CN116070327A - Vibration reduction track structure optimization method - Google Patents
Vibration reduction track structure optimization method Download PDFInfo
- Publication number
- CN116070327A CN116070327A CN202310122133.5A CN202310122133A CN116070327A CN 116070327 A CN116070327 A CN 116070327A CN 202310122133 A CN202310122133 A CN 202310122133A CN 116070327 A CN116070327 A CN 116070327A
- Authority
- CN
- China
- Prior art keywords
- track
- optimization
- design
- model
- track structure
- 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
- 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
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/10—Numerical modelling
-
- 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)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Geometry (AREA)
- Biophysics (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Computer Hardware Design (AREA)
- Computing Systems (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Mathematical Physics (AREA)
- Molecular Biology (AREA)
- General Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Biomedical Technology (AREA)
- Computational Linguistics (AREA)
- Pure & Applied Mathematics (AREA)
- Structural Engineering (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Architecture (AREA)
- Medical Informatics (AREA)
- Civil Engineering (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Mathematical Optimization (AREA)
- Physiology (AREA)
- Genetics & Genomics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Train Traffic Observation, Control, And Security (AREA)
Abstract
The invention discloses a vibration reduction track structure optimization method, which comprises the steps of determining an optimization target of a vibration reduction track structure, then establishing a corresponding model for analysis, making a design variable space according to an analysis result, simplifying a model by reducing design variables twice, optimizing multiple targets through a genetic algorithm, selecting a better solution according to the optimization result, and determining optimal design parameters of a track structure after the better solution is imported into a ballastless track-lower foundation structure coupling dynamics analysis model; the whole optimization process is simplified through the reduction of design variables, the optimization effect is good, complex numerical calculation is not needed, and the operation is simple and efficient.
Description
Technical Field
The invention relates to the technical field of rail transit construction, in particular to a vibration reduction rail structure optimization method.
Background
The construction of the rail transit can greatly relieve urban traffic pressure, but a plurality of associated problems inevitably exist, wherein the problems comprise the influence of vehicle-induced vibration on the environment, and the influence of the vibration induced by the train operation on resident life work, use of precise instruments and equipment and the service life of a building structure can be formed to different degrees. Therefore, when the track traffic construction is carried out at present, a large number of track structure designs aiming at vibration reduction and noise reduction areas are required to be carried out.
At present, research on optimization design of foundation structure parameters of the lower part of the ballastless track at home and abroad mainly carries out simulation analysis by establishing a finite element numerical model, but tasks requiring thousands of times of simulation such as multi-parameter optimization design, sensitivity analysis and the like can cause the problems of high calculation difficulty, large calculation amount, limited solution and the like when the finite element model is directly solved. In order to solve the problem of the optimal design of the track structure, the prior invention patent CN201810906834.7 discloses a method for detecting and optimizing the reinforcement of the ballastless track structure, the modeling configuration of the invention is flexible, the invention can be used for the design and selection work of the ballastless track of urban rail transit, and the design scheme of the ballastless track is optimized. The invention patent CN201910994948.6 provides a matching optimization method of a high-speed railway bridge telescopic sleeper lifting device and a track structure, and a reasonable structural form is obtained by utilizing dynamic response and structural strength stability matching property of the sleeper lifting device in a coupling space model based on a finite element method. However, the optimization methods depend on complex numerical technology, have low optimization efficiency, and have low efficiency and complicated use when the vibration reduction structure is optimized.
Disclosure of Invention
Aiming at the defects that the prior art is dependent on complex numerical technology, low in optimization efficiency and inconvenient to use in the vibration reduction structure optimization, the invention provides a vibration reduction track structure optimization method which is simple to use, can realize track structure optimization without depending on complex numerical calculation and is high in optimization efficiency.
In order to achieve the above purpose, the technical scheme of the invention is as follows:
the vibration reduction track structure optimization method comprises the following steps:
s1: determining an optimization target of a vibration reduction track structure according to a track design parameter set of a specific line, and dividing the parameterization design into four sub-targets based on vehicle, wheel track, track power response indexes and track long-term service performance indexes;
s2: based on the optimization targets of the four sub-targets, a vehicle-track-lower foundation structure three-dimensional coupling dynamics model, a train-track-infrastructure space coupling model and a ballastless track-lower foundation structure coupling dynamics analysis model which take material nonlinearity into consideration are established;
s3: calculating to obtain output responses of the vehicle and the track subsystem in the time domain and the low frequency band and output responses of the vehicle and the track subsystem in the middle and high frequency bands, obtaining a proxy model based on an analysis result of the three-dimensional coupling dynamics model, and then making a design variable space;
s4: performing twice reduction on the design variable space;
s5: adopting a genetic algorithm to perform multi-objective optimization, and combining a self-adaptive variation function and a longhorn beetle whisker search algorithm to obtain a series of multi-objective Pareto solutions after variable constraint is changed;
s6: sequentially importing the optimization result of the upper layer into the optimization problem of the lower layer according to the layering optimization sequence of each index of the vehicle, the wheel track and the track until a better solution meeting the design parameters of the track structure of each layer of optimization target is found;
s7: and (3) introducing the optimized track design parameters into a ballastless track-lower foundation structure coupling dynamics analysis model, comparing load transmission and deformation characteristics of the line foundation structures before and after optimization and energy transmission and distribution rules, and researching and determining the optimal design parameters of each layer of structure of the track.
Further, the two-time reduction in the step S4 is specifically as follows:
s41: performing sensitivity analysis between an optimization target and the design parameters of the track structure, and completing one-time reduction of the design variable space;
s42: constructing a deep learning network by utilizing a neural network to obtain an improved neural network proxy model capable of replacing a train-track-infrastructure space coupling model to predict long-term dynamic response;
s43: the improved neural network agent model is utilized for continuous iterative training, an output sample of the current iterative step is used as an input sample of the next iterative step during iterative training, and then a plurality of mutually independent objective functions with four sub-targets are constructed for secondary reduction of a design variable space;
s44: and based on the established improved neural network proxy model, establishing a multi-objective optimization mathematical model of the vibration reduction track structure.
Further, in the step S41, the sensitivity is calculated using a sensitivity formula 4-1, wherein S (ik) is an input x i Influence degree O of performance response index of kth output neuron k The influence of (a) is a sensitivity value; w (W) ij Is the weight matrix from the ith input layer neuron to the jth hidden layer neuron, W jk Is the weight matrix of the j-th hidden layer neuron to the k-th output layer neuron.
Further, in the step S41, the one-time reduction of the design variable space is completed based on the expert priori knowledge and the latin hypercube design method, so as to reduce the dimension of the design variable space.
Further, in step S43, the design variable space completes parameter sensitivity calculation and key parameter identification again through formula 4-1, and performs dimension reduction processing on the high-dimensional multi-objective optimization problem, so as to realize secondary reduction of the design variable space.
Further, in the step S44, a multi-objective optimized mathematical model of the vibration reduction track structure is built through a formula 4-2, wherein x is a 7-dimensional design variable, and comprises a track bed board length L, a width B and a thickness H, a fastener vertical stiffness Ka, a transverse stiffness Kb, a system damping Ks and a sleeper interval L1; f (x) is an objective function, and comprises 3 sub-objective functions of ballastless track weight, wheeltrack sag and transverse force; g (x) is 5 power performance indexes such as derailment coefficient, and the requirement is lower than the existing standard value.
Minf(x)＝min[f 1 (x)，f 2 (x)，f 3 (x)] 4-2
St:x min ≤x i ≤x min i＝1，2...，7
g j (x)≤[g j (x)] j＝i，2...，5
Further, in the step S3, the step of designing the variable space is:
s31: comparing the proxy model response value with the existing experimental value;
s32: determining the value range of the design parameters with larger influence on the four optimization sub-targets;
s32: sampling is carried out in the value range of each design parameter, and a design variable space is generated.
Further, in the step S42, the neural network is one or more combinations of BP neural network, recurrent neural network or long-short-term memory neural network.
Further, the genetic algorithm of the multi-objective optimization in the step S5 is NSGA-II.
Compared with the prior art, the invention has the following advantages and beneficial effects:
1. firstly, determining an optimization target of a shock absorption track structure, then, analyzing by establishing a corresponding model, making a design variable space according to an analysis result, simplifying a model by reducing design variables twice, optimizing a plurality of targets by a genetic algorithm, then, selecting a better solution after optimization, and importing the better solution into a ballastless track-lower base structure coupling dynamics analysis model to determine optimal design parameters of the track structure; the whole optimization process is simplified through the reduction of design variables, the optimization effect is good, complex numerical calculation is not needed, and the operation is simple and efficient.
2. According to the method, the design variable space is reduced once through sensitivity analysis, a deep learning network is built, an improved neural network model is obtained, iterative training is carried out according to the model, a plurality of independent objective functions are built, the design variable space after the primary reduction is reduced twice, complicated calculation of track structure optimization is reduced through the two reduction steps, and the optimization method is simple and reliable.
Drawings
Fig. 1 is a basic operation procedure of a vibration damping track structure optimizing method.
FIG. 2 is a vehicle-rail-lower infrastructure three-dimensional coupled dynamics model of a method of vibration reduction rail structure optimization.
FIG. 3 is a graph of the response of the agent model versus the experimental value for a method of optimizing a vibration damping track structure.
FIG. 4 is a graph of sensitivity of dynamic index to design parameters for a vibration reduction track structure optimization method.
FIG. 5 is a vibration damping track structure optimization the neural network agent model is improved.
FIG. 6 is a multi-objective optimization diagram of a vibration reduction track structure optimization method.
FIG. 7 is a graph comparing dynamic response indexes of train-track systems before and after optimization of a vibration reduction track structure optimization method.
FIG. 8 is a diagram of a vibration reduction ballastless track indoor trial and static power test of a vibration reduction track structure optimization method.
Detailed Description
The invention is further described below with reference to the accompanying drawings.
Example 1:
the vibration reduction track structure optimization method comprises the following steps:
s1: determining an optimization target of a vibration reduction track structure according to a track design parameter set of a specific line, and dividing the parameterization design into four sub-targets based on vehicle, wheel track, track power response indexes and track long-term service performance indexes;
s2: based on the optimization targets of the four sub-targets, a vehicle-track-lower foundation structure three-dimensional coupling dynamics model, a train-track-infrastructure space coupling model and a ballastless track-lower foundation structure coupling dynamics analysis model which take material nonlinearity into consideration are established; wherein the vehicle-track-lower infrastructure three-dimensional coupling dynamics model is shown in fig. 2;
s3: calculating to obtain output responses of the vehicle and the track subsystem in the time domain and the low frequency band and output responses of the vehicle and the track subsystem in the medium and high frequency bands, obtaining a proxy model based on an analysis result of the three-dimensional coupling dynamics model, and then making a design variable space, wherein the steps of designing the variable space are as follows:
s31: comparing the proxy model response value with the existing experimental value, wherein the comparison result is shown in figure 3;
s32: determining the value range of the design parameters with larger influence on the four optimization sub-targets;
s32: sampling in the value range of each design parameter to generate a design variable space, wherein the determined design variables comprise the track bed plate length L, the track bed plate width B, the track bed plate thickness H, the track bed plate material density C, the track bed plate elastic modulus E, the elastic cushion elastic modulus E2, the elastic cushion thickness H2, the fastener vertical rigidity Ka, the fastener transverse rigidity Kb, the sleeper spacing L1, the fastener system damping Cs and the like;
s4: performing twice reduction on the design variable space;
the specific steps of twice reduction are as follows:
s41: developing sensitivity analysis between an optimization target and the design parameters of the track structure, completing one-time reduction of the design variable space based on expert priori knowledge and Latin hypercube design method, reducing the dimension of the design variable space, taking the transverse stiffness of a fastener as an example to make a sensitivity curve of a dynamic index to the design parameters as shown in figure 4, wherein the sensitivity is calculated by adopting a sensitivity formula 4-1, wherein S (ik) is input x i Influence degree O of performance response index of kth output neuron k The influence of (a) is a sensitivity value; w (W) ij Is the weight matrix from the ith input layer neuron to the jth hidden layer neuron, W jk Is the weight matrix from the jth hidden layer neuron to the kth output layer neuron;
s42: constructing a deep learning network by utilizing a neural network to obtain an improved neural network proxy model capable of replacing a train-track-infrastructure space coupling model to predict long-term dynamic response, as shown in fig. 5;
s43: the improved neural network agent model is utilized for continuous iterative training, an output sample of a current iteration step is used as an input sample of a next iteration step during iterative training, then a plurality of mutually independent objective functions of four sub-targets are constructed, parameter sensitivity calculation and key parameter identification are completed again through a formula 4-1 in a design variable space, and dimension reduction processing is carried out on a high-dimensional multi-target optimization problem, so that design variable space secondary reduction is realized;
s44: based on the established improved neural network agent model, establishing a multi-objective optimization mathematical model of the vibration reduction track structure; establishing a multi-objective optimized mathematical model of the vibration reduction track structure through a formula 4-2, wherein x is a 7-dimensional design variable, and comprises the length L, the width B and the thickness H of a track bed board, the vertical rigidity Ka, the transverse rigidity Kb, the system damping Ks and the sleeper interval L1 of a fastener; f (x) is an objective function, and comprises 3 sub-objective functions of ballastless track weight, wheeltrack sag and transverse force; g (x) is 5 power performance indexes such as derailment coefficient, and the requirement is lower than the existing standard value.
Minf(x)＝min[f 1 (x)，f 2 (x)，f 3 (x)] 4-2
St:x min ≤x i ≤x min i＝1，2...，7
g j (x)≤[g j (x)] j＝1，2...，5
S5: adopting a genetic algorithm to perform multi-objective optimization, and combining a self-adaptive variation function and a longhorn beetle whisker search algorithm to obtain a series of multi-objective Pareto solutions after variable constraint is changed;
s6: sequentially importing the optimization results of the upper layer into the optimization problem of the lower layer according to the layering optimization sequence of each index of the vehicle, the wheel track and the track until a better solution meeting the design parameters of the track structure of each layer of the optimization target is found, wherein the result is shown in figure 6;
s7: the optimized track design parameters are imported into a ballastless track-lower foundation structure coupling dynamics analysis model, load transfer, deformation characteristics and energy transfer and distribution rules of the line infrastructure before and after optimization are compared, the optimal design parameters of each layer of the track structure are researched and determined, and as shown in fig. 7, the optimal design parameter combination is finally obtained: l=5.57 m, b=2.8m, h=0.3 m, ka=35 kN/mm, kb=20 kN/mm, cs=50000N/m/s, l1=0.63 m. Through the indoor test and the static test shown in the graph 8, the ballastless track realizes 32.6% weight reduction while meeting the vibration reduction performance, thereby effectively reducing the structural cost and realizing the optimized design of the vibration reduction track structure.
Example 2:
the difference from embodiment 1 is that in step S42, the neural network is one or more combinations of BP neural network, recurrent neural network, or long-short-term memory neural network.
The working principle of this embodiment is the same as that of embodiment 1.
Example 3:
the difference from example 2 is that the genetic algorithm for multi-objective optimization in step S5 is NSGA-II.
The working principle of this embodiment is the same as that of embodiment 2.
In the description of the present invention, numerous specific details are set forth. However, it is understood that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some or all of the technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit of the invention, and are intended to be included within the scope of the appended claims and description.
Claims (9)
1. A vibration reduction track structure optimization method is characterized in that: the method comprises the following steps:
s1: determining an optimization target of a vibration reduction track structure according to a track design parameter set of a specific line, and dividing the parameterization design into four sub-targets based on vehicle, wheel track, track power response indexes and track long-term service performance indexes;
s2: based on the optimization targets of the four sub-targets, a vehicle-track-lower foundation structure three-dimensional coupling dynamics model, a train-track-infrastructure space coupling model and a ballastless track-lower foundation structure coupling dynamics analysis model which take material nonlinearity into consideration are established;
s3: calculating to obtain output responses of the vehicle and the track subsystem in the time domain and the low frequency band and output responses of the vehicle and the track subsystem in the middle and high frequency bands, obtaining a proxy model based on an analysis result of the three-dimensional coupling dynamics model, and then making a design variable space;
s4: performing twice reduction on the design variable space;
s5: adopting a genetic algorithm to perform multi-objective optimization, and combining a self-adaptive variation function and a longhorn beetle whisker search algorithm to obtain a series of multi-objective Pareto solutions after variable constraint is changed;
s6: sequentially importing the optimization result of the upper layer into the optimization problem of the lower layer according to the layering optimization sequence of each index of the vehicle, the wheel track and the track until a better solution meeting the design parameters of the track structure of each layer of optimization target is found;
s7: and (3) introducing the optimized track design parameters into a ballastless track-lower foundation structure coupling dynamics analysis model, comparing load transmission and deformation characteristics of the line foundation structures before and after optimization and energy transmission and distribution rules, and researching and determining the optimal design parameters of each layer of structure of the track.
2. A method of optimizing a vibration absorbing track structure as defined in claim 1, wherein: the two-time reduction of the step S4 is specifically as follows:
s41: performing sensitivity analysis between an optimization target and the design parameters of the track structure, and completing one-time reduction of the design variable space;
s42: constructing a deep learning network by utilizing a neural network to obtain an improved neural network proxy model capable of replacing a train-track-infrastructure space coupling model to predict long-term dynamic response;
s43: the improved neural network agent model is utilized for continuous iterative training, an output sample of the current iterative step is used as an input sample of the next iterative step during iterative training, and then a plurality of mutually independent objective functions with four sub-targets are constructed for secondary reduction of a design variable space;
s44: and based on the established improved neural network proxy model, establishing a multi-objective optimization mathematical model of the vibration reduction track structure.
3. A method of optimizing a vibration absorbing track structure as claimed in claim 2, wherein: in the step S41, the sensitivity is calculated using the sensitivity formula 4-1, where S (ik) is the input x i Influence degree O of performance response index of kth output neuron k The influence of (a) is a sensitivity value; w (W) ij Is the weight matrix from the ith input layer neuron to the jth hidden layer neuron, W jk Is the weight matrix of the j-th hidden layer neuron to the k-th output layer neuron.
4. A method of optimizing a vibration absorbing track structure as claimed in claim 3, wherein: in the step S41, the design variable space is once reduced based on the expert priori knowledge and the latin hypercube design method, and the dimension of the design variable space is reduced.
5. A method of optimizing a vibration absorbing track structure as claimed in claim 3, wherein: in the step S43, the design variable space completes parameter sensitivity calculation and key parameter identification again through the formula 4-1, and performs dimension reduction processing on the high-dimension multi-objective optimization problem, so as to realize secondary reduction of the design variable space.
6. The method for optimizing a vibration reduction track structure according to claim 5, wherein: in the step S44, a multi-objective optimization mathematical model of the vibration reduction track structure is established through a formula 4-2, wherein x is a 7-dimensional design variable, and comprises the length L, the width B and the thickness H of a track bed board, the vertical rigidity Ka, the transverse rigidity Kb, the system damping Ks and the sleeper interval L1 of a fastener; f (x) is an objective function, and comprises 3 sub-objective functions of ballastless track weight, wheeltrack sag and transverse force; g (x) is 5 power performance indexes such as derailment coefficient, and the requirement is lower than the existing standard value.
Minf(x)＝min[f 1 (x)，f 2 (x)，f 3 (x)] 4-2
St:x min ≤x i ≤x min i＝1,2...,7
g j (x)≤[g j (x)] j＝1,2...,5
7. A method of optimizing a vibration absorbing track structure as defined in claim 1, wherein: in the step S3, the step of designing the variable space is:
s31: comparing the proxy model response value with the existing experimental value;
s32: determining the value range of the design parameters with larger influence on the four optimization sub-targets;
s32: sampling is carried out in the value range of each design parameter, and a design variable space is generated.
8. A method of optimizing a vibration absorbing track structure as defined in claim 1, wherein: in the step S42, the neural network is one or more combinations of BP neural network, recurrent neural network or long-short-term memory neural network.
9. A method of optimizing a vibration absorbing track structure as defined in claim 1, wherein: the genetic algorithm of the multi-objective optimization in the step S5 is NSGA-II.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310122133.5A CN116070327B (en) | 2023-02-16 | 2023-02-16 | Vibration reduction track structure optimization method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310122133.5A CN116070327B (en) | 2023-02-16 | 2023-02-16 | Vibration reduction track structure optimization method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116070327A true CN116070327A (en) | 2023-05-05 |
| CN116070327B CN116070327B (en) | 2023-09-29 |
Family
ID=86181852
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310122133.5A Active CN116070327B (en) | 2023-02-16 | 2023-02-16 | Vibration reduction track structure optimization method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116070327B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2007052784A1 (en) * | 2005-11-07 | 2007-05-10 | Keio University | Numerical structure analyzer by load transfer path method |
| CN106930159A (en) * | 2017-05-09 | 2017-07-07 | 隔而固(青岛)振动控制有限公司 | Vibration damping rank type variable railway roadbed and its application process |
-
2023
- 2023-02-16 CN CN202310122133.5A patent/CN116070327B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2007052784A1 (en) * | 2005-11-07 | 2007-05-10 | Keio University | Numerical structure analyzer by load transfer path method |
| CN106930159A (en) * | 2017-05-09 | 2017-07-07 | 隔而固(青岛)振动控制有限公司 | Vibration damping rank type variable railway roadbed and its application process |
Non-Patent Citations (5)
| Title |
|---|
| 周信: "地铁弹性车轮的减振降噪及动态特性研究", 《中国博士学位论文全文库》 * |
| 张剑: "基于代理模型技术的高速列车性能参数设计及优化", 《中国博士学位论文全文库》 * |
| 江茂;李军;: "城市轨道交通噪声分析及其控制措施", 装备机械, no. 03 * |
| 王继军;王梦;刘伟斌;赵勇;: "CRTSⅢ型板式无砟轨道系统技术", 中国铁路, no. 08 * |
| 许光辉: "多层弹性轨道结构的动力参数优化与减振控制研究", 《中国博士学位论文全文库》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116070327B (en) | 2023-09-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Jiang et al. | Dynamic wavelet neural network for nonlinear identification of highrise buildings | |
| Mackie et al. | Performance‐based seismic bridge design for damage and loss limit states | |
| CN101281116B (en) | Wide span rail traffic bridge damnification detecting system | |
| CN114997027B (en) | Method for intelligently solving random signals of axle system | |
| CN113283160B (en) | Vibration prediction method for railway overhead line environment under influence of multiple random variables | |
| Wang et al. | Optimizing the static–dynamic performance of the body-in-white using a modified non-dominated sorting genetic algorithm coupled with grey relational analysis | |
| Xiang et al. | Seismic response prediction of a train-bridge coupled system based on a LSTM neural network | |
| Fan et al. | A novel hybrid algorithm for solving multiobjective optimization problems with engineering applications | |
| Dong et al. | Robust optimization design method for structural reliability based on active-learning MPA-BP neural network | |
| CN116070327B (en) | Vibration reduction track structure optimization method | |
| Wang et al. | A novel optimal fuzzy integrated control method of active suspension system | |
| Yan et al. | Modeling and parameter optimization of dynamic characteristic variables of ballast bed during operation for dynamic track stabilizer | |
| CN105628868A (en) | Undersampled signal impact positioning processing method and system for compound material structure | |
| Lin et al. | Dynamic finite element model updating of prestressed concrete continuous box-girder bridge | |
| CN106682312A (en) | Industrial process soft-measurement modeling method of local weighing extreme learning machine model | |
| Yang | Construction of graduate behavior dynamic model based on dynamic decision tree algorithm | |
| Zeng et al. | Response prediction of stochastic dynamics by neural networks: theory and application on railway vehicles | |
| Xu et al. | Neural network predictive control of vehicle suspension | |
| CN103034754B (en) | The data processing subdivided modeling method of the Decoupling Mode of body lightening design | |
| Yang et al. | Application of uncertainty reasoning based on cloud theory in spatial load forecasting | |
| CN111126867B (en) | Service sensitivity analysis method for multi-domain association of track system | |
| Chen et al. | GA-LQR for vehicle semi-active suspension with BiLSTM inverse model of magnetic rheological damper | |
| Du et al. | Simulation of spatially varying ground motion of urban buildings based on wavelet packet neural network | |
| Wu et al. | Train‐Bridge Dynamic Behaviour of Long‐Span Asymmetrical‐Stiffness Cable‐Stayed Bridge | |
| Zhang et al. | Multi-objective optimization design of assembled wheel lightweight based on implicit parametric method and modified NSGA-II |
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 |