CN114861458B - Bridge traffic safety rapid evaluation method based on mapping relation proxy model - Google Patents
Bridge traffic safety rapid evaluation method based on mapping relation proxy model Download PDFInfo
- Publication number
- CN114861458B CN114861458B CN202210590453.9A CN202210590453A CN114861458B CN 114861458 B CN114861458 B CN 114861458B CN 202210590453 A CN202210590453 A CN 202210590453A CN 114861458 B CN114861458 B CN 114861458B
- Authority
- CN
- China
- Prior art keywords
- mapping relation
- model
- bridge
- proxy model
- safety
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T90/00—Enabling technologies or technologies with a potential or indirect contribution to GHG emissions mitigation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Hardware Design (AREA)
- Evolutionary Computation (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Train Traffic Observation, Control, And Security (AREA)
Abstract
The invention discloses a rapid bridge uplink vehicle safety evaluation method based on a mapping relation proxy model, which comprises the following steps of 1, recording service performance evolution of an infrastructure; step 2, constructing a multipoint mapping relation required by the proxy model; step 3, constructing a mapping relation proxy model; and 4, evaluating driving safety and comfort based on the agent model. The invention discloses a multi-objective parallel optimization new algorithm which can simultaneously consider global search and local development of a system, and is combined with a vehicle-rail-bridge coupling vibration model to build a mapping relation proxy model for calculating driving safety parameters with high efficiency under complex service conditions, so as to form an on-bridge driving safety evaluation device, thereby realizing rapid and accurate evaluation of the on-bridge driving safety.
Description
Technical Field
The invention relates to the technical field of train driving safety, in particular to a rapid bridge driving safety evaluation method based on a mapping relation proxy model.
Background
The operation mileage of the high-speed railway in China reaches 4 ten thousand kilometers, and the average bridge accounts for 58%. The line mileage under special geology such as soft soil, high temperature and frost heaving and complex climatic conditions is longer and longer, and the phenomena of deformation of an offline foundation structure and performance degradation of an interlayer structure are increasingly prominent. Aiming at high-speed railway bridges, the safety and the comfort of running trains on the tracks are more concerned.
Since the evolution of the performance of the basic structure is a complicated nonlinear problem, if nonlinear factors such as various additional deformations, interlayer connection failures and the like are directly considered in the dynamics of the vehicle-basic structure system, huge calculation scale is caused, and the safety of the bridge running in a complex environment is difficult to rapidly evaluate in real time. Based on the agent model technology, the method for efficiently predicting the complex response of the real system by simulating the mapping relation between input and output can solve the problems of long time consumption, high calculation cost and the like of dynamic analysis numerical simulation to a certain extent, but the method is usually based on the prediction optimizing of the specific response of the real system, so that the change rule of the global trend of the system is difficult to describe accurately, and the optimizing efficiency and the final precision are all to be improved.
Disclosure of Invention
The invention aims to provide a rapid bridge uplink vehicle safety evaluation method based on a mapping relation proxy model, which establishes a proxy model for efficiently solving driving safety parameters under the condition of information updating, thereby realizing rapid evaluation and prejudgment of driving safety performance under the complex service condition and guaranteeing the safe service of a bridge-track system.
The invention is realized by the following technical scheme:
a bridge traffic safety evaluation method based on a mapping relation proxy model comprises the following steps,
and 4, evaluating driving safety and comfort based on the agent model.
In the prior art, the performance of a basic structure evolves into a complex nonlinear problem, nonlinear factors such as various additional deformation, interlayer connection failure and the like cannot be combined with dynamics of a vehicle-basic structure system, namely, the driving safety on a bridge in a complex environment cannot be accurately evaluated in real time; the specific operation steps are as follows:
firstly, recording and obtaining service states of a bridge-track structure along a high-speed rail, such as information of pier settlement and the like, through a detection and monitoring module to obtain evolution data of service performance of a basic structure, and predicting an influence rule of a train dynamic performance by using a train-rail-bridge coupling vibration model based on the obtained evolution data to further construct a multipoint mapping relation required by a proxy model; and extracting an initial modeling sample based on the multipoint mapping relation, establishing an initial Kriging proxy model, and then completing the construction of the mapping relation proxy model according to an EF-MSE algorithm.
It should be noted that the EF-MSE algorithm includes an EF function and an MSE function, and the MSE function is used to take a point with greater prediction uncertainty as an update sample.
In the step 3, the mapping relation proxy model is constructed as follows:
firstly, extracting an initial modeling sample by using a Latin hypercube test based on a multipoint mapping relation, and establishing an initial Kriging proxy model;
and secondly, carrying out parallel iterative optimization on the integral dynamic response change trend and the safety limit value region according to an EF-MSE algorithm until the optimization convergence requirement is met, and finally completing the construction of the mapping relation proxy model.
The step 3 of constructing a mapping relation proxy model comprises the following steps,
step 3.1, generating initial sample variables required by modeling in a given design space;
step 3.2, obtaining actual response of the existing sample variable through physical methods such as numerical analysis and the like, and constructing a Kriging proxy model aiming at the corresponding sample pair;
step 3.3, calculating the global trend of the current Kriging model, and the deviation situation of the prediction of the threshold region and the actual response respectively;
step 3.4, checking whether the Kriging model is converged, if the set convergence condition is met, stopping iteration, and outputting the current model as an optimal proxy model; otherwise, the next step is needed to be executed, and the optimization and the updating are continued;
step 3.5, solving two point adding criteria based on an EF function and an MSE function through an intelligent optimization algorithm, and obtaining a plurality of parallel new samples;
step 3.6, performing correlation analysis between new samples and between the new samples and the existing samples by utilizing a Gaussian rule to delete redundant samples to obtain a final optimized sample;
wherein the expression of the gaussian criterion is as follows:
in θ i As related function parameters, the method can be solved through maximum likelihood estimation;
and 3.7, adding the optimized sample into the existing sample variable, and turning to the step 3.2, so as to continuously update the Kriging proxy model until convergence.
In the step 3.1, sampling is performed by using a Latin hypercube design method which enables the samples to be randomly distributed in the whole design space.
In said step 3.5, the form of the EF function is as follows:
in the method, in the process of the invention,
s (x) is the prediction mean value and standard deviation estimation of the Kriging model respectively; z is a specified threshold; z + 、z - Values around and above the threshold, respectively, are generally denoted as z ± ＝z±μ；/>
Is->
Is used to determine the probability density of (1),
on the basis, the optimization updating of the proxy model can be realized by solving the sample point corresponding to the maximum value of EF (x):
x new ＝argmax{EF(x)}。
in said step 3.5, the form of the MSE function is as follows:
wherein x is new As new sample variables for optimization;
representing a mean square error estimated value of a response prediction result of the relevant real system; arg is the mapping relationship between the independent variable and the dependent variable.
In the step 1, the service state of the high-speed rail along the bridge-track structure comprises pier settlement, beam end corner, gap, plate bottom void and arch-up state.
The system also comprises a performance evolution data detection and monitoring module, which is used for recording the service state of the bridge-track structure along the high-speed rail;
the train response prediction module is used for inputting the measured data into the mapping relation proxy model and outputting the vehicle response value and the change trend in real time;
and the rapid evaluation and early warning module is used for analyzing the response value and the change trend of the vehicle and outputting the driving safety and comfort evaluation and early warning result in real time.
Through the cooperation of the performance evolution data detection monitoring module, the train response prediction module and the rapid evaluation and early warning module, the safety evaluation and early warning of the bridge traveling on the road can be more efficiently and accurately carried out by the detection personnel in the field, and the safety service of the bridge-track system is ensured.
Compared with the prior art, the invention has the following advantages and beneficial effects:
1. the EF-MSE algorithm provided by the invention can optimize global search and local development in parallel in sequence optimization iteration, adaptively improves model multi-objective optimization precision, obviously reduces the number of adding points, greatly improves convergence speed, shows good stability, has small calculation amount of solving agent models, has physical mechanism interpretation, and can calculate driving power response characteristics on a bridge with high precision and high efficiency;
2. the bridge traffic safety evaluation device formed based on the method can be used for rapid evaluation and pre-judgment of traffic safety performance under complex service conditions, promotes intelligent evaluation of traffic safety on a high-speed railway bridge and gradual formation of an early warning system, and powerfully ensures the safety service of a bridge-track system.
Drawings
The accompanying drawings, which are included to provide a further understanding of embodiments of the invention and are incorporated in and constitute a part of this application, illustrate embodiments of the invention. In the drawings:
FIG. 1 is a flow chart of an evaluation method in the present invention;
FIG. 2 is a flowchart of a mapping relation proxy model constructed based on an EF-MSE method;
FIG. 3 is a block diagram of the device for evaluating the driving safety and the speed in the invention;
FIG. 4 is a graph showing the acceleration response of a train in the combined bridge pier settlement and slab bottom void conditions according to example 1;
FIG. 5 is a graph showing the vertical force response of the train wheel rail in the combined conditions of pier settlement and slab bottom void in example 1;
FIG. 6 is a mapping relationship between pier subsidence and maximum reduction in wheel-rail vertical force under plate bottom void conditions in example 1;
FIG. 7 is a mapping relationship between pier settlement and maximum variation of vertical acceleration under the condition of plate bottom void in example 1;
FIG. 8 is a two-dimensional nonlinear multi-modal function global accuracy optimization process of example 2;
FIG. 9 is a two-dimensional nonlinear multi-modal function threshold accuracy optimization process of example 2;
FIG. 10 is a two-dimensional nonlinear cubic function global accuracy optimization process of example 2;
FIG. 11 is a two-dimensional nonlinear cubic function threshold accuracy optimization process of example 2.
Detailed Description
For the purpose of making apparent the objects, technical solutions and advantages of the present invention, the present invention will be further described in detail with reference to the following examples and the accompanying drawings, wherein the exemplary embodiments of the present invention and the descriptions thereof are for illustrating the present invention only and are not to be construed as limiting the present invention. It should be noted that the present invention is already in a practical development and use stage.
Example 1
As shown in fig. 1, the present embodiment includes the following steps,
taking the uplink section of Beijing high-speed rail (K1308+ 733.919-K1309+ 159.71375) as an example, the actual measurement data of the performance evolution of the basic structure is recorded by a detection and monitoring module, and the data are shown in Table 1.
TABLE 1 Beijing high-speed railway infrastructure performance evolution actual measurement data
Note that: the plate bottom void is the longitudinal void of the rail plate bottom and corresponds to the pier top position of the bridge pier in the table.
the method is characterized in that a Beijing Shanghai high-speed railway 32m simple support beam bridge, a CRTS II plate-type ballastless track and a CRH2 train are taken as research objects, aiming at typical working conditions of pier settlement and base plate void, based on a bridge-track deformation mapping model, track addition irregularity is solved, and the track addition irregularity is input into a train-rail-bridge coupling vibration model as system excitation, so that train dynamic response under typical working conditions is obtained.
As shown in fig. 4 and 5, as the bridge pier subsidence and the plate bottom void only cause the rail to vertically deform, when the train passes through the subsidence and void area, the vertical acceleration of the train body and the vertical force of the wheel rail are obviously changed, and the transverse acceleration and the transverse force of the wheel rail are basically unchanged, which indicates that the combined action of the bridge pier subsidence and the rail plate void mainly affects the vertical vibration of the train-rail-bridge system, and the influence on the transverse dynamic performance is smaller.
Measurement and calculation results show that typical diseases of a high-speed railway foundation structure in a soft soil area are uneven settlement of piers and void of the bottoms of track plates, and the vertical dynamic performance of a train is obviously affected. Therefore, the running safety and the comfort of the running high-speed rail in the sedimentation area are comprehensively considered, the running speed of 350km/h is taken as a calculation working condition, the combined action of sedimentation and void is considered in the mapping relation, and the vertical force and the vertical acceleration change of the train wheel rail caused by the combined action are correspondingly considered.
Wherein the sedimentation and the void ranges are respectively 0-30 mm and 0-6 m, and the void positions are selected from sedimentation adjacent piers which are more unfavorable for track deformation.
the overall accuracy of the model is based on a plurality of sample pairs uniformly distributed in a design space, and the average error of a response prediction result and a rail bridge finite element simulation result is calculated for inspection.
For the definition precision of the threshold contour, calculating the deviation between the numerical simulation result and the threshold value through a plurality of sample pairs which are uniformly extracted from the threshold value contour line simulated by the current agent model;
firstly, 20 different combined working conditions of pier settlement and plate bottom void are selected by adopting pull Ding Chao cube sampling, corresponding train wheel rail vertical force variation is obtained through a train-rail-bridge coupling vibration model, an initial sample pair is formed, and therefore an initial Kriging proxy model is established; and secondly, carrying out parallel iterative optimization on the integral change trend of the power response and the safety limit value area according to two point adding criteria of the EF function and the MSE function until the optimization convergence requirement is met, and finally completing the construction of the mapping relation proxy model. The overall accuracy of the model is based on 20 sample pairs uniformly distributed in a design space, and the average error of a response prediction result and a rail bridge finite element simulation result is calculated for inspection. And for the definition precision of the threshold contour, the deviation between the numerical simulation result and the threshold is calculated and checked through 20 sample pairs which are uniformly extracted from the threshold contour line simulated by the current agent model. In the example, the global prediction average absolute error is less than 5% and the threshold prediction deviation is less than 0.1% as the precision convergence condition.
The accuracy test result shows that for the whole design space, the average absolute error of the vertical force variation of the wheel track predicted by the agent mapping model is 2.86%, and the prediction deviation of the area near the safety limit value is only 0.81%, which meets the optimization target, and the agent model optimized based on the EF-MSE algorithm can better realize the prediction requirements of the global trend and the threshold profile. The simulation result of the converged proxy model for the wheel-rail vertical force variation is shown in fig. 6.
Similarly, based on EF-MSE optimization algorithm, the mapping relation of pier settlement and the maximum variation of vertical acceleration under the condition of plate bottom void is constructed. FIG. 7 is a mapping relationship of the proxy model simulation after convergence, comparing the numerical simulation results, the average deviation of the model overall prediction is 1.78%, and the threshold region prediction deviation is 0.18%, so as to meet the convergence requirement.
In addition, for other various basic structure performance degradation phenomena such as beam end rotation angle, gap, upper arch and the like, the driving power response under the corresponding working condition can be rapidly output through training the mapping relation based on the agent model technology, so that large-scale vehicle-rail-bridge coupling calculation is avoided.
Step 4, evaluating driving safety and comfort based on the agent model; and replacing complex and time-consuming track and bridge calculation by the constructed mapping relation proxy model analysis, outputting a train power response result, and evaluating train driving safety and comfort indexes and early warning in real time.
By adopting the driving safety evaluation method based on the agent model, the complex time-consuming track and bridge calculation is replaced by the constructed mapping relation, and train power responses under different working conditions of the uplink sections (K1308+ 733.919-K1309+ 159.71375) of the Beijing high iron are accurately output in real time, as shown in the table 2.
Table 2 solving train dynamic response based on mapping agent model
As can be seen from Table 2, when the train passes through No. 441 bridge pier from No. 440 bridge pier, the running safety and comfort are overrun, the wheel weight load shedding rate is up to 0.646, and the maximum vertical acceleration is 1.746m/s 2 At this time, the differential settlement and the void are respectively 27mm and 2.5m, and the train passing through the bridge span should be sent out to early warning of deceleration in time so as to ensure the safety and the comfort of the train. Therefore, the driving safety evaluation method based on the agent model realizes rapid and accurate driving safety evaluation and early warning, and provides a basis for guaranteeing long-term operation safety of the train.
Example 2
As shown in fig. 2, the present embodiment is based on embodiment 1, wherein the mapping relation proxy model is constructed in step 3, specifically comprising the following steps,
step 3.1, generating initial sample variables required by modeling in a given design space; sampling is carried out by using a Latin hypercube experimental design method which enables samples to be randomly distributed in the whole design space.
Step 3.2, obtaining actual response of the existing sample variable through physical methods such as numerical analysis and the like, and constructing a Kriging proxy model aiming at the corresponding sample pair;
step 3.3, calculating the global trend of the current Kriging model, and the deviation situation of the prediction of the threshold region and the actual response respectively;
step 3.4, checking whether the Kriging model is converged, if the set convergence condition is met, stopping iteration, and outputting the current model as an optimal proxy model; otherwise, the next step is needed to be executed, and the optimization and the updating are continued;
step 3.5, solving two point adding criteria based on an EF function and an MSE function through an intelligent optimization algorithm, and obtaining a plurality of parallel new samples; preferably, the optimization algorithm adopts a genetic algorithm with strong global optimization and high search efficiency;
step 3.6, performing correlation analysis between new samples and between the new samples and the existing samples by utilizing a Gaussian rule to delete redundant samples to obtain a final optimized sample;
wherein the expression of the gaussian criterion is as follows:
in θ i As related function parameters, the method can be solved through maximum likelihood estimation;
and 3.7, adding the optimized sample into the existing sample variable, and turning to the step 3.2, so as to continuously update the Kriging proxy model until convergence.
The arithmetic processing of the EF function and the MSE function involved in the present embodiment,
wherein the form of the EF function is as follows:
in the method, in the process of the invention,
s (x) is the prediction mean value and standard deviation estimation of the Kriging model respectively; z is a specified threshold; z + 、z - Values around and above the threshold, respectively, are generally denoted as z ± ＝z±μ；/>
Is->
Is used to determine the probability density of (1),
on the basis, the optimization updating of the proxy model can be realized by solving the sample point corresponding to the maximum value of EF (x):
x new ＝argmax{EF(x)}。
the form of the MSE function is as follows:
wherein x is new As new sample variables for optimization;
representing a mean square error estimated value of a response prediction result of the relevant real system; arg is the mapping relationship between the independent variable and the dependent variable.
Taking two typical complex two-dimensional nonlinear functions as examples, the superiority of the EF-MSE algorithm in terms of global trend and threshold search is compared and analyzed. Both function thresholds are defined as function zeros.
The specific expression of the two-dimensional function is as follows:
(1) Two-dimensional nonlinear multi-modal function:
x 1 ∈[-4,7]x 2 ∈[-3,8]，
(2) Two-dimensional nonlinear cubic function:
since the EF-MSE algorithm is a parallel optimization process, when each optimization function in the convergence criterion meets the convergence requirement, the optimization process is only ended, and the overall optimization process of the algorithm is not ended.
Based on 20 initial samples, the optimization process of the two-dimensional nonlinear function global and threshold prediction precision by adopting different algorithms is shown in fig. 8-11.
The convergence results of the different optimization algorithms are shown in table 3.
Table 3 comparison of convergence results for different optimization algorithms
According to table 3, it can be found that optimization by using EF-MSE algorithm can effectively reduce the number of optimization times while maintaining good prediction accuracy, and accordingly, while EGRA algorithm only needs 7.62 times of optimization for cubic function with more regular spatial distribution, premature convergence and larger function gradient also result in poor prediction result.
As an optimization algorithm for parallel computing, the total running time of the EF-MSE algorithm program is greatly shortened compared with other algorithms, and the optimization efficiency is obviously improved; in addition, under the condition that the convergence condition of the same optimization function is the same, although samples added by the EF-MSE algorithm in one parallel optimization process are twice as many as those of other algorithms, the total number of samples is only slightly larger than that of the other algorithms, which indicates that the EF-MSE algorithm is not a simple superposition of the two algorithms, but has more stable and efficient optimization performance.
Example 3
As shown in fig. 3, the embodiment further includes a performance evolution data detection and monitoring module, based on the embodiment 1, for recording the service state of the bridge-track structure along the high-speed rail;
the train response prediction module is used for inputting the measured data into the mapping relation proxy model and outputting the vehicle response value and the change trend in real time;
and the rapid evaluation and early warning module is used for analyzing the response value and the change trend of the vehicle and outputting the driving safety and comfort evaluation and early warning result in real time.
Through the cooperation of the performance evolution data detection monitoring module, the train response prediction module and the rapid evaluation and early warning module, the safety evaluation and early warning of the bridge traveling on the road can be more efficiently and accurately carried out by the detection personnel in the field, and the safety service of the bridge-track system is ensured.
The foregoing description of the embodiments has been provided for the purpose of illustrating the general principles of the invention, and is not meant to limit the scope of the invention, but to limit the invention to the particular embodiments, and any modifications, equivalents, improvements, etc. that fall within the spirit and principles of the invention are intended to be included within the scope of the invention.
Claims (6)
1. A quick evaluation method for bridge traffic safety based on a mapping relation proxy model is characterized by comprising the following steps: comprises the steps of,
step 1, recording service performance evolution of a foundation structure; recording the service state of the bridge-track structure along the high-speed rail by a detection monitoring module;
step 2, constructing a multipoint mapping relation required by the proxy model; predicting the influence rule of the high-speed rail along the bridge-track structure service state based on the train-track-bridge coupling vibration model according to the detected and monitored high-speed rail along the bridge-track structure service state, and further clarifying the multipoint mapping relation required to be constructed by the agent model;
step 3, constructing a mapping relation proxy model; extracting an initial modeling sample based on a multipoint mapping relation, and establishing an initial Kriging agent model; then according to EF-MSE algorithm, the construction of the mapping relation proxy model is completed; the mapping relation proxy model is constructed as follows:
firstly, extracting an initial modeling sample by using a Latin hypercube test based on a multipoint mapping relation, and establishing an initial Kriging proxy model;
secondly, carrying out parallel iterative optimization on the integral change trend of the dynamic response and the safety limit value area according to an EF-MSE algorithm until the optimization convergence requirement is met, and finally completing construction of a mapping relation proxy model; the mapping relation proxy model is constructed, which comprises the following steps,
step 3.1, generating initial sample variables required by modeling in a given design space;
step 3.2, obtaining actual response of the existing sample variable through numerical analysis, and constructing a Kriging proxy model aiming at the corresponding sample pair;
step 3.3, calculating the global trend of the current Kriging model, and the deviation situation of the prediction of the threshold region and the actual response respectively;
step 3.4, checking whether the Kriging model is converged, if the set convergence condition is met, stopping iteration, and outputting the current model as an optimal proxy model; otherwise, the next step is needed to be executed, and the optimization and the updating are continued;
step 3.5, solving two point adding criteria based on an EF function and an MSE function through an intelligent optimization algorithm, and obtaining a plurality of parallel new samples;
step 3.6, performing correlation analysis between new samples and between the new samples and the existing samples by utilizing a Gaussian rule to delete redundant samples to obtain a final optimized sample;
wherein the expression of the gaussian criterion is as follows:
in the method, in the process of the invention,
as related function parameters, the method can be solved through maximum likelihood estimation;
step 3.7, adding the optimized sample into the existing sample variable, and turning to step 3.2, so as to continuously update the Kriging proxy model until convergence;
and 4, evaluating driving safety and comfort based on the agent model.
2. The method for rapidly evaluating the safety of the bridge crane based on the mapping relation proxy model according to claim 1, wherein the method comprises the following steps: in the step 3.1, sampling is performed by using a Latin hypercube design method which enables the samples to be randomly distributed in the whole design space.
3. The method for rapidly evaluating the safety of the bridge crane based on the mapping relation proxy model according to claim 1, wherein the method comprises the following steps: in said step 3.5, the form of the EF function is as follows:
in the method, in the process of the invention,
、/>
respectively estimating a prediction mean value and a standard deviation of the Kriging model; />
Is a specified threshold; />
、
The values above and below the threshold are usually denoted as +.>
；/>
Is->
Is used to determine the probability density of (1),
；
on the basis, by solving for
The sample point corresponding to the maximum value can realize the optimization updating of the agent model:
4. the method for rapidly evaluating the safety of the bridge crane based on the mapping relation proxy model according to claim 1, wherein the method comprises the following steps: in said step 3.5, the form of the MSE function is as follows:
in the method, in the process of the invention,
as new sample variables for optimization; />
Representing a mean square error estimated value of a response prediction result of the relevant real system; arg is the mapping relationship between independent and dependent variablesIs tied up.
5. The method for rapidly evaluating the safety of the bridge crane based on the mapping relation proxy model according to claim 1, wherein the method comprises the following steps: in the step 1, the service state of the high-speed rail along the bridge-track structure comprises pier settlement, beam end corner, gap, plate bottom void and arch-up state.
6. The method for rapidly evaluating the safety of the bridge crane based on the mapping relation proxy model according to any one of claims 1 to 5, wherein the method is characterized by comprising the following steps: and also comprises
The performance evolution data detection and monitoring module is used for recording the service state of the bridge-track structure along the high-speed rail;
the train response prediction module is used for inputting the measured data into the mapping relation proxy model and outputting the vehicle response value and the change trend in real time;
and the rapid evaluation and early warning module is used for analyzing the response value and the change trend of the vehicle and outputting the driving safety and comfort evaluation and early warning result in real time.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210590453.9A CN114861458B (en) | 2022-05-26 | 2022-05-26 | Bridge traffic safety rapid evaluation method based on mapping relation proxy model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210590453.9A CN114861458B (en) | 2022-05-26 | 2022-05-26 | Bridge traffic safety rapid evaluation method based on mapping relation proxy model |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114861458A CN114861458A (en) | 2022-08-05 |
| CN114861458B true CN114861458B (en) | 2023-07-14 |
Family
ID=82641111
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210590453.9A Active CN114861458B (en) | 2022-05-26 | 2022-05-26 | Bridge traffic safety rapid evaluation method based on mapping relation proxy model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114861458B (en) |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103336869A (en) * | 2013-07-05 | 2013-10-02 | 广西大学 | Multi-objective optimization method based on Gaussian process simultaneous MIMO model |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110728017B (en) * | 2019-08-21 | 2021-03-12 | 西南交通大学 | Method and device for constructing dynamic mapping relation between bridge additional deformation and driving safety |
| CN110609975B (en) * | 2019-09-20 | 2023-02-17 | 大连理工大学 | Parallel computing global optimization method based on Kriging agent model |
| CN113505545B (en) * | 2021-06-21 | 2022-04-15 | 西南交通大学 | Rail transit vehicle pneumatic multi-objective optimization method based on improved point adding criterion |
| CN114117840B (en) * | 2021-10-28 | 2022-09-06 | 中国运载火箭技术研究院 | Structural performance prediction method based on simulation and test data hybrid drive |
-
2022
- 2022-05-26 CN CN202210590453.9A patent/CN114861458B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103336869A (en) * | 2013-07-05 | 2013-10-02 | 广西大学 | Multi-objective optimization method based on Gaussian process simultaneous MIMO model |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114861458A (en) | 2022-08-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zhu et al. | Recent developments in inverse problems of vehicle–bridge interaction dynamics | |
| CN111144039B (en) | Train dynamic weighing system and weighing method based on deep learning | |
| CN111256924B (en) | Intelligent monitoring method for expansion joint of large-span high-speed railway bridge | |
| Li et al. | Dynamic response prediction of vehicle-bridge interaction system using feedforward neural network and deep long short-term memory network | |
| Lu et al. | Fatigue reliability evaluation of orthotropic steel bridge decks based on site-specific weigh-in-motion measurements | |
| CN110319990B (en) | Bridge dynamic deflection monitoring method based on inclinometer optimized arrangement | |
| CN116881819B (en) | Stay cable working state monitoring method based on isolated forest | |
| Peng et al. | A novel bagged tree ensemble regression method with multiple correlation coefficients to predict the train body vibrations using rail inspection data | |
| CN106257541A (en) | A kind of modification method of bridge finite element model | |
| Zhang et al. | An adaptive surrogate model approach for random vibration analysis of the train–bridge system | |
| CN103344395B (en) | A kind of confirmation method of bridge strengthening target bearing capacity and device | |
| Gao et al. | Estimation of rail renewal period in small radius curves: A data and mechanics integrated approach | |
| Li et al. | Deep learning models for time-history prediction of vehicle-induced bridge responses: A comparative study | |
| Liu et al. | Review of Perspectives on Pantograph-Catenary Interaction Research for High-Speed Railways Operating at 400 km/h and above | |
| Xie et al. | Stochastic analysis of dynamic stress amplification factors for slab track foundations | |
| You et al. | Frequency response function-based model updating of flexible vehicle body using experiment modal parameter | |
| CN114861458B (en) | Bridge traffic safety rapid evaluation method based on mapping relation proxy model | |
| CN110344327B (en) | Method for calculating CPIII point of track control network on cable-stayed bridge in real time | |
| Qian et al. | The prediction of vibration and noise for the high-speed train based on neural network and boundary element method | |
| CN115481488B (en) | Fang Zhui type energy-absorbing structure crashworthiness multi-objective optimization method based on machine learning | |
| Li et al. | Updating time-variant dimension for complex traffic flows in analysis of vehicle–bridge dynamic interaction | |
| Shi et al. | Estimation of cement asphalt mortar disengagement degree using vehicle dynamic response | |
| CN115618209B (en) | Railway track state evaluation method based on sparse extreme learning machine and hypothesis test | |
| CN116663126A (en) | Bridge temperature effect prediction method based on channel attention BiLSTM model | |
| Chen et al. | Recent Research and Applications of Numerical Simulation for Dynamic Response of Long‐Span Bridges Subjected to Multiple Loads |
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 |