CN111738996B - Bridge health monitoring and early warning system based on machine learning - Google Patents
Bridge health monitoring and early warning system based on machine learning Download PDFInfo
- Publication number
- CN111738996B CN111738996B CN202010526405.4A CN202010526405A CN111738996B CN 111738996 B CN111738996 B CN 111738996B CN 202010526405 A CN202010526405 A CN 202010526405A CN 111738996 B CN111738996 B CN 111738996B
- Authority
- CN
- China
- Prior art keywords
- bridge
- local
- data
- structure data
- neural network
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Alarm Systems (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
Abstract
The invention discloses a bridge health monitoring and early warning system based on machine learning, which comprises: the data acquisition module comprises various sensors for detecting the bridge, a camera for shooting the local fixed point of the bridge and a data sending unit; the data storage module is used for storing the bridge structure data and the bridge local photos sent by the data acquisition module according to time points; the data processing module is used for converting deformation quantities of the same local position of the bridge on the local photos of the bridge at adjacent time points into actual local deformation quantities of the bridge, and the data processing module is also used for constructing a neural network model; and the monitoring and early warning module is used for inputting the bridge structure data acquired at the latest time point into the neural network model to obtain the predicted actual bridge local deformation, and then comparing the predicted actual bridge local deformation with the bridge local deformation design threshold. The invention can mutually verify the data collected by multiple parties, and improves the accuracy of bridge health monitoring and early warning.
Description
Technical Field
The invention relates to the technical field of bridges. More specifically, the invention relates to a bridge health monitoring and early warning system based on machine learning.
Background
Large-scale foundation buildings such as bridges and the like are the material guarantee for the rapid development of national economy in China, and once natural disasters or structural aging occur, disastrous consequences are brought to the nation and people. Therefore, in recent years, the work of monitoring and warning the bridge health has been started by a plurality of units, and the process of monitoring the bridge health includes: the method comprises the steps of obtaining dynamic and static response measured values of a bridge at regular time through a series of sensors, extracting damage-sensitive characteristic factors from the measured values, and carrying out statistical analysis on the characteristic factors so as to obtain the current health condition of the structure. For long-term health monitoring, the system receives real-time information about expected functional changes caused by aging and degradation of the structure in its operating environment. However, the current sensing system is exposed in the field and can be affected by factors such as high temperature, high humidity and strong interference, the working environment is very bad, which causes that the acquired data contains a large amount of interference information, and meanwhile, the aging of the sensing system per se can also reduce the reliability of the data provided by the sensing system, so that the data acquired by multiple parties need to be mutually verified to improve the accuracy of bridge health monitoring and early warning.
Disclosure of Invention
An object of the present invention is to solve at least the above problems and to provide at least the advantages described later.
The invention also aims to provide a bridge health monitoring and early warning system based on machine learning, which can verify data acquired by multiple parties mutually and improve the accuracy of bridge health monitoring and early warning.
To achieve these objects and other advantages in accordance with the purpose of the invention, there is provided a bridge health monitoring and warning system based on machine learning, comprising:
the data acquisition module comprises a plurality of sensors for detecting the bridge, a camera for shooting the local fixed point of the bridge and a data sending unit, wherein the sensors are used for acquiring the structural data of the bridge at a first preset time interval, the camera is used for shooting the local picture of the bridge at a second preset time interval, and the data sending unit is used for sending the structural data of the bridge and the local picture of the bridge acquired by the sensors in a wireless network connection mode;
the data storage module is used for storing the bridge structure data and the bridge local photos sent by the data acquisition module according to time points, storing a first preset number of bridge structure data and a second preset number of bridge local photos, and deleting the bridge structure data and the bridge local photos at the oldest time points when the data storage module receives the bridge structure data and the bridge local photos at the newest time points after the bridge structure data stored in the data storage module reaches the first preset number and the number of the bridge local photos reaches the second preset number;
the data processing module is used for converting deformation quantities of the same local position of the bridge on the local photos of the bridge at adjacent time points into an actual local deformation quantity of the bridge, and is also used for constructing a first neural network model and a second neural network model, wherein the first neural network model takes the actual local deformation quantity of the bridge as an input sample, the bridge structure data stored in the data storage module as an output sample, and the second neural network model takes the bridge structure data stored in the data storage module as an input sample and the actual local deformation quantity of the bridge as an output sample;
the monitoring and early warning module is used for comparing bridge structure data acquired at the latest time point with a design threshold of the bridge structure data, outputting 1 if the bridge structure data is larger than the design threshold, otherwise outputting 0, comparing an actual bridge local deformation quantity at the latest time point with the design threshold of the bridge local deformation quantity, outputting 1 if the bridge structure data is larger than the design threshold of the bridge structure data, otherwise outputting 0, inputting the actual bridge local deformation quantity at the latest time point into a first neural network model to obtain predicted bridge structure data, then comparing the predicted bridge structure data with the design threshold of the bridge structure data, outputting 1 if the bridge structure data is larger than the design threshold, otherwise outputting 0, inputting the bridge structure data acquired at the latest time point into a second neural network model to obtain the predicted actual bridge local deformation quantity, then comparing the predicted actual bridge local deformation quantity with the design threshold, outputting 1 if the bridge structure data is larger than the design threshold, otherwise outputting 0, if the output result of the comparison contains at least one 1, the monitoring and early warning module sends warning information, and otherwise, the monitoring and early warning information is not sent by the monitoring and early warning module.
Preferably, the first neural network model and the second neural network model are the same and each include an input layer, a first hidden layer, a second hidden layer and an output layer which are connected in sequence, the output of each neuron of the previous layer is used as the input of each neuron of the next layer, the neurons of the same layer are independent of each other, the connection strength between any two connected neurons is expressed by a weight value, each neuron in the output layer is provided with a bias coefficient, and each neuron in the first hidden layer and the second hidden layer is provided with a weight value of the neuron.
Preferably, the method for converting the deformation amount of the same local position of the bridge on the local photos of the bridge at the adjacent time points into the actual local deformation amount of the bridge in the data processing module comprises the following steps: and setting a calibration object at the local part of the bridge, calculating the scaling of the local picture of the bridge according to the size of the calibration object on the local picture of the bridge and the actual size of the calibration object, and converting the scaling of the local picture of the deformation beam at the same local position of the bridge on the local pictures of the bridge at the adjacent time points into the actual local deformation of the bridge.
Preferably, the data processing module is further configured to obtain a difference between the predicted bridge structure data and the bridge structure data stored in the data storage module by using the first loss function, train the first neural network model by using a back propagation algorithm to optimize the first neural network model, simultaneously obtain a difference between the predicted actual bridge local deformation amount and the actual bridge local deformation amount obtained through the bridge local photograph by using the second loss function, and train the second neural network model by using the back propagation algorithm to optimize the second neural network model.
Preferably, the plurality of sensors includes a stress sensor, a strain sensor, and an acceleration sensor.
Preferably, before the data processing module trains the first neural network and the second neural network, normalization processing is performed on the actual bridge local deformation and the bridge structure data stored in the data storage module respectively.
The invention at least comprises the following beneficial effects: not only can be to the concrete bridge, can also be to the steel structure bridge, adopt multiple sensor to gather the structural data of bridge under the operation state, adopt the camera to gather the local outward appearance photo condition of bridge, deduce the contact between bridge structure and the outward appearance through the neural network model, the accuracy of bridge structural data and outward appearance photo each other is testified again, when having avoided judging bridge health status through single structural data, the situation of misjudgement appears in the structural data after receiving the interference when gathering, also avoided single when judging bridge health status through outward appearance photo, the situation that the photo took the trouble to appear the picture to take the unusual misjudgement to lead to when the local photo of bridge that gathers receives the external disturbance to appear abnormal deformation or equipment to appear the trouble, the accuracy of bridge health monitoring early warning has been improved greatly.
Additional advantages, objects, and features of the invention will be set forth in part in the description which follows and in part will become apparent to those having ordinary skill in the art upon examination of the following or may be learned from practice of the invention.
Drawings
Fig. 1 is a schematic structural diagram of a bridge health monitoring and early warning system based on machine learning according to the present invention.
Detailed Description
The present invention is described in further detail below with reference to the attached drawings so that those skilled in the art can implement the invention by referring to the description text.
It is to be noted that the experimental methods described in the following embodiments are all conventional methods unless otherwise specified, and the reagents and materials described therein are commercially available unless otherwise specified; in the description of the present invention, the terms "lateral", "longitudinal", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc., indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, are only for convenience in describing the present invention and simplifying the description, and do not indicate or imply that the device or element being referred to must have a particular orientation, be constructed and operated in a particular orientation, and thus, should not be construed as limiting the present invention.
As shown in fig. 1, the present invention provides a bridge health monitoring and early warning system based on machine learning, which includes:
the data acquisition module, it includes the multiple sensor that detects to the bridge, the camera and the data transmission unit of shooing the local fixed point of bridge, the sensor is used for regularly gathering the structural data of bridge at first preset time interval, the camera is used for regularly shooing the local photo of bridge at second preset time interval, the data transmission unit is used for adopting wireless network connection's mode to send the bridge structural data and the local photo of bridge that the sensor gathered.
The various sensors comprise stress sensors, strain sensors and acceleration sensors, the existing pre-embedded type stress sensors can more accurately detect the real-time stress of the key point positions of the bridge, the strain sensors can be attached to the key point positions of the bridge to detect the real-time strain of the key point positions of the bridge, and the acceleration sensors can detect the vibration speed of the key point positions of the bridge along the longitudinal direction of the bridge and the vibration speed of the key point positions of the bridge along the transverse direction of the bridge.
The point locations arranged by the sensors can be in a compressive stress concentration area at the bridge piers and can also be in a tensile stress concentration area at the back of the middle part of a bridge between the two bridge piers, and each point location can be provided with a group of equipment comprising a stress sensor, a strain sensor, an acceleration sensor, a camera and the like, so that the stress data and the appearance condition of the key point locations can be recorded and transmitted in real time.
And the data storage module is used for storing the bridge structure data and the bridge local photos sent by the data acquisition module according to time points, storing a first preset number of bridge structure data and a second preset number of bridge local photos, and deleting the bridge structure data and the bridge local photos at the oldest time points when the bridge structure data stored in the data storage module reach the first preset number and the number of the bridge local photos reach the second preset number and the data storage module receives the bridge structure data and the bridge local photos at the newest time points.
The bridge structure data and the local photos of the bridge acquired at different key point positions of the bridge at each time are preferably at the same time point, so that a complete data model of the bridge at the time point can be formed, and the data acquisition module can be sent for multiple times in the data sending process, so that the phenomenon that the network is blocked and even the data is lost when the data acquired at the same time point are sent at the same time is avoided.
The bridge structure data and the bridge local photos stored in the data storage module are processed in a first-in first-out mode, and when the newly collected bridge structure data and the newly collected bridge local photos exist, the oldest bridge structure data and the oldest bridge local photos are discarded, so that the data storage capacity can be reduced, and the latest state data of the bridge can be kept and recorded.
The data processing module is used for converting the deformation quantity of the same local position of the bridge on the local pictures of the bridge at the adjacent time points into an actual local deformation quantity of the bridge, the data processing module is also used for constructing a first neural network model and a second neural network model, the first neural network model takes the actual local deformation quantity of the bridge as an input sample, the bridge structure data stored in the data storage module is taken as an output sample, and the second neural network model takes the bridge structure data stored in the data storage module as an input sample and the actual local deformation quantity of the bridge as an output sample.
Here, the deformation amount of the same local position of the bridge on the local photos of the bridge at the adjacent time points is calculated in the following manner: establishing the same plane coordinate system on the local pictures of the bridges at the adjacent time points, recording the coordinate points of the coordinate system of the same local position of the bridge on each local picture of the bridge, and calculating the distance between the coordinate points of the same local position of the bridge on the local pictures of the bridges at the adjacent time points, namely the deformation quantity.
The method for converting the deformation quantity of the same local position of the bridge on the local photos of the bridge at the adjacent time points into the actual local deformation quantity of the bridge in the data processing module comprises the following steps: and setting a calibration object at the local part of the bridge, calculating the scaling of the local picture of the bridge according to the size of the calibration object on the local picture of the bridge and the actual size of the calibration object, and converting the deformation quantity of the same local position of the bridge on the local pictures of the bridge at adjacent time points into the actual local deformation quantity of the bridge according to the scaling of the local pictures of the bridge.
The first neural network model and the second neural network model may adopt the same structural model, and each neural network model includes an input layer, a first hidden layer, a second hidden layer and an output layer, which are connected in sequence, an output of each neuron of a previous layer is used as an input of each neuron of a next layer, the neurons of the same layer are independent of each other, a connection strength is expressed by a weight value between any two connected neurons, each neuron in the output layer is provided with a bias coefficient, and each neuron in the first hidden layer and the second hidden layer is provided with a weight value of itself. The data processing module takes the actual bridge local deformation amount as an input sample, takes the bridge structure data stored in the data storage module as an output sample, trains the first neural network model, takes the bridge structure data stored in the data storage module as an input sample, and takes the actual bridge local deformation amount as an output sample, and trains the second neural network model.
The monitoring and early warning module is used for comparing bridge structure data acquired at the latest time point with a design threshold of the bridge structure data, outputting 1 if the bridge structure data is larger than the design threshold, otherwise outputting 0, comparing an actual bridge local deformation quantity at the latest time point with the design threshold of the bridge local deformation quantity, outputting 1 if the bridge structure data is larger than the design threshold of the bridge structure data, otherwise outputting 0, inputting the actual bridge local deformation quantity at the latest time point into a first neural network model to obtain predicted bridge structure data, then comparing the predicted bridge structure data with the design threshold of the bridge structure data, outputting 1 if the bridge structure data is larger than the design threshold, otherwise outputting 0, inputting the bridge structure data acquired at the latest time point into a second neural network model to obtain the predicted actual bridge local deformation quantity, then comparing the predicted actual bridge local deformation quantity with the design threshold, outputting 1 if the bridge structure data is larger than the design threshold, otherwise outputting 0, if the output result of the comparison contains at least one 1, the monitoring and early warning module sends warning information, and otherwise, the monitoring and early warning information is not sent by the monitoring and early warning module.
Above-mentioned embodiment is in the use, can be to the concrete bridge, can also be to steel structure bridge, adopt multiple sensor to gather the structural data of bridge under the operating condition, adopt the local outward appearance photo condition of bridge of camera collection, deduce the relation between bridge structure and the outward appearance through the neural network model, the accuracy of bridge structural data and outward appearance photo is testified each other again, when having avoided judging bridge health status through single structural data, the situation of misjudgement appears in the structural data after receiving the interference when gathering, also avoided singly to judge bridge health status through outward appearance photo, the situation that the photo took place to take unusually to lead to misjudgement when the local photo of bridge that gathers receives the external disturbance and appears abnormal deformation or equipment to appear the trouble, the accuracy of bridge health monitoring early warning has been improved greatly.
In another embodiment, the data processing module is further configured to obtain a difference between the predicted bridge structure data and the bridge structure data stored in the data storage module by using a first loss function, train the first neural network model by using a back propagation algorithm to optimize the first neural network model, simultaneously obtain a difference between the predicted actual bridge local deformation amount and the actual bridge local deformation amount obtained through the bridge local photograph by using a second loss function, and train the second neural network model by using a back propagation algorithm to optimize the second neural network model.
In another embodiment, before the data processing module trains the first neural network and the second neural network, the data processing module respectively performs normalization processing on the actual bridge local deformation quantity and the bridge structure data stored in the data storage module.
While embodiments of the invention have been described above, it is not limited to the applications set forth in the description and the embodiments, which are fully applicable in various fields of endeavor to which the invention pertains, and further modifications may readily be made by those skilled in the art, it being understood that the invention is not limited to the details shown and described herein without departing from the general concept defined by the appended claims and their equivalents.
Claims (6)
1. Bridge health monitoring early warning system based on machine learning, its characterized in that includes:
the data acquisition module comprises a plurality of sensors for detecting the bridge, a camera for shooting the local fixed point of the bridge and a data sending unit, wherein the sensor is used for acquiring the structural data of the bridge at a first preset time interval, the camera is used for shooting the local picture of the bridge at a second preset time interval, and the data sending unit is used for sending the bridge structural data and the local picture of the bridge acquired by the sensor in a wireless network connection mode;
the data storage module is used for storing the bridge structure data and the bridge local photos sent by the data acquisition module according to time points, storing a first preset amount of bridge structure data and a second preset amount of bridge local photos, and deleting the bridge structure data and the bridge local photos at the oldest time points when the data storage module receives the bridge structure data and the bridge local photos at the newest time points after the bridge structure data stored in the data storage module reaches the first preset amount and the bridge local photos reach the second preset amount;
the data processing module is used for converting deformation quantities of the same local position of the bridge on the local photos of the bridge at adjacent time points into an actual local deformation quantity of the bridge, and is also used for constructing a first neural network model and a second neural network model, wherein the first neural network model takes the actual local deformation quantity of the bridge as an input sample, the bridge structure data stored in the data storage module as an output sample, and the second neural network model takes the bridge structure data stored in the data storage module as an input sample and the actual local deformation quantity of the bridge as an output sample;
and the monitoring and early warning module is used for comparing the bridge structure data acquired at the latest time point with the design threshold of the bridge structure data, if the bridge structure data are larger than the design threshold of the bridge structure data, outputting 1, otherwise, outputting 0, inputting the actual bridge local deformation at the latest time point into the first neural network model to obtain predicted bridge structure data, then comparing the predicted bridge structure data with the design threshold of the bridge structure data, if the bridge structure data are larger than the design threshold of the bridge structure data, otherwise, outputting 1, otherwise, outputting 0, inputting the bridge structure data acquired at the latest time point into the second neural network model to obtain the predicted actual bridge local deformation, then comparing the predicted actual bridge local deformation with the design threshold of the bridge structure data, if the bridge structure data are larger than the design threshold of the bridge structure data, otherwise, outputting 1, otherwise, outputting 0, if the output result of the comparison contains at least one 1, the monitoring and early warning module sends warning information, and otherwise, the monitoring and early warning information is not sent by the monitoring and early warning module.
2. The bridge health monitoring and early warning system based on machine learning of claim 1, wherein the first neural network model and the second neural network model are the same, and each neural network model comprises an input layer, a first hidden layer, a second hidden layer and an output layer which are connected in sequence, the output of each neuron of the previous layer is used as the input of each neuron of the next layer, the neurons of the same layer are independent of each other, the connection strength is represented by a weight value between any two connected neurons, each neuron in the output layer is provided with a bias coefficient, and each neuron in the first hidden layer and the second hidden layer is provided with its own weight value.
3. The bridge health monitoring and early warning system based on machine learning of claim 1, wherein the method for converting the deformation quantity of the same local position of the bridge on the local photos of the bridge at the adjacent time points into the actual local deformation quantity of the bridge in the data processing module comprises the following steps: and setting a calibration object at the local part of the bridge, calculating the scaling of the local picture of the bridge according to the size of the calibration object on the local picture of the bridge and the actual size of the calibration object, and converting the deformation quantity of the same local position of the bridge on the local pictures of the bridge at adjacent time points into the actual local deformation quantity of the bridge according to the scaling of the local pictures of the bridge.
4. The machine learning-based bridge health monitoring and early warning system of claim 1, wherein the data processing module is further configured to use a first loss function to obtain a difference between the predicted bridge structure data and the bridge structure data stored in the data storage module, train the first neural network model using a back propagation algorithm to optimize the first neural network model, simultaneously use a second loss function to obtain a difference between the predicted actual bridge local deformation and the actual bridge local deformation obtained through the bridge local photograph, and train the second neural network model using a back propagation algorithm to optimize the second neural network model.
5. The machine learning-based bridge health monitoring and pre-warning system of claim 1, wherein the plurality of sensors comprise stress sensors, strain sensors, acceleration sensors.
6. The bridge health monitoring and early warning system based on machine learning of claim 1, wherein before the data processing module trains the first neural network and the second neural network, the data processing module respectively normalizes the actual bridge local deformation and the bridge structure data stored in the data storage module.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010526405.4A CN111738996B (en) | 2020-06-09 | 2020-06-09 | Bridge health monitoring and early warning system based on machine learning |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010526405.4A CN111738996B (en) | 2020-06-09 | 2020-06-09 | Bridge health monitoring and early warning system based on machine learning |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111738996A CN111738996A (en) | 2020-10-02 |
CN111738996B true CN111738996B (en) | 2023-04-07 |
Family
ID=72648742
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010526405.4A Active CN111738996B (en) | 2020-06-09 | 2020-06-09 | Bridge health monitoring and early warning system based on machine learning |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111738996B (en) |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112802021B (en) * | 2021-04-09 | 2021-07-30 | 泰瑞数创科技(北京)有限公司 | Urban bridge road diagnosis method and system based on digital twin technology |
CN113255820B (en) * | 2021-06-11 | 2023-05-02 | 成都通甲优博科技有限责任公司 | Training method for falling-stone detection model, falling-stone detection method and related device |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101586996A (en) * | 2009-06-26 | 2009-11-25 | 贵州师范大学 | Cable force prediction method of cable stayed bridge based on artificial neural network |
CN104200005A (en) * | 2014-07-28 | 2014-12-10 | 东北大学 | Bridge damage identification method based on neural network |
CN105550506A (en) * | 2015-12-09 | 2016-05-04 | 东南大学 | Method for directly predicting wind-induced vibration response of bridge based on long-term actually measured data |
CN107871161A (en) * | 2017-11-07 | 2018-04-03 | 中国铁道科学研究院铁道建筑研究所 | A kind of bridge entirety damage alarming method based on neutral net |
CN108446838A (en) * | 2018-03-08 | 2018-08-24 | 佛山科学技术学院 | A kind of bridge safety supervision system based on big data |
CN109685331A (en) * | 2018-12-06 | 2019-04-26 | 中国软件与技术服务股份有限公司 | A kind of high-speed rail bogie sensor fault diagnosis method based on machine learning |
CN109902344A (en) * | 2019-01-23 | 2019-06-18 | 同济大学 | Short/Medium Span Bridge group structure performance prediction apparatus and system |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20160217226A1 (en) * | 2015-01-28 | 2016-07-28 | Brian Westcott | Methods and systems for infrastructure performance: monitoring, control, operations, analysis and adaptive learning |
-
2020
- 2020-06-09 CN CN202010526405.4A patent/CN111738996B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101586996A (en) * | 2009-06-26 | 2009-11-25 | 贵州师范大学 | Cable force prediction method of cable stayed bridge based on artificial neural network |
CN104200005A (en) * | 2014-07-28 | 2014-12-10 | 东北大学 | Bridge damage identification method based on neural network |
CN105550506A (en) * | 2015-12-09 | 2016-05-04 | 东南大学 | Method for directly predicting wind-induced vibration response of bridge based on long-term actually measured data |
CN107871161A (en) * | 2017-11-07 | 2018-04-03 | 中国铁道科学研究院铁道建筑研究所 | A kind of bridge entirety damage alarming method based on neutral net |
CN108446838A (en) * | 2018-03-08 | 2018-08-24 | 佛山科学技术学院 | A kind of bridge safety supervision system based on big data |
CN109685331A (en) * | 2018-12-06 | 2019-04-26 | 中国软件与技术服务股份有限公司 | A kind of high-speed rail bogie sensor fault diagnosis method based on machine learning |
CN109902344A (en) * | 2019-01-23 | 2019-06-18 | 同济大学 | Short/Medium Span Bridge group structure performance prediction apparatus and system |
Non-Patent Citations (6)
Title |
---|
"Application Research of Neural Network Algorithm in Bridge Health Status Monitoring System";Qingchun Zhang et al.;《2019 International Conference on Robots & Intelligent System (ICRIS)》;全文 * |
"一种基于BP神经网络的老旧桥梁健康诊断方法";李禹剑等;《国外电子测量技术》(第02期);全文 * |
"基于新奇检测技术的桥梁结构损伤预警方法";孙宗光等;《公路交通科技》;第24卷(第10期);全文 * |
"基于时序数据分析的桥梁结构健康状态识别";王成菀;《中国优秀硕士学位论文全文数据库 基础科学辑》(第04期);全文 * |
"桥梁结构状态预警系统研究";温青等;《城市道桥与防洪》(第06期);全文 * |
"混凝土梁桥剩余使用寿命研究";张立业等;《桥梁建设》;第44卷(第05期);全文 * |
Also Published As
Publication number | Publication date |
---|---|
CN111738996A (en) | 2020-10-02 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112987675B (en) | Method, device, computer equipment and medium for anomaly detection | |
CN111738996B (en) | Bridge health monitoring and early warning system based on machine learning | |
CN109099975A (en) | A kind of building structure health monitoring systems | |
CN104880217B (en) | A kind of fault sensor signal reconstruct method based on the measured value degree of association | |
CN107860425A (en) | Bridge structure health monitoring and early warning system and method | |
CN115526515B (en) | Safety monitoring system of gate for water conservancy and hydropower | |
CN107255526A (en) | A kind of temperature checking method, detection module and detecting system | |
CN113192283A (en) | Wireless fire early warning system with multi-sensor information fusion | |
CN115100819B (en) | Landslide hazard early warning method and device based on big data analysis and electronic equipment | |
CN106908101A (en) | A kind of Health Monitoring for Civil Engineering system and method | |
CN112349057A (en) | Deep learning-based indoor smoke and fire detection method | |
Moeinifard et al. | Lost vibration test data recovery using convolutional neural network: a case study | |
CN116776267A (en) | Unsupervised data processing method and system for bridge construction control | |
CN113404655A (en) | Wind driven generator sensor state diagnosis system based on PS0-ANFIS | |
CN108759920B (en) | Warehouse safety monitoring system based on thing networking | |
CN116522096B (en) | Three-dimensional digital twin content intelligent manufacturing method based on motion capture | |
CN116308293B (en) | Intelligent agricultural equipment management system and method based on digital platform | |
CN113128098A (en) | DE-LOF-based concrete dam singular value detection method and equipment | |
CN112711052A (en) | GNSS coordinate sequence step detection improvement method and system based on continuous t inspection | |
CN206656749U (en) | Heat-engine plant sensor fault diagnosis system | |
CN114926588A (en) | Bridge static displacement prediction method based on deep learning LSTM network | |
CN114004138A (en) | Building monitoring method and system based on big data artificial intelligence and storage medium | |
CN117091799B (en) | Intelligent three-dimensional monitoring method and system for oxygen supply safety of medical center | |
CN115078239B (en) | Reinforcing steel bar corrosion data acquisition unit, monitoring subsystem, regional system and monitoring system | |
CN117723917B (en) | Monitoring application method based on optical fiber extrinsic Fabry-Perot type ultrasonic sensor |
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 |