CN113607817A - Pipeline girth weld detection method and system, electronic equipment and medium - Google Patents
Pipeline girth weld detection method and system, electronic equipment and medium Download PDFInfo
- Publication number
- CN113607817A CN113607817A CN202110888632.6A CN202110888632A CN113607817A CN 113607817 A CN113607817 A CN 113607817A CN 202110888632 A CN202110888632 A CN 202110888632A CN 113607817 A CN113607817 A CN 113607817A
- Authority
- CN
- China
- Prior art keywords
- ultrasonic
- pipeline
- model
- signal
- parameter
- 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.)
- Granted
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
- G01N29/04—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
-
- 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
- G01N2291/26—Scanned objects
- G01N2291/262—Linear objects
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E30/00—Energy generation of nuclear origin
- Y02E30/30—Nuclear fission reactors
Abstract
The invention is suitable for the technical field of ultrasonic detection, and provides a method, a system, electronic equipment and a medium for detecting a pipeline girth weld, wherein the method comprises the following steps: establishing an ultrasonic echo model of the pipeline circumferential weld according to the ultrasonic parameters and the pipeline parameters; acquiring an ultrasonic signal of a pipeline circumferential weld, inputting the ultrasonic signal into the ultrasonic echo model, and acquiring a sample data set; establishing a detection model for diagnosing the defect of the pipeline circumferential weld according to the sample data set; collecting an ultrasonic signal of a circumferential weld of a pipeline to be detected, and inputting the ultrasonic signal into the ultrasonic echo model to obtain an ultrasonic echo signal to be detected; inputting the ultrasonic echo signal to be detected into the detection model to obtain a detection result; thereby the detectable rate to pipeline girth weld defect when having improved ultrasonic detection.
Description
In the technical field of
The invention relates to the technical field of ultrasonic detection, in particular to a method and a system for detecting a pipeline girth weld, electronic equipment and a medium.
Background
Pipeline transportation of oil and gas resources is an important part of resource allocation systems in China, and compared with a traditional transportation mode, the pipeline transportation has the advantages of being economical and applicable and simple to lay. However, as pipelines increase and the ages of the pipelines increase, leakage accidents are easily caused by the defects of the pipelines under the working environment of high temperature and high pressure, so that huge economic property loss and serious environmental pollution are caused. Long distance oil and gas transmission pipelines are built by welding a large number of pipelines together, which makes the circumferential weld between successive pipelines a significant weak point of the entire pipeline. In addition, when the pipeline works, the pipeline circumferential weld position can gradually generate microscopic and macroscopic defects, and at the moment, a stress concentration area can be easily formed at the defect position of the pipeline circumferential weld, so that the weld defect is developed into a crack, and finally, the limit bearing state of the pipe is reached, and the pipeline is caused to lose efficacy. Therefore, the method and the device can be used for periodically detecting the circumferential weld of the oil and gas pipeline, and early warning is particularly important. In addition, the pipeline circumferential weld has the characteristics of narrow and small internal space of the pipeline, uneven surface, uneven internal pressure and the like, so that the internal detection technology of the pipeline circumferential weld becomes a difficult point for detection.
Disclosure of Invention
The invention provides a method, a system, electronic equipment and a medium for detecting a circumferential weld of a pipeline, and aims to solve the problems of high detection difficulty and low detection accuracy of the circumferential weld of an oil-gas pipeline in the prior art.
The invention provides a pipeline girth weld detection method, which comprises the following steps:
establishing an ultrasonic echo model of the pipeline circumferential weld according to the ultrasonic parameters and the pipeline parameters;
acquiring an ultrasonic signal of a pipeline circumferential weld, inputting the ultrasonic signal into the ultrasonic echo model, and acquiring a sample data set;
establishing a detection model for diagnosing the defect of the pipeline circumferential weld according to the sample data set, wherein the detection model comprises a first model for characteristic extraction and a second model for classifying the output result of the first model;
collecting an ultrasonic signal of a circumferential weld of a pipeline to be detected, and inputting the ultrasonic signal into the ultrasonic echo model to obtain an ultrasonic echo signal to be detected;
and inputting the ultrasonic echo signal to be detected into the detection model to obtain a detection result.
Optionally, the acquiring an ultrasonic signal of a pipe circumferential weld, inputting the ultrasonic signal into the ultrasonic echo model, and acquiring a sample data set specifically includes:
acquiring an ultrasonic signal of a pipeline circumferential weld, and inputting the ultrasonic signal into the ultrasonic echo model to obtain a sample signal;
selecting wavelet basis functions and decomposition layer numbers to decompose the sample signals, and obtaining wavelet coefficients of each layer;
setting a threshold according to a threshold selection rule;
carrying out quantization processing on the wavelet coefficients of each layer according to the set threshold;
and performing wavelet inverse transformation on the wavelet coefficients of each layer after quantization processing to form a sample data set.
Optionally, the selecting method of the wavelet basis function includes:
determining different alternative wavelet basis functions;
respectively acquiring signal parameters after denoising of different alternative wavelet basis functions under the same wavelet decomposition layer number and the same threshold selection rule, wherein the signal parameters comprise a signal-to-noise ratio, a peak signal-to-noise ratio and a mean square error;
and selecting the wavelet basis function according to the signal parameters of the denoised wavelet basis functions with different alternatives.
Optionally, the first model is a convolutional neural network, and the second model is a support vector machine.
Optionally, the establishing a detection model for diagnosing the defect of the pipe girth weld according to the sample data set specifically includes:
inputting the sample data set into the convolutional neural network, extracting the features of the sample data set, inputting the extracted features into the support vector machine, and classifying the features;
and determining the loss of the final classification after forward propagation, and performing iterative update of the weight by adopting a backward propagation algorithm until the loss value of the full convolution neural network model tends to be converged, and stopping training to obtain the detection model.
The invention also provides a pipeline girth weld detection system, which comprises:
the ultrasonic echo model establishing module is used for establishing an ultrasonic echo model of the pipeline circumferential weld according to the ultrasonic parameters and the pipeline parameters;
the sample data set acquisition module is used for acquiring an ultrasonic signal of the pipeline girth weld, inputting the ultrasonic signal into the ultrasonic echo model and acquiring a sample data set;
the detection model establishing module is used for establishing a detection model for diagnosing the defect of the pipeline circumferential weld according to the sample data set, and the detection model comprises a first model for characteristic extraction and a second model for classification;
the to-be-detected signal acquisition module is used for acquiring an ultrasonic signal of a circumferential weld of a to-be-detected pipeline and inputting the ultrasonic signal into the ultrasonic echo model to obtain an ultrasonic echo signal to be detected;
and the detection result output module is used for inputting the ultrasonic echo signal to be detected into the detection model to obtain a detection result.
Optionally, the sample data set obtaining module includes a sample signal collecting unit and a sample signal processing unit;
the ultrasonic signal acquisition unit is used for scanning the outer surface of the pipeline welding line by the electromagnetic ultrasonic transducer and receiving ultrasonic signals reflected by the outer surface of the pipeline welding line, and the scanning points on the outer surface of the pipeline welding line are uniformly distributed;
and the ultrasonic signal processing unit is used for inputting the reflected ultrasonic signal into the ultrasonic echo model to obtain a sample data set.
Optionally, the pipeline parameters include a first pipeline sub-parameter and a second pipeline sub-parameter, the ultrasonic parameters include a first ultrasonic sub-parameter and a second ultrasonic sub-parameter, and the establishing an ultrasonic echo model of the pipeline girth weld according to the ultrasonic parameters and the pipeline parameters specifically includes:
establishing an ultrasonic echo amplitude model of the pipeline girth weld according to the first pipeline sub-parameter and the first ultrasonic sub-parameter, wherein the first pipeline sub-parameter comprises a density difference between a pipeline and a defect, and the first ultrasonic sub-parameter comprises ultrasonic angular frequency and ultrasonic particle parameters;
acquiring an ultrasonic signal of a pipeline circumferential weld, and inputting the ultrasonic signal into the ultrasonic echo amplitude model to obtain an echo amplitude parameter;
and establishing an ultrasonic echo model of the pipeline circumferential weld according to the echo amplitude parameter, the second pipeline sub-parameter and the second ultrasonic sub-parameter, wherein the second pipeline sub-parameter comprises a pipeline thickness parameter, and the second ultrasonic sub-parameter comprises the central frequency, the bandwidth factor and the phase information of the echo.
The present invention also provides an electronic device comprising: a processor and a memory;
the memory is configured to store a computer program and the processor is configured to execute the computer program stored by the memory to cause the electronic device to perform the pipe girth weld detection method.
The present invention also provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the pipe girth weld detection method as described above.
The invention has the beneficial effects that: according to the pipeline girth weld detection method, firstly, an ultrasonic echo model of the pipeline girth weld is established, then the obtained ultrasonic signal of the pipeline girth weld is input into the ultrasonic echo model, so that a sample data set is formed, and then a detection model for diagnosing the pipeline girth weld defects is established according to the sample data set, so that nondestructive detection of the pipeline girth weld to be detected is realized. An ultrasonic echo model is input through a pipeline girth weld ultrasonic signal, so that a defect region signal and a non-defect region signal can be better distinguished; on the basis, a detection model for diagnosing the defects of the pipeline circumferential weld is established, so that the accurate detection of the defects of the pipeline circumferential weld is improved. The wavelet denoising is adopted to eliminate the electronic noise and the backscattering noise in the original signal, and a detection model is established on the basis, so that the inaccuracy of a detection result caused by the noise is avoided, and the detection accuracy is improved. The invention also obtains the ultrasonic signal of the pipeline girth weld by scanning the outer surface of the pipeline welding line by adopting the electromagnetic ultrasonic transducer, thereby reducing the detection difficulty.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed for the embodiments or the prior art descriptions will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.
FIG. 1 is a schematic flow chart of a method for detecting a circumferential weld of a pipeline according to an embodiment of the present invention;
FIG. 2 is a schematic flowchart of a method for acquiring a sample data set according to an embodiment of the present invention;
FIG. 3 is a schematic flow chart of a pipe girth weld inspection system according to an embodiment of the present invention;
FIG. 4 is a diagram of a field device of a pipeline intelligent detection system in an embodiment of the invention.
Detailed Description
The embodiments of the present invention are described below with reference to specific embodiments, and other advantages and effects of the present invention will be easily understood by those skilled in the art from the disclosure of the present specification. The invention is capable of other and different embodiments and of being practiced or of being carried out in various ways, and its several details are capable of modification in various respects, all without departing from the spirit and scope of the present invention. It is to be noted that the features in the following embodiments and examples may be combined with each other without conflict.
It should be noted that the drawings provided in the following embodiments are only for illustrating the basic idea of the present invention, and the components related to the present invention are only shown in the drawings rather than drawn according to the number, shape and size of the components in actual implementation, and the type, quantity and proportion of the components in actual implementation may be changed freely, and the layout of the components may be more complicated.
In order to explain the technical means of the present invention, the following description will be given by way of specific examples.
First embodiment
FIG. 1 is a schematic flow chart of a method for detecting a girth weld in a pipe according to an embodiment of the present invention.
As shown in FIG. 1, the pipeline girth weld detection method comprises steps S110-S150:
s110, establishing an ultrasonic echo model of the pipeline circumferential weld according to the ultrasonic parameters and the pipeline parameters;
s120, acquiring an ultrasonic signal of the pipeline circumferential weld, inputting the ultrasonic signal into an ultrasonic echo model, and acquiring a sample data set;
s130, establishing a detection model for diagnosing the defects of the pipeline circumferential weld according to the sample data set;
s140, collecting an ultrasonic signal of the circumferential weld of the pipeline to be detected, and inputting the ultrasonic signal into an ultrasonic echo model to obtain an ultrasonic echo signal to be detected;
s150, inputting the ultrasonic echo signal to be detected into the detection model to obtain a detection result.
In step S110 of this embodiment, the pipeline parameter includes a first pipeline sub-parameter and a second pipeline sub-parameter, and the ultrasonic wave parameter includes a first ultrasonic wave sub-parameter and a second ultrasonic wave sub-parameter. Establishing an ultrasonic echo model of the pipeline circumferential weld according to the ultrasonic parameters and the pipeline parameters, which specifically comprises the following steps: establishing an ultrasonic echo amplitude model of the pipeline girth weld according to a first pipeline sub-parameter and a first ultrasonic sub-parameter, wherein the first pipeline sub-parameter comprises a density difference between a pipeline and a defect, and the first ultrasonic sub-parameter comprises ultrasonic angular frequency and ultrasonic particle parameters; acquiring an ultrasonic signal of a pipeline circumferential weld, and inputting the ultrasonic signal into the ultrasonic echo amplitude model to obtain an echo amplitude parameter; and establishing an ultrasonic echo model of the pipeline circumferential weld according to the echo amplitude parameter, the second pipeline sub-parameter and the second ultrasonic sub-parameter, wherein the second pipeline sub-parameter comprises a pipeline thickness parameter, and the second ultrasonic sub-parameter comprises the central frequency, the bandwidth factor and the phase information of the echo.
Specifically, the mathematical expression of the echo amplitude parameter β in the ultrasonic echo amplitude model of the pipe girth weld is as follows:
where P represents the electrical power propagating through the cable, δ ρ is the density difference between the pipe and the defect, i is the unit pure imaginary number, ω is the angular frequency of the ultrasonic wave, and u ° is the particle pole without defect field variationStandard of polarization, u is the standard of particle polarization, VFA region for generating ultrasonic echo signals for a pipe girth weld.
Through the mathematical expression of the echo amplitude parameter beta, it can be found that: if a defect occurs in the propagation path of the received echo, P > 0. The amplitude β decreases with increasing P, thus demonstrating that the echo amplitude received from the defective region is more severely attenuated than the echo received from the non-defective region. And inputting the pipeline girth weld ultrasonic signal into the ultrasonic echo model established on the basis to form a sample data set, and establishing a detection model for diagnosing the pipeline girth weld defects according to the sample data set, thereby improving the accuracy of detecting the pipeline girth weld to be detected.
Specifically, the ultrasonic echo model of the pipe girth weld may be denoted as f (t) ═ s (t) + σ e (t);
wherein f (t) is the ultrasonic echo signal, s (t) is the received attenuated ultrasonic echo signal, σ e (t) is the distribution of σ e (t)2(0,1) noise of gaussian random variable distribution;
the mathematical expression of s (t) is:
where β is the echo amplitude parameter, e is a mathematical constant, α is the bandwidth factor, t is time, τ is the pipe thickness parameter, fc is the center frequency of the echo,
indicating the phase.
In step S120 of this embodiment, an ultrasonic signal of a pipe circumferential weld is acquired, and is input into an ultrasonic echo model, and a specific implementation method of acquiring a sample data set is shown in fig. 2, where fig. 2 is a schematic flow diagram of the method for acquiring a sample data set according to an embodiment of the present invention.
As shown in fig. 2, the method for acquiring the sample data set may include the following steps S210-S250:
s210, acquiring an ultrasonic signal of a pipeline circumferential weld, and inputting the ultrasonic signal into an ultrasonic echo model to obtain a sample signal;
s220, selecting wavelet basis functions and decomposition layer number decomposition sample signals, and obtaining wavelet coefficients of each layer;
s230, setting a threshold according to a threshold selection rule;
s240, carrying out quantization processing on wavelet coefficients of each layer according to a set threshold;
and S250, performing inverse wavelet transform on the wavelet coefficients of each layer after quantization processing to form a sample data set.
In steps S210-S250 of this embodiment, the time series signals are converted into a two-dimensional scalar scale map by using a wavelet threshold denoising method, so as to eliminate electronic noise and backscatter noise in the ultrasonic signals of the pipe girth welds; on the basis, a detection model is established, so that inaccuracy of a detection result caused by noise is avoided, and the detection accuracy is improved.
Specifically, the method for selecting the wavelet basis function comprises the following steps: determining different alternative wavelet basis functions; respectively acquiring signal parameters after denoising of different alternative wavelet basis functions under the same wavelet decomposition layer number and the same threshold selection rule, wherein the signal parameters comprise a signal-to-noise ratio, a peak signal-to-noise ratio and a mean square error; and selecting the wavelet basis function according to the signal parameters of the denoised wavelet basis functions with different alternatives. The wavelet basis functions may be selected from a wide range of wavelet basis functions including, but not limited to, Haar wavelets, Daubechies wavelets, mexican hat wavelets, Morlet wavelets, Meyer wavelets. Carrying out N-layer wavelet decomposition on the sample signal by adopting a wavelet basis function to obtain an Nth-layer approximate component of a wavelet coefficient and detail components from the 1 st layer to the Nth layer, and then carrying out threshold quantization denoising processing on the detail components from the 1 st layer to the Nth layer; the threshold selection rule adopts a birge-Massart punishment method, the threshold is adjusted according to the standard deviation of wavelet coefficient estimation noise layers of different decomposition layers, and the maximum decomposition layer number can be set to be 5. Applying wavelet inverse transformation to the N-level correction coefficient, and reconstructing an original signal to obtain a two-dimensional scalar scale map; the sample data set is then formed from the two-dimensional scalar scale map.
In step S130 of this embodiment, the first model is a convolutional neural network, and the second model is a support vector machine. Establishing a detection model for diagnosing the defect of the pipeline circumferential weld according to the sample data set, and specifically comprising the following steps of: inputting a sample data set into the convolutional neural network, extracting the characteristics of the sample data set, inputting the extracted characteristics into a support vector machine, and classifying the characteristics; and determining the loss of the final classification after forward propagation, and performing iterative update of the weight by adopting a backward propagation algorithm until the loss value of the full convolution neural network model tends to be converged, and stopping training to obtain the detection model. Specifically, the convolutional neural network comprises a convolutional layer, an activation layer, a pooling layer and a full-link layer; performing convolution operation on the two-dimensional scalar scale map by the convolution layer to obtain a feature map; the activation layer carries out nonlinear processing and normalization processing on the feature map; the pooling layer is used for pooling the characteristic graph subjected to normalization treatment; and the full connection layer maps the characteristic graph after the pooling treatment to the sample signal to obtain a characteristic vector.
In particular, the convolutional layer computes the outputs of neurons connected to local regions of a two-dimensional scalar scale map, each neuron computing the dot product between their weights and small regions connected to the input volume. The kernel filter will scan the entire area of the coefficient map and perform a convolution operation. N filters are selected, and the calculation result is regarded as a feature map. As the number of layers of convolution increases, the convergence time of the training process also increases. To address this issue, a batchnorm normalization layer was introduced after the Relu layer was activated. In this layer, all input values will be normalized by using the mean and variance of the values in the current mini-batch. Thus, the convergence speed of the training process will be faster and also allow a higher learning rate to be used. The learning rate can be set to 0.1 to balance fast convergence and avoid overfitting problems. Next, the role of the pooling layer is to perform dimensionality reduction on the feature map, thereby reducing the number of parameters and the amount of computation. Common pooling operations are maximum pooling, average pooling and random pooling. Downsampling pooling operations are performed along the spatial dimensions (width, height) of the element map using a Maxpooling layer. After the mth periodic convolution-renormalization gather operation, the output of the last gather layer is connected to the Dropout layer, overcoming the over-fitting problem. Then, the score is calculated next to the full-connection layer, and the feature map is mapped to the sample space to predict the object class, so that the feature map can play the role of a classifier. Finally, the output of the neural network is used to train an SVM classifier with a radial basis kernel. The SVM converts the input into two types of labels, defective or non-defective, thereby achieving classification of the input signal. In this way, the presence of crack defects on the inner surface of the girth weld of the oil and gas pipeline can be identified.
In step S150 of this embodiment, before inputting the ultrasonic echo signal to be detected into the detection model, selecting a wavelet basis function and decomposing the number of layers to decompose the ultrasonic echo signal to be detected, and obtaining wavelet coefficients of each layer; setting a threshold according to a threshold selection rule; carrying out quantization processing on wavelet coefficients of each layer according to a set threshold; and performing inverse wavelet transform on each layer of wavelet coefficients after quantization processing to obtain a two-dimensional scalar scale map corresponding to the ultrasonic echo signal to be detected. And then inputting the two-dimensional scalar scale diagram corresponding to the ultrasonic echo signal to be detected into the detection model to obtain a detection result, thereby realizing the detection of the pipeline to be detected, wherein the detection result comprises defects or no defects.
Second embodiment
Based on the same inventive concept as the method in the first embodiment, correspondingly, the embodiment also provides a pipeline girth weld detection system.
FIG. 3 is a schematic flow chart of a pipe girth weld inspection system provided by the present invention.
As shown in fig. 3, the system 3 shown comprises: the device comprises a 31 ultrasonic echo model establishing module, a 32 sample data set acquiring module, a 33 detection model establishing module, a 34 to-be-detected signal acquiring module and a 35 detection result outputting module.
The ultrasonic echo model establishing module is used for establishing an ultrasonic echo model of the pipeline circumferential weld according to the ultrasonic parameters and the pipeline parameters;
the sample data set acquisition module is used for acquiring an ultrasonic signal of the pipeline girth weld, inputting the ultrasonic signal into the ultrasonic echo model and acquiring a sample data set;
the detection model establishing module is used for establishing a detection model for diagnosing the defect of the pipeline circumferential weld according to the sample data set, and the detection model comprises a first model for characteristic extraction and a second model for classification;
the to-be-detected signal acquisition module is used for acquiring an ultrasonic signal of a circumferential weld of a to-be-detected pipeline and inputting the ultrasonic signal into the ultrasonic echo model to obtain an ultrasonic echo signal to be detected;
and the detection result output module is used for inputting the ultrasonic echo signal to be detected into the detection model to obtain a detection result.
In some exemplary embodiments, the sample data set acquisition module includes a sample signal acquisition unit and a sample signal processing unit;
the ultrasonic signal acquisition unit is used for scanning the outer surface of the pipeline welding line by the electromagnetic ultrasonic transducer and receiving ultrasonic signals reflected by the outer surface of the pipeline welding line, and the scanning points on the outer surface of the pipeline welding line are uniformly distributed;
and the ultrasonic signal processing unit is used for inputting the reflected ultrasonic signal into the ultrasonic echo model to obtain a sample data set.
In some exemplary embodiments, the ultrasonic signal acquisition unit is a pipe gauge, a PC end and mobile client, a database server. The meter is an embedded ARM processor device. The preamplifier is directly connected with an electromagnetic acoustic transducer (EMAT) probe, the electromagnetic ultrasonic transducer scans on the outer surface of a pipeline welding line, the distance between adjacent scanning points is 1 mm, and the scanning original signal of each point is obtained. The original signal is amplified by an amplifier, is subjected to AD conversion and is processed by a signal processing board, and the acquired data is transmitted to a data server through a wireless transmission module. In the transmission process of signals, a mode of double-shielding connection and configuration of a special electric appliance cabinet is adopted, so that electromagnetic interference is effectively reduced.
Specifically, the ultrasonic signal acquisition unit adopts a pipeline intelligent detection system. Wherein the electromagnetic ultrasonic transducer at the pipeline end is a sensing layer in the Internet of things system, the network for transmitting data and commands is a network layer, and the user and the server are application layers. The server is responsible for storing the data of the system, processing and analyzing the data and sending instructions to the detection instrument. The PC end and the mobile end can check the measurement results received by the server in real time. In the intelligent pipeline detection system, a data processing layer is a data server. The method comprises the steps that a server webpage is logged in a PC end or a mobile end, a measurement instruction is sent to a measuring instrument, after an equipment identification instruction, data detection is started, then the data are transmitted to a server through a transmission layer, the server processes and stores the data, and the PC end and the mobile end can obtain required data from the server end to achieve online monitoring.
FIG. 4 is a diagram of a field device of the pipeline intelligent detection system provided by the invention.
As shown in fig. 4, in an industrial internet of things system for intelligent detection of pipelines, a potentiostat is used for providing cathodic protection voltage of the pipelines, a current interrupter is arranged between the potentiostat and the pipelines for on-off control, and a measuring instrument needs to measure the protection voltage and current of the pipelines when the pipelines are powered on and off. The EMAT nondestructive testing system is added with other auxiliary functions for improving the testing precision, speed and intelligentization requirements of the system. When the electromagnetic ultrasonic transducer collects data, the parameters of the probe, the angle setting and the material attenuation parameter are required to be set.
In some exemplary embodiments, the ultrasound echo modeling module includes:
the first pipe sub-parameters include a density difference between the pipe and the defect, the first ultrasonic sub-parameters include an ultrasonic angular frequency and an ultrasonic particle parameter,
the ultrasonic echo amplitude model establishing unit is used for establishing an ultrasonic echo amplitude model of the pipeline circumferential weld according to a first pipeline sub-parameter and a first ultrasonic sub-parameter, wherein the first pipeline sub-parameter comprises the density difference between a pipeline and a defect, and the first ultrasonic sub-parameter comprises ultrasonic angular frequency and ultrasonic particle parameters;
the amplitude parameter acquisition unit is used for acquiring an ultrasonic signal of the pipeline girth weld and inputting the ultrasonic signal into the ultrasonic echo amplitude model to obtain an echo amplitude parameter;
and the ultrasonic echo model establishing unit is used for establishing an ultrasonic echo signal model of the pipeline circumferential weld according to the echo amplitude parameter, the second pipeline sub-parameter and the second ultrasonic sub-parameter, wherein the second pipeline sub-parameter comprises a pipeline thickness parameter, and the second ultrasonic sub-parameter comprises the central frequency, the bandwidth factor and the phase information of the echo.
In some exemplary embodiments, the sample data set acquisition module comprises:
the sample signal acquisition unit is used for acquiring an ultrasonic signal of the pipeline girth weld and inputting the ultrasonic signal into the ultrasonic echo model to obtain a sample signal;
each layer of wavelet coefficient acquisition unit is used for selecting a wavelet basis function and decomposing the layer number to decompose the sample signal and acquiring each layer of wavelet coefficient;
a threshold value determining unit for setting a threshold value according to a threshold value selection rule;
the quantization processing unit is used for performing quantization processing on the wavelet coefficients of each layer according to the set threshold;
the wavelet inverse transformation unit is used for performing wavelet inverse transformation on the quantized wavelet coefficients of each layer to form a sample data set.
In some exemplary embodiments, each layer of the wavelet coefficient acquisition unit includes:
the wavelet basis function acquisition unit is used for determining different alternative wavelet basis functions; respectively acquiring signal parameters after denoising of different alternative wavelet basis functions under the same wavelet decomposition layer number and the same threshold selection rule, wherein the signal parameters comprise a signal-to-noise ratio, a peak signal-to-noise ratio and a mean square error; and selecting the wavelet basis function according to the signal parameters of the denoised wavelet basis functions with different alternatives.
In some exemplary embodiments, the detection model building module comprises:
the training unit is used for inputting the sample data set into the convolutional neural network, extracting the characteristics of the sample data set, inputting the extracted characteristics into the support vector machine and classifying the characteristics;
and the parameter updating unit is used for determining the final classification loss after forward propagation, and performing iterative updating on the weight by adopting a backward propagation algorithm until the loss value of the full convolution neural network model tends to be converged, and stopping training to obtain the detection model.
The present embodiment also provides a computer-readable storage medium on which a computer program is stored, which when executed by a processor implements any of the methods in the present embodiments.
The present embodiment also provides an electronic device, including: a processor and a memory;
the memory is used for storing computer programs, and the processor is used for executing the computer programs stored by the memory so as to enable the electronic equipment to execute the method in the embodiment.
The computer-readable storage medium in the present embodiment can be understood by those skilled in the art as follows: all or part of the steps for implementing the above method embodiments may be performed by hardware associated with a computer program. The aforementioned computer program may be stored in a computer readable storage medium. When executed, the program performs steps comprising the method embodiments described above; and the aforementioned storage medium includes: various media that can store program codes, such as ROM, RAM, magnetic or optical disks.
The electronic device provided by the embodiment comprises a processor, a memory, a transceiver and a communication interface, wherein the memory and the communication interface are connected with the processor and the transceiver and are used for realizing mutual communication, the memory is used for storing a computer program, the communication interface is used for carrying out communication, and the processor and the transceiver are used for operating the computer program to enable the electronic device to execute the steps of the method.
In this embodiment, the Memory may include a Random Access Memory (RAM), and may also include a non-volatile Memory (non-volatile Memory), such as at least one disk Memory.
The Processor may be a general-purpose Processor, and includes a Central Processing Unit (CPU), a Network Processor (NP), and the like; the Integrated Circuit may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, a discrete Gate or transistor logic device, or a discrete hardware component.
In the above-described embodiments, references in the specification to "the present embodiment," "an embodiment," "another embodiment," "in some exemplary embodiments," or "other embodiments" means that a particular feature, structure, or characteristic described in connection with the embodiments is included in at least some embodiments, but not necessarily all embodiments. The various appearances of the phrase "the present embodiment," "one embodiment," or "another embodiment" are not necessarily all referring to the same embodiment.
In the embodiments described above, although the present invention has been described in conjunction with specific embodiments thereof, many alternatives, modifications, and variations of these embodiments will be apparent to those skilled in the art in light of the foregoing description. For example, other memory structures (e.g., dynamic ram (dram)) may use the discussed embodiments. The embodiments of the invention are intended to embrace all such alternatives, modifications and variances that fall within the broad scope of the appended claims.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the system embodiment, since it is substantially similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment.
The invention is operational with numerous general purpose or special purpose computing system environments or configurations. For example: personal computers, server computers, hand-held or portable devices, tablet-type devices, multiprocessor systems, microprocessor-based systems, set top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments that include any of the above systems or devices, and the like.
The invention may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The invention may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.
The foregoing embodiments are merely illustrative of the principles of the present invention and its efficacy, and are not to be construed as limiting the invention. Any person skilled in the art can modify or change the above-mentioned embodiments without departing from the spirit and scope of the present invention. Accordingly, it is intended that all equivalent modifications or changes which can be made by those skilled in the art without departing from the spirit and technical spirit of the present invention be covered by the claims of the present invention.
Claims (10)
1. A method of detecting a pipe girth weld, the method comprising:
establishing an ultrasonic echo model of the pipeline circumferential weld according to the ultrasonic parameters and the pipeline parameters;
acquiring an ultrasonic signal of a pipeline circumferential weld, inputting the ultrasonic signal into the ultrasonic echo model, and acquiring a sample data set;
establishing a detection model for diagnosing the defect of the pipeline circumferential weld according to the sample data set, wherein the detection model comprises a first model for characteristic extraction and a second model for classifying the output result of the first model;
collecting an ultrasonic signal of a circumferential weld of a pipeline to be detected, and inputting the ultrasonic signal into the ultrasonic echo model to obtain an ultrasonic echo signal to be detected;
and inputting the ultrasonic echo signal to be detected into the detection model to obtain a detection result.
2. The method according to claim 1, wherein the acquiring an ultrasonic signal of the pipe girth weld, inputting the ultrasonic signal into the ultrasonic echo model, and acquiring a sample data set specifically comprises:
acquiring an ultrasonic signal of a pipeline circumferential weld, and inputting the ultrasonic signal into the ultrasonic echo model to obtain a sample signal;
selecting wavelet basis functions and decomposition layer numbers to decompose the sample signals, and obtaining wavelet coefficients of each layer;
setting a threshold according to a threshold selection rule;
carrying out quantization processing on the wavelet coefficients of each layer according to the set threshold;
and performing wavelet inverse transformation on the wavelet coefficients of each layer after quantization processing to form a sample data set.
3. The pipeline girth weld detection method of claim 2, wherein the wavelet basis functions are selected by a method comprising:
determining different alternative wavelet basis functions;
respectively acquiring signal parameters after denoising of different alternative wavelet basis functions under the same wavelet decomposition layer number and the same threshold selection rule, wherein the signal parameters comprise a signal-to-noise ratio, a peak signal-to-noise ratio and a mean square error;
and selecting the wavelet basis function according to the signal parameters of the denoised wavelet basis functions with different alternatives.
4. The pipe girth weld detection method of claim 1, wherein the first model is a convolutional neural network and the second model is a support vector machine.
5. The pipeline girth weld detection method according to claim 4, wherein the establishing of the detection model for the fault diagnosis of the pipeline girth weld according to the sample data set specifically comprises:
inputting the sample data set into the convolutional neural network, extracting the features of the sample data set, inputting the extracted features into the support vector machine, and classifying the features;
and determining the loss of the final classification after forward propagation, and performing iterative update of the weight by adopting a backward propagation algorithm until the loss value of the full convolution neural network model tends to be converged, and stopping training to obtain the detection model.
6. The method according to claim 1, wherein the pipe parameters include a first pipe sub-parameter and a second pipe sub-parameter, the ultrasonic parameters include a first ultrasonic sub-parameter and a second ultrasonic sub-parameter, and the establishing an ultrasonic echo signal model of the pipe girth weld according to the ultrasonic parameters and the pipe parameters specifically includes:
establishing an ultrasonic echo amplitude model of the pipeline girth weld according to the first pipeline sub-parameter and the first ultrasonic sub-parameter, wherein the first pipeline sub-parameter comprises a density difference between a pipeline and a defect, and the first ultrasonic sub-parameter comprises ultrasonic angular frequency and ultrasonic particle parameters;
acquiring an ultrasonic signal of a pipeline circumferential weld, and inputting the ultrasonic signal into the ultrasonic echo amplitude model to obtain an echo amplitude parameter;
and establishing an ultrasonic echo signal model of the pipeline circumferential weld according to the echo amplitude parameter, the second pipeline sub-parameter and the second ultrasonic sub-parameter, wherein the second pipeline sub-parameter comprises a pipeline thickness parameter, and the second ultrasonic sub-parameter comprises the central frequency, the bandwidth factor and the phase information of the echo.
7. A pipe girth weld detection system, the system comprising:
the ultrasonic echo model establishing module is used for establishing an ultrasonic echo model of the pipeline circumferential weld according to the ultrasonic parameters and the pipeline parameters;
the sample data set acquisition module is used for acquiring an ultrasonic signal of the pipeline girth weld, inputting the ultrasonic signal into the ultrasonic echo model and acquiring a sample data set;
the detection model establishing module is used for establishing a detection model for diagnosing the defect of the pipeline circumferential weld according to the sample data set, and the detection model comprises a first model for characteristic extraction and a second model for classification;
the to-be-detected signal acquisition module is used for acquiring an ultrasonic signal of a circumferential weld of a to-be-detected pipeline and inputting the ultrasonic signal into the ultrasonic echo model to obtain an ultrasonic echo signal to be detected;
and the detection result output module is used for inputting the ultrasonic echo signal to be detected into the detection model to obtain a detection result.
8. The pipe girth weld inspection system of claim 7, wherein the system comprises:
the sample data set acquisition module comprises a sample signal acquisition unit and a sample signal processing unit;
the ultrasonic signal acquisition unit is used for scanning the outer surface of the pipeline welding line by the electromagnetic ultrasonic transducer and receiving ultrasonic signals reflected by the outer surface of the pipeline welding line, and the scanning points on the outer surface of the pipeline welding line are uniformly distributed;
and the ultrasonic signal processing unit is used for inputting the reflected ultrasonic signal into the ultrasonic echo model to obtain a sample data set.
9. An electronic device comprising a processor, a memory, and a communication bus;
the communication bus is used for connecting the processor and the memory;
the processor is configured to execute a computer program stored in the memory to implement the method of any one of claims 1-6.
10. A computer-readable storage medium, having stored thereon a computer program for causing a computer to perform the method of any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110888632.6A CN113607817B (en) | 2021-08-03 | 2021-08-03 | Pipeline girth weld detection method, system, electronic equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110888632.6A CN113607817B (en) | 2021-08-03 | 2021-08-03 | Pipeline girth weld detection method, system, electronic equipment and medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113607817A true CN113607817A (en) | 2021-11-05 |
| CN113607817B CN113607817B (en) | 2023-07-18 |
Family
ID=78339363
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110888632.6A Active CN113607817B (en) | 2021-08-03 | 2021-08-03 | Pipeline girth weld detection method, system, electronic equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113607817B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115062515A (en) * | 2022-06-23 | 2022-09-16 | 中国矿业大学 | Quantification method for wall thickness, weld reinforcement and defect size of pipeline |
| CN115905961A (en) * | 2023-03-09 | 2023-04-04 | 广东广宇科技发展有限公司 | Pipeline defect analysis method based on multi-source data |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4817016A (en) * | 1986-05-21 | 1989-03-28 | Iowa State University Research Foundation, Inc. | Non-destructive evaluation means and method of flaw reconstruction utilizing an ultrasonic multi-viewing transducer data acquistion system |
| US4922421A (en) * | 1986-12-15 | 1990-05-01 | General Electric Company | Flaw characterization by multiple angle inspection |
| EP1916032A1 (en) * | 2006-10-26 | 2008-04-30 | Interuniversitair Microelektronica Centrum | Manipulation of magnetic or magnetizable objects using combined magnetophoresis and dielectrophoresis |
| CN102636577A (en) * | 2012-03-23 | 2012-08-15 | 南京航空航天大学 | Method for extracting rim ultrasonic flaw detection signal on the basis of wavelet transformation |
| CN107179676A (en) * | 2017-05-24 | 2017-09-19 | 成都理工大学 | Ultrasonic wave flight time measuring method based on digital demodulation |
| CN108613645A (en) * | 2018-05-11 | 2018-10-02 | 中南大学 | A kind of Pb-Zn deposits absorbing well, absorption well surveying on sludge thickness method based on parameter Estimation |
| CN109738519A (en) * | 2019-01-04 | 2019-05-10 | 国网四川省电力公司广安供电公司 | A kind of denoising method of transformer high-voltage bushing lead ultrasound detection |
| CN110045015A (en) * | 2019-04-18 | 2019-07-23 | 河海大学 | A kind of concrete structure Inner Defect Testing method based on deep learning |
| CN110243934A (en) * | 2019-05-30 | 2019-09-17 | 中国计量大学上虞高等研究院有限公司 | A kind of ultrasonic weld seam detection method based on wavelet convolution neural network |
| CN113177432A (en) * | 2021-03-16 | 2021-07-27 | 重庆兆光科技股份有限公司 | Head pose estimation method, system, device and medium based on multi-scale lightweight network |
-
2021
- 2021-08-03 CN CN202110888632.6A patent/CN113607817B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4817016A (en) * | 1986-05-21 | 1989-03-28 | Iowa State University Research Foundation, Inc. | Non-destructive evaluation means and method of flaw reconstruction utilizing an ultrasonic multi-viewing transducer data acquistion system |
| US4922421A (en) * | 1986-12-15 | 1990-05-01 | General Electric Company | Flaw characterization by multiple angle inspection |
| EP1916032A1 (en) * | 2006-10-26 | 2008-04-30 | Interuniversitair Microelektronica Centrum | Manipulation of magnetic or magnetizable objects using combined magnetophoresis and dielectrophoresis |
| CN102636577A (en) * | 2012-03-23 | 2012-08-15 | 南京航空航天大学 | Method for extracting rim ultrasonic flaw detection signal on the basis of wavelet transformation |
| CN107179676A (en) * | 2017-05-24 | 2017-09-19 | 成都理工大学 | Ultrasonic wave flight time measuring method based on digital demodulation |
| CN108613645A (en) * | 2018-05-11 | 2018-10-02 | 中南大学 | A kind of Pb-Zn deposits absorbing well, absorption well surveying on sludge thickness method based on parameter Estimation |
| CN109738519A (en) * | 2019-01-04 | 2019-05-10 | 国网四川省电力公司广安供电公司 | A kind of denoising method of transformer high-voltage bushing lead ultrasound detection |
| CN110045015A (en) * | 2019-04-18 | 2019-07-23 | 河海大学 | A kind of concrete structure Inner Defect Testing method based on deep learning |
| CN110243934A (en) * | 2019-05-30 | 2019-09-17 | 中国计量大学上虞高等研究院有限公司 | A kind of ultrasonic weld seam detection method based on wavelet convolution neural network |
| CN113177432A (en) * | 2021-03-16 | 2021-07-27 | 重庆兆光科技股份有限公司 | Head pose estimation method, system, device and medium based on multi-scale lightweight network |
Non-Patent Citations (9)
| Title |
|---|
| FUKUSHIMA, Y等: "A Performance Study of a Laser Doppler Vibrometer for Measuring Waveforms from Piezoelectric Transducers", 《 IEEE TRANSACTIONS ON ULTRASONICS FERROELECTRICS AND FREQUENCY CONTROL》, vol. 56, no. 7, pages 1442 - 1450, XP011263393 * |
| LU, CY等: "Ultrasonic feature imaging of a multi-layered structure beyond a thin, highly reflective layer using a convolutional neural network", 《INSIGHT 》, vol. 63, no. 4, pages 219 - 228 * |
| THOMPSON, RB等: "A MODEL RELATING ULTRASONIC SCATTERING MEASUREMENTS THROUGH LIQUID SOLID INTERFACES TO UNBOUNDED MEDIUM SCATTERING-AMPLITUDES", 《JOURNAL OF THE ACOUSTICAL SOCIETY OF AMERICA》, vol. 74, no. 4, pages 1279 - 1290 * |
| 张春晓等: "超声多普勒回波信号瞬时幅度和瞬时频率估计的新方法", 《西安交通大学学报》, no. 1, pages 65 - 70 * |
| 戴波等: "超声波管道内检测腐蚀缺陷分类识别研究", 《机床与液压》, no. 7, pages 194 - 198 * |
| 李力等: "液浸法超声检测的探头选择方法研究", 《中国测试》, vol. 41, no. 1, pages 71 - 73 * |
| 杨博: "基于虚拟仪器的表面粗糙钢管超声检测信号处理技术研究", 《中国优秀硕士学位论文全文数据库工程科技Ⅱ辑》, no. 3, pages 028 - 90 * |
| 钟光彬: "基于电磁超声的管道缺陷检测技术研究", 《中国优秀硕士学位论文全文数据库工程科技Ⅰ辑》, no. 3, pages 019 - 87 * |
| 门平等: "材料早期损伤的非线性超声诊断", 《仪器仪表学报》, vol. 38, no. 5, pages 1101 - 1118 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115062515A (en) * | 2022-06-23 | 2022-09-16 | 中国矿业大学 | Quantification method for wall thickness, weld reinforcement and defect size of pipeline |
| CN115062515B (en) * | 2022-06-23 | 2023-09-12 | 中国矿业大学 | Quantification method for wall thickness, weld seam surplus height and defect size of pipeline |
| CN115905961A (en) * | 2023-03-09 | 2023-04-04 | 广东广宇科技发展有限公司 | Pipeline defect analysis method based on multi-source data |
| CN115905961B (en) * | 2023-03-09 | 2023-05-05 | 广东广宇科技发展有限公司 | Pipeline defect analysis method based on multi-source data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113607817B (en) | 2023-07-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113607817B (en) | Pipeline girth weld detection method, system, electronic equipment and medium | |
| Benstock et al. | The influence of surface roughness on ultrasonic thickness measurements | |
| CN112013285B (en) | Method and device for detecting pipeline leakage point, storage medium and terminal | |
| CN103499432B (en) | A kind of image quality detection method of imaging system and system | |
| Wang et al. | Prediction model of natural gas pipeline crack evolution based on optimized DCNN-LSTM | |
| CN112668527A (en) | Ultrasonic guided wave semi-supervised imaging detection method | |
| Sawant et al. | Unsupervised learning framework for temperature compensated damage identification and localization in ultrasonic guided wave SHM with transfer learning | |
| CN115901954A (en) | Nondestructive detection method for ultrasonic guided wave pipeline defects | |
| Liang et al. | A novel faults diagnosis method for rolling element bearings based on ELCD and extreme learning machine | |
| Li et al. | Experimental investigation for fault diagnosis based on a hybrid approach using wavelet packet and support vector classification | |
| Wang et al. | Pipeline leak detection method based on acoustic-pressure information fusion | |
| Peng et al. | A visual vibration characterization method for intelligent fault diagnosis of rotating machinery | |
| Kulakovskyi et al. | Statistical analysis of guided wave imaging algorithms performance illustrated by a simple structural health monitoring configuration | |
| Xiao et al. | Fault diagnosis of gearbox based on wavelet packet transform and CLSPSO-BP | |
| Fridelin et al. | Implementation of microservice architectures on SEMAR extension for air quality monitoring | |
| Ruan et al. | Exploration and effect analysis of improvement in convolution neural network for bearing fault diagnosis | |
| CN115949891B (en) | Intelligent control system and control method for LNG (liquefied Natural gas) station | |
| CN117214294A (en) | Ultrasonic guided wave detection device for pipeline damage and three-dimensional reconstruction method for damage signal of ultrasonic guided wave detection device | |
| CN111090834A (en) | Ocean observation data product quality off-line inspection method and device and server | |
| CN113447111B (en) | Visual vibration amplification method, detection method and system based on morphological component analysis | |
| Yang et al. | A deep learning-based framework for damage detection with time series | |
| Panduman et al. | Implementation of data abstraction layer using kafka on SEMAR platform for air quality monitoring | |
| CN117783279A (en) | Large storage tank defect online monitoring and tracing method and system based on equivalent sound source | |
| CN114460175B (en) | Thin-wall structure damage detection method | |
| Shoupeng et al. | A fractal-dimension-based signal-processing technique and its use for nondestructive testing |
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 | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 400000 6-1, 6-2, 6-3, 6-4, building 7, No. 50, Shuangxing Avenue, Biquan street, Bishan District, Chongqing Applicant after: CHONGQING ZHAOGUANG TECHNOLOGY CO.,LTD. Address before: 400000 2-2-1, 109 Fengtian Avenue, tianxingqiao, Shapingba District, Chongqing Applicant before: CHONGQING ZHAOGUANG TECHNOLOGY CO.,LTD. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |