CN118065977B - Tunnel secondary lining concrete falling block monitoring method based on SVM and ASA - Google Patents
Tunnel secondary lining concrete falling block monitoring method based on SVM and ASA Download PDFInfo
- Publication number
- CN118065977B CN118065977B CN202410481101.9A CN202410481101A CN118065977B CN 118065977 B CN118065977 B CN 118065977B CN 202410481101 A CN202410481101 A CN 202410481101A CN 118065977 B CN118065977 B CN 118065977B
- Authority
- CN
- China
- Prior art keywords
- acoustic
- data
- concrete
- representing
- svm
- 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.)
- Active
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 33
- 238000000034 method Methods 0.000 title claims abstract description 21
- 238000013507 mapping Methods 0.000 claims abstract description 10
- 239000013598 vector Substances 0.000 claims description 23
- 230000008859 change Effects 0.000 claims description 9
- 230000000903 blocking effect Effects 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000005457 optimization Methods 0.000 claims description 3
- 230000000737 periodic effect Effects 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 3
- 238000012423 maintenance Methods 0.000 description 8
- 238000012549 training Methods 0.000 description 5
- 230000002159 abnormal effect Effects 0.000 description 4
- 238000002790 cross-validation Methods 0.000 description 4
- 238000011156 evaluation Methods 0.000 description 3
- 238000013178 mathematical model Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000003673 groundwater Substances 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000003014 reinforcing effect Effects 0.000 description 1
- 238000012502 risk assessment Methods 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
- 230000003313 weakening effect Effects 0.000 description 1
Landscapes
- Investigating Or Analyzing Materials By The Use Of Ultrasonic Waves (AREA)
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
Abstract
The invention discloses a tunnel secondary lining concrete block drop monitoring method based on SVM and ASA, which belongs to the technical field of concrete block drop monitoring and comprises the following steps: collecting sound wave pressure data of concrete in real time; calculating the acoustic singularities of the acoustic pressure data; mapping the acoustic singularity data to a high-dimensional space through a radial basis function kernel RBF, and calculating an inner product of the acoustic singularity data; adjusting the hyper-parameters of the SVM model and the bandwidth parameters of the radial basis function kernel RBF, and optimizing the SVM model; inputting the inner product of the acoustic singularity data into the optimized SVM model, and automatically identifying and positioning the concrete falling blocks; and setting a self-adaptive threshold value, evaluating the risk level of the concrete falling blocks through the threshold value, and carrying out early warning on the concrete falling blocks to finish monitoring of the concrete falling blocks of the second lining of the tunnel. The invention solves the problems that the traditional monitoring method is limited and the position and degree of concrete falling blocks cannot be comprehensively and accurately identified.
Description
Technical Field
The invention belongs to the technical field of concrete block drop monitoring, and particularly relates to a tunnel secondary lining concrete block drop monitoring method based on SVM and ASA.
Background
Tunnel engineering has wide application in modern society, and is used for transportation, underground pipeline, hydroelectric engineering, etc. The concrete structure is used as a common material in tunnel engineering, and plays an important role in supporting and protecting. However, concrete structures are susceptible to various factors, such as temperature changes, groundwater pressure, earthquakes, etc., which result in changes in the structural health. Among them, the problem of chipping is one of the common hidden troubles in concrete structures. Concrete chipping may result in weakening of the structure, corrosion, crack propagation, and overall reduced safety. Traditional monitoring methods are limited, and the positions and the degrees of concrete dropping blocks cannot be comprehensively and accurately identified.
Therefore, a more efficient and accurate monitoring method is needed to solve the concrete fall-off problem. The acoustic singularity analysis ASA combines acoustic features and a mathematical model, can calculate the acoustic singularity features in the acoustic wave sensor data, and can be used for deeply knowing the state of a concrete structure. The ASA can accurately identify the position and degree of the concrete block dropping problem by analyzing the acoustic singularity, and provide timely early warning information, so that the monitoring and maintenance of a concrete structure are improved, and the safety and the sustainability of tunnel engineering are enhanced.
Disclosure of Invention
The invention provides a tunnel secondary lining concrete block falling monitoring method based on SVM and ASA, which solves the problems that the traditional monitoring method is limited and the position and degree of concrete blocks cannot be comprehensively and accurately identified.
In order to solve the technical problems, the technical scheme of the invention is as follows: a tunnel secondary lining concrete block falling monitoring method based on SVM and ASA comprises the following steps:
S1, installing a plurality of acoustic wave sensors on the surface of concrete lining of a tunnel, and acquiring acoustic wave pressure data of the concrete in real time through the acoustic wave sensors;
s2, calculating the acoustic singularities of the sound wave pressure data through ASA (acoustic singularities analysis) to obtain acoustic singularities data;
S3, mapping the acoustic singularity data to a high-dimensional space through a radial basis function kernel RBF, and calculating an inner product of the acoustic singularity data;
S4, adjusting the super-parameters of the SVM model and the bandwidth parameters of the radial basis function kernel RBF, and optimizing the SVM model;
s5, inputting the inner product of the acoustic singularity data into the optimized SVM model, and automatically identifying and positioning concrete dropping blocks;
And S6, setting a self-adaptive threshold value, dynamically adjusting the threshold value according to the historical acoustic singularity data, evaluating the risk level of the concrete falling blocks through the threshold value, and carrying out early warning on the concrete falling blocks to finish monitoring on the concrete falling blocks of the second lining of the tunnel.
Further, the expression of the acoustic wave pressure data in S1 is:
Wherein, Representing the acoustic wave pressure data,Representing the energy of the sound wave,A periodic representation of the sound wave is represented.
Further, the specific step of S2 is as follows:
S21, calculating the differential of the acoustic wave signal in the acoustic wave pressure data in the time domain to obtain the change rate of the acoustic wave pressure;
s22, converting the sound wave signals into a frequency domain through Fourier transformation to obtain the characteristics of the sound wave signals under different frequencies;
S23, carrying out local time-frequency analysis on the change rate of the sound wave pressure and the characteristics of the sound wave signals under different frequencies by adopting short-time Fourier transform STFT to obtain local time-frequency characteristics of the sound wave signals;
s24, calculating the acoustic singularities of the local time-frequency characteristics through ASA (analog to digital) acoustic singularities analysis to obtain acoustic singularity data.
Further, the calculation formula of the acoustic singularities in S24 is:
Wherein, Representing the acoustic singularities,Representing the pressure of the sound wave,Indicating the rate of change of the acoustic wave pressure,The time is represented by the time period of the day,The number of the virtual-parts is represented,Representing the frequency.
Further, the kernel function expression of the radial basis function kernel RBF in S3 is:
Wherein, Representing post-mapping itemData pointsAnd (d)Data pointsThe inner product of the two-way valve,Representing an index the function of the function is that,Bandwidth parameters representing radial basis function kernel RBF kernel functions,Representing post-mapping itemData pointsAnd (d)Data pointsThe square of the euclidean distance between them.
Further, the expression of the super parameter in S4 is:
Wherein, Representing the regularized hyper-parameters of the SVM model,Representing the magnitude of the acoustic wave pressure data,Represent the firstThe data points support the weights of the vectors,Represent the firstThe data points support the weights of the vectors,Represent the firstThe data points support the labels of the vectors,Represent the firstData points support the labels of vectors.
Further, the expression of the decision function of the SVM model after optimization in S5 is:
Wherein, Representation ofIs used for classifying the result of the classification of (a),The sign function is represented by a sign function,Representation ofAnd (3) withIs used for the internal product of (a),The value of the offset is indicated and,The feature vector is represented by a vector of features,Representing the number of support vectors.
Further, the expression of the threshold in S6 is:
Wherein, The threshold value is indicated and the threshold value,Representing the mean value of the acoustic singularity data,Indicating that the parameters of the multiple can be adjusted,Representing the standard deviation of the acoustic singularity data.
The beneficial effects of the invention are as follows: (1) The acoustic singularity analysis ASA combines acoustic features and a mathematical model and can be used for deep understanding of the state of a concrete structure. The position and the degree of the concrete block dropping problem can be accurately identified by analyzing the acoustic singularity, a more accurate monitoring result is provided, and meanwhile, timely early warning information is provided, so that the monitoring and maintenance of a concrete structure are improved, and the safety and the sustainability of tunnel engineering are enhanced;
(2) The ASA combines real-time data acquisition and rapid algorithm processing, so that the monitoring process has high real-time performance and efficiency. This helps in time discover potential problem, reduces the maintenance cost, improves tunnel engineering's security. Meanwhile, the relation between the acoustic singularities and the falling blocks can be automatically learned through the SVM model, so that the accuracy and the automation level of monitoring are improved, the concrete falling blocks are automatically identified and positioned, the SVM model is optimized, and the accuracy of identification and positioning and the model performance can be improved;
(3) By setting the self-adaptive threshold value and triggering the early warning mechanism, early warning can be sent out in time when the risk of falling a block exceeds the threshold value, so that maintenance personnel can take measures in time, and the risk of a concrete structure is reduced.
Drawings
FIG. 1 is a flow chart of a method for monitoring the blocking of a tunnel secondary lining concrete based on SVM and ASA.
FIG. 2 is a diagram of a performance evaluation index according to the present invention.
Detailed Description
Those of ordinary skill in the art will recognize that the embodiments described herein are for the purpose of aiding the reader in understanding the principles of the present invention and should be understood that the scope of the invention is not limited to such specific statements and embodiments. Those of ordinary skill in the art can make various other specific modifications and combinations from the teachings of the present disclosure without departing from the spirit thereof, and such modifications and combinations remain within the scope of the present disclosure.
Examples
As shown in fig. 1, the invention provides a tunnel secondary lining concrete block-falling monitoring method based on SVM and ASA, which comprises the following steps:
S1, installing a plurality of acoustic wave sensors on the surface of concrete lining of a tunnel, and acquiring acoustic wave pressure data of the concrete in real time through the acoustic wave sensors;
s2, calculating the acoustic singularities of the sound wave pressure data through ASA (acoustic singularities analysis) to obtain acoustic singularities data;
S3, mapping the acoustic singularity data to a high-dimensional space through a radial basis function kernel RBF, and calculating an inner product of the acoustic singularity data;
S4, adjusting the super-parameters of the SVM model and the bandwidth parameters of the radial basis function kernel RBF, and optimizing the SVM model;
s5, inputting the inner product of the acoustic singularity data into the optimized SVM model, and automatically identifying and positioning concrete dropping blocks;
And S6, setting a self-adaptive threshold value, dynamically adjusting the threshold value according to the historical acoustic singularity data, evaluating the risk level of the concrete falling blocks through the threshold value, and carrying out early warning on the concrete falling blocks to finish monitoring on the concrete falling blocks of the second lining of the tunnel.
The expression of the sound wave pressure data in the S1 is as follows:
Wherein, Representing the acoustic wave pressure data,Representing the energy of the sound wave,A periodic representation of the sound wave is represented.
The specific steps of the S2 are as follows:
S21, calculating the differential of the acoustic wave signal in the acoustic wave pressure data in the time domain to obtain the change rate of the acoustic wave pressure;
s22, converting the sound wave signals into a frequency domain through Fourier transformation to obtain the characteristics of the sound wave signals under different frequencies;
S23, carrying out local time-frequency analysis on the change rate of the sound wave pressure and the characteristics of the sound wave signals under different frequencies by adopting short-time Fourier transform STFT to obtain local time-frequency characteristics of the sound wave signals;
s24, calculating the acoustic singularities of the local time-frequency characteristics through ASA (analog to digital) acoustic singularities analysis to obtain acoustic singularity data.
The calculation formula of the acoustic singularities in the step S24 is as follows:
Wherein, Representing the acoustic singularities,Representing the pressure of the sound wave,Indicating the rate of change of the acoustic wave pressure,The time is represented by the time period of the day,The number of the virtual-parts is represented,Representing the frequency.
The kernel function expression of the radial basis function kernel RBF in the S3 is as follows:
Wherein, Representing post-mapping itemData pointsAnd (d)Data pointsThe inner product of the two-way valve,Representing an index the function of the function is that,Bandwidth parameters representing radial basis function kernel RBF kernel functions,Representing post-mapping itemData pointsAnd (d)Data pointsThe square of the euclidean distance between them.
In this embodiment, the radial basis function kernel RBF is used to map the acoustic singularity data into a high dimensional space for nonlinear classification. In the mapped high-dimensional space, the inner product is used to calculate the decision function and interval of the support vector machine for classification.
The expression of the super parameter in the S4 is as follows:
Wherein, Representing the regularized hyper-parameters of the SVM model,Representing the magnitude of the acoustic wave pressure data,Represent the firstThe data points support the weights of the vectors,Represent the firstThe data points support the weights of the vectors,Represent the firstThe data points support the labels of the vectors,Represent the firstData points support the labels of vectors.
The expression of the decision function of the SVM model after optimization in the S5 is as follows:
Wherein, Representation ofIs used for classifying the result of the classification of (a),The sign function is represented by a sign function,Representation ofAnd (3) withIs used for the internal product of (a),The value of the offset is indicated and,The feature vector is represented by a vector of features,Representing the number of support vectors.
In the present embodiment, feature vectorsTo include vectors of features that describe corresponding data points, each feature may represent a different attribute or value of an attribute of the data point.
The expression of the threshold in S6 is:
Wherein, The threshold value is indicated and the threshold value,Representing the mean value of the acoustic singularity data,Indicating that the parameters of the multiple can be adjusted,Representing the standard deviation of the acoustic singularity data.
In this embodiment, the marked acoustic singularity data including acoustic singularity data in a normal state and abnormal acoustic singularity data caused by concrete chipping are collected and collated. And extracting the characteristics of acoustic singularities from the training data for training of the SVM model. These features include statistical and frequency domain features of acoustic singularities, etc. And training the SVM model by using the marked acoustic singularity data, so that the model can learn the distinction between the normal acoustic singularity data and the abnormal acoustic singularity data, and the automatic identification of concrete dropping blocks is realized.
The trained SVM model is evaluated and a verification dataset is used to verify the model performance. According to the evaluation result, adjusting the hyper-parameters of the SVM modelBandwidth parameters for radial basis function kernel RBFTo optimize the performance of the model. And storing the trained SVM model, wherein the SVM model is used for analyzing and identifying the block drop of the real-time acoustic singularity data in the monitoring stage.
Wherein, according to the performance evaluation result in the training process, selecting the hyper-parameters of the proper SVM modelBandwidth parameters for radial basis function kernel RBFIs set to be a constant value. Then through grid search method, hyper-parameters of SVM model are performed in a certain rangeBandwidth parameters for radial basis function kernel RBFAnd combining a plurality of groups of different values. These combinations will be used for cross-validation assessment of model performance. The training data is divided into subsets and cross-validation techniques, such as K-fold cross-validation, are used to evaluate the model performance of each superparameter combination. The performance indicators obtained by cross-validation, such as accuracy, recall, and F1 score, are used to evaluate the model performance of each hyper-parametric combination. And selecting the hyper-parameter combination with the best performance in the cross verification as the parameter setting of the final SVM model. The selected optimal hyper-parametric combination is used to retrain the SVM model to optimize the model performance, and then the optimized SVM model is saved for automatic identification and positioning of concrete dropping blocks.
As shown in fig. 2, data points of a normal state and an abnormal state are represented by different colors, decision boundaries of an SVM model are plotted on the graph, the accuracy of this embodiment is 0.99, and the F1 score is 0.98, wherein feature 1 represents a measured value of acoustic characteristics such as sound amplitude, frequency, energy and the like, such as intensity or frequency component of sound, feature 2 represents a measured value of another acoustic characteristic, such as periodicity or amplitude of sound, to provide more information about the acoustic signal, and the acoustic singularity data in the normal state corresponds to the acoustic feature data recorded when the concrete structure is in the normal state, and the acoustic singularity data in the abnormal state corresponds to the acoustic feature data recorded when the concrete structure has a problem (such as concrete fall).
In this embodiment, according to the historical distribution of real-time acoustic singularity data and the acoustic singularities of the concrete in a normal state, an adaptive threshold is set for determining the risk of chipping. And comparing the real-time acoustic singular value with a set threshold value, and judging whether the concrete block falling risk exists. If the acoustic singularity value exceeds a threshold, anomaly detection is triggered. According to the deviation degree of the acoustic singularity value, the risk degree of concrete falling blocks is evaluated, and the concrete falling blocks can be divided into different early warning levels, such as high risk, medium risk and low risk. And triggering early warning of corresponding levels according to the risk assessment result, and sending early warning information to related maintenance personnel or monitoring systems so as to take corresponding maintenance measures. According to the risk level of concrete falling blocks, corresponding maintenance suggestions such as repairing concrete, reinforcing supports and the like are provided so as to reduce risks.
Therefore, the invention improves a more efficient and accurate monitoring method to solve the concrete block dropping problem, wherein the ASA (acoustic singularity analysis) combines acoustic characteristics and a mathematical model, and can be used for deeply knowing the state of a concrete structure. By analyzing the acoustic singularities, the position and degree of the concrete block dropping problem can be accurately identified, and timely early warning information is provided, so that monitoring and maintenance of a concrete structure are improved, safety and sustainability of tunnel engineering are enhanced, the defects of a traditional monitoring method are overcome, and innovation and progress are brought to the field of tunnel engineering and concrete structure monitoring.
Claims (4)
1. A tunnel secondary lining concrete block falling monitoring method based on SVM and ASA is characterized by comprising the following steps:
S1, installing a plurality of acoustic wave sensors on the surface of concrete lining of a tunnel, and acquiring acoustic wave pressure data of the concrete in real time through the acoustic wave sensors;
s2, calculating the acoustic singularities of the sound wave pressure data through ASA (acoustic singularities analysis) to obtain acoustic singularities data;
S3, mapping the acoustic singularity data to a high-dimensional space through a radial basis function kernel RBF, and calculating an inner product of the acoustic singularity data;
S4, adjusting the super-parameters of the SVM model and the bandwidth parameters of the radial basis function kernel RBF, and optimizing the SVM model;
s5, inputting the inner product of the acoustic singularity data into the optimized SVM model, and automatically identifying and positioning concrete dropping blocks;
s6, setting a self-adaptive threshold value, dynamically adjusting the threshold value according to historical acoustic singularity data, evaluating the risk level of concrete falling blocks through the threshold value, and carrying out early warning on the concrete falling blocks to finish monitoring of the concrete falling blocks of the second lining of the tunnel;
the specific steps of the S2 are as follows:
S21, calculating the differential of the acoustic wave signal in the acoustic wave pressure data in the time domain to obtain the change rate of the acoustic wave pressure;
s22, converting the sound wave signals into a frequency domain through Fourier transformation to obtain the characteristics of the sound wave signals under different frequencies;
S23, carrying out local time-frequency analysis on the change rate of the sound wave pressure and the characteristics of the sound wave signals under different frequencies by adopting short-time Fourier transform STFT to obtain local time-frequency characteristics of the sound wave signals;
S24, calculating the acoustic singularities of the local time-frequency characteristics through ASA (analog to digital) acoustic singularities analysis to obtain acoustic singularity data;
The kernel function expression of the radial basis function kernel RBF in the S3 is as follows:
Wherein, Representing post-mapping itemData pointsAnd (d)Data pointsThe inner product of the two-way valve,Representing an index the function of the function is that,Bandwidth parameters representing radial basis function kernel RBF kernel functions,Representing post-mapping itemData pointsAnd (d)Data pointsSquaring the Euclidean distance between the two;
the expression of the super parameter in the S4 is as follows:
Wherein, Representing the regularized hyper-parameters of the SVM model,Representing the magnitude of the acoustic wave pressure data,Represent the firstThe data points support the weights of the vectors,Represent the firstThe data points support the weights of the vectors,Represent the firstThe data points support the labels of the vectors,Represent the firstA label of the data point support vector;
the expression of the decision function of the SVM model after optimization in the S5 is as follows:
Wherein, Representation ofIs used for classifying the result of the classification of (a),The sign function is represented by a sign function,Representation ofAnd (3) withIs used for the internal product of (a),The value of the offset is indicated and,The feature vector is represented by a vector of features,Representing the number of support vectors.
2. The method for monitoring the blocking of the tunnel secondary lining concrete based on the SVM and the ASA according to claim 1, wherein the expression of the acoustic wave pressure data in the S1 is as follows:
Wherein, Representing the acoustic wave pressure data,Representing the energy of the sound wave,A periodic representation of the sound wave is represented.
3. The method for monitoring the blocking loss of the tunnel secondary lining concrete based on the SVM and the ASA according to claim 1, wherein the calculation formula of the acoustic singularities in the S24 is as follows:
Wherein, Representing the acoustic singularities,Representing the pressure of the sound wave,Indicating the rate of change of the acoustic wave pressure,The time is represented by the time period of the day,The number of the virtual-parts is represented,Representing the frequency.
4. The method for monitoring the blocking loss of the tunnel secondary lining concrete based on the SVM and the ASA according to claim 1, wherein the expression of the threshold value in the S6 is:
Wherein, The threshold value is indicated and the threshold value,Representing the mean value of the acoustic singularity data,Indicating that the parameters of the multiple can be adjusted,Representing the standard deviation of the acoustic singularity data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410481101.9A CN118065977B (en) | 2024-04-22 | 2024-04-22 | Tunnel secondary lining concrete falling block monitoring method based on SVM and ASA |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410481101.9A CN118065977B (en) | 2024-04-22 | 2024-04-22 | Tunnel secondary lining concrete falling block monitoring method based on SVM and ASA |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118065977A CN118065977A (en) | 2024-05-24 |
| CN118065977B true CN118065977B (en) | 2024-07-05 |
Family
ID=91095825
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410481101.9A Active CN118065977B (en) | 2024-04-22 | 2024-04-22 | Tunnel secondary lining concrete falling block monitoring method based on SVM and ASA |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118065977B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109239226A (en) * | 2018-10-22 | 2019-01-18 | 嘉兴迈维代谢生物科技有限公司 | A method of it improves while 10 kinds of gibberellin of detection detects stability |
| CN114942268A (en) * | 2022-05-18 | 2022-08-26 | 重庆交通大学 | Tunnel lining crack detection method and inspection system based on acoustic wave change matching |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP5050607B2 (en) * | 2006-05-09 | 2012-10-17 | オムロン株式会社 | INSPECTION DEVICE, INSPECTION METHOD, INSPECTION PROGRAM, AND COMPUTER-READABLE RECORDING MEDIUM CONTAINING THE SAME |
| WO2015164807A1 (en) * | 2014-04-25 | 2015-10-29 | Texas State University | Detection of brain injury and subject state with eye movement biometrics |
| CN112904414B (en) * | 2021-01-19 | 2022-04-01 | 中南大学 | Earth sound event positioning and instability disaster early warning method, sensor and monitoring system |
| KR102350323B1 (en) * | 2021-04-21 | 2022-01-12 | 케이.엘.이.에스 주식회사 | Pipe load monitoring system and method |
| US20230087465A1 (en) * | 2021-09-10 | 2023-03-23 | University Of South Carolina | Short-term AE Monitoring to Identifying ASR Progression in Concrete Structures |
| CN115761732A (en) * | 2022-10-19 | 2023-03-07 | 同济大学 | Three-stage gold wire bonding defect detection method |
-
2024
- 2024-04-22 CN CN202410481101.9A patent/CN118065977B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109239226A (en) * | 2018-10-22 | 2019-01-18 | 嘉兴迈维代谢生物科技有限公司 | A method of it improves while 10 kinds of gibberellin of detection detects stability |
| CN114942268A (en) * | 2022-05-18 | 2022-08-26 | 重庆交通大学 | Tunnel lining crack detection method and inspection system based on acoustic wave change matching |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118065977A (en) | 2024-05-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Regan et al. | Wind turbine blade damage detection using supervised machine learning algorithms | |
| CN111597651B (en) | Rolling bearing performance degradation evaluation method based on HWPSO-SVDD model | |
| CN114563150B (en) | Bridge health online detection module generation method, detection method, tool box and device | |
| CN101718634B (en) | Equipment state comprehensive dynamic alarming method based on multivariate probability model | |
| CN101829689B (en) | Drift fault recognition method of hot-rolling strip steel based on sound signals | |
| Hutton et al. | Real-time burst detection in water distribution systems using a Bayesian demand forecasting methodology | |
| Yang et al. | Pipeline safety early warning by multifeature-fusion CNN and LightGBM analysis of signals from distributed optical fiber sensors | |
| CN111538311B (en) | Flexible multi-state self-adaptive early warning method and device for mechanical equipment based on data mining | |
| CN111695452B (en) | RBF neural network-based parallel reactor internal aging degree assessment method | |
| CN110985310A (en) | Wind driven generator blade fault monitoring method and device based on acoustic sensor array | |
| CN112507479B (en) | Oil drilling machine health state assessment method based on manifold learning and softmax | |
| CN108334988A (en) | A kind of short-term Load Forecasting based on SVM | |
| CN114675261A (en) | Ground penetrating radar-based urban underground disease body full life cycle management method | |
| CN110555235A (en) | Structure local defect detection method based on vector autoregressive model | |
| CN117171657A (en) | Wind power generation equipment fault diagnosis method and device, electronic equipment and storage medium | |
| CN117191147A (en) | Flood discharge dam water level monitoring and early warning method and system | |
| CN118065977B (en) | Tunnel secondary lining concrete falling block monitoring method based on SVM and ASA | |
| Lin et al. | Damage detection in a benchmark structure using long short-term memory networks | |
| CN117007977B (en) | Energy storage battery health state diagnosis method | |
| CN116662899A (en) | Noise-containing data anomaly detection method based on self-adaptive strategy | |
| CN116384732A (en) | Intelligent assessment method, system, storage medium and computing device for station pipeline risk | |
| Lyu et al. | Two-stage intrusion events recognition for vibration signals from distributed optical fiber sensors | |
| CN116415163A (en) | Unmanned aerial vehicle identification method based on radar data | |
| Maxime et al. | Anomaly detection in orthogonal metal cutting based on autoencoder method | |
| CN114969638A (en) | Bridge performance abnormity early warning method based on modal equivalent standardization |
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 |