CN117949539A - Engineering building strength detection system and detection method thereof - Google Patents
Engineering building strength detection system and detection method thereof Download PDFInfo
- Publication number
- CN117949539A CN117949539A CN202410345792.XA CN202410345792A CN117949539A CN 117949539 A CN117949539 A CN 117949539A CN 202410345792 A CN202410345792 A CN 202410345792A CN 117949539 A CN117949539 A CN 117949539A
- Authority
- CN
- China
- Prior art keywords
- data
- reflected wave
- monitoring
- path
- strength
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 32
- 238000012544 monitoring process Methods 0.000 claims abstract description 80
- 238000013507 mapping Methods 0.000 claims abstract description 13
- 238000011156 evaluation Methods 0.000 claims abstract description 8
- 230000004927 fusion Effects 0.000 claims abstract description 8
- 238000000034 method Methods 0.000 claims description 31
- 238000012545 processing Methods 0.000 claims description 12
- 108010076504 Protein Sorting Signals Proteins 0.000 claims description 7
- 238000000605 extraction Methods 0.000 claims description 7
- 230000002776 aggregation Effects 0.000 claims description 6
- 238000004220 aggregation Methods 0.000 claims description 6
- 239000000284 extract Substances 0.000 claims description 6
- 238000010606 normalization Methods 0.000 claims description 6
- 230000006870 function Effects 0.000 description 15
- 238000003745 diagnosis Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000005553 drilling Methods 0.000 description 4
- 238000004590 computer program Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 230000002238 attenuated effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000003763 carbonization Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000008054 signal transmission Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000000844 transformation Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Landscapes
- Investigating Or Analyzing Materials By The Use Of Ultrasonic Waves (AREA)
Abstract
The invention provides an engineering building strength detection system and a detection method thereof, which relate to the technical field of strength detection, and are used for constructing a plurality of monitoring paths of a region to be detected and respectively collecting path data of the plurality of monitoring paths; analyzing the collected multiple groups of path data, and selecting a monitoring path corresponding to the path data with the largest clustering gap value as an optimal monitoring path; extracting reflected wave signals in the optimal monitoring path data; carrying out convolution operation on the reflected wave signals, extracting the characteristics of the reflected wave and carrying out characteristic mapping; the data mapped by the features are classified based on a multi-data fusion algorithm, so that the strength state evaluation is carried out, the accuracy and the reliability of the detection result are improved, and a powerful guarantee is provided for the safety and the durability of the building.
Description
Technical Field
The invention provides an engineering building strength detection system and a detection method thereof, and relates to the technical field of strength detection.
Background
In engineering construction, strength detection is a vital link, which concerns the safety and durability of the building. However, although there are a number of detection methods available, each method has its unique advantages and disadvantages. In addition to selecting an appropriate detection method, other important factors in intensity detection should be considered. For example, the representative part of the sample should be selected as much as possible for detection, so that the influence on the overall evaluation result due to local abnormality is avoided. In addition, the influence of environmental factors such as temperature, humidity, etc. should be focused to ensure the stability and reliability of the detection result.
The direct method is the most intuitive method of strength detection, which measures the strength of a structure by performing a pressure test directly on the building structure. The method has high result accuracy, but has great operation difficulty, and can cause damage to building structures. In addition, the direct method is very difficult to implement for large or complex building structures.
The rebound method uses a rebound instrument to measure the hardness of the concrete surface, thereby calculating the compressive strength thereof. The method is simple and convenient to operate, does not damage the surface of the structure, has relatively low precision, and has certain requirements on the water content and carbonization depth of the concrete.
The core drilling method detects the compressive strength of a concrete core sample by drilling it. The method has accurate results, but can cause certain damage to the structure, and has great difficulty in drilling core samples for large or complex building structures.
The comprehensive method combines a plurality of detection methods to improve the accuracy and reliability of the detection result. For example, by combining the rebound method and the core drilling method, the advantages of both methods can be fully utilized, thereby improving the detection accuracy. However, the complex operation of the overall process is high, requiring more equipment and human input.
Disclosure of Invention
In order to solve the technical problems, the invention provides an engineering building strength detection system and a detection method thereof, wherein the detection method comprises the following steps:
S1, constructing a plurality of monitoring paths of a region to be detected, and respectively acquiring path data of the plurality of monitoring paths;
S2, analyzing the collected multiple groups of path data, and selecting a monitoring path corresponding to the path data with the largest clustering gap value as an optimal monitoring path;
S3, extracting reflected wave signals in the optimal monitoring path data;
s4, carrying out convolution operation on the reflected wave signals, extracting the characteristics of the reflected wave and carrying out characteristic mapping;
and S5, classifying the data mapped by the features based on a multi-data fusion algorithm, so as to evaluate the intensity state.
Further, in step S2: the fuzzy clustering gap V D is:
wherein V D represents a fuzzy clustering gap, d b represents an outer gap, d w represents an inner gap, Represents the mean of class 1 data,/>Represents the average of class 2 data, w represents the aggregation direction, T represents the transpose, x i represents the i-th data, n 1 represents the number of class 1 data, and n 2 represents the number of class 2 data.
Further, in step S3: x A (t) is the signal when weak intensity occurs at time t; x B (t) is the signal when the intensity is normal at time t; taking the peak of the first arriving pulse as a reference to perform normalization processing, wherein the signals after normalization processing are as follows:
；
；
In the middle of Is the maximum of the peak of the head wave of the x A (t) signal; /(I)Is the maximum of the peak of the head wave of the x B (t) signal;
the expression of the reflected wave signal r (t) is:
。
Further, in step S4, the expression of reflected wave feature extraction is:
Wherein, Representing convolution operation, H being a convolution window; m represents the number of convolution kernels, M represents the total number of convolution kernels, and Y (t) is the characteristic of the output reflected wave;
and combining the reflected wave characteristics generated at all the moments T in the monitoring period T to form a reflected wave characteristic sequence, wherein the number of the reflected wave characteristic sequences is equal to the number of the moments T in the monitoring period T.
Further, a reflected wave signal sequence obtained in the monitoring period T is setTransmitting the reflected wave signal sequence to the full connection layer for weighted feature mapping:
；
；
；
wherein W S is the weight of the full connection layer, b S is the bias term, u (t) is the output variable of the full connection layer, And f is the final weighted feature map.
Further, in step S5, the category function is expressed as:
；
Output predicted value corresponding to feature map f Expressed as:
；
where y represents the actual class, L is the error function, As a regularization function,/>And (3) the M-th iteration is performed on the diagnostic network model, M is the total iteration number, and Q is all mode spaces of the diagnostic network model.
The invention also provides an engineering building strength detection system for realizing the engineering building strength detection method, which comprises the following steps: the system comprises a plurality of sensors, a central ultrasonic generator, a data acquisition unit, a data processing unit, a monitoring unit and a processor;
installing a plurality of sensors and a central ultrasonic generator on a region to be detected of a building, constructing a plurality of monitoring paths of the region to be detected, and respectively acquiring path data of the plurality of monitoring paths by a data acquisition unit;
The data processing unit analyzes the multiple groups of path data acquired by the data acquisition unit, and selects a monitoring path corresponding to the path data with the largest clustering gap value as an optimal monitoring path;
the monitoring unit extracts reflected wave signals in the optimal monitoring path data;
the processor carries out convolution operation on the reflected wave signals extracted by the monitoring unit, extracts the characteristics of the reflected wave and carries out characteristic mapping; classifying the feature mapped data based on a multi-data fusion algorithm;
and the evaluation unit is used for evaluating the intensity state according to the classification result of the processor.
Compared with the prior art, the invention has the following beneficial technical effects:
The method comprises the steps of constructing a plurality of monitoring paths of a region to be detected, and respectively collecting path data of the plurality of monitoring paths; analyzing the collected multiple groups of path data, and selecting a monitoring path corresponding to the path data with the largest clustering gap value as an optimal monitoring path; extracting reflected wave signals in the optimal monitoring path data; carrying out convolution operation on the reflected wave signals, extracting the characteristics of the reflected wave and carrying out characteristic mapping; classifying the data mapped by the features based on a multi-data fusion algorithm, thereby evaluating the intensity state. The invention can effectively perform nondestructive detection and strength evaluation, and can perform comprehensive scanning and data acquisition on a region to be detected by utilizing the propagation characteristic of ultrasonic waves, thereby providing detailed information about structural integrity and strength, greatly reducing the storage amount and transmission amount of data, improving the accuracy and reliability of detection results and providing powerful guarantee for the safety and durability of a building.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the description of the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort to a person skilled in the art.
FIG. 1 is a flow chart of the method for detecting the strength of an engineering building.
Fig. 2 is a schematic diagram of a reflected wave signal according to the present invention.
Fig. 3 is a schematic diagram of a monitoring path according to the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present application more apparent, the technical solutions of the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application, and it is apparent that the described embodiments are some embodiments of the present application, but not all embodiments of the present application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
In the drawings of the specific embodiments of the present invention, in order to better and more clearly describe the working principle of each element in the system, the connection relationship of each part in the device is represented, but only the relative positional relationship between each element is clearly distinguished, and the limitations on the signal transmission direction, connection sequence and the structure size, dimension and shape of each part in the element or structure cannot be constructed.
As shown in fig. 1, the method for detecting the strength of the engineering building according to the invention comprises the following steps:
S1, constructing a plurality of monitoring paths of a region to be detected, and respectively acquiring path data of the plurality of monitoring paths.
A central ultrasonic generator having a plurality of transducers is mounted on the area of the structure of the building to be measured. The plurality of sensors and the central ultrasonic generator form a plurality of monitoring paths, each of which is composed of the central ultrasonic generator and the sensor, and then data acquisition is performed on each of the monitoring paths.
S2, analyzing the collected multiple groups of path data, and selecting a monitoring path corresponding to the path data with the largest fuzzy clustering gap value as an optimal monitoring path.
And analyzing the plurality of path data by adopting linear discriminant analysis, calculating fuzzy clustering gap values of the plurality of path data, and taking a monitoring path with the maximum fuzzy clustering gap value as an optimal monitoring path.
Based on mass data collection of each monitoring path, the difference among a plurality of monitoring paths is analyzed by utilizing a linear discriminant analysis method, so that the monitoring capability of each monitoring path is evaluated, and the optimal monitoring path is extracted.
The linear discriminant analysis method is a statistical learning method. It projects data from a multidimensional space to a one-dimensional space by finding the most easily classified direction of aggregation to achieve mathematical transformations. The basic idea is to find an aggregation direction such that the gap between two categories in this direction is as large as possible, which gap is also called the outer gap, and the gap inside the same category is as small as possible, which is called the inner gap. To achieve this goal, linear discriminant analysis determines the direction of aggregation by maximizing the ratio of the outer variance to the minimized inner variance.
The key of the optimal monitoring path extraction is to evaluate the capability of each path to monitor damage, and the size of the fuzzy clustering gap determines the damage separability based on the idea that the outer gap is as discrete as possible and the inner gap is as concentrated as possible. The fuzzy clustering gap V D is defined as the ratio of the outer gap to the inner gap:
wherein V D represents a fuzzy clustering gap, d b represents an outer gap, d w represents an inner gap, Represents the mean of class 1 data,/>Represents the mean of class 2 data, w represents the aggregation direction, x i represents the i-th data, n 1 represents the number of class 1 data, and n 2 represents the number of class 2 data.
The damage monitoring capability assessment is mapped into the assessment of the size of a fuzzy clustering gap value of a monitored path, the fuzzy clustering gap of one path represents the damage monitoring capability of the path, and the larger the fuzzy clustering gap is, the stronger the damage distinguishing capability is, otherwise, the smaller the fuzzy clustering gap is, and the weaker the damage monitoring capability is. And selecting a monitoring path corresponding to the path data with the largest clustering gap value as an optimal monitoring path.
And S3, extracting the reflected wave signals in the optimal monitoring path data.
During the propagation of ultrasonic waves, the amplitude of the ultrasonic waves is attenuated along with the propagation gap. In order to make the signals sensed by different sensors have the same effect on weak intensity, the signals need to be normalized.
X A (t) is the signal when weak intensity occurs at time t; x B (t) is the signal when the intensity is normal at time t; taking the peak of the first arriving pulse as a reference to perform normalization processing, wherein the signals after normalization processing are as follows:
；
；
In the middle of Is the maximum of the peak of the head wave of the x A (t) signal; /(I)Is the maximum of the first wave peak of the x B (t) signal.
The expression of the reflected wave signal r (t) is:
s4, carrying out convolution operation on the reflected wave signals, extracting the characteristics of the reflected wave and carrying out characteristic mapping.
Using a convolutional neural network, performing convolutional operation on the reflected wave signals by using a plurality of convolutional checks in a convolutional layer, and performing feature extraction and feature mapping;
a plurality of convolution kernels are defined, each of which can be regarded as a small filter, for identifying and extracting the reflected wave signal sequence.
For each time in the sequence of reflected wave signals, a convolution operation is performed using a defined convolution kernel. The convolution operation may cause each convolution kernel to perform feature extraction on the input reflected wave signal to generate an output reflected wave feature.
As shown in fig. 2, a schematic diagram of a reflected wave signal r (t), where the reflected wave signal r (t) forms a one-dimensional time sequence along with the propagation of the wave, and the distribution of the reflected wave signal r (t) along the time axis changes. When one-dimensional convolution window is used for convolution feature extraction along a time axis, the extracted features have time sequence characteristics
The expression of reflected wave feature extraction is:
Wherein, Representing convolution operation, H being a convolution window; m represents the number of convolution kernels, M represents the total number of convolution kernels, and Y (t) is the output reflected wave characteristic.
And combining the reflected wave characteristics generated at all the moments T in the monitoring period T to form a reflected wave characteristic sequence, wherein the number of the reflected wave characteristic sequences is equal to the number of the moments T in the monitoring period T.
Set up the reflected wave signal sequence obtained in the monitoring period TAnd transmitting the reflected wave signal sequence to the full connection layer for weighted feature mapping.
The process can be shown by the following formula:
；
；
；
Wherein W S is the weight of the full connection layer, b s is the bias term, u (t) is the output variable of the hidden layer, And f is the weight of the output variable at the moment t, and f is the final weighted feature mapping, so that important features are enhanced, and finally, the features for model classification have more expressive ability.
And S5, classifying the data mapped by the features based on a multi-data fusion algorithm, so as to evaluate the intensity state.
And establishing an intensity state diagnosis network model by using a fault classifier, and carrying out fault diagnosis on the data to be tested according to a diagnosis strategy of the intensity state diagnosis network model to obtain a diagnosis result.
Output predicted value corresponding to feature map fExpressed as:
；
In the method, in the process of the invention, And (3) the M-th iteration is performed on the diagnostic network model, M is the total iteration number, and Q is all mode spaces of the diagnostic network model.
The class function of this embodiment classifies the intensity state, and represents the relationship between the predicted class and the actual class of the intensity state. The class functions include an output predicted value, an actual class, an error function, and a regularization function, in a given class function, the predicted output value is compared to the actual class by the error function to calculate a predicted error, and the difference between the predicted value and the actual value is measured by the error function.
The class function is expressed as:
；
In the method, in the process of the invention, And the output predicted value is represented, y represents the actual category, L is an error function, and the error function can adopt any one of square error and cross entropy error.
The regularization function is used for preventing the model from being overfitted, and constraint or punishment is applied to the model parameters, so that the model is more focused on generalization capability in the training process.
The invention also provides an engineering building strength detection system, which comprises: the system comprises a plurality of sensors, a central ultrasonic generator, a data acquisition unit, a data processing unit, a monitoring unit, a processor and an evaluation unit.
The method comprises the steps of installing a plurality of sensors and a central ultrasonic generator on a region to be detected of a building, constructing a plurality of monitoring paths of the region to be detected, and respectively carrying out path data acquisition on the plurality of monitoring paths by a data acquisition unit.
And selecting a proper region to be tested, and installing a plurality of sensors and a central ultrasonic generator according to a preset layout. The sensor and the generator are tightly attached to the area to be detected, so that accurate monitoring data can be obtained.
And constructing a plurality of monitoring paths according to the actual requirements and the shape of the region to be detected. These monitoring paths should cover all directions and critical areas of the area under test to ensure that their integrity is fully assessed. As shown in fig. 3, a schematic diagram of a monitoring path is shown.
The data acquisition unit is configured to be capable of respectively carrying out data acquisition on each monitoring path. The data acquisition unit can record the propagation time, speed and waveform of the ultrasonic wave in the region to be measured.
The data processing unit is used for analyzing the multiple groups of path data acquired by the data acquisition unit, extracting information about the structural strength and the integrity of the region to be detected, comparing the data of different monitoring paths, and selecting the monitoring path corresponding to the path data with the largest clustering gap value as the optimal monitoring path.
The monitoring unit extracts reflected wave signals in the optimal monitoring path data.
The processor carries out convolution operation on the reflected wave signals extracted by the monitoring unit, extracts the characteristics of the reflected wave and carries out characteristic mapping; classifying the feature mapped data based on a multi-data fusion algorithm,
And the evaluation unit is used for evaluating the strength state according to the classification result of the processor and evaluating the structural strength of the building. Further, corresponding advice or repair measures may be provided and detailed intensity detection reports generated based on the evaluation results.
In the above embodiments, it may be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, produces a flow or function in accordance with embodiments of the present application, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. The computer instructions may be stored in or transmitted across a computer-readable storage medium. The computer readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that contains an integration of one or more available media. The usable medium may be a magnetic medium (e.g., floppy disk, hard disk, tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid State Disk (SSD)), etc.
While the application has been described with reference to certain preferred embodiments, it will be understood by those skilled in the art that various changes and substitutions of equivalents may be made and equivalents will be apparent to those skilled in the art without departing from the scope of the application. Therefore, the protection scope of the application is subject to the protection scope of the claims.
Claims (7)
1. The method for detecting the strength of the engineering building is characterized by comprising the following steps of:
S1, constructing a plurality of monitoring paths of a region to be detected, and respectively acquiring path data of the plurality of monitoring paths;
S2, analyzing the collected multiple groups of path data, and selecting a monitoring path corresponding to the path data with the largest clustering gap value as an optimal monitoring path;
S3, extracting reflected wave signals in the optimal monitoring path data;
s4, carrying out convolution operation on the reflected wave signals, extracting the characteristics of the reflected wave and carrying out characteristic mapping;
and S5, classifying the data mapped by the features based on a multi-data fusion algorithm, so as to evaluate the intensity state.
2. The method for detecting the strength of an engineering building according to claim 1, wherein in step S2: the clustering gap value V D is:
；
Wherein d b represents the outer gap, d w represents the inner gap, Represents the mean of class 1 data,/>Represents the average of class 2 data, w represents the aggregation direction, T represents the transpose, x i represents the i-th data, n 1 represents the number of class 1 data, and n 2 represents the number of class 2 data.
3. The method for detecting the strength of an engineering building according to claim 1, wherein in step S3: x A (t) is the signal when weak intensity occurs at time t; x B (t) is the signal when the intensity is normal at time t; taking the peak of the head wave as a reference to perform normalization processing, wherein the signals after normalization processing are as follows:
；
；
In the middle of Is the maximum of the peak of the head wave of signal x A (t); /(I)Is the maximum of the peak of the head wave of signal x B (t);
the expression of the reflected wave signal r (t) is:
。
4. the method for detecting the strength of an engineering building according to claim 3, wherein in the step S4, the expression of the reflected wave feature extraction is:
；
Wherein, Representing convolution operation, H being a convolution window; m represents the number of convolution kernels, M represents the total number of convolution kernels, and Y (t) is the characteristic of the output reflected wave;
and combining the reflected wave characteristics generated at all the moments T in the monitoring period T to form a reflected wave characteristic sequence, wherein the number of the reflected wave characteristic sequences is equal to the number of the moments T in the monitoring period T.
5. The method for detecting the strength of an engineering building according to claim 4, wherein the reflected wave signal sequence obtained in the monitoring period T is setTransmitting the reflected wave signal sequence to a full connection layer for weighted feature mapping:
；
；
；
wherein W S is the weight of the full connection layer, b S is the bias term, u (t) is the output variable of the full connection layer, And f is a weighted feature map, and is the weight of the output variable at the time t.
6. The method for detecting the strength of an engineering building according to claim 5, wherein in the step S5, the class function H is expressed as:
；
Predicted value corresponding to weighted feature map f Expressed as:
；
where y represents the actual class, L is the error function, As a regularization function,/>And (3) the M-th iteration is performed on the diagnostic network model, M is the total iteration number, and Q is all mode spaces of the diagnostic network model.
7. An engineering building strength detection system, for implementing the engineering building strength detection method according to any one of claims 1 to 6, comprising: the system comprises a plurality of sensors, a central ultrasonic generator, a data acquisition unit, a data processing unit, a monitoring unit and a processor;
installing a plurality of sensors and a central ultrasonic generator on a region to be detected of a building, constructing a plurality of monitoring paths of the region to be detected, and respectively acquiring path data of the plurality of monitoring paths by a data acquisition unit;
The data processing unit analyzes the multiple groups of path data acquired by the data acquisition unit, and selects a monitoring path corresponding to the path data with the largest clustering gap value as an optimal monitoring path;
the monitoring unit extracts reflected wave signals in the optimal monitoring path data;
the processor carries out convolution operation on the reflected wave signals extracted by the monitoring unit, extracts the characteristics of the reflected wave and carries out characteristic mapping; classifying the feature mapped data based on a multi-data fusion algorithm;
and the evaluation unit is used for evaluating the intensity state according to the classification result of the processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410345792.XA CN117949539B (en) | 2024-03-26 | Engineering building strength detection system and detection method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410345792.XA CN117949539B (en) | 2024-03-26 | Engineering building strength detection system and detection method thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117949539A true CN117949539A (en) | 2024-04-30 |
| CN117949539B CN117949539B (en) | 2024-06-21 |
Family
ID=
Citations (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101109732A (en) * | 2007-08-08 | 2008-01-23 | 哈尔滨工业大学 | Ultrasound nondestructive detecting echo signal classificating method based on vague plane characteristic |
| CN102393422A (en) * | 2011-08-22 | 2012-03-28 | 江苏省产品质量监督检验研究院 | Ultrasonic time of flight diffraction (TOFD)-based offline defect judgment method |
| CN107367552A (en) * | 2017-07-20 | 2017-11-21 | 厦门大学 | Damage propatagtion method of real-time based on FCM algorithms under the influence of time varying temperature |
| JP2019011996A (en) * | 2017-06-29 | 2019-01-24 | 株式会社フジタ | Standard test body for state evaluation device |
| CN109632958A (en) * | 2018-12-24 | 2019-04-16 | 北京航空航天大学 | A kind of Lamb wave damage detecting method considering crackle orientation |
| CN110221172A (en) * | 2019-06-17 | 2019-09-10 | 海南电网有限责任公司电力科学研究院 | A kind of transmission line of electricity distributed diagnostics automation algorithm |
| CN110503244A (en) * | 2019-07-29 | 2019-11-26 | 武汉大学 | A kind of more observation method networking optimization monitoring methods towards Enteromorpha disaster overlay area |
| CN112557494A (en) * | 2020-11-05 | 2021-03-26 | 广州海关技术中心 | Pollack species identification method based on multiple elements and chemometrics |
| CN112698112A (en) * | 2021-03-23 | 2021-04-23 | 中国人民解放军国防科技大学 | Electromagnetic spectrum map construction method and device, computer equipment and storage medium |
| JP2021081212A (en) * | 2019-11-14 | 2021-05-27 | 株式会社アミック | Diagnosis method for structure |
| CN113933387A (en) * | 2021-09-08 | 2022-01-14 | 南京邮电大学 | Composite material structure damage monitoring method and system |
| CN113933806A (en) * | 2021-08-31 | 2022-01-14 | 西北工业大学 | Sky wave radar multi-path measurement clustering method |
| CN113945641A (en) * | 2021-10-19 | 2022-01-18 | 合肥工业大学 | Ultrasonic-based prestressed pipeline grouting quality detection method |
| CN115173962A (en) * | 2022-06-30 | 2022-10-11 | 中国汽车工程研究院股份有限公司 | V2X channel model cross test verification method facing typical scene |
| CN115308135A (en) * | 2022-08-06 | 2022-11-08 | 福州大学 | Spectrum imaging-based marine dinoflagellate cell concentration detection variable selection method |
| CN115343369A (en) * | 2022-08-18 | 2022-11-15 | 南京工业职业技术大学 | Steel plate defect ultrasonic detection and identification method based on multi-value domain feature classification |
| US20230152212A1 (en) * | 2021-11-13 | 2023-05-18 | Tata Consultancy Services Limited | Non-invasive mechanism providing simultaneous determination of viscosity-temperature variation of lubricant |
| CN116242791A (en) * | 2023-02-09 | 2023-06-09 | 西北农林科技大学 | Apple moldy heart disease detection method integrating spectral morphological characteristics |
| CN116735807A (en) * | 2023-08-09 | 2023-09-12 | 山东优控智能技术有限公司 | Air quality detection and evaluation method based on multi-sensor data |
| CN117147699A (en) * | 2023-10-31 | 2023-12-01 | 江苏蓝格卫生护理用品有限公司 | Medical non-woven fabric detection method and system |
| CN117434144A (en) * | 2023-09-22 | 2024-01-23 | 中国计量科学研究院 | Ultrasonic guided wave damage detection and in-situ calibration method |
Patent Citations (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101109732A (en) * | 2007-08-08 | 2008-01-23 | 哈尔滨工业大学 | Ultrasound nondestructive detecting echo signal classificating method based on vague plane characteristic |
| CN102393422A (en) * | 2011-08-22 | 2012-03-28 | 江苏省产品质量监督检验研究院 | Ultrasonic time of flight diffraction (TOFD)-based offline defect judgment method |
| JP2019011996A (en) * | 2017-06-29 | 2019-01-24 | 株式会社フジタ | Standard test body for state evaluation device |
| CN107367552A (en) * | 2017-07-20 | 2017-11-21 | 厦门大学 | Damage propatagtion method of real-time based on FCM algorithms under the influence of time varying temperature |
| CN109632958A (en) * | 2018-12-24 | 2019-04-16 | 北京航空航天大学 | A kind of Lamb wave damage detecting method considering crackle orientation |
| CN110221172A (en) * | 2019-06-17 | 2019-09-10 | 海南电网有限责任公司电力科学研究院 | A kind of transmission line of electricity distributed diagnostics automation algorithm |
| CN110503244A (en) * | 2019-07-29 | 2019-11-26 | 武汉大学 | A kind of more observation method networking optimization monitoring methods towards Enteromorpha disaster overlay area |
| JP2021081212A (en) * | 2019-11-14 | 2021-05-27 | 株式会社アミック | Diagnosis method for structure |
| CN112557494A (en) * | 2020-11-05 | 2021-03-26 | 广州海关技术中心 | Pollack species identification method based on multiple elements and chemometrics |
| CN112698112A (en) * | 2021-03-23 | 2021-04-23 | 中国人民解放军国防科技大学 | Electromagnetic spectrum map construction method and device, computer equipment and storage medium |
| CN113933806A (en) * | 2021-08-31 | 2022-01-14 | 西北工业大学 | Sky wave radar multi-path measurement clustering method |
| CN113933387A (en) * | 2021-09-08 | 2022-01-14 | 南京邮电大学 | Composite material structure damage monitoring method and system |
| CN113945641A (en) * | 2021-10-19 | 2022-01-18 | 合肥工业大学 | Ultrasonic-based prestressed pipeline grouting quality detection method |
| US20230152212A1 (en) * | 2021-11-13 | 2023-05-18 | Tata Consultancy Services Limited | Non-invasive mechanism providing simultaneous determination of viscosity-temperature variation of lubricant |
| CN115173962A (en) * | 2022-06-30 | 2022-10-11 | 中国汽车工程研究院股份有限公司 | V2X channel model cross test verification method facing typical scene |
| CN115308135A (en) * | 2022-08-06 | 2022-11-08 | 福州大学 | Spectrum imaging-based marine dinoflagellate cell concentration detection variable selection method |
| CN115343369A (en) * | 2022-08-18 | 2022-11-15 | 南京工业职业技术大学 | Steel plate defect ultrasonic detection and identification method based on multi-value domain feature classification |
| CN116242791A (en) * | 2023-02-09 | 2023-06-09 | 西北农林科技大学 | Apple moldy heart disease detection method integrating spectral morphological characteristics |
| CN116735807A (en) * | 2023-08-09 | 2023-09-12 | 山东优控智能技术有限公司 | Air quality detection and evaluation method based on multi-sensor data |
| CN117434144A (en) * | 2023-09-22 | 2024-01-23 | 中国计量科学研究院 | Ultrasonic guided wave damage detection and in-situ calibration method |
| CN117147699A (en) * | 2023-10-31 | 2023-12-01 | 江苏蓝格卫生护理用品有限公司 | Medical non-woven fabric detection method and system |
Non-Patent Citations (7)
| Title |
|---|
| 冉志红;李乔;: "基于模糊聚类和支持向量机的损伤识别方法", 振动工程学报, no. 06, 15 December 2007 (2007-12-15) * |
| 姜绍飞;张帅;: "基于模糊神经网络的数据融合结构损伤识别方法", 工程力学, no. 02, 28 February 2008 (2008-02-28) * |
| 张巍;任环;张凯;李成明;姜青山;: "基于移动软件行为大数据挖掘的恶意软件检测技术", 集成技术, no. 02, 15 March 2016 (2016-03-15) * |
| 本杰明 普朗什: "《计算机视觉实战 基于TensorFlow 2》", 31 August 2021, 机械工业出版社, pages: 71 - 73 * |
| 秦勇等: "《计算智能与交通运输工程应用》", 30 September 2022, 中国铁道出版社有限公司, pages: 87 - 96 * |
| 罗文祁;: "房屋结构健康诊断及发展应用", 广东建材, no. 04, 20 April 2009 (2009-04-20) * |
| 贾海涛: "《基于PyTorch的深度学习与计算机视觉》", 30 June 2022, 电子科技大学出版社, pages: 54 - 56 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104712542B (en) | A kind of reciprocating compressor sensitive features based on Internet of Things are extracted and method for diagnosing faults | |
| Zhang et al. | Deep convolutional neural network probability imaging for plate structural health monitoring using guided waves | |
| CN113435314B (en) | Rolling bearing acoustic signal early fault sensitivity characteristic screening method and system | |
| Miller et al. | Classification of flaw severity using pattern recognition for guided wave-based structural health monitoring | |
| CN112946081B (en) | Ultrasonic imaging method based on intelligent extraction and fusion of defect multiple features | |
| CN112668527A (en) | Ultrasonic guided wave semi-supervised imaging detection method | |
| Sun et al. | Machine learning for ultrasonic nondestructive examination of welding defects: A systematic review | |
| CN106198749A (en) | A kind of data fusion method of multiple sensor based on Metal Crack monitoring | |
| CN111753877B (en) | Product quality detection method based on deep neural network migration learning | |
| Du et al. | Three-dimensional stress wave imaging of wood internal defects using TKriging method | |
| CN112200048A (en) | Regression model-based rotating equipment fault prediction method and system and readable storage medium | |
| CN114705432B (en) | Method and system for evaluating health state of explosion-proof motor bearing | |
| Noh et al. | Application of time series based damage detection algorithms to the benchmark experiment at the National Center for Research on Earthquake Engineering (NCREE) in Taipei, Taiwan | |
| Cao et al. | Seismic damage identification of high arch dams based on an unsupervised deep learning approach | |
| Liu et al. | Monitoring the propagation of mechanical discontinuity using data-driven causal discovery and supervised learning | |
| Simula et al. | Process monitoring and visualization using self-organizing maps | |
| CN114443338A (en) | Sparse negative sample-oriented anomaly detection method, model construction method and device | |
| Sazonov et al. | Fuzzy logic expert system for automated damage detection from changes in strain energy mode shapes | |
| CN117949539B (en) | Engineering building strength detection system and detection method thereof | |
| CN117041972A (en) | Channel-space-time attention self-coding based anomaly detection method for vehicle networking sensor | |
| CN117949539A (en) | Engineering building strength detection system and detection method thereof | |
| Zhao et al. | Automated quantification of small defects in ultrasonic phased array imaging using AWGA-gcForest algorithm | |
| CN114371677B (en) | Industrial process state monitoring method based on spectrum radius-interval principal component analysis | |
| Banerjee et al. | Confidence metric for signal classification in non destructive evaluation | |
| CN112069621B (en) | Method for predicting residual service life of rolling bearing based on linear reliability index |
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 | ||
| GR01 | Patent grant |