CN113945253A - Water level measuring method for rail transit rail area - Google Patents
Water level measuring method for rail transit rail area Download PDFInfo
- Publication number
- CN113945253A CN113945253A CN202111212759.2A CN202111212759A CN113945253A CN 113945253 A CN113945253 A CN 113945253A CN 202111212759 A CN202111212759 A CN 202111212759A CN 113945253 A CN113945253 A CN 113945253A
- Authority
- CN
- China
- Prior art keywords
- water level
- data
- layer
- rail
- sensor
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01F—MEASURING VOLUME, VOLUME FLOW, MASS FLOW OR LIQUID LEVEL; METERING BY VOLUME
- G01F23/00—Indicating or measuring liquid level or level of fluent solid material, e.g. indicating in terms of volume or indicating by means of an alarm
- G01F23/14—Indicating or measuring liquid level or level of fluent solid material, e.g. indicating in terms of volume or indicating by means of an alarm by measurement of pressure
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01F—MEASURING VOLUME, VOLUME FLOW, MASS FLOW OR LIQUID LEVEL; METERING BY VOLUME
- G01F23/00—Indicating or measuring liquid level or level of fluent solid material, e.g. indicating in terms of volume or indicating by means of an alarm
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/30—Assessment of water resources
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Fluid Mechanics (AREA)
- Pure & Applied Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computing Systems (AREA)
- Algebra (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Measurement Of Levels Of Liquids Or Fluent Solid Materials (AREA)
Abstract
The invention discloses a water level measuring method of a rail transit rail area, which comprises the following steps: s1: acquiring first water level data in a preset time period of a rail area by using first water level acquisition equipment; s2: acquiring second water level data in a preset time period of the rail area by using second water level acquisition equipment; s3: according to the first water level data and the second water level data, utilizing an information fusion network to obtain final water level data of the rail area; s4: and according to the final water level data of the rail area, obtaining a water level change curve in a preset time period, and completing water level measurement.
Description
Technical Field
The invention relates to the technical field of traffic water level measurement, in particular to a water level measurement method for a rail traffic track area.
Background
In recent years, the rainfall is obviously increased compared with the past year, so that the accumulated water of part of subways is excessive due to construction planning. Because the accumulated water of the subway can cause the shutdown of the subway line, and even endanger the personal safety and the loss of train equipment in serious cases, the method is particularly important for measuring the accumulated water of the subway.
Disclosure of Invention
The invention aims to provide a water level measuring method for a rail transit rail area, which aims to solve the problem that accumulated water in the subway cannot be accurately measured.
The technical scheme for solving the technical problems is as follows:
the invention provides a water level measuring method of a rail transit rail area, which comprises the following steps:
s1: acquiring first water level data in a preset time period of a rail area by using first water level acquisition equipment;
s2: acquiring second water level data in a preset time period of the rail area by using second water level acquisition equipment;
s3: according to the first water level data and the second water level data, utilizing an information fusion network to obtain final water level data of the rail area;
s4: and according to the final water level data of the rail area, obtaining a water level change curve in a preset time period, and completing water level measurement.
Optionally, one of the first water level collection apparatus and the second water level collection apparatus is configured as a pressure type liquid level sensor, and the other is configured as a camera.
Optionally, the pressure type liquid level sensor and the cameras are both multiple, and the multiple pressure type liquid level sensors and the multiple cameras are uniformly distributed on two sides of the rail area.
Optionally, in step S3, the information fusion network includes a first data input layer, a linear transformation layer, a comparison layer, a second data input layer, a classification layer and an output layer, the first data input layer is connected to an input of the linear transformation layer, the linear transformation layer includes a first output end and a second output end, the first output end is connected to a first input end of the comparison layer, the second data input layer is connected to a second input end of the comparison layer, an output end of the comparison layer is connected to an input end of the classification layer, and an output end of the classification layer and a second output end of the linear transformation layer are simultaneously connected to the output layer.
Alternatively, the step S3 includes:
s31: acquiring time sequence data of the first water level data within a preset time period;
s32: performing linear transformation operation on the time series data of the first water level data to obtain information to be matched and information to be extracted;
s33: acquiring time sequence data of second water level data in the preset time period;
s34: performing data comparison operation on the information to be matched and the time series data of the second water level data to obtain a data comparison result;
s35: classifying and normalizing the data comparison result to obtain a classification and normalization result;
s36: and obtaining final water level data of the track area according to the classification and normalization result and the information to be extracted.
Alternatively, in step S32, the linear transformation operation is:
ki=Wkxi
vi=Wvxi
wherein x isiIs a d-dimensional vector, WkAnd WvIs a d x d transformation matrix, kiIs information to be matched, viIs the information to be extracted.
Optionally, in step S34, the data comparing operation is:
wherein, a1,iRepresents a similarity value of the 1 st sensor data and the ith sensor data,represents the jth component of the first sensor data,representing the jth component of the ith sensor data, i representing the first sensor, j representing the jth component, d representing the dataDimension.
Optionally, the normalizing operation is:
wherein, c1,iRepresenting a similarity value representing the 1 st sensor data and the ith sensor data after normalization, a1,iRepresenting the similarity value of the 1 st sensor data and the ith sensor data, a1,jAnd representing the similarity value of the 1 st component and the jth component, i represents the first sensor, j represents the jth component, and n represents the number of sensors.
Optionally, in step S4, the final water level data in the track area is fitted by using a decision tree and/or linear ridge regression, so as to obtain a water level variation curve within a preset time period.
The invention has the following beneficial effects:
according to the invention, by fusing the first water level data acquired by the first water level acquisition equipment and the second water level data acquired by the second water level acquisition equipment, the more accurate water level of the rail transit track area can be obtained, so that the water accumulation in the rail transit can be conveniently checked, the maintenance personnel can conveniently clean the water in time, the occurrence of subway operation accidents is further avoided, and the subway can smoothly run.
Drawings
Fig. 1 is a flowchart of a method for measuring a water level in a rail transit area according to an embodiment of the present invention;
fig. 2 is a schematic diagram illustrating a setting manner of a water level collecting device in the water level measuring method for the rail transit rail area according to the embodiment of the present invention;
FIG. 3 is a flowchart illustrating the substeps of step S3 in FIG. 1;
fig. 4 is a schematic structural diagram of an information fusion network provided by the present invention.
Detailed Description
The principles and features of this invention are described below in conjunction with the following drawings, which are set forth by way of illustration only and are not intended to limit the scope of the invention.
Examples
The technical scheme for solving the technical problems is as follows:
the invention provides a water level measuring method of a rail transit rail area, which is shown in a figure 1 and comprises the following steps:
s1: acquiring first water level data in a preset time period of a rail area by using first water level acquisition equipment;
s2: acquiring second water level data in a preset time period of the rail area by using second water level acquisition equipment;
here, the first water level collection apparatus may be a pressure type liquid level sensor or a camera. Because the pressure type liquid level sensor adopts the diffused silicon piezoresistive pressure sensor with the stainless steel isolating membrane as a signal measuring element, the pressure type liquid level sensor can accurately measure the hydrostatic pressure which is in direct proportion to the liquid level depth, and establishes the linear corresponding relation between the output signal and the liquid depth, thereby realizing the accurate measurement of the liquid depth; the camera projects the optical signal obtained by the optical component onto the image sensor, completes the conversion from the optical signal to the electric signal, and then converts the electric signal to the digital signal. Therefore, in the invention, one of the pressure type liquid level sensor and the camera is used as a first water level acquisition device, and the other is used as a second water level acquisition device, so that the data acquired by the pressure type liquid level sensor and the camera can be fused at the later stage, and more accurate water level measurement data can be obtained.
A person skilled in the art can set the first water level acquisition device as a pressure type liquid level sensor, and then the second water level acquisition device is a camera; if the second water level collecting device is a pressure type liquid level sensor, the first water level collecting device can be set as a camera, and the invention is not limited in particular.
In addition, referring to fig. 2, a specific setting mode of the first water level collecting device and the second water level collecting device according to the present invention is shown, and since the collected water level is collected in the rail area, a single set of water level collecting device is inevitably provided, and the measurement is not accurate enough, therefore, the present invention provides a plurality of water level collecting devices, wherein the plurality of water level collecting devices include a plurality of pressure type liquid level sensors and a plurality of cameras, and the plurality of pressure type liquid level sensors and the plurality of cameras are uniformly distributed on both sides of the rail area.
Specifically, a graduated scale is arranged above the pressure type liquid level sensor, and the reading on the graduated scale needs to be calibrated with the output of the liquid level sensor so as to ensure that the upper water level position output by the sensor is consistent with the reading of the graduated scale. On the other hand, the graduated scale can be shot by the visual field of the camera, and the position of the water level and the reading on the graduated scale can be identified through an image identification algorithm (the image identification algorithm can be any one identification algorithm, and the invention is not limited). Given a set of time series data generated by multiple sensors, the goal of fusing them is to find the most similar data from between the sequences, thus reducing outlier interference when fitting subsequent data, and thus calculating the similarity between the sequences is a key step in the fusion.
S3: according to the first water level data and the second water level data, utilizing an information fusion network to obtain final water level data of the rail area;
optionally, in step S3, the information fusion network includes a first data input layer, a linear transformation layer, a comparison layer, a second data input layer, a classification layer and an output layer, the first data input layer is connected to an input of the linear transformation layer, the linear transformation layer includes a first output end and a second output end, the first output end is connected to a first input end of the comparison layer, the second data input layer is connected to a second input end of the comparison layer, an output end of the comparison layer is connected to an input end of the classification layer, and an output end of the classification layer and a second output end of the linear transformation layer are simultaneously connected to the output layer.
Alternatively, referring to fig. 3, the step S3 includes:
s31: acquiring time sequence data of the first water level data within a preset time period;
if the first water level acquisition equipment is a pressure type liquid level sensor, the first water level data is acquired through the pressure type liquid level sensor, and similarly, if the first water level acquisition equipment is a camera, the first water level data is acquired through the camera. In the specific embodiment provided by the invention, the first water level acquisition equipment is a pressure type liquid level sensor, so that the time sequence data of the first water level data is a plurality of time sequences generated by a plurality of sensors in a preset time period, and the second water level data is a plurality of time sequences generated by a plurality of cameras in the preset time period.
S32: performing linear transformation operation on the time series data of the first water level data to obtain information to be matched and information to be extracted;
alternatively, in step S32, the linear transformation operation is:
ki=Wkxi
vi=Wvxi
wherein x isiIs a d-dimensional vector, WkAnd WvIs a d x d transformation matrix, kiIs information to be matched, viIs the information to be extracted.
S33: acquiring time sequence data of second water level data in the preset time period;
s34: performing data comparison operation on the information to be matched and the time series data of the second water level data to obtain a data comparison result;
wherein, a1,iRepresents a similarity value of the 1 st sensor data and the ith sensor data,represents the jth component of the first sensor data,indicates the ith sensorThe jth component of the data, i denotes the first sensor, j denotes the jth component, and d denotes the dimension of the data.
S35: classifying and normalizing the data comparison result to obtain a classification and normalization result; optionally, the normalizing operation is:
wherein, c1,iRepresenting a similarity value representing the 1 st sensor data and the ith sensor data after normalization, a1,iRepresenting the similarity value of the 1 st sensor data and the ith sensor data, a1,jAnd representing the similarity value of the 1 st component and the jth component, i represents the first sensor, j represents the jth component, and n represents the number of sensors.
S36: and obtaining final water level data of the track area according to the classification and normalization result and the information to be extracted.
Suppose there are n pairs of cameras and hydraulic sensors, where one pair generates a time series of (x)i,yi) I ∈ (0, n), then the sequence xiFusion was performed by a transformer information fusion network as shown in fig. 4 and other sequences. The N sequences are converted linearly to obtain N pairs (k)i,vi) I ∈ (0, n), where kiIs the vector to be matched, viAre vectors of information to be extracted, their length being the same as x and y.
The information fusion process is calculated as shown in fig. 4. A sequence vector y1And each kiRespectively calculating vector dot products to obtain the acquaintance value a between every two1,iAnd is andthese values are normalized by the classification layer (i.e. soft-max layer in the figure), i.e.These values range from [0,1 ]]And their sumIs 1. Finally, a sequence vector b is obtained1=∑ic1,iviIt is based on y1And xiWeighted summation of similarity, which represents y1And xiThe most similar features in between, and some dissimilar parts are excluded.
Other y can be calculated by the same principleiAnd xiThe fused vector of, and xiAnd yiThe total number of the fusion vectors b is 2n, and finally, the vectors are fitted by using a decision tree or linear ridge regression, so that a water level change curve in a certain time period is obtained.
S4: and according to the final water level data of the rail area, obtaining a water level change curve in a preset time period, and completing water level measurement.
Optionally, in step S4, the final water level data in the track area is fitted by using a decision tree and/or linear ridge regression, so as to obtain a water level variation curve within a preset time period.
The invention has the following beneficial effects:
according to the invention, by fusing the first water level data acquired by the first water level acquisition equipment and the second water level data acquired by the second water level acquisition equipment, the more accurate water level of the rail transit track area can be obtained, so that the water accumulation in the rail transit can be conveniently checked, the maintenance personnel can conveniently clean the water in time, the occurrence of subway operation accidents is further avoided, and the subway can smoothly run.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (9)
1. A water level measuring method of a rail transit rail area is characterized by comprising the following steps:
s1: acquiring first water level data in a preset time period of a rail area by using first water level acquisition equipment;
s2: acquiring second water level data in a preset time period of the rail area by using second water level acquisition equipment;
s3: according to the first water level data and the second water level data, utilizing an information fusion network to obtain final water level data of the rail area;
s4: and according to the final water level data of the rail area, obtaining a water level change curve in a preset time period, and completing water level measurement.
2. The method for measuring a water level of a rail transit section according to claim 1, wherein one of the first and second water level collection apparatuses is configured as a pressure type liquid level sensor, and the other is configured as a camera.
3. The method as claimed in claim 2, wherein the pressure type liquid level sensor and the plurality of cameras are provided in plurality, and the plurality of pressure type liquid level sensors and the plurality of cameras are uniformly disposed at both sides of the rail area.
4. The method for measuring water level in a rail transit section according to claim 1, wherein in step S3, the information fusion network comprises a first data input layer, a linear transformation layer, a comparison layer, a second data input layer, a classification layer and an output layer, wherein the first data input layer is connected to an input of the linear transformation layer, the linear transformation layer comprises a first output end and a second output end, the first output end is connected to a first input end of the comparison layer, the second data input layer is connected to a second input end of the comparison layer, an output end of the comparison layer is connected to an input end of the classification layer, and an output end of the classification layer and a second output end of the linear transformation layer are simultaneously connected to the output layer.
5. The method for measuring a water level of a rail transit section according to claim 1 or 4, wherein the step S3 includes:
s31: acquiring time sequence data of the first water level data within a preset time period;
s32: performing linear transformation operation on the time series data of the first water level data to obtain information to be matched and information to be extracted;
s33: acquiring time sequence data of second water level data in the preset time period;
s34: performing data comparison operation on the information to be matched and the time series data of the second water level data to obtain a data comparison result;
s35: classifying and normalizing the data comparison result to obtain a classification and normalization result;
s36: and obtaining final water level data of the track area according to the classification and normalization result and the information to be extracted.
6. The method for measuring water level of a rail transit section according to claim 5, wherein in the step S32, the linear transformation operation is:
ki=Wkxi
vi=Wvxi
wherein x isiIs a d-dimensional vector, WkAnd WvIs a d x d transformation matrix, kiIs information to be matched, viIs the information to be extracted.
7. The method for measuring water level in a rail transit section according to claim 5, wherein the data comparison operation in step S34 is:
wherein, a1,iRepresents a similarity value of the 1 st sensor data and the ith sensor data,represents the jth component of the first sensor data,represents the jth component of the ith sensor data, i represents the first sensor, j represents the jth component, and d represents the dimension of the data.
8. The method of measuring water level of a rail transit rail zone of claim 5, wherein the normalizing operation is:
wherein, c1,iRepresenting a similarity value representing the 1 st sensor data and the ith sensor data after normalization, a1,iRepresenting the similarity value of the 1 st sensor data and the ith sensor data, a1,jAnd representing the similarity value of the 1 st component and the jth component, i represents the first sensor, j represents the jth component, and n represents the number of sensors.
9. The method for measuring the water level in the rail transit section as claimed in claim 1, wherein in step S4, the final water level data in the rail transit section is fitted by using a decision tree and/or linear ridge regression to obtain a water level variation curve within a predetermined time period.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111212759.2A CN113945253B (en) | 2021-10-18 | 2021-10-18 | Water level measuring method for rail traffic track area |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111212759.2A CN113945253B (en) | 2021-10-18 | 2021-10-18 | Water level measuring method for rail traffic track area |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113945253A true CN113945253A (en) | 2022-01-18 |
CN113945253B CN113945253B (en) | 2023-07-07 |
Family
ID=79331317
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111212759.2A Active CN113945253B (en) | 2021-10-18 | 2021-10-18 | Water level measuring method for rail traffic track area |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113945253B (en) |
Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH075894A (en) * | 1993-06-17 | 1995-01-10 | Nippondenso Co Ltd | Device for normalizing pattern length |
CN101236599A (en) * | 2007-12-29 | 2008-08-06 | 浙江工业大学 | Human face recognition detection device based on multi- video camera information integration |
CN102013095A (en) * | 2010-12-09 | 2011-04-13 | 哈尔滨工业大学 | Distribution transform-based multi-sensor image fusion method |
CN103557884A (en) * | 2013-09-27 | 2014-02-05 | 杭州银江智慧城市技术集团有限公司 | Multi-sensor data fusion early warning method for monitoring electric transmission line tower |
CN105023191A (en) * | 2015-07-24 | 2015-11-04 | 金川集团股份有限公司 | Online recursive calculation method for fume occurrence rate of metallurgical furnace |
CN105426889A (en) * | 2015-11-13 | 2016-03-23 | 浙江大学 | PCA mixed feature fusion based gas-liquid two-phase flow type identification method |
CN106453033A (en) * | 2016-08-31 | 2017-02-22 | 电子科技大学 | Multilevel Email classification method based on Email content |
CN108287007A (en) * | 2017-01-09 | 2018-07-17 | 山东省水利勘测设计院 | A kind of intelligent water-level instrumentation based on Data fusion technique |
CN109063729A (en) * | 2018-06-20 | 2018-12-21 | 上海电力学院 | A kind of Multisensor Image Fusion Scheme based on PSO-NSCT |
CN109858015A (en) * | 2018-12-12 | 2019-06-07 | 湖北工业大学 | A kind of semantic similarity calculation method and device based on CTW and KM algorithm |
CN109948165A (en) * | 2019-04-24 | 2019-06-28 | 吉林大学 | Fine granularity feeling polarities prediction technique based on mixing attention network |
CN113091827A (en) * | 2021-04-29 | 2021-07-09 | 中铁第四勘察设计院集团有限公司 | Intelligent flood automatic monitoring system for urban rail transit underground complex |
-
2021
- 2021-10-18 CN CN202111212759.2A patent/CN113945253B/en active Active
Patent Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH075894A (en) * | 1993-06-17 | 1995-01-10 | Nippondenso Co Ltd | Device for normalizing pattern length |
CN101236599A (en) * | 2007-12-29 | 2008-08-06 | 浙江工业大学 | Human face recognition detection device based on multi- video camera information integration |
CN102013095A (en) * | 2010-12-09 | 2011-04-13 | 哈尔滨工业大学 | Distribution transform-based multi-sensor image fusion method |
CN103557884A (en) * | 2013-09-27 | 2014-02-05 | 杭州银江智慧城市技术集团有限公司 | Multi-sensor data fusion early warning method for monitoring electric transmission line tower |
CN105023191A (en) * | 2015-07-24 | 2015-11-04 | 金川集团股份有限公司 | Online recursive calculation method for fume occurrence rate of metallurgical furnace |
CN105426889A (en) * | 2015-11-13 | 2016-03-23 | 浙江大学 | PCA mixed feature fusion based gas-liquid two-phase flow type identification method |
CN106453033A (en) * | 2016-08-31 | 2017-02-22 | 电子科技大学 | Multilevel Email classification method based on Email content |
CN108287007A (en) * | 2017-01-09 | 2018-07-17 | 山东省水利勘测设计院 | A kind of intelligent water-level instrumentation based on Data fusion technique |
CN109063729A (en) * | 2018-06-20 | 2018-12-21 | 上海电力学院 | A kind of Multisensor Image Fusion Scheme based on PSO-NSCT |
CN109858015A (en) * | 2018-12-12 | 2019-06-07 | 湖北工业大学 | A kind of semantic similarity calculation method and device based on CTW and KM algorithm |
CN109948165A (en) * | 2019-04-24 | 2019-06-28 | 吉林大学 | Fine granularity feeling polarities prediction technique based on mixing attention network |
CN113091827A (en) * | 2021-04-29 | 2021-07-09 | 中铁第四勘察设计院集团有限公司 | Intelligent flood automatic monitoring system for urban rail transit underground complex |
Non-Patent Citations (1)
Title |
---|
张冬至;夏伯锴;曾蕾蕾;: "基于遗传神经网络的多传感器信息融合及应用", 传感器与微***, no. 04, pages 40 - 45 * |
Also Published As
Publication number | Publication date |
---|---|
CN113945253B (en) | 2023-07-07 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107036581B (en) | bridge deformation online monitoring system and method based on MEMS gyroscope | |
CN112232685B (en) | Engineering quality supervision acceptance real-time detection analysis management system based on big data | |
CN113065578A (en) | Image visual semantic segmentation method based on double-path region attention coding and decoding | |
CN105335726A (en) | Face recognition confidence coefficient acquisition method and system | |
Yang et al. | Rapid detection of building cracks based on image processing technology with double square artificial marks | |
CN112132157B (en) | Gait face fusion recognition method based on raspberry pie | |
CN114970743B (en) | Multi-source remote sensing rainfall data fusion method based on multi-modal deep learning | |
CN112883802A (en) | Method for identifying destructive event of pipeline optical fiber vibration safety early warning system | |
CN103745238A (en) | Pantograph identification method based on AdaBoost and active shape model | |
CN111403031A (en) | Physique test data acquisition and detection system and method | |
CN110514366B (en) | Method for detecting weak leakage of pipeline under small sample condition | |
CN113945253B (en) | Water level measuring method for rail traffic track area | |
Lydon et al. | Development and testing of a composite system for bridge health monitoring utilising computer vision and deep learning | |
CN117553840A (en) | Instrument based on intelligent management and system thereof | |
CN110672058B (en) | On-line calibration data sequence matching method and device of sensor for structure monitoring | |
CN115941807B (en) | Efficient data compression method for park security system | |
CN106708786A (en) | Method and system for calculating problem severity of iron tower based on sensor detection | |
CN110570022A (en) | mGBDT-based building energy consumption prediction method and system | |
CN113610167B (en) | Equipment risk detection method based on metric learning and visual perception | |
CN111696103B (en) | Constant-load linear mapping method of single-span simple girder bridge under uninterrupted traffic condition | |
CN113128158A (en) | Coupling coefficient identification method of wireless power transmission system | |
CN112097915B (en) | Face recognition temperature measurement method and device | |
CN101629407A (en) | Pavement structural strength forecasting method | |
CN113973403A (en) | Temperature-induced strain field redistribution intelligent sensing method based on structure discrete measuring point topology | |
CN107796323A (en) | A kind of micro- change detecting system of bridge based on hot spot vision signal intellectual analysis |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |