CN112287586A - Rapid reliability assessment method based on medium and small bridge damage identification result - Google Patents
Rapid reliability assessment method based on medium and small bridge damage identification result Download PDFInfo
- Publication number
- CN112287586A CN112287586A CN202011221880.7A CN202011221880A CN112287586A CN 112287586 A CN112287586 A CN 112287586A CN 202011221880 A CN202011221880 A CN 202011221880A CN 112287586 A CN112287586 A CN 112287586A
- Authority
- CN
- China
- Prior art keywords
- damage
- bridge
- medium
- reliability
- small
- 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
- 238000000034 method Methods 0.000 title claims abstract description 38
- 238000011156 evaluation Methods 0.000 claims abstract description 20
- 238000010801 machine learning Methods 0.000 claims abstract description 11
- 238000013507 mapping Methods 0.000 claims abstract description 10
- 230000009467 reduction Effects 0.000 claims abstract description 7
- 238000012549 training Methods 0.000 claims abstract description 5
- 238000013461 design Methods 0.000 claims abstract description 4
- 238000001514 detection method Methods 0.000 claims abstract description 4
- 238000005452 bending Methods 0.000 claims description 3
- 230000006870 function Effects 0.000 claims description 3
- 238000004215 lattice model Methods 0.000 claims description 3
- 239000007787 solid Substances 0.000 claims description 3
- 238000005303 weighing Methods 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 6
- 238000012360 testing method Methods 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/23—Design optimisation, verification or simulation using finite element methods [FEM] or finite difference methods [FDM]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/14—Force analysis or force optimisation, e.g. static or dynamic forces
Abstract
The invention discloses a quick reliability evaluation method based on a medium and small bridge damage identification result, which comprises the following steps of: establishing an initial finite element model of the medium and small bridge based on bridge design parameters; selecting probability distribution of bridge resistance according to bridge field detection results or historical statistical data; establishing a random traffic load model; designing various bridge damage working conditions based on rigidity reduction, and covering all potential damage positions and multi-stage representative damage degrees; establishing a corresponding finite element model based on the initial model by adjusting corresponding model parameters; reliability evaluation is carried out to obtain a reliability sample corresponding to the damage working condition; training a machine learning algorithm, and establishing a mapping relation between the damage working condition and the reliability index. The method can quickly evaluate the reliability of the medium and small bridges based on the measured data and the results of the existing bridge damage identification method, so that the results of the existing damage identification method have guiding significance, and meanwhile, the potential damage of the medium and small bridges can be found more timely, and accidents are avoided.
Description
Technical Field
The invention relates to the field of bridge evaluation methods, in particular to a quick reliability evaluation method based on a medium and small bridge damage identification result.
Background
Because the performance of the medium and small bridges is gradually reduced under the action of the load of the upper vehicle reciprocating for a long time, the safety of upper traffic personnel and vehicles is guaranteed in order to avoid the occurrence of potential accidents, and the medium and small bridges need to be evaluated in real time. However, the current common method is completed through a load test, and the practice shows that the load test has low development efficiency and long operation time, needs to interrupt traffic, and can seriously affect normal vehicle passing. Therefore, the bridge rapid damage identification assessment based on health monitoring is particularly necessary. At present, many scholars have developed a lot of damage identification algorithms, but the existing damage identification algorithms can only obtain the damage position and degree preliminarily, and cannot directly explain the bridge condition, so that a basis is provided for the later maintenance of the bridge. Moreover, the existing bridge evaluation method is based on the reliability theory, a large amount of finite element random analysis is often needed, and the analysis time is long, so that the evaluation result is difficult to give in time.
Disclosure of Invention
The purpose of the invention is as follows: in order to solve the technical problems, the invention provides a quick reliability evaluation method based on a medium and small bridge damage identification result.
The technical scheme is as follows: the invention discloses a quick reliability evaluation method based on a medium and small bridge damage identification result, which comprises the following steps of:
step 1: establishing an initial finite element model of the medium and small bridge based on bridge design parameters;
step 2: selecting probability distribution of bridge resistance according to bridge field detection results or historical statistical data;
and step 3: establishing a random traffic load model according to a random traffic sample collected by dynamic weighing equipment;
and 4, step 4: designing various bridge damage working conditions based on rigidity reduction according to the structure type and damage identification result of the medium and small bridges, and covering all potential damage positions and multi-stage representative damage degrees;
and 5: establishing a corresponding finite element model based on the initial model by adjusting corresponding model parameters according to the designed damage condition;
step 6: based on probability distribution of bridge resistance and a random traffic load model, reliability evaluation is carried out by combining bridge finite element models corresponding to all damage working conditions to obtain reliability samples corresponding to the damage working conditions;
and 7: training a machine learning algorithm by using the damage working condition and reliability samples, and establishing a mapping relation between the damage working condition and reliability indexes;
and 8: based on the mapping relation between the damage working condition and the reliability index, and in combination with a damage identification method, the reliability of the medium and small bridges can be quickly evaluated through a damage identification result.
Preferably, the finite element model in step 1 is a solid element based model or a beam lattice model.
Preferably, the bridge resistance in step 2 refers to midspan bending resistance bearing capacity, fatigue limit and midspan deflection limit.
Preferably, the damage identification method in the step refers to a method capable of realizing damage positioning and quantifying functions in mainstream, and the position and the degree of the rigidity reduction of the bridge can be obtained preliminarily.
Preferably, the damage identification method is a frequency domain method or a time domain method.
Preferably, the machine learning algorithm in the step 7 is an algorithm with mapping capability, the input parameters of the algorithm are the position and degree of the damage of the bridge, and the output parameters are the corresponding reliability.
Preferably, in step 8, a damaged area and a damaged position of the bridge are obtained through a damage recognition algorithm, and then the recognition result is input into a trained machine learning algorithm to obtain a reliability evaluation result.
Has the advantages that: the method can quickly evaluate the reliability of the medium and small bridges based on the measured data and the results of the existing bridge damage identification method, so that the results of the existing damage identification method have guiding significance, and meanwhile, the potential damage of the medium and small bridges can be found more timely, and accidents are avoided.
Drawings
FIG. 1 is a schematic flow chart illustrating steps of a method for evaluating the fast reliability based on the identification result of the medium and small bridge damage according to the present invention;
FIG. 2 is a schematic diagram of a finite element model of a medium and small bridge;
FIG. 3 is a schematic diagram of random traffic flow;
FIG. 4 is a schematic diagram of a model vehicle type distribution of a random traffic flow;
FIG. 5 is a schematic diagram of vehicle type categories of a stochastic traffic flow model;
FIG. 6 is a schematic representation of a stochastic traffic flow model axle redistribution;
FIG. 7 is a schematic diagram of the distribution of random traffic flow model traffic distances;
FIG. 8 is a schematic diagram of a machine learning algorithm training process;
fig. 9 is a flow chart of the method for evaluating the fast reliability based on the identification result of the medium and small bridge damages according to the present invention.
Detailed Description
The invention will be further explained with reference to the drawings.
As shown in fig. 1 to 3, the method for evaluating the rapid reliability based on the identification result of the medium and small bridge damages includes the following steps:
step 1: establishing an initial finite element model of the medium and small bridge based on bridge design parameters; as shown in fig. 2, the finite element model may be a solid element based model or a beam lattice model.
Step 2: selecting probability distribution of bridge resistance according to bridge field detection results or historical statistical data; bridge resistance refers to midspan bending resistance bearing capacity, fatigue limit and midspan deflection limit.
And step 3: establishing a random traffic load model according to a random traffic sample (figure 3) collected by the dynamic weighing equipment; as shown in fig. 4-7, the random traffic flow model should consider the probability distribution of random parameters such as vehicle type, axle weight, and vehicle distance.
And 4, step 4: according to the structure type of the medium and small bridges and the recognition result of the existing damage recognition method, various bridge damage working conditions are designed based on rigidity reduction, and all potential damage positions and multi-stage representative damage degrees are covered; the existing damage identification method refers to a method which can realize damage positioning and quantifying functions in mainstream, such as a frequency domain method and a time domain method, and can preliminarily obtain the position and the degree of bridge rigidity reduction.
And 5: establishing a corresponding finite element model based on the initial model by adjusting corresponding model parameters according to the designed damage condition;
step 6: based on probability distribution of bridge resistance and a random traffic load model, reliability evaluation is carried out by combining bridge finite element models corresponding to all damage working conditions to obtain reliability samples corresponding to the damage working conditions; the reliability evaluation needs to consider the load capacity limit state and the normal use limit state.
And 7: as shown in fig. 8, training a machine learning algorithm by using the damage condition and reliability samples to establish a mapping relationship between the damage condition and the reliability index; the machine learning algorithm may select an algorithm that supports vector regression, neural networks, etc. with mapping capabilities. The input parameters of the algorithm are the position and the degree of the damage of the bridge, and the output parameters are the corresponding reliability.
And 8: based on the mapping relation between the damage working condition and the reliability index, the reliability of the medium and small bridges can be rapidly evaluated through the damage identification result by combining the existing damage identification method. Specifically, a damaged area and a damaged position of the bridge are obtained through a damage recognition algorithm, and then the recognition result is input into a trained machine learning algorithm to obtain a reliability evaluation result, as shown in fig. 9.
Claims (7)
1. A quick reliability assessment method based on a medium and small bridge damage identification result is characterized by comprising the following steps:
step 1: establishing an initial finite element model of the medium and small bridge based on bridge design parameters;
step 2: selecting probability distribution of bridge resistance according to bridge field detection results or historical statistical data;
and step 3: establishing a random traffic load model according to a random traffic sample collected by dynamic weighing equipment;
and 4, step 4: designing various bridge damage working conditions based on rigidity reduction according to the structure type and damage identification result of the medium and small bridges, and covering all potential damage positions and multi-stage representative damage degrees;
and 5: according to the designed damage condition, establishing a corresponding finite element model based on the initial model by adjusting corresponding rigidity parameters in the initial finite element model;
step 6: based on probability distribution of bridge resistance and a random traffic load model, reliability evaluation is carried out by combining bridge finite element models corresponding to all damage working conditions to obtain reliability samples corresponding to the damage working conditions;
and 7: training a machine learning algorithm by using the damage working condition and reliability samples, and establishing a mapping relation between the damage working condition and reliability indexes;
and 8: based on the mapping relation between the damage working condition and the reliability index, and in combination with a damage identification method, the reliability of the medium and small bridges can be quickly evaluated through a damage identification result.
2. The method for rapid reliability evaluation based on the identification result of the medium and small bridge damage according to claim 1, characterized in that: the finite element model in the step 1 is a model based on solid units or a beam lattice model.
3. The method for rapid reliability evaluation based on the identification result of the medium and small bridge damage according to claim 1, characterized in that: and in the step 2, the bridge resistance refers to midspan bending resistance bearing capacity, fatigue limit and midspan deflection limit value.
4. The method for rapid reliability evaluation based on the identification result of the medium and small bridge damage according to claim 1, characterized in that: in the step, the damage identification method refers to a method capable of realizing damage positioning and quantifying functions in mainstream, and the position and the degree of rigidity reduction of the bridge can be obtained preliminarily.
5. The method for rapidly evaluating the reliability based on the identification result of the medium and small bridge damages as claimed in claim 4, wherein: the damage identification method is a frequency domain method or a time domain method.
6. The method for rapid reliability evaluation based on the identification result of the medium and small bridge damage according to claim 1, characterized in that: in the step 7, the machine learning algorithm is an algorithm with mapping capability, the input parameters of the algorithm are the position and the degree of the damage of the bridge, and the output parameters are the corresponding reliability.
7. The method for rapid reliability evaluation based on the identification result of the medium and small bridge damage according to claim 1, characterized in that: in step 8, firstly, a damaged area and a damaged position of the bridge are obtained through a damage recognition algorithm, and then the recognition result is input into a trained machine learning algorithm to obtain a reliability evaluation result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011221880.7A CN112287586B (en) | 2020-11-05 | 2020-11-05 | Quick reliability assessment method based on medium-and-small bridge damage recognition result |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011221880.7A CN112287586B (en) | 2020-11-05 | 2020-11-05 | Quick reliability assessment method based on medium-and-small bridge damage recognition result |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112287586A true CN112287586A (en) | 2021-01-29 |
| CN112287586B CN112287586B (en) | 2024-01-30 |
Family
ID=74351411
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011221880.7A Active CN112287586B (en) | 2020-11-05 | 2020-11-05 | Quick reliability assessment method based on medium-and-small bridge damage recognition result |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112287586B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112818577A (en) * | 2021-02-01 | 2021-05-18 | 青岛理工大学 | Method for identifying post-fire damage of laminated beam based on deep learning theory |
| CN117291072A (en) * | 2023-09-20 | 2023-12-26 | 宁波朗达工程科技有限公司 | Bridge damage identification method |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106556498A (en) * | 2016-10-31 | 2017-04-05 | 石家庄铁道大学 | Damage Identification Methods for Bridge Structures and system |
| WO2017202139A1 (en) * | 2016-05-26 | 2017-11-30 | 东南大学 | Bridge damage identification method based on long-gauge-length strain influence envelope |
-
2020
- 2020-11-05 CN CN202011221880.7A patent/CN112287586B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2017202139A1 (en) * | 2016-05-26 | 2017-11-30 | 东南大学 | Bridge damage identification method based on long-gauge-length strain influence envelope |
| CN106556498A (en) * | 2016-10-31 | 2017-04-05 | 石家庄铁道大学 | Damage Identification Methods for Bridge Structures and system |
Non-Patent Citations (2)
| Title |
|---|
| 刘扬;鲁乃唯;邓扬;: "基于实测车流的钢桥面板疲劳可靠度评估", 中国公路学报, no. 05 * |
| 肖新辉;鲁乃唯;刘扬;: "随机车流下公路钢桥疲劳可靠度分析", 浙江大学学报(工学版), no. 09 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112818577A (en) * | 2021-02-01 | 2021-05-18 | 青岛理工大学 | Method for identifying post-fire damage of laminated beam based on deep learning theory |
| CN112818577B (en) * | 2021-02-01 | 2022-11-11 | 青岛理工大学 | Method for identifying post-fire damage of laminated beam based on deep learning theory |
| CN117291072A (en) * | 2023-09-20 | 2023-12-26 | 宁波朗达工程科技有限公司 | Bridge damage identification method |
| CN117291072B (en) * | 2023-09-20 | 2024-03-15 | 宁波朗达工程科技有限公司 | Bridge damage identification method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112287586B (en) | 2024-01-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103793854B (en) | The overhead transmission line operation risk informatization evaluation method that Multiple Combination is optimized | |
| CN100470416C (en) | Power plant thermal equipment intelligent state diagnosing and analyzing system | |
| CN108873859B (en) | Bridge type grab ship unloader fault prediction model method based on improved association rule | |
| CN112287586B (en) | Quick reliability assessment method based on medium-and-small bridge damage recognition result | |
| CN112785091A (en) | Method for performing fault prediction and health management on oil field electric submersible pump | |
| CN110865924B (en) | Health degree diagnosis method and health diagnosis framework for internal server of power information system | |
| CN116651971B (en) | Online detection method and system for automobile stamping die | |
| CN106656669A (en) | Equipment parameter abnormity detection system and method based on self-adaptive setting of threshold | |
| CN106682159A (en) | Threshold configuration method | |
| CN114266289A (en) | Complex equipment health state assessment method | |
| CN116720324A (en) | Traction substation key equipment fault early warning method and system based on prediction model | |
| CN115270238A (en) | Dynamic load-based bridge static behavior prediction method | |
| CN109408998B (en) | Fatigue life evaluation method by rapidly acquiring stress spectrum based on sample continuous increment | |
| CN113742993A (en) | Method, device, equipment and storage medium for predicting life loss of dry-type transformer | |
| CN117191147A (en) | Flood discharge dam water level monitoring and early warning method and system | |
| CN105741184A (en) | Transformer state evaluation method and apparatus | |
| CN110533213A (en) | Transmission line of electricity defect Risk Modeling and its prediction technique based on support vector machines | |
| CN113392576A (en) | Staying balloon main cable tension state assessment early warning method | |
| CN111061191B (en) | Distributed oil-gas storage tank remote operation and maintenance method | |
| CN111382946B (en) | Autonomous evaluation method and system for health state of equipment and industrial internet equipment | |
| CN114429032A (en) | Bridge health online intelligent monitoring system | |
| Li et al. | Methods for the rapid detection of boundary condition variations in structural systems | |
| CN111931407A (en) | Structure reliability evaluation prediction method and system based on long-term monitoring data | |
| CN117473302B (en) | Method, device, equipment and storage medium for testing structural reliability of automobile parts | |
| CN115793516B (en) | Control system and method for intelligent bridge movement detection |
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 |