Modular train braking method, system and equipment and storage medium

Abstract

The invention relates to the technical field of train braking, provides a modularized train braking method, system and equipment and a storage medium, and solves the problems that in the prior art, braking pressure adjustment lacks space pertinence, local heat accumulation is intensified, and heat management efficiency is low. The method comprises the following steps: identifying a local hot spot region of which the temperature exceeds a preset safety range from a temperature distribution image, and extracting a target geometric feature parameter of the local hot spot region; in combination with the current running state information of the train, a brake pressure adjusting parameter of the train is generated through the heat conduction model; and optimizing the brake pressure adjustment parameter to obtain a pressure adjustment parameter, and sending the pressure adjustment parameter to a pneumatic brake device in the modular train brake system, so that the pneumatic brake device applies a dynamically changing brake force based on the optimized brake pressure adjustment parameter. Local overheating feature recognition can be achieved, the braking pressure is dynamically adjusted to accurately control the temperature, and safe and reliable braking is ensured.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of train braking technology, and in particular to a modular train braking method, system, device and storage medium. BACKGROUND

[0002] During high-speed braking of a train, the area between the brake disc and the pneumatic device is prone to instantaneous high temperature due to intense energy conversion, and the local temperature can reach above 800℃, resulting in material thermal degradation, thermal cracks and brake performance degradation. To ensure safety and stability under emergency braking conditions, the temperature field distribution characteristics of the friction interface need to be obtained in real time, the abnormal overheating area needs to be accurately identified, and the brake force distribution needs to be quickly and adaptively adjusted based on multi-dimensional dynamic parameters to avoid brake failure risks caused by local thermal runaway.

[0003] The existing scheme uses an infrared thermal imager to monitor the temperature distribution of the brake disc, extracts the over-temperature area through threshold segmentation, calculates the overall brake pressure compensation value by combining a fixed weight algorithm, and finally adjusts the brake force uniformly through the brake control system.

[0004] However, the existing scheme only relies on simple area statistics of the high-temperature area, resulting in lack of spatial pertinence in brake pressure adjustment, aggravating local heat accumulation, and reducing the effectiveness of heat management. SUMMARY

[0005] The present application provides a modular train braking method, system, device and storage medium to solve the problems of lack of spatial pertinence in brake pressure adjustment, aggravation of local heat accumulation and low effectiveness of heat management in the prior art.

[0006] In a first aspect, the present application provides a modular train braking method, comprising:

[0007] obtaining temperature distribution data of a target area on a train, the target area being an area on the train where the surface of a brake disc contacts a pneumatic braking device;

[0008] identifying a local hot spot area whose temperature exceeds a preset safety range from a temperature distribution image corresponding to the temperature distribution data, and extracting a target geometric feature parameter of the local hot spot area from the temperature distribution image;

[0009] generating a brake pressure adjustment parameter of the train based on the target geometric feature parameter of the local hot spot area and in combination with current running state information of the train using a heat conduction model;

[0010] optimizing the brake pressure adjustment parameter to obtain an optimized brake pressure adjustment parameter;

[0011] The optimized brake pressure adjustment parameter is sent to a pneumatic braking device in the modular train braking system, so that the pneumatic braking device applies a dynamically changing braking force based on the optimized brake pressure adjustment parameter.

[0012] Optionally, the local hotspot region with a temperature exceeding a preset safety range is identified from a temperature distribution image corresponding to the temperature distribution data, and a target geometric feature parameter of the local hotspot region is extracted from the temperature distribution image, including:

[0013] In the temperature distribution image, a local hotspot region with a temperature value exceeding a preset safety range is identified through a preset safety temperature range threshold;

[0014] Boundary detection is performed on the local hotspot region to obtain a boundary contour of the local hotspot region, and an initial geometric feature parameter of the local hotspot region is calculated based on the boundary contour;

[0015] Based on the initial geometric feature parameter, morphological analysis is performed on the local hotspot region to obtain a structural distribution feature of the local hotspot region;

[0016] The initial geometric feature parameter and the structural distribution feature are fused to generate an intermediate geometric feature parameter of the local hotspot region;

[0017] The intermediate geometric feature parameter is optimized to eliminate redundant parameters, retain feature parameters with a contribution value greater than a preset threshold for describing the local hotspot region, and generate a target geometric feature parameter of the local hotspot region.

[0018] In a second aspect, the present application provides a modular train braking system, including:

[0019] An acquisition module is configured to acquire temperature distribution data of a target region on a train, the target region being a region on the train where a brake disc surface contacts a pneumatic braking device;

[0020] An extraction module is configured to identify a local hotspot region with a temperature exceeding a preset safety range from a temperature distribution image corresponding to the temperature distribution data, and extract a target geometric feature parameter of the local hotspot region from the temperature distribution image;

[0021] A generation module is configured to generate a brake pressure adjustment parameter of the train based on the target geometric feature parameter of the local hotspot region, in combination with current running state information of the train, and using a heat conduction model;

[0022] An optimization module is configured to optimize the brake pressure adjustment parameter to obtain an optimized brake pressure adjustment parameter;

[0023] sending module; sending the optimized brake pressure adjustment parameter to a pneumatic brake device in the modular train braking system, so that the pneumatic brake device applies a dynamically changing brake force based on the optimized brake pressure adjustment parameter.

[0024] In a third aspect, the present application provides a computing device, comprising a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component, to implement the modular train braking method according to any one of the first aspect.

[0025] In a fourth aspect, the present application provides a computer storage medium, which stores a computer program; when the computer program is executed by a computer, the modular train braking method according to any one of the first aspect is implemented.

[0026] The beneficial effects of the present application are as follows:

[0027] The modular train braking method provided in the present application has the following beneficial effects: by obtaining the temperature distribution data of the contact area between the brake disc surface and the pneumatic brake device, the upgrade from traditional single-point temperature measurement to two-dimensional temperature field monitoring is realized, the temperature change of the region can be fully captured, the local high-temperature point is avoided, and high-resolution data basis is provided for subsequent analysis; then, the local hotspot area exceeding the safe range is identified based on the temperature distribution image, and its geometric feature parameters are extracted, the thermal anomaly phenomenon is converted into quantifiable physical indicators, this step uses image processing algorithm to realize intelligent diagnosis, reduces the error of manual intervention, and provides accurate input parameters for the heat conduction model;

[0028] Then, the development trend of the local hotspot is calculated by using the heat conduction model combined with the current running state of the train, and the corresponding brake pressure adjustment parameter is generated, this process considers the thermal-mechanical coupling effect, ensures that the dynamic adjustment of the brake pressure can effectively inhibit the deterioration of the hotspot, and will not excessively affect the overall braking performance; subsequently, the brake pressure adjustment parameter is optimized, a balance between cooling demand and braking efficiency is achieved through a multi-objective optimization algorithm, and interference factors such as sensor noise are eliminated, and the control stability is improved;

[0029] On this basis, the optimized brake pressure adjustment parameter is sent to the actuator of the modular train braking system, a dynamically changing brake force is applied to the region corresponding to the local hotspot, and precise regulation and control is realized. This method can effectively inhibit the fault risks such as thermal cracking and brake disc deformation, prolong the service life of the braking system, and adapt to the braking thermal management demand under different operating conditions.

[0030] Further, the method realizes high-precision quantification of the geometric characteristics of the hot spot area through multi-level feature fusion and optimization; the spatial distribution of the hot spot can be comprehensively described by combining the boundary contour and morphological analysis, overcoming the limitations of traditional single parameters such as the highest temperature; the contributions of geometric and structural characteristics are adaptively balanced in the normalization and nonlinear superposition process, improving the prediction ability of the features on the evolution trend of the hot spot, and after eliminating the redundant parameters, the calculation burden is reduced, and the relevance of the input parameters of the heat conduction model is ensured, thereby enhancing the accuracy and real-time performance of the brake pressure regulation.

[0031] These aspects or other aspects of the present application will be more apparent in the following description of the embodiments. BRIEF DESCRIPTION OF DRAWINGS

[0032] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor.

[0033] Figure 1 A flowchart of a modular train braking method provided by an embodiment of the present application;

[0034] Figure 2 A structural schematic diagram of a modular train braking system provided by an embodiment of the present application;

[0035] Figure 3 A structural schematic diagram of a computing device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0036] In order to enable those skilled in the art to better understand the technical solutions of the present application, the technical solutions in the embodiments of the present application will be described clearly and completely in the following with reference to the drawings in the embodiments of the present application.

[0037] In some of the processes described in the specification and in the drawings of the present application, a plurality of operations appear in a specific order, but it should be clearly understood that these operations can be executed or performed in parallel, or in a different order from that in which they appear in the present text. The serial numbers of the operations, such as 11, 12, etc., are only used to distinguish different operations, and the serial numbers themselves do not represent any execution order. In addition, these processes can include more or fewer operations, and the operations can be executed in sequence or in parallel. It should be noted that the descriptions of "first", "second", etc. in the present text are used to distinguish different messages, devices, modules, etc., and do not represent the order of precedence. Also, "first", "second" are not of different types.

[0038] With reference to the accompanying drawings, the technical solutions in the embodiments of the present application will be described clearly and completely. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work fall within the scope of the present application.

[0039] Figure 1 A flow chart of a modular train braking method provided in the embodiments of the present application is shown in FIG. 1, which comprises the following steps. Figure 1

[0040] S11, acquiring temperature distribution data of a target region on a train, the target region being a region on the train where a brake disc surface contacts a pneumatic braking device.

[0041] The pneumatic braking device can refer to a pneumatic relay, and thus the target region can specifically refer to an interface where the train brake disc contacts the pneumatic relay.

[0042] The temperature distribution data contains temperature values and spatial distribution characteristics of each coordinate point in the region, and the temperature distribution data can be collected by a plurality of temperature sensors arranged on the brake disc surface.

[0043] Moreover, the present application is provided with a controller, which establishes stable data connection with the temperature sensors distributed on the brake disc surface and the contact position of the pneumatic braking device, and receives temperature data collected by each temperature sensor in real time.

[0044] Then, the received original temperature data is preprocessed, which includes operations such as removing noise interference, data calibration, and data format conversion, to ensure the accuracy and consistency of the data. Then, a three-dimensional data model reflecting the temperature distribution of the target region is constructed according to the preprocessed temperature data, to provide accurate data basis for subsequent generation of temperature distribution images.

[0045] S12, identifying a local hot spot region whose temperature exceeds a preset safety range from a temperature distribution image corresponding to the temperature distribution data, and extracting target geometric feature parameters of the local hot spot region from the temperature distribution image.

[0046] The local hot spot region refers to a continuous high-temperature region whose temperature exceeds the allowable threshold of the material, and the target geometric feature parameters include hot spot area, perimeter, and shape factor.

[0047] ​The step can include the following process: based on a predetermined image generation algorithm, converting the temperature distribution data into an intuitive temperature distribution image, in which the gray value or color value of each pixel point in the image corresponds to the actual temperature value at the corresponding position in the target area; on the generated temperature distribution image, by setting a suitable temperature threshold, using image recognition algorithm to automatically identify the local hot spot area whose temperature exceeds the preset safety range, and marking the identified hot spot area; for the marked local hot spot area, using image analysis techniques such as edge detection, contour extraction and other algorithms to accurately calculate the geometric feature parameters of the local hot spot area, which will be an important basis for subsequent analysis.

[0048] S13, based on the target geometric feature parameters of the local hot spot area, combining the current running state information of the train, using the heat conduction model to generate the brake pressure adjustment parameter of the train.

[0049] Wherein, the brake pressure adjustment parameter is a dynamic pressure correction coefficient for each hot spot area, such as 0.8~1.2, which is used for local brake force adjustment; the running state information includes the running speed of the train, the load condition and the brake history record, etc.

[0050] The heat conduction model is constructed and applied as follows: a heat conduction model considering the material properties, heat conduction properties and fluid dynamics of the train brake system is established; the geometric feature parameters of the local hot spot area, the current running state information of the train and the heat conduction coefficient of the brake disc and the pneumatic brake device and other related parameters are input into the heat conduction model; the heat conduction model simulates and calculates the temperature variation trend and heat transfer process of the local hot spot area under different brake pressures according to the input parameters.

[0051] It should be noted that the specific structure and form of the heat conduction model are not limited in this embodiment, and can be set according to the actual situation.

[0052] S14, optimizing the brake pressure adjustment parameter to obtain an optimized brake pressure adjustment parameter.

[0053] Wherein, the optimization process can be solved by multi-objective constraint, which can balance temperature suppression and brake force stability.

[0054] S15, sending the optimized brake pressure adjustment parameter to the pneumatic brake device in the modular train brake system, so that the pneumatic brake device is based on the optimized brake pressure adjustment parameter.

[0055] Wherein, the application can refer to independent pressure control of each brake cylinder based on the pressure parameter table.

[0056] Modular train brake system is a brake system based on distributed control architecture, which can be composed of multiple independent functional modules such as control unit, pressure regulating module, sensor network, etc. through high-speed communication bus interconnection, supporting on-demand configuration, dynamic reconstruction and fault isolation.

[0057] The local hot spot area is the part of the brake disc that is actually in contact with the pneumatic device, and its spatial distribution and pressure load dynamically change with the braking condition. It is the core area of the pneumatic braking energy conversion and heat generation.

[0058] The following is a specific example: in the high-speed rail emergency braking scenario, when the train is emergency braking at 350km / h, the optical fiber sensor detects a 720℃ hot spot with a diameter of 8mm at the 3 o'clock direction of the No. 3 brake disc, and generates a temperature distribution matrix; then the hot spot area is segmented, and its area is calculated as 50mm 2 , the shape factor is 0.42, and it is determined as a regular circular high temperature area; then combined with the current speed and axle load of 23t, the pressure correction coefficient of the area is output from 1.0 to 0.85 through the heat conduction model; after optimization by the multi-objective optimization algorithm (Nondominated Sorting Genetic Algorithm II, NSGA-II), the coefficient is adjusted to 0.82, and the hardware-in-the-loop test shows that the temperature can be reduced to 655℃ and the braking force fluctuation is 2.7%; the brake controller sends a pressure command of 0.82 times to the No. 3 brake cylinder in the next 10ms period, and the hot spot temperature falls to 630℃ within 2 seconds after synchronous adjustment.

[0059] By executing S11-S15, the embodiment of the present application realizes the active inhibition of brake interface thermal runaway by high-resolution temperature field real-time sensing, hot spot geometric feature accurate extraction, multi-physical field coupling modeling and distributed dynamic pressure regulation; under the condition of 350km / h emergency braking, the local hot spot temperature rise peak value can be reduced by 18%-22%, the brake disc life is extended to more than 400,000 kilometers, and at the same time, the brake unit pressure synchronous error of the whole train is less than 1.5%, and the brake distance fluctuation rate is controlled within 2.8% of the standard requirement.

[0060] In one possible embodiment, S12, from the temperature distribution image corresponding to the temperature distribution data, identify the local hot spot area whose temperature exceeds the preset safety range, and extract the target geometric feature parameters of the local hot spot area from the temperature distribution image, including:

[0061] Step 121, in the temperature distribution image, identify the local hot spot area whose temperature value exceeds the preset safety range through the preset safety temperature range threshold.

[0062] The preset safety temperature range threshold is a temperature threshold of a dynamic temperature interval set according to the thermal recession characteristic of the brake disc material, and the upper limit and the lower limit of the threshold are not specifically limited in the embodiment; the local hot spot region refers to a connected domain formed by continuous over-temperature pixels in the temperature distribution image.

[0063] In step 121, the processing flow of the temperature distribution image starts from an adaptive threshold segmentation technique, which intelligently identifies the local hot spot region exceeding the safety range through a dynamic multi-threshold segmentation algorithm. Specifically, after the infrared thermal imager captures the surface temperature data of the brake disc, a non-local mean filter is first applied to eliminate motion blur caused by the rotation of the brake disc, and then a double-threshold division scheme is automatically generated based on the maximum inter-class variance method to divide the temperature field into a safety zone, a transition zone and an over-temperature zone. Then, when performing 8-neighbor connected domain labeling on the over-temperature zone, morphological closing operation is combined to filter out noise interference and accurately mark the continuous high-temperature region.

[0064] This process fully embodies the intelligent characteristics: the threshold parameter is adjusted in real time according to the thermal recession characteristic of the brake disc material, the connected domain analysis ensures that only the persistent thermal risk region is marked, and the filtering algorithm is specially optimized to cope with high-speed rotating conditions. The whole recognition mechanism is closely related to the main control process of the system.

[0065] For example, taking the brake disc temperature monitoring under a certain train emergency braking condition as an example, the real-time temperature distribution image captured by the infrared thermal imager has a resolution of 1024x768 pixels and a temperature range of 0~800℃. On this basis, the safety temperature threshold is set to 650℃, and the improved multi-threshold segmentation algorithm is combined with morphological gradient edge detection to identify hot spots: non-local mean denoising is performed on the original thermal image, such as filter parameter h=0.8, to eliminate motion blur caused by the rotation of the brake disc.

[0066] The maximum inter-class variance method is used to automatically determine the double-threshold in the temperature histogram, where the upper temperature threshold T1=630℃ and the lower temperature threshold T2=650℃, and then the image is divided into a safety zone with T<630℃, a transition zone with 630℃≤T<650℃ and an over-temperature zone with T≥650℃. 8-neighbor connected domain labeling is performed on the over-temperature zone to identify two local hot spots: hot spot A and hot spot B.

[0067] In step 122, the boundary of the local hot spot region is detected to obtain the boundary contour of the local hot spot region, and based on the boundary contour, the initial geometric feature parameters of the local hot spot region are calculated.

[0068] The boundary contour refers to the peripheral continuous pixel chain of the hot spot region, and the initial geometric feature parameters include area, perimeter, minimum circumscribed rectangle aspect ratio, etc.

[0069] Boundary detection is used to identify the edge of local hot spot region and the surrounding area in temperature distribution image, and its core is to locate the transition area with significant changes in temperature field by calculating the pixel gradient or contrast mutation.

[0070] The boundary contour is a closed geometric figure generated by polygon fitting of the discrete edge point set output by boundary detection, which is used to represent the shape, size and topological structure of the local hot spot region.

[0071] In step 122, after completing the hot spot recognition, it enters the boundary detection stage. Specifically, an improved edge detection algorithm is used to realize sub-pixel level contour extraction through Gaussian kernel filtering and non-maximum suppression technology. When the hot spot boundary chain code is obtained, the algorithm applies Green's theorem to convert the area integral of the region to the curve integral of the boundary, and establishes the conversion matrix of image coordinates and brake disc physical position.

[0072] The boundary detection result in this stage directly affects the quality of subsequent features, and its precision advantage enables the system to accurately quantify the morphological characteristics of hot spots, providing reliable input for heat conduction modeling.

[0073] For example, in the temperature monitoring scene of a certain high-speed train brake disc, the 1024x768 resolution temperature image collected by the infrared thermal imager shows a local over-temperature region. The improved edge detection algorithm is used for boundary detection, where the Gaussian kernel parameter σ is 1.5, and the double threshold is set to 630℃ and 650℃ respectively. After non-maximum suppression of the over-temperature region, the closed boundary contour is obtained through 8-neighbor connected component analysis, and the hot spot A contour contains 85 pixel points and is distributed in an elliptical shape.

[0074] Through Green's theorem, the area integral of the region is converted to the curve integral of the boundary, and the area of hot spot A and its proportion of the contact surface are calculated. Then the aspect ratio is calculated using the vertex chain code. If the major axis is 15 pixels and the minor axis is 7 pixels, the aspect ratio is about 2.14. For example, the offset Δx from the center of the brake disc is +12.3 mm; the sampling interval is 0.1 mm, and the maximum gradient calculated along the boundary normal is 78℃ / mm.

[0075] Compared with the three-dimensional profile reconstructed by laser scanning point cloud, this method effectively reduces the boundary positioning error and the relative error of area calculation, and realizes sub-pixel level geometric feature extraction by integrating the integral conversion of discrete Green's theorem and the boundary coding of vertex chain code, which improves the calculation efficiency compared with the traditional chain code method.

[0076] Step 123, based on the initial geometric feature parameters, morphological analysis is performed on the local hot spot region to obtain the structural distribution characteristics of the local hot spot region.

[0077] The core of the morphological analysis is to analyze the geometric complexity and internal defects of the high-temperature area, and the specific algorithm type used in the morphological analysis is not limited in the embodiment, and can be set according to the actual situation. For example, the shape of the target area is topologically operated by a circular kernel, a rectangular kernel or the like, so as to extract the internal structure, hole distribution and edge feature thereof.

[0078] The structural distribution characteristics of the local hot spot area are quantitative parameters for describing the internal topological morphology and edge irregularity of the hot spot, including hole density, skeleton branch degree, convex hull defect rate, Euler number and the like.

[0079] In step 123, the internal structure of the hot spot is topologically analyzed based on the mathematical morphological principle, and then the corrosion-expansion operation is performed by the circular structure kernel designed by optimization, so as to effectively separate the hot spot core area and the transition area. In this process, the algorithm calculates the fractal dimension to quantify the boundary irregularity characteristics, and combines the Voronoi diagram to analyze the influence of the heat dissipation structure on the heat conduction path.

[0080] In specific implementation, the morphological analysis can include a multi-layer processing procedure executed in sequence or selectively, so as to gradually deepen the understanding of the hot spot structure and ensure the reliability of the analysis.

[0081] Firstly, in the morphological analysis stage of the local hot spot area, the processing strategy is dynamically adjusted according to the detected initial geometric characteristic parameters, such as: the optimal size of the structure element is automatically calculated and generated based on the hot spot area, so as to ensure that the diameter of the circular kernel is accurately matched with the size of the hot spot; at the same time, the rectangular kernel or the circular kernel type is intelligently selected in combination with the shape factor, so as to effectively adapt to the processing needs of different morphological hot spots; for the hot spot with spatial offset, the orientation of the structure element is rotated in real time according to the centroid offset, so as to accurately match the spatial orientation characteristics of the target area. Through this step, an adaptive structure element configuration system can be established.

[0082] Secondly, on the basis of completing the configuration of the structure element, the depth topological analysis is realized by combining multi-level morphological operations, for example, the directed corrosion operation is first applied to strip the temperature transition area outside the hot spot, and then the high-temperature core area is accurately extracted based on the connected domain reorganization algorithm, and the area ratio parameter of the core area and the whole area is calculated. In the internal structure analysis layer, the hole defect in the hot spot can be identified by using the difference topological analysis method, a hole distribution thermal map model is established, and the density and spatial distribution characteristics thereof are quantified. For the complex boundary characteristics, the multi-scale boundary unfolding operation is performed to accurately calculate the fractal dimension index.

[0083] In another embodiment, based on the morphological features obtained by the above morphological analysis, a heat conduction path prediction model is further constructed; the difference in heat conduction efficiency of the hot spot in different directions is revealed through anisotropy analysis, a mapping relationship between the morphological features and the spatial distribution of the heat dissipation ribs of the brake disc is established, and the formation trend of the high gradient risk area is predicted according to the morphological features; the above conduction model intelligently associates the geometric features with the actual thermodynamic behavior, and provides a decision basis at the physical mechanism level for brake pressure regulation.

[0084] In other embodiments, to ensure the accuracy of the morphological features, the embodiment constructs a closed-loop verification optimization mechanism. Specifically, the mapping relationship between the morphological features and the material micro-damage is established by using X-ray tomography technology to verify the spatial correlation between the hole distribution and the material phase change area; then the morphological features and the microstructure are confirmed to have high consistency through three-dimensional reconstruction comparison, and the structure elements are dynamically calibrated based on the verification results, and a structure confidence evaluation system is established.

[0085] For example, in the temperature monitoring of a certain high-speed train brake disc, based on the initial geometric feature parameters such as the hot spot A area 38mm 2 , shape factor 2.14, and centroid offset 12.3mm, morphological spatial pattern analysis is adopted to extract structural distribution features:

[0086] First, a 3x3 circular structure kernel is used to perform erosion-expansion operation to separate the continuous high-temperature area, and the core area of the hot spot A is determined to be 32mm 2 , accounting for 84.2% of the overall area, with an equivalent diameter of 6.2mm and a boundary fractal dimension of 1.28; among them, the fractal dimension of 1.28 indicates that there is local anisotropy in the heat conduction path; then the temperature data is sampled along the normal direction of the boundary, and the gradient distribution curve is fitted, which shows that the gradient on the northwest side rises steeply, with a peak value of 92℃ / mm, and this area corresponds to the missing area of the heat dissipation ribs of the brake disc; further, the Euler number and the shape index are calculated, and combined with the Thiessen polygon diagram, it is found that the hot spot spacing d obeys the power law distribution d=2.3mm; then the X-ray tomography results show that the spatial matching degree of the structural distribution features obtained by the above morphological spatial pattern analysis and the micro-crack distribution of the brake disc is as high as 89%, confirming that the high-temperature area has a "core-shell" structure, with the core being a martensite phase change area and the periphery being a heat affected zone.

[0087] In this stage, the internal defects can be accurately quantified by using an automated hole recognition algorithm, the parameterized description of the gradient distribution curve reveals the temperature transfer law, and the X-ray verification mechanism ensures the spatial matching degree of the features and the physical damage. This deep analysis enables the system to capture the essential laws of hot spot evolution, improving the accuracy of thermal stress prediction.

[0088] Step 124: Fuse the initial geometric feature parameters with the structural distribution features to generate intermediate geometric feature parameters for local hotspot regions.

[0089] In step 124, the feature fusion stage can use a dynamic weighting mechanism to optimize parameters. For example, firstly, the geometric features and structural distribution features are normalized to eliminate dimensional differences. Then, the contribution weight of each feature is dynamically calculated using the entropy weighting method. In the weight allocation stage, a spatial decay function can be introduced to automatically increase the weight coefficient of the edge region. Finally, the hyperbolic tangent function is applied to achieve nonlinear superposition of features.

[0090] It should be noted that the specific implementation process of step 124 can be referred to steps a1~a3, and will not be repeated here.

[0091] The core of this process lies in establishing a dynamic correlation between weight allocation and thermal coupling strength: when a high-gradient region is detected, the weight of structural distribution features is automatically increased; while for homogeneous temperature regions, geometric features are strengthened. This adaptive balancing mechanism ensures that high-risk regions receive higher weights in decision-making, enabling the generated feature vectors to accurately reflect the evolution trend of hot spots.

[0092] Step 125: Optimize the intermediate geometric feature parameters to remove redundant parameters and retain feature parameters whose contribution to the description of local hotspot regions is greater than a preset threshold, thereby generating target geometric feature parameters for local hotspot regions.

[0093] In step 125, feature dimensionality reduction and selection can be achieved through parameter optimization. In this stage, the intermediate feature vector generated in step 124 is used as input, and machine learning technology is used to select the core parameters with the greatest representational ability.

[0094] Specifically, firstly, high-dimensional features are mapped to the principal component space using principal component analysis, automatically identifying and retaining the feature dimensions that contribute the most to the hotspot state variance. Based on this, a filtering algorithm based on a preset threshold is applied to directly remove parameters with low correlation to the principal components or those with redundant information. Next, to verify the physical meaning and predictive value of the retained features, an importance assessment is performed using a random forest model. For example, multiple decision trees are constructed, and the average decrease in impurity caused by each feature during tree node splitting is calculated, thereby quantifying its predictive importance for the hotspot evolution trend. The entire optimization process, through the three-level processing mechanism of principal component screening, threshold filtering, and model evaluation, ensures that only core feature parameters with a contribution exceeding the preset threshold are retained.

[0095] This application embodiment achieves efficient transformation from raw temperature data to high-value decision parameters through an end-to-end intelligent processing flow. While meeting the real-time requirements of the braking control system, it provides a precise and reliable basis for thermal state assessment and decision-making for modular braking systems.

[0096] Here is a specific example: In a hotspot analysis scenario for a certain type of train brake disc, when the train brakes at 300 km / h, an infrared thermal imager detects an abnormal area on the brake disc surface with a temperature reaching 680℃. The system first performs threshold correction on this area, dynamically increasing the threshold to 665℃, and marks three valid hotspots accordingly. Subsequently, edge detection is performed on the largest hotspot, fitting a 28-sided contour, and then calculating its initial geometric features, such as an area of ​​82 mm². 2 The perimeter is 36.7 mm and the length-to-width ratio is 1.8.

[0097] Based on this, a morphological analysis was further performed on the hotspot. The analysis results showed that the hotspot contained two holes, accounting for 7% of the area; its skeleton branching degree was 3, and the maximum convex hull depression depth was 0.32 mm. Then, the 15-dimensional features obtained above were weighted and fused to generate an intermediate feature vector. In this vector, the area and the number of holes became the main components.

[0098] Finally, through joint screening using principal component analysis and minimum absolute shrinkage and selection operator algorithms, the four core parameters of area, perimeter, number of holes, and convex hull depth were retained, with their total contribution reaching 91%.

[0099] This application's embodiments improve the accuracy of hot spot geometric feature extraction to the sub-millimeter level through dynamic threshold correction, multi-scale morphological analysis, and feature contribution optimization. Furthermore, in high-speed braking scenarios at 300km / h, it can accurately identify hot spots with a diameter >3mm, reduce feature parameter redundancy by 60%, provide highly reliable input for subsequent thermo-mechanical coupling control, and ultimately control the local temperature rise prediction error of the brake disc within ±8℃, thereby reducing the risk of thermal cracking.

[0100] In one possible embodiment, step 124, fusing the initial geometric feature parameters with the structural distribution features to generate intermediate geometric feature parameters for the local hotspot region, includes:

[0101] Step a1: Normalize the initial geometric feature parameters and structural distribution features respectively to construct the first and second tensors that are spatially aligned with the local hotspot regions.

[0102] The initial geometric feature parameters include basic geometric quantities such as the area, perimeter, and shape factor of the hotspot region.

[0103] It should be noted that this embodiment does not impose specific limitations on the calculation formula for the shape factor, and can be set accordingly based on the actual situation.

[0104] Step a2: Calculate the dynamic weight coefficients corresponding to the first tensor and the second tensor respectively.

[0105] Among them, the dynamic weighting coefficient reflects the contribution of geometric feature parameters and structural distribution characteristics to the final result, and varies with spatial location.

[0106] In this embodiment, the information entropy can be dynamically calculated using the entropy weight method, and then the corresponding weight can be determined based on the entropy value. Furthermore, this embodiment can also introduce a spatial decay function in the calculation process of the weight coefficient, thereby achieving spatial adaptation of the weight coefficient.

[0107] It should be noted that the expressions for the entropy weight method and the spatial decay function can be found in relevant techniques, and will not be elaborated here.

[0108] Step a3: Based on the dynamic weight coefficients, nonlinearly superimpose the first tensor and the second tensor to obtain the intermediate geometric feature parameters of the local hotspot region.

[0109] Nonlinear superposition enhances feature interaction through weighted fusion and nonlinear transformation.

[0110] This application's embodiments can eliminate the dimensional differences between geometric feature parameters and structural distribution features through normalized alignment, constructing a spatially aligned standardized vector; then, based on dynamic weight allocation, the contribution of geometric feature parameters and structural distribution features is adaptively adjusted; finally, nonlinear superposition is used to enhance feature interaction and generate high-precision intermediate geometric feature parameters. Therefore, in scenarios such as hot spot detection of high-speed rail brake discs, this method reduces positioning errors and improves the robustness of analysis under complex working conditions.

[0111] In one possible embodiment, S13, based on the target geometric feature parameters of the local hotspot region and combined with the train's current operating status information, the train's braking pressure adjustment parameters are generated using a heat conduction model, including:

[0112] Step 131: Spatial discretization of the target geometric feature parameters in the local hot spot area to generate a geometric parameter matrix aligned with the grid cells of the brake disc.

[0113] Among them, the local hot spot area can refer to the part of the brake disc surface where the temperature is significantly higher than the surrounding area due to the heat generated by the conversion of pneumatic braking energy; the target geometric feature parameters include spatial attributes such as the radius of curvature, area, and depth of the hot spot area;

[0114] The geometric parameter matrix is ​​a numerical matrix that is discretized into target geometric feature parameters by using finite element mesh generation technology, and corresponds one-to-one with the mesh element of the brake disc.

[0115] Step 132: Extract the real-time speed, braking duration, and ambient temperature parameters from the train's current operating status information to construct an operating status vector.

[0116] The operating state vector consists of three dimensions: real-time speed, braking duration, and ambient temperature parameters, and is used to characterize the dynamic thermal boundary conditions during the train braking process.

[0117] Step 133: Couple the geometric parameter matrix with the running state vector in multiple dimensions to generate a joint input feature set.

[0118] Among them, multidimensional coupling refers to associating geometric parameter matrices with dynamic vectors in spatial and temporal dimensions through tensor operations.

[0119] Step 134: Based on the joint input feature set, calculate the dynamic evolution process of the surface temperature field and internal thermal stress field of the brake disc through the heat conduction equation in the heat conduction model, and generate spatiotemporal distribution data to characterize the temperature gradient and stress concentration region.

[0120] The heat conduction equation can be expressed using the transient Fourier equation, and the specific expression of the heat conduction equation is not specifically limited in the embodiments of this application. It can be set according to the actual situation.

[0121] The spatiotemporal distribution data is a set of spatiotemporal coordinates of temperature gradient and stress concentration region.

[0122] Step 135: Based on the spatiotemporal distribution data, with the goal of homogenizing the thermal load on the brake disc, the brake pressure adjustment parameters are solved iteratively in reverse, and the effectiveness of the parameters is verified through preset boundary constraints. The brake pressure adjustment parameters of the train are then output.

[0123] Among them, the brake pressure adjustment parameter refers to the brake cylinder pressure value that needs to be optimized; the boundary constraints include the maximum allowable temperature and stress threshold, such as 600℃ and 80% of the material yield strength.

[0124] This application embodiment achieves accurate prediction of the brake disc thermal-mechanical field through geometric feature discretization and dynamic state coupling. Then, through reverse optimization, the uniformity of thermal load distribution is improved by 35%, avoiding the risk of thermal cracks caused by hot spots, while the braking distance is shortened by 8%.

[0125] In one possible embodiment, S14, optimizing the brake pressure adjustment parameters to obtain optimized brake pressure adjustment parameters includes:

[0126] Step 141: Discretize the brake pressure adjustment parameters to generate a parameter distribution matrix that maps one-to-one with the grid cells of the brake disc.

[0127] Among them, the braking pressure adjustment parameters include control variables such as target pressure and pressure gradient;

[0128] The parameter distribution matrix is ​​a two-dimensional matrix that establishes a mapping relationship between the coordinates of the finite element mesh of the brake disc and the pressure parameters.

[0129] Step 142: Based on the preset mechanical structure constraints of the brake disc, perform boundary stability testing on the parameters corresponding to each grid cell in the parameter distribution matrix, and select the adjustable parameter range.

[0130] Among them, the mechanical structure constraints include the maximum allowable stress, such as 271 MPa, and the thermal deformation threshold, such as 0.15 mm; the adjustable parameter range may include the pressure range, which is an interval consisting of the lower pressure limit and the upper pressure limit.

[0131] Step 143: Within the adjustable parameter range, based on the dynamic coupling relationship between braking pressure and temperature field, iteratively weight the parameters of adjacent units to generate an initial parameter sequence.

[0132] The adjustable parameter range can avoid exceeding the allowable stress of the material; the embodiments of this application do not specifically limit the expression of the above dynamic coupling relationship and its application process in the weight allocation process, and can be set accordingly according to the actual situation;

[0133] Furthermore, this embodiment does not specifically limit the type of parameters; the initial parameter sequence refers to the set of parameters generated through dynamic coupling and iterative weight allocation during the braking pressure optimization process.

[0134] Step 144: Perform multiphysics joint verification on the initial parameter sequence to obtain the verified parameter sequence.

[0135] If a parameter causes a sudden change in stress or an abnormal temperature gradient in a local mesh element, the system reverts to the pre-adjustment state and reduces the adjustment step size. The validated parameter sequence refers to the set of optimized parameters that, after joint verification within a multiphysics environment, satisfy all physical constraints and performance indicators. These parameters may include material properties, boundary conditions, and load parameters, and their validation ensures their effectiveness and reliability in a multiphysics environment.

[0136] It should be noted that this embodiment does not specifically limit the process, specific method, or type of algorithm used for multiphysics joint verification.

[0137] Step 145: Generate incremental update rules based on the verified parameter sequence. Based on the incremental update rules and combined with the real-time pressure feedback data of the braking system, generate optimized braking pressure adjustment parameters.

[0138] Among them, the incremental update rule is a dynamic adjustment strategy that generates a recursive formula for parameter adjustment based on the verified parameter sequence, such as the verified braking pressure and temperature field distribution, through mathematical modeling or machine learning methods.

[0139] It should be noted that the embodiments of this application do not specifically limit the specific content of the incremental update rules or the specific implementation process of the algorithm used in the generation process.

[0140] This application embodiment achieves precise control of the brake disc's thermo-mechanical coupling by discretizing pressure parameters and mapping them to a mesh, combined with multiphysics verification and real-time feedback. This improves the uniformity of thermal stress, shortens the braking distance, and avoids the risk of thermal cracking.

[0141] In one possible embodiment, step 144 involves performing multiphysics joint verification on the initial parameter sequence to obtain the verified parameter sequence, including:

[0142] Step b1: Based on the parameters corresponding to each grid cell in the initial parameter sequence, detect the grid cells with heat conduction continuity index and stress field abrupt changes.

[0143] The initial parameter sequence contains the optimized pressure value set for each grid cell. The heat conduction continuity index is a local heat flow consistency value calculated using Fourier's law. If this value exceeds the threshold, it is considered discontinuous.

[0144] Step b2: Adjust the state of the mesh element with abrupt stress field changes to the state corresponding to the parameters of the previous iteration, reduce the adjustment step size, and adjust the initial parameter sequence according to the reduced adjustment step size to generate an intermediate parameter sequence. Perform three consecutive iterations to verify the intermediate parameter sequence.

[0145] The previous iteration parameter is the pressure value of the unit in the previous optimization result. In this embodiment, the specific expression for reducing the adjustment step size is not specifically limited.

[0146] Step b3: Based on the verified intermediate parameter sequence, generate a verified post-parameter sequence that covers all grid cells and satisfies the multi-field equilibrium condition.

[0147] Among them, the multi-field equilibrium condition satisfies the thermal, mechanical, and acoustic coupling equations, for example:

[0148] Where k is the thermal conductivity of the material, and T is the temperature field distribution. The coefficient of friction, To contact pressure, Where ρ is the relative sliding velocity, ρ is the material density, and c is the specific heat capacity. The rate of change of temperature over time; For the von Mises equivalent effect, For the material's yield strength, These are the eigenvalues ​​of the acoustic modes. To take the real part of the complex number, a negative value indicates modal decay.

[0149] The embodiments of this application reduce the uneven distribution of heat and force in the brake disc through a three-step iteration of anomaly detection, local correction and global verification, while eliminating brake squealing noise. It is applicable to scenarios such as aircraft brakes and high-speed rail brake discs.

[0150] In one possible embodiment, step a2, calculating the dynamic weight coefficients corresponding to the first tensor and the second tensor respectively, includes:

[0151] Step a21: Calculate the first initial weight and the second initial weight based on the spatial correlation of the brake disc.

[0152] Spatial correlation is used to reflect the geometric distance and physical property relationship between brake disc grid cells, such as heat conduction path. In this application embodiment, no specific limitations are made on the specific meaning of spatial correlation, the specific calculation method, and the process for calculating each initial weight.

[0153] Step a22: Based on the preset mechanical structure constraints of the brake disc, dynamically adjust the first initial weight and the second initial weight to generate the dynamic weight coefficients corresponding to the first tensor and the second tensor respectively.

[0154] It should be noted that this embodiment does not specifically limit the content of the mechanical structure constraints, the basis for dynamic adjustment, or the type of dynamic adjustment algorithm used.

[0155] This application embodiment reduces the temperature of the hot spot area of ​​the high-speed rail brake disc by dynamically adjusting the weights of different tensors, thereby reducing stress unevenness, avoiding brake squeal, and improving the reliability and lifespan of the braking system.

[0156] Figure 2 This is a schematic diagram of a modular train braking system provided in an embodiment of this application, as shown below. Figure 2 As shown, the system includes:

[0157] The acquisition module 21 is used to acquire temperature distribution data of a target area on the train, where the target area is the area on the train where the brake disc surface is in contact with the pneumatic braking device.

[0158] Extraction module 22 is used to identify local hotspot areas whose temperature exceeds a preset safety range from the temperature distribution image corresponding to the temperature distribution data, and to extract the target geometric feature parameters of the local hotspot areas from the temperature distribution image.

[0159] The generation module 23 is used to generate the braking pressure adjustment parameters of the train based on the target geometric feature parameters of the local hot spot area and the current operating status information of the train, using a heat conduction model.

[0160] The optimization module 24 is used to optimize the brake pressure adjustment parameters to obtain the optimized brake pressure adjustment parameters.

[0161] The sending module 25 is used to send the optimized braking pressure adjustment parameters to the pneumatic braking device in the modular train braking system, so that the pneumatic braking device can apply dynamically changing braking force based on the optimized braking pressure adjustment parameters.

[0162] Figure 2 The modular train braking system described above can perform... Figure 1 The implementation principle and technical effects of the modular train braking method described in the illustrated embodiment will not be repeated here. The specific operation methods of each module and unit in the modular train braking system described above have been described in detail in the embodiments related to this method, and will not be elaborated upon here.

[0163] In one possible design, Figure 2 A modular train braking system of the embodiment shown can be implemented as a computing device, such as... Figure 3 As shown, the computing device may include a storage component 31 and a processing component 32.

[0164] The storage component 31 stores one or more computer instructions, wherein the one or more computer instructions are invoked and executed by the processing component 32.

[0165] The processing component 32 is used to: acquire temperature distribution data of a target area on the train, the target area being the area on the train's brake disc surface in contact with the pneumatic braking device; identify local hotspot areas whose temperatures exceed a preset safety range from the temperature distribution image corresponding to the temperature distribution data, and extract target geometric feature parameters of the local hotspot areas from the temperature distribution image corresponding to the temperature distribution data; generate brake pressure adjustment parameters for the train using a heat conduction model based on the target geometric feature parameters of the local hotspot areas and the train's current operating status information; optimize the brake pressure adjustment parameters to obtain optimized brake pressure adjustment parameters; and send the optimized brake pressure adjustment parameters to the pneumatic braking device in the modular train braking system so that the pneumatic braking device applies dynamically changing braking force based on the optimized brake pressure adjustment parameters.

[0166] The processing component 32 may include one or more processors to execute computer instructions to complete all or part of the steps in the above-described method. Alternatively, the processing component may be implemented as one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above-described method.

[0167] Storage component 31 is configured to store various types of data to support operations at the terminal. The storage component can be implemented from any type of volatile or non-volatile storage device or a combination thereof, such as Random Access Memory (RAM), Static Random-Access Memory (SRAM), Electrically Erasable Programmable Read Only Memory (EEPROM), Erasable Programmable Read Only Memory (EPROM), Programmable Read Only Memory (PROM), Read Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0168] Of course, computing devices may also include other components, such as input / output interfaces, display components, communication components, etc.

[0169] Input / output interfaces provide interfaces between processing components and peripheral interface modules, which can be output devices, input devices, etc.

[0170] The communication components are configured to facilitate wired or wireless communication between computing devices and other devices.

[0171] The computing device can be a physical device or an elastic computing host provided by a cloud computing platform. In this case, the computing device can refer to a cloud server, and the aforementioned processing components, storage components, etc., can be basic server resources rented or purchased from the cloud computing platform.

[0172] This application also provides a computer storage medium storing a computer program, which, when executed by a computer, can perform the above-described functions. Figure 1 A modular train braking method according to the embodiment shown.

[0173] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0174] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0175] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0176] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A modular train braking method, characterized in that, A controller used in a modular train braking system includes: Acquire temperature distribution data for a target area on the train, where the target area is the region on the train where the brake disc surface contacts the pneumatic braking device. Identify local hotspot areas where the temperature exceeds a preset safety range from the temperature distribution image corresponding to the temperature distribution data, and extract the target geometric feature parameters of the local hotspot areas from the temperature distribution image corresponding to the temperature distribution data. Based on the target geometric feature parameters of the local hotspot area and combined with the current operating status information of the train, the braking pressure adjustment parameters of the train are generated using a heat conduction model. The brake pressure adjustment parameters are optimized to obtain the optimized brake pressure adjustment parameters; The optimized braking pressure adjustment parameters are sent to the pneumatic braking device in the modular train braking system, so that the pneumatic braking device applies dynamically changing braking force based on the optimized braking pressure adjustment parameters.

2. The modular train braking method according to claim 1, characterized in that, The step of identifying local hotspot regions whose temperatures exceed a preset safety range from the temperature distribution image corresponding to the temperature distribution data, and extracting target geometric feature parameters of the local hotspot regions from the temperature distribution image, includes: In the temperature distribution image, local hotspot areas where the temperature value exceeds the preset safe temperature range are identified by using a preset safe temperature range threshold. Boundary detection is performed on the local hotspot region to obtain the boundary contour of the local hotspot region, and the initial geometric feature parameters of the local hotspot region are calculated based on the boundary contour. Based on the initial geometric feature parameters, morphological analysis is performed on the local hotspot region to obtain the structural distribution characteristics of the local hotspot region; The initial geometric feature parameters are fused with the structural distribution features to generate intermediate geometric feature parameters for local hotspot regions; The intermediate geometric feature parameters are optimized to remove redundant parameters and retain feature parameters whose contribution to the description of local hotspot regions is greater than a preset threshold, thereby generating target geometric feature parameters for local hotspot regions.

3. The modular train braking method according to claim 2, characterized in that, The step of fusing the initial geometric feature parameters with the structural distribution features to generate intermediate geometric feature parameters for local hotspot regions includes: The initial geometric feature parameters and structural distribution features are normalized respectively to construct a first tensor and a second tensor that are spatially aligned with the local hotspot region. Calculate the dynamic weight coefficients corresponding to the first tensor and the second tensor respectively; Based on the dynamic weighting coefficients, the first tensor and the second tensor are nonlinearly superimposed to obtain the intermediate geometric feature parameters of the local hotspot region.

4. The modular train braking method according to claim 1, characterized in that, The method of generating train braking pressure adjustment parameters based on the target geometric feature parameters of the local hotspot region, combined with the train's current operating status information, using a heat conduction model includes: The target geometric feature parameters of the local hotspot region are spatially discretized to generate a geometric parameter matrix aligned with the grid cells of the brake disc. Extract real-time speed, braking duration, and ambient temperature parameters from the train's current operating status information to construct an operating status vector; The geometric parameter matrix is ​​coupled with the running state vector in multiple dimensions to generate a joint input feature set; Based on the joint input feature set, the dynamic evolution process of the surface temperature field and internal thermal stress field of the brake disc is calculated through the heat conduction equation in the heat conduction model, generating spatiotemporal distribution data to characterize the temperature gradient and stress concentration region. Based on the spatiotemporal distribution data, with the goal of homogenizing the thermal load on the brake disc, the brake pressure adjustment parameters are solved iteratively in reverse. The effectiveness of the parameters is verified by the preset boundary constraints, and the brake pressure adjustment parameters of the train are output.

5. The modular train braking method according to claim 1, characterized in that, The optimization of the brake pressure adjustment parameters to obtain optimized brake pressure adjustment parameters includes: The braking pressure adjustment parameters are discretized to generate a parameter distribution matrix that maps one-to-one with the grid cells of the brake disc. Based on the preset mechanical structure constraints of the brake disc, the boundary stability of the parameters corresponding to each grid cell in the parameter distribution matrix is ​​tested to select the adjustable parameter range. Within the adjustable parameter range, based on the dynamic coupling relationship between braking pressure and temperature field, the parameters of adjacent units are iteratively weighted to generate an initial parameter sequence. Perform multiphysics joint verification on the initial parameter sequence to obtain the verified parameter sequence; Incremental update rules are generated based on the verified parameter sequence. Based on the incremental update rules and combined with the real-time pressure feedback data of the braking system, optimized braking pressure adjustment parameters are generated.

6. The modular train braking method according to claim 5, characterized in that, The step of performing multiphysics joint verification on the initial parameter sequence to obtain the verified parameter sequence includes: Based on the parameters corresponding to each grid cell in the initial parameter sequence, detect grid cells with heat conduction continuity index and stress field abrupt changes. The state of the mesh element with abrupt stress field changes is adjusted to the state corresponding to the parameters of the previous iteration, the adjustment step size is reduced, and the initial parameter sequence is adjusted according to the reduced adjustment step size to generate an intermediate parameter sequence. The intermediate parameter sequence is then verified by three consecutive iterations. Based on the validated intermediate parameter sequence, a validated post-parameter sequence covering all grid cells and satisfying multi-field equilibrium conditions is generated.

7. The modular train braking method according to claim 3, characterized in that, The calculation of the dynamic weight coefficients corresponding to the first tensor and the second tensor includes: Calculate the first initial weight and the second initial weight based on the spatial correlation of the brake disc; Based on the preset mechanical structure constraints of the brake disc, the first initial weight and the second initial weight are dynamically adjusted to generate the dynamic weight coefficients corresponding to the first tensor and the second tensor, respectively.

8. A modular train braking system, characterized in that, include: The acquisition module is used to acquire temperature distribution data of a target area on the train, wherein the target area is the area on the train where the brake disc surface is in contact with the pneumatic braking device. The extraction module is used to identify local hotspot areas whose temperatures exceed a preset safety range from the temperature distribution image corresponding to the temperature distribution data, and to extract the target geometric feature parameters of the local hotspot areas from the temperature distribution image; The generation module is used to generate the train's braking pressure adjustment parameters based on the target geometric feature parameters of the local hot spot area and the train's current operating status information, using a heat conduction model. An optimization module is used to optimize the brake pressure adjustment parameters to obtain optimized brake pressure adjustment parameters; The transmitting module is used to send the optimized braking pressure adjustment parameters to the pneumatic braking device in the modular train braking system, so that the pneumatic braking device applies dynamically changing braking force based on the optimized braking pressure adjustment parameters.

9. A computing device, characterized in that, It includes a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are invoked and executed by the processing component to implement a modular train braking method as described in any one of claims 1 to 7.

10. A computer storage medium, characterized in that, The system contains a computer program that, when executed by a computer, implements a modular train braking method as described in any one of claims 1 to 7.

Images