samples as initial clustering centers; calculating the distance between each input vector and the clustering center, distributing the input vectors to the class with the minimum distance from the clustering center to obtain an initial classification scheme, and recalculating the clustering center according to the mean value of each class; reclassifying the samples according to the new clustering centers; and (5) repeatedly and circularly calculating and reclassifying, and finishing clustering when the clustering center is converged.
In the process of obtaining the clustering centers respectively corresponding to the three stages, the effective clustering conditions are determined as follows: the Euclidean distance is used as the numerical value of the similarity measure between the acoustic emission signals and is larger than a preset threshold value; the similarity measure formula is:
wherein a (1) represents the average distance between the ith point and other points in the same class; b (1, k) is a vector representing the average distance of the 1 st point from each point in the different categories. After iterative computation, when the value of s is larger than a preset threshold value, the clustering effectiveness can be determined.
Secondly, the marginalized data of each cluster center is subjected to strengthening processing through a compensation algorithm to obtain the cluster category with clear limit. Because the signal classification of the edge between the clustering centers and the clustering centers at different stages is not clear, the characteristics are not obvious, and the edge is easy to be blurred in the classification process, thereby causing false identification, the edge data of each clustering center is subjected to strengthening processing, and the classification boundary can be clearer. In the embodiment, a compensation algorithm for edge data is used, namely, a cluster center generated by k-means algorithm clustering is selected as an anchor point, the cluster center is used as a circle center, the maximum value of Euclidean distance is used as a radius, the distance is segmented, a clustering signal in a classification mode is divided into a plurality of regions, different degrees of compensation are performed on different regions, and a corresponding compensation coefficient is given based on a dichotomy, so that the significance degree of sound source characteristics (namely, marginalized data) of each region is equal to the cluster center, the fuzzy current situation of the marginalized data is weakened, and the recognition accuracy is improved. Specifically, the maximum distance value can be set as x, the x is segmented based on a bisection method, the segmentation is set as n segments, the iteration step number of the bisection method is n-1, n regions can be sequentially segmented, the reciprocal of the distance length of each region is taken for comparison, the weight occupied by each proportion is calculated according to the comparison value, and the weight is the finally obtained compensation coefficient.
And S105, taking time domain parameters and wavelet energy spectrum coefficients of different regions in the clustering category as input, taking an acoustic emission source in three stages as output, and training a hydrogen induced cracking process recognition model. The hydrogen induced cracking process identification model of the embodiment preferably adopts an algorithm model based on a BP neural network. Specifically, the extracted six characteristic parameters of the rise time, the amplitude, the energy, the count, the duration and the calculated wavelet energy spectrum coefficient of the acoustic emission signals in different areas are used as an input layer of a hydrogen induced cracking process recognition model, three different types of acoustic emission sources are used as an output layer, a three-layer BP neural network consisting of the input layer, a hidden layer and the output layer is established, the compensation coefficient calculated in the step S104 is added into an algorithm of model connection weight, a training sample set and a test sample set of the model are established by using typical data obtained in an experiment, and the model is trained and tested.
And S106, identifying three stages of hydrogen induced cracking processes corresponding to different acoustic emission signals through the trained hydrogen induced cracking process identification model. An intelligent identification method is provided for analyzing the hydrogen induced cracking damage process, and a theoretical basis is provided for on-site monitoring of hydrogen induced cracking of a hydrogen pressure vessel.
The invention provides a direct basis for the research on damage evolution and failure mechanism in the process of hydrogen induced cracking of the material, and the hydrogen induced cracking acoustic emission signal can be effectively identified through a hydrogen induced cracking process identification model established based on a BP neural network, so that the property of the acoustic emission signal source is determined, namely the failure mechanism of the material is judged, different stages of hydrogen induced cracking of the material can be distinguished, and the method has great significance for the real-time monitoring of the in-service hydrogen pressure container. The characteristic parameters of the hydrogen induced cracking process identification model can be more effectively represented through the time domain parameters of the five acoustic emission signals and the wavelet energy spectrum coefficient obtained through calculation, and the identification accuracy is higher. A compensation algorithm is added in the clustering analysis process, and data at the edge of each clustering center can be subjected to enhanced processing, so that the boundaries of clustering categories are clearer, and errors in classification and identification are avoided to the greatest extent.
Example 2
As shown in fig. 2, the identification apparatus for hydrogen induced cracking process of this embodiment is an apparatus corresponding to the identification method in embodiment 1, that is, the method in embodiment 1 is implemented by means of a virtual apparatus, and each virtual module constituting the identification apparatus for hydrogen induced cracking process may be executed by an electronic device, such as a network device, a terminal device, or a server.
The identification device for the hydrogen induced cracking process provided by the embodiment mainly comprises: an acoustic emission signal acquisition module 201, a cluster analysis module 202, a model training module 203, and a process identification module 204. The acoustic emission signal acquisition module 201 is used for acquiring an acoustic emission signal of the whole process when a hydrogen induced cracking process is monitored on a metal tensile test piece under the conditions of constant load and temperature-controlled hydrogen charging experiment; the clustering analysis module 202 is configured to perform clustering analysis by using the time domain parameters extracted from the acoustic emission signals and the calculated wavelet energy spectrum coefficients as input variables, and obtain clustering categories respectively corresponding to three stages of bubble generation and breakage, material surface cracking and separation, and hydrogen induced crack growth; the model training module 203 is used for training the hydrogen induced cracking process recognition model by taking time domain parameters and wavelet energy spectrum coefficients of different regions in the clustering category as input and taking an acoustic emission source in three stages as output; the process identification module 204 is configured to identify three stages of the hydrogen induced cracking process corresponding to different acoustic emission signals through the trained hydrogen induced cracking process identification model.
Example 3
The present embodiments provide a memory that may be a non-transitory (non-volatile) computer storage medium having stored thereon computer-executable instructions that may perform the steps of the method of identifying a hydrogen induced cracking process in any of the above-described method embodiments and achieve the same technical effect.
Example 4
The embodiment provides an identification device for a hydrogen induced cracking process, the device comprises a memory, a corresponding computer program product, and program instructions contained in the computer program product are executed by a computer, so that the computer can execute the identification method for the hydrogen induced cracking process in the above aspects, and achieve the same technical effects.
Fig. 3 is a schematic diagram of a hardware structure of the electronic device according to the embodiment, and as shown in fig. 3, the device includes one or more processors 610 and a memory 620. Take a processor 610 as an example. The apparatus may further include: an input device 630 and an output device 640.
The processor 610, the memory 620, the input device 630, and the output device 640 may be connected by a bus or other means, and are exemplified by a bus in fig. 3.
The memory 620, which is a non-transitory computer readable storage medium, may be used to store non-transitory software programs, non-transitory computer executable programs, and modules. The processor 610 executes various functional applications of the electronic device and data processing, i.e., a processing method implementing the above-described method embodiments, by executing non-transitory software programs, instructions, and modules stored in the memory 620.
The memory 620 may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data and the like. Further, the memory 620 may include high-speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid state storage device. In some embodiments, the memory 620 optionally includes memory located remotely from the processor 610, which may be connected to the processing device via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The input device 630 may receive input numeric or character information and generate a signal input. The output device 640 may include a display device such as a display screen.
The one or more modules are stored in the memory 620 and, when executed by the one or more processors 610, perform: the invention relates to a method for identifying a hydrogen induced cracking process. The product can execute the method provided by the embodiment of the invention, and has corresponding functional modules and beneficial effects of the execution method. For technical details that are not described in detail in this embodiment, reference may be made to the method provided by the embodiment of the present invention.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (12)
1. A method for identifying a hydrogen induced cracking process is characterized by comprising the following steps:
A. when a hydrogen induced cracking process of a metal tensile test piece is monitored under the constant load and temperature-controlled hydrogen charging experimental conditions, acoustic emission signals of the whole process are collected;
B. performing cluster analysis by taking the time domain parameters extracted from the acoustic emission signals and the wavelet energy spectrum coefficient obtained by calculation as input variables to obtain cluster categories respectively corresponding to three stages of bubble generation and breakage, material surface cracking and separation and hydrogen induced crack growth;
C. taking the time domain parameters and wavelet energy spectrum coefficients of different regions in the clustering category as input and the acoustic emission sources in the three stages as output, and training a hydrogen induced cracking process recognition model;
D. and identifying the three stages of the hydrogen induced cracking process corresponding to different acoustic emission signals through the trained hydrogen induced cracking process identification model.
2. The method of identifying a hydrogen induced cracking process of claim 1, wherein the time domain parameters include: rise time, amplitude, energy, count, and duration of the acoustic emission signal.
3. The method for identifying a hydrogen induced cracking process according to claim 1, wherein the calculation of the wavelet energy spectrum coefficients specifically comprises:
calculating a wavelet decomposition scale for determining the level number of wavelet decomposition;
calculating energy values and total energy values in all levels of the waveform function according to the levels of the wavelet decomposition;
and calculating the wavelet energy spectrum coefficient through the energy values in each stage and the total energy value.
4. The method for identifying a hydrogen induced cracking process according to claim 3, wherein the calculation formula of the wavelet decomposition scale is as follows:
wherein f is s For the sampling frequency, L f Is the filter length, N is the sample length;
the waveform function is specifically expressed as:
f(t)＝f 0 (t)+f 1 (t)+…+f j (t) formula (2);
wherein f is 0 (t)，f 1 (t)，…，f j (t) stages for decomposing the signal;
the energy in each stage is:
the total energy is:
the calculation formula of the wavelet energy spectrum coefficient of each level under the wavelet scale is as follows:
R (j) (t)＝E (j) (t)/E (T) (t) formula (5).
5. The method for identifying a hydrogen induced cracking process according to claim 1, wherein the clustering analysis in the step B is based on a k-means algorithm for iterative computation, and specifically comprises:
taking the time domain parameters and the wavelet energy spectrum coefficients after normalization processing as the input of the k-means, classifying the acoustic emission signals of the three stages by using weighted Euclidean distances, and acquiring clustering centers corresponding to the three stages respectively;
and performing strengthening treatment on the marginal data of each cluster center through a compensation algorithm to obtain the cluster category with a clear limit.
6. The method for identifying the hydrogen induced cracking process according to claim 5, wherein in the process of obtaining the clustering centers corresponding to the three stages respectively, the condition for determining the clustering effectiveness is as follows: the Euclidean distance is larger than a preset threshold value as a numerical value of similarity measure among the acoustic emission signals; the similarity measure formula is as follows:
wherein a (1) represents the average distance between the ith point and other points in the same class; b (1, k) is a vector representing the average distance of the 1 st point from each point in the different categories.
7. The method for identifying a hydrogen induced cracking process according to claim 6, wherein the strengthening treatment of the marginalization data through a compensation algorithm specifically comprises:
selecting a cluster center generated by clustering as an anchor point, taking the cluster center as a circle center, taking the maximum value of the Euclidean distance as a radius, segmenting the Euclidean distance, dividing a clustering signal in a classification mode into a plurality of regions, compensating each different region to different degrees, and obtaining corresponding compensation coefficients based on a dichotomy so that the marginalized data of each region is equal to the cluster center.
8. The method for identifying a hydrogen induced cracking process according to claim 1, wherein the hydrogen induced cracking process identification model in the step C is an algorithm model based on a BP neural network.
9. The method for identifying the hydrogen induced cracking process according to claim 7, wherein the compensation coefficient is added to an algorithm of the connection weight of the hydrogen induced cracking process identification model in the process of establishing the hydrogen induced cracking process identification model.
10. An apparatus for identifying a hydrogen induced cracking process, comprising:
the acoustic emission signal acquisition module is used for acquiring an acoustic emission signal of the whole process when monitoring a hydrogen induced cracking process of the metal tensile test piece under the constant load and temperature-controlled hydrogen charging experimental conditions;
the clustering analysis module is used for performing clustering analysis by taking the time domain parameters extracted from the acoustic emission signals and the wavelet energy spectrum coefficients obtained by calculation as input variables to obtain clustering categories respectively corresponding to three stages of bubble generation and breakage, material surface cracking and separation and hydrogen induced crack growth;
the model training module is used for training a hydrogen induced cracking process recognition model by taking the time domain parameters and the wavelet energy spectrum coefficients of different regions in the clustering class as input and taking the acoustic emission sources in the three stages as output;
and the process identification module is used for identifying the three stages of the hydrogen induced cracking process corresponding to different acoustic emission signals through the trained hydrogen induced cracking process identification model.
11. A memory comprising a set of instructions adapted to a processor to perform the steps of the method of identifying a hydrogen induced cracking process according to any one of claims 1 to 9.
12. An apparatus for identifying a hydrogen induced cracking process, comprising a bus, an input device, an output device, a processor and a memory as claimed in claim 11;
the bus is used for connecting the memory, the input device, the output device and the processor;
the input device and the output device are used for realizing interaction with a user;
the processor is configured to execute a set of instructions in the memory.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110172982.2A CN114910553A (en) | 2021-02-08 | 2021-02-08 | Memory, and identification method, device and equipment for hydrogen induced cracking process |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110172982.2A CN114910553A (en) | 2021-02-08 | 2021-02-08 | Memory, and identification method, device and equipment for hydrogen induced cracking process |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114910553A true CN114910553A (en) | 2022-08-16 |
Family
ID=82762139
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110172982.2A Pending CN114910553A (en) | 2021-02-08 | 2021-02-08 | Memory, and identification method, device and equipment for hydrogen induced cracking process |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114910553A (en) |
-
2021
- 2021-02-08 CN CN202110172982.2A patent/CN114910553A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Sun et al. | Statistical wavelet-based method for structural health monitoring | |
| CN109164343B (en) | Transformer fault diagnosis method based on characteristic information quantization and weighted KNN | |
| CN110319982B (en) | Buried gas pipeline leakage judgment method based on machine learning | |
| Ravanfar et al. | A two-step damage identification approach for beam structures based on wavelet transform and genetic algorithm | |
| CN111753776B (en) | Structural damage identification method based on echo state and multi-scale convolution combined model | |
| Paulraj et al. | Structural steel plate damage detection using non destructive testing, frame energy based statistical features and artificial neural networks | |
| CN111398798A (en) | Circuit breaker energy storage state identification method based on vibration signal interval characteristic extraction | |
| CN114217025B (en) | Analysis method for evaluating influence of meteorological data on air quality concentration prediction | |
| CN115856529A (en) | CVT insulation aging state evaluation method based on PDC multi-feature-quantity weight | |
| CN117233347B (en) | Carbon steel spheroidization grade measuring method, system and equipment | |
| CN110568083A (en) | acoustic emission detection method for online monitoring of corrosion fatigue damage of steel | |
| Li et al. | Magnetic barkhausen noise technique for early-stage fatigue prediction in martensitic stainless-steel samples | |
| Tu et al. | A coupling model of multi-feature fusion and multi-machine learning model integration for defect recognition | |
| CN117191956A (en) | Acoustic emission-based titanium alloy stress corrosion damage classification method and apparatus | |
| Wang et al. | The optimal wavelet threshold de-nosing method for acoustic emission signals during the medium strain rate damage process of concrete | |
| CN109840386B (en) | Damage identification method based on factor analysis | |
| CN114910553A (en) | Memory, and identification method, device and equipment for hydrogen induced cracking process | |
| Yan et al. | Mutual Information‐Assisted Wavelet Function Selection for Enhanced Rolling Bearing Fault Diagnosis | |
| CN113238908B (en) | Server performance test data analysis method and related device | |
| Chen et al. | Acoustic emission signal-based non-destructive testing of carbon content of Pr-Nd alloys | |
| CN114609483A (en) | Hilbert transform-based GIS partial discharge signal feature extraction method | |
| CN114462127A (en) | Structural damage identification method and system based on deep extreme learning machine | |
| Kats et al. | Optimization of the features extraction method in cyber physical systems of monitoring energy infrastructure facilities | |
| Joseph et al. | Improved discrimination of electrochemical noise signals using wavelet analysis | |
| Dai et al. | Corrosion process monitoring using wavelet analysis |
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 |