CN115688555B - Bridge life prediction method - Google Patents
Bridge life prediction method Download PDFInfo
- Publication number
- CN115688555B CN115688555B CN202211088670.4A CN202211088670A CN115688555B CN 115688555 B CN115688555 B CN 115688555B CN 202211088670 A CN202211088670 A CN 202211088670A CN 115688555 B CN115688555 B CN 115688555B
- Authority
- CN
- China
- Prior art keywords
- bridge
- resistance
- time
- varying
- 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
- 238000000034 method Methods 0.000 title claims abstract description 36
- 238000013528 artificial neural network Methods 0.000 claims abstract description 20
- 230000001066 destructive effect Effects 0.000 claims abstract description 16
- 238000012549 training Methods 0.000 claims abstract description 14
- 125000004122 cyclic group Chemical group 0.000 claims abstract description 12
- 230000000694 effects Effects 0.000 claims description 11
- 238000004364 calculation method Methods 0.000 claims description 9
- 239000000463 material Substances 0.000 claims description 9
- 230000006866 deterioration Effects 0.000 claims description 5
- 230000015556 catabolic process Effects 0.000 claims description 4
- 238000006731 degradation reaction Methods 0.000 claims description 4
- 229910001294 Reinforcing steel Inorganic materials 0.000 claims description 2
- 229910000831 Steel Inorganic materials 0.000 claims description 2
- 230000004807 localization Effects 0.000 claims description 2
- 230000000306 recurrent effect Effects 0.000 claims description 2
- 239000010959 steel Substances 0.000 claims description 2
- 238000005516 engineering process Methods 0.000 abstract description 2
- 238000004458 analytical method Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 5
- 238000012544 monitoring process Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000003014 reinforcing effect Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 239000004566 building material Substances 0.000 description 1
- 230000001186 cumulative effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000009795 derivation Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Landscapes
- Bridges Or Land Bridges (AREA)
Abstract
The invention discloses a bridge life prediction method, which comprises the following steps: modeling the bridge to obtain a bridge model; dividing the bridge model into a plurality of parts; analyzing the resistance and the destructive power of each part; constructing a cyclic neural network, and training the cyclic neural network based on the resistance and the destructive power of each part; and predicting the service life of the bridge based on the trained cyclic neural network. According to the invention, the data acquired from the sensor is analyzed through the cyclic neural network, so that the process of calculating the service life of the bridge by professionals is replaced, and the automation of predicting the service life is realized. Compared with manual survey, the technology can collect real-time alarm in real time, does not need to consider weather influence when collecting data, is not limited by site, has time sequence of data, and is accurate and reliable.
Description
Technical Field
The invention belongs to the field of electronic information, and particularly relates to a bridge life prediction method.
Background
The existing bridge life prediction mainly collects various data of the bridge through a sensor, and performs manual analysis or semi-automatic analysis on the collected data, the data is mainly delivered to professionals, the professionals judge whether the bridge can pass through the data, if the bridge can not be subjected to limited-line processing and subsequent maintenance or reconstruction judgment, if the bridge can pass through the bridge, the data is converted into life information, and only professionals know the derivation process. Semi-automatic analysis is a tool for assisting professionals to preliminarily judge whether the bridge can pass or not, and the degree of automation is low.
However, the manual analysis method has the defects of large data volume, low analysis efficiency, long time consumption, high intelligence cost and large manpower consumption, and needs professional workers, and meanwhile, the manual analysis is inevitably wrong, so that the accuracy needs repeated detection for many times. The semi-automatic analysis has higher dependence on manpower, human-computer interaction is required frequently, a threshold range is often required to be manually given during decision-making, the real-time decision-making degree is not high, and the safety cannot be guaranteed.
Disclosure of Invention
The invention aims to provide a bridge life prediction method for solving the problems existing in the prior art.
In order to achieve the above object, the present invention provides a bridge life prediction method, including:
modeling the bridge to obtain a bridge model;
dividing the bridge model into a plurality of local areas;
analyzing the resistance and the destructive power of each local area;
constructing a cyclic neural network, and training the cyclic neural network based on the resistance and the destructive power of each local area;
and predicting the service life of the bridge based on the trained cyclic neural network.
Optionally, the process after obtaining the bridge model includes: and taking points of the bridge model, simulating the process of time change of bridge damage caused by external force, and obtaining various data changes of the bridge model.
Optionally, the process of dividing the bridge model into a plurality of local areas includes:
based on the localization method, the force is integrated for each of the cross-sections of the local areas, each force representing a cross-section.
Optionally, the process of analyzing the resistance and the destructive power of each local area includes:
analyzing the resistance based on a time-varying resistance calculation;
the destructive power is analyzed based on a time-varying load bearing effect calculation.
Optionally, the calculating process of the time-varying resistance includes:
acquiring resistance values of the bridge structure at different moments based on engineering material standards;
calculating a resistance deterioration function;
the time-varying resistance is obtained based on the resistance value and the resistance degradation function calculation.
Optionally, the method for calculating the resistance degradation function is as follows:
wherein g (t) is a resistance deterioration function, K s Represents the co-operating coefficient, R a (t),R a 0 represents the time-varying strength and the initial strength of the concrete respectively; r is R g (t),R g 0 respectively represents the time-varying yield strength and the initial yield strength of the steel bar; a is that g (t),A g 0 represents the time-varying cross-sectional area and the initial cross-sectional area of the reinforcing bar, respectively.
Optionally, the method for calculating the time-varying bearer effect includes:
wherein S (t) is a time-varying bearing effect, and M (t) is a varying function of the breaking force S (t).
Optionally, the training the recurrent neural network based on the resistance and the destructive power of each local area includes:
acquiring the service life of a current bridge;
and training the circulating neural network by taking the time-varying resistance and the time-varying bearing effect of each local area as a training set and the current bridge life as a label.
The invention has the technical effects that:
according to the invention, the data acquired from the sensor is analyzed through the cyclic neural network, so that the process of calculating the service life of the bridge by professionals is replaced, and the automation of predicting the service life is realized. Compared with manual survey, the technology can collect real-time alarm in real time, does not need to consider weather influence when collecting data, is not limited by site, has time sequence of data, is accurate and reliable, and has less manpower and material resources; compared with semi-automatic monitoring, when an emergency occurs, abnormal fluctuation of data can occur, real-time alarm can be realized, and meanwhile, the intelligent monitoring system does not need professional personnel to participate, so that intelligent investment is saved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application, illustrate and explain the application and are not to be construed as limiting the application. In the drawings:
FIG. 1 is a basic roadmap of a conventional bridge life prediction technique;
FIG. 2 is a schematic flow chart of a method according to an embodiment of the invention;
FIG. 3 is a schematic diagram illustrating the classification of influencing factors in an embodiment of the present invention;
FIG. 4 is a schematic diagram of bridge resistance calculation according to an embodiment of the present invention;
FIG. 5 is a schematic diagram of a neural network training process in an embodiment of the present invention;
FIG. 6 is a schematic diagram of a bridge life prediction process according to an embodiment of the present invention;
fig. 7 is a general diagram of a technical route in an embodiment of the present invention.
Detailed Description
It should be noted that, in the case of no conflict, the embodiments and features in the embodiments may be combined with each other. The present application will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.
It should be noted that the steps illustrated in the flowcharts of the figures may be performed in a computer system such as a set of computer executable instructions, and that although a logical order is illustrated in the flowcharts, in some cases the steps illustrated or described may be performed in an order other than that illustrated herein.
Example 1
As shown in fig. 1 to 7, the present embodiment provides a bridge life prediction method, which includes:
the technical route is shown in fig. 2, in the first step, because factors such as noise and the like influence sensor data in a real bridge, the factors influence the neural network training process to a certain extent, meanwhile, in a test stage, the real data are often difficult to obtain, and therefore, the bridge is modeled by adopting ansys finite element modeling software, an absolute healthy bridge is constructed, after the bridge is built, a point is taken in the model to replace a sensor, the pressurizing force on the bridge is used for replacing the vehicle driving process, the process that external force changes the bridge damage in time and the like can be simulated, and each data change of the bridge in the change can be simply obtained.
In the second step, the bridge locating point is required to be analyzed, and the factors affecting the bridge are classified, as shown in fig. 3, into internal factors and external factors, wherein the internal factors are caused by the attenuation of various materials of the bridge, and the external factors are caused by the influence of the external environment on the bridge, so that the relationship between the resistance and the destructive power can be understood. Resistance: the building materials of the bridge structure gradually age along with the time loss in the natural environment, and the performances and the strength of different materials gradually decay along with the time loss, namely the resistance of the bridge is reduced along with the time loss. The resistance values of different materials can be obtained by referring to engineering material standards, or the resistance values at different moments can be sampled at fixed time on the bridge. Breaking force: bridge mathematical model constructed based on Ansys can directly obtain the value of the local structural force of the bridge through taking points in the model. In practical applications, the values may be obtained by corresponding sensors. The next point of retrieval and sensor placement is only related to the destructive forces, here a localized approach is taken, taking the bridge cross section as one part, each part integrating the force, representing one force as one cross section, the benefit of doing so: the error of the external force value can be effectively avoided by using a fitting and integrating method in engineering practice; the installation positions of the sensors in the local structure are not limited, the number of the sensors is more than or equal to 2, local external force calculation can be performed, and project cost can be effectively reduced due to non-limitation. Here, a local concept is introduced to divide the bridge into a plurality of parts, and resistance and destructive power are divided for each part, and the influence of the relation between the parts on life prediction is obtained through neural network self-learning.
Thirdly, respectively calculating the resisting force and the breaking force, wherein the time-varying resisting force R (t) is used as a resisting force analysis, and the main formula is as follows:
R(t)=g(t)·R 0
where R0 is the initial resistance of the structure, g (t) is a resistance degradation function, and the resistance value is related to factors such as structural materials, types, use conditions, stress and the like. Ks represents a cooperative work coefficient, ra (t), and Ra0 represents time-varying strength and initial strength of the concrete respectively; rg (t), rg0 respectively represents the time-varying yield strength and the initial yield strength of the reinforcing steel bar; ag (t), ag0 represents the time-varying cross-sectional area and the initial cross-sectional area of the reinforcing bar, respectively. Bridge materials are different, the products used here are different, but the formulas are communicating. The final result is shown in FIG. 4. For destructive power, expressed by using a time-varying bearing effect S (t), the cumulative damage condition is expressed by an integral, and the formula is as follows:
m (t) is a function of the change in breaking force S (t).
And fourthly, taking the time-varying resistance R (t) and the time-varying bearing effect S (t) as inputs, training the cyclic neural network, wherein the training set comprises R (t) and S (t) of each part corresponding to time and N parts, N groups of R (t) and S (t) exist at the same time, the labels are the current bridge life, the labels are acquired by professionals, the trained network can be used for predicting the bridge life in real time, and the network can learn the relation of data, so that the manner of processing the data by professionals is learned. The training process is shown in fig. 5, and the prediction process is shown in fig. 6.
The overall technical scheme is shown in fig. 7.
The foregoing is merely a preferred embodiment of the present application, but the scope of the present application is not limited thereto, and any changes or substitutions easily contemplated by those skilled in the art within the technical scope of the present application should be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (1)
1. The bridge life prediction method is characterized by comprising the following steps of:
modeling the bridge to obtain a bridge model;
dividing the bridge model into a plurality of local areas;
analyzing the resistance and the destructive power of each local area;
the process of analyzing the resistance and breaking force of each local area includes:
analyzing the resistance based on a time-varying resistance calculation;
analyzing the destructive power based on a time-varying load bearing effect calculation;
the time-varying resistance calculation process comprises the following steps:
acquiring resistance values of the bridge structure at different moments based on engineering material standards;
calculating a resistance deterioration function;
calculating and acquiring the time-varying resistance based on the resistance value and the resistance degradation function
The method for calculating the resistance deterioration function comprises the following steps:
wherein g (t) is a resistance deterioration function, K s Represents the co-operating coefficient, R a (t),R a0 Respectively represent the time-varying strength of the concreteInitial strength; r is R g (t),R g0 Respectively representing the time-varying yield strength and the initial yield strength of the steel bar; a is that g (t),A g0 Respectively representing the time-varying sectional area and the initial sectional area of the reinforcing steel bar;
the calculation method of the time-varying bearing effect comprises the following steps:
wherein S (t) is a time-varying bearing effect, and M (t) is a variation function of the destructive power S (t);
constructing a cyclic neural network, and training the cyclic neural network based on the resistance and the destructive power of each local area; the influence of the local-local relation on life prediction is obtained through self-learning of a neural network;
predicting the service life of the bridge based on the trained cyclic neural network;
the process after the bridge model is acquired comprises the following steps: taking points of the bridge model, simulating the process of time change of bridge damage caused by external force, and obtaining various data changes of the bridge model;
the process of dividing the bridge model into a plurality of local regions includes:
integrating the forces over the cross-section of each of said localized areas based on a localization method, each force representing a cross-section;
the training of the recurrent neural network based on the resistive and destructive forces of each local region includes:
acquiring the service life of a current bridge;
and training the circulating neural network by taking the time-varying resistance and the time-varying bearing effect of each local area as a training set and the current bridge life as a label.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211088670.4A CN115688555B (en) | 2022-09-07 | 2022-09-07 | Bridge life prediction method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211088670.4A CN115688555B (en) | 2022-09-07 | 2022-09-07 | Bridge life prediction method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN115688555A CN115688555A (en) | 2023-02-03 |
CN115688555B true CN115688555B (en) | 2024-03-26 |
Family
ID=85060722
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211088670.4A Active CN115688555B (en) | 2022-09-07 | 2022-09-07 | Bridge life prediction method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115688555B (en) |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20220009057A (en) * | 2020-07-15 | 2022-01-24 | 국토안전관리원 | Monitoring system of cable-supported bridge using artficial intelligence and monitoring method of cable-supported bridge using it |
CN114626305A (en) * | 2022-03-21 | 2022-06-14 | 西南交通大学 | Method, device, equipment and medium for predicting residual fatigue life of steel bridge deck |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109300126B (en) * | 2018-09-21 | 2022-01-07 | 重庆建工集团股份有限公司 | High-precision intelligent detection method for bridge diseases based on spatial positions |
US11592377B2 (en) * | 2020-04-20 | 2023-02-28 | Vishay Measurements Group, Inc. | Fatigue life sensor for measuring repetitive loads applied to a structure based upon cracks propagating from crack initiation features of the sensor |
-
2022
- 2022-09-07 CN CN202211088670.4A patent/CN115688555B/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20220009057A (en) * | 2020-07-15 | 2022-01-24 | 국토안전관리원 | Monitoring system of cable-supported bridge using artficial intelligence and monitoring method of cable-supported bridge using it |
CN114626305A (en) * | 2022-03-21 | 2022-06-14 | 西南交通大学 | Method, device, equipment and medium for predicting residual fatigue life of steel bridge deck |
Non-Patent Citations (4)
Title |
---|
何伟.中、下承式拱桥健康监测实践.中国环境出版社,2017,第2-4页. * |
基于时变可靠度分析的桥梁使用寿命预测;李海涛;中国安全科学学报;22(06);第100-103页 * |
基于桥梁长期健康监测数据的时变可靠性分析和寿命预测;雷秀强;中国优秀硕士学位论文全文数据库(第12期);第1-63页 * |
李海涛.基于时变可靠度分析的桥梁使用寿命预测.中国安全科学学报.2012,22(06),第100-103页. * |
Also Published As
Publication number | Publication date |
---|---|
CN115688555A (en) | 2023-02-03 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108764601B (en) | Structural health monitoring abnormal data diagnosis method based on computer vision and deep learning technology | |
CN109583570B (en) | Method for determining abnormal data source of bridge health monitoring system based on deep learning | |
CN111274737A (en) | Method and system for predicting remaining service life of mechanical equipment | |
CN108873859B (en) | Bridge type grab ship unloader fault prediction model method based on improved association rule | |
CN105716814B (en) | A kind of real-time monitoring system and its method for assessing truss structure damage | |
CN108399277B (en) | Bridge damage identification method based on temperature and strain correlation | |
CN115034578A (en) | Intelligent management construction method and system for hydraulic metal structure equipment based on digital twinning | |
CN113723010B (en) | Bridge damage early warning method based on LSTM temperature-displacement correlation model | |
CN111737909A (en) | Structural health monitoring data anomaly identification method based on space-time graph convolutional network | |
CN210924883U (en) | Bridge structure health monitoring system | |
CN111625988A (en) | Bridge health management analysis and prediction system and method based on deep learning | |
CN115329812B (en) | Bridge infrastructure anomaly monitoring method based on artificial intelligence | |
CN111881495A (en) | Prestress steel structure safety assessment method based on digital twinning | |
CN114118673A (en) | Workshop intelligent fault diagnosis early warning method based on digital twin technology | |
CN115438726A (en) | Device life and fault type prediction method and system based on digital twin technology | |
CN116341272A (en) | Construction safety risk management and control system for digital distribution network engineering | |
CN110728089B (en) | Large-span bridge stay cable structure damage diagnosis method based on BOTDA technology | |
CN104504265B (en) | A kind of method of servicing bridges monitoring information security evaluation | |
CN115688555B (en) | Bridge life prediction method | |
CN110262417A (en) | A kind of production equipment failure predication diagnostic method | |
CN116910879A (en) | Cable force abnormality diagnosis method and device for bridge stay cable under random vehicle-mounted action | |
CN117094180A (en) | Digital twin model quantization manufacturing system | |
CN116663126A (en) | Bridge temperature effect prediction method based on channel attention BiLSTM model | |
CN111160490A (en) | Deep learning dangerous rock deformation prediction method and device based on multiple time sequences | |
CN111062827A (en) | Engineering supervision method based on artificial intelligence mode |
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 |