Brake Energy Consumption Optimization Method and System for Rail Train Operation

Abstract

The present invention discloses a method and system for optimizing the braking energy consumption of an orbital train operation, which relates to the technical field of braking energy consumption optimization, and includes: loading a predetermined operation plan of a target orbital train, decomposing the stations, and generating a plurality of node operation plans; predicting the potential of braking energy recovery to obtain a plurality of node regenerative braking energies; performing energy recovery scheduling on a plurality of braking energy recovery devices to establish a plurality of node braking energy recovery scheduling spaces; constructing a braking energy recovery evaluation component; performing optimization analysis on a plurality of node braking energy recovery scheduling spaces to obtain a plurality of node energy recovery optimization strategies, and encrypting and sending them to the train operation control terminal, and the train operation control terminal performs braking energy recovery on the target orbital train according to a plurality of braking energy recovery devices and a plurality of node energy recovery optimization strategies. The present invention solves the technical problem of low energy utilization rate in the prior art during the energy recovery process, and achieves the technical effect of improving the energy utilization rate.

Description

Technical Field

[0001] The present invention relates to the technical field of braking energy consumption optimization, and particularly to a method and system for optimizing the braking energy consumption of rail train operation. Background Art

[0002] With the continuous increase in the demand for rail transportation, the braking energy consumption optimization technology of rail trains has received extensive attention and application in the field of rail transit. However, with the increase in train operating speed, the extension of operating lines, and the continuous rise in energy costs, the energy consumption management of rail trains faces greater challenges. Traditional braking energy recovery methods have many deficiencies in energy consumption optimization, including low energy recovery efficiency, inaccurate prediction of recovery potential, etc., resulting in a large amount of kinetic energy waste during the energy recovery process and making it difficult to achieve efficient energy utilization. Summary of the Invention

[0003] This application provides a method and system for optimizing the braking energy consumption of rail train operation, which is used to solve the technical problem that kinetic energy is wasted during the energy recovery process in the prior art, resulting in low energy utilization efficiency.

[0004] In view of the above problems, this application provides a method and system for optimizing the braking energy consumption of rail train operation.

[0005] In the first aspect of this application, a method for optimizing the braking energy consumption of rail train operation is provided. The method includes:

[0006] According to the train operation control terminal, load the predetermined operation plan of the target rail train, and decompose the predetermined operation plan into stations to generate multiple node operation plans. Among them, the target rail train includes multiple braking energy recovery devices; based on the multiple node operation plans, predict the braking energy recovery potential of the target rail train according to the ARIMA-LSTM combined model to obtain multiple node regenerative braking energies; based on the multiple node regenerative braking energies, respectively perform energy recovery scheduling on the multiple braking energy recovery devices to establish multiple node braking energy recovery scheduling spaces; based on multiple braking energy recovery evaluation factors, construct a braking energy recovery evaluation component, where the multiple braking energy recovery evaluation factors include braking energy recovery efficiency, braking energy recovery safety, and braking energy recovery stability; based on the braking energy recovery evaluation component, perform optimization analysis on the multiple node braking energy recovery scheduling spaces respectively according to the constraint of the number of optimization times for recovery scheduling to obtain multiple node energy recovery optimization strategies; encrypt and send the multiple node energy recovery optimization strategies to the train operation control terminal, and the train operation control terminal performs braking energy recovery on the target rail train according to the multiple braking energy recovery devices and the multiple node energy recovery optimization strategies.

[0007] In the second aspect of the present application, a braking energy consumption optimization system for the operation of an orbital train is provided. The system includes:

[0008] A node operation plan generation module, which loads a predetermined operation plan of a target orbital train according to the train operation control terminal and decomposes the predetermined operation plan into stations to generate a plurality of node operation plans. Among them, the target orbital train includes a plurality of braking energy recovery devices; a recovery potential prediction module, which predicts the braking energy recovery potential of the target orbital train based on the plurality of node operation plans according to the ARIMA-LSTM combined model to obtain a plurality of node regenerative braking energies; an energy recovery scheduling module, which respectively performs energy recovery scheduling on the plurality of braking energy recovery devices based on the plurality of node regenerative braking energies to establish a plurality of node braking energy recovery scheduling spaces; an evaluation component construction module, which constructs a braking energy recovery evaluation component based on multiple braking energy recovery evaluation factors. Among them, the multiple braking energy recovery evaluation factors include braking energy recovery efficiency, braking energy recovery safety, and braking energy recovery stability; an optimization analysis module, which performs optimization analysis on the plurality of node braking energy recovery scheduling spaces respectively according to the recovery scheduling optimization times constraint based on the braking energy recovery evaluation component to obtain a plurality of node energy recovery optimization strategies; a braking energy recovery module, which encrypts and sends the plurality of node energy recovery optimization strategies to the train operation control terminal, and the train operation control terminal performs braking energy recovery on the target orbital train according to the plurality of braking energy recovery devices and the plurality of node energy recovery optimization strategies.

[0009] One or more technical solutions provided in the present application have at least the following technical effects or advantages:

[0010] According to the train operation control terminal, this application loads the predetermined operation plan of the target track train, decomposes the predetermined operation plan by stations, and generates multiple node operation plans. Among them, the target track train includes multiple braking energy recovery devices; based on the multiple node operation plans, the braking energy recovery potential of the target track train is predicted according to the ARIMA-LSTM combined model to obtain multiple node regenerative braking energies; based on the multiple node regenerative braking energies, the energy recovery scheduling of multiple braking energy recovery devices is respectively carried out to establish multiple node braking energy recovery scheduling spaces; based on multiple braking energy recovery evaluation factors, a braking energy recovery evaluation component is constructed. Among them, the multiple braking energy recovery evaluation factors include braking energy recovery efficiency, braking energy recovery safety, and braking energy recovery stability; based on the braking energy recovery evaluation component, optimization analysis is respectively carried out on multiple node braking energy recovery scheduling spaces according to the constraints of the number of recovery scheduling optimization times to obtain multiple node energy recovery optimization strategies; the multiple node energy recovery optimization strategies are encrypted and sent to the train operation control terminal, and the train operation control terminal performs braking energy recovery on the target track train according to multiple braking energy recovery devices and multiple node energy recovery optimization strategies. The present invention solves the technical problem that kinetic energy is wasted in the prior art during the energy recovery process, resulting in low energy utilization rate. By loading the operation plan through the train operation control terminal, predicting the braking energy recovery potential using the model, optimizing the scheduling of the energy recovery devices at each node, and performing optimization analysis on the scheduling space based on the evaluation component, and transmitting the optimization strategy to the control terminal, efficient and stable energy recovery of the track train is realized, achieving the technical effect of improving the energy utilization rate. Brief Description of the Drawings

[0011] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0012] Figure 1 Schematic flow chart of the braking energy consumption optimization method for the operation of the track train provided by the embodiment of this application;

[0013] Figure 2 Schematic structural diagram of the braking energy consumption optimization system for the operation of the track train provided by the embodiment of this application.

[0014] Description of the reference numerals: Node operation plan generation module 11, recovery potential prediction module 12, energy recovery scheduling module 13, evaluation component construction module 14, optimization analysis module 15, braking energy recovery module 16. Detailed Embodiments

[0015] The present application provides a method and system for optimizing the braking energy consumption of a rail train. Aiming at solving the technical problem in the prior art that there is kinetic energy waste during the energy recovery process, resulting in low energy utilization rate, a running plan is loaded through the train operation control terminal, the braking energy recovery potential is predicted by using a model, the energy recovery devices at each node are scheduled and optimized, and the scheduling space is optimized and analyzed based on an evaluation component. Then, the optimization strategy is transmitted to the control terminal to achieve efficient and stable energy recovery of the rail train and improve the energy utilization rate.

[0016] Next, the technical solutions in the embodiments of the present application will be clearly and completely described with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without creative efforts shall fall within the protection scope of the present application.

[0017] It should be noted that any variations of the terms "including" and "having" are intended to cover non-exclusive inclusions. For example, a process, method, system, product or server that includes a series of steps or units does not necessarily have to be limited to those clearly listed steps or units, but may include other steps or modules that are not clearly listed or are inherent to these processes, methods, products or devices.

[0018] Embodiment 1, as Figure 1 shown, the present application provides a method for optimizing the braking energy consumption of a rail train, and the method includes:

[0019] Step S100: According to the train operation control terminal, load the predetermined operation plan of the target rail train, and decompose the predetermined operation plan by stations to generate multiple node operation plans, where the target rail train includes multiple braking energy recovery devices.

[0020] In the embodiment of the present application, the train operation control terminal loads the predetermined operation plan before starting to run, that is, the planned route, speed, stopping stations and operation instructions to be executed. After loading the predetermined operation plan, it is decomposed by stations, and the entire running process is split into multiple relatively independent running nodes according to stations. Each node represents the process of the train from one station to the next station, specifically including operations such as acceleration, deceleration, and constant speed in this section. Through this process, multiple node operation plans are generated.

[0021] The target rail train includes multiple braking energy recovery devices, and relies on these devices to recover braking energy. These devices convert the excess kinetic energy generated during braking into electrical energy, which is then stored or reused. The braking energy recovery device includes an electric braking system and a supercapacitor energy storage device. The electric braking system brakes through a generator, converts kinetic energy into electrical energy, and then feeds it back to the train power grid. The supercapacitor energy storage device utilizes the characteristics of rapid charging and discharging of supercapacitors to quickly store the electrical energy generated during braking and release it when needed to support subsequent train acceleration or other high-energy consumption requirements.

[0022] Step S200: Based on the multiple node operation plans, predict the braking energy recovery potential of the target rail train according to the ARIMA-LSTM combined model to obtain the regenerative braking energy of multiple nodes.

[0023] In the embodiment of the present application, first, based on multiple node operation plans, load prediction is performed on the target rail train to generate predicted load data for each node. Next, historical braking energy recovery records are retrieved to construct a sample node operation plan set, a sample node train load set, and a sample node train recovered braking energy set. Based on these sample data, joint learning is performed on the ARIMA model and the LSTM model respectively to build a braking energy recovery potential prediction channel. This channel can capture the energy recovery potential of the train during braking, identify and predict the regenerative braking energy of each node. Finally, the multiple node operation plans and the predicted loads are input into this channel to obtain the regenerative braking energy of multiple nodes.

[0024] Further, in the method provided by the embodiment of the application, predicting the braking energy recovery potential of the target rail train according to the ARIMA-LSTM combined model based on the multiple node operation plans to obtain the regenerative braking energy of multiple nodes further includes:

[0025] Performing load prediction on the target rail train based on the multiple node operation plans to obtain the predicted loads of multiple node trains; retrieving the braking energy recovery records of the target rail train to obtain a sample node operation plan set, a sample node train load set, and a sample node train recovered braking energy set; the ARIMA-LSTM combined model includes an ARIMA model and an LSTM model; based on the sample node operation plan set, the sample node train load set, and the sample node train recovered braking energy set, performing joint learning on the ARIMA model and the LSTM model to build a braking energy recovery potential prediction channel; inputting the multiple node operation plans and the predicted loads of multiple node trains into the braking energy recovery potential prediction channel to obtain the regenerative braking energy of multiple nodes.

[0026] In the embodiment of the present application, first, the load of the rail train is predicted based on the operation plans of multiple nodes. Here, the historical data mean method is used for load prediction. Specifically, the load data of the same time period and section in the past seven days are extracted from the historical database. Then, the obtained seven-day load data are averaged to obtain the predicted load of each node. In this way, the predicted load data of multiple nodes are generated.

[0027] Next, to generate the training data set of the ARIMA-LSTM model, the braking energy recovery records of the target rail train are retrieved, and the sample node operation plan set, the sample node train load set, and the sample node train recovered braking energy set of the target rail train are obtained from the historical database. The sample node operation plan set records the actual operation plans of the target rail train at each historical node. The sample node train load set corresponds to the actual load data of the train at each historical node. The sample node train recovered braking energy set is the energy data recovered during the actual braking process at the corresponding node.

[0028] Subsequently, in the process of predicting the braking energy recovery potential of the rail train, an ARIMA-LSTM combined model is used. This model is composed of an ARIMA model and an LSTM model, and the prediction of the energy recovery potential is realized through joint learning. Specifically, first, based on the sample node operation plan set, the sample node train load set, and the sample node train recovered braking energy set, the ARIMA and LSTM models are jointly trained. Among them, the ARIMA model takes the sample node operation plan set and the sample node train load set as inputs and the sample node train recovered braking energy set as the output, and the ARIMA model is supervised and trained to obtain the first model for predicting the recovery potential, which is used for predicting the trend of the load. The LSTM model also takes the sample node operation plan set and the sample node train load set as inputs and the sample node train recovered braking energy set as the output, and the LSTM model is trained to enable it to identify and capture the non-linear relationships in the data, thereby generating the second model for predicting the recovery potential.

[0029] After the training of the ARIMA and LSTM models is completed, the outputs of the two models are integrated into a fused training data set, and further training and testing are carried out in combination with the sample node train recovered braking energy set, so as to obtain the fused model for predicting the recovery potential. Finally, the ARIMA and LSTM models are used as the first-level nodes, and the fused model is used as the second-level node, and these nodes are connected to construct a prediction channel for the braking energy recovery potential.

[0030] Finally, the operation plans and predicted load data of multiple nodes are input into this prediction channel, and the regenerative braking energy of each node is output to obtain the regenerative braking energy of multiple nodes.

[0031] Further, in the method provided by the application embodiment, based on the sample node operation scenario set, the sample node train load set, and the sample node train recovered braking energy set, joint learning is performed on the ARIMA model and the LSTM model to build a braking energy recovery potential prediction channel, and it further includes:

[0032] Taking the sample node operation scenario set and the sample node train load set as input information, and the sample node train recovered braking energy set as output information, performing supervised training on the ARIMA model to obtain a first recovery potential prediction model; performing supervised training on the LSTM model according to the sample node operation scenario set, the sample node train load set, and the sample node train recovered braking energy set to obtain a second recovery potential prediction model; collecting the output data of the first recovery potential prediction model and the second recovery potential prediction model to obtain a fusion training data set; performing training and testing according to the fusion training data set and the sample node train recovered braking energy set to obtain a recovery potential prediction fusion model; taking the first recovery potential prediction model and the second recovery potential prediction model as the first-level nodes of the braking energy recovery potential prediction, and taking the recovery potential prediction fusion model as the second-level node of the braking energy recovery potential prediction; connecting the first-level nodes of the braking energy recovery potential prediction and the second-level node of the braking energy recovery potential prediction to generate the braking energy recovery potential prediction channel.

[0033] In the embodiment of the present application, first, taking the sample node operation scenario set and the sample node train load set as input data, and the sample node train recovered braking energy set as output data, supervised training is performed on the ARIMA model. The ARIMA model generates a first recovery potential prediction model by identifying trends and seasonal variations in the time series, which is used to predict the energy recovery trend of the train during braking.

[0034] Next, the LSTM model is trained, using the same sample node operation scenario set and train load set as input, and the sample node train recovered braking energy set as output. The LSTM model can handle non-linear and complex time series features. By learning the relationship between the load and energy recovery, it generates a second recovery potential prediction model, which is used to capture the short-term fluctuations and non-linear features between the train load and energy recovery.

[0035] After the training of the ARIMA and LSTM models is completed, the output data of these two models are collected to form a fused training dataset. Then, using the fused training dataset as the input and combining the sample node train regenerative braking energy set as the target output, a fused model is trained. This fused model is trained using a multi-layer perceptron (MLP) model to achieve an optimal balance between different model outputs. Through cross-validation, the prediction effect of the fused model is tested and verified to ensure that it has a high generalization ability for the energy recovery potential of different nodes, thereby obtaining a fused model for predicting the recovery potential.

[0036] When constructing the prediction channel for the regenerative braking energy recovery potential, the ARIMA and LSTM models are set as the first-level nodes to capture the trend and non-linear features in the data respectively, and the fused model for predicting the recovery potential is used as the second-level node to integrate the outputs of the first-level nodes and improve the overall prediction accuracy. The connection between the first-level node and the second-level node constitutes the prediction channel for the regenerative braking energy recovery potential.

[0037] Step S300: Based on the regenerative braking energy of the multiple nodes, perform energy recovery scheduling for the multiple braking energy recovery devices respectively to establish a braking energy recovery scheduling space for the multiple nodes.

[0038] In the embodiment of the present application, based on the regenerative braking energy of multiple nodes, energy recovery scheduling is performed for multiple braking energy recovery devices node by node to construct a braking energy recovery scheduling space for multiple nodes. Specifically, first, extract the regenerative braking energy of each node, such as the q-th node, and collect the energy storage characteristic parameters of each recovery device to generate an energy storage characteristic dataset. Then, taking the regenerative braking energy of this node as the scheduling target and combining the energy storage characteristic dataset, make an energy recovery decision for multiple recovery devices to form a corresponding scheduling space.

[0039] After constructing the scheduling space for each node, check whether the number of decisions in the scheduling space of this node meets the preset quantity constraint. If the constraint condition is met, add this scheduling space to the overall multi-node scheduling space; if not, expand the scheduling scheme based on the scheduling target and the energy storage characteristic data. Finally, through the above process, a braking energy recovery scheduling space for multiple nodes is obtained.

[0040] Furthermore, in the method provided by the embodiment of the application, based on the regenerative braking energy of the multiple nodes, performing energy recovery scheduling for the multiple braking energy recovery devices respectively to establish a braking energy recovery scheduling space for the multiple nodes further includes:

[0041] Regenerate braking energy according to the multiple nodes, extract the regenerative braking energy of the q-th node, where q is a positive integer; collect the energy storage characteristic parameters of the multiple braking energy recovery devices to obtain an energy storage characteristic data set; use the regenerative braking energy of the q-th node as the energy recovery scheduling target, and make an energy recovery decision on the multiple braking energy recovery devices according to the energy storage characteristic data set to obtain the braking energy recovery scheduling space of the q-th node; collect the decision quantity parameter of the braking energy recovery scheduling space of the q-th node to obtain the decision quantity of the q-th space; determine whether the decision quantity of the q-th space meets the decision quantity constraint; if the decision quantity of the q-th space meets the decision quantity constraint, add the braking energy recovery scheduling space of the q-th node to the braking energy recovery scheduling spaces of the multiple nodes; if the decision quantity of the q-th space does not meet the decision quantity constraint, based on the decision quantity constraint, make a decision expansion on the braking energy recovery scheduling space of the q-th node according to the energy recovery scheduling target and the energy storage characteristic data set.

[0042] In the embodiment of the present application, first, the currently processed node, such as the regenerative braking energy of the q-th node, is extracted from the regenerative braking energy data of multiple nodes, and it is used as the energy recovery scheduling target of this node. Through a query operation, the specific energy value of the q-th node is directly obtained from the regenerative braking energy data set. Wherein, q is a positive integer.

[0043] Next, the energy storage characteristic parameters of all braking energy recovery devices of this node are obtained from a preset database, and an energy storage characteristic data set is formed, including information such as the energy storage capacity, charging rate, and current energy storage level of each device.

[0044] After obtaining the scheduling objectives and energy storage characteristic datasets of the q-th node, energy allocation is performed through a constrained optimization algorithm to construct the braking energy recovery scheduling space of the q-th node. Here, the energy demand of the q-th node is taken as the core optimization objective, and a series of constraints are set for each recovery device on this basis. Specifically, first, ensure that the allocated energy of each recovery device does not exceed its maximum energy storage capacity. This constraint ensures that the energy storage device will not be overloaded during the energy recovery process. Second, the constraint on the charging rate ensures that the charging rate of each device is within the range allowed by the device to prevent overheating or damage to the device caused by too high a charging rate. In addition, considering the current energy storage state of each device, a quota is set for energy allocation based on the existing energy storage level to avoid energy waste caused by full energy storage. These constraints are preset by technical experts. Under the framework of the above optimization objectives and constraints, this information is input into the constrained optimization algorithm. Through the solution process of the algorithm, the optimal energy allocation scheme that satisfies all constraints is searched under the defined conditions. This process uses optimization methods such as the gradient descent method or the interior point method. Through these solution techniques, the best solution for energy allocation is found under multiple constraints. After the solution is completed, multiple eligible recovery scheduling decisions are generated. Each decision represents an energy allocation combination, and these combinations together constitute the braking energy recovery scheduling space of the q-th node.

[0045] Subsequently, calculate the decision number parameter in the scheduling space of the q-th node, that is, the total number of feasible recovery scheduling schemes in this scheduling space. This parameter is obtained through statistical calculation. Compare this decision number parameter with the preset decision number constraint to ensure that the number of schemes in the scheduling space is sufficient to cope with different energy demands. If the decision number meets the constraint requirements, add the scheduling space of the q-th node to the overall braking energy recovery scheduling space of multiple nodes, which means that the energy recovery scheduling of this node has been successfully completed.

[0046] If the decision number of the q-th node does not meet the preset requirements, use the heuristic extension method to expand the decision of the scheduling space of this node. During the expansion process, increase the decision number by generating new recovery scheduling combinations. For example, use genetic algorithms or simulated annealing algorithms to generate more allocation schemes to ensure sufficient scheduling scheme support under diverse recovery demands. Through these extension techniques, improve the number and diversity of scheduling schemes, so as to maintain high flexibility in different energy recovery scenarios.

[0047] Through the above process, gradually construct the braking energy recovery scheduling space including all nodes. The scheduling space of each node contains multiple recovery scheduling decisions.

[0048] Step S400: Based on multiple braking energy recovery evaluation factors, construct a braking energy recovery evaluation component, where the multiple braking energy recovery evaluation factors include braking energy recovery efficiency, braking energy recovery safety, and braking energy recovery stability.

[0049] In the embodiments of the present application, the multiple braking energy recovery evaluation factors include braking energy recovery efficiency, braking energy recovery safety, and braking energy recovery stability. First, perform importance analysis according to these three evaluation factors to obtain the key coefficients of each factor, and based on these key coefficients, allocate weights to each factor to construct a weighted network, that is, a braking energy recovery evaluation weighted network.

[0050] On the basis of the weighted network, further train three network models for predicting different evaluation factors to obtain a braking energy recovery efficiency prediction network, a braking energy recovery safety prediction network, and a braking energy recovery stability prediction network. Set these networks as the first-level nodes to evaluate the performance of each factor respectively. Then connect these first-level nodes to the second-level node, and the second-level node is the weighted network, serving as the comprehensive evaluation output node. Through the connection of the first-level nodes and the second-level nodes, a braking energy recovery evaluation component is finally formed.

[0051] Furthermore, in the method provided by the embodiments of the application, based on multiple braking energy recovery evaluation factors, constructing a braking energy recovery evaluation component further includes:

[0052] Perform importance evaluation according to the multiple braking energy recovery evaluation factors to obtain multiple evaluation factor key coefficients; allocate weights to the multiple braking energy recovery evaluation factors according to the multiple evaluation factor key coefficients to establish a braking energy recovery evaluation weighted network; based on the multiple braking energy recovery evaluation factors, train a braking energy recovery efficiency prediction network, a braking energy recovery safety prediction network, and a braking energy recovery stability prediction network; use the braking energy recovery efficiency prediction network, the braking energy recovery safety prediction network, and the braking energy recovery stability prediction network as the first-level nodes of the braking energy recovery evaluation; use the braking energy recovery evaluation weighted network as the second-level node of the braking energy recovery evaluation; connect the first-level nodes and the second-level nodes of the braking energy recovery evaluation to generate the braking energy recovery evaluation component.

[0053] In the embodiments of the present application, first, an importance evaluation is performed on the multi - factor braking energy recovery evaluation factors to determine the relative importance of each factor. Here, the multiple linear regression method is adopted, and through regression analysis, the influence degree of each factor on the overall energy recovery effect of the system is determined. Specifically, the historical data of three factors, namely recovery efficiency, safety, and stability, are used as independent variables, and the overall energy recovery performance, such as the recovery rate, is used as the dependent variable for multiple linear regression analysis. After the regression model is generated, the regression coefficient of each factor is obtained. The larger the regression coefficient, the greater the influence of the factor on the system performance. Finally, based on the regression coefficients, the key coefficients of each factor are determined. For example, if the regression coefficient of the recovery efficiency is 0.7, the safety is 0.2, and the stability is 0.1, then the recovery efficiency has the highest importance and the relatively larger key coefficient. Through this process, the key coefficients of multiple evaluation factors are obtained.

[0054] Next, according to the key coefficients of multiple evaluation factors, weight distribution is performed on the multi - factor braking energy recovery evaluation factors, and on this basis, a weighted network for braking energy recovery evaluation is established. The construction of the weighted network is based on the weighted summation method, and the key coefficients are directly used as the weight parameters of the weighted network to ensure that each factor is reflected in the final comprehensive score according to its importance. For example, the key coefficient of the recovery efficiency is 0.7, which is used as the weight of the recovery efficiency factor in the weighted network; similarly, the weights of the safety and stability factors are 0.2 and 0.1 respectively. Through this weight distribution, the influence of each factor is reasonably integrated in the comprehensive evaluation.

[0055] After the weighted network is established, three independent prediction networks are trained respectively, namely the braking energy recovery efficiency prediction network, the braking energy recovery safety prediction network, and the braking energy recovery stability prediction network. Each network is used to independently predict the performance of the corresponding factor. These networks are all neural network models. During the training process, the historical data of each factor are input into the corresponding network for training. Through the backpropagation algorithm and the gradient descent method, the parameters of the network are optimized and adjusted to enable the network to accurately predict the recovery efficiency, safety, and stability scores. The output of each prediction network represents the factor scores under different conditions, providing a basis for the subsequent comprehensive evaluation.

[0056] Afterwards, the above three prediction networks are used as first-level nodes, and each first-level node outputs the recycling efficiency, safety, and stability scores respectively. Then, these scores are input into the braking energy recovery evaluation weighted network of the second-level node. As the second-level node, the role of the weighted network is to perform a weighted sum of the scores of each factor according to their weights to output a comprehensive evaluation score. Specifically, the weighted network multiplies the scores output by the first-level nodes by the corresponding weights respectively. For example, the recycling efficiency score is multiplied by 0.7, safety by 0.2, and stability by 0.1, and these results are added together to obtain an overall evaluation score. This score reflects the comprehensive performance of the recycling device.

[0057] By connecting the first-level nodes and the second-level nodes, the construction of the braking energy recovery evaluation component is finally completed.

[0058] Step S500: Based on the braking energy recovery evaluation component, perform an optimization analysis on the braking energy recovery scheduling spaces of the multiple nodes respectively according to the recycling scheduling optimization times constraint to obtain multiple node energy recovery optimization strategies.

[0059] In the embodiment of the present application, based on the braking energy recovery evaluation component, an optimization analysis is performed on the braking energy recovery scheduling space of each node respectively to generate an energy recovery optimization strategy for each node. In this process, an independent optimization operation is performed on the scheduling space of each node in sequence, such as the q-th node. Specifically, an initial scheduling scheme, i.e., the m-th scheme, is randomly extracted from the scheduling space of the q-th node, and the energy recovery performance of this scheme is calculated using the evaluation component to obtain its evaluation coefficient. Subsequently, the next scheduling scheme, i.e., the m + 1-th scheme, is extracted from the scheduling space, its evaluation coefficient is calculated and compared with the previous scheme, and the current winning scheme is selected as the new benchmark.

[0060] This process is repeated within the scheduling space of each node, continuously extracting new schemes from the scheduling space for evaluation and comparison, and gradually optimizing the performance of the scheduling strategy. During the iteration process, according to the preset recycling scheduling optimization times constraint, the best scheduling scheme is searched for within the limited number of iteration times. When the number of optimization times reaches the constraint condition, the optimal scheme of this node is determined as its energy recovery optimization strategy. This optimization process is performed on the scheduling spaces of all nodes in sequence, and finally an independent energy recovery optimization strategy is generated for each node, and these strategies are summarized to obtain multiple node energy recovery optimization strategies.

[0061] Furthermore, in the method provided by the embodiment of the application, performing an optimization analysis on the braking energy recovery scheduling spaces of the multiple nodes respectively according to the recycling scheduling optimization times constraint to obtain multiple node energy recovery optimization strategies further includes:

[0062] According to the braking energy recovery scheduling space of the q-th node, randomly extract the m-th braking energy recovery scheduling decision, where m is a positive integer; based on the braking energy recovery evaluation component, conduct a recovery prediction evaluation on the m-th braking energy recovery scheduling decision to obtain the m-th braking energy recovery evaluation coefficient; according to the braking energy recovery scheduling space of the q-th node, extract the (m + 1)-th braking energy recovery scheduling decision, and combine it with the braking energy recovery evaluation component to calculate the (m + 1)-th braking energy recovery evaluation coefficient; based on the m-th braking energy recovery evaluation coefficient and the (m + 1)-th braking energy recovery evaluation coefficient, conduct a winning identification on the m-th braking energy recovery scheduling decision and the (m + 1)-th braking energy recovery scheduling decision to obtain the current winning recovery scheduling decision; based on the braking energy recovery evaluation component, continue to perform iterative optimization on the current winning recovery scheduling decision according to the braking energy recovery scheduling space of the q-th node until the number of iterative optimization times meets the recovery scheduling optimization times constraint, and generate the q-th node energy recovery optimization strategy; add the q-th node energy recovery optimization strategy to the multiple node energy recovery optimization strategies.

[0063] In the embodiment of the present application, when optimizing the braking energy recovery scheduling space of the q-th node, first randomly extract an m-th braking energy recovery scheduling decision, where m is a positive integer, and use the braking energy recovery evaluation component to conduct a recovery prediction evaluation on this decision to obtain the m-th braking energy recovery evaluation coefficient. Specifically, extract the operation plan of the q-th node according to the operation plans of multiple nodes, and model the target rail train to obtain the target train model. Based on this model and the m-th scheduling decision, conduct a braking energy recovery simulation to obtain the energy recovery performance data of the m-th decision. Subsequently, input these data into the first-level node of the evaluation component, and calculate the recovery efficiency prediction coefficient, recovery safety prediction coefficient, and recovery stability prediction coefficient. These coefficients reflect the energy recovery performances of the m-th plan, and are comprehensively weighted processed at the second-level node of the evaluation component to output a comprehensive score, that is, the m-th braking energy recovery evaluation coefficient.

[0064] After obtaining the evaluation coefficient of the m-th plan, continue to extract the next scheduling decision from the scheduling space of the q-th node, that is, the (m + 1)-th scheduling decision, and calculate its (m + 1)-th braking energy recovery evaluation coefficient through the same process. Compare the evaluation coefficients of the m-th and (m + 1)-th plans, and record the scheduling plan with a higher score as the current winning recovery scheduling decision.

[0065] Within the scheduling space of the q-th node, iterative optimization is performed based on the current winning solution. By continuously extracting new solutions, calculating their evaluation coefficients, and comparing them with the current winning solution, the scheduling decision is gradually optimized, and the solution with the highest score is always retained. This process is carried out under the constraint of the preset number of iterations for the recovery scheduling optimization. When the number of iterations reaches the upper limit, the current winning solution is determined as the energy recovery optimization strategy for the q-th node.

[0066] Finally, the optimal strategy of this node is added to the set of energy recovery optimization strategies for multiple nodes. The same optimization analysis is performed on all nodes in sequence to ensure finding the energy recovery strategy with the best overall performance among multiple nodes.

[0067] Furthermore, in the method provided by the application embodiment, based on the braking energy recovery evaluation component, a recovery prediction evaluation is performed on the m-th braking energy recovery scheduling decision to obtain the m-th braking energy recovery evaluation coefficient, and it further includes:

[0068] According to the operation plans of the multiple nodes, the operation plan of the q-th node is extracted; based on the target rail train, a target train model is established; based on the operation plan of the q-th node, according to the m-th braking energy recovery scheduling decision, a braking energy recovery simulation is performed on the target train model to obtain the m-th decision energy recovery simulation data set; the m-th decision energy recovery simulation data set is input into the first-level node of the braking energy recovery evaluation to obtain the m-th recovery efficiency prediction coefficient, the m-th recovery safety prediction coefficient, and the m-th recovery stability prediction coefficient; the m-th recovery efficiency prediction coefficient, the m-th recovery safety prediction coefficient, and the m-th recovery stability prediction coefficient are input into the second-level node of the braking energy recovery evaluation, and the m-th braking energy recovery evaluation coefficient is output.

[0069] In the embodiment of the present application, first, according to the operation plans of multiple nodes, the operation plan of the q-th node is extracted. The operation plan of the q-th node provides the operation conditions and task parameters of this node, laying a foundation for subsequent energy recovery evaluation.

[0070] Next, based on the specific attributes of the target rail train, a model is established, and a target train model is built. This model includes the physical characteristics of the train during braking, including information such as mass, speed, braking force, and the configuration of the energy recovery device, ensuring that the model can accurately reflect the energy conversion behavior of the train during operation.

[0071] Based on the operation plan of the q-th node, the m-th braking energy recovery scheduling decision is applied to simulate the braking energy recovery of the target train model, thereby generating an m-th decision energy recovery simulation dataset. This dataset records the energy recovery performance under the m-th scheduling decision and contains multiple energy recovery indicators, such as data on recovery efficiency, safety, and stability, providing specific performance data support for subsequent evaluation. Then, the generated m-th decision energy recovery simulation dataset is input into the first-level node of the braking energy recovery evaluation component. The first-level node calculates the performance of the scheme in terms of recovery efficiency, safety, and stability respectively, and outputs the corresponding m-th recovery efficiency prediction coefficient, m-th recovery safety prediction coefficient, and m-th recovery stability prediction coefficient. These prediction coefficients respectively quantify the effects of this decision in terms of energy recovery efficiency, safety, and operation stability, providing sub-item support for comprehensive evaluation.

[0072] Finally, the m-th recovery efficiency prediction coefficient, m-th recovery safety prediction coefficient, and m-th recovery stability prediction coefficient are input into the second-level node of the evaluation component, and the second-level node performs comprehensive weighted calculation to output the m-th braking energy recovery evaluation coefficient.

[0073] Step S600: Encrypt and send the multiple node energy recovery optimization strategies to the train operation control end, and the train operation control end performs braking energy recovery on the target rail train according to the multiple braking energy recovery devices and the multiple node energy recovery optimization strategies.

[0074] In the embodiment of the present application, first, the multiple node energy recovery optimization strategies are encrypted to ensure that the data is not intercepted or tampered with during the transmission process. The encryption process uses a symmetric encryption algorithm (such as AES) or an asymmetric encryption algorithm (such as RSA) to generate a key and convert the energy recovery strategies of each node into encrypted data packets. The encrypted data packets ensure that they can only be decrypted and read at the authorized control end.

[0075] After encryption is completed, the encrypted data packets are sent to the train operation control end, and the data security during the transmission process is further ensured through a secure transmission protocol, such as a TLS or VPN channel. After reaching the control end, the operation control end decrypts the data with the shared decryption key to restore the original multiple node energy recovery optimization strategies.

[0076] After the operation control end obtains and decrypts the data, combined with the actual configuration and status of the multiple braking energy recovery devices, it gradually applies the energy recovery strategy of each node to perform braking energy recovery operations on the target rail train, ensuring the optimal energy recovery effect at each node.

[0077] In the embodiment of the present application, in summary, the embodiment of the present application has at least the following technical effects:

[0078] This application loads a predetermined operation plan for a target track train according to the train operation control terminal, decomposes the predetermined operation plan by stations, and generates multiple node operation plans. Among them, the target track train includes multiple braking energy recovery devices; based on the multiple node operation plans, the braking energy recovery potential of the target track train is predicted according to the ARIMA-LSTM combined model to obtain multiple node regenerative braking energies; based on the multiple node regenerative braking energies, the energy recovery scheduling of multiple braking energy recovery devices is performed respectively to establish multiple node braking energy recovery scheduling spaces; based on multiple braking energy recovery evaluation factors, a braking energy recovery evaluation component is constructed. Among them, the multiple braking energy recovery evaluation factors include braking energy recovery efficiency, braking energy recovery safety, and braking energy recovery stability; based on the braking energy recovery evaluation component, the optimization analysis of multiple node braking energy recovery scheduling spaces is performed respectively according to the constraints of the number of times of recovery scheduling optimization to obtain multiple node energy recovery optimization strategies; the multiple node energy recovery optimization strategies are encrypted and sent to the train operation control terminal, and the train operation control terminal performs braking energy recovery on the target track train according to the multiple braking energy recovery devices and the multiple node energy recovery optimization strategies. The present invention solves the technical problem in the prior art that there is kinetic energy waste during the energy recovery process, resulting in low energy utilization rate. By loading the operation plan by the train operation control terminal, predicting the braking energy recovery potential using the model, optimizing the scheduling of the energy recovery devices at each node, and performing optimization analysis on the scheduling space based on the evaluation component, and transmitting the optimization strategy to the control terminal, the efficient and stable energy recovery of the track train is realized, and the technical effect of improving the energy utilization rate is achieved.

[0079] Embodiment 2, based on the same inventive concept as the braking energy consumption optimization method for the operation of the track train in the foregoing embodiment, as Figure 2 shown, this application provides a braking energy consumption optimization system for the operation of the track train. The system in the embodiment of this application and the method embodiment are based on the same inventive concept. Among them, the system includes:

[0080] Node operation plan generation module 11, which loads the predetermined operation plan of the target track train according to the train operation control terminal and decomposes the predetermined operation plan by stations to generate multiple node operation plans. Among them, the target track train includes multiple braking energy recovery devices; Recovery potential prediction module 12, which predicts the braking energy recovery potential of the target track train based on the multiple node operation plans according to the ARIMA-LSTM combined model to obtain multiple node regenerative braking energies; Energy recovery scheduling module 13, which schedules the energy recovery of the multiple braking energy recovery devices respectively based on the multiple node regenerative braking energies to establish multiple node braking energy recovery scheduling spaces; Evaluation component construction module 14, which constructs a braking energy recovery evaluation component based on multiple braking energy recovery evaluation factors. Among them, the multiple braking energy recovery evaluation factors include braking energy recovery efficiency, braking energy recovery safety, and braking energy recovery stability; Optimization analysis module 15, which performs optimization analysis on the multiple node braking energy recovery scheduling spaces respectively according to the recovery scheduling optimization times constraint based on the braking energy recovery evaluation component to obtain multiple node energy recovery optimization strategies; Braking energy recovery module 16, which encrypts and sends the multiple node energy recovery optimization strategies to the train operation control terminal, and the train operation control terminal performs braking energy recovery on the target track train according to the multiple braking energy recovery devices and the multiple node energy recovery optimization strategies.

[0081] Further, the system is also used to implement the following functions:

[0082] Based on the multiple node operation plans, perform load prediction on the target track train to obtain multiple node train predicted loads; Retrieve the braking energy recovery records of the target track train to obtain a sample node operation plan set, a sample node train load set, and a sample node train recovered braking energy set; The ARIMA-LSTM combined model includes an ARIMA model and an LSTM model; Based on the sample node operation plan set, the sample node train load set, and the sample node train recovered braking energy set, perform joint learning on the ARIMA model and the LSTM model to build a braking energy recovery potential prediction channel; Input the multiple node operation plans and the multiple node train predicted loads into the braking energy recovery potential prediction channel to obtain the multiple node regenerative braking energies.

[0083] Further, the system is also used to implement the following functions:

[0084] Taking the sample node operation scenario set and the sample node train load set as input information, and the sample node train regenerative braking energy set as output information, the ARIMA model is supervised and trained to obtain the first model for predicting the recovery potential; according to the sample node operation scenario set, the sample node train load set and the sample node train regenerative braking energy set, the LSTM model is supervised and trained to obtain the second model for predicting the recovery potential; the output data of the first model for predicting the recovery potential and the second model for predicting the recovery potential are collected to obtain a fusion training data set; according to the fusion training data set and the sample node train regenerative braking energy set, training and testing are carried out to obtain a fusion model for predicting the recovery potential; taking the first model for predicting the recovery potential and the second model for predicting the recovery potential as the first-level nodes for predicting the braking energy recovery potential, and the fusion model for predicting the recovery potential as the second-level node for predicting the braking energy recovery potential; connecting the first-level nodes for predicting the braking energy recovery potential and the second-level node for predicting the braking energy recovery potential to generate the prediction channel for the braking energy recovery potential.

[0085] Further, the system is also used to implement the following functions:

[0086] According to the regenerative braking energy of the multiple nodes, the regenerative braking energy of the q-th node is extracted, where q is a positive integer; the energy storage characteristic parameters of the multiple braking energy recovery devices are collected to obtain an energy storage characteristic data set; taking the regenerative braking energy of the q-th node as the energy recovery scheduling target, according to the energy storage characteristic data set, energy recovery decisions are made for the multiple braking energy recovery devices to obtain the braking energy recovery scheduling space of the q-th node; the decision quantity parameter of the braking energy recovery scheduling space of the q-th node is collected to obtain the decision quantity of the q-th space; it is judged whether the decision quantity of the q-th space meets the decision quantity constraint; if the decision quantity of the q-th space meets the decision quantity constraint, the braking energy recovery scheduling space of the q-th node is added to the braking energy recovery scheduling spaces of the multiple nodes; if the decision quantity of the q-th space does not meet the decision quantity constraint, based on the decision quantity constraint, according to the energy recovery scheduling target and the energy storage characteristic data set, the braking energy recovery scheduling space of the q-th node is decision-expanded.

[0087] Further, the system is also used to implement the following functions:

[0088] Perform importance evaluation based on the multi - element braking energy recovery evaluation factors to obtain key coefficients of multiple evaluation factors; perform weight allocation on the multi - element braking energy recovery evaluation factors according to the key coefficients of the multiple evaluation factors to establish a weighted network for braking energy recovery evaluation; train a braking energy recovery efficiency prediction network, a braking energy recovery safety prediction network, and a braking energy recovery stability prediction network based on the multi - element braking energy recovery evaluation factors; use the braking energy recovery efficiency prediction network, the braking energy recovery safety prediction network, and the braking energy recovery stability prediction network as the first - level nodes for braking energy recovery evaluation; use the weighted network for braking energy recovery evaluation as the second - level node for braking energy recovery evaluation; connect the first - level nodes for braking energy recovery evaluation and the second - level node for braking energy recovery evaluation to generate the braking energy recovery evaluation component.

[0089] Furthermore, the system is also used to implement the following functions:

[0090] Randomly extract the m - th braking energy recovery scheduling decision according to the braking energy recovery scheduling space of the q - th node, where m is a positive integer; perform recovery prediction evaluation on the m - th braking energy recovery scheduling decision based on the braking energy recovery evaluation component to obtain the m - th braking energy recovery evaluation coefficient; extract the (m + 1) - th braking energy recovery scheduling decision according to the braking energy recovery scheduling space of the q - th node, and calculate the (m + 1) - th braking energy recovery evaluation coefficient in combination with the braking energy recovery evaluation component; perform a winner identification on the m - th braking energy recovery scheduling decision and the (m + 1) - th braking energy recovery scheduling decision based on the m - th braking energy recovery evaluation coefficient and the (m + 1) - th braking energy recovery evaluation coefficient to obtain the current winning recovery scheduling decision; continue to perform iterative optimization on the current winning recovery scheduling decision based on the braking energy recovery evaluation component according to the braking energy recovery scheduling space of the q - th node until the number of iterative optimization times meets the constraint of the recovery scheduling optimization times, and generate the energy recovery optimization strategy for the q - th node; add the energy recovery optimization strategy for the q - th node to the energy recovery optimization strategies of the multiple nodes.

[0091] Furthermore, the system is also used to implement the following functions:

[0092] According to the multiple node operation schemes, extract the operation scheme of the q-th node; based on the target rail train, perform modeling to obtain a target train model; based on the operation scheme of the q-th node, according to the m-th braking energy recovery scheduling decision, perform braking energy recovery simulation on the target train model to obtain the m-th decision energy recovery simulation data set; input the m-th decision energy recovery simulation data set into the first-level node of braking energy recovery evaluation to obtain the m-th recovery efficiency prediction coefficient, the m-th recovery safety prediction coefficient, and the m-th recovery stability prediction coefficient; input the m-th recovery efficiency prediction coefficient, the m-th recovery safety prediction coefficient, and the m-th recovery stability prediction coefficient into the second-level node of braking energy recovery evaluation to output the m-th braking energy recovery evaluation coefficient.

[0093] It should be noted that the above sequence of embodiments of the present application is only for description and does not represent the superiority or inferiority of the embodiments. And the above describes specific embodiments of this specification. The processes depicted in the drawings do not necessarily require the specific order and continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0094] The above are only the preferred embodiments of the present application and are not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application shall be included within the protection scope of the present application.

[0095] This specification and the drawings are only exemplary descriptions of the present application and are considered to have covered any and all modifications, variations, combinations, or equivalents within the scope of the present application. Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalent technologies, the present application is intended to include these changes and modifications.

Claims

1. A method for optimizing braking energy consumption of a rail vehicle, characterized in that: The method comprises: According to the train operation control terminal, a predetermined operation plan of a target rail train is loaded, and the predetermined operation plan is decomposed into stations to generate multiple node operation plans, wherein the target rail train includes multiple braking energy recovery devices; Based on the multiple node operation schemes, predict the braking energy recovery potential of the target rail train according to the ARIMA-LSTM combined model to obtain the regenerative braking energy of multiple nodes; Based on the regenerative braking energy of the multiple nodes, respectively perform energy recovery scheduling on the multiple braking energy recovery devices to establish multiple node braking energy recovery scheduling spaces; Based on the multivariate braking energy recovery evaluation factors, a braking energy recovery evaluation component is constructed, wherein the multivariate braking energy recovery evaluation factors include braking energy recovery efficiency, braking energy recovery safety and braking energy recovery stability; Based on the braking energy recovery evaluation component, the plurality of node braking energy recovery scheduling spaces are respectively optimized and analyzed according to the recovery scheduling optimization number constraint to obtain the plurality of node energy recovery optimization strategies; The multiple node energy recovery optimization strategies are encrypted and sent to the train operation control terminal, and the train operation control terminal performs braking energy recovery on the target rail train according to the multiple braking energy recovery devices and the multiple node energy recovery optimization strategies.

2. The method according to claim 1, characterized in that Based on the multiple node operation schemes, the braking energy recovery potential of the target rail train is predicted according to the ARIMA-LSTM combined model to obtain the regenerative braking energy of multiple nodes, including: Perform load prediction on the target rail train based on the multiple node operation plans to obtain multiple node train predicted loads; Retrieving the braking energy recovery record of the target rail train to obtain a sample node operation plan set, a sample node train load set, and a sample node train recovery braking energy set; The ARIMA-LSTM combined model includes an ARIMA model and an LSTM model; Based on the sample node operation scheme set, the sample node train load set and the sample node train recovery braking energy set, the ARIMA model and the LSTM model are jointly learned to build a braking energy recovery potential prediction channel; The multiple node operation plans and the multiple node train predicted loads are input into the braking energy recovery potential prediction channel to obtain the multiple node regenerative braking energies.

3. The method according to claim 2, characterized in that Based on the sample node operation scheme set, the sample node train load set and the sample node train recovery braking energy set, the ARIMA model and the LSTM model are jointly learned to build a braking energy recovery potential prediction channel, including: Taking the sample node operation scheme set and the sample node train load set as input information and the sample node train recovery braking energy set as output information, the ARIMA model is supervised and trained to obtain a first recovery potential prediction model; Performing supervised training on the LSTM model according to the sample node operation scheme set, the sample node train load set, and the sample node train recovery braking energy set to obtain a second recovery potential prediction model; Collecting output data of the first recycling potential prediction model and the second recycling potential prediction model to obtain a fusion training data set; Training and testing are performed according to the fused training data set and the sample node train recovery braking energy set to obtain a recovery potential prediction fusion model; The first recovery potential prediction model and the second recovery potential prediction model are used as a first-level node for braking energy recovery potential prediction, and the recovery potential prediction fusion model is used as a second-level node for braking energy recovery potential prediction; The braking energy recovery potential prediction primary node and the braking energy recovery potential prediction secondary node are connected to generate the braking energy recovery potential prediction channel.

4. The method according to claim 1, characterized in that Based on the regenerative braking energy of the multiple nodes, respectively performing energy recovery scheduling on the multiple braking energy recovery devices, and establishing multiple node braking energy recovery scheduling spaces, including: Extracting the qth node regenerative braking energy according to the plurality of node regenerative braking energies, wherein q is a positive integer; Collecting energy storage characteristic parameters of the plurality of braking energy recovery devices to obtain an energy storage characteristic data set; Taking the regenerative braking energy of the qth node as the energy recovery scheduling target, making energy recovery decisions for the multiple braking energy recovery devices according to the energy storage characteristic data set, and obtaining the braking energy recovery scheduling space of the qth node; Collecting the decision quantity parameter of the qth node braking energy recovery scheduling space to obtain the qth space decision quantity; Determine whether the qth spatial decision quantity satisfies the decision quantity constraint; If the qth spatial decision quantity satisfies the decision quantity constraint, adding the qth node braking energy recovery scheduling space to the multiple node braking energy recovery scheduling spaces; If the qth spatial decision quantity does not satisfy the decision quantity constraint, based on the decision quantity constraint, the qth node braking energy recovery scheduling space is expanded according to the energy recovery scheduling target and the energy storage characteristic data set.

5. The method according to claim 1, characterized in that Based on the multivariate braking energy recovery evaluation factors, a braking energy recovery evaluation component is constructed, including: Performing importance evaluation according to the multivariate braking energy recovery evaluation factors to obtain multiple evaluation factor key coefficients; Allocating weights to the multivariate braking energy recovery evaluation factors according to the multiple evaluation factor key coefficients to establish a braking energy recovery evaluation weighted network; Based on the multivariate braking energy recovery evaluation factor, training a braking energy recovery efficiency prediction network, a braking energy recovery safety prediction network, and a braking energy recovery stability prediction network; The braking energy recovery efficiency prediction network, the braking energy recovery safety prediction network and the braking energy recovery stability prediction network are used as the first-level nodes for braking energy recovery evaluation; The braking energy recovery evaluation weighted network is used as a braking energy recovery evaluation secondary node; The braking energy recovery evaluation primary node and the braking energy recovery evaluation secondary node are connected to generate the braking energy recovery evaluation component.

6. The method according to claim 1, characterized in that Based on the braking energy recovery evaluation component, the plurality of node braking energy recovery scheduling spaces are respectively optimized and analyzed according to the recovery scheduling optimization number constraint, and a plurality of node energy recovery optimization strategies are obtained, including: According to the qth node braking energy recovery scheduling space, randomly extract the mth braking energy recovery scheduling decision, where m is a positive integer; Based on the braking energy recovery evaluation component, a recovery prediction evaluation is performed on the m-th braking energy recovery scheduling decision to obtain an m-th braking energy recovery evaluation coefficient; Extracting the m+1th braking energy recovery scheduling decision according to the qth node braking energy recovery scheduling space, and calculating the m+1th braking energy recovery evaluation coefficient in combination with the braking energy recovery evaluation component; Based on the mth braking energy recovery evaluation coefficient and the m+1th braking energy recovery evaluation coefficient, the mth braking energy recovery scheduling decision and the m+1th braking energy recovery scheduling decision are identified as superior to obtain a current superior recovery scheduling decision; Based on the braking energy recovery evaluation component, the current winning recovery scheduling decision is continuously iterated and optimized according to the q-th node braking energy recovery scheduling space until the number of iterative optimizations meets the recovery scheduling optimization number constraint, thereby generating the q-th node energy recovery optimization strategy; The q-th node energy recovery optimization strategy is added to the multiple node energy recovery optimization strategies.

7. The method according to claim 6, characterized in that Based on the braking energy recovery evaluation component, a recovery prediction evaluation is performed on the m-th braking energy recovery scheduling decision to obtain the m-th braking energy recovery evaluation coefficient, including: Extracting the qth node operation plan according to the multiple node operation plans; Modeling is performed based on the target track train to obtain a target train model; Based on the qth node operation plan, performing a braking energy recovery simulation on the target train model according to the mth braking energy recovery scheduling decision to obtain an mth decision energy recovery simulation data set; Inputting the mth decision energy recovery simulation data set into the first-level node of braking energy recovery evaluation to obtain the mth recovery efficiency prediction coefficient, the mth recovery safety prediction coefficient and the mth recovery stability prediction coefficient; The mth recovery efficiency prediction coefficient, the mth recovery safety prediction coefficient and the mth recovery stability prediction coefficient are input into a braking energy recovery evaluation secondary node, and the mth braking energy recovery evaluation coefficient is output.

8. A braking energy consumption optimization system for rail train operation, characterized in that: The system comprises: A node operation plan generation module, wherein the node operation plan generation module loads a predetermined operation plan of a target rail train according to a train operation control terminal, and performs station decomposition on the predetermined operation plan to generate a plurality of node operation plans, wherein the target rail train includes a plurality of braking energy recovery devices; A recovery potential prediction module, wherein the recovery potential prediction module predicts the braking energy recovery potential of the target rail train based on the multiple node operation schemes and according to an ARIMA-LSTM combined model to obtain the regenerative braking energy of multiple nodes; An energy recovery scheduling module, wherein the energy recovery scheduling module performs energy recovery scheduling on the multiple braking energy recovery devices based on the regenerative braking energy of the multiple nodes, and establishes multiple node braking energy recovery scheduling spaces; An evaluation component construction module, wherein the evaluation component construction module constructs a braking energy recovery evaluation component based on a multivariate braking energy recovery evaluation factor, wherein the multivariate braking energy recovery evaluation factor includes braking energy recovery efficiency, braking energy recovery safety, and braking energy recovery stability; An optimization analysis module, wherein the optimization analysis module performs optimization analysis on the multiple node braking energy recovery scheduling spaces based on the braking energy recovery evaluation component and according to the recovery scheduling optimization number constraint to obtain multiple node energy recovery optimization strategies; A braking energy recovery module, wherein the braking energy recovery module encrypts the multiple node energy recovery optimization strategies and sends them to the train operation control terminal, and the train operation control terminal performs braking energy recovery on the target rail train according to the multiple braking energy recovery devices and the multiple node energy recovery optimization strategies.

Images