CN113935189A - Train braking capacity prediction method, electronic equipment and computer storage medium - Google Patents
Train braking capacity prediction method, electronic equipment and computer storage medium Download PDFInfo
- Publication number
- CN113935189A CN113935189A CN202111288826.9A CN202111288826A CN113935189A CN 113935189 A CN113935189 A CN 113935189A CN 202111288826 A CN202111288826 A CN 202111288826A CN 113935189 A CN113935189 A CN 113935189A
- Authority
- CN
- China
- Prior art keywords
- train
- factors
- mathematical model
- train braking
- braking capacity
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/21—Design, administration or maintenance of databases
- G06F16/215—Improving data quality; Data cleansing, e.g. de-duplication, removing invalid entries or correcting typographical errors
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/15—Vehicle, aircraft or watercraft design
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Computer Hardware Design (AREA)
- Mathematical Optimization (AREA)
- Databases & Information Systems (AREA)
- Pure & Applied Mathematics (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Operations Research (AREA)
- Life Sciences & Earth Sciences (AREA)
- Automation & Control Theory (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Aviation & Aerospace Engineering (AREA)
- Probability & Statistics with Applications (AREA)
- Algebra (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Quality & Reliability (AREA)
- Electric Propulsion And Braking For Vehicles (AREA)
Abstract
The application provides a train braking capacity prediction method, electronic equipment and a computer storage medium, wherein the method is used for combing influence factors influencing the train braking capacity; depending on actual lines and vehicles, carrying out field experiments on the influence factors to obtain experimental data; analyzing the experimental data to determine main factors influencing the braking capacity of the train; establishing a train braking capability mathematical model based on the main factors; training a train braking capacity mathematical model based on a neural network to obtain a trained train braking capacity mathematical model; and predicting the braking capacity of the train according to the trained mathematical model of the braking capacity of the train. According to the method, the influence factors influencing the train braking capacity are combed, field experiments are carried out on the basis of actual lines and vehicles, then a train braking capacity mathematical model is established, the train braking capacity is predicted according to the trained train braking capacity mathematical model, and more reliable and accurate prediction results can be obtained.
Description
Technical Field
The present application relates to the field of rail transit technologies, and in particular, to a train braking capability prediction method, an electronic device, and a computer storage medium.
Background
With the increasing running speed of trains, the safety of trains is becoming the focus of attention. As a key system for train operation safety, the performance of a brake system is more prominent. In a train safety protection model, the emergency braking rate of a train is usually a small value due to safety consideration, an actual train can have better braking performance under most conditions, and as a result, the braking distance calculated theoretically is larger, so that the train tracking interval is increased, and the running efficiency is reduced.
At present, a modeling mode is adopted to predict the braking capacity of the train. During prediction, factors of the influence factors are determined based on the experimental environment, experimental data are obtained, a model is built based on the influence factors, and the experimental data are input into the built model to obtain a final prediction result.
However, the experimental environment is greatly different from the actual line, and the experimental data acquired based on the experimental environment cannot completely represent the data in the actual line, so that the prediction result acquired based on the experimental data acquired based on the experimental environment cannot accurately predict the braking capability of the actual train, and the prediction result of the existing scheme is inaccurate.
Disclosure of Invention
In order to solve one of the technical defects, the application provides a train braking capability prediction method, an electronic device and a computer storage medium.
In a first aspect of the present application, a method for predicting train braking capacity is provided, where the method includes:
influence factors influencing the braking capacity of the train are combed;
depending on actual lines and vehicles, carrying out field experiments on the influence factors to obtain experimental data;
analyzing the experimental data to determine main factors influencing the braking capacity of the train;
establishing a train braking capability mathematical model based on the main factors;
training the train braking capacity mathematical model based on a neural network to obtain a trained train braking capacity mathematical model;
and predicting the braking capacity of the train according to the trained mathematical model of the braking capacity of the train.
Optionally, the influencing factors include one or more of: vehicle braking system factors, running gear factors, wheel-rail contact surface factors, line factors and train running speed;
the vehicle braking system factors include one or more of: the expected braking rate, the performance of an electric control conversion valve, the performance of a relay valve, the diameter of a brake pipe, the speed of an electric idle point conversion and the wear rate of a brake disc;
the running gear factors include one or more of: axle weight, connecting elements, geometric arrangement, wheel diameter;
the wheel-rail contact surface factors include one or more of the following: contamination layer, temperature, humidity, material properties, roughness;
the line factors include one or more of: curvature of curve, slope.
Optionally, the method includes performing a field experiment on the influence factor by relying on an actual line and a vehicle to obtain experiment data, and includes:
selecting factors to be evaluated from the influencing factors;
determining the level of the factor to be evaluated;
carrying out experimental design according to the factors to be evaluated and the levels of the factors to be evaluated;
making an experiment plan based on the experiment design;
and carrying out field experiments on the factors to be evaluated based on the experiment plan by depending on actual lines and vehicles, and acquiring experiment data.
Alternatively, the experimental design may be such that,
the gradient is the gradient of an ascending slope, or the gradient of a flat road, or the gradient of a descending slope;
the humidity is wet rail humidity or dry rail humidity;
the brake disc wear rate is the brake disc wear rate of a new car, or the brake disc wear rate of an old car, wherein a train running for less than 1 year is the new car, and a train running for more than 1 year is the old car.
Optionally, the analyzing the experimental data to determine main factors affecting the train braking capability includes:
preprocessing the experimental data;
dividing the preprocessed data into a data set and a test set;
regression analysis and variance analysis are carried out on the data set and the test set, and the correlation between each influence factor and the train braking capacity is determined;
determining a primary factor based on the correlation.
Optionally, the establishing a train braking capability mathematical model based on the main factors includes:
and carrying out data modeling according to the physical law and the main factors to obtain a train braking capacity mathematical model.
Alternatively, the main factors are: expected braking rate, brake disc wear rate, grade, humidity, train operating speed;
the train braking capability mathematical model is composed of the main factors, the brake disc wear rate coefficient, the gradient coefficient, the humidity coefficient, the train running speed coefficient and the deviation caused by the interaction among the main factors.
Optionally, the training the train braking capability mathematical model based on the neural network to obtain a trained train braking capability mathematical model includes:
determining the structure and parameters of the neural network;
training the train braking capability mathematical model based on the structure and the parameters to obtain a training result;
verifying the train braking capability mathematical model according to the training result, and if the verification result meets the preset training end condition, taking the current train braking capability mathematical model as the trained train braking capability mathematical model; and if the verification result does not meet the preset training end condition, optimizing the structure and parameters of the neural network and the parameters of the current train braking capability mathematical model, repeatedly executing the step of training the train braking capability mathematical model based on the optimized structure and parameters to obtain a training result, and verifying the train braking capability mathematical model according to the training result until the verification result meets the preset training end condition.
In a second aspect of the present application, there is provided an electronic device comprising:
a memory;
a processor; and
a computer program;
wherein the computer program is stored in the memory and configured to be executed by the processor to implement the method according to the first aspect.
In a third aspect of the present application, there is provided a computer readable storage medium having a computer program stored thereon; the computer program is executed by a processor to implement the method according to the first aspect as described above.
The application provides a train braking capacity prediction method, electronic equipment and a computer storage medium, wherein the method is used for combing influence factors influencing the train braking capacity; depending on actual lines and vehicles, carrying out field experiments on the influence factors to obtain experimental data; analyzing the experimental data to determine main factors influencing the braking capacity of the train; establishing a train braking capability mathematical model based on the main factors; training a train braking capacity mathematical model based on a neural network to obtain a trained train braking capacity mathematical model; and predicting the braking capacity of the train according to the trained mathematical model of the braking capacity of the train.
According to the method, influence factors influencing the train braking capacity are combed, field experiments are carried out on actual lines and vehicles, then a train braking capacity mathematical model is built, the train braking capacity is predicted according to the trained train braking capacity mathematical model, and more reliable and accurate prediction results can be obtained.
In addition, in one implementation, the influence factors are defined in detail, and because the factors influencing the braking capacity of the train are very many and different factors have interaction, the parameters of the subsequent model can be determined by defining the influence factors in detail, so that the accurate modeling of the subsequent model is ensured, and a more reliable and accurate prediction result can be obtained through the model.
In addition, in one implementation, the factors to be evaluated are selected, experimental design is carried out according to the factors to be evaluated and the levels of the factors to be evaluated to obtain an experimental plan, and then field experiments are carried out on the factors to be evaluated based on the experimental plan by relying on actual lines and vehicles to obtain experimental data, so that the experimental data are ensured to meet the actual conditions of the trains, the influence of main factors on the braking capacity of the trains can be reflected, and the accuracy of determination of the follow-up main factors is improved.
In addition, in one implementation, design factors in the experimental design are limited, comprehensiveness and variability of the experimental design are guaranteed, it is further guaranteed that experimental data obtained based on the experimental design meet the actual conditions of the train, influences of main factors on the braking capacity of the train can be reflected, and accuracy of determination of the follow-up main factors is improved.
In addition, in one implementation, the experimental data is preprocessed, and then regression analysis and variance analysis are performed to determine main factors, invalid values and abnormal values in the data can be removed through preprocessing, and digitization is performed, so that the accuracy of subsequent regression analysis and variance analysis is guaranteed, and the accuracy of the main factors is further guaranteed.
In addition, in one implementation, data modeling is carried out according to the physical law and the main factors to obtain a train braking capacity mathematical model, so that the train braking capacity mathematical model conforms to the physical law and the characteristics of the main factors of the train braking capacity, and a more reliable and accurate prediction result can be obtained through the train braking capacity mathematical model.
In addition, in one implementation, a mathematical model of train braking capability under the condition of expected braking rate, brake disc wear rate, gradient, humidity and train running speed is defined as a main factor, and the mathematical model of train braking capability under the condition is clarified.
In addition, in one implementation, the train braking capability mathematical model is trained and optimized through the neural network, so that the accuracy of the model for predicting the train braking capability is ensured, and a more reliable and accurate prediction result can be obtained.
According to the electronic equipment, the computer program is executed by the processor to comb the influence factors influencing the train braking capacity, the field experiment is carried out on the basis of actual lines and vehicles, then a train braking capacity mathematical model is built, the train braking capacity is predicted according to the trained train braking capacity mathematical model, and a more reliable and accurate prediction result can be obtained.
According to the computer-readable storage medium provided by the application, the computer program is executed by the processor to comb the influence factors influencing the train braking capacity, the field experiment is carried out on the basis of the actual line and the train, the train braking capacity mathematical model is further established, the train braking capacity is predicted according to the trained train braking capacity mathematical model, and a more reliable and accurate prediction result can be obtained.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the application and together with the description serve to explain the application and not to limit the application. In the drawings:
fig. 1 is a schematic flow chart of a method for predicting braking capability of a train according to an embodiment of the present application;
fig. 2 is a schematic flow chart of another train braking capability prediction method provided in the embodiment of the present application.
Detailed Description
In order to make the technical solutions and advantages of the embodiments of the present application more apparent, the following further detailed description of the exemplary embodiments of the present application with reference to the accompanying drawings makes it clear that the described embodiments are only a part of the embodiments of the present application, and are not exhaustive of all embodiments. It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict.
In the process of implementing the application, the inventor finds that the train braking capacity can be predicted by adopting a modeling mode at present. During prediction, factors of the influence factors are determined based on the experimental environment, experimental data are obtained, a model is built based on the influence factors, and the experimental data are input into the built model to obtain a final prediction result.
However, the experimental environment is greatly different from the actual line, and the experimental data acquired based on the experimental environment cannot completely represent the data in the actual line, so that the prediction result acquired based on the experimental data acquired based on the experimental environment cannot accurately predict the braking capability of the actual train, and the prediction result of the existing scheme is inaccurate.
In order to solve the above problems, embodiments of the present application provide a train braking capability prediction method, an electronic device, and a computer storage medium, where the method is used to comb influence factors that influence train braking capability; depending on actual lines and vehicles, carrying out field experiments on the influence factors to obtain experimental data; analyzing the experimental data to determine main factors influencing the braking capacity of the train; establishing a train braking capability mathematical model based on the main factors; training a train braking capacity mathematical model based on a neural network to obtain a trained train braking capacity mathematical model; and predicting the braking capacity of the train according to the trained mathematical model of the braking capacity of the train.
In the method provided by the application, the experimental data are obtained by carrying out field experiments on the influence factors depending on actual lines and vehicles, namely, the experimental data in the prior art are obtained by experiments in a pure experimental environment. The experimental data in the method are obtained through experiments under the actual line and vehicle environment, so that the experimental data are more suitable for the conditions of the actual line and the vehicle, and the data can be accurate and standard actual line and vehicle real operation data.
Referring to fig. 1, the implementation process of the train braking capability prediction method provided by this embodiment is as follows:
and 101, combing the influence factors influencing the braking capacity of the train.
The factors influencing the braking capacity of the train are very many, and the different factors have interaction, so that the physical modeling of the accurate relation cannot be carried out. According to the current research on train braking force, the factors influencing the braking capability of the train mainly include the following aspects, including a vehicle braking system, a running gear device, a wheel-rail contact surface, a line condition and a speed.
Thus, influencing factors in this step include, but are not limited to, one or more of the following: vehicle braking system factors, running gear factors, wheel-rail contact surface factors, line factors, and train operating speed.
Wherein the content of the first and second substances,
vehicle braking system factors including, but not limited to, one or more of: expected braking rate, electronically controlled switching valve performance, relay valve performance, brake pipe diameter, electronic idle switching point speed, brake disc wear rate.
Running gear factors including, but not limited to, one or more of: axle weight, connecting elements, geometric arrangement, wheel diameter.
Wheel track interface factors including, but not limited to, one or more of the following: contamination layer, temperature, humidity, material properties, roughness.
Line factors including, but not limited to, one or more of: curvature of curve, slope.
Parameters of the subsequent model can be determined by defining the influence factors in detail, so that accurate modeling of the subsequent model is guaranteed, and a more reliable and accurate prediction result can be obtained through the model.
102, depending on actual lines and vehicles, carrying out field experiments on the influence factors and obtaining experimental data.
In particular, the method comprises the following steps of,
102-1, selecting factors to be evaluated from the influencing factors.
102-2, determining the level of the factor to be evaluated.
102-3, carrying out experimental design according to the factors to be evaluated and the levels of the factors to be evaluated.
In the design of the experiment, it was shown that,
the train running speed (i.e. the initial braking speed) may be 10km/h, alternatively 30km/h, alternatively 50km/h, alternatively 70km/h, alternatively 90 km/h.
The gradient is the gradient of an uphill slope, or the gradient of a level road, or the gradient of a downhill slope.
The humidity (i.e., track humidity) is a wet track humidity, or a dry track humidity.
The brake disc wear rate is the brake disc wear rate of a new vehicle or the brake disc wear rate of an old vehicle.
Wherein, the train running for less than 1 year is a new train, and the train running for more than 1 year is an old train.
The expected braking rate may be 1.0m/s2Or, alternatively, 1.2m/s2Or, alternatively, 1.5m/s2。
Design factors in the experimental design are limited, comprehensiveness and variability of the experimental design are guaranteed, it is further guaranteed that experimental data obtained based on the experimental design meet the actual conditions of the train, influences of main factors on the braking capacity of the train can be reflected, and accuracy of determination of follow-up main factors is improved.
102-4, making an experimental plan based on the experimental design.
The experimental plan is a driving schedule.
102-5, depending on actual lines and vehicles, carrying out field experiments on the factors to be evaluated based on the experiment plan, and obtaining experiment data.
The step can determine the factors and levels to be researched according to the specific conditions of the line and the vehicle, and carry out experimental design.
For example, in experimental design, the experimental factors and levels are set forth below:
1. train running speed (i.e., initial braking speed): 5 levels were set, 10km/h, 30km/h, 50km/h, 70km/h and 90km/h, respectively.
2. Gradient: 3 levels are set, namely an ascending slope, a level road and a descending slope, and the specific gradient value is determined according to the actual condition of the line.
3. Humidity (i.e. track humidity): 2 levels, namely a wet rail and a dry rail, are arranged, wherein the environment of the wet rail needs to artificially create experimental conditions for experiments.
4. Wear rate of brake disc: 2 levels are set, namely a new vehicle and an old vehicle which has been running for more than 1 year.
5. Expected braking rate: set 3 levels, 1.0m/s respectively2Or, alternatively, 1.2m/s2Or, alternatively, 1.5m/s2。
If the full factorial experiment design is carried out, at least 180 braking experiments are carried out, wherein the braking experiments are carried out at a rate of 5 multiplied by 3 multiplied by 2 multiplied by 3. If the number of times of experiment is too large, other experiment design modes such as orthogonal experiment and the like can be adopted. Some additional level of experimentation is required as test set data.
After the experiment design is completed, a detailed experiment plan (namely a driving schedule) is braked according to the experiment design scheme, a driving route is designed, all experiment contents are completed according to the experiment plan, and driving data are obtained and collected and sorted.
And (4) finishing all experimental contents according to an experimental plan according to an experimental design braking detailed experimental plan, acquiring related data, and analyzing and sorting.
According to the method, the factors to be evaluated are selected, the experiment design is carried out according to the factors to be evaluated and the levels of the factors to be evaluated to obtain the experiment plan, the factors to be evaluated are subjected to field experiments based on the experiment plan by depending on actual lines and vehicles, the experiment data are obtained, the experiment data are guaranteed to meet the actual conditions of the train, the influence of the main factors on the braking capacity of the train can be reflected, and the accuracy of the determination of the follow-up main factors is improved.
And 103, analyzing the experimental data and determining main factors influencing the braking capacity of the train.
In particular, the method comprises the following steps of,
103-1, preprocessing the experimental data.
103-2, dividing the preprocessed data into data sets and test sets.
And 103-3, performing regression analysis and variance analysis on the data set and the test set, and determining the correlation of each influence factor and the train braking capacity.
103-4, determining the main factor according to the correlation.
The method comprises the following steps of preprocessing data, removing invalid and abnormal values, and digitizing to form a training set and a testing set for training and testing the neural network. And secondly, sequencing the correlation between each factor and the train braking capacity by means of variance analysis, regression analysis and the like, and using the correlation as a basis for establishing a mathematical model of the train braking capacity. Invalid values and abnormal values in the data can be removed through preprocessing, digitization is carried out, the accuracy of subsequent regression analysis and variance analysis is guaranteed, and the accuracy of main factors is further guaranteed.
And 104, establishing a train braking capability mathematical model based on the main factors.
And performing data modeling according to the physical law and the main factors to obtain a train braking capability mathematical model, so that the train braking capability mathematical model conforms to the physical law and the characteristics of the main factors of the train braking capability, and a more reliable and accurate prediction result can be obtained through the train braking capability mathematical model.
The main factors are as follows: expected braking rate BeThe wear rate mu of the brake disc,The gradient r, the humidity h and the train running speed v are taken as examples, and the train braking capability mathematical model consists of main factors, a brake disc wear rate coefficient, a gradient coefficient, a humidity coefficient, a train running speed coefficient and deviation caused by interaction among the main factors.
For example, the mathematical model of train braking capability is:
wherein, BrActual brake rate of train, w1Coefficient of wear of brake disc, w2Is the coefficient of gradient, w3Is the coefficient of humidity, w4Is a train running speed coefficient, w5The deviation caused by the interaction of the main factors.
And 105, training the train braking capacity mathematical model based on the neural network to obtain the trained train braking capacity mathematical model.
For example, the structure and parameters of the neural network are determined. And training the train braking capacity mathematical model based on the structure and the parameters to obtain a training result. And verifying the train braking capability mathematical model according to the training result, and if the verification result meets the preset training ending condition, taking the current train braking capability mathematical model as the trained train braking capability mathematical model. And if the verification result does not meet the preset training end condition, optimizing the structure and parameters of the neural network and the parameters of the current train braking capability mathematical model, repeatedly executing the training of the train braking capability mathematical model based on the optimized structure and parameters to obtain a training result, and verifying the train braking capability mathematical model according to the training result until the verification result meets the preset training end condition.
Determining the structure and parameters of the neural network according to the data volume and the number of the model parameters, establishing a neural network model, training and verifying, and repeatedly optimizing and adjusting the network structure and the mathematical model parameters to obtain a more optimal model. Train and debug the train braking ability mathematical model through the neural network, have guaranteed the accuracy of the model carrying on train braking ability prediction, can obtain more reliable, accurate prediction result.
And 106, predicting the braking capacity of the train according to the trained mathematical model of the braking capacity of the train.
The train braking capacity prediction method provided by the embodiment is a model data dual-drive train braking capacity prediction method, can accurately and reliably predict train capacity parameters, effectively improves the average train traveling speed, and improves train operation efficiency.
Referring to fig. 2, the method provided by the present embodiment is:
1. and comprehensively combing and analyzing influence factors influencing the braking capacity of the train.
2. Depending on actual lines and vehicles, experimental design and field experiments are carried out, and data of all factors in the list are collected and sorted.
3. And (4) preprocessing the experimental data and analyzing the data to determine main factors influencing the braking capacity of the train.
4. And establishing a train braking capability mathematical model based on the main factors to form a model parameter list.
5. And establishing a neural network model, and carrying out network training and verification by taking the model parameters as targets.
The method provided by the embodiment can be used for predicting the braking capacity by combining the basic state information of the train braking system, the parameters of the train running part, the conditions of the wheel-rail contact surface, the line conditions and the speed which are monitored by the PHM system according to the design principle of the train braking system, so that the reliability and the accuracy of prediction can be improved, the interpretability of the prediction method is improved, and the verification is facilitated; meanwhile, the train control is carried out based on the prediction data, so that the train operation efficiency can be greatly improved, and the safety in the train control process is improved.
In the method provided by this embodiment, the experimental data is obtained by performing a field experiment on the influence factors depending on an actual line and a vehicle, that is, the experimental data in the prior art is obtained by an experiment in a pure experimental environment. The experimental data in the method provided by the embodiment are obtained through experiments under the actual line and vehicle environment, so that the experimental data of the embodiment are more suitable for the conditions of the actual line and the vehicle, and the data can be accurate and standard actual operation data of the actual line and the vehicle.
Based on the same inventive concept of the train braking capability prediction method, the embodiment provides an electronic device, which includes: memory, processor, and computer programs.
Wherein the computer program is stored in the memory and configured to be executed by the processor to implement a train braking capability prediction method as shown in fig. 1 or fig. 2.
In particular, the method comprises the following steps of,
influence factors influencing the braking capacity of the train are combed;
depending on actual lines and vehicles, carrying out field experiments on the influence factors to obtain experimental data;
analyzing the experimental data to determine main factors influencing the braking capacity of the train;
establishing a train braking capability mathematical model based on the main factors;
training a train braking capacity mathematical model based on a neural network to obtain a trained train braking capacity mathematical model;
and predicting the braking capacity of the train according to the trained mathematical model of the braking capacity of the train.
Optionally, the influencing factors include one or more of: vehicle braking system factors, running gear factors, wheel-rail contact surface factors, line factors and train running speed;
vehicle braking system factors including one or more of: the expected braking rate, the performance of an electric control conversion valve, the performance of a relay valve, the diameter of a brake pipe, the speed of an electric idle point conversion and the wear rate of a brake disc;
running gear factors including one or more of: axle weight, connecting elements, geometric arrangement, wheel diameter;
a wheel-rail interface factor comprising one or more of: contamination layer, temperature, humidity, material properties, roughness;
line factors including one or more of: curvature of curve, slope.
Optionally, depending on an actual line and a vehicle, performing a field experiment on the influence factors to obtain experiment data, including:
selecting factors to be evaluated from the influencing factors;
determining the level of a factor to be evaluated;
carrying out experimental design according to the factors to be evaluated and the levels of the factors to be evaluated;
making an experiment plan based on the experiment design;
depending on actual lines and vehicles, the factors to be evaluated are subjected to field experiments based on the experiment plan, and experiment data are obtained.
Alternatively, the experimental design may be such that,
the gradient is the gradient of an ascending slope, or the gradient of a flat road, or the gradient of a descending slope;
the humidity is wet rail humidity or dry rail humidity;
the brake disc wear rate is the brake disc wear rate of a new car, or the brake disc wear rate of an old car, wherein a train running for less than 1 year is the new car, and a train running for more than 1 year is the old car.
Optionally, analyzing the experimental data to determine main factors affecting the braking capability of the train, including:
preprocessing experimental data;
dividing the preprocessed data into a data set and a test set;
regression analysis and variance analysis are carried out on the data set and the test set, and the correlation between each influence factor and the train braking capacity is determined;
the main factor is determined according to the correlation.
Optionally, establishing a train braking capability mathematical model based on the main factors, including:
and carrying out data modeling according to the physical law and the main factors to obtain a train braking capacity mathematical model.
Alternatively, the main factors are: expected braking rate, brake disc wear rate, grade, humidity, train operating speed;
the train braking capability mathematical model is composed of main factors, brake disc wear rate coefficient, gradient coefficient, humidity coefficient, train operation speed coefficient and deviation caused by interaction among the main factors.
Optionally, training the train braking capability mathematical model based on the neural network to obtain a trained train braking capability mathematical model, including:
determining the structure and parameters of the neural network;
training a train braking capability mathematical model based on the structure and the parameters to obtain a training result;
verifying the train braking capability mathematical model according to the training result, and if the verification result meets the preset training end condition, taking the current train braking capability mathematical model as the trained train braking capability mathematical model; and if the verification result does not meet the preset training end condition, optimizing the structure and parameters of the neural network and the parameters of the current train braking capability mathematical model, repeatedly executing the training of the train braking capability mathematical model based on the optimized structure and parameters to obtain a training result, and verifying the train braking capability mathematical model according to the training result until the verification result meets the preset training end condition.
In the electronic device provided in this embodiment, the computer program is executed by the processor to comb the influence factors influencing the train braking capability, perform field experiments on the train and the actual line, further establish a train braking capability mathematical model, and predict the train braking capability according to the trained train braking capability mathematical model.
Because the experimental data in the embodiment are obtained by performing field experiments on the influence factors depending on actual lines and vehicles, that is, the experimental data in the prior art is obtained by experiments in a pure experimental environment. The experimental data in the embodiment are obtained through experiments under the actual line and vehicle environments, so that the experimental data of the embodiment is more suitable for the conditions of the actual line and the vehicle, and the data can be accurate in standard actual line and vehicle real operation data.
Based on the same inventive concept of the above-described train braking capability prediction method, the present embodiment provides a computer-readable storage medium on which a computer program is stored. The computer program is executed by a processor to implement a train braking capability prediction method as shown in fig. 1 or fig. 2.
In particular, the method comprises the following steps of,
influence factors influencing the braking capacity of the train are combed;
depending on actual lines and vehicles, carrying out field experiments on the influence factors to obtain experimental data;
analyzing the experimental data to determine main factors influencing the braking capacity of the train;
establishing a train braking capability mathematical model based on the main factors;
training a train braking capacity mathematical model based on a neural network to obtain a trained train braking capacity mathematical model;
and predicting the braking capacity of the train according to the trained mathematical model of the braking capacity of the train.
Optionally, the influencing factors include one or more of: vehicle braking system factors, running gear factors, wheel-rail contact surface factors, line factors and train running speed;
vehicle braking system factors including one or more of: the expected braking rate, the performance of an electric control conversion valve, the performance of a relay valve, the diameter of a brake pipe, the speed of an electric idle point conversion and the wear rate of a brake disc;
running gear factors including one or more of: axle weight, connecting elements, geometric arrangement, wheel diameter;
a wheel-rail interface factor comprising one or more of: contamination layer, temperature, humidity, material properties, roughness;
line factors including one or more of: curvature of curve, slope.
Optionally, depending on an actual line and a vehicle, performing a field experiment on the influence factors to obtain experiment data, including:
selecting factors to be evaluated from the influencing factors;
determining the level of a factor to be evaluated;
carrying out experimental design according to the factors to be evaluated and the levels of the factors to be evaluated;
making an experiment plan based on the experiment design;
depending on actual lines and vehicles, the factors to be evaluated are subjected to field experiments based on the experiment plan, and experiment data are obtained.
Alternatively, the experimental design may be such that,
the gradient is the gradient of an ascending slope, or the gradient of a flat road, or the gradient of a descending slope;
the humidity is wet rail humidity or dry rail humidity;
the brake disc wear rate is the brake disc wear rate of a new car, or the brake disc wear rate of an old car, wherein a train running for less than 1 year is the new car, and a train running for more than 1 year is the old car.
Optionally, analyzing the experimental data to determine main factors affecting the braking capability of the train, including:
preprocessing experimental data;
dividing the preprocessed data into a data set and a test set;
regression analysis and variance analysis are carried out on the data set and the test set, and the correlation between each influence factor and the train braking capacity is determined;
the main factor is determined according to the correlation.
Optionally, establishing a train braking capability mathematical model based on the main factors, including:
and carrying out data modeling according to the physical law and the main factors to obtain a train braking capacity mathematical model.
Optionally, expected braking rate, brake disc wear rate, grade, humidity, train operating speed;
the train braking capability mathematical model is composed of main factors, brake disc wear rate coefficient, gradient coefficient, humidity coefficient, train operation speed coefficient and deviation caused by interaction among the main factors.
Optionally, training the train braking capability mathematical model based on the neural network to obtain a trained train braking capability mathematical model, including:
determining the structure and parameters of the neural network;
training a train braking capability mathematical model based on the structure and the parameters to obtain a training result;
verifying the train braking capability mathematical model according to the training result, and if the verification result meets the preset training end condition, taking the current train braking capability mathematical model as the trained train braking capability mathematical model; and if the verification result does not meet the preset training end condition, optimizing the structure and parameters of the neural network and the parameters of the current train braking capability mathematical model, repeatedly executing the training of the train braking capability mathematical model based on the optimized structure and parameters to obtain a training result, and verifying the train braking capability mathematical model according to the training result until the verification result meets the preset training end condition.
In the computer-readable storage medium provided in this embodiment, the computer program on the computer-readable storage medium is executed by the processor to comb the influence factors influencing the train braking capability, perform field experiments on actual lines and vehicles, further establish a train braking capability mathematical model, and predict the train braking capability according to the trained train braking capability mathematical model.
Because the experimental data in the embodiment are obtained by performing field experiments on the influence factors depending on actual lines and vehicles, that is, the experimental data in the prior art is obtained by experiments in a pure experimental environment. The experimental data in the embodiment are obtained through experiments under the actual line and vehicle environments, so that the experimental data of the embodiment is more suitable for the conditions of the actual line and the vehicle, and the data can be accurate in standard actual line and vehicle real operation data.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein. The scheme in the embodiment of the application can be implemented by adopting various computer languages, such as object-oriented programming language Java and transliterated scripting language JavaScript.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While the preferred embodiments of the present application have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all alterations and modifications as fall within the scope of the application.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present application without departing from the spirit and scope of the application. Thus, if such modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is intended to include such modifications and variations as well.
Claims (10)
1. A train braking capability prediction method, characterized in that the method comprises:
influence factors influencing the braking capacity of the train are combed;
depending on actual lines and vehicles, carrying out field experiments on the influence factors to obtain experimental data;
analyzing the experimental data to determine main factors influencing the braking capacity of the train;
establishing a train braking capability mathematical model based on the main factors;
training the train braking capacity mathematical model based on a neural network to obtain a trained train braking capacity mathematical model;
and predicting the braking capacity of the train according to the trained mathematical model of the braking capacity of the train.
2. The method of claim 1, wherein the influencing factors comprise one or more of: vehicle braking system factors, running gear factors, wheel-rail contact surface factors, line factors and train running speed;
the vehicle braking system factors include one or more of: the expected braking rate, the performance of an electric control conversion valve, the performance of a relay valve, the diameter of a brake pipe, the speed of an electric idle point conversion and the wear rate of a brake disc;
the running gear factors include one or more of: axle weight, connecting elements, geometric arrangement, wheel diameter;
the wheel-rail contact surface factors include one or more of the following: contamination layer, temperature, humidity, material properties, roughness;
the line factors include one or more of: curvature of curve, slope.
3. The method of claim 1, wherein the influencing factors are subjected to field experiments depending on actual lines and vehicles to obtain experimental data, and the experimental data comprises:
selecting factors to be evaluated from the influencing factors;
determining the level of the factor to be evaluated;
carrying out experimental design according to the factors to be evaluated and the levels of the factors to be evaluated;
making an experiment plan based on the experiment design;
and carrying out field experiments on the factors to be evaluated based on the experiment plan by depending on actual lines and vehicles, and acquiring experiment data.
4. The method of claim 3, wherein, in the experimental design,
the gradient is the gradient of an ascending slope, or the gradient of a flat road, or the gradient of a descending slope;
the humidity is wet rail humidity or dry rail humidity;
the brake disc wear rate is the brake disc wear rate of a new car, or the brake disc wear rate of an old car, wherein a train running for less than 1 year is the new car, and a train running for more than 1 year is the old car.
5. The method of claim 1, wherein analyzing the experimental data to determine primary factors affecting train braking capacity comprises:
preprocessing the experimental data;
dividing the preprocessed data into a data set and a test set;
regression analysis and variance analysis are carried out on the data set and the test set, and the correlation between each influence factor and the train braking capacity is determined;
determining a primary factor based on the correlation.
6. The method of claim 1, wherein the building a mathematical model of train braking capability based on the primary factors comprises:
and carrying out data modeling according to the physical law and the main factors to obtain a train braking capacity mathematical model.
7. The method according to claim 6, characterized in that the main factors are: expected braking rate, brake disc wear rate, grade, humidity, train operating speed;
the train braking capability mathematical model is composed of the main factors, the brake disc wear rate coefficient, the gradient coefficient, the humidity coefficient, the train running speed coefficient and the deviation caused by the interaction among the main factors.
8. The method of claim 1, wherein the training the train braking capability mathematical model based on the neural network to obtain the trained train braking capability mathematical model comprises:
determining the structure and parameters of the neural network;
training the train braking capability mathematical model based on the structure and the parameters to obtain a training result;
verifying the train braking capability mathematical model according to the training result, and if the verification result meets the preset training end condition, taking the current train braking capability mathematical model as the trained train braking capability mathematical model; and if the verification result does not meet the preset training end condition, optimizing the structure and parameters of the neural network and the parameters of the current train braking capability mathematical model, repeatedly executing the step of training the train braking capability mathematical model based on the optimized structure and parameters to obtain a training result, and verifying the train braking capability mathematical model according to the training result until the verification result meets the preset training end condition.
9. An electronic device, comprising:
a memory;
a processor; and
a computer program;
wherein the computer program is stored in the memory and configured to be executed by the processor to implement the method of any one of claims 1-8.
10. A computer-readable storage medium, having stored thereon a computer program; the computer program is executed by a processor to implement the method of any one of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111288826.9A CN113935189A (en) | 2021-11-02 | 2021-11-02 | Train braking capacity prediction method, electronic equipment and computer storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111288826.9A CN113935189A (en) | 2021-11-02 | 2021-11-02 | Train braking capacity prediction method, electronic equipment and computer storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113935189A true CN113935189A (en) | 2022-01-14 |
Family
ID=79285253
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111288826.9A Pending CN113935189A (en) | 2021-11-02 | 2021-11-02 | Train braking capacity prediction method, electronic equipment and computer storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113935189A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115223271A (en) * | 2022-06-28 | 2022-10-21 | 东软睿驰汽车技术（沈阳）有限公司 | Method for obtaining attention of vehicle residual information error and related device |
-
2021
- 2021-11-02 CN CN202111288826.9A patent/CN113935189A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115223271A (en) * | 2022-06-28 | 2022-10-21 | 东软睿驰汽车技术（沈阳）有限公司 | Method for obtaining attention of vehicle residual information error and related device |
| CN115223271B (en) * | 2022-06-28 | 2024-05-07 | 东软睿驰汽车技术（沈阳）有限公司 | Attention degree obtaining method and related device for vehicle residual information errors |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110610260B (en) | Driving energy consumption prediction system, method, storage medium and equipment | |
| US9053593B2 (en) | Vehicle data analysis method and vehicle data analysis system | |
| CN107564290B (en) | Urban road intersection saturated flow rate calculation method | |
| CN111688713B (en) | Driving behavior analysis method and device | |
| CN111477005B (en) | Intelligent perception early warning method and system based on vehicle state and driving environment | |
| CN101706996A (en) | Method for identifying traffic status of express way based on information fusion | |
| CN106218668B (en) | Wheel out of round degree detection method and device | |
| CN111144485B (en) | Vehicle accident judging method and system based on xgboost classification algorithm | |
| CN114881076B (en) | Rail corrugation identification method, device, equipment and medium based on support vector machine | |
| CN113935189A (en) | Train braking capacity prediction method, electronic equipment and computer storage medium | |
| CN103955135A (en) | Method for calculating locomotive optimized operation sequence based on double-layer mode curve | |
| CN111994129A (en) | Wheel-rail train antiskid control method and system | |
| CN112198799B (en) | High-speed train parking control method and system based on deep learning | |
| CN108189842A (en) | A kind of hill gradient recognition methods and device based on acceleration signal | |
| CN106585675B (en) | Train operation optimized handling method and apparatus | |
| CN102622883A (en) | Method and device for judging release of traffic incident | |
| Malvezzi et al. | Feasibility of degraded adhesion tests in a locomotive roller rig | |
| CN112129290A (en) | System and method for monitoring riding equipment | |
| CN111027859B (en) | Driving risk prevention method and system based on motor vehicle state monitoring data mining | |
| Liu et al. | Development of Driver‐Behavior Model Based onWOA‐RBM Deep Learning Network | |
| CN110143217B (en) | Track state measuring method, system and device | |
| Wan et al. | Binary segmentation for structural condition classification using structural health monitoring data | |
| CN112967420B (en) | Interval two-type based heavy-duty train operation process monitoring method and system | |
| CN110941517A (en) | Data verification method for intelligent control system of locomotive | |
| CN116278778A (en) | Electric vehicle braking method, device, equipment and medium based on energy recovery |
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 |