CN115266929A - High-speed railway fundamental resonance early warning method and system based on deep learning - Google Patents
High-speed railway fundamental resonance early warning method and system based on deep learning Download PDFInfo
- Publication number
- CN115266929A CN115266929A CN202210951709.4A CN202210951709A CN115266929A CN 115266929 A CN115266929 A CN 115266929A CN 202210951709 A CN202210951709 A CN 202210951709A CN 115266929 A CN115266929 A CN 115266929A
- Authority
- CN
- China
- Prior art keywords
- roadbed
- equivalent modulus
- comprehensive equivalent
- speed railway
- pile
- 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
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N29/00—Investigating or analysing materials by the use of ultrasonic, sonic or infrasonic waves; Visualisation of the interior of objects by transmitting ultrasonic or sonic waves through the object
- G01N29/04—Analysing solids
- G01N29/043—Analysing solids in the interior, e.g. by shear waves
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N29/00—Investigating or analysing materials by the use of ultrasonic, sonic or infrasonic waves; Visualisation of the interior of objects by transmitting ultrasonic or sonic waves through the object
- G01N29/44—Processing the detected response signal, e.g. electronic circuits specially adapted therefor
- G01N29/4472—Mathematical theories or simulation
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N29/00—Investigating or analysing materials by the use of ultrasonic, sonic or infrasonic waves; Visualisation of the interior of objects by transmitting ultrasonic or sonic waves through the object
- G01N29/44—Processing the detected response signal, e.g. electronic circuits specially adapted therefor
- G01N29/4481—Neural networks
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N2291/00—Indexing codes associated with group G01N29/00
- G01N2291/02—Indexing codes associated with the analysed material
- G01N2291/023—Solids
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N2291/00—Indexing codes associated with group G01N29/00
- G01N2291/02—Indexing codes associated with the analysed material
- G01N2291/028—Material parameters
- G01N2291/0289—Internal structure, e.g. defects, grain size, texture
-
- 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
Abstract
The invention provides a high-speed railway foundation resonance early warning method and system based on deep learning, which comprises the following steps: step 1: embedding a sound measuring tube and placing a sound wave transmitter and a sound wave receiver; step 2: periodically detecting internal defects of a pile foundation part of the high-speed rail roadbed; and 3, step 3: inverting a high-speed railway foundation pile base damage profile based on the acquired data; and 4, step 4: reconstructing a three-dimensional model of the roadbed, and calculating the comprehensive equivalent modulus of the roadbed; and 5: predicting the roadbed comprehensive equivalent modulus at the future moment through an LSTM model; and 6: acquiring the characteristic frequency of a roadbed bearing plate of a pile plate structure; and 7: when the characteristic frequency of the bearing plate is close to the loading frequency of the train, alarm information is output; otherwise, exiting. The method considers the influence of traffic load and complex hydrogeological environment change on the characteristic frequency change of the high-speed rail pile plate structure roadbed bearing plate, predicts the potential resonance of the high-speed rail pile plate structure roadbed bearing plate and guarantees the driving safety.
Description
Technical Field
The invention relates to the field of railway engineering roadbed service safety, in particular to a high railway roadbed resonance early warning method and system based on deep learning.
Background
Under the action of high-speed rail load and the complex and severe underground corrosion environment, the pile foundation part of the high-speed rail pile structure roadbed is inevitably damaged internally, and the characteristic frequency of the bearing plate can be further influenced by the change of the bearing rigidity of the bearing plate caused by the damage of the pile foundation. When the characteristic frequency of the bearing plate is close to the loading frequency of the train, the dynamic response of the structure and the train is remarkably increased, so that the operation safety of the train and the comfort of passengers are influenced, and the bearing plate becomes a problem to be solved urgently in the field of railway engineering roadbed service safety.
Because pile foundation is buried in soil in high-speed railway pilework structure road bed, be difficult to detect its damage, and there is not mature theory at present to establish the relation between pile foundation damage and its rigidity, can't realize the early warning to high-speed railway pilework structure road bed potential resonance admittedly, missed the best opportunity to high-speed railway pilework structure road bed maintenance, cause serious economic loss, consequently need a high-speed railway pilework structure road bed resonance early warning method and system based on degree of depth study urgently.
Disclosure of Invention
The technical problem solved by the invention is as follows: the method solves the problems that in the prior art, the damage of the pile foundation in the pile-plate structure roadbed is difficult to detect and the potential resonance of the pile-plate structure roadbed cannot be predicted.
The technical solution of the invention is as follows: a high-speed railway foundation resonance early warning method based on deep learning comprises the following steps:
step 1: and pre-burying and arranging the acoustic measurement pipe in the construction process of the high-speed rail pile structure roadbed, and placing the acoustic transmitter and the acoustic receiver.
Step 2: and (3) during the operation of the train, regularly utilizing the sound wave transmitter and the sound wave receiver pre-buried in the step (1) to detect the internal defects of the pile foundation of the high-speed rail pile plate structure roadbed.
And step 3: and (3) processing and inverting the data received by the acoustic wave receiver in the step (2) by adopting a Radon algorithm to obtain a post-pile damage profile of the high-speed railway foundation.
And 4, step 4: importing the damaged section map obtained in the step 3 into Mimics software to reconstruct a three-dimensional model of the roadbed, generate a corresponding finite element model and calculate the comprehensive equivalent modulus of the roadbed; the Mimics is software for three-dimensional reconstruction of sequence images, and provides a highly automated interface to perform format conversion on the established model and combines with finite element software.
And 5: recording the roadbed comprehensive equivalent modulus at different moments according to a time sequence, training the roadbed comprehensive equivalent modulus advanced prediction LSTM model by using the roadbed comprehensive equivalent modulus advanced prediction LSTM model as a data set, and acquiring the roadbed comprehensive equivalent modulus advanced prediction LSTM model updated in real time along with the time.
Step 6: and predicting the roadbed comprehensive equivalent modulus value at the future moment by adopting the trained LSTM model.
And 7: and (6) establishing a finite element model of the bearing plate, uniformly distributing springs for bottom support of the bearing plate, uniformly distributing spring stiffness as the roadbed comprehensive equivalent modulus value obtained by calculation in the step 6, and carrying out modal analysis on the bearing plate model to obtain characteristic frequency.
And 8: calculating the train loading frequency according to the train speed, and setting a resonance threshold value based on the characteristic frequency of the bearing plate at the future moment predicted in the steps 6 and 7eWhen the difference between the characteristic frequency value and the train loading frequency value is less thaneAnd judging that the high-speed rail pile plate structure roadbed is easy to resonate, and outputting alarm information.
Further, step 1 crowbar pile structure road bed includes: bearing platform board, road bed filler and reinforced concrete pile foundation.
Furthermore, 4 acoustic pipes are arranged along the perimeter of the pile foundation of the roadbed with the high-iron pile plate structure in the step 1, the connecting lines of the acoustic pipes are square, the acoustic pipes are filled with liquid coupling agents, one acoustic pipe is used for placing an acoustic transmitter, and the other acoustic pipes are used for placing acoustic receivers.
Further, the calculation process of calculating the comprehensive equivalent modulus of the roadbed in the step 4 is as follows:
and applying a load controlled by displacement on the top of the three-dimensional finite element model of the roadbed, extracting a load-strain curve, and taking the slope of an original point tangent as the comprehensive equivalent modulus of the roadbed.
Further, the LSTM model for integrated equivalent modulus look-ahead of the basis in step 5 is written by Matlab, and includes an input layer, a hidden layer and an output layerT n The time of day (the subscript n is the order,T n the time is the nth time at fixed time intervals) to be recorded in time sequenceT 1 、T 2 、T 3 …T n The comprehensive equivalent modulus of the roadbed at a moment is used as a data set, the input parameters are x continuous comprehensive equivalent moduli of the roadbed (x is less than n), and the number of x and hidden layer units is determined by a grid search method.
Further, the step 5 of obtaining the roadbed comprehensive equivalent modulus advanced prediction LSTM model updated in real time along with the time lapse comprises the following steps:
in thatT i The time being recorded in chronological orderT i+1 、T i+2 、T i+3 …T i+n The roadbed comprehensive equivalent modulus at a moment is taken as a data set to obtainT i And (3) constantly updating the roadbed comprehensive equivalent modulus advanced prediction LSTM model.
Further, in the step 6, a trained LSTM model is used to predict the roadbed comprehensive equivalent modulus at a future time, and the process is as follows:
in thatT n Time of day based onT n Constantly trained roadbed comprehensive equivalent modulus advanced prediction LSTM model toT n-x+1 、T n-x+2 、…、T n Predicting the time subgrade comprehensive equivalent modulus (x total) as an input parameterT n+1 The comprehensive equivalent modulus of the roadbed at any moment;
to be provided withT n-x+2 、…、T n And predictedT n+1 Prediction of roadbed comprehensive equivalent modulus at moment as input parameter (x in total)T n+2 The roadbed comprehensive equivalent modulus at the moment is predicted by analogy to obtain the preset roadbed comprehensive equivalent modulus at the future moment;
a high-speed railway fundamental resonance early warning system based on deep learning comprises an information acquisition module, a processing module and an early warning module;
the information acquisition module is used for acquiring data received by the sound wave receiver;
the processing module is used for inverting a pile foundation damage profile of the high-speed railway foundation; loading the Mimics software to reconstruct a roadbed three-dimensional model according to the damaged profile and converting the profile into a format and importing the format into finite element software to generate a finite element model; loading a finite element software computing module to compute the comprehensive equivalent modulus of the roadbed; loading a Matlab script, and training a roadbed comprehensive equivalent modulus advanced prediction LSTM model; loading the trained roadbed comprehensive equivalent modulus advanced prediction LSTM model to predict roadbed comprehensive equivalent modulus value at the future moment; loading finite element software to calculate the characteristic frequency of the bearing plate;
the early warning module is used for judging whether the characteristic frequency of the bearing plate is close to the train loading frequency, if the characteristic frequency of the bearing plate is close to the train loading frequency at a certain future moment, outputting moment information which is possible to generate resonance, and if not, exiting.
Compared with the prior art, the invention has the advantages that:
according to the scheme provided by the embodiment of the invention, the influence of the pile plate structure roadbed on traffic load and underground complex corrosion environment is considered, and the comprehensive equivalent modulus of the roadbed after the pile foundation is damaged is quantified by combining sound wave CT nondestructive testing, three-dimensional reconstruction and finite element means; and establishing a roadbed comprehensive equivalent modulus degradation model based on LSTM deep learning, and predicting the characteristic frequency change and the resonance time point of the bearing plate. The method provides powerful means for the potential resonance early warning of the high-speed railway subgrade; the analysis method is clear and has strong reliability.
Drawings
Fig. 1 is a schematic flow chart of an early warning method according to an embodiment of the present invention;
fig. 2 is a schematic cross-sectional view of a high-speed rail pile structure roadbed provided by the embodiment of the invention.
Detailed Description
Those skilled in the art will appreciate that those matters not described in detail in the present specification are not particularly limited to the specific examples described herein.
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, a high-speed rail foundation resonance early warning method based on deep learning provided by the embodiment of the invention is shown, and the method comprises the following steps:
step 101: and pre-burying and arranging the acoustic measurement pipe in the construction process of the high-speed rail pile structure roadbed, and placing the acoustic transmitter and the acoustic receiver.
High-speed railway pilework structure road bed refers to high-speed railway pilework structure road bed cross section schematic diagram as shown in figure 2, includes: a bearing platform plate 1, a roadbed filling 2 and a reinforced concrete pile foundation 3.
The perimeter of a pile foundation of the roadbed with the high-speed iron pile plate structure is prolonged by 4 sound measuring pipes, the connecting lines of the sound measuring pipes are square, the sound measuring pipes are filled with liquid coupling agent, one sound measuring pipe is used for placing a sound wave emitter, and the rest sound measuring pipes are used for placing sound wave receivers.
Step 102: and (2) during the operation of the train, periodically utilizing the sound wave transmitter and the sound wave receiver pre-buried in the step 1 to detect the internal defects of the pile foundation of the high-speed rail pile structure.
Step 103: and (3) processing and inverting the data received by the acoustic wave receiver in the step 102 by adopting a Radon algorithm to obtain a post-pile damage profile of the high-speed railway foundation.
Step 104: importing the damaged section map obtained in the step 103 into Mimics software to reconstruct a three-dimensional model of the roadbed, generating a corresponding finite element model, and applying a vertical load to calculate the comprehensive equivalent modulus of the roadbed; the Mimics are software for three-dimensional reconstruction of sequence images, and provide a highly automated interface to perform format conversion on the established model and combine with finite element software.
The calculation process of the roadbed comprehensive equivalent modulus is as follows:
and applying a load controlled by displacement on the top of the three-dimensional finite element model of the roadbed, extracting a load-strain curve, and taking the slope of the tangent line of the origin as the comprehensive equivalent modulus of the roadbed.
Step 105: recording the roadbed comprehensive equivalent modulus at different moments according to the time sequence, and training the roadbed comprehensive equivalent modulus advanced prediction LSTM model by using the roadbed comprehensive equivalent modulus advanced prediction LSTM model as a data set.
The LSTM model for advanced prediction of roadbed integrated equivalent modulus is written by Matlab and comprises an input layer, a hidden layer and an output layerT n Time of day (subscript n is times)The sequence of the method is as follows,T n the time is the nth time at fixed time intervals) to be recorded in time sequenceT 1 、T 2 、T 3 …T n And taking the roadbed comprehensive equivalent modulus at the moment as a data set, wherein the input parameters are x continuous roadbed comprehensive equivalent moduli (x is less than n), and the number of x and hidden layer units is determined by a grid search method.
And acquiring a roadbed comprehensive equivalent modulus advanced prediction LSTM model updated in real time along with the time.
In thatT i The time being recorded in chronological orderT i+1 、T i+2 、T i+3 …T i+n The roadbed comprehensive equivalent modulus at a moment is taken as a data set to obtainT i And (3) constantly updating the roadbed comprehensive equivalent modulus advanced prediction LSTM model.
The trained LSTM model is adopted to predict the roadbed comprehensive equivalent modulus at the future moment, and the process is as follows:
in thatT n Time of day based onT n The roadbed comprehensive equivalent modulus well trained at any moment is used for predicting the LSTM model in advance so as toT n-x+1 、T n-x+2 、…、T n Predicting the time subgrade comprehensive equivalent modulus (x total) as an input parameterT n+1 The roadbed comprehensive equivalent modulus at any moment;
to be provided withT n-x+2 、…、T n And predictedT n+1 Prediction of roadbed comprehensive equivalent modulus at moment as input parameter (x in total)T n+2 The roadbed comprehensive equivalent modulus at the moment is predicted by analogy to obtain the preset roadbed comprehensive equivalent modulus at the future moment;
step 106: and (3) establishing a finite element model of the bearing plate, uniformly distributing springs for supporting the bottom of the bearing plate, uniformly distributing the spring stiffness as the roadbed comprehensive equivalent modulus value obtained by the calculation in the step 105, and carrying out modal analysis on the bearing plate model to obtain characteristic frequency.
Step 107: setting a resonance thresholdeCalculating the train loading frequency according to the train speed and calculating the loading frequencyThe characteristic frequency of the bearing plate at the future moment predicted in the steps 105 to 106 is obtained, and when the difference between the characteristic frequency value and the train loading frequency value is less thaneWhen, judge that high-speed railway pilework structure road bed easily takes place resonance, send alarm information to control personnel, otherwise withdraw from.
Referring to the schematic cross-sectional view of the high-speed rail pile structure roadbed shown in fig. 2, the roadbed comprises a bearing platform plate 1, roadbed filling 2, a reinforced concrete pile foundation 3, an acoustic pipe 4 and soft soil 5.
According to the scheme provided by the embodiment of the invention, the influence of a pile foundation part in a high-speed rail pile plate structure roadbed on traffic load and an underground complex corrosion environment is considered, and the comprehensive equivalent modulus of the roadbed after the pile foundation is damaged is quantified by combining sound wave CT nondestructive testing, three-dimensional reconstruction and finite element means; a roadbed comprehensive equivalent modulus degradation model based on LSTM deep learning is established to predict bearing plate characteristic frequency change and roadbed potential resonance, so that advanced maintenance and maintenance decisions of related workers are facilitated, and high-speed rail driving safety and passenger riding comfort are improved.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrases "comprising a component of' 8230; \8230;" does not exclude the presence of another like element in a process, method, article, or apparatus that comprises the element.
While the present invention has been described with reference to the embodiments shown in the drawings, the present invention is not limited to the embodiments, which are illustrative and not restrictive, and it will be apparent to those skilled in the art that various changes and modifications can be made therein without departing from the spirit and scope of the invention as defined in the appended claims.
Claims (8)
1. A high-speed railway foundation resonance early warning method based on deep learning is characterized by comprising the following steps:
step 1: pre-burying a sound detection pipe in the construction process of the high-speed rail pile structure roadbed, and placing a sound wave transmitter and a sound wave receiver;
step 2: during the operation of the train, regularly utilizing the sound wave transmitter and the sound wave receiver pre-buried in the step 1 to detect the internal defects of the pile foundation of the high-speed rail pile plate structure roadbed;
and step 3: processing and inverting the data received by the acoustic wave receiver in the step 2 by adopting a Radon algorithm to obtain a post-pile damage profile of the high-speed railway foundation;
and 4, step 4: importing the damaged section map obtained in the step 3 into Mimics software to reconstruct a three-dimensional model of the roadbed, generating a corresponding finite element model and calculating the comprehensive equivalent modulus of the roadbed; the Mimics is software for three-dimensional reconstruction of sequence images, and a highly automated interface is provided to combine format conversion of the established model with finite element software;
and 5: recording the comprehensive equivalent modulus of the roadbed at different moments according to a time sequence, training the comprehensive equivalent modulus advanced prediction LSTM model of the roadbed as a data set, and acquiring the roadbed comprehensive equivalent modulus advanced prediction LSTM model updated in real time along with the time lapse;
step 6: predicting a roadbed comprehensive equivalent modulus value at a future moment by adopting a trained LSTM model;
and 7: establishing a finite element model of the bearing plate, uniformly distributing springs for supporting the bottom of the bearing plate, wherein the rigidity of the uniformly distributed springs is the comprehensive equivalent modulus value of the roadbed calculated in the step 6, and performing modal analysis on the bearing plate model to obtain characteristic frequency;
and 8: calculating the train loading frequency according to the train speed, and setting a resonance threshold value based on the characteristic frequency of the bearing plate at the future moment predicted in the steps 6 and 7eWhen the difference between the characteristic frequency value and the train loading frequency value is less thaneAnd judging that the high-speed rail pile plate structure roadbed is easy to resonate, and outputting alarm information.
2. The high-speed railway subgrade resonance early warning method based on deep learning of claim 1, wherein the high-speed railway pile structure subgrade in the step 1 comprises the following steps: bearing platform board, road bed filler and reinforced concrete pile foundation.
3. The high-speed railway foundation resonance early warning method based on deep learning of claim 1, wherein in step 1, 4 acoustic pipes are arranged along the perimeter of a pile foundation of a roadbed with a high-speed railway pile slab structure, the connecting lines of the acoustic pipes are square, the acoustic pipes are filled with a liquid coupling agent, one of the acoustic pipes is used for placing an acoustic transmitter, and the other acoustic pipes are used for placing an acoustic receiver.
4. The high-speed railway subgrade resonance early warning method based on deep learning as claimed in claim 1, wherein the calculation process of calculating the subgrade comprehensive equivalent modulus in the step 4 is as follows:
and applying a load controlled by displacement on the top of the three-dimensional finite element model of the roadbed, extracting a load-strain curve, and taking the slope of the tangent line of the origin as the comprehensive equivalent modulus of the roadbed.
5. The deep learning-based high-speed railway subgrade resonance early warning method as claimed in claim 1, wherein the road-based integrated equivalent modulus look-ahead LSTM model in step 5 is written by Matlab, and comprises an input layer, a hidden layer and an output layerT n The time of day (the index n is the order,T n time of day is the nth time of day at regular intervals) recorded in chronological orderT 1 、T 2 、T 3 …T n The comprehensive equivalent modulus of the roadbed at a moment is used as a data set, the input parameters are x continuous comprehensive equivalent moduli of the roadbed (x is less than n), and the number of x and hidden layer units is determined by a grid search method.
6. The high-speed railway subgrade resonance early warning method based on deep learning as claimed in claim 1, wherein the step 5 of obtaining the roadbed comprehensive equivalent modulus advanced prediction LSTM model updated in real time along with the time lapse comprises the following steps:
in thatT i The time being recorded in chronological orderT i+1 、T i+2 、T i+3 …T i+n The roadbed comprehensive equivalent modulus at a moment is taken as a data set to obtainT i And (3) constantly updating the roadbed comprehensive equivalent modulus advanced prediction LSTM model.
7. The high-speed railway subgrade resonance early warning method based on deep learning as claimed in claim 1, wherein in step 6, a trained LSTM model is adopted to predict the subgrade comprehensive equivalent modulus at a future time, and the process is as follows:
in thatT n Time of day based onT n The roadbed comprehensive equivalent modulus well trained at any moment is used for predicting the LSTM model in advance so as toT n-x+1 、T n-x+2 、…、T n Predicting the time subgrade comprehensive equivalent modulus (x total) as an input parameterT n+1 The comprehensive equivalent modulus of the roadbed at any moment;
to be provided withT n-x+2 、…、T n And predictedT n+1 Prediction of roadbed comprehensive equivalent modulus at moment as input parameter (x in total)T n+2 And predicting to obtain the preset roadbed comprehensive equivalent modulus at the future moment by analogy.
8. The system adopting any one of the deep learning-based high-speed railway fundamental resonance early warning methods of claims 1 to 7 is characterized by comprising an information acquisition module, a processing module and an early warning module;
the information acquisition module is used for acquiring data received by the sound wave receiver;
the processing module is used for inverting a pile foundation damage profile of the high-speed railway foundation; loading Mimics software to reconstruct a roadbed three-dimensional model according to the damaged section diagram and converting the form and importing the model into finite element software to generate a finite element model; loading a finite element software computing module to compute the comprehensive equivalent modulus of the roadbed; loading a Matlab script, and training a roadbed comprehensive equivalent modulus advanced prediction LSTM model; loading the trained roadbed comprehensive equivalent modulus advanced prediction LSTM model to predict a roadbed comprehensive equivalent modulus value at a future moment; loading finite element software to calculate the characteristic frequency of the bearing plate;
the early warning module is used for judging whether the characteristic frequency of the bearing plate is close to the train loading frequency, if the characteristic frequency of the bearing plate is close to the train loading frequency at a certain future moment, outputting moment information which is possible to generate resonance, and if not, exiting.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210951709.4A CN115266929B (en) | 2022-08-09 | 2022-08-09 | High-speed railway base resonance early warning method and system based on deep learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210951709.4A CN115266929B (en) | 2022-08-09 | 2022-08-09 | High-speed railway base resonance early warning method and system based on deep learning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115266929A true CN115266929A (en) | 2022-11-01 |
| CN115266929B CN115266929B (en) | 2023-05-23 |
Family
ID=83751587
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210951709.4A Active CN115266929B (en) | 2022-08-09 | 2022-08-09 | High-speed railway base resonance early warning method and system based on deep learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115266929B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116366369A (en) * | 2023-05-15 | 2023-06-30 | 成都工业职业技术学院 | Data communication method, communication device and communication terminal in rail transit |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106767583A (en) * | 2016-12-30 | 2017-05-31 | 华中科技大学 | For the longitudinal profile Equivalent Pile footpath computational methods of pile detection sound wave transmission method |
| CN110361207A (en) * | 2019-07-25 | 2019-10-22 | 中南大学 | A kind of intelligence train EEF bogie presence forecasting system and its method |
| CN111562077A (en) * | 2020-07-14 | 2020-08-21 | 中国铁道科学研究院集团有限公司铁道建筑研究所 | High-speed railway roadbed comprehensive test system and method |
| CN111737808A (en) * | 2020-08-06 | 2020-10-02 | 北京大成国测科技有限公司 | Railway roadbed early warning system and method based on artificial neural network |
| CN114491781A (en) * | 2022-04-08 | 2022-05-13 | 西南交通大学 | Ballastless track foundation bed damage early warning method and system considering uncertainty |
| CN114757365A (en) * | 2022-06-13 | 2022-07-15 | 西南交通大学 | High-speed railway roadbed settlement prediction and early warning method based on deep learning |
-
2022
- 2022-08-09 CN CN202210951709.4A patent/CN115266929B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106767583A (en) * | 2016-12-30 | 2017-05-31 | 华中科技大学 | For the longitudinal profile Equivalent Pile footpath computational methods of pile detection sound wave transmission method |
| CN110361207A (en) * | 2019-07-25 | 2019-10-22 | 中南大学 | A kind of intelligence train EEF bogie presence forecasting system and its method |
| CN111562077A (en) * | 2020-07-14 | 2020-08-21 | 中国铁道科学研究院集团有限公司铁道建筑研究所 | High-speed railway roadbed comprehensive test system and method |
| CN111737808A (en) * | 2020-08-06 | 2020-10-02 | 北京大成国测科技有限公司 | Railway roadbed early warning system and method based on artificial neural network |
| CN114491781A (en) * | 2022-04-08 | 2022-05-13 | 西南交通大学 | Ballastless track foundation bed damage early warning method and system considering uncertainty |
| CN114757365A (en) * | 2022-06-13 | 2022-07-15 | 西南交通大学 | High-speed railway roadbed settlement prediction and early warning method based on deep learning |
Non-Patent Citations (3)
| Title |
|---|
| 亓伟: "有砟轨道与无砟轨道垂向振动纵向传递特性差异研究" * |
| 高广运: "高铁桩网复合路基环境振动影响因素分析" * |
| 高盟: "地震-列车移动荷载耦合作用下 高铁路基振动特性研究" * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116366369A (en) * | 2023-05-15 | 2023-06-30 | 成都工业职业技术学院 | Data communication method, communication device and communication terminal in rail transit |
| CN116366369B (en) * | 2023-05-15 | 2023-07-25 | 成都工业职业技术学院 | Data communication method, communication device and communication terminal in rail transit |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115266929B (en) | 2023-05-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Webb et al. | Categories of SHM deployments: Technologies and capabilities | |
| Prendergast et al. | Determining the presence of scour around bridge foundations using vehicle-induced vibrations | |
| Le Pen et al. | The behaviour of railway level crossings: Insights through field monitoring | |
| Olivier et al. | The effect of embankment on high speed rail ground vibrations | |
| Ribeiro et al. | Finite element model updating of a bowstring-arch railway bridge based on experimental modal parameters | |
| Zhang et al. | Importance of load frequency in applying cyclic loads to investigate ballast deformation under high-speed train loads | |
| Rhayma et al. | Reliability analysis of maintenance operations for railway tracks | |
| CN107609304A (en) | The fault diagnosis and prediction system and method based on PHM of LONG-SPAN RAILWAY bridge | |
| Lam et al. | A feasibility study on railway ballast damage detection utilizing measured vibration of in situ concrete sleeper | |
| CN104390629A (en) | Method for determining dynamic load of subway operating train and long-term settlement of tunnel | |
| CN115266929B (en) | High-speed railway base resonance early warning method and system based on deep learning | |
| Berawi | Improving railway track maintenance using power spectral density (PSD) | |
| CN109278053A (en) | A kind of railway tunnel detection method | |
| Kaewunruen et al. | Digital twins for managing railway maintenance and resilience | |
| CN103669428A (en) | Integrity detection system with bearing platform foundation pile | |
| Askarinejad et al. | Field studies on sleeper deflection and ballast pressure in heavy haul track | |
| JP2007051873A (en) | Soundness diagnostic method for structure | |
| Xiong et al. | Time-frequency-based bridge scour identification by trend-change detection | |
| Coelho et al. | Towards network assessment of permanent railway track deformation | |
| Hu et al. | A feasibility study on void detection of cement-emulsified asphalt mortar for slab track system utilizing measured vibration data | |
| Chen et al. | Comparative structural performance assessment of electrified road systems | |
| CN102680078B (en) | Three-dimensional frequency-domain analysis method for adjacent construction vibration caused by metro traffic | |
| Buiter et al. | The role of subduction in the evolution of the Apennines foreland basin | |
| Li et al. | Mud pumping defect detection of high-speed rail slab track based on track geometry data | |
| CN114491781A (en) | Ballastless track foundation bed damage early warning method and system considering uncertainty |
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 |