CN110632643A - Detection alarm method for preventing third-party construction excavation - Google Patents
Detection alarm method for preventing third-party construction excavation Download PDFInfo
- Publication number
- CN110632643A CN110632643A CN201910899361.7A CN201910899361A CN110632643A CN 110632643 A CN110632643 A CN 110632643A CN 201910899361 A CN201910899361 A CN 201910899361A CN 110632643 A CN110632643 A CN 110632643A
- Authority
- CN
- China
- Prior art keywords
- excavation
- vector
- seismic
- frequency joint
- signal sample
- 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
- 238000009412 basement excavation Methods 0.000 title claims abstract description 75
- 238000010276 construction Methods 0.000 title claims abstract description 29
- 238000000034 method Methods 0.000 title claims abstract description 21
- 238000001514 detection method Methods 0.000 title claims abstract description 19
- 239000013598 vector Substances 0.000 claims abstract description 47
- 238000000354 decomposition reaction Methods 0.000 claims abstract description 16
- 238000013136 deep learning model Methods 0.000 claims abstract description 14
- 230000000694 effects Effects 0.000 claims abstract description 11
- 238000012937 correction Methods 0.000 claims description 24
- 230000006870 function Effects 0.000 claims description 18
- 230000009977 dual effect Effects 0.000 claims description 14
- 239000011159 matrix material Substances 0.000 claims description 12
- 238000003062 neural network model Methods 0.000 claims description 9
- 238000012549 training Methods 0.000 claims description 6
- 238000013528 artificial neural network Methods 0.000 claims description 3
- 238000013135 deep learning Methods 0.000 claims description 3
- 238000011478 gradient descent method Methods 0.000 claims description 3
- 230000010355 oscillation Effects 0.000 claims description 3
- 238000005070 sampling Methods 0.000 claims description 3
- 238000012546 transfer Methods 0.000 claims description 3
- 238000005553 drilling Methods 0.000 claims description 2
- 230000002265 prevention Effects 0.000 description 4
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical compound [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 229910052742 iron Inorganic materials 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 238000011897 real-time detection Methods 0.000 description 1
Images
Classifications
-
- G01V1/01—
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01V—GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
- G01V1/00—Seismology; Seismic or acoustic prospecting or detecting
- G01V1/28—Processing seismic data, e.g. analysis, for interpretation, for correction
- G01V1/282—Application of seismic models, synthetic seismograms
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01V—GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
- G01V1/00—Seismology; Seismic or acoustic prospecting or detecting
- G01V1/28—Processing seismic data, e.g. analysis, for interpretation, for correction
- G01V1/30—Analysis
- G01V1/307—Analysis for determining seismic attributes, e.g. amplitude, instantaneous phase or frequency, reflection strength or polarity
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01V—GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
- G01V2210/00—Details of seismic processing or analysis
- G01V2210/60—Analysis
- G01V2210/63—Seismic attributes, e.g. amplitude, polarity, instant phase
Abstract
The invention provides a detection alarm method for preventing third-party construction excavation, which comprises the following steps: s1, collecting seismic signal samples of different types, and constructing a seismic signal sample database; s2, performing double time-frequency joint decomposition on the acquired seismic signal sample to construct a double time-frequency joint feature vector of the seismic signal sample; s3, constructing a deep learning model for seismic signal detection through the double time-frequency joint feature vectors; s4, the detected seismic signals are predicted and classified by utilizing the deep learning model, and the construction situation with excavation activities is alarmed.
Description
Technical Field
The invention relates to a method for signal detection and pattern recognition, in particular to a detection and alarm method for preventing third-party construction excavation.
Background
The urban underground pipeline is an important infrastructure of a city, is a 'life line' for organically connecting and operating all functional areas of the city, and can cause serious economic loss and potential safety hazard once being excavated and damaged. In practice, various pipelines are buried at different depths in the ground, and many construction activities do not completely grasp the specific situations of the underground pipelines before the road surface is excavated, and do not make a perfect excavation plan to protect the underground pipelines, so that the underground pipelines are easily damaged in the construction process. On the other hand, the underground pipelines are complex and diverse in layout, the sensors are respectively arranged on different pipelines to perform excavation prevention detection alarm, the cost is high, and centralized management and maintenance are difficult. Therefore, a simple and easy third-party construction excavation prevention detection alarm method is needed, real-time detection and alarm are carried out aiming at third-party construction excavation activities, unified safety protection is carried out on underground pipelines, and safe operation of the underground pipelines is effectively guaranteed.
Disclosure of Invention
The invention aims to provide a detection and alarm method for preventing third-party construction excavation.
In practice, according to the length of a pipeline to be monitored, a certain number of seismic sensors are buried in the superficial layer of the earth surface at certain intervals in advance, seismic signals are collected in real time through the sensors, then the excavation signals are detected by using an excavation signal detection depth learning model, excavation signals are identified and classified, and once the fact that construction excavation activities are going on is detected, an alarm signal is sent immediately.
In order to achieve the purpose, the invention provides a detection and alarm method for preventing third-party construction excavation, which comprises the following steps:
s1, collecting seismic signal samples of different types, and constructing a seismic signal sample database;
s2, performing double time-frequency joint decomposition on the acquired seismic signal sample to construct a double time-frequency joint feature vector of the seismic signal sample;
s3, constructing a deep learning model for seismic signal detection through the double time-frequency joint feature vectors;
and S4, utilizing the deep learning model to predict and classify the detected seismic signals and give an alarm for the construction situation with excavation activities.
Preferably, the step S1 further includes: the method comprises the steps of respectively collecting a plurality of excavator excavation background noise type earthquake motion signal samples, a plurality of rammers excavation background noise type earthquake motion signal samples, a plurality of drilling machine excavation background noise type earthquake motion signal samples, a shovel excavation background noise type earthquake motion signal sample and a plurality of excavation-free background noise type earthquake motion signal samples, and constructing an earthquake motion signal database according to the collected various earthquake motion signal samples.
Preferably, the acquisition frequency of the seismic motion signal is 7500 points per second, and the sampling time of the seismic motion signal sample is 10 seconds.
Preferably, the step S2 further includes: defining the seismic signal samples as a time sequence fNFor the time sequence fNCarrying out variation modal decomposition and extracting the time sequence fNCalculating the f of the modal component of different dominant frequenciesNThe variation mode matrix of (2):
A＝VMD(fN，n)
the VMD () is a variation mode decomposition function, N is a preset component number and is N rows and N columns, wherein N is 4, and N is 75000;
performing empirical wavelet transform on each modal component in the A, extracting partial wavelet reconstruction components, and calculating an empirical wavelet reconstruction matrix of the jth component in the A:
Bj＝EWT(Aj，m)，j＝1，...，n
wherein, EWT () is an empirical wavelet transform function, m is a frequency domain division number, and the size is m rows and N columns, where m is 4 and N is 75000;
calculating fNDual time-frequency joint decomposition matrix G：
G＝{Bj}j＝1，...，n＝{gi}i＝1，...，m×n
Wherein, giIs fNThe ith dual time-frequency joint decomposition vector of (1);
obtaining a dual time-frequency joint feature vector Z of the seismic signal sample:
Z＝β·medianc(G)
wherein, the median () is a matrix column vector median function, and the beta is a dual time-frequency joint component weight vector.
Preferably, the step S3 further includes:
constructing an L-layer margin correction deep neural network model;
the input layer is the dual time-frequency joint characteristic vector Z, the output layer is an excavation classification mark vector y, the L-2 middle layers are margin correction learning layers, all the neural network layers are in a full-connection form, wherein L is 7, and the middle layer transfer vector is xk：
Wherein u iskLearning vectors for features, vkIs a margin correction vector, rrnc () is a margin correction intermediate layer network model;
the excavation classification mark vector y is as follows:
y＝sortma(opnc(xL-2))＝(y1，y2，y3，y4，y5)
wherein opnc () is a margin correction output layer model, sortma () is a maximum value retrieval function, the element with the maximum absolute value in the excavation classification mark vector y is set as 1, and other elements are set as 0; definition of y1Indicating excavator excavation type, y2Indicating rammer excavation type, y3Indicating the excavation type and y of the driller4Indicating shovel excavation type and y5Indicating a non-excavation type, wherein the value of 1 represents that the corresponding construction excavation type is detected;
and training the margin correction deep neural network model by taking the data in the seismic motion signal sample database as a training set, wherein a cost function of deep learning is defined as:
c＝(y-a)2/2
wherein y is an excavation classification mark vector, a is an excavation classification mark vector in the seismic oscillation signal sample database, and c is a cost value;
and presetting a cost threshold as sigma, and when c is larger than or equal to sigma, performing parameter correction on the margin correction deep neural network model by using a back propagation gradient descent method until c is smaller than sigma, and completing the construction of the deep learning model.
Preferably, the step S4 further includes: predicting the detected seismic signals by using the deep learning model, and calculating a prediction category label value:
where θ is the confidence of classification probability, hiFor class i match probability, max () is the maximum function, argi() And the class number i, j with the maximum matching probability is taken as a prediction class label.
The classification decision is then as follows:
and according to the classification decision, alarming is carried out on the detected excavation activity construction situation.
The invention has the following beneficial effects:
the invention realizes a third-party construction excavation prevention detection alarm method by constructing an excavation signal detection depth learning model, can monitor the third-party construction excavation activities of the road surface in real time, immediately alarms once an excavation event is detected, can accurately judge the excavation type, and provides a basis for subsequent emergency treatment decision. The method can implement uniform safety protection on the underground pipeline, early warning is carried out on potential pipeline damage through excavation warning, and safe operation of the underground pipeline is effectively guaranteed.
Drawings
FIG. 1 shows a flow chart of the third-party construction excavation prevention detection alarm method.
Detailed Description
In order to make the technical solutions and advantages of the present invention more apparent, the following further detailed description of exemplary embodiments of the present invention is provided with reference to the accompanying drawings, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and are not exhaustive of all embodiments, and the embodiments and features in the embodiments in the present description may be combined with each other without conflict.
Referring to fig. 1, an embodiment of the present invention provides a detection and alarm method for preventing third-party construction excavation, including the following steps:
s1, collecting seismic signal samples of different types, and constructing a seismic signal sample database;
specifically, a plurality of excavator excavation background noise type earthquake motion signal samples, a plurality of rammer excavation background noise type earthquake motion signal samples, a plurality of driller excavation background noise type earthquake motion signal samples, an iron shovel excavation background noise type earthquake motion signal sample and a plurality of excavation-free background noise type earthquake motion signal samples are collected respectively, the collection frequency of earthquake motion signals is 7500 points per second, the sampling duration of the earthquake motion signal samples is 10 seconds, and an earthquake motion signal database is constructed according to the collected earthquake motion signal samples.
S2, performing double time-frequency joint decomposition on the acquired seismic signal sample to construct a double time-frequency joint feature vector of the seismic signal sample;
defining the seismic signal samples as a time sequence fNFor the time sequence fNCarrying out variation modal decomposition and extracting the time sequence fNCalculating the f of the modal component of different dominant frequenciesNThe variation mode matrix of (2):
A＝VMD(fN，n)
the VMD () is a variation mode decomposition function, N is a preset component number and is N rows and N columns, wherein N is 4, and N is 75000;
performing empirical wavelet transform on each modal component in the A, extracting partial wavelet reconstruction components, and calculating an empirical wavelet reconstruction matrix of the jth component in the A:
Bj＝EWT(Aj，m)，j＝1，...，n
wherein, EWT () is an empirical wavelet transform function, m is a frequency domain division number, and the size is m rows and N columns, where m is 4 and N is 75000;
calculating fNThe dual time-frequency joint decomposition matrix G:
G＝{Bj}j＝1，...，n＝{gi}i＝1，...，m×n
wherein, giIs fNThe ith dual time-frequency joint decomposition vector of (1);
obtaining a dual time-frequency joint feature vector Z of the seismic signal sample:
Z＝β·medianc(G)
wherein, the median () is a matrix column vector median function, and the beta is a dual time-frequency joint component weight vector.
S3, constructing a deep learning model for seismic signal detection through the double time-frequency joint feature vectors;
constructing an L-layer margin correction deep neural network model;
the input layer is the dual time-frequency joint characteristic vector Z, the output layer is an excavation classification mark vector y, the L-2 middle layers are margin correction learning layers, all the neural network layers are in a full-connection form, wherein L is 7, and the middle layer transfer vector is xk：
Wherein u iskLearning vectors for features, vkIs a margin correction vector, rrnc () is a margin correction intermediate layer network model;
the excavation classification mark vector y is as follows:
y＝sortma(opnc(xL-2))＝(y1，y2，y3，y4，y5)
wherein opnc () is a margin correction output layer model, sortma () is a maximum value retrieval function, the element with the maximum absolute value in the excavation classification mark vector y is set as 1, and other elements are set as 0; definition of y1Indicating excavator excavation type, y2Indicating rammer excavation type, y3Indicating the excavation type and y of the driller4Indicating shovel excavation type and y5Indicating a non-excavation type, wherein the value of 1 represents that the corresponding construction excavation type is detected;
and training the margin correction deep neural network model by taking the data in the seismic motion signal sample database as a training set, wherein a cost function of deep learning is defined as:
c＝(y-a)2/2
wherein y is an excavation classification mark vector, a is an excavation classification mark vector in the seismic oscillation signal sample database, and c is a cost value;
and presetting a cost threshold as sigma, and when c is larger than or equal to sigma, performing parameter correction on the margin correction deep neural network model by using a back propagation gradient descent method until c is smaller than sigma, and completing the construction of the deep learning model.
S4, utilizing the deep learning model to predict and classify the detected earthquake motion signals and give an alarm for the construction situation with excavation activities;
predicting the detected seismic signals by using the deep learning model, and calculating a prediction category label value:
where θ is the confidence of classification probability, hiFor class i match probability, max () is the maximum function, argi() And the class number i, j with the maximum matching probability is taken as a prediction class label.
The classification decision is then as follows:
and according to the classification decision, alarming is carried out on the detected excavation activity construction situation.
It should be understood that the above-mentioned embodiments of the present invention are only examples for clearly illustrating the present invention, and are not intended to limit the embodiments of the present invention, and it will be obvious to those skilled in the art that other variations or modifications may be made on the basis of the above description, and all embodiments may not be exhaustive, and all obvious variations or modifications may be included within the scope of the present invention.
Claims (6)
1. The detection and alarm method for preventing third-party construction excavation is characterized by comprising the following steps of:
s1, collecting seismic signal samples of different types, and constructing a seismic signal sample database;
s2, performing double time-frequency joint decomposition on the acquired seismic signal sample to construct a double time-frequency joint feature vector of the seismic signal sample;
s3, constructing a deep learning model for seismic signal detection through the double time-frequency joint feature vectors;
and S4, utilizing the deep learning model to predict and classify the detected seismic signals and give an alarm for the construction situation with excavation activities.
2. The alarm method according to claim 1, wherein the step S1 further comprises: the method comprises the steps of respectively collecting a plurality of excavator excavation background noise type earthquake motion signal samples, a plurality of rammers excavation background noise type earthquake motion signal samples, a plurality of drilling machine excavation background noise type earthquake motion signal samples, a shovel excavation background noise type earthquake motion signal sample and a plurality of excavation-free background noise type earthquake motion signal samples, and constructing an earthquake motion signal database according to the collected various earthquake motion signal samples.
3. The warning method according to claim 2, wherein the acquisition frequency of the seismic signals is 7500 points per second, and the sampling time of the seismic signals is 10 seconds.
4. The alarm method according to claim 1, wherein the step S2 further comprises: defining the seismic signal samples as a time sequence fNFor the time sequence fNCarrying out variation modal decomposition and extracting the time sequence fNCalculating the f of the modal component of different dominant frequenciesNThe variation mode matrix of (2):
A＝VMD(fN，n)
the VMD () is a variation mode decomposition function, N is a preset component number and is N rows and N columns, wherein N is 4, and N is 75000;
performing empirical wavelet transform on each modal component in the A, extracting partial wavelet reconstruction components, and calculating an empirical wavelet reconstruction matrix of the jth component in the A:
Bj＝EWT(Aj，m)，j＝1，…，n
wherein, EWT () is an empirical wavelet transform function, m is a frequency domain division number, and the size is m rows and N columns, where m is 4 and N is 75000;
calculating fNThe dual time-frequency joint decomposition matrix G:
G＝{Bj}j＝1，…，n＝{gi}i＝1，...，m×n
wherein, giIs fNThe ith dual time-frequency joint decomposition vector of (1);
obtaining a dual time-frequency joint feature vector Z of the seismic signal sample:
Z＝β·medianc(G)
wherein, the median () is a matrix column vector median function, and the beta is a dual time-frequency joint component weight vector.
5. The alarm method according to claim 4, wherein the step S3 further comprises:
constructing an L-layer margin correction deep neural network model;
the input layer is the dual time-frequency joint characteristic vector Z, the output layer is an excavation classification mark vector y, the L-2 middle layers are margin correction learning layers, all the neural network layers are in a full-connection form, wherein L is 7, and the middle layer transfer vector is xk：
Wherein u iskLearning vectors for features, vkIs a margin correction vector, rrnc () is a margin correction intermediate layer network model;
the excavation classification mark vector y is as follows:
y＝sortma(opnc(xL-2))＝(y1，y2，y3，y4，y5)
wherein opnc () is a margin correction output layer model, sortma () is a maximum value retrieval function, the element with the maximum absolute value in the excavation classification mark vector y is set as 1, and other elements are set as 0; definition of y1Indicating excavator excavation type, y2Indicating rammer excavation type, y3Indicating the excavation type and y of the driller4Indicating shovel excavation type and y5Indicating a non-excavation type, wherein the value of 1 represents that the corresponding construction excavation type is detected;
and training the margin correction deep neural network model by taking the data in the seismic motion signal sample database as a training set, wherein a cost function of deep learning is defined as:
c＝(y-a)2/2
wherein y is an excavation classification mark vector, a is an excavation classification mark vector in the seismic oscillation signal sample database, and c is a cost value;
and presetting a cost threshold as sigma, and when c is larger than or equal to sigma, performing parameter correction on the margin correction deep neural network model by using a back propagation gradient descent method until c is smaller than sigma, and completing the construction of the deep learning model.
6. The alarm method according to claim 5, wherein the step S4 further comprises: predicting the detected seismic signals by using the deep learning model, and calculating a prediction category label value:
where θ is the confidence of classification probability, hiFor class i match probability, max () is the maximum function, argi() And the class number i, j with the maximum matching probability is taken as a prediction class label.
The classification decision is then as follows:
and according to the classification decision, alarming is carried out on the detected excavation activity construction situation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910899361.7A CN110632643B (en) | 2019-09-23 | 2019-09-23 | Detection alarm method for preventing third-party construction excavation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910899361.7A CN110632643B (en) | 2019-09-23 | 2019-09-23 | Detection alarm method for preventing third-party construction excavation |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110632643A true CN110632643A (en) | 2019-12-31 |
| CN110632643B CN110632643B (en) | 2021-03-16 |
Family
ID=68972324
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910899361.7A Active CN110632643B (en) | 2019-09-23 | 2019-09-23 | Detection alarm method for preventing third-party construction excavation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110632643B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113063489A (en) * | 2021-02-24 | 2021-07-02 | 戴天智能科技（上海）有限公司 | Vibration detection system with AI self-learning algorithm |
| CN114913477A (en) * | 2022-05-06 | 2022-08-16 | 广州市城市规划勘测设计研究院 | Urban pipeline excavation prevention early warning method, device, equipment and medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103091096A (en) * | 2013-01-23 | 2013-05-08 | 北京信息科技大学 | Extraction method for early failure sensitive characteristics based on ensemble empirical mode decomposition (EEMD) and wavelet packet transform |
| US20160124100A1 (en) * | 2014-10-29 | 2016-05-05 | Wisconsin Alumni Research Foundation | Systems and Methods for Non-Parametric Autopicking of Seismic Wave Features from Seismic Data |
| CN106052837A (en) * | 2016-05-25 | 2016-10-26 | 西南交通大学 | Train vibration noise identifying method used in high-speed railway earthquake warning |
| CN106646587A (en) * | 2016-12-29 | 2017-05-10 | 北京知觉科技有限公司 | Target detecting and identifying method and target detecting and identifying system based on sound vibration signal |
| CN110133714A (en) * | 2019-06-05 | 2019-08-16 | 山东科技大学 | A kind of microseismic signals classification discrimination method based on deep learning |
| CN110186682A (en) * | 2019-07-08 | 2019-08-30 | 石家庄铁道大学 | Fault Diagnosis of Roller Bearings based on fractional order variation mode decomposition |
-
2019
- 2019-09-23 CN CN201910899361.7A patent/CN110632643B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103091096A (en) * | 2013-01-23 | 2013-05-08 | 北京信息科技大学 | Extraction method for early failure sensitive characteristics based on ensemble empirical mode decomposition (EEMD) and wavelet packet transform |
| US20160124100A1 (en) * | 2014-10-29 | 2016-05-05 | Wisconsin Alumni Research Foundation | Systems and Methods for Non-Parametric Autopicking of Seismic Wave Features from Seismic Data |
| CN106052837A (en) * | 2016-05-25 | 2016-10-26 | 西南交通大学 | Train vibration noise identifying method used in high-speed railway earthquake warning |
| CN106646587A (en) * | 2016-12-29 | 2017-05-10 | 北京知觉科技有限公司 | Target detecting and identifying method and target detecting and identifying system based on sound vibration signal |
| CN110133714A (en) * | 2019-06-05 | 2019-08-16 | 山东科技大学 | A kind of microseismic signals classification discrimination method based on deep learning |
| CN110186682A (en) * | 2019-07-08 | 2019-08-30 | 石家庄铁道大学 | Fault Diagnosis of Roller Bearings based on fractional order variation mode decomposition |
Non-Patent Citations (1)
| Title |
|---|
| 李余: "基于DSP的单传感器地面运动目标震动波检测及识别预警", 《中国优秀硕士学位论文全文数据量·信息科学辑》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113063489A (en) * | 2021-02-24 | 2021-07-02 | 戴天智能科技（上海）有限公司 | Vibration detection system with AI self-learning algorithm |
| CN113063489B (en) * | 2021-02-24 | 2023-01-13 | 戴天智能科技（上海）有限公司 | Vibration detection system with AI self-learning algorithm |
| CN114913477A (en) * | 2022-05-06 | 2022-08-16 | 广州市城市规划勘测设计研究院 | Urban pipeline excavation prevention early warning method, device, equipment and medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110632643B (en) | 2021-03-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11562224B2 (en) | 1D-CNN-based distributed optical fiber sensing signal feature learning and classification method | |
| CN106021875B (en) | Multi-scale debris flow risk assessment method for seismic disturbance zone | |
| Xue et al. | A two-step comprehensive evaluation model for rockburst prediction based on multiple empirical criteria | |
| CN103758160B (en) | Super deep underground diaphragm wall deformation automatic real-time monitoring device and operating method thereof | |
| CN102610055B (en) | Wireless intelligent alarming system for automatically monitoring multivariate information of tunnel | |
| CN110632643B (en) | Detection alarm method for preventing third-party construction excavation | |
| Chang et al. | Artificial neural networks for estimating regional arsenic concentrations in a blackfoot disease area in Taiwan | |
| CN108256172B (en) | Dangerous case early warning and forecasting method in process of pipe jacking and downward passing existing box culvert | |
| DE112008003302T5 (en) | Methods and systems for estimating borehole events | |
| Zhou et al. | Unsupervised spectral clustering for shield tunneling machine monitoring data with complex network theory | |
| CN106437853B (en) | A kind of coal petrography bump dynamic disaster method for early warning | |
| CN115638833B (en) | Monitoring data processing method and system | |
| CN109447152A (en) | A kind of failure prediction method based on Monte Carlo tree search and neural network | |
| CN106640194B (en) | A kind of compound coal rock gas dynamic disaster method for early warning | |
| CN104159087A (en) | Field monitoring platform for drilling machine | |
| Wu et al. | A dynamic decision approach for risk analysis in complex projects | |
| CN112576312A (en) | Data collection and processing method for electric-hydraulic control support of intelligent fully-mechanized coal mining face | |
| Liu et al. | Slope displacement prediction using sequential intelligent computing algorithms | |
| CN115929406A (en) | Neural network-based surrounding rock stability prediction method, system and storage medium | |
| Qiu et al. | TBM tunnel surrounding rock classification method and real-time identification model based on tunneling performance | |
| Tao et al. | A structural monitoring data processing model based on signal musicalization | |
| Turarbek et al. | 2-d deep convolutional neural network for predicting the intensity of seismic events | |
| CN115423263A (en) | Side slope risk early warning and sliding volume prediction method based on Prophet-LSTM | |
| CN113869240A (en) | Transmission optical cable real-time warning method and device based on deep learning algorithm | |
| CN113095588A (en) | Method for predicting influence of rainfall on underground pipe gallery |
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 | ||
| GR01 | Patent grant |