Method, system and equipment for calculating traction and braking performance parameters of vehicle and medium

Abstract

The invention relates to the technical field of vehicle performance testing, and provides a method, a system, equipment and a medium for calculating vehicle traction and braking performance parameters, the method comprises the following steps: acquiring time and periodic data of vehicle speed and level change to construct a data set, and training a linear regression model by using the data set to obtain a linear regression model; the vehicle traction and braking performance parameters can be accurately output, so that a trained model is obtained; secondly, real-time speed pulse change data of the vehicle under different working conditions are collected, and relevant data of speed and level change are extracted from the real-time speed pulse change data; and inputting the extracted data into a trained linear regression model to obtain the traction and braking performance parameters of the vehicle, so as to replace manual calculation and improve the efficiency and the precision. According to the method, a complex manual calculation process can be omitted, the labor cost is saved, and the calculation period is greatly shortened.

Description

Technical Field

[0001] The present disclosure belongs to the technical field of train control, and in particular, relates to a method and system for calculating vehicle traction and braking performance parameters. Background Art

[0002] Vehicle traction and braking performance parameters mainly include traction delay, braking delay, acceleration and deceleration, etc. These parameters reflect the performance of the vehicle during traction and braking. Accurate vehicle traction and braking performance parameters are of great significance for vehicle safe driving, performance optimization, and accurate signal automatic vehicle control.

[0003] During the signal EMU debugging stage, it is necessary to verify the vehicle traction and braking performance parameters according to the debugging content in the EMU manual. The main method is to import the EMU test data into the EMU tool for manual analysis, calculation, and statistics to obtain the vehicle's actual traction and braking acceleration, traction delay, braking delay and other vehicle control parameters, and compare them with the relevant standards in the interface file to determine whether the signal requirements are met.

[0004] However, due to the large number of dynamic adjustment test items and huge data volume, relying on the current calculation method will result in problems such as high labor costs, long calculation cycle, and insufficient calculation result accuracy. Summary of the invention

[0005] To solve the above problems, the present disclosure provides a method, system, device and medium for calculating vehicle traction and braking performance parameters, and adopts a method for automatically calculating vehicle traction and braking performance parameters based on a machine learning algorithm. This technology can solve the problems of high cost, long cycle and insufficient accuracy of manual calculation.

[0006] The following is the technical content of the present invention:

[0007] A method for calculating vehicle traction braking performance parameters, characterized by comprising:

[0008] Acquire the speed change time and speed change cycle data of the vehicle, the level change time and level change cycle data of the vehicle, and construct a data set;

[0009] The linear regression model is trained using the data set. When the linear regression model outputs accurate vehicle traction and braking performance parameters according to the speed change time and speed change cycle data, the vehicle's gear change time and gear change cycle data, a trained linear regression model is obtained.

[0010] Collect real-time speed pulse change data of the vehicle under different working conditions, and extract the speed change time and speed change cycle data of the vehicle, the level change time and level change cycle data of the vehicle according to the real-time speed pulse change data;

[0011] The extracted data is input into the trained linear regression model to obtain the vehicle traction and braking performance parameters.

[0012] Further,

[0013] The vehicle traction braking performance parameters include:

[0014] Vehicle acceleration, vehicle deceleration, vehicle traction delay time, vehicle braking delay time.

[0015] Further,

[0016] The real-time speed pulse change data of the vehicle under different working conditions is collected; including:

[0017] Open the vehicle-mounted dynamic adjustment tool, connect the computer to the vehicle-mounted ATC equipment via RS232, and collect the real-time speed pulse change data of the signal speed sensor installed on the 1st and 3rd axes of the bogie at the TC end of the vehicle under different working conditions.

[0018] Further,

[0019] The mean square error function is used as the loss function for training the linear regression model.

[0020] Further,

[0021] Use the stochastic gradient descent algorithm as the optimizer for training the linear regression model.

[0022] Further,

[0023] After obtaining the vehicle traction and braking performance parameters, the calculated vehicle traction and braking performance parameters are compared and analyzed with the standard parameters specified in the interface file to determine whether the calculated actual vehicle parameters are within the standard range, and based on this, it is proposed whether the test is passed and the test results are generated.

[0024] Further,

[0025] Also includes:

[0026] The test results are exported as charts or reports in the form of xslx files for reference by signal debugging personnel.

[0027] A calculation system for vehicle traction and braking performance parameters, characterized by comprising:

[0028] A data acquisition module, used to acquire the speed change time and speed change cycle data of the vehicle, the gear change time and gear change cycle data of the vehicle, and construct a data set;

[0029] A model building module is used to train a linear regression model using a data set. When the linear regression model outputs accurate vehicle traction and braking performance parameters according to speed change time and speed change cycle data, vehicle level change time and level change cycle data, a trained linear regression model is obtained.

[0030] A data acquisition module is used to collect real-time speed pulse change data of the vehicle under different working conditions, and extract the speed change time and speed change cycle data of the vehicle, the level change time and level change cycle data of the vehicle according to the real-time speed pulse change data;

[0031] The calculation module is used to input the extracted data into the trained linear regression model to obtain the vehicle traction and braking performance parameters.

[0032] Compared with the prior art, the present invention has the following advantages:

[0033] The present invention realizes a fully automated process of data collection, model training and application; by real-time collection of speed pulse change data under different working conditions of the vehicle, and automatically extracting the time and cycle data of speed and level change from it, the tedious work of manual collection and sorting of data is avoided, which greatly saves time and manpower. At the same time, the linear regression model is trained using these data so that it can accurately output the vehicle traction and braking performance parameters. In practical applications, the calculation results can be quickly obtained by simply inputting the extracted data into the trained model without manual complex calculation and analysis, thereby greatly shortening the calculation cycle.

[0034] The method of the present invention is used to calculate the traction and braking performance parameters of the vehicle. The process of manually collating test data and calculating the traction and braking performance parameters of the vehicle is replaced by the present invention, which can omit the complicated manual calculation process, save labor costs, greatly shorten the calculation cycle, and accurately determine whether various operating parameters of the train meet the requirements of the signal for vehicle performance.

[0035] Other features and advantages of the present disclosure will be described in the following description, and partly become apparent from the description, or be understood by implementing the present disclosure. The purpose and other advantages of the present disclosure can be realized and obtained by the structures pointed out in the description, claims and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the embodiments of the present disclosure or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0037] Figure 1 A schematic diagram of the method of the present invention is shown. DETAILED DESCRIPTION

[0038] In order to make the purpose, technical solution and advantages of the embodiments of the present disclosure clearer, the technical solution in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present disclosure.

[0039] Figure 1 A schematic diagram of the method according to the present invention is shown, and the specific implementation details of the present invention include:

[0040] Step 1: Collect data

[0041] Open the on-board dynamic adjustment tool, connect the PC and the on-board ATC equipment via RS232, and collect the real-time speed pulse change data of the signal speed sensor installed on the 1st and 3rd axes of the bogie at the TC end of the vehicle under different working conditions.

[0042] Among them, sensors installed on the vehicle are used to collect real-time speed pulse change data. During the operation of the vehicle, the sensor will continuously detect the speed pulse signal of the vehicle and transmit this data to the data acquisition system in real time.

[0043] For example, when a vehicle accelerates, the sensor will detect that the frequency of speed pulses gradually increases. The data acquisition system will record the timestamp of each pulse, and the period of speed change can be calculated by the time difference between adjacent pulses. At the same time, based on the change in pulse frequency, the speed change of the vehicle can be inferred, and then the time of speed change can be determined.

[0044] For the detection of gear changes, relevant information can be obtained through the connection with the vehicle control system. When the driver changes the gear of the vehicle (such as accelerating, decelerating or maintaining a constant speed), the vehicle control system will send a corresponding signal. After receiving these signals, the data acquisition system records the time of the gear change.

[0045] Assume that in a test, the vehicle accelerates from rest, and the speed pulse change data detected by the sensor shows that at time point t1, the speed is 0, then at time point t2, the speed increases to 10km / h, and at time point t3, the speed increases to 20km / h. By calculating t2-t1 and t3-t2, the speed change cycle can be obtained. At the same time, the time period from t1 to t2 is the change time of the speed from 0 to 10km / h.

[0046] Similarly, for the gear change, assuming that at time point t4, the driver changes the gear from 1st gear to 2nd gear, the data acquisition system will record t4 as the time of the gear change.

[0047] Step 2: Data processing

[0048] The real-time collected data is saved in the PC host in TXT file format, and the collected data files are renamed respectively.

[0049] Step 3: Parameter calculation

[0050] Import each parameter data file into the corresponding position in the vehicle traction and braking performance calculation tool. (The vehicle traction and braking performance calculation tool refers to the machine learning model, and the machine learning model can use a linear regression model.) Click the Generate Calculation Results button in the vehicle traction and braking performance calculation tool. The tool calculates the vehicle's actual traction and braking delay, acceleration and deceleration and other performance parameters through the time and period of vehicle speed and level changes recorded in the data, as well as the time period of acceleration and deceleration changes. (The parameters input to the machine learning model are the three-way pulse number collected from the speed transmission and the time during the pulse change process; the output parameters are the acceleration and deceleration values ​​calculated by the linear rules of pulses and time, and whether they meet the standard value range).

[0051] There are two main types of results that are expected from the calculation of machine learning models:

[0052] 1. Acceleration and deceleration calculation: According to a=(v_t-v_0) / t, a represents acceleration, v_t represents final velocity, v_0 represents initial velocity, and t represents time.

[0053] 2. Delay calculation: Determine the traction / braking delay time based on the time difference between the input level change and the actual speed change.

[0054] Training the model is done through the following steps:

[0055] Data preparation: Prepare a set of typical data sets, which include information such as expected speed changes, time, and level changes. The goal is to use the typical data sets to make the model output the expected acceleration and deceleration values ​​and delay time.

[0056] To train the model, we use mean squared error (MSE) as the loss function to measure the difference between the predicted value and the actual value of our model, and use stochastic gradient descent as the optimizer.

[0057] The actual collected data is imported into the model and the model output results are evaluated through the model output results to obtain a trained model.

[0058] Step 4: Data Analysis

[0059] The calculated performance parameters are compared and analyzed with the standard parameters specified in the interface file to determine whether the actual calculated vehicle parameters are within the standard range, and based on this, it is proposed whether the test has passed.

[0060] Step 5: Output the results

[0061] The analysis results are exported as xslx files in the form of charts or reports for reference by signal debugging personnel.

[0062] The characteristics of this method are that it can collect and process vehicle data in real time, automatically calculate vehicle performance parameters, and conduct comparative analysis based on actual driving conditions, which can provide signal debugging personnel with faster, more accurate and professional information.

[0063] The key technical points of the present invention are:

[0064] 1. Automatically calculate the parameters such as traction delay, braking delay, acceleration and deceleration through the imported data.

[0065] 2. Compare the calculated results with the standard parameters and output whether they meet the standards.

[0066] 3. Export the corresponding calculation results into a file in xlsx format.

[0067] Based on the method of the present invention, the embodiment of the present disclosure also provides a system corresponding to the above method, which includes:

[0068] A data acquisition module, used to acquire the speed change time and speed change cycle data of the vehicle, the gear change time and gear change cycle data of the vehicle, and construct a data set;

[0069] A model building module is used to train a linear regression model using a data set. When the linear regression model outputs accurate vehicle traction and braking performance parameters according to speed change time and speed change cycle data, vehicle level change time and level change cycle data, a trained linear regression model is obtained.

[0070] A data acquisition module is used to collect real-time speed pulse change data of the vehicle under different working conditions, and extract the speed change time and speed change cycle data of the vehicle, the level change time and level change cycle data of the vehicle according to the real-time speed pulse change data;

[0071] The calculation module is used to input the extracted data into a trained linear regression model, and the linear regression model outputs vehicle traction and braking performance parameters.

[0072] Based on the same inventive concept as the above disclosed content, an embodiment of the present disclosure also provides a computing device corresponding to the above method, which includes at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the above method.

[0073] It should be noted that the electrical connection between the above-mentioned units does not necessarily mean the connection between lines. An indirect connection method can be applied to the embodiments of the present disclosure as long as the purpose of the present disclosure is achieved.

[0074] Based on the same inventive concept, the present disclosure also provides a computer storage medium on which executable instructions are stored. When the instructions are executed by a processor, the processor performs the above method.

[0075] Although the present disclosure has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present disclosure.

Claims

1. A method for calculating vehicle traction and braking performance parameters, characterized in that: include: Acquire the speed change time and speed change cycle data of the vehicle, the level change time and level change cycle data of the vehicle, and construct a data set; The linear regression model is trained using the data set. When the linear regression model outputs accurate vehicle traction and braking performance parameters according to the speed change time and speed change cycle data, the vehicle's gear change time and gear change cycle data, a trained linear regression model is obtained. Collect real-time speed pulse change data of the vehicle under different working conditions, and extract the speed change time and speed change cycle data of the vehicle, the level change time and level change cycle data of the vehicle according to the real-time speed pulse change data; The extracted data is input into the trained linear regression model, and the linear regression model outputs the vehicle traction and braking performance parameters.

2. The method for calculating vehicle traction and braking performance parameters according to claim 1, characterized in that: The vehicle traction braking performance parameters include: Vehicle acceleration, vehicle deceleration, vehicle traction delay time, vehicle braking delay time.

3. The method for calculating vehicle traction and braking performance parameters according to claim 2, characterized in that: The real-time speed pulse change data of the vehicle under different working conditions is collected; including: Open the vehicle-mounted dynamic adjustment tool, connect the computer to the vehicle-mounted ATC equipment via RS232, and collect the real-time speed pulse change data of the signal speed sensor installed on the 1st and 3rd axes of the bogie at the TC end of the vehicle under different working conditions.

4. The method for calculating vehicle traction and braking performance parameters according to claim 1, characterized in that: The mean square error function is used as the loss function for training the linear regression model.

5. The method for calculating vehicle traction and braking performance parameters according to claim 1, characterized in that: Use the stochastic gradient descent algorithm as the optimizer for training the linear regression model.

6. The method for calculating vehicle traction and braking performance parameters according to claim 1, characterized in that: After obtaining the vehicle traction and braking performance parameters, the calculated vehicle traction and braking performance parameters are compared and analyzed with the standard parameters specified in the interface file to determine whether the calculated actual vehicle parameters are within the standard range, and based on this, it is proposed whether the test is passed and the test results are generated.

7. The method for calculating vehicle traction and braking performance parameters according to claim 6, characterized in that: Also includes: The test results are exported as xslx files in the form of charts or reports for reference by signal debugging personnel.

8. A system for calculating vehicle traction and braking performance parameters, characterized in that: include: A data acquisition module, used to acquire the speed change time and speed change cycle data of the vehicle, the gear change time and gear change cycle data of the vehicle, and construct a data set; A model building module is used to train a linear regression model using a data set. When the linear regression model outputs accurate vehicle traction and braking performance parameters according to speed change time and speed change cycle data, vehicle level change time and level change cycle data, a trained linear regression model is obtained. A data acquisition module is used to collect real-time speed pulse change data of the vehicle under different working conditions, and extract the speed change time and speed change cycle data of the vehicle, the level change time and level change cycle data of the vehicle according to the real-time speed pulse change data; The calculation module is used to input the extracted data into the trained linear regression model, and the linear regression model outputs the vehicle traction and braking performance parameters.

9. A device for calculating vehicle traction and braking performance parameters, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor so that the at least one processor can execute the method for calculating vehicle traction and braking performance parameters as described in any one of claims 1 to 7.

10. A computer storage medium having executable instructions stored thereon, wherein when the instructions are executed by a processor, the processor is enabled to implement the method according to any one of claims 1 to 7.

Images