Self-adaptive control method and device of urban rail transit energy router

Abstract

The invention relates to a self-adaptive control method and device for an urban rail transit energy router. The method comprises the following steps: acquiring network routing energy data and network routing spatio-temporal data corresponding to a rail transit network; according to the network routing energy data and the network routing spatio-temporal data, analyzing a spatio-temporal-electric energy relationship of the rail transit network to obtain spatio-temporal electric energy distribution data; performing class energy state transition analysis on the space-time electric energy distribution data to obtain network energy state real-time evolution data; and adjusting calculation parameters of the time-space electric energy distribution data by using the network energy state real-time evolution data until the stability of the network energy state real-time evolution data accords with a preset stability parameter, thereby obtaining network energy routing control data corresponding to the rail transit network. By adopting the method, the self-adaptive adjustment capability of the real-time operation state can be met, and the energy utilization efficiency can be improved.

Description

Technical Field

[0001] This application relates to the field of intelligent control technology, and in particular to an adaptive control method and apparatus for an urban rail transit energy router. Background Technology

[0002] In traditional technologies, energy router control methods for urban rail transit mainly rely on preset fixed control strategies. A centralized dispatching system manages the energy flow in the traction power supply network to achieve coordinated energy distribution and localized utilization of regenerative braking energy. However, traditional technologies typically set parameters based on historical data and operational experience, making it difficult to respond in real-time to dynamic changes in complex traffic scenarios. This lack of adaptive adjustment capabilities to real-time operating conditions results in low energy utilization efficiency. Summary of the Invention

[0003] Therefore, it is necessary to provide an adaptive control method, device, and computer equipment for an urban rail transit energy router that can improve energy utilization efficiency by satisfying the adaptive adjustment capability for real-time operating status.

[0004] Firstly, this application provides an adaptive control method for an urban rail transit energy router, including:

[0005] Acquire network routing energy data and network routing spatiotemporal data corresponding to the rail transit network;

[0006] Based on the network routing energy data and the network routing spatiotemporal data, the spatiotemporal-electrical energy relationship of the rail transit network is analyzed to obtain spatiotemporal electrical energy distribution data;

[0007] The spatiotemporal power distribution data are subjected to energy state transition analysis to obtain real-time network energy state evolution data;

[0008] Using the real-time evolution data of the network energy state, the calculation parameters of the spatiotemporal power distribution data are adjusted until the stability of the real-time evolution data of the network energy state meets the preset stability parameters, thereby obtaining the network energy routing control data corresponding to the rail transit network.

[0009] Secondly, this application also provides an adaptive control device for an urban rail transit energy router, comprising:

[0010] The network data acquisition module is used to acquire network routing energy data and network routing spatiotemporal data corresponding to the rail transit network.

[0011] The distribution data calculation module is used to analyze the spatiotemporal-electrical energy relationship of the rail transit network based on the network routing energy data and the network routing spatiotemporal data, and obtain spatiotemporal electrical energy distribution data.

[0012] The evolution data calculation module is used to perform energy state transition analysis on the spatiotemporal electrical energy distribution data to obtain real-time network energy state evolution data;

[0013] The control data acquisition module is used to adjust the calculation parameters of the spatiotemporal power distribution data using the real-time evolution data of the network energy state until the stability of the real-time evolution data of the network energy state meets the preset stability parameters, thereby obtaining the network energy routing control data corresponding to the rail transit network.

[0014] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement any step in an adaptive control method for an urban rail transit energy router.

[0015] The aforementioned adaptive control method and device for urban rail transit energy routers acquires energy consumption data and corresponding spatiotemporal operational data for each network route in the rail transit network. This constructs a refined spatiotemporal-electrical energy correlation model of the rail transit network, comprehensively depicting the changing patterns of energy distribution under different time and spatial conditions. By performing energy state transition-like analysis on the spatiotemporal electrical energy distribution data, the model dynamically reflects the changing process of energy states within the network, accurately capturing potential energy mutations or instabilities that may occur during system operation. Based on this, the model parameters are iteratively optimized using real-time evolution data of the network energy states, making the model more closely match actual operational characteristics until the system energy state evolution process reaches the preset stability requirements, ultimately generating high-precision network energy routing control data. This effectively meets the adaptive adjustment requirements for real-time operational states, improving energy utilization efficiency and thereby enhancing the energy efficiency management, operational safety, and intelligent control capabilities of the entire system in complex traffic scenarios. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments or related technologies of this application, the accompanying drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 This is an application environment diagram of the adaptive control method for urban rail transit energy routers in one embodiment;

[0018] Figure 2 This is a flowchart illustrating an adaptive control method for an urban rail transit energy router in one embodiment.

[0019] Figure 3 This is a flowchart illustrating a method for obtaining real-time network energy state evolution data in one embodiment.

[0020] Figure 4 This is a flowchart illustrating a method for obtaining spatiotemporal data at a transition point in one embodiment.

[0021] Figure 5 This is a flowchart illustrating the second method for obtaining real-time network energy state evolution data in one embodiment;

[0022] Figure 6 This is a flowchart illustrating the first method for obtaining spatiotemporal electrical energy distribution data in one embodiment;

[0023] Figure 7 This is a flowchart illustrating the second method for obtaining spatiotemporal electrical energy distribution data in one embodiment;

[0024] Figure 8 This is a structural block diagram of an adaptive control device for an urban rail transit energy router in one embodiment;

[0025] Figure 9 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0026] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0027] This application provides an adaptive control method for an urban rail transit energy router, which can be applied to, for example... Figure 1 In the application environment shown, terminal 102 communicates with server 104 via a network. A data storage system can store the data that server 104 needs to process. The data storage system can be integrated onto server 104, or it can be located in the cloud or on other network servers. Server 104 can be implemented using a standalone server or a server cluster consisting of multiple servers.

[0028] In one exemplary embodiment, such as Figure 2 As shown, an adaptive control method for an urban rail transit energy router is provided, which is then applied to... Figure 1 Taking the server in the example, the explanation includes the following steps 202 to 208. Wherein:

[0029] Step 202: Obtain the network routing energy data and network routing spatiotemporal data corresponding to the rail transit network.

[0030] Step 204: Based on the network routing energy data and the network routing spatiotemporal data, analyze the spatiotemporal-electrical energy relationship of the rail transit network to obtain spatiotemporal electrical energy distribution data.

[0031] Step 206: Perform energy state transition analysis on the spatiotemporal power distribution data to obtain real-time network energy state evolution data.

[0032] Step 208: Use the real-time evolution data of network energy state to adjust the calculation parameters of spatiotemporal power distribution data until the stability of the real-time evolution data of network energy state meets the preset stability parameters, and obtain the network energy routing control data corresponding to the rail transit network.

[0033] The rail transit network can be a complex transportation system consisting of multiple track lines, train operation paths, station nodes, power supply systems, traction and braking systems, etc. It has a clear topological structure, time-series scheduling rules and energy flow paths. The network not only covers the physical path of train operation, but also its power supply topology, control logic and energy conversion relationship.

[0034] Among them, network routing energy data can be various raw or processed data related to energy transmission that occur along the train running path (routes) in the rail transit network, including train traction power, braking feedback power, power output of power supply points, energy loss estimation, energy storage device status, etc.

[0035] Among them, network routing spatiotemporal data can be the time and spatial location information associated with the train running path in the rail transit network, which usually includes information such as the train's position, speed, acceleration, inter-station interval relationship, entry and exit time, and signal status at different times.

[0036] The spatiotemporal-electrical energy relationship can be seen as the propagation and change of electrical energy in the rail transit network over time and space, reflecting the coupling mechanism between train operation behavior (such as acceleration, deceleration, and stopping) and power supply behavior (such as traction power supply and regenerative braking). This relationship can reveal the entire process of energy flow in the system dynamically spreading, superimposing, or dissipating along the train's path and operating time.

[0037] Among them, spatiotemporal power distribution data can be calculated based on the structure of the rail transit network, the train operation status and energy behavior. It is continuous distribution data of power density in the spatial and temporal domains of the system, used to describe the power state at any time and any network location. It usually exists in the form of an energy density field or power distribution function.

[0038] Among them, energy state transition analysis can draw on the idea of ​​state transition in quantum systems, model the energy distribution state in the rail transit network as "energy states", and analyze the transition path, transition amplitude and transition frequency of these energy states under the influence of factors such as train operation and power supply interference, so as to identify unstable energy fluctuations, abnormally concentrated areas or imbalance propagation phenomena in the system.

[0039] Among them, the real-time evolution data of network energy states can be obtained through energy state transition analysis, which reflects the evolution process of each energy state in the rail transit network over time. It usually includes information such as transition start and end points, path trajectory, transition amplitude, duration, and disturbance source type.

[0040] The calculation parameters can be various control variables and numerical factors used when establishing the energy propagation and distribution models of the rail transit network, such as the diffusion coefficient of the pulse propagation kernel, the pulse amplitude coefficient, the train energy response efficiency, the energy superposition weight, the time step, and the spatial resolution.

[0041] Among them, the preset stability parameters can be evaluation standards set in advance during the design phase or in the operation strategy to measure whether the rail transit energy system has reached a stable state, including the maximum allowable energy fluctuation range, transition frequency threshold, upper limit of disturbance recovery time, energy density gradient limit, etc.

[0042] Among them, network energy routing control data can be a set of data output after spatiotemporal power modeling, energy state evolution analysis and stability assessment are completed. It is used to control the energy flow direction, distribution path and energy supply response behavior in the rail transit network. It usually includes energy scheduling instructions for each train, energy storage device start-up and shutdown logic, local power supply priority, path dynamic adjustment suggestions, etc., to guide the actual energy flow allocation and response strategy execution.

[0043] Specifically, by collecting real-time monitoring and historical scheduling data, a dataset containing information such as train traction / braking power, energy feedback, power injection nodes, train running trajectory, timetable, and signal control logic is constructed, forming network routing energy data (such as power time series and power supply response events) and network routing spatiotemporal data (such as train position-time mapping and path topology changes).

[0044] A method based on the energy perturbation pulse propagation model is adopted, which regards the rail transit network as a spatiotemporally coupled energy propagation medium. Then, the traction or braking behavior of each train is modeled as a local energy injection source. The Gaussian modulated pulse function and the spatial propagation kernel function are used for modeling. The integral is superimposed in the partitioned space (spatial-temporal grid) of the rail transit network to form a continuous function describing the distribution of electrical energy density at each location and time. The function is solved to obtain the spatiotemporal electrical energy distribution data of energy diffusion, interference, time delay and coupling.

[0045] Based on the spatiotemporal variation gradient and local fluctuation characteristics in spatiotemporal power distribution data, a state-like model of the rail transit network is constructed to characterize the changes in power density, abrupt changes in flow direction, and disturbance boundaries as transition behaviors in the state space. The state-like model is used to extract local discontinuities (such as energy flow jumps and power feedback boundaries) and anomalous paths (such as energy rebound flows and accumulation zones) from the spatiotemporal power distribution data. Path transition analysis is performed to construct transition data and transition sequences, generating real-time network energy state evolution data containing "transition start point - end point - path - time - disturbance type".

[0046] Through a feedback control mechanism, indicators such as transition frequency, path disturbance amplitude, and energy gradient drift in the real-time evolution data of network energy state are compared with preset stability parameters, such as maximum energy fluctuation amplitude and average disturbance recovery time. If the stability does not meet the stability constraints of the preset stability parameters, the calculation parameters of the spatiotemporal power distribution data (such as the diffusion coefficient of the propagation kernel function, local weights, train energy injection factors, etc.) are iteratively adjusted, and the real-time evolution data of network energy state is continuously recalculated until the transition mode is stable within a controllable range, that is, the stability of the real-time evolution data of network energy state meets the preset stability parameters. The network energy routing control data, including the energy supply priority order of each track segment, train energy management strategy, and local energy storage start-up and shutdown logic, is then output. The server 104 then controls each energy router in the rail transit network through the network energy routing control data.

[0047] The aforementioned adaptive control method for urban rail transit energy routers acquires energy consumption data and corresponding spatiotemporal operational data for each network route in the rail transit network, constructing a refined spatiotemporal-electrical energy correlation model of the rail transit network to comprehensively depict the changing patterns of energy distribution under different time and spatial conditions. By performing energy state transition-like analysis on the spatiotemporal electrical energy distribution data, the method dynamically reflects the changing process of energy states within the network, accurately capturing potential energy mutations or instabilities that may occur during system operation. Based on this, the model parameters are iteratively optimized using real-time evolution data of the network energy state, making the model more closely match actual operational characteristics until the system energy state evolution process reaches the preset stability requirements, ultimately generating high-precision network energy routing control data. This method effectively meets the adaptive adjustment requirements of real-time operational states, improving energy utilization efficiency and thereby enhancing the energy efficiency management, operational safety, and intelligent control capabilities of the entire system in complex traffic scenarios.

[0048] In one exemplary embodiment, such as Figure 3 As shown, the step of performing energy state transition-like analysis on the spatiotemporal electrical energy distribution data to obtain real-time network energy state evolution data includes steps 302 to 304. Wherein:

[0049] Step 302: Perform class transition path planning on the spatiotemporal power distribution data to obtain the spatiotemporal data of the transition point execution.

[0050] Step 304: Perform class-based transition control on the spatiotemporal data of the transition points to obtain real-time evolution data of the network energy state.

[0051] Among them, state transition path planning can be the process of identifying and predicting the optimal path sequence for the network to transition from the current energy state to the target energy state based on the continuous changing trend of the spatiotemporal electrical energy distribution in the rail transit network. This path is not a physical track, but a control channel for the propagation and transfer of energy disturbances in spacetime. It is usually determined based on principles such as minimum energy consumption, minimum disturbance, or shortest recovery time, by analyzing anomalous regions, local gradient boundaries, and interference centers in the energy density field, to determine the transition start point, end point, intermediate nodes, and their sequence.

[0052] The spatiotemporal data for transition points can be the specific spatial location and corresponding execution time information of each transition node extracted during the process of planning the energy transition path. This information is used to determine when and where to intervene and control the electrical state in the rail transit network. These data describe a series of key "control trigger points," which are a set of execution parameters for realizing energy transition control. They typically include key data items such as transition point number, path segment, expected energy change, time window, and surrounding coupling effects.

[0053] Among them, state transition control can be based on spatiotemporal data of the transition point to apply precise energy perturbation (such as adjusting train traction power, guiding feedback energy diversion, and controlling energy storage device switching) at a specified time and location in the rail transit network, thereby guiding the system energy state to transition along the planned path and gradually evolve to the target stable state. This control method simulates the state transition logic between energy levels in quantum transition, and in engineering, it is manifested as the redistribution of system energy under the guidance of continuous perturbation.

[0054] Specifically, the spatiotemporal power distribution data of the rail transit network is first treated as a continuous energy density field. By analyzing the characteristics of this field, such as local gradient maxima, abnormal fluctuation regions, and energy flux density breakpoints, candidate points that may lead to "energy state transitions" are identified. Then, based on the principle of minimum energy consumption path or minimum disturbance, the path sequence required to transition from the current energy state to the desired steady state is planned, including the start point, end point, scope of influence, and estimated time required for the transition. This determines the execution location and execution time of the transition point, thus forming the spatiotemporal data of the transition point execution.

[0055] Using the spatiotemporal data of transition points as input, a virtual energy router or node control module is constructed to determine the transition point location within the spatiotemporal data and apply control perturbations (such as simulated traction reduction, feedback weighting, and energy storage regulation). Combined with local perturbation functions or propagation kernel functions, the energy state is observed to adjust in response to transition control behavior. The energy density change paths and system energy accumulation or release processes triggered by these controls are recorded in real time. Transition state sequences, fluctuation amplitudes, and system response curves are extracted to obtain real-time network energy state evolution data.

[0056] In this embodiment, by performing class-based transition path planning on spatiotemporal power distribution data and implementing class-based transition control based on the transition points, it is possible to actively guide and dynamically intervene in power fluctuation regions within the rail transit network, enabling the system's energy state to evolve along the expected path and tend towards stability. This significantly improves the network's anti-disturbance capability and the accuracy of energy routing regulation, thereby achieving efficient power distribution and optimal local energy feedback utilization within the rail system.

[0057] In one exemplary embodiment, such as Figure 4 As shown, the step of performing type transition path planning on the spatiotemporal power distribution data to obtain the spatiotemporal data of the transition point execution includes steps 402 to 406. Wherein:

[0058] Step 402: Based on the network routing energy data and the network routing spatiotemporal data, set the target energy state corresponding to the rail transit network.

[0059] Step 404: Using the principle of minimum dissipation, calculate the spatiotemporal energy transition sequence between the spatiotemporal energy distribution data and the target-like energy state.

[0060] Step 406: Determine the execution time and execution location of various transition points from the spatiotemporal energy transition sequence to obtain the spatiotemporal data of transition point execution.

[0061] Among them, the target energy state can be an idealized and structurally reasonable power distribution state of the entire network during the operation of the rail transit network, based on factors such as current train scheduling, energy consumption demand, power supply capacity and energy storage strategy. This energy state not only considers the total power or total energy balance, but also requires it to have characteristics such as low fluctuation, small gradient and fast response in the spatiotemporal dimension.

[0062] The principle of minimum dissipation can be defined as an optimization strategy where, when a conductive energy state transitions from its current distribution state to a target state, the selected path minimizes the total energy consumption, energy gradient disturbance, or state change cost during the transition. Essentially, it is a dynamic optimization criterion used to select the most "natural" or economical energy transfer trajectory, thereby minimizing energy losses, system instability, or local overload risks caused by regulation.

[0063] In this context, a spatiotemporal energy transition sequence can be a series of spatiotemporally continuous energy transfer steps or path segments constructed based on the principle of minimum dissipation between the current energy distribution state and the target energy state. Each transition sequence describes the change in the electrical state that the system should undergo within a certain spatial region and time interval. It typically consists of a set of candidate transition points, corresponding energy offsets, propagation directions, and evolution time windows, used to characterize how the orbital network gradually adjusts its electrical state to achieve overall optimal migration.

[0064] Among them, transition points can be key action points identified in a spatiotemporal energy transition sequence. They represent control anchor points where the system should perform energy intervention, control operations, or state transitions at specific spatial locations and time nodes to trigger local transitions. These transition points are usually located at critical positions where energy disturbances are concentrated, fluctuations are abrupt, or paths are switched. They are the smallest units for achieving continuous transition evolution and determine the accuracy of regulation execution and response efficiency within the control cycle.

[0065] Specifically, by comprehensively analyzing network routing energy data (such as train traction / braking power, energy storage behavior, etc.) and network routing spatiotemporal data (such as train timetables, section occupancy, transfer relationships, etc.) of the rail transit network, and under the premise of satisfying the current operational constraints of each train in the rail transit network, a desired overall network electrical energy state is set as a target energy state. This target state is not a single power target in the traditional sense, but rather an energy state structure with continuous spatiotemporal distribution, a gentle energy gradient, and low volatility.

[0066] Taking the current spatiotemporal energy distribution data as the initial state and the target-like energy state as the final state, an optimal transition trajectory connecting these two states is constructed based on the principle of minimum dissipation (i.e., minimizing the total power loss or energy gradient perturbation in the energy migration path). By solving the minimum path dissipation model or the minimum perturbation offset function, multiple transition sequences with minimum energy cost are obtained. Each segment in the sequence represents the spatial transition region and time adjustment window required for the transition from the current state to the target state. By superimposing multiple transition sequences with minimum energy cost, a spatiotemporal energy transition sequence is formed.

[0067] Based on the segmented characteristics of the energy transfer path in the aforementioned spatiotemporal energy transition sequence, key excitation points or turning points in the transition process are identified, i.e., the key locations and time nodes in the energy density field that will trigger structural changes or perturbation transduction. Through clustering, abrupt gradient identification, or energy flow switching criteria, the precise execution locations and times of these transition points are extracted, forming spatiotemporal data of transition point execution, including transition point number, spatial coordinates, action window, and path attribution.

[0068] In this embodiment, a target-like energy state is defined based on network routing energy data and network routing spatiotemporal data. The principle of minimum dissipation is used to construct a spatiotemporal energy transition sequence from the current state to the target state. The execution time and location of key transition points are then extracted, enabling proactive guidance and local intervention in the energy evolution path of the rail transit network. This significantly improves the system's adaptability to complex dynamics such as sudden loads, train congestion, and feedback energy surges, achieving precise, distributed regulation of energy routing and localized disturbance control, effectively enhancing the resilience and efficiency of the rail transit energy supply system.

[0069] In one exemplary embodiment, such as Figure 5 As shown, the step of performing spatiotemporal data analysis on the transition points to obtain real-time network energy state evolution data includes steps 502 to 506.

[0070] in:

[0071] Step 502: Set up virtual energy routers at various transition points in the real-time evolution data of network energy state to obtain router-type spatiotemporal transition data.

[0072] Step 504: Apply a local perturbation function to the router-type spatiotemporal transition data to obtain the router-type spatiotemporal perturbation field.

[0073] Step 506: Simulate the energy state transitions of each virtual energy router in the router-type spatiotemporal perturbation field to obtain real-time network energy state evolution data.

[0074] Among them, the virtual energy router can be a non-physical node built based on the logical location of a specific transition point in the rail transit energy control model. It is used to simulate the dynamic access, diversion, delay, feedback or damping of electrical energy in the real system. The router has the functions of sensing changes in surrounding electrical energy, participating in local energy decision-making and guiding energy state transitions. It is a key intermediary mechanism in realizing energy state transition control process, and is used to decouple the relationship between the whole network control and local regulation.

[0075] Router-like spatiotemporal transition data refers to a set of information associated with each virtual energy router, describing its energy behavior evolution at different times and locations. This mainly includes router activation time, control triggering conditions, energy state transition values, transition direction, and influence range. This data is used to record and predict the router's participation path and timing of action in state transition control, serving as a fundamental data source for constructing perturbation field and energy state evolution models.

[0076] The local disturbance function can be a mathematical expression used to characterize the diffusion characteristics of energy disturbances caused by factors such as control operations, power injection, and external disturbances in a local space and time around a specific router or transition point. This function can take the form of Gaussian kernel, sinusoidal modulation pulse, convolution propagation kernel, etc., to reflect properties such as disturbance intensity, propagation speed, attenuation range, and feedback time delay.

[0077] Among them, the router-type spatiotemporal disturbance field can be a continuous field formed by the superposition of the local disturbance functions of multiple virtual energy routers in the spatial and temporal domains in the rail transit network. It is used to simulate how disturbances propagate, interfere, diffuse and affect the state evolution of the entire energy system from various transition points. This disturbance field reflects the real propagation path of the system's energy state fluctuations and can be used to predict the system response region and identify stability risk areas.

[0078] Among them, energy state transition can be the process by which the electrical energy state of a certain region or node in a rail transit system transitions from a relatively stable distribution state to another state under certain disturbances or control effects. This is manifested as a sudden change in energy density, a change in direction, a redistribution of flow, or a change in oscillation mode. This transition is not a simple numerical change, but reflects the evolution of the system from one macroscopic energy state to another functional state.

[0079] Specifically, the various transition points previously identified from the real-time evolution data of network energy state are used as action centers, and virtual energy routers are set up at these points through logical modeling. Each virtual router simulates a control node with the same local energy scheduling, switching, buffering, and feedback capabilities as the real node, and records its spatiotemporal coordinates, range of action, control weight, and adjacency topology. By comprehensively setting each virtual energy router to the various transition points identified in the real-time evolution data of network energy state, router-type spatiotemporal transition data is obtained.

[0080] Based on router-like spatiotemporal transition data with virtual energy routers configured, formalized local perturbation functions (such as impulse functions, convolution kernels, and energy wave propagation models) are introduced to simulate the local diffusion and interference processes of energy disturbances in the network caused by control commands, environmental disturbances, or sudden changes in train state. During the simulation, these perturbation functions are applied to the router transition trajectories, and their propagation effects in space and time are calculated to construct a router-like spatiotemporal perturbation field describing how disturbances propagate from local transition points to other areas throughout the network.

[0081] By running an energy transition simulation model within a pre-constructed spatiotemporal perturbation field, the energy state evolution behavior of each virtual energy router under the influence of its local perturbation field is simulated, including dynamic processes such as changes in energy input and output, state response delay, and accumulation of transition interference. Subsequently, the energy state change trajectory of each router is continuously recorded, and the energy state transition evolution path of the entire network is superimposed to construct the final network-level energy state evolution data.

[0082] For the spatiotemporal perturbation field of routers, the calculation formula is as follows:

[0083]

[0084]

[0085] in, For the spatiotemporal perturbation field of the router class; i is the imaginary unit; Ψ(x,t) is Planck's constant; Ψ(x,t) is the energy-like state function; ρ(x,t) is the energy density function; θ(x,t) is the energy phase function; x is the first spatial variable; t is the first time variable; x′ is the second spatial variable; t′ is the second time variable; It is an intrinsic Hamiltonian operator; Γ(x′,t′) is the local disturbance function; K(xx′,tt′) is the source disturbance function; Ω is the spatiotemporal disturbance kernel function; and Ω is the spatiotemporal integration region of the rail transit network.

[0086] In this embodiment, by setting up virtual energy routers at various transition points and applying local perturbation functions based on their spatiotemporal transition data to construct a perturbation propagation field, the energy state transition process is simulated, enabling precise modeling and controllable intervention of the electrical energy evolution behavior in the rail transit network. This significantly improves system stability and routing adaptability under complex scenarios such as multi-vehicle concurrent operation, fluctuating energy injection, and regenerative braking feedback, effectively supporting the achievement of optimal energy allocation and minimum electrical disturbance control objectives.

[0087] In one exemplary embodiment, such as Figure 6 As shown, the step of analyzing the spatiotemporal-electrical energy relationship of the rail transit network based on the network routing energy data and the network routing spatiotemporal data to obtain spatiotemporal electrical energy distribution data includes steps 602 to 606. Wherein:

[0088] Step 602: Based on the network routing spatiotemporal data, divide the spatial segments and time windows of the rail transit network to obtain each network traffic spatiotemporal cell.

[0089] Step 604: Based on the network routing energy data and the network routing spatiotemporal data, establish the corresponding energy pulse propagation model in each network traffic spatiotemporal cell.

[0090] Step 606: Combine and solve the propagation models of each energy pulse to obtain spatiotemporal electrical energy distribution data.

[0091] In this context, a spatial segment can be a basic physical unit within a rail transit network, defined by dividing the spatial dimensions of the line based on factors such as train operating paths, power supply zones, and track topology. Each spatial segment typically corresponds to an inter-station section, a power supply grid, or a specific control section, used to clearly define the energy behavior of trains at different locations.

[0092] In this context, a time window can be a discretized time interval set to capture the changes in train energy behavior over time when dynamically modeling a rail transit network. Each time window covers a fixed or adaptive length of time period, used to describe the processes of energy injection, transfer, and decay in the system in segments, ensuring the resolution and traceability of the model on the time axis.

[0093] In the context of network traffic spatiotemporal grids, these grids can be considered the fundamental analytical units formed by the two-dimensional intersection of spatial segments and time windows during rail transit energy modeling. Each spatiotemporal grid represents a collection of train operating states, electrical energy injection behaviors, and energy propagation processes within a specific track segment and time window. It serves as the basic grid structure for establishing spatiotemporally coupled energy propagation models, performing pulse disturbance calculations, and predicting system evolution.

[0094] Among them, the energy pulse propagation model can be a physical modeling method in rail transit systems, using train traction or braking behavior as the energy disturbance source, and describing how electrical energy diffuses in space, decays in time, and superimposes or reflects in neighboring cells through mathematical functions. This model can use Gaussian modulation functions, convolution kernel functions, or propagation partial differential equations to simulate the dynamic propagation law of unsteady energy waves in complex rail power supply systems.

[0095] Specifically, based on the train operation path, section distribution, station layout, and train timetable in the network routing spatiotemporal data, the entire rail transit network is spatially discretized and time-sliced. The rail transit network is divided into several "space-time cells" with clear physical boundaries and time coverage as each network traffic space-time cell. Each network traffic space-time cell represents the area of ​​train operation in a certain section and a certain time window.

[0096] Within each defined spatiotemporal cell, combining energy data such as train traction power, braking feedback power, energy inflow and outflow nodes, and power supply status, the electrical disturbances caused by train behavior are used as pulse source terms. The propagation kernel function is used to describe the diffusion of energy in space and its decay or superposition in time, thereby simulating how electrical energy flows, accumulates, or reflects in each cell. The model parameters can be dynamically configured according to the train's operating status, power supply method, and load characteristics, thus constructing an energy pulse propagation model.

[0097] The energy pulse propagation models corresponding to all spatiotemporal cells of the network traffic are fused and iteratively solved. Considering the boundary effects, coupling relationships, and disturbance superposition laws between adjacent cells, a continuous spatiotemporal power distribution data field covering the entire network is formed as spatiotemporal power distribution data. This spatiotemporal power distribution data describes the state and trend of power density at any time and any spatial location.

[0098] In this embodiment, the rail transit network is divided into spatial segments and time windows based on network routing spatiotemporal data to construct a high-resolution network traffic spatiotemporal grid. An energy pulse propagation model is then established within each network traffic spatiotemporal grid. Finally, the entire network model is fused and solved, enabling accurate spatiotemporal modeling and dynamic tracking of electrical disturbances caused by train traction and braking behaviors. This allows for real-time reflection of energy propagation paths, interference regions, and local accumulation effects in the rail network, significantly improving the response speed and distribution control accuracy of energy scheduling in the rail system, and enhancing the system's robustness and predictive ability against energy fluctuations.

[0099] In one exemplary embodiment, such as Figure 7 As shown, the process of fusing and solving each of the energy pulse propagation models to obtain the spatiotemporal electrical energy distribution data includes steps 702 to 708. Wherein:

[0100] Step 702: Apply the power supply events and state change events of each train corresponding to the rail transit network to each energy pulse propagation model to obtain each local energy pulse function.

[0101] Step 704: Perform spatiotemporal superposition processing on each local energy pulse function to obtain the global energy pulse function.

[0102] Step 706: Based on the traction energy consumption of each train in the rail transit network and the braking feedback status of each train, dynamically adjust the amplitude, diffusion coefficient, or frequency parameters of the global energy pulse function to obtain the adjusted energy pulse function.

[0103] Step 708: Use the adjusted energy pulse function to solve for the spatiotemporal grid of each network traffic to obtain spatiotemporal electrical energy distribution data.

[0104] Among them, the train power supply event can be the behavior of a train absorbing electrical energy from the power supply network through the traction system to drive the vehicle during traction operation, which usually occurs in the stages of starting, acceleration, and speed-up. This event is characterized by power demand, duration, location of action, and traction mode, and is the main energy injection source term in the energy pulse propagation model.

[0105] Train state change events can be behaviors that involve a train switching states during operation, such as switching from traction to braking, from acceleration to constant speed, or from running to stopping or waiting. These events may be accompanied by drastic changes or reversals in power output, causing pulse-type disturbances to the power system and are important triggering factors for modeling nonlinear energy propagation behavior.

[0106] Among them, the local energy pulse function can be a mathematical function constructed within a specific spatiotemporal cell based on a single train power supply event or state change event, used to simulate the disturbance effect of the event on the distribution of electrical energy in a local spatial and temporal range. This function usually considers the injection intensity, propagation direction, spatial diffusion and timeliness.

[0107] Spatiotemporal superposition processing can be a process of comprehensively superimposing multiple local energy impulse functions in both spatial and temporal dimensions, taking into account the superposition enhancement, interference reduction and coupling effects of each disturbance source at different lattices and different time points, thereby constructing an overall dynamic energy distribution model.

[0108] The global energy impulse function can be a continuous function that describes the overall electrical energy disturbance distribution of the rail transit system, obtained by spatiotemporally superimposing all local energy impulse functions.

[0109] Among them, train traction energy consumption can be the electrical energy consumed by the train from the power system during traction operation to overcome resistance, accelerate and maintain speed. It is usually closely related to train mass, track gradient, traction mode and operating speed.

[0110] Train braking regenerative braking can be described as a dynamic process in which, during braking, the traction motor reverses to generator mode, converting kinetic energy into electrical energy and feeding it back to the power grid. This state is typically determined by parameters such as braking level, network voltage level, and regenerative braking equipment capacity, and it positively injects energy into the flow of energy.

[0111] Among them, adjusting the energy pulse function can be a new function obtained by dynamically adjusting parameters such as amplitude, diffusion coefficient, and propagation frequency in the pulse function based on the global energy pulse function and according to the real-time collected traction energy consumption and feedback state data, so as to more realistically reflect the energy evolution characteristics of the actual system.

[0112] Specifically, energy supply events (traction power output) and state change events (brake feedback, mode switching, etc.) corresponding to each train in the rail transit network at different operating stages (such as start-up, acceleration, constant speed, deceleration, and stopping) are extracted and input as pulse source terms into the energy pulse propagation model in their respective spatiotemporal lattice. Each event generates a local energy pulse function representing the local energy disturbance behavior by defining parameters such as its energy input / output, action time window, and propagation influence radius.

[0113] The local energy pulse functions generated by all trains in different network traffic spatiotemporal cells are superimposed in space and time. Considering the superposition enhancement, interference reduction and propagation overlap effects between events, a continuous field is formed by using mathematical methods such as integration / convolution with spatiotemporal variables. The dynamic power evolution data of the entire track network under a given schedule are given, and a global energy pulse function reflecting the power disturbance trend of the entire network is constructed.

[0114] The formula for calculating the global energy impulse function is as follows:

[0115]

[0116] Where Π(x,t) is the global energy impulse function; W i (x′,t′) is the self-modulation weighting function of the i-th pulse source at (x′,t′); Γ i (x,t|(x′,t′) is the spatial propagation kernel function of the i-th pulse source propagating from (x′,t′) to (x,t); δE i (x′,t′) represents the local energy injection value of the i-th pulse source in (x′,t′); δ(·) represents the Dirac function; N represents the pulse source identifier; and Ω represents the spatiotemporal integration region of the rail transit network.

[0117] By combining the traction energy consumption and braking feedback status (such as feedback current, voltage, and resistance status) of each train in the rail transit network during actual operation, the key parameters in the original global energy pulse function are dynamically corrected. This includes adjusting the amplitude coefficient to match the actual power input, adjusting the diffusion coefficient to reflect changes in energy propagation speed, or adjusting the frequency parameter to simulate the energy fluctuation cycle and system response delay, thereby generating an adjusted energy pulse function that better fits the physical state and operating behavior.

[0118] By adjusting the energy impulse function, numerical solutions or analytical approximations are performed in each network traffic spatiotemporal cell to obtain the energy density or power state of each network traffic spatiotemporal cell at a specific time. The solution results of all network traffic spatiotemporal cells are merged and reconstructed across the entire network to form continuously distributed spatiotemporal energy distribution data.

[0119] In this embodiment, by mapping the power supply events and state change events of each train in the rail transit network to an energy pulse propagation model, a local energy pulse function is constructed. This is then overlaid across the entire network in a spatiotemporal manner to generate a global energy pulse function. Furthermore, the parameters are dynamically adjusted in conjunction with train traction energy consumption and braking feedback states. Ultimately, this achieves high-precision energy solutions for each network's spatiotemporal lattice, effectively reconstructing the dynamic electrical energy evolution process of the rail transit system. The system's ability to respond to and predict asynchronous operation of multiple trains, energy fluctuation propagation, and energy reconstruction paths in real time enhances the visualization and control level of the rail transit power supply system, the efficiency of feedback energy utilization, and the overall stability and robustness of the power supply system.

[0120] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0121] Based on the same inventive concept, this application also provides an adaptive control device for an urban rail transit energy router used to implement the adaptive control method for the urban rail transit energy router described above. For example... Figure 8 As shown, it includes: a network data acquisition module 802, a distributed data calculation module 804, an evolution data calculation module 806, and a control data acquisition module 808. The solution provided by this device is similar to the solution described in the above method. Therefore, the specific limitations of one or more adaptive control device embodiments of urban rail transit energy routers provided below can be found in the limitations of an adaptive control method for an urban rail transit energy router described above, and will not be repeated here.

[0122] The various modules in the aforementioned adaptive control device for an urban rail transit energy router can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the corresponding operations of each module.

[0123] In one exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 9 As shown, this computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operating system and computer programs stored in the non-volatile storage media. The database stores server data. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communication with external terminals via a network connection. When executed by the processor, the computer program implements an adaptive control method for an urban rail transit energy router.

[0124] Those skilled in the art will understand that Figure 9 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0125] In one embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above method embodiments.

[0126] In one embodiment, a computer-readable storage medium is provided storing a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0127] In one embodiment, a computer program product or computer program is provided, the computer program product or computer program including computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and executes the computer instructions, causing the computer device to perform the steps in the above method embodiments.

[0128] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0129] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0130] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0131] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. An adaptive control method for an urban rail transit energy router, characterized in that, The method includes: Acquire network routing energy data and network routing spatiotemporal data corresponding to the rail transit network; Based on the network routing energy data and the network routing spatiotemporal data, the spatiotemporal-electrical energy relationship of the rail transit network is analyzed to obtain spatiotemporal electrical energy distribution data; The spatiotemporal power distribution data are subjected to energy state transition analysis to obtain real-time network energy state evolution data; Using the real-time evolution data of the network energy state, the calculation parameters of the spatiotemporal power distribution data are adjusted until the stability of the real-time evolution data of the network energy state meets the preset stability parameters, thereby obtaining the network energy routing control data corresponding to the rail transit network.

2. The method according to claim 1, characterized in that, The analysis of the spatiotemporal electrical energy distribution data to obtain real-time network energy state evolution data includes: Perform type transition path planning on the spatiotemporal power distribution data to obtain the spatiotemporal data of the transition point execution; The spatiotemporal data of the transition points are used to perform class-based transition control to obtain the real-time evolution data of the network energy state.

3. The method according to claim 2, characterized in that, The step of performing class-based transition path planning on the spatiotemporal power distribution data to obtain the spatiotemporal data of the transition point execution includes: Based on the network routing energy data and the network routing spatiotemporal data, the target energy state corresponding to the rail transit network is set; Using the principle of minimum dissipation, the spatiotemporal energy distribution data and the target-like energy state are calculated to form a spatiotemporal energy transition sequence. The execution time and execution location of various transition points are determined from the spatiotemporal electrical energy transition sequence to obtain the spatiotemporal data of the transition point execution.

4. The method according to claim 2, characterized in that, The step of performing spatiotemporal transition control on the transition points to obtain the real-time evolution data of the network energy state includes: Virtual energy routers are set up at various transition points in the real-time evolution data of the network energy state to obtain router-type spatiotemporal transition data; A local perturbation function is applied to the spatiotemporal transition data of the router class to obtain the spatiotemporal perturbation field of the router class; The energy state transitions of each virtual energy router are simulated in the spatiotemporal perturbation field of the router class to obtain real-time evolution data of the network energy state.

5. The method according to claim 4, characterized in that, The calculation formula for the router-type spatiotemporal disturbance field is as follows: Ψ(x,t)=ρ(x,t)·e iθ(x,t) in, For the spatiotemporal perturbation field of the router class; i is the imaginary unit; Ψ(x,t) is Planck's constant; Ψ(x,t) is the energy-like state function; ρ(x,t) is the energy density function; θ(x,t) is the energy phase function; x is the first spatial variable; t is the first time variable; x′ is the second spatial variable; t′ is the second time variable; It is an intrinsic Hamiltonian operator; Γ(x′,t′) is the local perturbation function; K(xx′,tt′) is the source perturbation function; Ω is the spatiotemporal perturbation kernel function; and Ω is the spatiotemporal integration region of the rail transit network.

6. The method according to claim 1, characterized in that, The step involves analyzing the spatiotemporal-electrical energy relationship of the rail transit network based on the network routing energy data and the network routing spatiotemporal data to obtain spatiotemporal electrical energy distribution data, including: Based on the network routing spatiotemporal data, the spatial segments and time windows of the rail transit network are divided to obtain each network traffic spatiotemporal cell; Based on the network routing energy data and the network routing spatiotemporal data, a corresponding energy pulse propagation model is established in each of the network traffic spatiotemporal cells; By integrating and solving the various energy pulse propagation models, the spatiotemporal electrical energy distribution data are obtained.

7. The method according to claim 6, characterized in that, The fusion solution of each of the energy pulse propagation models yields the spatiotemporal electrical energy distribution data, including: The energy supply events and state change events of each train corresponding to the rail transit network are respectively applied to the energy pulse propagation models to obtain local energy pulse functions. The local energy pulse functions are spatiotemporally superimposed to obtain the global energy pulse function. Based on the traction energy consumption of each train in the rail transit network and the braking feedback status of each train, the amplitude, diffusion coefficient, or frequency parameters of the global energy pulse function are dynamically adjusted to obtain the adjusted energy pulse function. Using the adjusted energy pulse function, the spatiotemporal grids of each network traffic are solved to obtain the spatiotemporal electrical energy distribution data.

8. The method according to claim 7, characterized in that, The formula for calculating the global energy impulse function is as follows: Where Π(x,t) is the global energy impulse function; W i (x′,t′) is the self-modulation weighting function of the i-th pulse source at (x′,t′); Γ i (x,t)|(x′,t′) is the spatial propagation kernel function of the i-th pulse source propagating from (x′,t′) to (x,t); δE i (x′,t′) represents the local energy injection value of the i-th pulse source in (x′,t′); δ(·) represents the Dirac function; N represents the pulse source identifier; and Ω represents the spatiotemporal integration region of the rail transit network.

9. An adaptive control device for an urban rail transit energy router, characterized in that, The device includes: The network data acquisition module is used to acquire network routing energy data and network routing spatiotemporal data corresponding to the rail transit network. The distribution data calculation module is used to analyze the spatiotemporal-electrical energy relationship of the rail transit network based on the network routing energy data and the network routing spatiotemporal data, and obtain spatiotemporal electrical energy distribution data. The evolution data calculation module is used to perform energy state transition analysis on the spatiotemporal electrical energy distribution data to obtain real-time network energy state evolution data; The control data acquisition module is used to adjust the calculation parameters of the spatiotemporal power distribution data using the real-time evolution data of the network energy state until the stability of the real-time evolution data of the network energy state meets the preset stability parameters, thereby obtaining the network energy routing control data corresponding to the rail transit network.

10. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 8.

Images