Railway vehicle RAMS data monitoring method, electronic device and storage medium

Abstract

The present application relates to a kind of rail vehicle RAMS data monitoring method, electronic equipment and storage medium, comprising: obtaining the running data of various vehicle samples under different RAMS indicators;According to the correlation of the running data after data cleaning and corresponding vehicle RAMS indicators, the optimized running data is screened out;The optimized running data is used as training sample, input into neural network and trained to obtain rail vehicle RAMS data prediction model;The running data of target vehicle is input into rail vehicle RAMS data prediction model to obtain the RAMS indicator of target vehicle.The present application can quickly obtain the running data of a large number of vehicle samples based on big data technology, and through data cleaning and screening, the accuracy and reliability of data are improved, and then the RAMS indicator of target vehicle can be more accurately predicted, so that potential problems can be found in advance, and fault risk is reduced.

Description

Technical Field

[0001] This invention relates to the field of RAMS data monitoring technology, and in particular to a method for monitoring RAMS data of rail vehicles based on big data technology. Background Technology

[0002] With the continuous development of rail transit systems, monitoring the reliability, availability, maintainability, and safety (RAMS) data of rail vehicles has become an important issue. Traditional methods for monitoring RAMS data of rail vehicles mainly rely on manual inspections and sensor data collection, which suffers from problems such as incomplete data collection, poor real-time performance, and low data processing efficiency. However, the rapid development of big data technology has provided new ideas for solving these problems.

[0003] Big data technology possesses the ability to efficiently process massive amounts of data, enabling real-time collection, storage, processing, and analysis of various data from rail vehicles. Through big data technology, comprehensive monitoring and analysis of rail vehicle RAMS data can be achieved, improving data accuracy and reliability and providing a more scientific basis for the operation and maintenance of rail vehicles.

[0004] Therefore, RAMS data monitoring methods for rail vehicles based on big data technology have become a current research hotspot. Big data technology enables real-time monitoring and analysis of various data from rail vehicles, providing more reliable support for their safe operation and maintenance. Summary of the Invention

[0005] To address the aforementioned problems, the purpose of this invention is to provide a method for monitoring RAMS data of rail vehicles based on big data technology.

[0006] A method for monitoring RAMS data of rail vehicles based on big data technology, comprising:

[0007] Step 1: Obtain the operating data of various vehicle samples under different RAMS indicators; the operating data includes: motor current, maximum traction force of the power system, maximum vehicle speed, vehicle core temperature, maximum acceleration, wheel axle vibration, wheel axle load, vehicle body tilt angle, remaining fuel in the fuel tank, fuel consumption rate, and vehicle interior humidity;

[0008] Step 2: Perform data cleaning on the operating data under the different RAMS indicators to obtain cleaned operating data;

[0009] Step 3: Filter the optimized operating data based on the correlation between the cleaned operating data and the corresponding vehicle RAMS index;

[0010] Step 4: Use the optimized running data as training samples and input them into the neural network to train and obtain the RAMS data prediction model for rail vehicles;

[0011] Step 5: Input the target vehicle's operating data into the rail vehicle RAMS data prediction model to obtain the target vehicle's RAMS index.

[0012] Preferably, in step 1, the vehicle core temperature is obtained through the following steps:

[0013] Step 1.1: Use an infrared camera to acquire infrared images of the vehicle samples;

[0014] Step 1.2: Smooth the infrared image to obtain a smoothed infrared image;

[0015] Step 1.3: Calculate the gradient direction of each pixel in the smoothed infrared image;

[0016] Step 1.4: Compare the pixel values ​​of the target pixel with those of its neighboring pixels in the corresponding gradient direction, and extract the target pixel corresponding to the maximum pixel value as the contour point. Traverse the entire smoothed infrared image to obtain the core temperature infrared contour map of the vehicle sample.

[0017] Step 1.5: Calculate the core temperature of the vehicle sample at the corresponding location based on the core temperature infrared profile map.

[0018] Preferably, step 1.2: smoothing the infrared image to obtain a smoothed infrared image includes:

[0019] Step 1.2.1: Construct a smoothing window, and use a smoothing model to smooth the infrared image within the smoothing window to obtain the corresponding image within the smoothing window; wherein, the smoothing model is:

[0020]

[0021] In the formula, f(a,b) represents the smoothed pixel value of pixel (a,b), D is an adjustable coefficient, x(a,b) represents the pixel value of pixel (a,b) within the smoothing window, mean(a,b) represents the mean of all pixels within the smoothing window, and σ x (a,b) represents the variance of all pixel values ​​within the smoothing window;

[0022] Step 1.2.2: Slide the smoothing window until the entire infrared image is traversed to obtain the smoothed infrared image.

[0023] Preferably, in step 1.3, the formula for calculating the gradient direction of a pixel is:

[0024]

[0025] Among them, f x (x i ,y j f represents the gradient value in the horizontal direction of the smoothed infrared image. y (x i ,y j f(x) represents the gradient value of the infrared image in the vertical direction after smoothing. i ,y j ) indicates the infrared image after smoothing in (x i ,y j The gray value at position ) , θ represents the gray value at (x i ,y j The gradient direction of the pixel at position )

[0026] Preferably, step 3: selecting optimized operating data based on the correlation between the cleaned operating data and the corresponding vehicle RAMS index, includes:

[0027] Step 3.1: Arrange the cleaned operational data and vehicle RAMS indicators in order of vehicle remaining service life to obtain the operational data queue and RAMS indicator queue;

[0028] Step 3.2: Normalize the running data queue and the RAMS indicator queue to obtain a normalized running data queue and the RAMS indicator queue;

[0029] Step 3.3: Subtract the normalized running data queue and the RAMS index queue sequentially to obtain the data sequence;

[0030] Step 3.4: Calculate the correlation coefficient based on the data sequence;

[0031] Step 3.5: Construct a correlation calculation model based on the correlation coefficient;

[0032] Step 3.6: Remove the running data with a relevance less than the preset threshold to obtain the optimized running data.

[0033] Preferably, step 3.4: calculating the correlation coefficient based on the data sequence includes:

[0034] Formula used:

[0035]

[0036] Calculate the correlation coefficient; where r 0j (k) represents the difference coefficient, Δ j (k)=|x0(k)-xj (k)|, j=1,2,...,n, x0(k) represents the value of the normalized operating data with k remaining service life, x j (k) represents the normalized RAMS metric over the remaining useful life of k, Δ j (k) represents the j-th value in the data sequence, m represents the minimum value in the data sequence, M represents the maximum value in the data sequence, and ξ represents the preset coefficient.

[0037] Preferably, the relevance calculation model is as follows:

[0038]

[0039] Where θ represents the relevance.

[0040] Preferably, in step 3.2, the normalization formula is:

[0041]

[0042] Where, x′ pi Let x be the normalized value of the i-th variable in the running data queue and the RAMS indicator queue. pi Let X be the original value of the i-th variable in the running data queue and the RAMS indicator queue, min{X} be the minimum value in the running data queue and the RAMS indicator queue, and max{X} be the maximum value in the running data queue and the RAMS indicator queue.

[0043] The present invention also provides an electronic device, including a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor. The transceiver, the memory, and the processor are connected via the bus. The computer program, when executed by the processor, implements the steps in the above-described method for monitoring RAMS data of rail vehicles based on big data technology.

[0044] The present invention also provides a computer-readable storage medium having a computer program stored thereon, characterized in that the computer program, when executed by a processor, implements the steps in the above-described method for monitoring RAMS data of rail vehicles based on big data technology.

[0045] According to specific embodiments provided by the present invention, the present invention discloses the following technical effects:

[0046] This invention relates to a method for monitoring RAMS data of rail vehicles based on big data technology. Compared with the prior art, this invention can quickly acquire a large amount of operational data of vehicle samples based on big data technology. Through data cleaning and screening, the accuracy and reliability of the data are improved, which can more accurately predict the RAMS index of the target vehicle, thereby discovering potential problems in advance and reducing the risk of failure.

[0047] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0048] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0049] Figure 1 A flowchart of a rail vehicle RAMS data monitoring method based on big data technology is provided in an embodiment of the present invention;

[0050] Figure 2 A training principle diagram provided in the embodiments of the present invention. Detailed Implementation

[0051] In the description of this invention, it should be understood that the terms "center," "longitudinal," "lateral," "length," "width," "thickness," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," "clockwise," and "counterclockwise," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing this invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this invention.

[0052] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0053] In this invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," "linking," and "fixing," etc., should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0054] Reference Figure 1 A method for monitoring RAMS data of rail vehicles based on big data technology, comprising:

[0055] Step 1: Obtain the operating data of various vehicle samples under different RAMS indicators; the operating data includes: motor current, maximum traction force of the power system, maximum vehicle speed, vehicle core temperature, maximum acceleration, wheel axle vibration, wheel axle load, vehicle body tilt angle, remaining fuel in the fuel tank, fuel consumption rate, and vehicle interior humidity;

[0056] In practical applications, vehicle temperature distribution is a crucial parameter that significantly impacts a vehicle's RAMS (Rapid Energy Storage System) indicators. For example, if a vehicle's engine malfunctions, it may generate abnormal heat. This abnormal heat is typically detected and identified by temperature sensors. However, traditional temperature sensors usually only measure the temperature of a single point on an object, failing to provide information on the overall temperature distribution across the surface. Furthermore, most temperature sensors require contact with the object being measured, which can potentially harm the object, especially under high temperatures or in fragile conditions. Therefore, this invention, through the analysis and processing of infrared images, can identify the core temperature at various points on the vehicle.

[0057] Specifically, in step 1, the vehicle core temperature is obtained through the following steps:

[0058] Step 1.1: Use an infrared camera to acquire infrared images of the vehicle samples;

[0059] Step 1.2: Smooth the infrared image to obtain a smoothed infrared image;

[0060] Specifically, step 1.2 includes:

[0061] Step 1.2.1: Construct a smoothing window, and use a smoothing model to smooth the infrared image within the smoothing window to obtain the corresponding image within the smoothing window; wherein, the smoothing model is:

[0062]

[0063] In the formula, f(a,b) represents the smoothed pixel value of pixel (a,b), D is an adjustable coefficient, x(a,b) represents the pixel value of pixel (a,b) within the smoothing window, mean(a,b) represents the mean of all pixels within the smoothing window, and σ x (a,b) represents the variance of all pixel values ​​within the smoothing window;

[0064] Step 1.2.2: Slide the smoothing window until the entire infrared image is traversed to obtain the smoothed infrared image.

[0065] Since details and features in infrared images are not prominent enough, the present invention smooths them to help highlight the main features in the image, making them clearer and easier to identify contours.

[0066] Step 1.3: Calculate the gradient direction of each pixel in the smoothed infrared image; in Step 1.3, the formula for calculating the gradient direction of a pixel is:

[0067]

[0068] Among them, f x (x i ,y j f represents the gradient value in the horizontal direction of the smoothed infrared image. y (x i ,y j f(x) represents the gradient value of the infrared image in the vertical direction after smoothing. i ,y j ) indicates the infrared image after smoothing in (x i ,y j The gray value at position ) , θ represents the gray value at (x i ,y j The gradient direction of the pixel at position )

[0069] Step 1.4: Compare the pixel values ​​of the target pixel with those of its neighboring pixels in the corresponding gradient direction, and extract the target pixel corresponding to the maximum pixel value as the contour point. Traverse the entire smoothed infrared image to obtain the core temperature infrared contour map of the vehicle sample.

[0070] Step 1.5: Calculate the core temperature of the vehicle sample at the corresponding location based on the core temperature infrared profile map.

[0071] Step 2: Perform data cleaning on the operating data under the different RAMS indicators to obtain cleaned operating data;

[0072] Step 3: Filter the optimized operating data based on the correlation between the cleaned operating data and the corresponding vehicle RAMS index;

[0073] In actual production activities, vehicle operating data is often closely related to vehicle RAMS (Range Performance Index). For example, if a vehicle's engine temperature is abnormal, its RAMS will decrease accordingly. Therefore, to predict vehicle RAMS, it is essential to first analyze, summarize, and select operating data to improve the relevance of the sample.

[0074] Furthermore, step 3 includes:

[0075] Step 3.1: Arrange the cleaned operational data and vehicle RAMS indicators in order of vehicle remaining service life to obtain the operational data queue and RAMS indicator queue;

[0076] Step 3.2: Normalize the running data queue and the RAMS indicator queue to obtain a normalized running data queue and the RAMS indicator queue; this invention can use the max-min normalization method to complete the data normalization process, wherein the normalization formula is:

[0077]

[0078] Where, x′ pi Let x be the normalized value of the i-th variable in the running data queue and the RAMS indicator queue. pi Let X be the original value of the i-th variable in the running data queue and the RAMS indicator queue, min{X} be the minimum value in the running data queue and the RAMS indicator queue, and max{X} be the maximum value in the running data queue and the RAMS indicator queue.

[0079] Step 3.3: Subtract the normalized running data queue and the RAMS index queue sequentially to obtain the data sequence;

[0080] Step 3.4: Calculate the correlation coefficient based on the data sequence;

[0081] In step 3.4, the following formula can be used:

[0082]

[0083] Calculate the correlation coefficient; where r 0j (k) represents the difference coefficient, Δ j (k)=|x0(k)-x j (k)|,j=1 , 2,...,n, where x0(k) represents the normalized operating data value with k remaining service life, x j (k) represents the normalized RAMS metric over the remaining useful life of k, Δ j(k) represents the j-th value in the data sequence, m represents the minimum value in the data sequence, M represents the maximum value in the data sequence, and ξ represents the preset coefficient.

[0084] Step 3.5: Construct a correlation calculation model based on the correlation coefficient; specifically, the correlation calculation model is as follows:

[0085]

[0086] Where θ represents the relevance.

[0087] This invention utilizes a correlation calculation model to filter out operational data that vary significantly with RAMS indices under different service lives, thus eliminating overfitting caused by operational data with low correlation.

[0088] Step 3.6: Remove the running data with a relevance less than the preset threshold to obtain the optimized running data.

[0089] Step 4: Use the optimized running data as training samples and input them into the neural network to train and obtain the RAMS data prediction model for rail vehicles;

[0090] Reference Figure 2 The selected operational data is input into a BP neural network, and optimization algorithms such as backpropagation are used to update the weights and biases of each layer so that the objective function is minimized, thus obtaining the RAMS data prediction model for rail vehicles.

[0091] Step 5: Input the target vehicle's operating data into the rail vehicle RAMS data prediction model to obtain the target vehicle's RAMS index.

[0092] This invention, based on big data technology, can quickly acquire operational data from a large number of vehicle samples. Through data cleaning and filtering, it improves the accuracy and reliability of the data, thereby enabling more accurate prediction of the RAMS index of the target vehicle, thus identifying potential problems in advance and reducing the risk of failure.

[0093] The present invention also provides an electronic device, including a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor. The transceiver, the memory, and the processor are connected via the bus. The computer program, when executed by the processor, implements the steps in the above-described method for monitoring RAMS data of rail vehicles based on big data technology.

[0094] Compared with the prior art, the beneficial effects of the electronic device provided by the present invention are the same as those of the RAMS data monitoring method for rail vehicles based on big data technology described in the above technical solution, and will not be repeated here.

[0095] The present invention also provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps in the above-described method for monitoring RAMS data of rail vehicles based on big data technology.

[0096] Compared with the prior art, the beneficial effects of the computer-readable storage medium provided by the present invention are the same as those of the RAMS data monitoring method for rail vehicles based on big data technology described in the above technical solution, and will not be repeated here.

[0097] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for monitoring RAMS data of rail vehicles, characterized in that, include: Step 1: Obtain the operating data of various vehicle samples under different RAMS indicators; the operating data includes: motor current, maximum traction force of the power system, maximum vehicle speed, vehicle core temperature, maximum acceleration, wheel axle vibration, wheel axle load, vehicle body tilt angle, remaining fuel in the fuel tank, fuel consumption rate, and vehicle interior humidity; Step 2: Perform data cleaning on the operating data under the different RAMS indicators to obtain cleaned operating data; Step 3: Filter the optimized operating data based on the correlation between the cleaned operating data and the corresponding vehicle RAMS index; Step 4: Use the optimized running data as training samples and input them into the neural network to train and obtain the RAMS data prediction model for rail vehicles; Step 5: Input the target vehicle's operating data into the rail vehicle RAMS data prediction model to obtain the target vehicle's RAMS index; In step 1, the vehicle core temperature is obtained through the following steps: Step 1.1: Use an infrared camera to acquire infrared images of the vehicle samples; Step 1.2: Smooth the infrared image to obtain a smoothed infrared image; Step 1.3: Calculate the gradient direction of each pixel in the smoothed infrared image; Step 1.4: Compare the pixel values ​​of the target pixel with those of its neighboring pixels in the corresponding gradient direction, and extract the target pixel corresponding to the maximum pixel value as the contour point. Traverse the entire smoothed infrared image to obtain the core temperature infrared contour map of the vehicle sample. Step 1.5: Calculate the core temperature of the vehicle sample at the corresponding location based on the core temperature infrared profile map; Step 1.2: Smoothing the infrared image to obtain a smoothed infrared image, including: Step 1.2.1: Construct a smoothing window, and use a smoothing model to smooth the infrared image within the smoothing window to obtain the corresponding image within the smoothing window; wherein, the smoothing model is: In the formula, Represents pixels ( a , b In the smoothed pixel values, D This is an adjustable coefficient. Represents pixels ( a , b Pixel values ​​within the smoothing window, This represents the mean of all pixels within the smoothing window. This represents the variance of all pixel values ​​within the smoothing window. Step 1.2.2: Slide the smoothing window until the entire infrared image is traversed to obtain the smoothed infrared image.

2. The method for monitoring RAMS data of rail vehicles according to claim 1, characterized in that, In step 1.3, the formula for calculating the gradient direction of a pixel is: in, This represents the gradient value in the horizontal direction of the smoothed infrared image. This represents the gradient value in the vertical direction of the smoothed infrared image. This indicates the infrared image after smoothing. The grayscale value at the location, Indicates in The gradient direction of the pixel at the given location.

3. The method for monitoring RAMS data of rail vehicles according to claim 1, characterized in that, Step 3: Based on the correlation between the cleaned operational data and the corresponding vehicle RAMS index, optimized operational data is selected, including: Step 3.1: Arrange the cleaned operational data and vehicle RAMS indicators in order of vehicle remaining service life to obtain the operational data queue and RAMS indicator queue; Step 3.2: Normalize the running data queue and the RAMS indicator queue to obtain a normalized running data queue and the RAMS indicator queue; Step 3.3: Subtract the normalized running data queue and the RAMS index queue sequentially to obtain the data sequence; Step 3.4: Calculate the correlation coefficient based on the data sequence; Step 3.5: Construct a correlation calculation model based on the correlation coefficient; Step 3.6: Remove the running data with a relevance less than the preset threshold to obtain the optimized running data.

4. The method for monitoring RAMS data of rail vehicles according to claim 3, characterized in that, Step 3.4: Calculate the correlation coefficient based on the data sequence, including: Formula used: Calculate the correlation coefficient; where, Indicates the difference coefficient. , j =1,2,..., n , Indicates in k The value of normalized operating data over the remaining service life. Indicates in k Normalized RAMS metric over remaining useful life Represents the first in the data sequence j A number, m This represents the minimum value in the data sequence. M Represents the maximum value in the data sequence. This indicates the preset coefficient.

5. The method for monitoring RAMS data of rail vehicles according to claim 4, characterized in that, The correlation calculation model is as follows: in, Indicates relevance.

6. The method for monitoring RAMS data of rail vehicles according to claim 3, characterized in that, In step 3.2, the normalization formula is: in, For the first run data queue and RAMS indicator queue i The normalized values ​​of each variable For the first run data queue and RAMS indicator queue i The original values ​​of each variable, The minimum value in the running data queue and the RAMS indicator queue. This represents the maximum value in the running data queue and the RAMS indicator queue.

7. An electronic device comprising a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the transceiver, the memory, and the processor are connected via the bus, characterized in that, When the computer program is executed by the processor, it implements the steps in the rail vehicle RAMS data monitoring method as described in any one of claims 1-6.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps in the rail vehicle RAMS data monitoring method as described in any one of claims 1-6.

Images