CN117874479B - Heavy-duty locomotive coupler force identification method based on data driving - Google Patents
Heavy-duty locomotive coupler force identification method based on data driving Download PDFInfo
- Publication number
- CN117874479B CN117874479B CN202410274777.0A CN202410274777A CN117874479B CN 117874479 B CN117874479 B CN 117874479B CN 202410274777 A CN202410274777 A CN 202410274777A CN 117874479 B CN117874479 B CN 117874479B
- Authority
- CN
- China
- Prior art keywords
- parameters
- model
- data
- heavy
- relative displacement
- 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
- 238000000034 method Methods 0.000 title claims abstract description 28
- 230000003137 locomotive effect Effects 0.000 title claims abstract description 15
- 238000006073 displacement reaction Methods 0.000 claims abstract description 24
- 238000012549 training Methods 0.000 claims abstract description 15
- 238000012360 testing method Methods 0.000 claims abstract description 14
- 238000005457 optimization Methods 0.000 claims abstract description 12
- 238000012795 verification Methods 0.000 claims abstract description 11
- 238000001914 filtration Methods 0.000 claims abstract description 10
- 238000009499 grossing Methods 0.000 claims abstract description 8
- 230000004913 activation Effects 0.000 claims abstract description 7
- 210000002569 neuron Anatomy 0.000 claims abstract description 6
- 238000012545 processing Methods 0.000 claims abstract description 6
- 210000003608 fece Anatomy 0.000 claims description 33
- 241000254173 Coleoptera Species 0.000 claims description 27
- 238000005096 rolling process Methods 0.000 claims description 10
- 239000013598 vector Substances 0.000 claims description 9
- 241001229848 Aphodius granarius Species 0.000 claims description 7
- 230000008569 process Effects 0.000 claims description 7
- 238000010606 normalization Methods 0.000 claims description 6
- 244000144987 brood Species 0.000 claims description 5
- 230000002159 abnormal effect Effects 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims description 3
- 238000012544 monitoring process Methods 0.000 abstract description 6
- 230000006870 function Effects 0.000 description 10
- 238000011161 development Methods 0.000 description 3
- 230000006872 improvement Effects 0.000 description 3
- 230000007774 longterm Effects 0.000 description 3
- 230000007547 defect Effects 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000003245 coal Substances 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012805 post-processing Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000010200 validation analysis Methods 0.000 description 1
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B61—RAILWAYS
- B61G—COUPLINGS; DRAUGHT AND BUFFING APPLIANCES
- B61G7/00—Details or accessories
- B61G7/14—Safety devices
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B61—RAILWAYS
- B61L—GUIDING RAILWAY TRAFFIC; ENSURING THE SAFETY OF RAILWAY TRAFFIC
- B61L15/00—Indicators provided on the vehicle or train for signalling purposes
- B61L15/0081—On-board diagnosis or maintenance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/10—Pre-processing; Data cleansing
- G06F18/15—Statistical pre-processing, e.g. techniques for normalisation or restoring missing data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/217—Validation; Performance evaluation; Active pattern learning techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/02—Preprocessing
- G06F2218/04—Denoising
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Mechanical Engineering (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Computing Systems (AREA)
- Probability & Statistics with Applications (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Molecular Biology (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
Abstract
The invention discloses a heavy-duty locomotive coupler force identification method based on data driving, which relates to the technical field of heavy-duty locomotive coupler state monitoring and comprises the following steps: collecting longitudinal relative displacement signals of a coupler body of a heavy-duty train; smoothly processing a longitudinal relative displacement signal of the coupler body; intercepting the longitudinal relative displacement signals of the coupler body after filtering and smoothing by adopting a sliding window, extracting the relative speed characteristics in each section of relative displacement signals, and constructing a data set; normalizing the data set; establishing a DBO-ELM model, taking the number of neurons of an ELM hidden layer, penalty parameters and activation function parameters as optimization parameters, taking the mean square error of a verification set identification result as an fitness function, and carrying out iterative optimization on the DBO-ELM model parameters by using the verification set; training the model by using a training set after obtaining the optimal parameters of the model; inputting the test set sample into the trained model, and determining the accuracy of the trained model according to the error of the coupler force recognition result; the invention has the advantages of low cost and high efficiency.
Description
Technical Field
The invention relates to the technical field of heavy-duty locomotive coupler state monitoring, in particular to a heavy-duty locomotive coupler force identification method based on data driving.
Background
As one of two development directions of railways in the world, the heavy load of cargo transportation provides guarantee for the rapid development of economy and society. The transportation of the road goods has the characteristics of large transportation capacity, low energy consumption, high reliability and the like, and particularly rapid development in countries with large specific gravity of large quantities of the goods such as coal, ore and the like. However, under complex operation conditions and operation delay caused by air wave speed, as the marshalling is continuously enlarged and the axle weight is continuously increased, the traction braking operation difficulty is increased, the heavy-duty train operates to generate more intense longitudinal impulse, and the longitudinal impulse at the middle locomotive of the currently-used twenty-thousand ton heavy-duty train is particularly intense. The coupler bears random and alternating pulling force, compression force, impact force and other actions in the train operation, and many train accidents are caused by the fact that the coupler is stressed beyond relevant indexes.
At present, a common car coupler state monitoring method is to install a force measuring car coupler device, wherein strain gauges are arranged on two sides of a car coupler body to form a full-bridge circuit, a load is applied on a car coupler force calibration test bed to obtain a calibration coefficient, and then a car coupler force signal is obtained through acquisition and post-processing of the strain signal; the method is influenced by complex running conditions of the train, the problems of damage to equipment such as strain gauge damage, loose adhesion, complete falling off after long-term use and the like are easily caused, a special car coupler calibration test bed is required to be used for acquiring calibration coefficients, and the car coupler force measuring equipment needs to be manufactured again after damage, so that the problems of high monitoring cost, high maintenance difficulty and the like are caused.
Disclosure of Invention
In order to solve the problems in the prior art, the invention aims to provide a heavy-duty locomotive coupler force identification method based on data driving.
In order to achieve the above purpose, the invention adopts the following technical scheme: a method for recognizing the coupler force of a heavy-duty locomotive based on data driving comprises the following steps:
step 1, acquiring longitudinal relative displacement signals of a coupler body of a heavy-duty train under different working conditions;
Step2, adopting low-pass filtering and weighted average smoothing to process the longitudinal relative displacement signal of the coupler body, filtering out signal noise generated by external environment, and eliminating abnormal signal values;
step 3, intercepting the longitudinal relative displacement signals of the coupler body after filtering and smoothing by adopting a sliding window, extracting the relative speed characteristics in each section of relative displacement signals, and constructing a data set by utilizing the processed signals;
step 4, carrying out normalization processing on the data set and dividing a training set, a verification set and a test set;
step 5, establishing a DBO-ELM model, taking the number of neurons of an ELM hidden layer, penalty parameters and activation function parameters as optimization parameters, taking the mean square error of the identification result of the verification set as a fitness function, and carrying out iterative optimization on the DBO-ELM model parameters by using the verification set;
step 6, training the model by using a training set after obtaining optimal parameters of the model;
And 7, inputting the test set sample into the trained model, and determining the accuracy of the trained model according to the error of the coupler force recognition result.
As a further improvement of the present invention, in the step 3, the window length of the sliding window is 500 to 2000 data points, the moving step length of the sliding window is 10 to 50 data points, and the relative velocity is characterized by the relative velocity of each data point and the first data point in the relative displacement signal of the segment.
As a further improvement of the present invention, in the step 4, the normalization processing is specifically performed on the data set as follows:
；
In the method, in the process of the invention, For normalized data,/>For data to be normalized in a sample,/>As the maximum value in the data set,Is the minimum in the dataset.
As a further improvement of the present invention, the step 5 specifically includes the steps of:
step 5.1, determining input variables and output variables of the DBO-ELM model;
Step 5.2, ELM activation function selecting Sigmoid function with controllable parameters added To achieve a nonlinear mapping as shown in the following equation:
；
Wherein: To input samples,/> Controllable parameters added for Sigmoid functions;
step 5.3, determining parameters to be optimized: ELM hidden layer neuron number Penalty parameter/>And controllable parameters/>; Determining the population scale/>, of dung beetlesMaximum number of iterations/>Ratio of rolling ball dung beetles, brooding dung beetles, small dung beetles and thieves, deflection coefficient/>Position updating parameter/> of ball dung beetleThieves update rule parameters/>; The updating formulas of the rolling ball dung beetles, brood dung beetles and thieves are as follows:
；
Wherein: Representing the current iteration number,/> And/>Respectively represent the/>First time of iteration/>Position information of ball dung beetles, brood dung beetles, small dung beetles and thieves only, and method for realizing position information of ball dung beetlesIndicating deflection coefficient,/>Representing the update parameters of the position of the ball dung beetles,/>Representing natural coefficients,/>Representing global worst position,/>Representing the optimal position of all individuals within the current population,/>Representing the best location of the thief individual within the current population,/>Representing the lower limit of the range of values of the position information x,/>Representing the upper limit of the range of values of the position information x,/>And/>Representing two independent random vectors of size 1×D, D representing the dimension of the optimization problem,/>Representing random numbers subject to normal distribution,/>Representing a random vector,/>Representing a random vector of size 1 x D following a normal distribution,/>Representing a thief updating the rule parameters.
The beneficial effects of the invention are as follows:
1. The invention recognizes the coupler force by extracting the longitudinal relative displacement signal of the coupler body, overcomes the defect that the force measuring coupler device is required to be manufactured and installed in the traditional method, and has the advantages of low cost and high efficiency.
2. The DBO algorithm is used for optimizing the number of neurons in the ELM hidden layer, punishment parameters and activation function parameters, the mean square error of the actual result and the predicted result of the verification set is taken as the fitness function, the optimal model parameters of the ELM are obtained through repeated iterative optimization, the defect of low recognition accuracy caused by manual selection of the parameters of the ELM is overcome, and the method is further applied to coupler force recognition to improve the recognition accuracy.
Drawings
FIG. 1 is a flow chart of a method for recognizing the coupler force of a heavy-duty locomotive according to an embodiment of the invention;
FIG. 2 is an iterative graph of fitness in a coupler force recognition model parameter optimization process in an embodiment of the invention;
FIG. 3 is a diagram of the coupler force recognition result in an embodiment of the present invention.
Detailed Description
Embodiments of the present invention will be described in detail below with reference to the accompanying drawings.
Examples
In recent years, a mechanical learning algorithm is rapidly developed in the field of heavy-load railway fault diagnosis such as wheel polygon recognition, track shortwave damage detection and the like, and long-term monitoring of heavy-load trains is realized based on a data driving technology by collecting signals only through simple sensors such as displacement, acceleration and the like. In order to realize long-term monitoring of locomotive coupler force and reduce maintenance cost of coupler force measuring equipment, the embodiment provides a heavy-load locomotive coupler force identification method based on data driving.
As shown in fig. 1, the method specifically includes:
1) The method comprises the steps of collecting longitudinal relative displacement signals of a coupler body of a heavy-duty train under different working conditions;
In the specific implementation mode, the longitudinal relative displacement of the coupler body under the operation condition of the heavy-duty locomotive is collected at the sampling frequency of 200Hz by establishing a locomotive-truck coupling dynamics simulation model.
2) Adopting low-pass filtering and weighted average smoothing to process the longitudinal relative displacement signal of the coupler body, filtering out signal noise generated by external environment, and eliminating the deviation of the measured value of the longitudinal relative displacement of the coupler body caused by sensor test faults;
In the specific implementation, the cut-off frequency of the adopted low-pass filter is 70Hz, the weighted average smoothing parameter is 200, and the abnormal value of the longitudinal relative displacement of the coupler body is removed.
3) Intercepting the longitudinal relative displacement signal of the coupler body after filtering and smoothing by adopting a sliding window, wherein the window length of the sliding window is 1000 data points, and the moving step length of the sliding window is 50 data points; extracting the relative speed characteristics in each section of relative displacement signal, and constructing a data set by using the processed signals;
In particular, the relative velocity of each data point and the first data point in each segment of the displacement signal is selected as the relative velocity characteristic of the segment of the signal.
4) Carrying out normalization processing on the data set, and dividing a training set, a verification set and a test set; the data set normalization process is shown in formula (1):
（1）；
In the method, in the process of the invention, For normalized data,/>For data to be normalized in a sample,/>As the maximum value in the data set,Is the minimum in the dataset.
In specific implementation, a training set in the data set is used for training a model, a verification set is used for optimizing model parameters, and a test set is used for testing the recognition effect of the model on the coupler force; the ratio of training set, validation set and test set is 4:1:1.
5) The DBO-ELM model is built, and the specific steps are as follows:
Step 5.1: input and output variables of the DBO-ELM model are determined.
Step 5.2: the ELM activation function selects the Sigmoid function to which the controllable parameters are added to achieve a nonlinear mapping, as shown in the following equation.
（2）；
Wherein: To input samples,/> Controllable parameters added for Sigmoid functions.
Step 5.3: determining parameters to be optimized; determining dung beetle population scaleMaximum number of iterations/>Ratio of rolling ball dung beetles, brooding dung beetles, small dung beetles and thieves, deflection coefficient/>Position updating parameter/> of ball dung beetleThieves update rule parameters/>; The updating formulas of the rolling ball dung beetles, brood dung beetles and thieves are as follows:
；
Wherein: Representing the current iteration number,/> And/>Respectively represent the/>First time of iteration/>Position information of ball dung beetles, brood dung beetles, small dung beetles and thieves only, and method for realizing position information of ball dung beetlesIndicating deflection coefficient,/>Representing the update parameters of the position of the ball dung beetles,/>Representing natural coefficients,/>Representing global worst position,/>Representing the optimal position of all individuals within the current population,/>Representing the best location of the thief individual within the current population,/>Representing the lower limit of the range of values of the position information x,/>Representing the upper limit of the range of values of the position information x,/>And/>Representing two independent random vectors of size 1×D, D representing the dimension of the optimization problem,/>Representing random numbers subject to normal distribution,/>Representing a random vector,/>Representing a random vector of size 1 x D following a normal distribution,/>Representing a thief updating the rule parameters.
In specific implementation, the population scale of the dung beetles30, Maximum iteration number/>100 Parts of the ratio of the rolling ball dung beetles to the brooding dung beetles to the small dung beetles to the thieves is 6:6:7:11, and the deflection coefficient/>0.1, The position update parameter of the ball dung beetle/>Updating rule parameters for 0.3, thieves/>0.5. And carrying out iterative optimization for 100 times according to the parameters to obtain an ELM optimal parameter combination, wherein the standard of the iteration end graph is that the iteration times reach 100 times, and the iteration result is shown in figure 2.
6) After the optimal parameters of the model are obtained, training is carried out on the model by utilizing a training set
In specific implementation, the optimized parameters in the model are set to optimized values, and then the training set is input into the ELM model to train the weight parameters between the hidden layer and the output layer.
7) And identifying the coupler force of the test set, and determining the accuracy of the model.
In a specific implementation, the test set sample is input into the trained model, and the mechanical energy of the output result is inversely normalized, so that the coupler force recognition result can be obtained, as shown in fig. 3. The mean square error of the coupler force recognition result is 8.586, the error is proved to be extremely small, and the constructed model can be used for recognizing the coupler force.
The foregoing examples merely illustrate specific embodiments of the invention, which are described in greater detail and are not to be construed as limiting the scope of the invention. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the invention, which are all within the scope of the invention.
Claims (3)
1. The method for recognizing the coupler force of the heavy-duty locomotive based on data driving is characterized by comprising the following steps of:
step 1, acquiring longitudinal relative displacement signals of a coupler body of a heavy-duty train under different working conditions;
Step2, adopting low-pass filtering and weighted average smoothing to process the longitudinal relative displacement signal of the coupler body, filtering out signal noise generated by external environment, and eliminating abnormal signal values;
step 3, intercepting the longitudinal relative displacement signals of the coupler body after filtering and smoothing by adopting a sliding window, extracting the relative speed characteristics in each section of relative displacement signals, and constructing a data set by utilizing the processed signals;
step 4, carrying out normalization processing on the data set and dividing a training set, a verification set and a test set;
step 5, establishing a DBO-ELM model, taking the number of neurons of an ELM hidden layer, penalty parameters and activation function parameters as optimization parameters, taking the mean square error of the identification result of the verification set as a fitness function, and carrying out iterative optimization on the DBO-ELM model parameters by using the verification set;
The step 5 specifically comprises the following steps:
step 5.1, determining input variables and output variables of the DBO-ELM model;
Step 5.2, ELM activation function selects Sigmoid function σ (x) with controllable parameters added to implement nonlinear mapping, as shown in the following equation:
wherein: x is an input sample, and alpha is a controllable parameter added by a Sigmoid function;
Step 5.3, determining parameters to be optimized: the ELM hidden layer neuron number m, penalty parameter L and controllable parameter alpha; determining a population scale P of the dung beetles, a maximum iteration number N, proportions of the rolling ball dung beetles, brooding dung beetles, small dung beetles and thieves, a deflection coefficient k, a rolling ball dung beetle position updating parameter b and a thief updating rule parameter S; the updating formulas of the rolling ball dung beetles, brood dung beetles and thieves are as follows:
x1i(t+1)＝x1i(t)+a×k×x1i(t-1)+b×|x1i(t)-Xw
x2i(t+1)＝X*+b1×(x2i(t)-Lb*)+b2×(x3i(t)-Ub*)
x3i(t+1)＝x3i(t)+C1×(x3i(t)-Lbb)+C2×(x3i(t)-Ubb)
x4i(t+1)＝Xb+S×g×(x4i(t)-X*|+x4i(t)-Xb)
Wherein: t represents the current iteration times, X 1i(t)、x2i(t)、x3i (t) and X 4i (t) represent the position information of i-th rolling ball dung beetles, brooding dung beetles, small dung beetles and thieves respectively in the t-th iteration, k represents an indication deflection coefficient, b represents a rolling ball dung beetle position updating parameter, a represents a natural coefficient, X w represents a global worst position, X * represents the optimal position of all individuals in the current population, X b represents the optimal position of thieves in the current population, ub represents the lower limit of the value range of the position information X, lb represents the upper limit of the value range of the position information X, b 1 and b 2 represent two independent random vectors with the size of 1 xD, D represents the dimension of an optimization problem, C 1 represents random numbers conforming to normal distribution, C 2 represents random vectors, g represents random vectors conforming to the normal distribution and the size of 1 xD, and S represents thief updating rule parameters;
step 6, training the model by using a training set after obtaining optimal parameters of the model;
And 7, inputting the test set sample into the trained model, and determining the accuracy of the trained model according to the error of the coupler force recognition result.
2. The method of claim 1, wherein in step 3, the sliding window has a window length of 500 to 2000 data points, the sliding window has a moving step length of 10 to 50 data points, and the relative velocity is characterized by a relative velocity between each data point and the first data point in the segment of the relative displacement signal.
3. The method for recognizing the coupler force of the heavy-duty locomotive based on data driving according to claim 2, wherein in the step 4, the normalization processing of the data set is specifically as follows:
wherein, C' is normalized data, C is data to be normalized in the sample, C max is the maximum value in the data set, and C min is the minimum value in the data set.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410274777.0A CN117874479B (en) | 2024-03-11 | 2024-03-11 | Heavy-duty locomotive coupler force identification method based on data driving |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410274777.0A CN117874479B (en) | 2024-03-11 | 2024-03-11 | Heavy-duty locomotive coupler force identification method based on data driving |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117874479A CN117874479A (en) | 2024-04-12 |
| CN117874479B true CN117874479B (en) | 2024-05-24 |
Family
ID=90579470
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410274777.0A Active CN117874479B (en) | 2024-03-11 | 2024-03-11 | Heavy-duty locomotive coupler force identification method based on data driving |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117874479B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118209337B (en) * | 2024-05-16 | 2024-08-20 | 山东新戈锐能源科技有限公司 | Railway vehicle operation safety testing system |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112085077A (en) * | 2020-08-28 | 2020-12-15 | 东软集团股份有限公司 | Method and device for determining lane change of vehicle, storage medium and electronic equipment |
| CN112947056A (en) * | 2021-03-04 | 2021-06-11 | 北京交通大学 | Magnetic-levitation train displacement speed tracking control method based on IGWO-BP-PID |
| CN113392900A (en) * | 2021-06-11 | 2021-09-14 | 西南交通大学 | Electric locomotive idling online identification method based on fuzzy entropy and kernel limit learning machine |
| CN113761660A (en) * | 2021-09-10 | 2021-12-07 | 南京工程学院 | Vehicle-mounted flywheel dynamic modeling method based on data driving and mechanism model fusion |
| CN114781252A (en) * | 2022-04-13 | 2022-07-22 | 杭州电子科技大学 | SVM band saw blade abrasion identification method based on improved artificial bee colony algorithm |
| CN115758780A (en) * | 2022-11-29 | 2023-03-07 | 中车株洲电力机车有限公司 | Train coupler stress monitoring method, system, terminal and storage medium |
| CN116339190A (en) * | 2023-02-16 | 2023-06-27 | 株洲中车时代电气股份有限公司 | Train operation control method based on non-reference track model predictive control |
| CN116467570A (en) * | 2023-06-16 | 2023-07-21 | 西南交通大学 | Heavy-duty locomotive coupler swing angle quantitative identification method based on data driving |
| CN117048667A (en) * | 2023-08-24 | 2023-11-14 | 北京全路通信信号研究设计院集团有限公司 | Heavy-duty train control method and system based on vehicle dynamic response identification |
| CN117217374A (en) * | 2023-09-11 | 2023-12-12 | 云南电网有限责任公司红河供电局 | Short-term wind power prediction method based on DBO-ELM |
| CN117272116A (en) * | 2023-10-13 | 2023-12-22 | 西安工程大学 | Transformer fault diagnosis method based on LORAS balance data set |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB201611326D0 (en) * | 2016-06-29 | 2016-08-10 | Optasense Holdings Ltd | Distributed fibre optic sensing for rail monitoring |
| AU2020230855A1 (en) * | 2019-03-04 | 2021-08-12 | Central Queensland University | Control system for operating long vehicles |
| CN110443002A (en) * | 2019-08-16 | 2019-11-12 | 中国水利水电科学研究院 | A kind of Deformation of Steep Slopes prediction technique and system |
-
2024
- 2024-03-11 CN CN202410274777.0A patent/CN117874479B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112085077A (en) * | 2020-08-28 | 2020-12-15 | 东软集团股份有限公司 | Method and device for determining lane change of vehicle, storage medium and electronic equipment |
| CN112947056A (en) * | 2021-03-04 | 2021-06-11 | 北京交通大学 | Magnetic-levitation train displacement speed tracking control method based on IGWO-BP-PID |
| CN113392900A (en) * | 2021-06-11 | 2021-09-14 | 西南交通大学 | Electric locomotive idling online identification method based on fuzzy entropy and kernel limit learning machine |
| CN113761660A (en) * | 2021-09-10 | 2021-12-07 | 南京工程学院 | Vehicle-mounted flywheel dynamic modeling method based on data driving and mechanism model fusion |
| CN114781252A (en) * | 2022-04-13 | 2022-07-22 | 杭州电子科技大学 | SVM band saw blade abrasion identification method based on improved artificial bee colony algorithm |
| CN115758780A (en) * | 2022-11-29 | 2023-03-07 | 中车株洲电力机车有限公司 | Train coupler stress monitoring method, system, terminal and storage medium |
| CN116339190A (en) * | 2023-02-16 | 2023-06-27 | 株洲中车时代电气股份有限公司 | Train operation control method based on non-reference track model predictive control |
| CN116467570A (en) * | 2023-06-16 | 2023-07-21 | 西南交通大学 | Heavy-duty locomotive coupler swing angle quantitative identification method based on data driving |
| CN117048667A (en) * | 2023-08-24 | 2023-11-14 | 北京全路通信信号研究设计院集团有限公司 | Heavy-duty train control method and system based on vehicle dynamic response identification |
| CN117217374A (en) * | 2023-09-11 | 2023-12-12 | 云南电网有限责任公司红河供电局 | Short-term wind power prediction method based on DBO-ELM |
| CN117272116A (en) * | 2023-10-13 | 2023-12-22 | 西安工程大学 | Transformer fault diagnosis method based on LORAS balance data set |
Non-Patent Citations (4)
| Title |
|---|
| Development and validation of a new code for longitudinal train dynamics simulation;Nicola Bosso等;《Proceedings of the Institution of Mechanical Engineers》;20200507;第235卷(第3期);第1-14页 * |
| 制动缸活塞行程对列车纵向动力学性能影响仿真研究;黎启玄等;《交通技术》;20230315;第12卷(第2期);第120-131页 * |
| 基于集成学习的重载列车辅助驾驶策略生成与优化研究;兰红勇;《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》;20230715(第7期);第C033-271页 * |
| 考虑纵向动力学的重载列车运行控制技术研究;郭金松;《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》;20220515(第5期);第C033-481页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117874479A (en) | 2024-04-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117874479B (en) | Heavy-duty locomotive coupler force identification method based on data driving | |
| CN101281116B (en) | Wide span rail traffic bridge damnification detecting system | |
| CN107379899B (en) | A kind of tire condition intelligent monitor system based on wireless sensor network | |
| CN100520317C (en) | Fixed type vehicle dynamic weighting system | |
| CN111581867B (en) | Rapid bridge damage detection method | |
| CN102063641A (en) | Method for forecasting wind speed of high speed railway line | |
| CN111027256A (en) | Bridge risk prediction method and system based on vehicle load spatial distribution | |
| Man et al. | AttGGCN model: A novel multi-sensor fault diagnosis method for high-speed train bogie | |
| CN112381027B (en) | Wheel polygon wave depth estimation method based on train axle box vertical acceleration signal | |
| CN106895900B (en) | Method based on the bridge dynamic strain identification bicycle number of axle | |
| CN114964781B (en) | Intelligent diagnosis method for train bearing faults | |
| CN106096096A (en) | Train suspension system failure analysis methods based on MPCA and system | |
| CN116881819B (en) | Stay cable working state monitoring method based on isolated forest | |
| CN104008644A (en) | Urban road traffic noise measurement method based on gradient descent | |
| CN115758258B (en) | Traction transformer fault diagnosis method based on vibration signals and domain knowledge | |
| CN115545101A (en) | High-speed train bogie fault diagnosis method based on residual error neural network | |
| CN116297841A (en) | Railway track disease identification method based on optical fiber distributed vibration detection | |
| Huang et al. | Slipping detection of electric locomotive based on empirical wavelet transform, fuzzy entropy algorithm and support vector machine | |
| CN115290133A (en) | Method and system for monitoring track structure at joint of light rail platform | |
| CN116467570B (en) | Heavy-duty locomotive coupler swing angle quantitative identification method based on data driving | |
| CN117668689A (en) | Rail transit train bearing fault diagnosis method and device based on meta-learning algorithm | |
| CN115828086B (en) | Heavy-duty locomotive coupler instability early warning method based on vehicle body lateral acceleration | |
| CN117312962A (en) | Long-service elevator guide rail fault diagnosis method based on transfer learning and data driving | |
| CN113159179B (en) | Subway and subway bogie running state identification method and system | |
| CN205388511U (en) | Dynamic vehicle weighing system |
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 |