Multi-parameter automatic optimization method and device based on ATO single-vehicle energy consumption model

Abstract

The invention relates to a multi-parameter automatic optimization method and device based on an ATO single-vehicle energy consumption model, and the method comprises the steps: building an ATO single-vehicle energy consumption model based on basic resistance, ramp additional resistance and a plurality of energy-saving parameters in the operation process of a target train; optimizing a range corresponding to each energy-saving parameter in the plurality of energy-saving parameters to generate at least one energy-saving parameter refinement range meeting a preset vehicle control requirement; and performing global optimization operation on the ATO single-vehicle energy consumption model iteration, acquiring the acquisition points of each energy-saving parameter refining range and probability distribution corresponding to all historical acquisition points in each iteration process, and obtaining an energy-saving parameter combination meeting a preset energy-saving requirement in combination with an acquisition function and an iteration termination condition. According to the method, the energy-saving parameter range is obtained by constructing the ATO single-vehicle energy consumption model and combining the parameter preprocessing operation, and the energy-saving parameters are optimized by adopting the global optimization method, so that the calculation cost is effectively reduced under the condition of ensuring the energy-saving effect.

Description

Technical Field

[0001] The present application relates to the field of ATO energy-saving technology, and in particular to a multi-parameter automatic optimization method and device based on an ATO single-vehicle energy consumption model. Background Art

[0002] At present, the core of the ATO energy-saving algorithm is to maximize the slope, curve and other line conditions, increase the idling condition, reduce unnecessary traction and braking conditions, and minimize traction energy consumption while meeting operational requirements. Specifically, ATO energy saving is mainly achieved in the following two ways:

[0003] (1) Method based on offline optimal vehicle control curve calculation: This method uses algorithms such as reinforcement learning to offline calculate the vehicle control curve with the lowest current energy consumption for a specific line and vehicle, and stores it in the train. When the train enters a specific working condition or section, the corresponding driving curve is executed.

[0004] (2) Method based on real-time vehicle control curve optimization: This method uses the line information ahead obtained by ATO to calculate the subsequent driving curve that meets energy-saving requirements in real time according to a specific algorithm, and directly controls the vehicle.

[0005] The method based on offline optimal energy-saving curve calculation is difficult to adapt to the changing operation and weather conditions. Slight changes in vehicles or lines may cause the optimal energy-saving curve to shift, and the robustness is poor. In addition, after the energy-saving effect shifts, this method cannot be debugged by on-site personnel (the entire vehicle control curve is stored and cannot be modified);

[0006] The method based on real-time vehicle control curve optimization is limited by the computing power of the vehicle system. Only relatively simple optimization methods can be used, and only the situation of a certain distance ahead can be focused on. It is difficult to achieve the global optimal energy-saving effect (the energy-saving effect is not ideal).

[0007] In summary, the existing ATO energy-saving technology is prone to optimal energy-saving curve deviation, which makes the energy-saving algorithm too generalized and cannot be debugged by on-site personnel, making it difficult to achieve the global optimal energy-saving effect, which needs to be solved urgently. Summary of the invention

[0008] The present application provides a multi-parameter automatic optimization method and device based on the ATO single-vehicle energy consumption model to solve the problems that the existing ATO energy-saving technology is prone to optimal energy-saving curve deviation, resulting in poor generalization of the energy-saving algorithm, inability to be debugged by on-site personnel, and difficulty in achieving the global optimal energy-saving effect.

[0009] The first aspect of the present application provides a multi-parameter automatic optimization method based on an ATO single-vehicle energy consumption model, comprising the following steps: obtaining the basic resistance, ramp additional resistance and curve additional resistance during the operation of a target train, and constructing an ATO single-vehicle energy consumption model based on the basic resistance, the ramp additional resistance, the curve additional resistance and a plurality of preset energy-saving parameters; optimizing the range corresponding to each of the multiple energy-saving parameters through a preset control variable optimization strategy to generate at least one energy-saving parameter refinement range corresponding to each energy-saving parameter that meets the preset vehicle control requirements; iteratively performing a global optimization operation on the ATO single-vehicle energy consumption model, and obtaining the probability distribution corresponding to the collection points of each energy-saving parameter refinement range and all historical collection points in the at least one energy-saving parameter refinement range in each iteration of the global optimization operation, so as to obtain an energy-saving parameter combination that meets the preset energy-saving requirements based on the probability distribution, the preset collection function and the preset iteration termination condition.

[0010] According to the above-mentioned technical means, the embodiment of the present application constructs an ATO single-vehicle energy consumption model and combines it with parameter preprocessing operations to obtain the energy-saving parameter range, and uses a global optimization method to optimize the energy-saving parameters, thereby effectively reducing the computing cost while ensuring the energy-saving effect, which is beneficial to subsequent on-site debugging and software iteration.

[0011] Optionally, in one embodiment of the present application, constructing an ATO single-vehicle energy consumption model based on the basic resistance, the ramp additional resistance, the curve additional resistance and preset multiple energy-saving parameters includes: obtaining line data, vehicle characteristic data and the multiple energy-saving parameters during the operation of the target train, so as to calculate the acceleration of the target train according to the line data, the vehicle characteristic data and the multiple energy-saving parameters; calculating the traction force of the target train based on the basic resistance, the ramp additional resistance, the curve additional resistance and the acceleration; obtaining the traction energy consumption of the entire line through the traction force, so as to construct the ATO single-vehicle energy consumption model according to the traction energy consumption of the entire line and the multiple energy-saving parameters.

[0012] According to the above technical means, the embodiment of the present application comprehensively considers the basic resistance, additional resistance on ramps and additional resistance on curves to construct a relatively complete ATO energy consumption model, thereby fully considering the line information, vehicle information, ATO configuration information, etc. of the entire line, greatly improving the simulation effect of the real scene.

[0013] Optionally, in one embodiment of the present application, the range corresponding to each energy-saving parameter in the multiple energy-saving parameters is optimized by a preset control variable optimization strategy to generate at least one energy-saving parameter refinement range corresponding to each energy-saving parameter that meets the preset vehicle control requirements, including: grid searching the range corresponding to each energy-saving parameter by the control variable optimization strategy to obtain multiple equally spaced sampling points of each energy-saving parameter; obtaining multiple pairs of adjacent sampling points in the multiple equally spaced sampling points, and establishing an energy-saving parameter range to be optimized corresponding to each pair of adjacent sampling points in the multiple pairs of adjacent sampling points; judging whether each pair of adjacent sampling points meets the preset vehicle control requirements, if any pair of adjacent sampling points does not meet the preset vehicle control requirements, deleting the energy-saving parameter range to be optimized composed of the any pair of adjacent sampling points, otherwise generating an energy-saving parameter refinement range corresponding to the any pair of adjacent sampling points.

[0014] According to the above technical means, the embodiment of the present application pre-processes the energy-saving parameter range through an equally spaced grid search, and generates a refined range of energy-saving parameters corresponding to each energy-saving parameter that meets the preset vehicle control requirements, thereby effectively reducing the computational overhead of subsequent global optimization and other operations.

[0015] Optionally, in one embodiment of the present application, the ATO single-vehicle energy consumption model is iteratively subjected to a global optimization operation, and during each iteration of the global optimization operation, the collection points of each energy-saving parameter refinement range and the probability distribution corresponding to all historical collection points in the at least one energy-saving parameter refinement range are obtained, so as to obtain an energy-saving parameter combination that meets the preset energy-saving requirements based on the probability distribution, a preset collection function and a preset iteration termination condition, including: determining the objective function of the ATO single-vehicle energy consumption model, and obtaining the parameter adjustment history based on all the historical collection points; establishing a probabilistic proxy model based on the parameter adjustment history and a preset estimator, so as to fit the objective function and the at least one energy-saving parameter constructed by the probabilistic proxy model. The corresponding relationship of the one-dimensional vector of the energy-saving parameter; obtaining the target evaluation point corresponding to each energy-saving parameter through a preset acquisition function, and determining the objective function corresponding to the target evaluation point through the corresponding relationship and the target evaluation point; judging whether the target evaluation point and the objective function corresponding to the target evaluation point meet the preset iteration termination condition; if the target evaluation point and the objective function corresponding to the target evaluation point do not meet the preset iteration termination condition, continuing to perform the global optimization operation according to the target evaluation point; if the target evaluation point and the objective function corresponding to the target evaluation point meet the preset iteration termination condition, terminating the global optimization operation, and obtaining the energy-saving parameter combination that meets the preset energy-saving requirement.

[0016] According to the above technical means, the embodiment of the present application further improves the model solving efficiency by optimizing the ATO energy-saving parameters and determining the next target parameter combination position based on the probability distribution of prior knowledge, thereby greatly reducing the training time while ensuring the optimization effect.

[0017] Optionally, in one embodiment of the present application, the mathematical expression of the traction energy consumption of the entire line is:

[0018]

[0019] Among them, inf_energy is the multiple energy-saving parameters that can be configured by ATO.

[0020] According to the above technical means, the embodiment of the present application constructs an ATO single-vehicle energy consumption model through a specific energy consumption model calculation method, with energy-saving parameters as independent variables and the energy consumption of single vehicles on the entire line as dependent variables, thereby reflecting the impact of energy-saving parameter adjustments on the energy consumption of the current train on the entire line.

[0021] The second aspect of the present application provides a multi-parameter automatic optimization device based on an ATO single-vehicle energy consumption model, including: a construction module, used to obtain the basic resistance, ramp additional resistance and curve additional resistance during the operation of a target train, and construct the ATO single-vehicle energy consumption model based on the basic resistance, the ramp additional resistance, the curve additional resistance and a plurality of preset energy-saving parameters; a generation module, used to optimize the range corresponding to each of the multiple energy-saving parameters through a preset control variable optimization strategy, so as to generate at least one energy-saving parameter refinement range corresponding to each energy-saving parameter that meets the preset vehicle control requirements; an optimization module, used to iteratively perform a global optimization operation on the ATO single-vehicle energy consumption model, and obtain the probability distribution corresponding to the collection point of each energy-saving parameter refinement range and all historical collection points in the at least one energy-saving parameter refinement range in each iteration of the global optimization operation, so as to obtain an energy-saving parameter combination that meets the preset energy-saving requirements based on the probability distribution, the preset collection function and the preset iteration termination condition.

[0022] Optionally, in one embodiment of the present application, the construction module includes: a first calculation unit, used to obtain the line data, vehicle characteristic data and the multiple energy-saving parameters during the operation of the target train, so as to calculate the acceleration of the target train based on the line data, the vehicle characteristic data and the multiple energy-saving parameters; a second calculation unit, used to calculate the traction force of the target train based on the basic resistance, the slope additional resistance, the curve additional resistance and the acceleration; a construction unit, used to obtain the traction energy consumption of the entire line through the traction force, so as to construct the ATO single-vehicle energy consumption model according to the traction energy consumption of the entire line and the multiple energy-saving parameters.

[0023] Optionally, in one embodiment of the present application, the generation module includes: a search unit, used to perform a grid search on the range corresponding to each energy-saving parameter through the control variable optimization strategy to obtain multiple equally spaced sampling points of each energy-saving parameter; a sampling unit, used to obtain multiple pairs of adjacent sampling points among the multiple equally spaced sampling points, and establish an energy-saving parameter range to be optimized corresponding to each pair of adjacent sampling points among the multiple pairs of adjacent sampling points; a judgment unit, used to judge whether each pair of adjacent sampling points meets the preset vehicle control requirements, if any pair of adjacent sampling points does not meet the preset vehicle control requirements, then deleting the energy-saving parameter range to be optimized composed of the any pair of adjacent sampling points, otherwise generating a refined range of energy-saving parameters corresponding to the any pair of adjacent sampling points.

[0024] Optionally, in one embodiment of the present application, the optimization module includes: a determination unit, which is used to determine the objective function of the ATO single-vehicle energy consumption model and obtain the parameter adjustment history based on all the historical collection points; a fitting unit, which is used to establish a probabilistic proxy model based on the parameter adjustment history and a preset estimator, so as to fit the correspondence between the objective function and the one-dimensional vector of energy-saving parameters constructed by the at least one energy-saving parameter through the probabilistic proxy model; an evaluation unit, which is used to obtain the target evaluation point corresponding to each energy-saving parameter through a preset collection function, and determine the objective function corresponding to the target evaluation point through the correspondence and the target evaluation point; an iteration unit, which is used to determine whether the target evaluation point and the objective function corresponding to the target evaluation point meet the preset iteration termination condition; a loop unit, which is used to continue to perform the global optimization operation according to the target evaluation point if the target evaluation point and the objective function corresponding to the target evaluation point do not meet the preset iteration termination condition; a combination unit, which is used to terminate the global optimization operation if the target evaluation point and the objective function corresponding to the target evaluation point meet the preset iteration termination condition, and obtain an energy-saving parameter combination that meets the preset energy-saving requirement.

[0025] Optionally, in one embodiment of the present application, the mathematical expression of the traction energy consumption of the entire line is:

[0026]

[0027] Among them, inf_energy is the multiple energy-saving parameters that can be configured by ATO.

[0028] The third aspect of the present application provides an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the multi-parameter automatic optimization method based on the ATO single-vehicle energy consumption model as described in the above embodiment.

[0029] The fourth aspect of the present application provides a computer-readable storage medium, which stores a computer program. When the program is executed by a processor, it implements the above-mentioned multi-parameter automatic optimization method based on the ATO single-vehicle energy consumption model.

[0030] Therefore, the embodiments of the present application have the following beneficial effects:

[0031] The embodiments of the present application can obtain the basic resistance, ramp additional resistance and curve additional resistance during the operation of the target train, and construct an ATO single-vehicle energy consumption model based on the basic resistance, ramp additional resistance, curve additional resistance and multiple preset energy-saving parameters; optimize the range corresponding to each energy-saving parameter in the multiple energy-saving parameters through the preset control variable optimization strategy to generate at least one energy-saving parameter refinement range corresponding to each energy-saving parameter that meets the preset vehicle control requirements; perform global optimization operations on the iteration of the ATO single-vehicle energy consumption model, and obtain the probability distribution corresponding to the collection points and all historical collection points of each energy-saving parameter refinement range in at least one energy-saving parameter refinement range in each iteration of the global optimization operation, so as to obtain the energy-saving parameter combination that meets the preset energy-saving requirements based on the probability distribution, the preset collection function and the preset iteration termination condition. The present application constructs an ATO single-vehicle energy consumption model, and combines parameter preprocessing operations to obtain the energy-saving parameter range, and uses a global optimization method to optimize the energy-saving parameters, thereby effectively reducing the computing cost while ensuring the energy-saving effect, which is beneficial to subsequent on-site debugging and software iteration. This solves the problems that the existing ATO energy-saving technology is prone to optimal energy-saving curve deviation, resulting in poor generalization of the energy-saving algorithm, inability to be debugged by on-site personnel, and difficulty in achieving the global optimal energy-saving effect.

[0032] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0034] Figure 1 A flowchart of a multi-parameter automatic optimization method based on an ATO single-vehicle energy consumption model provided according to an embodiment of the present application;

[0035] Figure 2 A logical architecture diagram of a multi-parameter automatic optimization method based on an ATO single-vehicle energy consumption model provided for one embodiment of the present application;

[0036] Figure 3 A schematic diagram of an ATO energy-saving parameter optimization process provided for an embodiment of the present application;

[0037] Figure 4 This is an example diagram of a multi-parameter automatic optimization device based on an ATO single-vehicle energy consumption model according to an embodiment of the present application;

[0038] Figure 5 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application.

[0039] Among them, 10-a multi-parameter automatic optimization device based on the ATO single-vehicle energy consumption model; 100-a construction module, 200-a generation module, 300-an optimization module; 501-a memory, 502-a processor, 503-a communication interface. DETAILED DESCRIPTION

[0040] Embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0041] The following describes the multi-parameter automatic optimization method and device based on the ATO single-vehicle energy consumption model of the embodiment of the present application with reference to the accompanying drawings. In response to the problems mentioned in the above background technology, the present application provides a multi-parameter automatic optimization method based on the ATO single-vehicle energy consumption model, in which the basic resistance, ramp additional resistance and curve additional resistance of the target train during operation are obtained, and the ATO single-vehicle energy consumption model is constructed based on the basic resistance, ramp additional resistance, curve additional resistance and preset multiple energy-saving parameters; the range corresponding to each energy-saving parameter in the multiple energy-saving parameters is optimized by a preset control variable optimization strategy to generate at least one energy-saving parameter refinement range corresponding to each energy-saving parameter that meets the preset vehicle control requirements; the ATO single-vehicle energy consumption model is iteratively optimized globally, and the probability distribution corresponding to the collection points and all historical collection points in at least one energy-saving parameter refinement range in each iteration of the global optimization operation is obtained, so as to obtain the energy-saving parameter combination that meets the preset energy-saving requirements based on the probability distribution, the preset collection function and the preset iteration termination condition. This application constructs an ATO single-vehicle energy consumption model and combines parameter preprocessing operations to obtain the energy-saving parameter range, and uses a global optimization method to optimize the energy-saving parameters, thereby effectively reducing the computing cost while ensuring the energy-saving effect, which is beneficial to subsequent on-site debugging and software iteration. As a result, the existing ATO energy-saving technology is prone to optimal energy-saving curve deviation, making the energy-saving algorithm too generalized, unable to be debugged by on-site personnel, and difficult to achieve the global optimal energy-saving effect.

[0042] Specifically, Figure 1A flowchart of a multi-parameter automatic optimization method based on the ATO single-vehicle energy consumption model provided in an embodiment of the present application.

[0043] like Figure 1 As shown, the multi-parameter automatic optimization method based on the ATO single-vehicle energy consumption model includes the following steps:

[0044] In step S101, the basic resistance, slope additional resistance and curve additional resistance of the target train during operation are obtained, and an ATO single-vehicle energy consumption model is constructed based on the basic resistance, slope additional resistance, curve additional resistance and multiple preset energy-saving parameters.

[0045] The embodiment of the present application first obtains the basic resistance, slope additional resistance and curve additional resistance during the operation of the target train, calculates the traction force and its corresponding traction energy consumption, and then constructs an ATO single-vehicle energy consumption model with multiple preset energy-saving parameters as independent variables and traction energy consumption as dependent variable, thereby providing reliable technical support for subsequent multi-parameter automatic optimization.

[0046] Optionally, in one embodiment of the present application, an ATO single-vehicle energy consumption model is constructed based on basic resistance, additional resistance on slopes, additional resistance on curves and preset multiple energy-saving parameters, including: obtaining line data, vehicle characteristic data and multiple energy-saving parameters during the operation of the target train, so as to calculate the acceleration of the target train according to the line data, vehicle characteristic data and multiple energy-saving parameters; calculating the traction force of the target train based on the basic resistance, additional resistance on slopes, additional resistance on curves and acceleration; obtaining the traction energy consumption of the entire line through the traction force, so as to construct the ATO single-vehicle energy consumption model according to the traction energy consumption of the entire line and multiple energy-saving parameters.

[0047] It should be noted that the train running resistance in the embodiment of the present application includes basic resistance and additional resistance.

[0048] Among them, the basic resistance includes the movement resistance of the coupler connections between vehicles in the subway train formation, the air resistance encountered by the subway train during operation, etc.; the additional resistance is the resistance formed due to subway lines or elevated bridges, tunnel piston wind, etc., mainly including ramp additional resistance, curve additional resistance and tunnel additional resistance.

[0049] When performing bicycle modeling, the embodiments of the present application mainly consider basic resistance, slope additional resistance and curve additional resistance.

[0050] It should be understood by those skilled in the art that, according to force analysis, when a train is traveling on a line, it is mainly subjected to three forces: traction, basic resistance, and additional resistance (mainly including slope additional resistance and curve additional resistance), as shown in the following formula:

[0051] F t -Fbasic -F ramp -F cramp =ma(1)

[0052] Among them, F t 、F basic 、F ramp 、F cramp They represent traction, basic resistance, additional resistance on slopes and additional resistance on curves respectively, m is the total mass of the train (motor vehicle + trailer), and a is the acceleration.

[0053] Furthermore, formula (1) can be equivalent to:

[0054] F t =m(a+a basic +a ramp +a cramp )(2)

[0055] Among them, a basic 、a ramp 、a cramp They represent the acceleration caused by basic resistance, the acceleration caused by slope, and the acceleration caused by curves respectively.

[0056] In an embodiment of the present application, the ATO system can generate a full-line vehicle control curve according to the input electronic map and energy-saving related parameters, as shown in the following formula:

[0057] T, δ, a, v, r = f (inf_wayside, inf_train, inf_energy) (3)

[0058] Among them, inf_wayside is the line data, inf_train is the vehicle characteristic data, inf_energy is the energy-saving related parameter, δ, a, v, r are traction, impact rate, acceleration, speed and level information respectively, all of which are directly given by the ATO system with the line position x as the horizontal coordinate.

[0059] The mass of the train can be directly obtained based on the vehicle information. Therefore, the embodiment of the present application can obtain the mass m of the vehicle and the actual acceleration a at each position.

[0060] In addition, in the embodiment of the present application, the basic resistance (unit KN) formula is as follows:

[0061]

[0062] Among them, M is the weight of the EMU, which is 49.24 for Chongqing Guobo Line AW2 (capacity), in tons; T is the weight of the trailer, which is 48.06 for Chongqing Guobo Line AW2 (capacity), in tons; N is the number of trains, 6; v is the train speed, in km / h.

[0063] The acceleration caused by the unit basic resistance (in cm / s / s) is:

[0064] a basic =-F / (M+T)*100=-1.197-0.0136v-0.000675v 2 (5)

[0065] Furthermore, the unit additional resistance in the embodiment of the present application is composed of unit slope additional resistance and unit curve additional resistance.

[0066] It should be noted that the ramp in the embodiment of the present application is represented by ramp, and the uphill is positive, the downhill is negative, and the unit is ‰. When the slope is small, the acceleration caused by the unit additional resistance of the ramp (unit cm / s / s) is approximately as follows:

[0067] a ramp =-ramp(6)

[0068] The acceleration caused by the additional resistance of the curve unit (in cm / s / s) is:

[0069] a cramp =-A / R(7)

[0070] Among them, the empirical parameter of A is 600, and R is the curve radius, in meters.

[0071] Furthermore, the embodiment of the present application can obtain the traction force of the train at any position and the traction energy consumption W according to the above steps. s The following formula can be obtained by integrating the work done by the traction force on the entire line:

[0072]

[0073] Among them, F t is the traction force at each differential distance on the entire line.

[0074] Therefore, the embodiment of the present application comprehensively considers the basic resistance, ramp additional resistance and curve additional resistance to construct a relatively complete ATO energy consumption model, thereby fully considering the full line information, vehicle information, ATO configuration information, etc., greatly improving the simulation effect of real scenes.

[0075] Optionally, in one embodiment of the present application, the mathematical expression of the traction energy consumption of the entire line is:

[0076]

[0077] Among them, inf_energy refers to multiple energy-saving parameters that can be configured by ATO.

[0078] It should be noted that, for the same batch of trains on a given line, the embodiment of the present application can be combined with formula (3), where the line conditions and inf_train are fixed values. It is only necessary to give the energy-saving related parameter inf_energy to generate a unique train control curve to calculate the traction force at each position, thereby obtaining the traction energy consumption of the entire line, as shown in the following formula:

[0079]

[0080] Among them, inf_energy is the energy-saving related parameter configurable by ATO. It should be noted that the type and quantity of the specific values ​​of the energy-saving parameters are consistent with the configurable values ​​of the energy-saving part in the ATO algorithm. These values ​​can be completely different in different ATO algorithms, but do not affect the basic logic of the ATO algorithm.

[0081] Therefore, the embodiment of the present application constructs an ATO single-vehicle energy consumption model through a specific energy consumption model calculation method, with energy-saving parameters as independent variables and single-vehicle energy consumption of the entire line as dependent variables, thereby reflecting the impact of energy-saving parameter adjustment on the current train's energy consumption on the entire line.

[0082] In step S102, the range corresponding to each energy-saving parameter in the plurality of energy-saving parameters is optimized by a preset control variable optimization strategy to generate at least one energy-saving parameter refinement range corresponding to each energy-saving parameter that meets the preset vehicle control requirement.

[0083] After constructing the ATO bicycle energy consumption model, the embodiment of the present application can further use the equally spaced grid search method of the control variables to optimize the range corresponding to each energy-saving parameter, such as Figure 2 As shown, the energy-saving parameter range that does not meet the basic requirements of vehicle control is screened to obtain a refined energy-saving parameter range, that is, a refined energy-saving parameter range.

[0084] Optionally, in one embodiment of the present application, the range corresponding to each energy-saving parameter in multiple energy-saving parameters is optimized by a preset control variable optimization strategy to generate at least one energy-saving parameter refinement range corresponding to each energy-saving parameter that meets the preset vehicle control requirements, including: performing a grid search on the range corresponding to each energy-saving parameter by the control variable optimization strategy to obtain multiple equally spaced sampling points for each energy-saving parameter; obtaining multiple pairs of adjacent sampling points from the multiple equally spaced sampling points, and establishing an energy-saving parameter range to be optimized corresponding to each pair of adjacent sampling points in the multiple pairs of adjacent sampling points; judging whether each pair of adjacent sampling points meets the preset vehicle control requirements, if any pair of adjacent sampling points does not meet the preset vehicle control requirements, deleting the energy-saving parameter range to be optimized composed of any pair of adjacent sampling points, otherwise generating an energy-saving parameter refinement range corresponding to any pair of adjacent sampling points.

[0085] In the actual implementation process, the goal of the ATO energy-saving parameter optimization in the embodiment of the present application is to explore the optimal inf_energy parameter combination based on the above-mentioned ATO single-vehicle energy consumption model. This process mainly includes two parts: preprocessing and parameter optimization.

[0086] It should be noted that a set of energy-saving parameters that need to be optimized in the embodiment of the present application is: α1, α2, α3, ..., α7, a total of 7 parameters, and their corresponding names and meanings are shown in the following table:

[0087] Table 1

[0088]

[0089]

[0090] In the preprocessing process of ATO energy-saving parameter optimization, in order to ensure that the train operation meets the requirements of accurate stopping, stable stopping, and comfort, additional parameters such as accurate stopping, stable stopping, and impact rate need to be restricted, and recorded as β1, β2, β3, ..., β m There are m parameters in total. In the embodiment of the present application, four constraints are taken as an example. The specific meanings and constraints are shown in the following formula:

[0091]

[0092] For each energy-saving parameter α∈[α min ,α max ], and α is an integer. The embodiment of the present application can determine a set of outputs through grid search, and re-determine the range of α1, α2, α3, ..., α7 according to whether the output vehicle control curve meets the requirements of β1, β2, β3, β4, so as to update each α∈Z α The actual range of the algorithm can be reduced, which can narrow the optional range of subsequent algorithm parameter updates and improve search efficiency.

[0093] As an achievable method, the embodiment of the present application can control the variable optimization strategy, perform grid search on the range corresponding to each energy-saving parameter, discuss only one energy-saving parameter α each time, and sample 100 points at equal intervals, without discussing the common influence between parameters.

[0094] It should be noted that the principle of updating the parameter range in the embodiment of the present application is: if there is an energy-saving parameter α with a value of α i and α i+1 (two consecutive values), the requirements are not met, and the value of α should be excluded [α i ,α i+1 ] range; in addition, the parameter combination with the minimum energy consumption of the model in the grid search should also be recorded as the initial parameter list for subsequent parameter optimization.

[0095] Therefore, the embodiment of the present application preprocesses the energy-saving parameter range through an equally spaced grid search, and generates a refined range of energy-saving parameters corresponding to each energy-saving parameter that meets the preset vehicle control requirements, thereby effectively reducing the computational overhead of subsequent global optimization and other operations.

[0096] In step S103, a global optimization operation is performed on the ATO single-vehicle energy consumption model iteration, and the probability distribution corresponding to the collection points of each energy-saving parameter refinement range and all historical collection points in at least one energy-saving parameter refinement range is obtained during each iteration of the global optimization operation, so as to obtain an energy-saving parameter combination that meets the preset energy-saving requirements based on the probability distribution, the preset collection function and the preset iteration termination condition.

[0097] Furthermore, the embodiments of the present application can perform global optimization operations on the ATO single-vehicle energy consumption model iteration, and consider the probability distribution of historical collection point data in each iterative process of the global optimization operation, so as to infer the parameter combination most worth trying, significantly reducing the parameter optimization time and effectively saving computing power.

[0098] Optionally, in one embodiment of the present application, a global optimization operation is performed on the ATO single-vehicle energy consumption model iteration, and in each iteration of the global optimization operation, a probability distribution corresponding to a collection point of each energy-saving parameter refinement range and all historical collection points in at least one energy-saving parameter refinement range is obtained, so as to obtain an energy-saving parameter combination that meets the preset energy-saving requirements based on the probability distribution, the preset collection function and the preset iteration termination condition, including: determining the objective function of the ATO single-vehicle energy consumption model, and obtaining the parameter adjustment history according to all historical collection points; establishing a probabilistic proxy model based on the parameter adjustment history and the preset estimator, so as to fit the objective function and at least one through the probabilistic proxy model. The corresponding relationship of the one-dimensional vector of energy-saving parameters constructed by the energy-saving parameters; the target evaluation point corresponding to each energy-saving parameter is obtained through the preset acquisition function, and the objective function corresponding to the target evaluation point is determined through the corresponding relationship and the target evaluation point; it is judged whether the target evaluation point and the objective function corresponding to the target evaluation point meet the preset iteration termination condition; if the target evaluation point and the objective function corresponding to the target evaluation point do not meet the preset iteration termination condition, the global optimization operation is continued according to the target evaluation point; if the target evaluation point and the objective function corresponding to the target evaluation point meet the preset iteration termination condition, the global optimization operation is terminated, and the energy-saving parameter combination that meets the preset energy-saving requirements is obtained.

[0099] It can be understood that the embodiment of the present application performs ATO energy-saving parameter optimization, that is, when β1, β2, β3, β4 meet the operation requirements, α1, α2, α3, ..., α7 (i.e., x vector) are optimized so that Minimum (i.e. E=F(α1,α2,α3,……,α7)).

[0100] Specifically, Figure 3 This is a schematic diagram of the ATO energy-saving parameter optimization process. Figure 3 As shown, the steps of optimizing ATO energy-saving parameters in the embodiment of the present application are as follows:

[0101] Step 1, determine the objective function E = F (α1, α2, α3, ..., α7), where the value range of α1, α2, α3, ..., α7 is the value range after preprocessing;

[0102] Step 2: Initialize the acquisition point and use the (x, E) sequence in the previous grid search as the parameter adjustment history, denoted as: H = (x 1:k ,F(x 1:k )), add (x when not initialized t ,F(x t )) to the historical parameter adjustment records;

[0103] Step 3. Establish a probabilistic proxy model M based on the parameter adjustment history H. The probabilistic proxy model uses a tree-structured Parzen estimator. This optimizer can adaptively adjust the size of the parameter search space and find the global optimal solution in the fewest possible iterations. Therefore, the proxy model will fit a (x, F(x)) correspondence relationship based on the parameter adjustment history.

[0104] Step 4: Obtain the next most "potential" evaluation point x according to the acquisition function (ACF) t , ACF uses Expected Improvement (EI) as the acquisition function, that is, according to the probability distribution M, it fully balances the gains and losses of searching near the current lowest point and exploring the possible lowest value in the unknown area as much as possible. The expression of EI is as follows:

[0105]

[0106] Among them, y * is a certain threshold, EI is the expectation with x as the independent variable, and EI(x) represents y * Compared with the degree of improvement of y (i.e., energy consumption F(x)), ACF can select the x position with the largest improvement as x t Output.

[0107] Step 5: Determine (x t ,F(x t )) meets the requirements of jumping out of the loop. The iteration termination condition here can be set as: when the number of iterations (such as 10,000 times) is reached and the change of y does not exceed a certain value (such as 0.1%) for multiple consecutive times (such as 100 times), the model is considered to have converged and the iteration is terminated.

[0108] If the iteration termination condition is met, the iteration loop is exited; otherwise, the point is added to the historical parameter adjustment record, and steps 2 to 5 are executed again until the requirements are met, and an energy-saving parameter sequence that meets the requirements can be obtained.

[0109] Therefore, the embodiment of the present application further improves the model solving efficiency by optimizing the ATO energy-saving parameters and determining the next target parameter combination position based on the probability distribution of prior knowledge, thereby greatly reducing the training time while ensuring the optimization effect.

[0110] It can be understood that the embodiments of the present application can globally optimize the energy-saving parameters of the train under all line conditions. When the line conditions or operating conditions change, the energy-saving effect will not be significantly reduced. It has better adaptability to the changing operation scenarios on site, low parameter update cost, and is conducive to on-site fine-tuning. The energy-saving parameters are also interpretable and extensible, which is conducive to subsequent on-site debugging and software iteration. In addition, the embodiments of the present application can not only comprehensively consider the conditions of the entire line to achieve the global optimal energy-saving effect, but also avoid the problem of poor generalization of the energy-saving algorithm caused by the deviation of the optimal energy-saving curve (operation, line changes).

[0111] According to the multi-parameter automatic optimization method based on the ATO single-vehicle energy consumption model proposed in the embodiment of the present application, the basic resistance, ramp additional resistance and curve additional resistance during the operation of the target train are obtained, and the ATO single-vehicle energy consumption model is constructed based on the basic resistance, ramp additional resistance, curve additional resistance and multiple preset energy-saving parameters; the range corresponding to each energy-saving parameter in the multiple energy-saving parameters is optimized by the preset control variable optimization strategy to generate at least one energy-saving parameter refinement range corresponding to each energy-saving parameter that meets the preset vehicle control requirements; the ATO single-vehicle energy consumption model is iteratively optimized globally, and the probability distribution corresponding to the collection points and all historical collection points of each energy-saving parameter refinement range in at least one energy-saving parameter refinement range is obtained during each iteration of the global optimization operation, so as to obtain the energy-saving parameter combination that meets the preset energy-saving requirements based on the probability distribution, the preset collection function and the preset iteration termination condition. The present application constructs the ATO single-vehicle energy consumption model, and combines the parameter preprocessing operation to obtain the energy-saving parameter range, and uses the global optimization method to optimize the energy-saving parameters, thereby effectively reducing the calculation cost while ensuring the energy-saving effect, which is beneficial to subsequent on-site debugging and software iteration.

[0112] Secondly, the multi-parameter automatic optimization device based on the ATO single-vehicle energy consumption model proposed in accordance with the embodiment of the present application is described with reference to the accompanying drawings.

[0113] Figure 4 It is a block diagram of a multi-parameter automatic optimization device based on an ATO single-vehicle energy consumption model in an embodiment of the present application.

[0114] like Figure 4 As shown, the multi-parameter automatic optimization device 10 based on the ATO single-vehicle energy consumption model includes: a construction module 100, a generation module 200 and an optimization module 300.

[0115] Among them, the construction module 100 is used to obtain the basic resistance, slope additional resistance and curve additional resistance during the operation of the target train, and to construct an ATO single-vehicle energy consumption model based on the basic resistance, slope additional resistance, curve additional resistance and multiple preset energy-saving parameters.

[0116] The generation module 200 is used to optimize the range corresponding to each energy-saving parameter in the multiple energy-saving parameters through a preset control variable optimization strategy to generate at least one energy-saving parameter refinement range corresponding to each energy-saving parameter that meets the preset vehicle control requirements.

[0117] The optimization module 300 is used to perform global optimization operations on the ATO single-vehicle energy consumption model iteration, and obtain the probability distribution corresponding to each collection point of each energy-saving parameter refinement range and all historical collection points in at least one energy-saving parameter refinement range during each iteration of the global optimization operation, so as to obtain an energy-saving parameter combination that meets the preset energy-saving requirements based on the probability distribution, the preset collection function and the preset iteration termination condition.

[0118] Optionally, in one embodiment of the present application, the construction module 100 includes: a first calculation unit, a second calculation unit and a establishment unit.

[0119] Among them, the first calculation unit is used to obtain line data, vehicle characteristic data and multiple energy-saving parameters during the operation of the target train, so as to calculate the acceleration of the target train according to the line data, vehicle characteristic data and multiple energy-saving parameters.

[0120] The second calculation unit is used to calculate the traction of the target train based on the basic resistance, the slope additional resistance, the curve additional resistance and the acceleration.

[0121] A unit is established for obtaining the traction energy consumption of the entire line through the traction force, so as to construct an ATO single-vehicle energy consumption model according to the traction energy consumption of the entire line and multiple energy-saving parameters.

[0122] Optionally, in one embodiment of the present application, the generation module 200 includes: a search unit, a sampling unit and a judgment unit.

[0123] The search unit is used to perform a grid search on the range corresponding to each energy-saving parameter through a control variable optimization strategy to obtain a plurality of equally spaced sampling points for each energy-saving parameter.

[0124] The sampling unit is used to obtain multiple pairs of adjacent sampling points from multiple equally spaced sampling points, and establish a range of energy-saving parameters to be optimized corresponding to each pair of adjacent sampling points from the multiple pairs of adjacent sampling points.

[0125] The judgment unit is used to judge whether each pair of adjacent sampling points meets the preset vehicle control requirements. If any pair of adjacent sampling points does not meet the preset vehicle control requirements, the energy-saving parameter range to be optimized composed of any pair of adjacent sampling points is deleted, otherwise a refined energy-saving parameter range corresponding to any pair of adjacent sampling points is generated.

[0126] Optionally, in one embodiment of the present application, the optimization module 300 includes: a determination unit, a fitting unit, an evaluation unit, an iteration unit, a loop unit and a combination unit.

[0127] Among them, the determination unit is used to determine the objective function of the ATO single-vehicle energy consumption model and obtain the parameter adjustment history based on all historical collection points.

[0128] A fitting unit is used to establish a probabilistic proxy model based on the parameter adjustment history and a preset estimator, so as to fit the correspondence between the objective function and the one-dimensional vector of energy-saving parameters constructed by at least one energy-saving parameter through the probabilistic proxy model.

[0129] The evaluation unit is used to obtain the target evaluation point corresponding to each energy-saving parameter through a preset acquisition function, and determine the target function corresponding to the target evaluation point through the corresponding relationship and the target evaluation point.

[0130] The iteration unit is used to determine whether the target evaluation point and the objective function corresponding to the target evaluation point meet the preset iteration termination condition.

[0131] The loop unit is used to continue to perform the global optimization operation according to the target evaluation point if the target evaluation point and the objective function corresponding to the target evaluation point do not meet the preset iteration termination condition.

[0132] The combination unit is used to terminate the global optimization operation if the target evaluation point and the objective function corresponding to the target evaluation point meet the preset iteration termination condition, and obtain the energy-saving parameter combination that meets the preset energy-saving requirement.

[0133] Optionally, in one embodiment of the present application, the mathematical expression of the traction energy consumption of the entire line is:

[0134]

[0135] Among them, inf_energy refers to multiple energy-saving parameters that can be configured by ATO.

[0136] It should be noted that the above explanation of the embodiment of the multi-parameter automatic optimization method based on the ATO single-vehicle energy consumption model is also applicable to the multi-parameter automatic optimization device based on the ATO single-vehicle energy consumption model of this embodiment, and will not be repeated here.

[0137] According to the multi-parameter automatic optimization device based on the ATO single-vehicle energy consumption model proposed in the embodiment of the present application, it includes a construction module for obtaining the basic resistance, ramp additional resistance and curve additional resistance during the operation of the target train, and constructing the ATO single-vehicle energy consumption model based on the basic resistance, ramp additional resistance, curve additional resistance and multiple preset energy-saving parameters; a generation module for optimizing the range corresponding to each energy-saving parameter in multiple energy-saving parameters through a preset control variable optimization strategy to generate at least one energy-saving parameter refinement range corresponding to each energy-saving parameter that meets the preset vehicle control requirements; an optimization module for iteratively performing global optimization operations on the ATO single-vehicle energy consumption model, and obtaining the probability distribution corresponding to the collection points and all historical collection points of each energy-saving parameter refinement range in at least one energy-saving parameter refinement range in each iteration of the global optimization operation, so as to obtain the energy-saving parameter combination that meets the preset energy-saving requirements based on the probability distribution, the preset collection function and the preset iteration termination condition. The present application constructs the ATO single-vehicle energy consumption model, and combines the parameter preprocessing operation to obtain the energy-saving parameter range, and uses the global optimization method to optimize the energy-saving parameters, thereby effectively reducing the calculation cost while ensuring the energy-saving effect, which is conducive to subsequent on-site debugging and software iteration.

[0138] Figure 5 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. The electronic device may include:

[0139] A memory 501 , a processor 502 , and a computer program stored in the memory 501 and executable on the processor 502 .

[0140] When the processor 502 executes the program, the multi-parameter automatic optimization method based on the ATO single-vehicle energy consumption model provided in the above embodiment is implemented.

[0141] Furthermore, the electronic device further comprises:

[0142] The communication interface 503 is used for communication between the memory 501 and the processor 502 .

[0143] The memory 501 is used to store computer programs that can be executed on the processor 502 .

[0144] The memory 501 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0145] If the memory 501, the processor 502 and the communication interface 503 are implemented independently, the communication interface 503, the memory 501 and the processor 502 can be connected to each other through a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 5 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0146] Optionally, in a specific implementation, if the memory 501, the processor 502 and the communication interface 503 are integrated on a chip, the memory 501, the processor 502 and the communication interface 503 can communicate with each other through an internal interface.

[0147] The processor 502 may be a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application.

[0148] An embodiment of the present application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-mentioned multi-parameter automatic optimization method based on the ATO single-vehicle energy consumption model.

[0149] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or N embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0150] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0151] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or N executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present application belong.

[0152] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purpose of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or N wirings (electronic devices), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways as necessary and then storing it in a computer memory.

[0153] It should be understood that the various parts of the present application can be implemented by hardware, software, firmware or a combination thereof. In the above embodiment, the N steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. If implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0154] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0155] In addition, each functional unit in each embodiment of the present application may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0156] The storage medium mentioned above may be a read-only memory, a magnetic disk or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limiting the present application. A person of ordinary skill in the art may change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. A multi-parameter automatic optimization method based on the ATO single-vehicle energy consumption model, characterized in that: The following steps are involved: Obtaining the basic resistance, ramp additional resistance and curve additional resistance of the target train during operation, and building an ATO single-vehicle energy consumption model based on the basic resistance, the ramp additional resistance, the curve additional resistance and a plurality of preset energy-saving parameters; Optimizing the range corresponding to each energy-saving parameter in the multiple energy-saving parameters by using a preset control variable optimization strategy to generate at least one energy-saving parameter refinement range corresponding to each energy-saving parameter that meets the preset vehicle control requirements; A global optimization operation is performed on the ATO single-vehicle energy consumption model iteration, and in each iteration of the global optimization operation, the probability distribution corresponding to the collection points of each energy-saving parameter refinement range and all historical collection points in the at least one energy-saving parameter refinement range is obtained, so as to obtain an energy-saving parameter combination that meets the preset energy-saving requirement based on the probability distribution, the preset collection function and the preset iteration termination condition.

2. The method according to claim 1, characterized in that The ATO single-vehicle energy consumption model is constructed based on the basic resistance, the ramp additional resistance, the curve additional resistance and a plurality of preset energy-saving parameters, including: Acquiring line data, vehicle characteristic data and the plurality of energy-saving parameters during the operation of the target train, so as to calculate the acceleration of the target train according to the line data, the vehicle characteristic data and the plurality of energy-saving parameters; Calculating the traction force of the target train based on the basic resistance, the slope additional resistance, the curve additional resistance and the acceleration; The traction energy consumption of the entire line is obtained through the traction force, so as to construct the ATO single-vehicle energy consumption model according to the traction energy consumption of the entire line and the multiple energy-saving parameters.

3. The method according to claim 2, characterized in that The optimizing the range corresponding to each energy-saving parameter in the plurality of energy-saving parameters by using a preset control variable optimization strategy to generate at least one energy-saving parameter refinement range corresponding to each energy-saving parameter that meets the preset vehicle control requirements includes: By using the control variable optimization strategy, a grid search is performed on the range corresponding to each energy-saving parameter to obtain a plurality of equally spaced sampling points of each energy-saving parameter; Acquire multiple pairs of adjacent sampling points from the multiple equally spaced sampling points, and establish an energy-saving parameter range to be optimized corresponding to each pair of adjacent sampling points from the multiple pairs of adjacent sampling points; It is determined whether each pair of adjacent sampling points meets the preset vehicle control requirement. If any pair of adjacent sampling points does not meet the preset vehicle control requirement, the energy-saving parameter range to be optimized composed of the any pair of adjacent sampling points is deleted. Otherwise, a refined energy-saving parameter range corresponding to the any pair of adjacent sampling points is generated.

4. The method according to claim 3, characterized in that The iterative global optimization operation is performed on the ATO single-vehicle energy consumption model, and in each iterative process of the global optimization operation, the probability distribution corresponding to the collection points of each energy-saving parameter refinement range and all historical collection points in the at least one energy-saving parameter refinement range is obtained, so as to obtain an energy-saving parameter combination that meets the preset energy-saving requirements based on the probability distribution, the preset collection function and the preset iteration termination condition, including: Determine the objective function of the ATO single-vehicle energy consumption model, and obtain the parameter adjustment history according to all the historical collection points; Based on the parameter adjustment history and the preset estimator, a probabilistic proxy model is established to fit the corresponding relationship between the objective function and the one-dimensional vector of energy-saving parameters constructed by the at least one energy-saving parameter through the probabilistic proxy model; Acquire the target evaluation point corresponding to each energy-saving parameter through a preset acquisition function, and determine the objective function corresponding to the target evaluation point through the corresponding relationship and the target evaluation point; Determine whether the target evaluation point and the objective function corresponding to the target evaluation point satisfy the preset iteration termination condition; If the target evaluation point and the objective function corresponding to the target evaluation point do not satisfy the preset iteration termination condition, then continue to perform the global optimization operation according to the target evaluation point; If the target evaluation point and the objective function corresponding to the target evaluation point satisfy the preset iteration termination condition, the global optimization operation is terminated, and an energy-saving parameter combination that satisfies the preset energy-saving requirement is obtained.

5. The method according to claim 2, characterized in that: The mathematical expression of the traction energy consumption of the entire line is: Among them, inf_energy is the multiple energy-saving parameters that can be configured by ATO.

6. A multi-parameter automatic optimization device based on the ATO single-vehicle energy consumption model, characterized in that: include: A construction module is used to obtain the basic resistance, the slope additional resistance and the curve additional resistance during the operation of the target train, and to construct an ATO single-vehicle energy consumption model based on the basic resistance, the slope additional resistance, the curve additional resistance and a plurality of preset energy-saving parameters; A generating module, used for optimizing the range corresponding to each energy-saving parameter of the plurality of energy-saving parameters through a preset control variable optimization strategy, so as to generate at least one energy-saving parameter refinement range corresponding to each energy-saving parameter that meets the preset vehicle control requirement; The optimization module is used to perform global optimization operations on the iteration of the ATO single-vehicle energy consumption model, and obtain the probability distribution corresponding to the collection points of each energy-saving parameter refinement range and all historical collection points in the at least one energy-saving parameter refinement range during each iteration of the global optimization operation, so as to obtain an energy-saving parameter combination that meets the preset energy-saving requirements based on the probability distribution, the preset collection function and the preset iteration termination condition.

7. The device according to claim 6, characterized in that The building blocks include: a first calculation unit, configured to obtain line data, vehicle characteristic data, and the plurality of energy-saving parameters during the operation of the target train, so as to calculate the acceleration of the target train according to the line data, the vehicle characteristic data, and the plurality of energy-saving parameters; a second calculation unit, configured to calculate the traction of the target train based on the basic resistance, the ramp additional resistance, the curve additional resistance and the acceleration; A unit is established, which is used to obtain the traction energy consumption of the entire line through the traction force, so as to construct the ATO single-vehicle energy consumption model according to the traction energy consumption of the entire line and the multiple energy-saving parameters.

8. The device according to claim 7, characterized in that The generation module comprises: A search unit, configured to perform a grid search on the range corresponding to each energy-saving parameter through the control variable optimization strategy to obtain a plurality of equally spaced sampling points of each energy-saving parameter; A sampling unit, configured to obtain a plurality of pairs of adjacent sampling points from the plurality of equally spaced sampling points, and establish a range of energy-saving parameters to be optimized corresponding to each pair of adjacent sampling points from the plurality of pairs of adjacent sampling points; A judging unit is used to judge whether each pair of adjacent sampling points meets the preset vehicle control requirement. If any pair of adjacent sampling points does not meet the preset vehicle control requirement, the energy-saving parameter range to be optimized composed of the any pair of adjacent sampling points is deleted; otherwise, a refined energy-saving parameter range corresponding to the any pair of adjacent sampling points is generated.

9. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the multi-parameter automatic optimization method based on the ATO single-vehicle energy consumption model as described in any one of claims 1 to 5.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: The program is executed by a processor to implement a multi-parameter automatic optimization method based on an ATO single-vehicle energy consumption model as described in any one of claims 1 to 5.

Images