CN113111416A - Data-driven reinforced concrete structure earthquake damage quantitative evaluation method - Google Patents
Data-driven reinforced concrete structure earthquake damage quantitative evaluation method Download PDFInfo
- Publication number
- CN113111416A CN113111416A CN202110372196.7A CN202110372196A CN113111416A CN 113111416 A CN113111416 A CN 113111416A CN 202110372196 A CN202110372196 A CN 202110372196A CN 113111416 A CN113111416 A CN 113111416A
- Authority
- CN
- China
- Prior art keywords
- damage
- linear
- structural
- earthquake damage
- reinforced concrete
- 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.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/13—Architectural design, e.g. computer-aided architectural design [CAAD] related to design of buildings, bridges, landscapes, production plants or roads
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Geometry (AREA)
- Theoretical Computer Science (AREA)
- Computer Hardware Design (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Architecture (AREA)
- Civil Engineering (AREA)
- Structural Engineering (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
- Geophysics And Detection Of Objects (AREA)
Abstract
The invention relates to a data-driven reinforced concrete structure earthquake damage quantitative evaluation method, which comprises the following steps of: 1) identifying an inversion structure linear reference model to obtain structure linear rigidity; 2) calculating the predicted reference response x of the structural linear reference model under the same seismic excitation as the actual structurer(ii) a 3) Acquiring a real response x of a structure through structure health monitoring, and calculating a time domain tracking error r; 4) constructing a structural earthquake damage model, and calculating related damage parameters; 5) and calculating a damage index DI value according to the structural earthquake damage model, and evaluating the structural earthquake damage condition according to the damage index DI value. Compared with the prior art, the method has the advantages of good economy, no need of predicting the key nonlinear behavior characteristics of the structure in advance, adaptability, accurate real-time evaluation and the like.
Description
Technical Field
The invention relates to the field of civil engineering structure health monitoring and earthquake damage assessment, in particular to a reinforced concrete structure earthquake damage quantitative assessment method based on health monitoring data driving.
Background
The engineering seismic design based on ductility allows the structure to enter a nonlinear state under strong earthquake, namely allows the structure to generate earthquake damage, and brings requirements for the safety and performance evaluation of the earthquake damage structure. In order to reasonably evaluate seismic damage, a reasonable seismic damage evaluation model is required. The existing model mostly considers two performance indexes of deformation and hysteretic energy consumption, corresponds to the peak value and the cumulative effect of structural damage, and combines priori knowledge to construct a normalization index form on the basis.
However, such earthquake damage models based on physical and mechanical concepts can be directly applied to numerical simulation and experimental research with complete information, and are limited by uncertainty of numerical modeling and incompleteness of observed information when facing large-scale structural vibration table tests and actual structural strong earthquake observations. Therefore, a classical damage assessment model in the field of seismic engineering is difficult to be directly applied to the assessment of nonlinear damage and seismic behavior of an in-service engineering structure.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provide a quantitative evaluation method for earthquake damage of a reinforced concrete structure based on data driving, which utilizes structural health monitoring data to realize quantitative evaluation of the structural damage under the action of an earthquake under the condition that the key nonlinear response of the structure cannot be predicted in advance.
The purpose of the invention can be realized by the following technical scheme:
a data-driven reinforced concrete structure earthquake damage quantitative evaluation method comprises the following steps:
1) based on the reinforced concrete structure health monitoring data, according to the structure real mechanical behavior, identifying an inverse structure linear reference model, and obtaining the structure linear rigidity Klinear；
2) Calculating the predicted reference response x of the structural linear reference model under the same seismic excitation as the actual structurer；
3) Acquiring a real response x of a structure through structure health monitoring, and calculating a time domain tracking error r;
4) calculating the root mean square value r of the time domain tracking error r at any timeRMSPredicted reference response xrRoot mean square value of
Actual maximum responseCorresponding equivalent stiffness KeffAnd the hysteresis loop linear regression coefficient R corresponding to the actual maximum response2And constructing a structural seismic damage model;
5) and calculating a damage index DI value according to the structural earthquake damage model, and evaluating the structural earthquake damage condition according to the damage index DI value.
In the step 1), a structural linear reference model can be constructed by using the minor earthquake observation data and the system identification technology to describe the initial earthquake resistant behavior and the linear state of the in-service structure, and the method specifically comprises the following steps:
under the working condition of small earthquake, the hysteresis behavior of the structure is in a linear state, a hysteresis curve in the linear state is fitted, a structural linear reference model in a healthy state is established, and the structural linear rigidity K is obtained through recognitionlinear。
In the step 2), the reference response x is predictedrAnd calculating the response acquisition under the same seismic excitation through the linear structure identified by the system.
In the step 2), under the condition of the same seismic load input or acting force, the prediction reference response is obtained by utilizing the known reference model to calculate
Corresponding to displacement, velocity and acceleration, respectively.
In the step 3), the real response is obtained by the structural health monitoring means
Respectively corresponding to displacement, speed and acceleration, and the expression of the time domain tracking error r is as follows:
the time domain tracking error r can better reflect the development and accumulation of the hysteresis state of the structure.
In the step 4), the root mean square value r of the time domain tracking error rRMSAnd reflecting hysteretic energy consumption characteristics corresponding to the structural earthquake damage.
In the step 4), the structural earthquake damage model index is in an index form of normalization of a peak value term and an accumulation term, and the model expression is as follows:
wherein the content of the first and second substances,
is the damage index DI value, alphad、βdRespectively, a model parameter determined according to the actual structure, ndAre control parameters.
The model parameter alphadAnd betadThe relationship of (1) is:
αd+βd＝1。
for common reinforced concrete structure, the model parameter alphadIs in a range of 0.8 to 0.9, and controls a parameter ndIs 2.5.
Introducing a hysteresis loop linear regression coefficient R into a structural seismic damage model2The method is used for increasing the reliability of the evaluation result, regresses the linearity degree of the hysteresis curve of a single period in which the peak value response is positioned before the calculation moment, and can obtain the hysteresis loop linear regression coefficient R corresponding to the actual maximum response2The loss peak effect is directly reflected, and when the system state is in a strict linear state or the structure shows a linear response, R is2＝1.0。
In the structural earthquake damage model, the equivalent stiffness K corresponding to the actual maximum responseeffIn particular to the secant rigidity corresponding to the maximum response point of the structure appearing before the evaluation moment.
In the step 5), according to the result of the damage index DI
Evaluating structural earthquakesThe damage condition is specifically:
the finally calculated damage index DI value range is 0-1, and the larger the value is, the more serious the damage of the reaction structure is.
Compared with the prior art, the invention has the following advantages:
firstly, the invention can utilize the existing economic structure health detection system to obtain data, can carry out quantitative evaluation on the earthquake damage structure without predicting the key nonlinear behavior characteristics (such as yield force, ultimate deformation and the like) of the structure in advance, and can be widely applied to earthquake damage evaluation of real in-service structures.
The method can track the structural earthquake damage in the time domain, more accurately evaluate the structural damage at each moment, and provide important reference information for the post-earthquake safety and recoverability of the structure.
The method has adaptivity to model response, does not depend on one response, can evaluate the response type obtained by the structure, and has wide application range.
And fourthly, identifying the inversion structure reference model by utilizing the existing economic and reasonable structure health monitoring technology under the condition of intact structure state. When the structure enters a nonlinear state under the action of an earthquake, the nonlinear behavior of the structure can be tracked, the damage development condition of the structure can be further evaluated, and the characteristic of the nonlinear behavior of the structure does not need to be predicted.
The method can be applied to any structural hierarchy and used for evaluating the structural nonlinear hysteresis behavior in any response mode.
Sixthly, due to the fact that measurement errors may exist in structural response observation, uncertainty may exist in structural rigidity degradation through single maximum response point evaluation, and an evaluation parameter R is further introduced when a structural earthquake damage model is built2The reliability of the evaluation result is increased.
Drawings
FIG. 1 is a flow chart of the method of the present invention.
Fig. 2 is a schematic view of a monitoring sensor arrangement in an embodiment of the invention.
Fig. 3 is a schematic diagram of a structural hysteresis curve and a maximum displacement hysteresis loop in the embodiment of the present invention, wherein fig. 3a is a linear state and fig. 3b is a non-linear state.
Fig. 4 is a graph of the development of the structure hysteresis behavior and the time-domain tracking effect of the damage index in the embodiment of the present invention, where fig. 4a is the 0-30.6 second structure hysteresis behavior, fig. 4b is the 30.6-32.2 second structure hysteresis behavior, fig. 4c is the 32.2-43.5 second structure hysteresis behavior, fig. 4d is the 43.5-106.4 second structure hysteresis behavior, and fig. 4e is the intra-domain tracking effect at the structural damage index.
Detailed Description
The invention is described in detail below with reference to the figures and specific embodiments.
Examples
With the popularization and application of the health monitoring technology in the field of seismic engineering in recent years, a monitoring data driving method can provide necessary and valuable information for post-earthquake damage assessment, and the safety of the structure can be evaluated by tracking the difference and the change of the real earthquake-resistant behavior of the structure by comparing structural response data under the excitation of earthquakes with different intensities.
In view of the factors, the invention provides a data-driven reinforced concrete structure earthquake damage quantitative evaluation method. By tracking the difference between the structural nonlinear response and the reference response under the seismic sequence, the effects of quantitative evaluation and tracking on structural seismic damage are achieved. The method does not need to predict the nonlinear behavior of the structure, can acquire data by using an economical structure health monitoring system, has self-adaptability to the response type of the structure, and can be used for evaluating the performance of the seismic damage structure in the actual engineering.
As shown in fig. 1, the invention provides a data-driven quantitative evaluation method for earthquake damage of a reinforced concrete structure, which comprises the following steps:
the method comprises the following steps: fig. 2 is a diagram showing arrangement of monitoring points in an embodiment of a reinforced concrete column, in which a member is divided into a plurality of subsections by acceleration sensors distributed along the column height, a horizontal inertial force borne by each subsection is calculated according to the mass of the corresponding subsection and an actually measured absolute acceleration response, the accumulated parts can be equivalent to a base shear force of the RC column, and meanwhile, a transverse displacement of the column top can be determined by measuring a horizontal displacement of a top mass block, and a base shear force-column top displacement hysteresis curve of the RC column in the embodiment can be obtained after calculation;
step two: under the working condition of small earthquake, the hysteresis behavior of the member is in a linear state, fitting analysis is carried out on the hysteresis curve in the linear state, a reference model of the structural health state is established, and the linear state rigidity is obtained through identification and used as the structural reference model rigidity Klinear；
Step three; for the subsequent earthquake working condition, the same earthquake excitation is input into the linear reference model to obtain the corresponding reference response, in the embodiment, the substrate shear force F under the strong earthquake working condition is inputvTime series of (2), i.e. obtaining a reference displacement response xrThe time series of (c) then has:
xr＝Fv/Klinear；
step four: comparing the real displacement response x of the structure under strong earthquake acquired by the health monitoring system with the reference displacement response xrObtaining a structural damage assessment key parameter, namely a time sequence of a tracking error r;
step five: calculating the root mean square value r of the tracking error r under the structure seismic excitationRMSRoot mean square value of response x to measured structure
Step six: calculating secant stiffness of the point where the maximum response of the structure is located before the evaluation moment, and taking the secant stiffness as equivalent stiffness KeffThe hysteresis loop regression coefficient R corresponding to the actual maximum response2Fig. 3 shows an equivalent stiffness and hysteresis loop selection method corresponding to the maximum displacement in an embodiment, and the results of calculating each important parameter in the structural damage model obtained in the embodiment in the linear and nonlinear states are shown in table 1;
TABLE 1 important parameters in the structural Damage model in Linear and non-Linear states
Step seven: and calculating the damage index DI according to the structural earthquake damage model, wherein the calculation formula of the damage index DI is as follows:
for the reinforced concrete member in this embodiment, α is takend＝0.9，βd＝0.1，ndWhen the linear operating condition and the nonlinear operating condition are calculated respectively, the evaluation results shown in table 2 can be obtained, and the evaluation results have good correspondence with the development of the structural nonlinear behavior.
TABLE 2 evaluation results of Linear and non-Linear conditions
| Linear regime | Non-linear regime | |
| DI value of Damage index | 0.01 | 0.51 |
Step eight: for the third step to the seventh step, the time domain segmentation can be performed on the acquired structural response data, the damage indexes at different time points are calculated, and the time sequence of the damage indexes is obtained. The time sequence can reflect the development condition of the structural damage and better master the structural safety information. FIG. 4 shows the time-domain tracking effect of structural damage and corresponding structure hysteresis behavior in an embodiment.
According to the invention, the existing economic and reasonable health monitoring technology is utilized, firstly, the inversion structure reference model is identified under the condition that the structure state is intact, when the structure enters the nonlinear state under the action of earthquake, the structure nonlinear behavior can be tracked, the response difference between the damaged structure and the linear reference model is compared, the structure damage is further evaluated, and the structure nonlinear behavior characteristic does not need to be predicted. The method can be applied to any structural level, evaluates the structural nonlinear hysteresis behavior in any response mode, and has self-adaptability to response.
The above are only specific steps of the present invention and specific descriptions for possible embodiments of the present invention, and do not limit the scope of the present invention in any way; the method can be expanded and applied to the field of seismic damage quantitative evaluation of other structures, and all technical schemes formed by adopting equivalent transformation or equivalent replacement fall within the protection scope of the invention.
Claims (10)
1. A data-driven reinforced concrete structure earthquake damage quantitative evaluation method is characterized by comprising the following steps:
1) based on the reinforced concrete structure health monitoring data, according to the structure real mechanical behavior, identifying an inverse structure linear reference model, and obtaining the structure linear rigidity Klinear；
2) Calculating the predicted reference response x of the structural linear reference model under the same seismic excitation as the actual structurer；
3) Acquiring a real response x of a structure through structure health monitoring, and calculating a time domain tracking error r;
4) calculating the root mean square value r of the time domain tracking error r at any timeRMSPredicted reference response xrRoot mean square value of xr RMSEquivalent stiffness K corresponding to actual maximum responseeffAnd the hysteresis loop linear regression coefficient R corresponding to the actual maximum response2And constructing a structural seismic damage model;
5) and calculating a damage index DI value according to the structural earthquake damage model, and evaluating the structural earthquake damage condition according to the damage index DI value.
2. The data-driven reinforced concrete structure earthquake damage quantitative evaluation method according to claim 1, wherein in the step 1), under a small earthquake condition, the hysteretic behavior of the structure is in a linear state, a hysteretic curve in the linear state is fitted, a structural linear reference model in a healthy state is established, and the structural linear stiffness K is obtained through identificationlinear。
3. The method for quantitatively evaluating the earthquake damage of the reinforced concrete structure based on the data driving as claimed in claim 1, wherein in the step 2), the reference response x is predictedrAnd calculating the response acquisition under the same seismic excitation through the linear structure identified by the system.
4. The method for quantitatively evaluating the earthquake damage of the reinforced concrete structure based on the data driving as recited in claim 1, wherein in the step 3), the expression of the time-domain tracking error r is as follows:
r＝xr-x。
5. the method for quantitatively evaluating the earthquake damage of the reinforced concrete structure based on the data driving as claimed in claim 1, wherein in the step 4), the expression of the structural earthquake damage model is as follows:
wherein the content of the first and second substances,
is the damage index DI value, alphad、βdRespectively, a model parameter determined according to the actual structure, ndAre control parameters.
6. The method for quantitatively evaluating the earthquake damage of the reinforced concrete structure based on the data driving as recited in claim 5, wherein the model parameter α isdAnd betadThe relationship of (1) is:
αd+βd＝1。
7. the data-driven quantitative evaluation method for earthquake damage to a reinforced concrete structure according to claim 6, wherein the model parameter α isdIs in a range of 0.8 to 0.9, and controls a parameter ndIs 2.5.
8. The method for quantitatively evaluating the earthquake damage of the reinforced concrete structure based on the data driving as recited in claim 5, wherein a hysteresis loop linear regression coefficient R is introduced into the structural earthquake damage model2To increase the reliability of the evaluation result, R is set when the system state is strictly linear or the structure shows linear response2＝1.0。
9. The method for quantitatively evaluating the earthquake damage of the reinforced concrete structure based on the data driving as recited in claim 5, wherein in the structural earthquake damage model, the equivalent stiffness K corresponding to the actual maximum responseeffIn particular to the secant rigidity corresponding to the maximum response point of the structure appearing before the evaluation moment.
10. The method for quantitatively evaluating the earthquake damage of the reinforced concrete structure based on the data driving as claimed in claim 1, wherein in the step 5), the result according to the damage index DI is used as the basis
Evaluating the structural earthquake damage condition, specifically:
the finally calculated damage index DI value range is 0-1, and the larger the value is, the more serious the damage of the reaction structure is.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110372196.7A CN113111416A (en) | 2021-04-07 | 2021-04-07 | Data-driven reinforced concrete structure earthquake damage quantitative evaluation method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110372196.7A CN113111416A (en) | 2021-04-07 | 2021-04-07 | Data-driven reinforced concrete structure earthquake damage quantitative evaluation method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113111416A true CN113111416A (en) | 2021-07-13 |
Family
ID=76714274
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110372196.7A Pending CN113111416A (en) | 2021-04-07 | 2021-04-07 | Data-driven reinforced concrete structure earthquake damage quantitative evaluation method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113111416A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114781042A (en) * | 2022-05-11 | 2022-07-22 | 清华大学 | Optimization algorithm-based method and device for inverting time course of structural displacement under earthquake |
| CN117216846A (en) * | 2023-09-12 | 2023-12-12 | 华南理工大学 | Reinforced concrete member hysteresis curve prediction method, system, equipment and medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103678937A (en) * | 2013-12-29 | 2014-03-26 | 中国地震局工程力学研究所 | Method for evaluating overall earthquake damage level of reinforced concrete frame structure based on equivalent single-degree-of-freedom system |
| CN103911942A (en) * | 2014-04-14 | 2014-07-09 | 广西大学 | Anti-seismic capacity evaluation method for steel pipe concrete arch bridge based on damage and failure |
| CN105528520A (en) * | 2015-12-09 | 2016-04-27 | 哈尔滨工业大学 | Main shock-aftershock sequence-based method for estimating damage index |
| CN109325308A (en) * | 2018-10-17 | 2019-02-12 | 江苏开放大学（江苏城市职业学院） | Reinforced concrete hollow shear wall seismic Damage evaluation method based on energy transfer rate |
| CN110414066A (en) * | 2019-07-02 | 2019-11-05 | 东南大学 | Armored concrete damage model approximating method based on genetic algorithm |
-
2021
- 2021-04-07 CN CN202110372196.7A patent/CN113111416A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103678937A (en) * | 2013-12-29 | 2014-03-26 | 中国地震局工程力学研究所 | Method for evaluating overall earthquake damage level of reinforced concrete frame structure based on equivalent single-degree-of-freedom system |
| CN103911942A (en) * | 2014-04-14 | 2014-07-09 | 广西大学 | Anti-seismic capacity evaluation method for steel pipe concrete arch bridge based on damage and failure |
| CN105528520A (en) * | 2015-12-09 | 2016-04-27 | 哈尔滨工业大学 | Main shock-aftershock sequence-based method for estimating damage index |
| CN109325308A (en) * | 2018-10-17 | 2019-02-12 | 江苏开放大学（江苏城市职业学院） | Reinforced concrete hollow shear wall seismic Damage evaluation method based on energy transfer rate |
| CN110414066A (en) * | 2019-07-02 | 2019-11-05 | 东南大学 | Armored concrete damage model approximating method based on genetic algorithm |
Non-Patent Citations (1)
| Title |
|---|
| 单伽锃: "《基于监测数据的结构地震损伤追踪与量化评估方法》", 《工程力学》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114781042A (en) * | 2022-05-11 | 2022-07-22 | 清华大学 | Optimization algorithm-based method and device for inverting time course of structural displacement under earthquake |
| CN117216846A (en) * | 2023-09-12 | 2023-12-12 | 华南理工大学 | Reinforced concrete member hysteresis curve prediction method, system, equipment and medium |
| CN117216846B (en) * | 2023-09-12 | 2024-04-19 | 华南理工大学 | Reinforced concrete member hysteresis curve prediction method, system, equipment and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Avci et al. | A review of vibration-based damage detection in civil structures: From traditional methods to Machine Learning and Deep Learning applications | |
| Eftekhar Azam et al. | Damage detection in structural systems utilizing artificial neural networks and proper orthogonal decomposition | |
| CN109583570B (en) | Method for determining abnormal data source of bridge health monitoring system based on deep learning | |
| Yuen et al. | Two-stage structural health monitoring approach for phase I benchmark studies | |
| Niyirora et al. | Intelligent damage diagnosis in bridges using vibration-based monitoring approaches and machine learning: a systematic review | |
| CN112528365B (en) | Method for predicting healthy evolution trend of underground infrastructure structure | |
| CN113111416A (en) | Data-driven reinforced concrete structure earthquake damage quantitative evaluation method | |
| Fathnejat et al. | An efficient two-stage approach for structural damage detection using meta-heuristic algorithms and group method of data handling surrogate model | |
| CN103884776B (en) | A kind of method improving random damage Locating Vector Methods monitoring result accuracy | |
| CN115048998B (en) | Cable-stayed bridge group cable force abnormity identification and positioning method based on monitoring data | |
| Entezami et al. | Improving feature extraction via time series modeling for structural health monitoring based on unsupervised learning methods | |
| Alves et al. | An automated vibration-based structural damage localization strategy using filter-type feature selection | |
| CN110728089B (en) | Large-span bridge stay cable structure damage diagnosis method based on BOTDA technology | |
| CN107246944B (en) | A kind of Structural Damage Identification based on statistical moment theory | |
| CN110427716B (en) | Statistical moment-based high-rise structure model-free damage identification method | |
| De Simone et al. | Predictive maintenance and structural health monitoring via IoT system | |
| Yazdanpanah et al. | Seismic response prediction of RC bridge piers through stacked long short-term memory network | |
| Jiang et al. | Structural stiffness identification of traditional mortise-tenon joints based on statistical process control chart | |
| Bandara | Damage identification and condition assessment of building structures using frequency response functions and neural networks | |
| Chalabi et al. | Nonmodel rapid seismic assessment of eccentrically braced frames incorporating masonry infills using machine learning techniques | |
| CN116822146B (en) | Flexible protection system intelligent rapid calculation method based on multilayer perceptron | |
| CN117272202A (en) | Dam deformation abnormal value identification method and system | |
| Zhang et al. | Post-earthquake structural damage assessment and damage state evaluation for RC structures with experimental validation | |
| CN116663126A (en) | Bridge temperature effect prediction method based on channel attention BiLSTM model | |
| CN114692465A (en) | Nondestructive identification method of bridge damage position, storage medium and equipment |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20210713 |