Energy consumption optimization method and system for marshaling railway freight equipment based on data fusion

Abstract

The present invention discloses a method and system for optimizing the energy consumption of marshaled railway freight equipment based on data fusion, relating to the field of rail transit technology. The system includes: a dynamic data acquisition module for acquiring real-time data during the operation of railway freight equipment; a core calculation module for calculating real-time parameters using a multi-coupling effect model to obtain the atmospheric drag energy consumption of the railway freight equipment; a data processing module, an edge computing layer for constructing a dynamic wind attack angle correction model based on the operating status of the railway freight equipment, and using the dynamic wind attack angle correction model to correct the atmospheric drag energy consumption calculation process; an intelligent analysis layer for optimizing the railway freight equipment's travel strategy based on the atmospheric drag energy consumption; and a feedback control module for providing real-time feedback and control of the railway freight equipment based on the optimized railway freight equipment's travel strategy. The present invention can achieve accurate modeling, optimization, and safe control of atmospheric drag energy consumption in a dynamic environment.

Description

Technical Field

[0001] The present invention relates to the field of rail transportation technology, and in particular to a method and system for optimizing energy consumption of marshaled railway freight equipment based on data fusion. Background Art

[0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art.

[0003] With the continued growth of railway freight volume, energy consumption in railway freight equipment is receiving increasing attention. Atmospheric drag is a major source of energy consumption during train operation, particularly at high speeds or over long distances. Accurately calculating atmospheric drag energy consumption in train formations can optimize energy utilization: rationally planning traction power configurations and reducing fuel or electricity consumption. It can also reduce transportation costs: energy savings directly translate into operational economics, which is particularly important for railway systems with high freight volumes. It can also support the application of new energy technologies: providing data support for battery capacity design in electric and hybrid freight cars.

[0004] Traditional calculations of atmospheric drag for railway freight equipment rely heavily on static models, failing to fully account for the impact of dynamic conditions (such as sudden changes in wind speed and direction), train formation synergy (such as the effect of wake turbulence from various types of freight cars on the atmospheric drag of following vehicles), and infrastructure coupling (such as transient wind pressure shock in tunnels). This results in insufficient energy-saving potential. Furthermore, static parameters lack real-time performance and are unable to adapt to dynamic wind fields and track curvature variations, leading to large errors in the calculation of atmospheric drag and energy consumption. Furthermore, existing technologies lack a quantitative mechanism for predicting the risk of derailment due to the combined effects of crosswinds and curved sections.

[0005] In summary, how to realize the real-time and accurate calculation of the atmospheric resistance energy consumption of railway freight equipment based on multiple influencing factors, and to perform risk prediction and improvement optimization based on the calculated energy consumption, has become a technical problem that needs to be solved urgently in existing technologies. Summary of the Invention

[0006] In view of the shortcomings of the existing technology, the purpose of the present invention is to provide a method and system for optimizing the energy consumption of railway freight equipment based on data fusion, which can realize the accurate modeling, optimization and safe control of atmospheric resistance energy consumption in a dynamic environment.

[0007] In order to achieve the above object, the present invention is implemented through the following technical solutions:

[0008] A first aspect of the present invention provides a system for optimizing energy consumption of marshaled railway freight equipment based on data fusion, comprising:

[0009] Dynamic data acquisition module, used to obtain real-time data during the operation of railway freight equipment;

[0010] The core calculation module is used to calculate real-time parameters using a multi-coupling effect model to obtain the atmospheric resistance energy consumption of railway freight equipment. The multi-coupling effect model is constructed based on the marshaling effect, wind direction effect, and tunnel effect.

[0011] The data processing module includes an edge computing layer and an intelligent analysis layer. The edge computing layer is used to build a dynamic wind angle correction model based on the operating status of railway freight equipment and use the dynamic wind angle correction model to correct the atmospheric resistance energy consumption calculation process. The intelligent analysis layer is used to optimize the railway freight equipment's travel strategy based on atmospheric resistance energy consumption.

[0012] The feedback control module is used to provide real-time feedback and control to the railway freight equipment according to the optimized railway freight equipment travel strategy.

[0013] Furthermore, in the core calculation module, the marshaling effect is the shielding effect of the wake of the leading vehicle on the following vehicle caused by the marshaling condition of the railway freight equipment, the wind direction effect is the atmospheric resistance change effect caused by the relative wind attack angle during the operation of the railway freight equipment, and the tunnel effect is the transient pressure wave resistance effect brought about by the tunnel environment.

[0014] Furthermore, the edge computing layer also includes calculating the equivalent synthetic wind speed by combining the vehicle speed, natural wind speed and direction, and tunnel ventilation parameters; the equivalent synthetic wind speed integrates the wind speed vector, vehicle heading angle, and track curvature to construct a dynamic wind attack angle correction model, which is used to correct the atmospheric resistance energy consumption calculation process by real-time correction of the atmospheric resistance coefficient.

[0015] Furthermore, the intelligent analysis layer also includes a safety warning layer, which is used to predict the probability of derailment risk based on the dynamic critical rollover coefficient algorithm, integrating the wind load spectrum, track curvature and vehicle center of mass offset; perform real-time anomaly detection, extract features of real-time atmospheric resistance energy consumption, and warn of abnormal operating conditions based on the comparison results of real-time atmospheric resistance energy consumption and dynamic thresholds.

[0016] Furthermore, it also includes a static database module, including a track GIS database and a vehicle characteristic database, which are used to store the track and vehicle static parameters of railway freight equipment.

[0017] Furthermore, it also includes an environmental perception and communication module, which uses distributed meteorological monitoring stations, tunnel entrance wind speed monitoring devices and track status monitoring sensors deployed along the line to obtain environmental perception information, and adopts 5G or LoRa hybrid networking to achieve low-latency data transmission.

[0018] Furthermore, the feedback control module provides the driver with real-time atmospheric resistance change trends and optimized railway freight equipment travel strategies through the environmental perception and communication module.

[0019] A second aspect of the present invention provides a method for optimizing energy consumption of marshaled railway freight equipment based on data fusion, comprising the following steps:

[0020] Obtain real-time data on the operation of railway freight equipment;

[0021] The multi-coupling effect model is used to calculate the real-time parameters and obtain the atmospheric resistance energy consumption of railway freight equipment. The multi-coupling effect model is constructed based on the marshaling effect, wind direction effect and tunnel effect.

[0022] A dynamic wind attack angle correction model is constructed based on the operating status of railway freight equipment, and the atmospheric resistance energy consumption calculation process is corrected using the dynamic wind attack angle correction model.

[0023] Optimize the travel strategy of railway freight equipment based on atmospheric resistance energy consumption;

[0024] Provide real-time feedback and control of railway freight equipment based on the optimized railway freight equipment travel strategy.

[0025] The third aspect of the present invention provides a medium having a program stored thereon, which, when executed by a processor, implements the steps of the method for optimizing energy consumption of marshaled railway freight equipment based on data fusion as described in the second aspect of the present invention.

[0026] The fourth aspect of the present invention provides a device comprising a memory, a processor, and a program stored in the memory and executable on the processor. When the processor executes the program, the steps in the method for optimizing energy consumption of marshaled railway freight equipment based on data fusion as described in the second aspect of the present invention are implemented.

[0027] One or more of the above technical solutions have the following beneficial effects:

[0028] The present invention discloses a method and system for optimizing energy consumption of marshaled railway freight equipment based on data fusion. It also proposes a new atmospheric resistance energy consumption calculation model that takes into account multiple influencing factors, such as the equipment's shape, size, marshaling method, operating speed, wind direction and speed. This model can more accurately reflect the atmospheric resistance energy consumption level of railway freight equipment in its marshaled state. It also constructs a dynamic wind angle correction model through edge computing, which is then corrected to obtain more accurate real-time atmospheric resistance energy consumption calculation results. Based on this real-time atmospheric resistance energy consumption calculation, railway freight companies can more scientifically formulate energy-saving and emission-reduction measures, reduce operating costs, and improve economic efficiency.

[0029] The present invention proposes a new evaluation model for the atmospheric drag energy consumption level, which combines fluid mechanics, multi-body dynamics and the actual operating characteristics of railway freight equipment. Based on this model, the atmospheric drag energy consumption level of railway freight equipment under various formation states can be evaluated more accurately, facilitating the optimization of the formation of railway freight cars.

[0030] Through efficient data collection and processing, this invention acquires real-time operational data and environmental parameters of railway freight equipment in its marshaled state. This data, including equipment speed, location, wind direction and speed, is efficiently processed and analyzed to accurately derive atmospheric drag energy consumption. Through real-time monitoring and feedback, this invention monitors the atmospheric drag energy consumption of railway freight equipment in real time and transmits this data to relevant personnel or systems, enabling timely optimization and adjustment measures.

[0031] Advantages of additional aspects of the present invention will be given in part in the following description and in part will be obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] The accompanying drawings, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0033] Figure 1 This is an architecture diagram of a system for optimizing energy consumption of marshaled railway freight equipment based on data fusion in Example 1 of the present invention;

[0034] Figure 2 Schematic diagram of a dynamic wind attack angle correction model in Embodiment 1 of the present invention;

[0035] Figure 3 This is a calculation flow chart of the multi-coupling effect model in Example 1 of the present invention;

[0036] Figure 4 This is a logic diagram of the dynamic critical rollover coefficient risk warning algorithm in Example 1 of the present invention. DETAILED DESCRIPTION

[0037] It should be noted that the following detailed descriptions are exemplary and intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which the present invention belongs.

[0038] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is intended to include the plural form. In addition, it should be understood that when the terms "comprise" and / or "include" are used in this specification, they indicate the presence of features, steps, operations, devices, components and / or their combinations;

[0039] Example 1:

[0040] The first embodiment of the present invention provides a system for optimizing energy consumption of railway freight equipment based on data fusion, such as Figure 1 Shown, including:

[0041] The dynamic data acquisition module is used to obtain real-time data during the operation of railway freight equipment, including environmental data, vehicle operation data and static parameters. In this embodiment, the railway freight equipment is a railway freight train.

[0042] The dynamic data acquisition module includes an integrated nine-axis IMU (collecting three-dimensional acceleration and angular velocity), a GNSS or INS integrated navigation module, a pressure sensor, a temperature sensor, and a wind speed and direction sensor array. The nine-axis IMU collects three-dimensional acceleration and angular velocity, the GNSS or INS integrated navigation module collects position information, the pressure sensor collects pressure information, the temperature sensor collects temperature information, and the wind speed and direction sensor array, installed at the front, rear, and roof of the vehicle, collects wind direction and speed information.

[0043] The core calculation module is used to calculate real-time parameters using a multi-coupling effect model to obtain the atmospheric resistance energy consumption of railway freight equipment.

[0044] This embodiment constructs a multi-coupling effect model based on the marshaling effect, wind direction effect, and tunnel effect. The marshaling effect is the shielding effect of the wake of the leading vehicle on the following vehicle caused by the marshaling conditions of the railway freight equipment. Taking into account the shielding effect of the wake of the leading vehicle on the following vehicle, an atmospheric drag reduction coefficient is introduced. The wind direction effect is the atmospheric drag variation effect caused by the relative wind angle during the operation of the railway freight equipment. The relative wind angle is calculated using the moving coordinate system method, and a lookup table for the atmospheric drag coefficient of mixed marshaling is established. The tunnel effect is the transient pressure wave drag effect caused by the tunnel environment. A pressure wave drag calculation model is established based on the theory of one-dimensional unsteady compressible flow.

[0045] Multi-coupling effect models such as Figure 3As shown, the input parameters include dynamic and static data. Dynamic data includes wind speed, wind direction, acceleration, vehicle speed, position, and heading angle. Static data includes vehicle length, vehicle spacing, marshaling parameters, route map, and tunnel parameters. Data preprocessing is first performed based on the input parameters. This includes real-time calculation of vehicle speed and on-track position, determination of tunnel entrance and exit markers, and calculation of tunnel blockage ratio. Next, calculations are performed for marshaling effect coupling, tunnel effect coupling, wind direction effect coupling, and nonlinear coupled energy consumption modeling. Finally, the real-time atmospheric drag value and the aerodynamic energy consumption of the marshaling are output.

[0046] In one specific embodiment, railway freight equipment operates in tunnels and outside tunnels on a line, and the atmospheric drag energy consumption differs in these two situations. Therefore, to study the atmospheric drag energy consumption during the operation of railway freight equipment under marshaling conditions, a multi-particle rigid-body dynamics model of railway freight equipment is first established, assuming the operating speed of the railway freight equipment is v. For ease of illustration, the first railway freight equipment in a railway freight train is designated as sequence 1, and each railway freight equipment is numbered sequentially in the reverse direction of travel. Railway freight equipment j is the railway freight equipment numbered j.

[0047] For group reduction coefficient Initially, this parameter data (library) can be obtained through wind tunnel testing combined with flow field simulation. Later, through collection and accumulation, atmospheric resistance energy consumption characteristic data (library) under different climate zones and different formation forms can be obtained, supporting artificial intelligence (AI) to make more intelligent formation reasoning decisions.

[0048] In this embodiment, since the railway freight cars use standard couplers, the distance between the vehicles in the railway freight car marshaling is generally fixed. It is used to quantify the effect of the wake of the preceding vehicle on reducing the aerodynamic drag of the vehicle. The calculation needs to integrate the influence of vehicle type combination, formation length, vehicle position and tail effect. The specific method for coupling calculation of formation effect is as follows:

[0049] (1).

[0050] in, is the marshaling reduction coefficient of a vehicle j, is the preceding vehicle baseline reduction coefficient, is the vehicle combination correction factor, is the group length correction factor, is the vehicle position attenuation factor, is the tail correction factor.

[0051] In this embodiment, the j-th car's formation reduction coefficient is determined by the above five parts. Specifically:

[0052] 1. The preceding vehicle's baseline reduction coefficient ( ): The inherent reduction capacity of the preceding vehicle j-1 can be obtained by wind tunnel test or CFD simulation. Typical values are: 0.25 for tank car, 0.35 for open car, 0.22 for flat car (standard container), and 0.30 for covered car.

[0053] 2. Vehicle combination correction factor ( ): reflects the synergistic effect of the front car-rear car combination, which can be obtained by wind tunnel test or CFD simulation. Typical values are: tank car → open car: 1.2, flat car → covered car: 0.9, open car → flat car: 0.7.

[0054] 3. Group length correction factor ( ): The attenuation of the total number of sections in the group on the wake superposition, f length = 1 -0.008(N-1), the minimum value is 0.4;

[0055] 4. Vehicle position attenuation factor ( ): The influence of vehicle position on wake energy. The further back the position is, the more energy the wake of the front vehicle will attenuate after passing through multiple vehicles. The calculation method is ;

[0056] 5. Tail correction factor ( ): The last vehicle has increased aerodynamic drag due to the tail vortex, which requires compensation for the reduction coefficient. When vehicle j is at the tail, the value is 0.85, and otherwise it is 1.0.

[0057] According to the above formula, it can be obtained that low-resistance vehicles (such as tank cars) should be arranged at the tail of long formations (N>30) to reduce And avoid using an open car as the rear vehicle to reduce eddy current resistance.

[0058] Considering the atmospheric resistance when the vehicle is running on track, the atmospheric resistance energy consumption of a single railway freight equipment j when running on track is:

[0059] (2).

[0060] Where: is the total atmospheric drag energy consumed by railway freight equipment j during operation on track, in J; is the basic atmospheric drag energy consumption of railway freight equipment j when running on track, unit is J; It is the additional atmospheric resistance energy consumed by railway freight equipment j when running in a tunnel, that is, the energy consumed only when running in a tunnel, with the unit being J. is the additional atmospheric drag energy consumption effectiveness coefficient, which takes the value of 1 when the railway freight equipment j is in the tunnel section after trajectory calculation, and 0 otherwise.

[0061] Considering all railway freight equipment on the freight train, the total atmospheric drag energy consumption of railway freight equipment under marshaling conditions when running on track is:

[0062] (3).

[0063] Where: is the total atmospheric resistance energy consumption of all railway freight equipment of a freight train during track operation at any time t, with the unit being J; ∑ represents the sum of the atmospheric resistance energy consumption of all railway freight equipment in a freight train, and n is the total number of railway freight equipment.

[0064] Considering the definition of particle velocity and resistance work, the basic atmospheric resistance energy consumption in formula (3) is and additional atmospheric resistance energy consumption in tunnels It can be further expressed as:

[0065] (4),

[0066] (5).

[0067] Where: is the basic atmospheric resistance of railway freight equipment j during operation, in N; is the additional atmospheric resistance of railway freight equipment j when running in a tunnel, in N. is the operating speed of railway freight equipment j.

[0068] For the calculation of basic atmospheric resistance of railway freight equipment during operation, the calculation formula of basic atmospheric resistance of tunnel railway freight equipment under marshaling conditions can be expressed as:

[0069] (6).

[0070] Where: is the relative wind angle; is the operating speed of railway freight equipment j; is the atmospheric density at the operating position of railway freight equipment j, in kg / m 3 ; is the marshaling reduction coefficient of the atmospheric running resistance of railway freight equipment j under marshaling conditions. This coefficient is related to the marshaling position of the vehicle and the preceding and following vehicle types, and can be obtained through wind tunnel testing combined with flow field simulation; is the atmospheric drag coefficient of railway freight equipment j, obtained through wind tunnel tests or flow field simulations; is the windward projection positive area of railway freight equipment j, in m 2 ; It is the natural wind speed in the atmosphere during operation, and the tunnel wind speed when in the tunnel, with the unit of m / s.

[0071] make It indicates the ratio of the natural wind speed of the atmosphere to the operating speed during operation. ,Right now Then formula (6) can be expressed as:

[0072] (7).

[0073] When railway freight equipment j is in a tunnel during operation, there is a temperature gradient inside the tunnel, considering the influence of geothermal heat. Therefore, it is necessary to first calculate the atmospheric density of the tunnel at its location:

[0074] (8).

[0075] Where: is the atmospheric density at the operating position of railway freight equipment j in the tunnel, in kg / m 3 ; is the initial atmospheric density; is the initial air pressure; is the air pressure at the operating position of railway freight equipment j in the tunnel, in Pa; is the temperature at the operating position of railway freight equipment j in the tunnel, in °C.

[0076] When calculating the basic atmospheric resistance during the operation of railway freight equipment, the natural wind speed calculation formula in the tunnel section is:

[0077] (9).

[0078] Where: The natural wind speed in the tunnel section; is the atmospheric density at the operating position of railway freight equipment j in the tunnel, in kg / m 3 ; is the air density at altitude h, where h is the altitude, in kg / m 3 ; It is the excess static pressure difference between tunnel portals, which can be calculated and measured by atmospheric pressure measuring instruments, and the unit is Pa; is the wind speed at the tunnel entrance, in m / s; is the height difference between the two openings, in meters; is the resistance coefficient along the tunnel; is the tunnel length in m; is the hydraulic diameter of the tunnel, in m; is the local resistance coefficient of the tunnel, is the acceleration due to gravity, take 9.81 m / s 2 .

[0079] The tunnel effect is coupled with the pressure wave resistance calculation model: when railway freight equipment j is in a tunnel section during operation, the additional resistance formula of the tunnel can be expressed as:

[0080] (10),

[0081] (11).

[0082] Where: Additional atmospheric drag for railway freight equipment when running in tunnels; is the operating speed of railway freight equipment j; is the calculation coefficient of the additional resistance of the tunnel; is the tunnel blocking ratio when the freight train passes through the sd-th tunnel; is the tunnel blocking ratio when the freight train passes through Liangfengya Tunnel; is the total length of the freight train in m; is the tunnel length of the additional resistance line of the sd-th tunnel section, in meters; is the distance between the ends of two adjacent freight equipment j and freight equipment j-1 under the marshaling condition, in meters; is the distance between the ends of two adjacent freight equipment j+1 and freight equipment j under the marshaling condition, in meters; and are the vehicle lengths of two adjacent freight equipment j+1 and freight equipment j under the marshalling conditions, respectively, in meters.

[0083] Considering the above formula, the total atmospheric drag energy consumption of railway freight equipment under marshaling conditions when running on track can be expressed as:

[0084] (12),

[0085] The above formula is the nonlinear coupling energy consumption model, which can be further expressed as:

[0086] (13).

[0087] The nonlinear coupled energy consumption model outputs the real-time atmospheric resistance value and the real-time aerodynamic energy consumption of the marshaling. Specifically, the real-time aerodynamic energy consumption of the marshaling is obtained according to formula (13), and the real-time aerodynamic resistance value of the marshaling is obtained by adding formula (7) and formula (10) and summing them for each vehicle.

[0088] The data processing module includes an edge computing layer and an intelligent analysis layer. The edge computing layer is used to build a dynamic wind angle correction model based on the operating status of railway freight equipment and use it to correct the atmospheric drag energy consumption calculation process. The intelligent analysis layer is used to optimize the railway freight equipment's travel strategy based on atmospheric drag energy consumption.

[0089] In the edge computing layer, the track curvature is inferred based on the lateral acceleration spectrum, and the equivalent synthetic wind speed is calculated by combining the vehicle speed, natural wind speed and direction, and tunnel ventilation parameters. The equivalent synthetic wind speed integrates the wind speed vector, vehicle heading angle, and track curvature to construct a dynamic wind attack angle correction model. The dynamic wind attack angle correction model is used to correct the atmospheric resistance energy consumption calculation process by real-time correction of the atmospheric resistance coefficient, such as Figure 2 As shown in the figure, the input parameters include the ambient wind direction angle, the heading angle of the leading vehicle, the vehicle length, the vehicle spacing, the front acceleration and the ambient wind speed. The calculations are performed in sequence through the vehicle heading angle calculation module, the dynamic angle of attack calculation module and the atmospheric drag coefficient correction module, and the effective wind attack angle and the corrected atmospheric drag coefficient are output.

[0090] The specific steps are as follows:

[0091] The edge computing layer includes a vehicle heading angle calculation module, a dynamic angle of attack calculation module, and an atmospheric drag coefficient correction module:

[0092] (1) The edge computing layer first calculates the speed and displacement.

[0093] In a specific embodiment, the railway freight equipment is usually not powered, and the data acquisition equipment is usually installed on the traction locomotive. For the calculation of atmospheric drag, the speed of the traction locomotive can be considered to be the same as the speed of the railway freight vehicle. Therefore, the acceleration in the forward direction is Perform integral calculation with compensation to obtain the running speed of the freight train.

[0094] (14).

[0095] is the velocity at the initial moment of integration, in m / s; is the acceleration due to gravity, take 9.81 m / s 2 ; is the slope of the track ramp during operation.

[0096] The above calculation formula always includes the calculation of the impact of the slope on the vehicle speed.

[0097] Because acceleration data is used in multiple places in this embodiment, an indirect method is used to calculate train speed. This involves integrating the acceleration signal acquired by the acceleration sensor to obtain the speed. In other implementations, various methods, such as direct acquisition by onboard equipment or detection by trackside equipment, can also be used to obtain the train's forward speed.

[0098] The position of each piece of freight equipment on the line must be considered when marshaling a railway freight train in order to calculate atmospheric drag at different locations under different environmental conditions. Taking the middle position between the two bogies of freight equipment numbered 1 as the starting point for recording the position of the freight equipment in the train, the position X1 of the first freight equipment on the track at time t can be obtained by integrating the velocity v, and the accumulated error is periodically corrected using GNSS absolute position (error less than 0.05%). The displacement calculation formula is as follows:

[0099] (15).

[0100] Except for the first railway freight equipment, the running positions of other freight equipment j (at this time, j ≥ 2) running on the track at time t can be expressed as:

[0101] (16).

[0102] Where: is the running position of railway freight equipment j on the track at time t, in m; n is the total number of railway freight equipment under the marshaling condition; is the distance between the ends of two adjacent freight equipment j and freight equipment j-1 under the marshaling condition, in meters; and are the vehicle lengths of two adjacent freight equipment j-1 and freight equipment j under the marshalling conditions, respectively, in meters.

[0103] (2) Secondly, the edge computing layer performs curve and line identification. Specifically, it performs dynamic verification with the design route map in real time. The route map dynamic verification includes trajectory matching and position matching. Trajectory matching refers to whether the displacement point calculated by formula (16) is consistent with the displacement point measured by the satellite GPS navigation module. Position matching refers to whether the track curve or line information calculated according to formula (17) is consistent with the information in the track design route map.

[0104] In a specific embodiment, the wind direction effect is coupled and calculated. , combined with the vehicle speed v and the current position superelevation angle Real-time reverse calculation of track curvature radius R:

[0105] (17).

[0106] Automatic identification of straight or curved sections is achieved by determining whether R is infinite (∞). The running trajectory in this embodiment includes straight lines, curves, and ramps. After the straight or curved sections of the sections are identified, the positioning is performed by fusing GPS and inertial navigation data through Kalman filtering. According to the speed calculation formula (14) including ramp calculation, and based on the displacement calculation formula (15), the digital trajectory of the vehicle and its position on the track line are generated.

[0107] (3) Finally, the edge computing layer models the relative angles of the windmills.

[0108] In a specific embodiment, based on the vehicle heading angle and ambient wind direction angle , calculate the relative wind angle :

[0109] (18).

[0110] Typically, the heading angle of the traction locomotive is calculated from the CNSS or INS output or the cumulative change in the starting position along the track line. The heading angle of each railway freight vehicle is calculated from the locomotive heading angle combined with the position of each vehicle on the track. In formula (18), the speed of each vehicle is the same, and the vector synthesis of vehicle speed and relative wind speed is considered.

[0111] (19).

[0112] Where, is the heading angle of the first railway freight car; is the heading angle of the j-th railway freight car. The vehicle heading angle is dynamically updated in real time according to the vehicle's running position.

[0113] (20).

[0114] Where, is the corrected atmospheric drag coefficient, is the atmospheric drag coefficient of vehicle j without correction; is the nonlinear fitting coefficient, which can be obtained by numerical simulation method (CFD). is the curvature-attack angle coupling coefficient, which is generally between 0.1 and 0.3 rad·m.

[0115] In the above calculation process, the vehicle heading angle calculation module is used to calculate formulas (14), (17) and (19), the dynamic angle of attack calculation module is used to calculate formula (18), and the atmospheric drag coefficient correction module is used to calculate formula (20).

[0116] The equivalent synthetic wind speed is then calculated by combining vehicle speed, natural wind speed and direction, and tunnel ventilation parameters. By integrating the wind speed vector, vehicle heading angle, and track curvature, a dynamic wind attack angle correction model can be constructed to correct the atmospheric drag coefficient in real time.

[0117] The dynamic wind attack angle correction model of this embodiment corrects the atmospheric drag coefficient in real time by fusing the wind speed vector, vehicle heading angle and track curvature, with an error rate of less than 5%.

[0118] The intelligent analysis layer calculates atmospheric resistance through the marshaling-tunnel-wind direction coupling model and generates energy consumption optimization and safety warning strategies.

[0119] In one specific implementation, a case library of atmospheric drag characteristics in different climate zones and different train formations is accumulated to support case-based AI reasoning and decision-making. A reasonable train formation sequence for each railway freight equipment is recommended to minimize the atmospheric drag energy consumption during operation. The reasoning of the core energy consumption optimization algorithm is as follows:

[0120] Through the atmospheric resistance and energy consumption algorithm running in the core computing module, it can be obtained that the atmospheric resistance and energy consumption of railway freight equipment have nothing to do with the transport load, but are only related to the vehicle shape, size, aerodynamic performance, and formation sequence.

[0121] Under the same energy consumption, the shorter the transportation time and the longer the transportation distance (i.e., the vehicle running speed), the higher the atmospheric drag energy efficiency of railway freight equipment under the marshaling. Considering that eliminating the speed term helps to converge the diffusion effect of energy efficiency values, the atmospheric drag energy efficiency is The following definitions are given:

[0122] (twenty one).

[0123] Normally, the atmospheric drag operating efficiency of railway freight equipment under marshaling is compared at the same speed and the same time, i.e. is a constant term, then formula (21) can be further expressed as:

[0124] (twenty two).

[0125] Where, For the railway freight equipment under marshaling at the running speed The atmospheric resistance operating energy efficiency per unit time.

[0126] From formula (22), we can see that under the marshaling, the railway freight equipment is running at a speed of Atmospheric resistance energy efficiency per unit time There must be a minimum value. Its minimum value is mainly determined by formula (23):

[0127] (twenty three).

[0128] That is, under the same operating environment, mixed formations of different types of vehicles will result in a reduction coefficient of formation. Different values can produce the optimal vehicle formation. That is:

[0129] (twenty four).

[0130] in, It is the minimum value of atmospheric resistance energy efficiency.

[0131] In addition, a reinforcement learning algorithm is used to dynamically plan the optimal vehicle speed. For example, in strong wind sections, the vehicle speed is reduced to reduce atmospheric resistance, and after passing the strong wind section, the vehicle speed is increased to achieve energy and consumption reduction.

[0132] Establish an energy-saving driving strategy based on model predictive control (MPC), use current environmental data to generate the optimal speed curve under the future 3-5 km route conditions, and balance the real-time atmospheric resistance energy consumption and operating efficiency.

[0133] When trains are in formation, airflow between vehicles interferes with each other (e.g., due to front streamlines, gaps between vehicles, and tail vortices), affecting overall drag. This can be improved in the following areas: Improve the vehicle's exterior: Design a more streamlined front and reduce surface irregularities. Optimize the formation: Adjust vehicle spacing, close gaps, or adopt a linked design to reduce turbulence. Apply new materials: Select lightweight or low-drag materials to reduce energy consumption.

[0134] Because atmospheric drag is proportional to the square of speed, higher speeds result in more significant drag energy consumption. Analyzing drag characteristics under marshaling conditions can determine the economic speed range and find the optimal balance between energy consumption and transport efficiency. This can support speed-increasing research and provide a theoretical basis for the feasibility of high-speed freight trains. It can also serve as a reference for dynamic scheduling, optimizing train schedules based on drag characteristics and reducing peaks and valleys in energy consumption.

[0135] The optimized marshaling scheme in this embodiment is flexible and adaptable. It selects the optimal marshaling scheme based on the significant differences in aerodynamic characteristics between cargo types (e.g., containers, bulk cargo) and marshaling lengths (short and long). It also optimizes the efficiency of connecting rail with other modes of transportation (e.g., sea and road).

[0136] The intelligent analysis layer also includes a safety warning layer, which is used to predict the probability of derailment risk based on the dynamic critical rollover coefficient algorithm, integrating the wind load spectrum, track curvature and vehicle center of mass offset; perform real-time anomaly detection, extract features of real-time atmospheric resistance energy consumption, and warn of abnormal operating conditions based on the comparison results of real-time atmospheric resistance energy consumption and dynamic thresholds.

[0137] In a specific embodiment, based on the dynamic critical overturning coefficient (DCOT) algorithm, the wind load spectrum, track curvature and vehicle center of mass are integrated to predict the derailment risk probability and trigger a three-level braking response, such as Figure 4 As shown, the input parameters include real-time and static data. Real-time data includes wind speed, wind direction, acceleration, vehicle speed, position, and heading angle. Static data includes vehicle dimensions and weight, center of gravity height, track spacing, and wheel-rail friction coefficient. Data preprocessing is performed based on the input parameters, including real-time calculation of the vehicle's dynamic wind attack angle, vehicle lateral frontal area, vehicle dynamic lateral wind load, and track curve radius R. Dynamic overturning moment, anti-overturning moment, and dynamic critical overturning coefficient (DCOT) are then calculated. Finally, risk level determination and graded control output are performed. Risk level determination thresholds are set. A DCOT ≤ 0.8 is considered a Level 1 risk, and continuous early warning monitoring is initiated. A DCOT value of 0.8 < 1.2 is considered a Level 2 risk, and the train is braked and coasted. A DCOT value of 1.2 ≤ 1.2 is considered a Level 3 risk, and the train is emergency braked.

[0138] More specifically, the formula for calculating the dynamic overturning moment is:

[0139] .

[0140] in, is the dynamic overturning moment, is the weight of the vehicle, is the height of the vehicle's center of gravity, is the dynamic lateral wind load on the vehicle.

[0141] The formula for calculating the anti-overturning moment is:

[0142] .

[0143] in, For the anti-overturning moment, is the wheel-rail friction coefficient, is the distance between the two tracks.

[0144] The calculation formula of dynamic critical overturning coefficient (DCOT index) is:

[0145] .

[0146] in, is the dynamic critical overturning coefficient.

[0147] Real-time anomaly detection extracts features from atmospheric drag time-series data and sets dynamic thresholds to warn of abnormal operating conditions. When the risk threshold is exceeded, a graded braking command is triggered within 0.5 seconds. The atmospheric drag time-series data is historical data for all operating moments.

[0148] Atmospheric drag not only affects energy consumption but is also closely related to the dynamic stability of train operations. This example assesses derailment risk by calculating the aerodynamic loads on a train set in strong winds. Tunnel effects are simulated to predict the impact of air pressure fluctuations within the tunnel on the train and tunnel structure. Train set stability is also verified to prevent aerodynamic interference that could cause car body sway or fatigue in connected components.

[0149] The feedback control module provides real-time feedback and control of the railway freight equipment based on the optimized equipment travel strategy, adjusting vehicle speed and train spacing in real time and triggering graded braking commands. Through the environmental perception and communication module, the feedback control module provides the driver with real-time atmospheric resistance trends and the optimized equipment travel strategy, dynamically smoothing out energy consumption fluctuations.

[0150] The feedback control module is also used to provide a visual interface to display the vehicle's real-time position, wind field distribution, atmospheric resistance, energy consumption curve, energy consumption heat map and risk warning information.

[0151] The static database module, consisting of a track GIS database and a vehicle characteristics database, stores the static track and vehicle parameters of railway freight equipment. The track GIS database contains data such as slope, curve radius, and tunnel parameters, while the vehicle characteristics database contains aerodynamic parameters such as length, windward area, and atmospheric drag coefficient, as well as train configuration parameters such as vehicle spacing and atmospheric drag reduction coefficient.

[0152] The environmental perception and communication module uses distributed meteorological monitoring stations, tunnel entrance wind speed monitoring devices and track status monitoring sensors deployed along the line to obtain environmental perception information, and adopts 5G or LoRa hybrid networking to achieve low-latency data transmission.

[0153] The infrastructure optimization module is used to reverse-engineer route and vehicle design based on historical data. It includes a data mining layer and a reverse design layer.

[0154] The data mining layer generates a digital profile of the line's atmospheric characteristics based on historical operating data, identifying high-resistance bottlenecks, such as specific tunnel-curve combinations. By comparing the calculated curve radius in real time with the design value and employing a self-correction mechanism for the line diagram, a database of track geometry deviation corrections is constructed. The reverse design layer guides tunnel cross-section optimization (e.g., increasing the cross-sectional area by 10%-15% to reduce transient wind pressure shock). Optimizing track curvature design reduces peak atmospheric resistance by 20%-30%.

[0155] This system is adaptable to various types of freight trains and is suitable for diverse geographical environments (e.g., plateaus, coastal areas, and deserts). It can design adaptive train formations for varying climates and terrain conditions. It can also be used to assess the operational reliability of trains in cold or hot regions.

[0156] This embodiment provides a system operation process:

[0157] 1. The dynamic data acquisition module collects raw signals at a frequency of 100 Hz and generates 1-second feature vectors after preprocessing by the edge node.

[0158] 2. The core algorithm module updates the atmospheric resistance parameters every 5 seconds and predicts the resistance changes in the next 30 seconds based on the route conditions.

[0159] 3. The intelligent analysis layer generates energy consumption assessment reports every minute and energy saving potential analysis for every 10 kilometers of travel.

[0160] 4. Control commands are transmitted via a dedicated railway 5G network, with end-to-end latency kept to less than 50ms.

[0161] The present invention discloses a real-time collaborative optimization system and method for atmospheric resistance energy consumption in railway freight trains. Through multi-dimensional data fusion and edge intelligent computing, it realizes coupled modeling of dynamic wind field-training effect-tunnel effect, solving the problems of insufficient accuracy and poor real-time performance of traditional models. The system has millisecond-level energy consumption optimization and safety warning capabilities, promoting the upgrade of railway freight to green and intelligent. Through the combination of multi-source information fusion, physical models and data-driven methods, the system realizes accurate perception and dynamic optimization of atmospheric resistance in complex operating environments, providing a closed-loop intelligent solution for railway freight energy efficiency management.

[0162] Example 2:

[0163] A second embodiment of the present invention provides a method for optimizing energy consumption of marshaled railway freight equipment based on data fusion, comprising the following steps:

[0164] Obtain real-time data on the operation of railway freight equipment.

[0165] The real-time parameters are calculated using a multi-coupling effect model to obtain the atmospheric resistance energy consumption of railway freight equipment. The multi-coupling effect model is constructed based on the marshalling effect, wind direction effect and tunnel effect.

[0166] A dynamic wind attack angle correction model is constructed according to the operating status of railway freight equipment, and the atmospheric resistance energy consumption calculation process is corrected using the dynamic wind attack angle correction model.

[0167] The travel strategy of railway freight equipment is optimized according to the energy consumption of atmospheric resistance.

[0168] Provide real-time feedback and control of railway freight equipment based on the optimized railway freight equipment travel strategy.

[0169] Example 3:

[0170] A third embodiment of the present invention provides a medium having a program stored thereon. When the program is executed by a processor, the steps of the method for optimizing energy consumption of marshaled railway freight equipment based on data fusion as described in the second embodiment of the present invention are implemented.

[0171] Example 4:

[0172] Embodiment 4 of the present invention provides a device, including a memory, a processor, and a program stored in the memory and executable on the processor. When the processor executes the program, the steps in the method for optimizing energy consumption of marshaled railway freight equipment based on data fusion as described in Embodiment 2 of the present invention are implemented.

[0173] The steps involved in the above embodiments 2, 3 and 4 correspond to those in embodiment 1. For the specific implementation methods, please refer to the relevant description part of embodiment 1.

[0174] Those skilled in the art will appreciate that the modules or steps of the present invention described above can be implemented using a general-purpose computer device. Alternatively, they can be implemented using program code executable by a computing device, which can then be stored in a storage device and executed by the computing device. Alternatively, they can be fabricated into separate integrated circuit modules, or multiple modules or steps can be fabricated into a single integrated circuit module for implementation. The present invention is not limited to any specific combination of hardware and software.

[0175] Although the above describes the specific embodiments of the present invention in conjunction with the accompanying drawings, it is not intended to limit the scope of protection of the present invention. Those skilled in the art should understand that various modifications or variations that can be made by those skilled in the art on the basis of the technical solution of the present invention without any creative work are still within the scope of protection of the present invention.

Claims

1. A system for optimizing energy consumption of railway freight equipment based on data fusion, characterized in that: include: Dynamic data acquisition module, used to obtain real-time data during the operation of railway freight equipment; The core calculation module is used to calculate real-time parameters using a multi-coupling effect model to obtain the atmospheric resistance energy consumption of railway freight equipment. The multi-coupling effect model is constructed based on the marshaling effect, wind direction effect, and tunnel effect. Among them, the multi-coupling effect model is used to calculate the real-time parameters to obtain the atmospheric resistance energy consumption of railway freight equipment, specifically: Data preprocessing is performed based on input parameters, including real-time calculation of vehicle running speed, real-time calculation of vehicle on-track position, determination of tunnel entrance and exit markers, and calculation of tunnel blockage ratio. This is followed by calculation of marshaling effect coupling, tunnel effect coupling, wind direction effect coupling, and nonlinear coupling energy consumption model, outputting the real-time atmospheric resistance value and aerodynamic energy consumption of the marshaling. Input parameters include dynamic and static data. Dynamic data includes wind speed, wind direction, acceleration, vehicle speed, position, and heading angle; static data includes vehicle length, vehicle spacing, marshaling parameters, route map, and tunnel parameters. Among them, the real-time aerodynamic energy consumption of the formation is obtained according to the nonlinear coupling energy consumption model: in, Real-time aerodynamic energy consumption for marshaling; is the atmospheric density at the operating location of railway freight equipment j; is the marshaling reduction coefficient of the atmospheric running resistance of railway freight equipment j under marshaling conditions. This coefficient is related to the marshaling position of the vehicle and the preceding and following vehicle types, and is obtained through wind tunnel testing combined with flow field simulation; is the atmospheric drag coefficient of railway freight equipment j, obtained through wind tunnel tests or flow field simulations; is the windward projection positive area of railway freight equipment j; It represents the ratio of the natural wind speed of the atmosphere to the operating speed during operation, that is, , The speed of the natural wind in the atmosphere during operation, and the speed of the tunnel wind in the tunnel. is the operating speed of railway freight equipment j; is the relative wind angle; is the additional atmospheric drag energy consumption coefficient, which takes the value of 1 when the railway freight equipment j is in the tunnel section after trajectory calculation, and 0 otherwise; is the calculation coefficient of the additional resistance of the tunnel; The data processing module includes an edge computing layer and an intelligent analysis layer. The edge computing layer is used to build a dynamic wind angle correction model based on the operating status of railway freight equipment, and use the dynamic wind angle correction model to correct the atmospheric resistance energy consumption calculation process; Among them, the dynamic wind attack angle correction model is used to correct the atmospheric resistance energy consumption calculation process, specifically: Input the ambient wind direction angle, leading vehicle heading angle, vehicle length, vehicle spacing, vehicle head acceleration, and ambient wind speed parameters. Calculate through the vehicle heading angle calculation module, dynamic angle of attack calculation module, and atmospheric drag coefficient correction module to output the effective wind attack angle and the corrected atmospheric drag coefficient. Among them, the corrected atmospheric drag coefficient is obtained according to the atmospheric drag coefficient correction module: in, is the corrected atmospheric drag coefficient, is the atmospheric drag coefficient of vehicle j without correction; is the nonlinear fitting coefficient, obtained by numerical simulation method; is the curvature-angle of attack coupling coefficient; is the relative wind angle; is the track curvature radius; The intelligent analysis layer is used to optimize the travel strategy of railway freight equipment based on atmospheric resistance energy consumption; The feedback control module is used to provide real-time feedback and control to the railway freight equipment according to the optimized railway freight equipment travel strategy.

2. The energy consumption optimization system for railway freight equipment based on data fusion according to claim 1, characterized in that: In the core calculation module, the marshaling effect refers to the shielding effect of the wake of the leading vehicle on the following vehicle caused by the marshaling conditions of the railway freight equipment; the wind direction effect refers to the change effect of atmospheric resistance caused by the relative wind attack angle during the operation of the railway freight equipment; and the tunnel effect refers to the transient pressure wave resistance effect brought about by the tunnel environment.

3. The energy consumption optimization system for railway freight equipment based on data fusion according to claim 1, characterized in that: The edge computing layer also includes calculating the equivalent synthetic wind speed by combining vehicle speed, natural wind speed and direction, and tunnel ventilation parameters; The equivalent synthetic wind speed integrates the wind speed vector, vehicle heading angle and track curvature to construct a dynamic wind angle correction model. The dynamic wind angle correction model is used to correct the atmospheric drag energy consumption calculation process by correcting the atmospheric drag coefficient in real time.

4. The energy consumption optimization system for railway freight equipment based on data fusion according to claim 1, characterized in that: The intelligent analysis layer also includes a safety warning layer, which is used to predict the probability of derailment risk based on a dynamic critical rollover coefficient algorithm, integrating wind load spectrum, track curvature and vehicle center of mass offset; Perform anomaly detection in real time, extract features of real-time atmospheric resistance energy consumption, and warn of abnormal operating conditions based on the comparison results between real-time atmospheric resistance energy consumption and dynamic thresholds.

5. The energy consumption optimization system for railway freight equipment based on data fusion according to claim 1, characterized in that: It also includes a static database module, including a track GIS database and a vehicle characteristic database, which are used to store the track and vehicle static parameters of railway freight equipment.

6. The energy consumption optimization system for railway freight equipment based on data fusion according to claim 1, characterized in that: It also includes an environmental perception and communication module, which uses distributed meteorological monitoring stations, tunnel entrance wind speed monitoring devices and track status monitoring sensors deployed along the line to obtain environmental perception information, and adopts 5G or LoRa hybrid networking to achieve low-latency data transmission.

7. The energy consumption optimization system for railway freight equipment based on data fusion according to claim 6, characterized in that: The feedback control module provides the driver with real-time atmospheric resistance change trends and optimized railway freight equipment travel strategies through the environmental perception and communication module.

8. A method for optimizing energy consumption of railway freight equipment based on data fusion, characterized in that: The following steps are involved: Obtain real-time data on the operation of railway freight equipment; The multi-coupling effect model is used to calculate the real-time parameters and obtain the atmospheric resistance energy consumption of railway freight equipment. The multi-coupling effect model is constructed based on the marshaling effect, wind direction effect and tunnel effect. Among them, the multi-coupling effect model is used to calculate the real-time parameters to obtain the atmospheric resistance energy consumption of railway freight equipment, specifically: Data preprocessing is performed based on input parameters, including real-time calculation of vehicle running speed, real-time calculation of vehicle on-track position, determination of tunnel entrance and exit markers, and calculation of tunnel blockage ratio. This is followed by calculation of marshaling effect coupling, tunnel effect coupling, wind direction effect coupling, and nonlinear coupling energy consumption model, outputting the real-time atmospheric resistance value and aerodynamic energy consumption of the marshaling. Input parameters include dynamic and static data. Dynamic data includes wind speed, wind direction, acceleration, vehicle speed, position, and heading angle; static data includes vehicle length, vehicle spacing, marshaling parameters, route map, and tunnel parameters. Among them, the real-time aerodynamic energy consumption of the formation is obtained according to the nonlinear coupling energy consumption model: in, Real-time aerodynamic energy consumption for marshaling; is the atmospheric density at the operating location of railway freight equipment j; is the marshaling reduction coefficient of the atmospheric running resistance of railway freight equipment j under marshaling conditions. This coefficient is related to the marshaling position of the vehicle and the preceding and following vehicle types, and is obtained through wind tunnel testing combined with flow field simulation; is the atmospheric drag coefficient of railway freight equipment j, obtained through wind tunnel tests or flow field simulations; is the windward projection positive area of railway freight equipment j; It represents the ratio of the natural wind speed of the atmosphere to the operating speed during operation, that is, , The speed of the natural wind in the atmosphere during operation, and the speed of the tunnel wind in the tunnel. is the operating speed of railway freight equipment j; is the relative wind angle; is the additional atmospheric drag energy consumption coefficient, which takes the value of 1 when the railway freight equipment j is in the tunnel section after trajectory calculation, and 0 otherwise; is the calculation coefficient of the additional resistance of the tunnel; A dynamic wind attack angle correction model is constructed based on the operating status of railway freight equipment, and the atmospheric resistance energy consumption calculation process is corrected using the dynamic wind attack angle correction model. Among them, the dynamic wind attack angle correction model is used to correct the atmospheric resistance energy consumption calculation process, specifically: Input the ambient wind direction angle, leading vehicle heading angle, vehicle length, vehicle spacing, vehicle head acceleration, and ambient wind speed parameters. Calculate through the vehicle heading angle calculation module, dynamic angle of attack calculation module, and atmospheric drag coefficient correction module to output the effective wind attack angle and the corrected atmospheric drag coefficient. Among them, the corrected atmospheric drag coefficient is obtained according to the atmospheric drag coefficient correction module: in, is the corrected atmospheric drag coefficient, is the atmospheric drag coefficient of vehicle j without correction; is the nonlinear fitting coefficient, obtained by numerical simulation method; is the curvature-angle of attack coupling coefficient; is the relative wind angle; is the track curvature radius; Optimize the travel strategy of railway freight equipment based on atmospheric resistance energy consumption; Provide real-time feedback and control of railway freight equipment based on the optimized railway freight equipment travel strategy.

9. A computer-readable storage medium, characterized in that A plurality of instructions are stored therein, and the instructions are suitable for being loaded and executed by a processor of a terminal device, for the method for optimizing energy consumption of marshaled railway freight equipment based on data fusion as claimed in claim 8.

10. A terminal device, characterized in that: The method comprises a processor and a computer-readable storage medium, wherein the processor is used to implement various instructions; the computer-readable storage medium is used to store multiple instructions, wherein the instructions are suitable for being loaded by the processor and executed by the method for optimizing energy consumption of railway freight equipment based on data fusion according to claim 8.

Images