Traction energy-saving method and system based on dynamic load flow calculation for rail transit, electronic equipment and readable storage medium

Abstract

The invention discloses a traction energy-saving method and system based on dynamic load flow calculation for rail transit, electronic equipment and a readable storage medium, and the traction energy-saving method comprises the steps: planning a multi-vehicle collaborative energy-saving module through an ATO single-vehicle energy-saving + ATS working diagram, a dynamic diagram adjustment module according to passenger flow requirements, a regenerative braking energy feedback module and other modules; multi-dimensional coupling conditions of power supply, vehicles, signals, tracks and the like are dynamically analyzed, dynamic load flow calculation is performed from the perspective of energy flow through a dynamic load flow calculation and analysis module of the traction power supply system, technical means such as ATO energy saving, ATS energy saving and regenerative braking energy recovery device energy saving are dynamically coordinated, unified management and cooperative linkage are performed, and the dynamic load flow calculation and analysis module of the traction power supply system is realized. Energy consumption monitoring and statistical analysis are carried out for different traction energy-saving measures, and long-term energy-saving operation effect tracking and evaluation are carried out; and an energy-saving control strategy is continuously adjusted and optimized according to an analysis result through a prediction model between line energy consumption and operation data variables, so that a better energy-saving effect in a real sense is achieved.

Description

Technical Field

[0001] The present invention relates to the field of traction energy saving in rail transit systems, and in particular to a traction energy saving method, system, electronic equipment and readable storage medium based on dynamic power flow calculation in rail transit. Background Art

[0002] After several years of rapid development, rail transit has gradually transitioned from the high-speed construction period to the high-quality operation stage. During the high-speed construction period, the main consideration was how to ensure operational efficiency and safety, and basically no consideration was given to how to operate in an energy-saving manner.

[0003] According to statistics released by the China Urban Transportation Association, the total power consumption of urban rail in 2023 is 24.977 billion kWh, and the power consumption continues to show an upward trend, with huge consumption. Among them, traction power consumption accounts for 50-60%, station electromechanical power consumption accounts for 30-35%, and traction and electromechanical power consumption accounts for more than 80% of the total energy consumption. In the field of energy-saving research on rail transit systems, the energy-saving plans of various disciplines are in a small-scale, single-discipline pilot stage, and the energy-saving measures of various disciplines are separated. The overall energy-saving design has not been carried out from the perspective of power system energy flow. Sometimes energy-saving measures will increase more energy consumption. Therefore, further research is needed.

[0004] It should be understood that the above statements merely provide background technology related to the present invention and do not necessarily constitute prior art. Summary of the invention

[0005] Based on the aforementioned technical problems, the purpose of the present invention is to provide a traction energy-saving method, system, electronic device and readable storage medium for rail transit based on dynamic power flow calculation. The traction energy-saving method is based on dynamic analysis of multi-dimensional coupling conditions such as power supply, vehicles, signals, tracks, etc., and performs dynamic power flow calculation from the perspective of energy flow. It dynamically coordinates technical means such as ATO energy saving, ATS energy saving, and regenerative braking energy recovery device energy saving, and performs unified management and coordinated linkage. It monitors energy consumption and conducts statistical analysis on different traction energy-saving measures, tracks and evaluates long-term energy-saving operation effects, and continuously optimizes energy-saving control strategies based on analysis results, thereby achieving truly better energy-saving effects.

[0006] In order to achieve the above object, the present invention is implemented by the following technical solutions:

[0007] A traction energy-saving method for rail transit based on dynamic power flow calculation, comprising:

[0008] S1. Collecting rail transit real-time operation data through a rail transit real-time data module, wherein the rail transit real-time operation data includes real-time passenger flow data;

[0009] S2. Based on the real-time operation data of rail transit, the ATO energy-saving curve is obtained through the ATO single-vehicle energy-saving + ATS operation diagram planning multi-vehicle collaborative energy-saving module, the passenger flow data of the day is predicted through the passenger flow time series prediction module, and the dynamic diagram adjustment module according to the passenger flow requirements is based on the real-time passenger flow data collected in S1 and the passenger flow data of the day predicted by the passenger flow time series prediction module. The operation diagram of the day is dynamically adjusted to obtain an updated operation diagram, and the regenerative braking energy recovery device startup mechanism based on the updated operation diagram is obtained through the regenerative braking energy feedback module; the first operation strategy is formed based on the ATO energy-saving curve, the updated operation diagram, the startup mechanism of the regenerative braking energy recovery device and the predicted passenger flow data of the day;

[0010] S3, the traction power supply system power flow dynamic calculation and analysis module dynamically records and analyzes the distribution of trains corresponding to the first operation strategy in the power supply partition, the relationship between the traction braking moment and energy consumption of the train ATO energy-saving curve, and the total actual energy consumption data based on the first operation strategy;

[0011] S4. Optimizing the first operation strategy through a prediction model between line energy consumption and operation data variables to obtain a second operation strategy;

[0012] S5. The traction power supply system power flow dynamic calculation and analysis module dynamically records and analyzes the distribution of trains corresponding to the second operation strategy in the power supply partition, the relationship between the traction braking moment and energy consumption of the train ATO energy-saving curve, and the total actual energy consumption data based on the second operation strategy;

[0013] S6. Compare the total actual energy consumption data corresponding to the first operation strategy with the total actual energy consumption data corresponding to the second operation strategy. When the total actual energy consumption data corresponding to the second operation strategy is lower than the total actual energy consumption data corresponding to the first operation strategy, operate according to the second operation strategy.

[0014] Optionally, in S6, when the total actual energy consumption data corresponding to the second operating strategy is higher than the total actual energy consumption data corresponding to the first operating strategy, the first operating strategy is regenerated through step S2, and steps S3 to S6 are repeated until the total actual energy consumption data corresponding to the second operating strategy is lower than the total actual energy consumption data corresponding to the first operating strategy.

[0015] Optionally, the traction power supply system power flow dynamic calculation and analysis module performs analysis based on the traction power supply system power flow dynamic calculation, which specifically includes:

[0016] By real-time monitoring of traction power supply mode, traction power supply voltage, dynamic position and weight of the train, a dynamic circuit relationship between traction power supply and train is established;

[0017] The substation is equivalent to a power source, the overhead line is equivalent to a resistor, the train in traction state is equivalent to a resistor, and the train in braking state is equivalent to a power source. The entire section is divided into several sections. Under the condition of a dynamically moving train, the relationship between voltage, resistance, current, power and energy consumption in different sections is defined;

[0018] Real-time calculation of the power flow of the traction power supply system by real-time monitoring of traction voltage and current, train power consumption and energy feedback, and dynamic distribution of trains;

[0019] The total actual energy consumption data is collected through the power supply system and trains, and the distribution of trains in power supply areas and the relationship between the traction braking moment and energy consumption of the train ATO energy-saving curve are dynamically recorded and analyzed.

[0020] Optionally, in S2, the working method of the ATO single-vehicle energy saving + ATS operation diagram planning multi-vehicle collaborative energy saving module includes:

[0021] Based on the speed deviation of train operation, each ATO energy-saving curve is divided into multiple checkpoints, and each checkpoint records different ATO train control parameters. When the train passes a checkpoint, ATO comprehensively considers the remaining time at the station and the upstream and downstream operation curves to calculate the appropriate ATO target speed.

[0022] Train idling resistance is identified based on big data analysis, specifically different trains with different loads at different kilometer marker positions; idling resistance is known in advance through data accumulation and cleaning;

[0023] Use convex optimization models and algorithms to perform offline planning of energy-saving speed curves;

[0024] By adjusting the surplus time, the train section running time is adjusted, the utilization rate of the train regenerative braking energy is improved, the energy-saving operation diagram is optimized, and the train is automatically adjusted;

[0025] Through ATO single-vehicle energy saving + ATS operation diagram planning multi-vehicle collaborative technology, the dynamic energy consumption of single vehicle + multiple vehicles can be optimized.

[0026] Optionally, in S2, obtaining a regenerative braking energy recovery device start-up mechanism based on an operation diagram through a regenerative braking energy feedback module includes:

[0027] Based on the updated operation diagram, the train interval running time, station stop time and return time are optimized, and the simulated annealing intelligent algorithm technology is used to solve the large-scale transportation optimization problem with multiple constraints in complex networks, so that the entry and exit operation time of trains running in the same and / or adjacent power supply sections can overlap to the greatest extent, so that the outgoing trains can fully utilize the braking regeneration energy of the incoming trains;

[0028] Taking advantage of the predictability of the operating parameters of the signal system, a prediction algorithm is used to coordinate with the regenerative braking energy recovery device. When the running train is about to start braking, the regenerative braking energy recovery device is notified in advance, and the regenerative braking energy recovery device is immediately started to recover electric energy while the train is braking.

[0029] Based on the above, a regenerative braking energy recovery device activation mechanism based on the updated operation diagram is obtained.

[0030] Optionally, in S4, based on the real-time operation data of rail transit and the predicted passenger flow data of the day, the prediction model between the line energy consumption and the operation data variables is optimized in combination with the transportation plan;

[0031] The updated operation diagram and ATO energy-saving curve obtained in S2 are used as initial candidate solutions of the optimized prediction model between the line energy consumption and the operation data variables, and the updated operation diagram and ATO energy-saving curve are optimized to form a second operation strategy.

[0032] Optionally, the prediction model between the line energy consumption and the operation data variables can be expressed as:

[0033] E=f DNN (t_start i,j,k ,t_stop i,j,k ,t_hold i,j,k ,ato_curve i,j,k ,

[0034] weight k ,slope i,j ,p_flow i ,weather,E_brakingenergyi) 1＜i,j＜n,1＜k＜m

[0035] ato_curve i,j,k ∈Set_ato (1)

[0036] Among them, f DNN represents the deep neural network model function, E represents the line energy consumption, i and j represent the index of the i-th and j-th stations respectively, there are n stations in total, k represents the k-th train, there are m trains in total, t_start i,j,k , t_stop i,j,k , t_hold i,j,k 、ato_curve i,j,k They represent the departure time, arrival time, stop time at the jth station and the ATO energy-saving curve between stations of the kth train from the ith station to the jth station, Set_ato represents the ATO curve set, and weight krepresents the weight of the kth train, slope i,j represents the slope between the i-th station and the j-th station, p_flow i represents the passenger flow of the ith station, weather represents whether it is rainy or snowy, E_brakingenergy i It represents the energy recovered by the linkage between the i-th station signal and the regenerative braking energy recovery device.

[0037] Optionally, based on the real-time operation data of rail transit and the predicted passenger flow of the day, the prediction model between the optimized line energy consumption and the operation data variables is expressed as:

[0038]

[0039] in, is the optimized line energy consumption, t_start i,j,k ′、t_stop i,j,k ′、t_hold i,j,k ′ respectively represent the real-time departure time, arrival time, and stop time of the kth train from the ith station to the jth station, ato_curve i,j,k ′ is the inter-station ATO energy-saving curve obtained in S2.

[0040] Optionally, also include:

[0041] The health and abnormal energy consumption of train equipment are monitored through the abnormal energy consumption analysis module, and an alarm signal is issued when the abnormal energy consumption analysis module detects abnormal energy consumption.

[0042] Optionally, a traction energy-saving system for rail transit based on dynamic power flow calculation is used to implement the aforementioned traction energy-saving method for rail transit based on dynamic power flow calculation, the traction energy-saving system comprises a rail transit real-time data module and a business knowledge module,

[0043] The rail transit real-time data module is used to collect rail transit real-time operation data, and the rail transit real-time operation data includes real-time passenger flow data;

[0044] The business knowledge module includes:

[0045] ATO single-vehicle energy saving + ATS operation diagram planning multi-vehicle collaborative energy saving module, which is used to obtain the preliminary ATO energy saving curve;

[0046] Passenger flow time series prediction module, which is used to predict the passenger flow data of the day;

[0047] Energy-saving module for dynamically adjusting the diagram according to passenger flow requirements, which is used to obtain the operation diagram;

[0048] A regenerative braking energy feedback module, which is used to obtain a regenerative braking energy recovery device start-up mechanism based on an operation diagram;

[0049] The dynamic calculation and analysis module of the traction power supply system flow, which dynamically records and analyzes the distribution of the corresponding trains in the power supply partition, the relationship between the traction braking moment and energy consumption of the train ATO energy-saving curve based on the operation strategy, and obtains the total actual energy consumption data corresponding to the operation strategy;

[0050] A prediction model between line energy consumption and operating data variables is used to optimize the operation strategy.

[0051] Optionally, also include:

[0052] The big data module is used to store operation data.

[0053] Optionally, also include:

[0054] The equipment health and abnormal energy consumption analysis module is used to monitor the health and abnormal energy consumption of train equipment. When the abnormal energy consumption analysis module detects abnormal energy consumption, an alarm signal can be issued.

[0055] Optionally, the business knowledge module can establish the ATO single-vehicle energy saving + ATS operation diagram planning multi-vehicle collaborative energy saving module, the passenger flow time series prediction module, the dynamic diagram adjustment energy saving module according to passenger flow requirements, the regenerative braking energy feedback module, the traction power supply system flow dynamic calculation and analysis module and the prediction model between line energy consumption and operation data variables through knowledge graph technology.

[0056] Optionally, an electronic device comprises: a memory and a processor, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the steps of the aforementioned rail transit traction energy-saving method based on dynamic power flow calculation are implemented.

[0057] Optionally, a readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the aforementioned rail transit traction energy-saving method based on dynamic power flow calculation are implemented.

[0058] Compared with the prior art, the present invention has the following advantages:

[0059] In a traction energy-saving method, system, electronic device and readable storage medium for rail transit based on dynamic power flow calculation of the present invention, the traction energy-saving method is based on dynamic analysis of multi-dimensional coupling conditions such as power supply, vehicles, signals, tracks, etc., dynamic power flow calculation is performed from the perspective of energy flow, and technical means such as ATO energy saving, ATS energy saving, and regenerative braking energy recovery device energy saving are dynamically coordinated to perform unified management and coordinated linkage, and energy consumption monitoring and statistical analysis are performed for different traction energy-saving measures, and long-term energy-saving operation effect tracking and evaluation are performed, and energy-saving control strategies are continuously optimized according to the analysis results, so as to achieve truly better energy-saving effects. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] In order to more clearly illustrate the technical solution of the present invention, the following briefly introduces the drawings required for the description. Obviously, the drawings described below are an embodiment of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work:

[0061] Figure 1 It is a schematic diagram of a traction energy-saving method for rail transit based on dynamic power flow calculation according to the present invention;

[0062] Figure 2 An equivalent circuit diagram for traction power flow calculation of the present invention;

[0063] Figure 3 A schematic diagram of the coordinated linkage between a regenerative braking energy recovery device and a signal system of the present invention;

[0064] Figure 4 It is a schematic diagram of a traction energy-saving system of rail transit based on dynamic power flow calculation of the present invention. DETAILED DESCRIPTION

[0065] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0066] It should be noted that, in this article, the terms "include", "comprises", "has" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or terminal device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or terminal device. In the absence of further restrictions, the elements defined by the sentence "includes..." or "comprising..." do not exclude the existence of other elements in the process, method, article or terminal device including the elements.

[0067] It should be noted that the drawings are all in very simplified form and use inaccurate ratios, and are only used to conveniently and clearly assist in explaining the embodiments of the present invention.

[0068] like Figure 1 FIG. 1 is a schematic diagram of a traction energy-saving method for rail transit based on dynamic power flow calculation according to the present invention, the method comprising:

[0069] S1. Collecting rail transit real-time operation data through a rail transit real-time data module, wherein the rail transit real-time operation data includes real-time passenger flow data;

[0070] S2. Based on the real-time operation data of rail transit, the ATO energy-saving curve is obtained through the ATO single-vehicle energy-saving + ATS operation diagram planning multi-vehicle collaborative energy-saving module, the passenger flow data of the day is predicted through the passenger flow time series prediction module, and the dynamic diagram adjustment module according to the passenger flow requirements is based on the real-time passenger flow data collected in S1 and the passenger flow data of the day predicted by the passenger flow time series prediction module. The operation diagram of the day is dynamically adjusted to obtain an updated operation diagram, and the regenerative braking energy recovery device startup mechanism based on the updated operation diagram is obtained through the regenerative braking energy feedback module; the first operation strategy is formed based on the ATO energy-saving curve, the updated operation diagram, the startup mechanism of the regenerative braking energy recovery device and the predicted passenger flow data of the day;

[0071] S3, the traction power supply system power flow dynamic calculation and analysis module dynamically records and analyzes the distribution of trains corresponding to the first operation strategy in the power supply partition, the relationship between the traction braking moment and energy consumption of the train ATO energy-saving curve, and the total actual energy consumption data based on the first operation strategy;

[0072] S4. Optimizing the first operation strategy through a prediction model between line energy consumption and operation data variables to obtain a second operation strategy;

[0073] S5. The traction power supply system power flow dynamic calculation and analysis module dynamically records and analyzes the distribution of trains corresponding to the second operation strategy in the power supply partition, the relationship between the traction braking moment and energy consumption of the train ATO energy-saving curve, and the total actual energy consumption data based on the second operation strategy;

[0074] S6. Compare the total actual energy consumption data corresponding to the first operation strategy with the total actual energy consumption data corresponding to the second operation strategy. When the total actual energy consumption data corresponding to the second operation strategy is lower than the total actual energy consumption data corresponding to the first operation strategy, operate according to the second operation strategy. That is, determine whether the second operation strategy after the prediction model between line energy consumption and operation data variables is more optimized than the existing first operation strategy. If it is more optimized, that is, more energy-saving, operate according to the new operation strategy.

[0075] From the above, it can be seen that in the traction energy-saving method of rail transit based on dynamic power flow calculation of the present invention, through the ATO single-vehicle energy-saving + ATS operation diagram planning multi-vehicle collaborative energy-saving module, the dynamic diagram adjustment module according to passenger flow requirements and the regenerative braking energy feedback module and other modules, the power supply, vehicle, signal, track and other multi-dimensional coupling conditions are dynamically analyzed, and the traction power supply system power flow dynamic calculation and analysis module is used to perform dynamic power flow calculation from the perspective of energy flow, dynamically coordinate ATO energy saving, ATS energy saving, regenerative braking energy recovery device energy saving and other technical means, and carry out unified management and coordinated linkage, and carry out energy consumption monitoring and statistical analysis for different traction energy-saving measures, and track and evaluate the long-term energy-saving operation effect; and through the prediction model between line energy consumption and operation data variables, the energy-saving control strategy is continuously optimized according to the analysis results, so as to achieve a truly better energy-saving effect.

[0076] Furthermore, in S6, when the total actual energy consumption data corresponding to the second operation strategy is higher than the total actual energy consumption data corresponding to the first operation strategy, the first operation strategy is regenerated through step S2, and steps S3 to S6 are repeated until the total actual energy consumption data corresponding to the second operation strategy is lower than the total actual energy consumption data corresponding to the first operation strategy. Based on the above continuous cycle process, the energy-saving strategy can be continuously optimized to ensure energy-saving operation of the entire system.

[0077] On the other hand, the present invention conducts dynamic calculation and analysis of the traction power supply dynamic flow through the dynamic relationship between the traction power supply system and the train operation, and considers the energy-saving problem from the perspective of the flow, so as to effectively integrate various energy-saving measures and effectively plan the energy-saving measures as a whole.

[0078] The dynamic calculation and analysis module of the traction power supply system flow is analyzed based on the dynamic calculation of the traction power supply system flow, which specifically includes: establishing a dynamic circuit relationship between the traction power supply and the train through real-time monitoring of the traction power supply mode (double-sided, single-sided, large double-sided, etc.), traction power supply voltage, dynamic position and weighing of the train and other information; treating the substation as a power source, the contact network as a resistor, the train in the traction state as a resistor, and the train in the braking state as a power source, dividing the entire section into several sections (for example, one section every 100 meters, and other parameters can also be set), and defining the relationship between the voltage, resistance, current, power and energy consumption of different sections under the condition of a dynamically moving train; calculating the flow of the traction power supply system in real time by real-time monitoring of the traction voltage and current, the train power consumption and energy feedback, and the dynamic distribution of the train; collecting the total actual energy consumption data through the power supply system and the train, dynamically recording and analyzing the distribution of the train in the power supply partition, and the relationship between the traction braking moment and energy consumption of the train ATO energy-saving curve, to provide a theoretical basis and verification method for subsequent energy-saving strategies. Figure 2 As shown in the figure, it is an equivalent circuit diagram of traction power flow calculation of the present invention, in which U represents power supply and R represents resistance. Based on this method, combined with real-time driving information, dynamic calculation and analysis of power flow of traction power supply system is performed. Of course, the dynamic calculation and analysis module of power flow of traction power supply system of the present invention is not limited to Figure 2 The traction power supply system power flow dynamic calculation is performed in the manner described above for analysis. In other embodiments, other methods may also be used, and the present invention is not limited to this.

[0079] In the S2, the ATO single-vehicle energy saving + ATS operation diagram planning multi-vehicle collaborative energy saving module gives a preliminary ATO energy saving curve by combining the train operation interval with the line basic data simulation. Furthermore, it realizes multi-vehicle coordination through the overall planning of the ATS operation diagram, achieving the energy-saving effect of single-vehicle + multi-vehicle operation. Specifically, the working method of the ATO single-vehicle energy saving + ATS operation diagram planning multi-vehicle collaborative energy saving module includes: based on the speed deviation of the train operation, each ATO energy-saving curve, that is, the operation curve or the speed curve is divided by multiple checkpoints, that is, multiple segmentation checkpoints are set on each ATO energy-saving curve, and each checkpoint records different ATO vehicle control parameters; when the train passes a checkpoint, the ATO comprehensively considers the remaining time of the station and the upstream and downstream operation curves, and dynamically calculates the appropriate ATO target speed to minimize the number of traction and braking times of the train; train idling resistance identification based on big data analysis Identification, specifically different trains with different loads at different kilometer mark positions; know the idling resistance in advance through data accumulation and cleaning; use convex optimization (ConvexOptimization) models and algorithms to perform offline planning of energy-saving speed curves; adjust the train interval operation time by adjusting the use of surplus time, improve the utilization rate of train regenerative braking energy, optimize the energy-saving operation diagram, and automatically adjust the train according to different situations, where surplus time includes time for stops and return operations; optimize the dynamic energy consumption of single vehicles + multiple vehicles through ATO single vehicle energy saving + ATS operation diagram planning multi-vehicle collaborative technology. It can be understood that the ATO single vehicle energy saving + ATS operation diagram planning multi-vehicle collaborative energy saving module is not limited to realizing its corresponding functions through the above-mentioned methods, and it can also realize the corresponding functions through other methods.

[0080] Furthermore, in S2, the passenger flow data of the day is predicted by the passenger flow time series prediction module. In practical applications, the passenger flow time series prediction module can be established based on the historical passenger flow data in the big data module using the ARIMA algorithm, and the passenger flow of the day can be predicted based on the passenger flow obtained by the real-time data center. Of course, the passenger flow time series prediction module can also be established in other ways, and the present invention does not limit this.

[0081] Furthermore, in S2, the dynamic timetable adjustment module required by passenger flow is based on the real-time passenger flow data collected in S1 and the passenger flow data of the day predicted by the passenger flow time series prediction module. On the premise of meeting the operating indicators, it changes the existing fixed running mode according to the timetable, dynamically analyzes the passenger flow data in real time, and dynamically adjusts the running diagram of the day according to the passenger flow data to obtain an updated running diagram and realize running according to the passenger flow.

[0082] Furthermore, in S2, the regenerative braking energy feedback module makes full use of the real-time traction braking status information of the train controlled by the signal system, coordinates the operation of trains in the same power supply section, and starts the regenerative braking energy recovery device to recover energy when the traction system voltage dV / dt begins to increase, thereby making full use of the regenerative braking energy and avoiding the regenerative braking energy being consumed by the train resistance.

[0083] Specifically, the regenerative braking energy recovery device startup mechanism based on the operation diagram obtained through the regenerative braking energy feedback module includes: based on the updated operation diagram, optimizing the train interval operation time, station stop time and return time, using simulated annealing intelligent algorithm technology to solve the large-scale transportation optimization problem with multiple constraints in complex networks, so that the entry and exit operation time of trains running in the same and / or adjacent power supply sections overlap to the greatest extent, so that the outgoing train can make full use of the braking regeneration energy of the incoming train, effectively reduce the traction energy consumption of the outgoing train, and achieve a better energy-saving solution for the entire line. Based on the above, the regenerative braking energy feedback module achieves a maximum balance between acceleration and braking by coordinating trains in the same power supply section, so that the energy generated by braking can be used by the accelerated train to the maximum extent.

[0084] Furthermore, the regenerative braking energy recovery module utilizes the predictability of the operating parameters of the signal system, adopts a prediction algorithm to coordinate with the regenerative braking energy recovery device, and notifies the regenerative braking energy recovery device when the running train is about to start braking, and immediately starts the regenerative braking energy recovery device to recover electric energy while maintaining the train braking, rather than starting after the voltage is higher than a certain level, thereby avoiding a large amount of energy being absorbed by the braking resistor; based on the above, a regenerative braking energy recovery device startup mechanism based on the updated operation diagram is obtained. Figure 3 FIG. 1 is a schematic diagram of the coordinated linkage between the regenerative braking energy recovery device and the signal system in one embodiment of the present invention. It is understandable that the coordinated linkage between the regenerative braking energy recovery device and the signal system is not limited to Figure 3 In other embodiments, other methods may be used as long as the corresponding functions can be achieved, and the present invention does not limit this.

[0085] The prediction model between line energy consumption and operating data variables in S4 is based on the historical operating data stored in the big data module, including line energy consumption, ATS operation diagram, single-vehicle ATO operation curve, train weighing, line slope morphology, passenger flow, climate information, regenerative braking energy recovery start mechanism, etc., and uses a deep neural network to establish a prediction model between line energy consumption and other operating data variables. The prediction model between line energy consumption and operating data variables can be expressed as:

[0086] E=f DNN (t_start i,j,k ,t_stopi,j,k ,t_hold i,j,k ,ato_curve i,j,k ,

[0087] weight k ,slope i,j ,p_flow i ,weather,E_brakingenergy i ) 1＜i,j＜n,1＜k＜m

[0088] ato_curve i,j,k ∈Set_ato (1)

[0089] Among them, f DNN represents the deep neural network model function, E represents the line energy consumption, i and j represent the index of the i-th and j-th stations respectively, there are n stations in total, k represents the k-th train, there are m trains in total, t_start i,j,k , t_stop i,j,k , t_hold i,j,k 、ato_curve i,j,k They represent the departure time, arrival time, stop time at the jth station and the ATO energy-saving curve between stations of the kth train from the ith station to the jth station, Set_ato represents the ATO curve set, and weight k represents the weight of the kth train, slope i,j represents the slope between the i-th station and the j-th station, p_flow i represents the passenger flow of the ith station, weather represents whether it is rainy or snowy, E_brakingenergy i It represents the energy recovered by the linkage between the i-th station signal and the regenerative braking energy recovery device.

[0090] In practical applications, based on the acquired real-time rail transit operation data (such as weather data) and the predicted passenger flow data of the day, combined with constraints such as transportation plans, the prediction model between the line energy consumption and the operation data variables can be optimized, that is, the objective function can be optimized. The prediction model between the line energy consumption and the operation data variables after optimization can be expressed as:

[0091]

[0092] in, is the optimized line energy consumption, t_start i,j,k ′、t_stop i,j,k ′、t_hold i,j,k′ respectively represent the real-time departure time, arrival time, and stop time of the kth train from the ith station to the jth station, ato_curve i,j,k ′ is the inter-station ATO energy-saving curve obtained in S2.

[0093] Furthermore, the updated operation diagram and ATO energy-saving curve obtained in S2 are used as the initial candidate solutions of the prediction model between the energy consumption of the optimized line and the operating data variables. The optimization problem is solved using heuristic optimization methods such as genetic algorithm or particle swarm algorithm to obtain an updated optimal operation diagram and optimal ATO energy-saving curve for the day to form a second operation strategy, thereby changing the existing fixed running mode according to the diagram into a dynamic adjustment operation mode required by real-time passenger flow in real-time operation.

[0094] Based on the above, the present invention uses deep neural networks to establish a prediction model between line energy consumption and other operating data variables based on the energy-saving curves and energy consumption data of each specific interval under different conditions (such as train weighing, track adhesion coefficient caused by climate change, etc.) recorded in the traction energy-saving system every day, so as to mine better energy-saving curves under the same conditions through historical data accumulation. In actual applications, the system records the energy-saving operation diagram planned for each day, combines the daily passenger flow information, and mines out a better operation diagram required for transporting the same passenger flow on the premise of meeting various basic operating indicators, and changes the existing fixed running car mode according to the diagram to a dynamic adjustment operation mode required by the real-time passenger flow in real-time operation.

[0095] Furthermore, the rail transit traction energy-saving method based on dynamic power flow calculation also includes: monitoring the health and abnormal energy consumption of train equipment through an abnormal energy consumption analysis module, and issuing an alarm signal when the abnormal energy consumption analysis module detects abnormal energy consumption.

[0096] It is understandable that the various modules involved in the rail transit traction energy-saving method based on dynamic power flow calculation of the present invention are not limited to the above-mentioned implementation method, and the corresponding functions can also be realized by other existing methods, and the present invention does not limit this.

[0097] Based on the same inventive concept, the present invention also discloses a traction energy-saving system for rail transit based on dynamic power flow calculation (see Figure 4), the system is used to implement the aforementioned rail transit traction energy-saving method based on dynamic power flow calculation. Specifically, the traction energy-saving system includes a rail transit real-time data module and a business knowledge module. The rail transit real-time data module is used to collect rail transit real-time operation data, and the rail transit real-time operation data includes real-time passenger flow data. The business knowledge module is the business knowledge middle platform, which includes ATO single-vehicle energy saving + ATS operation diagram planning multi-vehicle collaborative energy saving module, passenger flow time series prediction module, dynamic diagram adjustment energy saving module according to passenger flow requirements, regenerative braking energy feedback module, traction power supply system flow dynamic calculation and analysis module and line energy consumption and operation data variables prediction model, wherein the ATO single-vehicle energy saving + ATS operation diagram planning multi-vehicle collaborative energy saving module can be used to obtain a preliminary ATO energy saving curve, the passenger flow time series prediction module can predict the passenger flow data of the day, the dynamic diagram adjustment energy saving module according to passenger flow requirements can be used to obtain the operation diagram, the regenerative braking energy feedback module can be used to obtain the regenerative braking energy recovery device start-up mechanism based on the operation diagram, the traction power supply system flow dynamic calculation and analysis module can dynamically record and analyze the distribution of corresponding trains in power supply partitions, the relationship between the traction braking moment and energy consumption of the train ATO energy saving curve based on the operation strategy, and obtain the total actual energy consumption data corresponding to the operation strategy, and the prediction model between the line energy consumption and operation data variables can be used to optimize the operation strategy.

[0098] From the above, it can be seen that in the rail transit traction energy-saving system based on dynamic power flow calculation of the present invention, through the rail transit real-time data module and business knowledge module, combined with the dynamic driving information of the signal system, track basic information, dynamic passenger flow information (train weighing), power supply system topology relationship and dynamic voltage and current, through dynamic power flow calculation and analysis, various traction energy-saving means such as train operation and regenerative braking energy recovery device are coordinated and adjusted to ensure that various energy-saving measures work together to achieve the goal of efficient energy saving.

[0099] Furthermore, the traction energy-saving system also includes a big data module, namely a big data middle platform, which is used to store operation data. In practical applications, by establishing a big data module and performing data mining on this basis through a business knowledge module, a better ATO curve, a better energy-saving operation diagram, and a better coordination strategy for the regenerative braking energy recovery device can be found from historical data.

[0100] Furthermore, the traction energy-saving system also includes an equipment health and abnormal energy consumption analysis module, which is used to monitor the health and abnormal energy consumption of the main equipment of the train. When the abnormal energy consumption analysis module detects abnormal energy consumption, it can issue an alarm signal. In actual applications, the equipment health and abnormal energy consumption analysis module constructs an energy consumption model of the main equipment of the train and analyzes its equipment health. When there is abnormal energy consumption, it issues an alarm in time to avoid long-term high-energy consumption work.

[0101] In actual applications, the traction energy-saving system collects real-time operation data of rail transit by establishing a real-time data module for rail transit, namely, a real-time data middle platform. The real-time operation data of rail transit includes real-time passenger flow data, real-time driving information, train weighing information, real-time traction power supply system voltage and current information, traction power supply system energy consumption information, single-vehicle energy consumption information and single-vehicle regeneration energy information, etc.

[0102] Furthermore, in the system architecture of the traction energy-saving system, the big data module is located in the data middle platform layer. By establishing a big data middle platform and using historical data to establish a prediction module between data such as operation diagrams and operation information and energy consumption, based on real-time data and passenger flow prediction, the optimal ATO energy-saving curve and line operation diagram planning under current operating needs are solved through optimization algorithms. Based on the above, in actual applications, by inputting transportation planning requirements, the system can automatically match a better energy-saving strategy, and compare the energy-saving efficiency of previous strategies to determine whether it is more energy-saving.

[0103] Furthermore, the traction energy-saving system establishes a business knowledge module, namely, a business knowledge middle platform, which can establish the ATO single-vehicle energy-saving + ATS operation diagram planning multi-vehicle collaborative energy-saving module, passenger flow time series prediction module, dynamic diagram adjustment energy-saving module according to passenger flow requirements, regenerative braking energy feedback module, traction power supply system flow dynamic calculation and analysis module, line energy consumption and operation data variables prediction model and equipment health and abnormal energy consumption analysis module through knowledge graph technology. Of course, the business knowledge middle platform can not only be used to establish the above modules, but also can establish modules with other functions, and the present invention does not limit this.

[0104] like Figure 4As shown, it is a schematic diagram of the architecture of a traction energy-saving system of the present invention, which includes a cloud platform layer, a data middle platform layer, an intelligent computing layer and a human-computer interaction layer. The cloud platform layer is used to provide basic computing resources and cloud management enhancement functions, specifically including enhancing the virtual machine CPU independent binding core, memory exclusive without over-division, and ensuring that the enhanced virtual machine computing resources are not preempted. The data middle platform layer includes an industrial real-time middle platform and a big data middle platform. The industrial real-time middle platform is responsible for the collection and processing of real-time data, and the big data middle platform performs data cleaning, mining and analysis on the real-time data and historical data processed by the real-time middle platform to support the business modeling of the business knowledge middle platform. The intelligent computing layer includes a business knowledge module, which is mainly based on knowledge graph technology, big data and AI algorithm technology, etc., to realize the modeling of various business analysis modules. The main modules involved in the intelligent computing layer include: stop / interval operation time optimization module, full map surplus time dynamic planning module, ATS+ATO multi-vehicle collaboration module, regenerative braking energy recovery module, traction power supply system flow dynamic calculation module, data mining optimal energy-saving curve module, dynamic map adjustment module according to passenger flow requirements, equipment health and abnormal energy consumption analysis module, etc.

[0105] Based on the same inventive concept, the present invention also provides an electronic device, comprising: a memory, a processor, wherein a computer program is stored on the memory, and when the computer program is executed by the processor, the steps of the aforementioned rail transit traction energy-saving method based on dynamic power flow calculation are implemented.

[0106] Based on the same inventive concept, the present invention also provides a readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the aforementioned rail transit traction energy-saving method based on dynamic power flow calculation are implemented.

[0107] In summary, in a traction energy-saving method, system, electronic device and readable storage medium based on dynamic power flow calculation for rail transit of the present invention, the traction energy-saving method dynamically analyzes multi-dimensional coupling conditions such as power supply, vehicles, signals, and tracks through modules such as ATO single-vehicle energy saving + ATS operation diagram planning multi-vehicle collaborative energy saving module, dynamic diagram adjustment module according to passenger flow requirements, and regenerative braking energy feedback module, and performs dynamic power flow calculation from the perspective of energy flow through the traction power supply system power flow dynamic calculation and analysis module, dynamically coordinates ATO energy saving, ATS energy saving, regenerative braking energy recovery device energy saving and other technical means, and performs unified management and coordinated linkage, performs energy consumption monitoring and statistical analysis for different traction energy-saving measures, and tracks and evaluates long-term energy-saving operation effects; and continuously optimizes the energy-saving control strategy according to the analysis results through the prediction model between line energy consumption and operation data variables, so as to achieve a truly better energy-saving effect.

[0108] Although the content of the present invention has been described in detail through the above preferred embodiments, it should be appreciated that the above description should not be considered as a limitation of the present invention. After reading the above content, it will be apparent to those skilled in the art that various modifications and substitutions of the present invention will occur. Therefore, the protection scope of the present invention should be limited by the appended claims.

Claims

1. A traction energy-saving method for rail transit based on dynamic power flow calculation, characterized in that: Include: S1. Collecting rail transit real-time operation data through a rail transit real-time data module, wherein the rail transit real-time operation data includes real-time passenger flow data; S2. Based on the real-time operation data of rail transit, the ATO energy-saving curve is obtained through the ATO single-vehicle energy-saving + ATS operation diagram planning multi-vehicle collaborative energy-saving module, the passenger flow data of the day is predicted through the passenger flow time series prediction module, and the dynamic diagram adjustment module according to the passenger flow requirements is based on the real-time passenger flow data collected in S1 and the passenger flow data of the day predicted by the passenger flow time series prediction module. The operation diagram of the day is dynamically adjusted to obtain an updated operation diagram, and the regenerative braking energy recovery device startup mechanism based on the updated operation diagram is obtained through the regenerative braking energy feedback module; the first operation strategy is formed based on the ATO energy-saving curve, the updated operation diagram, the startup mechanism of the regenerative braking energy recovery device and the predicted passenger flow data of the day; S3, the traction power supply system power flow dynamic calculation and analysis module dynamically records and analyzes the distribution of trains corresponding to the first operation strategy in the power supply partition, the relationship between the traction braking moment and energy consumption of the train ATO energy-saving curve, and the total actual energy consumption data based on the first operation strategy; S4. Optimizing the first operation strategy through a prediction model between line energy consumption and operation data variables to obtain a second operation strategy; S5. The traction power supply system power flow dynamic calculation and analysis module dynamically records and analyzes the distribution of trains corresponding to the second operation strategy in the power supply partition, the relationship between the traction braking moment and energy consumption of the train ATO energy-saving curve, and the total actual energy consumption data based on the second operation strategy; S6. Compare the total actual energy consumption data corresponding to the first operation strategy with the total actual energy consumption data corresponding to the second operation strategy. When the total actual energy consumption data corresponding to the second operation strategy is lower than the total actual energy consumption data corresponding to the first operation strategy, operate according to the second operation strategy.

2. The traction energy saving method for rail transit based on dynamic power flow calculation according to claim 1, characterized in that: In S6, when the total actual energy consumption data corresponding to the second operating strategy is higher than the total actual energy consumption data corresponding to the first operating strategy, the first operating strategy is regenerated through step S2, and steps S3 to S6 are repeated until the total actual energy consumption data corresponding to the second operating strategy is lower than the total actual energy consumption data corresponding to the first operating strategy.

3. The traction energy-saving method for rail transit based on dynamic power flow calculation according to claim 1, characterized in that: The traction power supply system power flow dynamic calculation and analysis module performs analysis based on the traction power supply system power flow dynamic calculation, which specifically includes: By real-time monitoring of traction power supply mode, traction power supply voltage, dynamic position and weight of the train, a dynamic circuit relationship between traction power supply and train is established; The substation is equivalent to a power source, the overhead line is equivalent to a resistor, the train in traction state is equivalent to a resistor, and the train in braking state is equivalent to a power source. The entire section is divided into several sections. Under the condition of a dynamically moving train, the relationship between voltage, resistance, current, power and energy consumption in different sections is defined; Real-time calculation of the power flow of the traction power supply system by real-time monitoring of traction voltage and current, train power consumption and energy feedback, and dynamic distribution of trains; The total actual energy consumption data is collected through the power supply system and trains, and the distribution of trains in power supply areas and the relationship between the traction braking moment and energy consumption of the train ATO energy-saving curve are dynamically recorded and analyzed.

4. The traction energy saving method for rail transit based on dynamic power flow calculation according to claim 1, characterized in that: In S2, the working method of the ATO single-vehicle energy saving + ATS operation diagram planning multi-vehicle collaborative energy saving module includes: Based on the speed deviation of train operation, each ATO energy-saving curve is divided into multiple checkpoints, and each checkpoint records different ATO train control parameters. When the train passes a checkpoint, ATO comprehensively considers the remaining time at the station and the upstream and downstream operation curves to calculate the appropriate ATO target speed. Train idling resistance is identified based on big data analysis, specifically different trains with different loads at different kilometer marker positions; idling resistance is known in advance through data accumulation and cleaning; Use convex optimization models and algorithms to perform offline planning of energy-saving speed curves; By adjusting the surplus time, the train section running time is adjusted, the utilization rate of the train regenerative braking energy is improved, the energy-saving operation diagram is optimized, and the train is automatically adjusted; Through ATO single-vehicle energy saving + ATS operation diagram planning multi-vehicle collaborative technology, the dynamic energy consumption of single vehicle + multiple vehicles can be optimized.

5. The traction energy saving method for rail transit based on dynamic power flow calculation according to claim 1, characterized in that: In S2, the regenerative braking energy recovery device startup mechanism based on the operation diagram is obtained through the regenerative braking energy feedback module, including: Based on the updated operation diagram, the train interval running time, station stop time and return time are optimized, and the simulated annealing intelligent algorithm technology is used to solve the large-scale transportation optimization problem with multiple constraints in complex networks, so that the entry and exit operation time of trains running in the same and / or adjacent power supply sections can overlap to the greatest extent, so that the outgoing trains can fully utilize the braking regeneration energy of the incoming trains; Taking advantage of the predictability of the operating parameters of the signal system, a prediction algorithm is used to coordinate with the regenerative braking energy recovery device. When the running train is about to start braking, the regenerative braking energy recovery device is notified in advance, and the regenerative braking energy recovery device is immediately started to recover electric energy while the train is braking. Based on the above, a regenerative braking energy recovery device activation mechanism based on the updated operation diagram is obtained.

6. The traction energy saving method for rail transit based on dynamic power flow calculation according to claim 1, characterized in that: In S4, based on the real-time operation data of rail transit and the predicted passenger flow data of the day, the prediction model between the line energy consumption and the operation data variables is optimized in combination with the transportation plan; The updated operation diagram and ATO energy-saving curve obtained in S2 are used as initial candidate solutions of the optimized prediction model between the line energy consumption and the operation data variables, and the updated operation diagram and ATO energy-saving curve are optimized to form a second operation strategy.

7. The traction energy saving method for rail transit based on dynamic power flow calculation according to claim 6, characterized in that: The prediction model between the line energy consumption and the operation data variables can be expressed as: E=f DNN (t_start i,j,k ,t_stop i,j,k ,t_hold i,j,k ,ato_curve i,j,k ,weight k ,slope i,j ,p_flow i ,weather,E_brakingenergy i ) 1＜i,j＜n,1＜k＜m ato_curve i,j,k ∈Set_ato (1) Among them, f DNN represents the deep neural network model function, E represents the line energy consumption, i and j represent the index of the i-th and j-th stations respectively, there are n stations in total, k represents the k-th train, there are m trains in total, t_start i,j,k , t_stop i,j,k , t_hold i,j,k 、ato_curve i,j,k They represent the departure time, arrival time, stop time at the jth station and the ATO energy-saving curve between stations of the kth train from the ith station to the jth station, Set_ato represents the ATO curve set, and weight k represents the weight of the kth train, slope i,j represents the slope between the i-th station and the j-th station, p_flow i represents the passenger flow of the ith station, weather represents whether it is rainy or snowy, E_brakingenergy i It represents the energy recovered by the linkage between the i-th station signal and the regenerative braking energy recovery device.

8. The method for traction energy saving based on dynamic power flow calculation for rail transit according to claim 6, characterized in that: Based on the real-time operation data of rail transit and the predicted passenger flow of the day, the prediction model between the optimized line energy consumption and the operation data variables is expressed as: in, is the optimized line energy consumption, t_start i,h,k ′、t_stop i,j,k ′、t_hold i,j,k ′ respectively represent the real-time departure time, arrival time, and stop time of the kth train from the ith station to the jth station, ato_curve i,j,k ′ is the inter-station ATO energy-saving curve obtained in S2.

9. The rail transit traction energy saving method based on dynamic power flow calculation according to claim 1, characterized in that: Also includes: The health and abnormal energy consumption of train equipment are monitored through the abnormal energy consumption analysis module, and an alarm signal is issued when the abnormal energy consumption analysis module detects abnormal energy consumption.

10. A traction energy-saving system for rail transit based on dynamic power flow calculation, which is used to implement the traction energy-saving method for rail transit based on dynamic power flow calculation as claimed in any one of claims 1 to 9, characterized in that: The traction energy-saving system comprises a rail transit real-time data module and a business knowledge module, wherein the rail transit real-time data module is used to collect rail transit real-time operation data, and the rail transit real-time operation data comprises real-time passenger flow data; The business knowledge module includes: ATO single-vehicle energy saving + ATS operation diagram planning multi-vehicle collaborative energy saving module, which is used to obtain the preliminary ATO energy saving curve; Passenger flow time series prediction module, which is used to predict the passenger flow data of the day; Energy-saving module for dynamically adjusting the diagram according to passenger flow requirements, which is used to obtain the operation diagram; A regenerative braking energy feedback module, which is used to obtain a regenerative braking energy recovery device start-up mechanism based on an operation diagram; The dynamic calculation and analysis module of the traction power supply system flow, which dynamically records and analyzes the distribution of the corresponding trains in the power supply partition, the relationship between the traction braking moment and energy consumption of the train ATO energy-saving curve based on the operation strategy, and obtains the total actual energy consumption data corresponding to the operation strategy; A prediction model between line energy consumption and operating data variables is used to optimize the operation strategy.

11. The rail transit traction energy-saving system based on dynamic power flow calculation as claimed in claim 10, characterized in that: Also includes: The big data module is used to store operation data.

12. The rail transit traction energy-saving system based on dynamic power flow calculation as claimed in claim 10, characterized in that: Also includes: The equipment health and abnormal energy consumption analysis module is used to monitor the health and abnormal energy consumption of train equipment. When the abnormal energy consumption analysis module detects abnormal energy consumption, an alarm signal can be issued.

13. The rail transit traction energy-saving system based on dynamic power flow calculation as claimed in claim 10, characterized in that: The business knowledge module can establish the ATO single-vehicle energy saving + ATS operation diagram planning multi-vehicle collaborative energy saving module, passenger flow time series prediction module, dynamic diagram adjustment energy saving module according to passenger flow requirements, regenerative braking energy feedback module, traction power supply system flow dynamic calculation and analysis module and prediction model between line energy consumption and operation data variables through knowledge graph technology.

14. An electronic device, characterized in that: The electronic device comprises: a memory and a processor, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the steps of the traction energy-saving method for rail transit based on dynamic power flow calculation are implemented as described in any one of claims 1 to 9.

15. A readable storage medium, characterized in that: The readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the traction energy-saving method for rail transit based on dynamic power flow calculation are implemented as described in any one of claims 1 to 9.

Images