Intelligent overload train group cooperative control method and device against sparse data

Abstract

The application provides an anti-sparse data intelligent heavy-haul train group cooperative control method and device, and belongs to the technical field of heavy-haul railway intelligent operation control. The method is based on a pseudo partial derivative linear driving model, which is obtained by dynamic linearization of a train group nonlinear dynamic model along an iteration domain. First, control instructions of each train at the current time, pseudo partial derivative estimation values, distributed cooperative tracking errors and communication transmission state information are acquired. Then, the pseudo partial derivative estimation values and the distributed cooperative tracking errors are updated, and the traction force or braking force instructions of each train at the next time are calculated and sent to the execution mechanism. The application solves the problem of inaccurate cooperative control in the sparse data scene such as limited communication and frequent network attacks in a complex communication environment, improves the stability and safety of train group operation, optimizes the traction and braking control strategy, reduces the traction energy consumption, and realizes the goal of safe, efficient and energy-saving cooperative operation of heavy-haul railway.

Description

Technical Field

[0001] This invention relates to the field of intelligent operation control technology for heavy-haul railways, and in particular to an intelligent collaborative control method and device for heavy-haul train groups that is resistant to sparse data. Background Technology

[0002] With the continuous increase in heavy-haul railway freight volume in my country, heavy-haul trains are developing towards larger traction tonnage, longer formations, and higher-density operation. The coordinated operation control of heavy-haul train groups has become a core technology for ensuring the safety of heavy-haul railway transportation and improving transportation efficiency.

[0003] In existing technologies, based on vehicle-to-vehicle wireless communication technology, the coordinated control of heavy-haul train groups is achieved through the sharing of status information and traction and braking coordination among trains in the heavy-haul train group. This enables precise control of the safe tracking interval between trains, avoiding safety accidents such as rear-end collisions and conflicts. At the same time, it optimizes the operation strategy of the heavy-haul train group, reduces traction energy consumption, and improves the overall transportation efficiency of the heavy-haul train group.

[0004] However, the operating environment of heavy-haul train groups is complex, and the wireless communication between trains is susceptible to terrain obstruction, electromagnetic interference, and other factors. At the same time, they face the threat of network attacks, such as periodic denial-of-service attacks, which can lead to severe packet loss and transmission interruption, forming a typical sparse data transmission scenario. This affects the stability of the coordinated control of heavy-haul train groups, such as deviations in safe distances, decreased synchronization of coordinated commands, and consequently, imbalances in traction and braking coordination, as well as deterioration in the accuracy of speed and relative spacing control between trains. In addition, the use of only simplified dynamic models makes it impossible to accurately predict longitudinal dynamic differences, which can easily lead to disordered train running pace and abnormal following distances, causing formation instability and significantly reducing the overall operational safety and traffic efficiency of heavy-haul train groups. Summary of the Invention

[0005] In view of this, the purpose of the present invention is to provide a method, device, electronic device and storage medium for cooperative control of heavy-load train groups based on anti-sparse data, so as to solve the technical problems of poor stability, safety and traffic efficiency of heavy-load train groups caused by sparse data transmission scenarios in the prior art.

[0006] In a first aspect, embodiments of the present invention provide a cooperative control method for heavy-load train groups based on anti-sparse data. The cooperative control method is based on a linear driving model of pseudo-partial derivatives, which is obtained by performing dynamic linearization processing along the iteration domain on the nonlinear dynamic model of the heavy-load train group. The cooperative control method includes: Obtain control command information for each train in the heavy-load train group at the current moment. The control command information includes traction / control force command, pseudo-partial derivative estimate, distributed cooperative tracking error, and communication transmission status information. When the communication connectivity status information is determined to be in a sparse interruption state, the pseudo-partial derivative estimate and the distributed cooperative tracking error are updated respectively to obtain the updated distributed cooperative tracking error and the updated pseudo-partial derivative estimate. Based on the updated pseudo-partial derivative estimate and the updated distributed cooperative tracking error, the traction / control force command of each train in the heavy-load train group at the next moment is obtained, and the control command information is updated to obtain the updated control command information. The updated control command information is sent to the traction and braking actuator of the heavy-haul train group.

[0007] In conjunction with the first aspect, embodiments of the present invention provide a first possible implementation of the first aspect, wherein determining that the communication connectivity status information is a data sparse interruption state includes: When the value corresponding to the communication connectivity status information is equal to the preset interruption value, the communication connectivity status information is determined to be a data sparse interruption state.

[0008] In conjunction with the first aspect, embodiments of the present invention provide a second possible implementation of the first aspect, wherein updating the pseudo-partial derivative estimate includes: At the current moment, obtain the first increment corresponding to the unit mass traction force / control force of each train in the heavy-haul train group, and the second increment corresponding to the speed of each train in the heavy-haul train group; Based on the speed and pseudo-partial derivative estimates of each train in the heavy-haul train group at the current moment, the first increment and the second increment are weighted to obtain the updated pseudo-partial derivative estimates.

[0009] Optionally, updating the pseudo-partial derivative estimate further includes: At the current moment, if the estimated value of the pseudo-partial derivative of each train is less than or equal to the parameter reset threshold, or the first increment of each train is less than or equal to the parameter reset threshold, or the sign of the pseudo-partial derivative of each train is inconsistent with the sign of the preset initial value of the pseudo-partial derivative, then the pseudo-partial derivative of each train is reset.

[0010] In conjunction with the first aspect, this embodiment of the invention provides a third possible implementation of the first aspect, wherein, before updating the distributed cooperative tracking error, the communication adjacency matrix of the heavy-haul train group is obtained, and the method includes: Obtain the virtual reference train of the heavy-haul train group; Based on the communication adjacency matrix, obtain the target train corresponding to each distributed system tracking error to be updated, and obtain the set of trains adjacent to the target train; The weighted difference between the speed of the target train and the speed of each train in the train set is calculated to determine the coordination value between the target train and its adjacent trains. The difference between the speed of the target train and the speed of the virtual reference train is also calculated to determine the coordination value between the target train and the heavy-haul train group. The updated distributed cooperative tracking error is obtained by summing the cooperative value between the target train and its adjacent trains and the cooperative value between the target train and the heavy-haul train group.

[0011] In conjunction with the first aspect, this embodiment of the invention provides a fourth possible implementation of the first aspect, wherein obtaining the traction / control force command for each train in the heavy-haul train group at the next moment, based on the updated pseudo-partial derivative estimate and the updated distributed cooperative tracking error, includes: Based on model-free adaptive iterative learning control, a preset adjustable step size parameter and a preset positive weighting factor are called to perform weighting processing on the updated pseudo-partial derivative estimate, the updated distributed system tracking error, and the communication transmission status information to obtain the correction amount of the model-free adaptive iterative learning control. Based on the sum of the traction / control force command at the current moment and the correction amount, the traction / control force command at the next moment is obtained.

[0012] Secondly, embodiments of the present invention also provide a cooperative control device for heavy-haul train groups based on anti-sparse data, comprising: The instruction acquisition module is used to acquire the control instruction information of each train in the heavy-load train group at the current moment. The control instruction information includes traction / control force instructions, pseudo-partial derivative estimates, distributed cooperative tracking errors, and communication transmission status information. The sparse data interruption determination and processing module is used to update the pseudo-partial derivative estimate and the distributed cooperative tracking error respectively when the communication connectivity status information is determined to be a sparse data interruption state, so as to obtain the updated distributed cooperative tracking error and the updated pseudo-partial derivative estimate. The control command update module is used to obtain the traction / control force command of each train in the heavy-load train group at the next moment based on the updated pseudo-partial derivative estimate and the updated distributed cooperative tracking error, and to update the control command information to obtain the updated control command information. The control command execution module is used to send the updated control command information to the traction and braking actuator of the heavy-haul train group.

[0013] In conjunction with the second aspect, embodiments of the present invention provide a second aspect, which further includes: The dynamic modeling and model linearization module is used to construct a nonlinear dynamic model of a heavy-haul train based on each train in the heavy-haul train group, and to perform dynamic linearization processing along the iteration domain on the nonlinear dynamic model to establish a linear data-driven model based on pseudo-partial derivatives. The nonlinear dynamic model is used to characterize the additional disturbances of the heavy-haul train group; the linear data-driven model based on pseudo-partial derivatives is used as the technical basis for model-free adaptive iterative learning control.

[0014] Thirdly, embodiments of the present invention also provide an electronic device, comprising: At least one processor; and at least one memory communicatively connected to the processor, wherein: the memory stores program instructions executable by the processor, and the processor invokes the program instructions to execute the heavy-load train group cooperative control method based on anti-sparse data as described in any of the first aspects of the present invention.

[0015] Fourthly, embodiments of the present invention also provide a computer-readable storage medium storing computer instructions that cause the computer to execute the heavy-load train group cooperative control method based on anti-sparse data as described in any of the first aspects of the present invention.

[0016] This invention addresses the data loss and transmission interruption problems caused by Ricean fading and periodic denial-of-service (PDoS) attacks in vehicle-to-vehicle wireless communication, i.e., sparse data transmission scenarios. It constructs a nonlinear dynamic model to characterize the additional disturbances during the operation of a heavy-haul train group and performs dynamic linearization along the iterative domain on the nonlinear dynamic model, establishing a linear data-driven model of pseudo-partial derivatives to achieve online iterative estimation of the pseudo-partial derivatives of the train system. Secondly, to address the sparse data transmission problem caused by channel fading and periodic denial-of-service attacks in vehicle-to-vehicle wireless communication, it introduces random coefficients to characterize data loss and communication interruption features and designs a sparse data compensation mechanism. Subsequently, it constructs the communication topology of the heavy-haul train group, generates the desired trajectory using a virtual reference train, and calculates the distributed cooperative tracking error of each train. Based on the compensated pseudo-partial derivative estimates, the linear data model, and the cooperative tracking error, it designs a model-free adaptive iterative learning cooperative control law resistant to sparse data, generating traction / braking force control commands for each train. Finally, it sends the control commands to the traction and braking actuators of the corresponding trains, driving the heavy-haul train group to cooperatively track the desired trajectory.

[0017] The embodiments of the present invention bring the following beneficial effects: without relying on the accurate dynamic model of heavy-haul trains, the impact of sparse data on cooperative control performance can be effectively suppressed, the operational safety and cooperative efficiency of heavy-haul train groups in complex communication environments can be improved, and it is applicable to automatic driving and cooperative operation scenarios of heavy-haul railway train groups.

[0018] Other features and advantages of the invention will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention are realized and obtained in accordance with the structures particularly pointed out in the description, claims and drawings.

[0019] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0020] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0021] Figure 1 A flowchart illustrating the collaborative control method provided in an embodiment of the present invention; Figure 2 Three-dimensional surface diagram of basic resistance of heavy-haul train group provided in embodiments of the present invention Figure 3 Three-dimensional surface diagram of additional resistance of heavy-haul train groups provided in embodiments of the present invention Figure 4 This is a schematic diagram illustrating the coupling between the periodic denial-of-service attack cycle and the iteration domain, provided in an embodiment of the present invention. Figure 5 This is a schematic diagram of the vehicle-to-vehicle wireless communication transmission status provided in an embodiment of the present invention; Figure 6 This is a schematic diagram of the communication topology of a heavy-haul train group provided in an embodiment of the present invention; Figure 7 This is a trajectory diagram showing the expected speed and position of a heavy-haul train group provided in an embodiment of the present invention. Figure 8 The velocity and position tracking response curves along the iteration axis direction provided in this embodiment of the invention; Figure 9 The maximum speed and position tracking error curve of a heavy-haul train group provided in an embodiment of the present invention.

[0022] Figure 10 A block diagram of an exemplary electronic device provided in an embodiment of the present invention. Detailed Implementation

[0023] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0024] Currently, most collaborative control methods for heavy-haul trains rely on precise dynamic models of the train. However, heavy-haul train systems are characterized by strong nonlinearity, time-varying parameters, and susceptibility to complex disturbances such as track gradients, curves, and wind resistance. It is difficult to establish accurate mathematical models, resulting in poor robustness and insufficient control precision of traditional model-based control methods, which cannot meet the needs of high-density collaborative operation of heavy-haul train groups.

[0025] With the development of data-driven control technology, Model-Free Adaptive Iterative Learning Control (MFAILC) has become a research hotspot in the field of heavy-haul train control because it does not rely on an accurate model of the controlled object and can achieve control using only the system's input and output data. MFAILC can fully utilize the repetitive information from the periodic operation of heavy-haul trains, optimize the control strategy through iterative learning, achieve precise control of the train's operating state, and effectively overcome the control challenges caused by model uncertainty.

[0026] However, most existing MFAILC cooperative control methods for heavy-haul train groups assume ideal, lossless train-to-train communication, failing to adequately consider the sparse data problem caused by channel fading and network attacks in real-world communication. When communication data is sparse, trains cannot obtain complete state information from neighboring trains, leading to spurious partial derivative estimation errors and increased cooperative tracking errors. This severely impacts the cooperative control performance of heavy-haul train groups and can even cause safety accidents. Furthermore, existing methods lack specific compensation mechanisms for sparse data scenarios, making them ineffective in addressing the issue.

[0027] Control requirements in complex communication environments make it difficult to guarantee the safe and efficient collaborative operation of heavy-haul train groups. Therefore, there is an urgent need to develop a collaborative control method for heavy-haul train groups that can effectively cope with sparse data transmission scenarios, in order to meet the development needs of intelligent and safe operation of heavy-haul railways.

[0028] Based on this, embodiments of the present invention provide an intelligent heavy-haul train group cooperative control method and device that resists sparse data, which can meet the requirements of precise control of heavy-haul train groups in complex communication environments, so as to enhance the safety and traffic efficiency of heavy-haul train groups during operation.

[0029] To facilitate understanding of this embodiment, a cooperative control method for heavy-load train groups based on sparse data resistance, as disclosed in this embodiment of the invention, will first be described in detail, referring to... Figure 1 , Figure 1 This is a flowchart illustrating the collaborative control method provided in an embodiment of the present invention. Figure 1 As shown, the collaborative control method includes: Step 101: Obtain the control command information of each train in the heavy-load train group at the current time. The control command information includes traction / control force commands, pseudo-partial derivative estimates, distributed cooperative tracking errors, and communication transmission status information.

[0030] It should be noted that when the control command information of a heavy-haul train group is communicated, if it encounters communication interruption or is attacked, i.e., in a sparse data transmission environment, the control command information is easily interfered with, resulting in deviations in the control command information. The collaborative control method provided by this invention mainly iteratively corrects the control command information of the heavy-haul train group in order to achieve accurate collaborative control of the train group's operation.

[0031] Furthermore, the entities that execute the cooperative control method provided by this invention include, but are not limited to, cooperative control devices or other on-board equipment installed in heavy-haul train groups.

[0032] The collaborative control method provided by this invention is based on a pseudo-partial derivative linear driving model, which can be derived from the nonlinear dynamic model of a heavy-haul train group. Optionally, the nonlinear dynamic model can be dynamically linearized along the iteration domain to obtain the pseudo-partial derivative linear driving model.

[0033] Specifically, for heavy-haul train groups running in the same direction along a heavy-haul railway line, a nonlinear dynamic model is established for each heavy-haul train. The position and speed of the train satisfy the following differential relationship:

[0034]

[0035] in, For time Differential operators; Train number; Runtime; This represents the number of iterations. , The first The train was at Next iteration, time step Position and velocity; For the first The traction or braking force per unit mass of a train; , The first The basic operating resistance and additional operating resistance per unit mass of a train.

[0036] For example, such as Figure 2 As shown, Figure 2 This invention provides a three-dimensional surface diagram of the basic resistance of a heavy-haul train group. It displays the variation of the train's basic resistance with time and iterative batches in the form of a three-dimensional surface. The resistance curve is continuous and smooth, reflecting the time-varying and iterative correlation characteristics of the resistance during the operation of the heavy-haul train group. Correspondingly, as... Figure 3 As shown, Figure 3 This is a three-dimensional surface plot of the additional resistance of a heavy-haul train group provided in an embodiment of the present invention. The plot shows the distribution characteristics of the additional resistance (gradients, curves, tunnels, etc.) of the heavy-haul train group in the time and iteration domains. The resistance variation is related to track conditions, providing a realistic environment input for dynamic modeling and collaborative control design of heavy-haul train groups.

[0037] Furthermore, the above differential model is discretized, with a sampling period (time) of... Time series Basic resistance after discretization and additional resistance This can be represented as the position of the train. The relevant function, where the basic resistance includes an unknown resistance coefficient. , , Additional resistance includes ramp resistance. Curve resistance and tunnel resistance Due to the strong nonlinearity and unknown dynamic characteristics of the above model, it is further simplified to a general form:

[0038] in, It contains all nonlinear and unknown structural information of the model.

[0039] Optionally, the nonlinear dynamic model can be linearized based on the following assumptions and lemmas. Assumption 1: Function about The partial derivatives are continuous; Assumption 2: The system satisfies the generalized Lipschitz condition, that is, for any , ,when When, there exists a constant , making ,in , .

[0040] The nonlinear dynamic model is linearized using pseudo-partial derivatives to obtain a linear driving model. Specifically, the velocity increment is defined as... Combining the dynamic model, we can obtain:

[0041] Defineable, ,Right now:

[0042] Based on the pre-defined mean value theorem, the above equation can be rewritten as:

[0043] in, for for The partial derivatives in and The value at a point between two points.

[0044] Consider the following equation ,for The equation has a unique solution. .make The aforementioned nonlinear driving model can be equivalently linearized into a linear driving model with pseudopartial derivatives. And parameters Bounded.

[0045] Based on the aforementioned method for obtaining the pseudo-partial derivative linear driving model, the estimated value of the pseudo-partial derivative can be obtained by combining the following formula.

[0046]

[0047] in, This introduces a positive weighting factor. Furthermore, the resulting linearized model... Substituting these values ​​into the above formula and minimizing them respectively, we can obtain the method for obtaining pseudo-partial derivative estimates:

[0048] in, It is an adjustable step size factor used to adjust for external disturbances; for The estimated value; After receiving control commands from the main control center, the onboard brain of the heavy-haul train group can receive the commands from the main control center and achieve coordinated control through vehicle-to-vehicle communication.

[0049] The control command information includes traction / control force commands, pseudo-partial derivative estimates, distributed cooperative tracking errors, and communication transmission status information. Specifically, the traction / control force commands characterize the train's operating dynamics; the pseudo-partial derivative estimates are used to characterize the estimation of unknown disturbances during train operation, such as coupling terms, gradient drag, and aerodynamic drag, to facilitate the correction of control command information; the distributed cooperative tracking error characterizes the control gap between a train and its neighboring trains, serving as a feedback quantity for cooperative control; and the communication connectivity status information characterizes the presence of sparse data, such as communication interruptions or attacks.

[0050] The cooperative control method provided by this invention can realize real-time control of heavy-haul train groups, that is, the cooperative control device iteratively corrects the control command information in real time. For example, based on the iterative correction of the control command information at the current moment, the control command information at the current moment is updated as the control command information for the next moment. Here, the moment mentioned in this invention can also be understood as a period.

[0051] Step 102: When the communication connectivity status information is determined to be in a sparse interruption state, the pseudo-partial derivative estimate and the distributed cooperative tracking error are updated respectively to obtain the updated distributed cooperative tracking error and the updated pseudo-partial derivative estimate.

[0052] Specifically, in order to improve the control accuracy of heavy-load train groups, this invention adds the judgment of data sparsity scenarios in communication, so as to correct the data sparsity interruption state, prevent communication data packet loss, communication interruption and other situations, thereby enhancing the accuracy of train-to-train communication.

[0053] Optionally, when the value corresponding to the communication connectivity status information is equal to the preset interruption value, the communication connectivity status information is determined to be a data sparse interruption state.

[0054] In real-world scenarios, communication connectivity information includes, but is not limited to, data packet loss information and communication interruption information. Determining whether the communication connectivity information is in a sparse interruption state includes: when the value corresponding to the data packet loss information is equal to a first preset value, and / or when the value corresponding to the communication interruption information is equal to a second preset value.

[0055] For ease of understanding, the random fading characteristics of vehicle-to-vehicle wireless communication can be characterized using a zero-order Ricean fading model, specifically expressed as:

[0056] in, The speed measurement value at the receiving end. Let be the Rice fading coefficient (which follows a Gaussian distribution). This represents the actual speed value at the sending end. It is zero-mean Gaussian white noise.

[0057] Accordingly, considering the random fading characteristics of wireless communication, a periodic denial-of-service (PDoS) attack model can be adopted, combined with Bernoulli random variables to characterize the sparse interruption state of data, defining... , For two independent Bernoulli random variables: Used to characterize communication interruption information, such as a PDoS attack status. This indicates that there has been no attack and communication is normal. This indicates an attack or communication interruption. In this case, the aforementioned second preset value is set to 0. Used to characterize data packet loss information, that is, the inherent data packet loss state of the channel. This indicates that the data transmission was successful. This indicates data packet loss. In this case, the aforementioned first preset value is set to 0.

[0058] like Figure 4 As shown, Figure 4 This diagram illustrates the coupling between the periodic denial-of-service attack cycle and the iteration domain, as provided in an embodiment of the present invention. kIndicates runtime, i The diagram represents the number of iterations. The physical meanings of the letters in the diagram are consistent with those described above. This diagram visually presents the periodic dormancy and attack phases of a PDoS attack, clearly defining the correspondence between the attack cycle and the train's iterative operation process. By distinguishing between dormancy and attack periods, it provides a clear model basis for designing anti-attack control strategies.

[0059] Comprehensive definition For the final transmission state of vehicle-to-vehicle communication, the following conditions must be met: Communication successful; data received normally. Communication interruption, data sparsity / packet loss: In this case, the preset value is 0; further calculations can be made using mathematical expectation. , The probability of successful communication is represented by the number of trains and the time of travel. Therefore, whether communication is successful or not is related to the train number and the time of travel, but not to the number of iterations.

[0060] Figure 5 This is a schematic diagram of the vehicle-to-vehicle wireless communication transmission status provided in an embodiment of the present invention, such as... Figure 5 As shown in the figure, this diagram illustrates the transmission status of vehicle-to-vehicle communication in the time and iteration domains, distinguishing between successful communication and sparse data packet loss. It visually reflects the communication interruption characteristics caused by Ricean fading and PDoS attacks, providing a basis for sparse data compensation.

[0061] It should be noted that PDoS attacks have a recurring characteristic of periodic dormancy followed by repeated attacks: a complete attack cycle is... ,Include Duration of the dormant phase (attacker accumulates energy, no attack) and The attack phase is lengthy (randomly initiated interruption attack), and communication interruption is only triggered during the attack phase. Simultaneously, the fading coefficient... With communication status They are independent of each other and are unrelated to state variables such as train speed and control force.

[0062] When it is determined that the communication connectivity information is in a sparse interruption state, the control command information at the current moment needs to be corrected, especially the pseudo-partial derivative estimate and the distributed cooperative tracking error mentioned above, in order to improve the accuracy of communication, thereby improving the accuracy of cooperative control of heavy-haul train groups and preventing situations such as tracking distances being too close or too far.

[0063] Optionally, the pseudo-partial derivative estimate can be updated by the following steps: at the current time, obtain the first increment corresponding to the unit mass traction force / control force of each train in the heavy-haul train group, and the second increment corresponding to the speed of each train in the heavy-haul train group; based on the speed and pseudo-partial derivative estimate of each train in the heavy-haul train group at the current time, perform weighted processing on the first increment and the second increment to obtain the updated pseudo-partial derivative estimate.

[0064] Based on the aforementioned process of obtaining pseudo-partial derivatives, and combined with the sparse data compensation mechanism, the update process of the pseudo-partial derivative estimate is executed according to the following formula.

[0065] in, This represents the first increment corresponding to the unit mass traction / control force. This is the second increment corresponding to the speed of each train in the train group.

[0066] This invention not only considers the case of updating the pseudo-partial derivative estimate to deal with tunnels, slopes, and other conditions, but also considers the case of resetting the pseudo-partial derivative to deal with the case where the received speed signal has not changed effectively due to fading or attacks. In this case, the pseudo-partial derivative estimate is reset to a preset initial value.

[0067] Optionally, at the current moment, if the estimated value of the pseudo-partial derivative of each train is less than or equal to the parameter reset threshold, or the first increment of each train is less than or equal to the parameter reset threshold, or the sign of the pseudo-partial derivative of each train is inconsistent with the sign of the preset initial value of the pseudo-partial derivative, then the estimated value of the pseudo-partial derivative of each train shall be reset.

[0068] In addition, when the communication connectivity is interrupted due to sparse data, the update process of the pseudo-partial derivative estimate is frozen to avoid error accumulation.

[0069] The rules for resetting pseudo-partial derivative estimates are set as follows:

[0070] in, Represents a small constant (typically taking the value of 1000). ), For symbolic functions, for The known initial reset values, This represents the increment of the fading rate signal in the iteration direction.

[0071] Optionally, updating the distributed cooperative tracking error can shorten the control gap between vehicles.

[0072] It should be noted that before updating the distributed cooperative tracking error, the communication adjacency matrix of the heavy-haul train group needs to be obtained, and the communication topology of the heavy-haul train group needs to be established so that each train only receives the sparse state information of its neighboring trains. A virtual reference train is introduced to generate the desired trajectory, and the distributed cooperative tracking error of each train is calculated. Among them, the sparse state information includes at least sparse speed signals affected by Ricean fading and periodic denial-of-service (PDoS) attacks.

[0073] Figure 6 This is a schematic diagram of the communication topology for heavy-haul train groups provided in an embodiment of the present invention. Figure 6 As shown in the figure, this diagram illustrates the distributed communication topology of a heavy-haul train group. Each train is represented as a node in a directed graph, with edges representing communication links between trains. The topology is strongly connected, meaning each train only interacts with its adjacent trains, providing a foundation for distributed collaborative control.

[0074] Specifically, the communication adjacency matrix can be obtained based on the communication topology, and the communication topology is constructed based on multi-agent theory, using an order of [missing information]. Strongly connected directed graph Modeling, in which, Indicates that there is One vertex, It is a set of edges. Let represent an adjacency matrix where all elements are non-negative.

[0075] This shall be implemented as follows: Each actual train may only communicate bidirectionally with its directly preceding and / or following adjacent trains; if information from train l can be communicated with the train... If received, then Otherwise ;train The neighbor is represented as Furthermore, the desired trajectory is generated by a virtual reference train, numbered 0; therefore, the extended directed graph is... The order is ,in and These are the corresponding edge matrix and adjacency matrix, respectively. The middle represents the virtual reference train 0 and the trains that follow. The communication relationship between them; if the train The required trajectory can be accessed from train 0. ,otherwise .

[0076] The virtual reference train is not a train in the actual sense, but a virtual benchmark train set up for a train group without mechanical connection during the virtual formation of heavy-haul trains. It is used to unify and coordinate the speed and running curve of each unit to achieve precise coordinated driving.

[0077] Based on the above communication topology, sparse speed signals, and communication state variables, the distributed cooperative tracking error of each train is obtained according to the following formula.

[0078] ; in, This is a distributed cooperative error based on multi-agent theory. The number of trains in the train group. The desired speed trajectory generated for the virtual reference train.

[0079] Figure 7 This is a trajectory diagram showing the expected speed and position of a heavy-haul train group, provided in an embodiment of the present invention. Figure 7 As shown in the figure, this diagram presents the running curves of the desired speed and position of the virtual reference train over time. The trajectory includes the entire process of starting, accelerating, cruising, decelerating, and stopping, serving as a unified target benchmark for coordinated tracking of the train group.

[0080] Step 103: Based on the updated pseudo-partial derivative estimate and the updated distributed cooperative tracking error, obtain the traction / control force command of each train in the heavy-load train group at the next moment, and update the control command information to obtain the updated control command information.

[0081] Optionally, based on model-free adaptive iterative learning control, preset adjustable step size parameters and preset positive weighting factors are invoked to perform weighted processing on the updated pseudo-partial derivative estimate, the updated distributed system tracking error, and the communication transmission status information to obtain the correction amount of model-free adaptive iterative learning control; based on the sum of the traction / control force command at the current moment and the correction amount, the traction / control force command at the next moment is obtained.

[0082] Based on the foregoing understanding, step 103 in this invention can obtain the traction / braking force control command for the next moment according to the following formula:

[0083] in, This refers to the traction / braking force control command for the current iteration cycle. These are adjustable parameters in the controller. pseudo-partial derivatives The estimated value, As a positive weighting factor, This represents the distributed cooperative tracking error for the next time step.

[0084] Therefore, after obtaining the traction / braking force control command for the next moment and updating the pseudo-partial derivative estimate, the control command information corresponding to the next moment can be generated.

[0085] Step 104: Send the updated control command information to the traction and braking actuators of the heavy-haul train group.

[0086] It should be noted that the traction braking actuator mentioned in this invention can be installed or carried in the aforementioned cooperative control device, and / or independently or carried inside the train.

[0087] The traction / braking force control commands are sent to the actuators of the corresponding trains to drive the heavy-haul train group to collaboratively track the desired trajectory. Specifically, the generated control force commands are sent to the first... The traction / braking actuator of the train outputs corresponding traction or braking force according to the command, driving the train to adjust its operating status, realizing precise collaborative tracking of heavy-haul train groups in an environment with sparse data and network attacks, and ensuring the safety and transportation efficiency of heavy-haul railway operation.

[0088] To visually illustrate the accuracy of the method in this embodiment, the effectiveness of the control method of the present invention is verified through numerical simulation and field testing of a high-speed train automatic operation system. Figure 8 The graph shows the velocity and position tracking response along the iteration axis, as provided in an embodiment of the present invention. Figure 8 As shown in the figure, this diagram illustrates the tracking effect of train speed and position as the number of iterations increases. The curve gradually approaches the desired trajectory with each iteration, intuitively verifying the convergence and tracking accuracy of the method of this invention.

[0089] Accordingly, according to the above theory, Figure 9 The maximum speed and position tracking error curves of a heavy-haul train group provided in an embodiment of the present invention are shown. Figure 9 As shown in the figure, the maximum speed of the train group and the position tracking error vary with the number of iterations. The error gradually decreases and tends to stabilize with each iteration, proving that the proposed method still has good control performance in sparse data environments.

[0090] This invention presents a model-free adaptive iterative learning control framework for heavy-haul train groups in sparse data transmission scenarios. Addressing the issues of data loss and transmission interruption caused by Ricean fading and periodic denial-of-service (PDoS) attacks in vehicle-to-vehicle wireless communication, it constructs an iterative domain linear data-driven model incorporating Bernoulli random variables, achieving an accurate and equivalent representation of heavy-haul train systems in sparse data environments. This framework does not rely on a precise dynamic model of the heavy-haul trains; it can complete system modeling using only limited available input and output data. It fundamentally solves the industry pain points of difficult modeling and low data utilization for heavy-haul train groups in complex communication environments, providing a novel technical path for the control of nonlinear complex systems in scenarios with limited communication and frequent network attacks.

[0091] Secondly, this invention designs an online pseudo-partial derivative estimation and adaptive reset mechanism with sparse data compensation. It optimizes the pseudo-partial derivative update logic for scenarios involving communication interruptions and sparse data, and achieves adaptive freezing and correction of control variables through Bernoulli communication state variables, effectively suppressing the negative impact of sparse data on the accuracy of pseudo-partial derivative estimation. Compared to traditional model-free control methods that rely on ideal, lossless communication scenarios, this invention maintains stable estimation performance even under extreme conditions of high data loss rates and persistent network attacks, significantly improving the robustness, anti-interference capabilities, and operational safety of coordinated control of heavy-haul train groups.

[0092] Furthermore, a distributed communication topology and cooperative control strategy adapted to the dynamic operation requirements of heavy-haul train groups were constructed, supporting dynamic switching of the communication topology's iterative domain. This perfectly adapts to dynamic operation scenarios such as heavy-haul train formation and de-formation. Through a distributed cooperative error design that integrates adjacent train status information and the desired trajectory of a virtual reference train, the safe tracking interval between trains is precisely controlled, effectively avoiding major safety risks such as rear-end collisions and conflicts in long-formation operation of heavy-haul trains. At the same time, the overall operation strategy of the train group is optimized, significantly improving the transportation efficiency and line carrying capacity of heavy-haul railways.

[0093] Finally, this invention fully leverages the repetitive information from the periodic operation of heavy-haul trains, relying on the iterative optimization characteristics of iterative learning control to achieve rapid convergence of the iterative domain of the cooperative tracking error, ultimately achieving accurate and complete tracking of the desired trajectory by the heavy-haul train group. Compared to traditional asymptotic tracking control methods, this scheme exhibits faster convergence speed and higher tracking accuracy in scenarios involving heavy-haul trains with large traction tonnage, long operating distances, and complex track conditions. Simultaneously, it optimizes train traction and braking control strategies, effectively reducing traction energy consumption and achieving the goal of safe, efficient, and energy-saving cooperative operation of heavy-haul railways.

[0094] The device provided in this application embodiment has the same implementation principle and technical effect as the aforementioned method embodiment. For the sake of brevity, any parts not mentioned in the device embodiment can be referred to the corresponding content in the aforementioned method embodiment.

[0095] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0096] It should be noted that similar labels and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures.

[0097] Figure 10 A block diagram of an exemplary electronic device provided in an embodiment of the present invention. Figure 10 The electronic device shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0098] like Figure 10 As shown, the electronic device is represented in the form of a general-purpose computing device. The components of the electronic device may include, but are not limited to: one or more processors 410, memory 430, and communication bus 440 connecting different system components (including memory 430 and processing unit 410).

[0099] Communication bus 440 represents one or more of several bus architectures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor, or a local bus using any of the various bus architectures. For example, these architectures include, but are not limited to, Industry Standard Architecture (ISA) buses, Micro Channel Architecture (MAC) buses, Enhanced ISA buses, Video Electronics Standards Association (VESA) local buses, and Peripheral Component Interconnect (PCI) buses.

[0100] Electronic devices typically include a variety of computer-readable media. These media can be any available media that can be accessed by the electronic device, including volatile and non-volatile media, and removable and non-removable media.

[0101] Memory 430 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) and / or cache memory. The electronic device may further include other removable / non-removable, volatile / non-volatile computer system storage media. Memory 430 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of the embodiments of this application.

[0102] A program / utility having a set (at least one) of program modules can be stored in memory 430. Such program modules include—but are not limited to—an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include an implementation of a network environment. The program modules typically perform the functions and / or methods described in the embodiments of this application.

[0103] Processor 410 executes various functional applications and data processing by running programs stored in memory 430, such as implementing embodiments of this application. Figure 1 The method provided in the illustrated embodiment.

[0104] This application provides a non-transitory computer-readable storage medium that stores computer instructions, which cause the computer to execute embodiments of this application. Figure 1 The method provided in the illustrated embodiment.

[0105] The aforementioned computer-readable storage medium may be any combination of one or more computer-readable media. A computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. A computer-readable storage medium may be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer-readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), or flash memory, optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium may be any tangible medium that contains or stores a program that may be used by or in connection with an instruction execution system, apparatus, or device.

[0106] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including—but not limited to—electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, capable of transmitting, propagating, or transmitting programs for use by or in connection with an instruction execution system, apparatus, or device.

[0107] The program code contained on a computer-readable medium may be transmitted using any suitable medium, including—but not limited to—wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0108] Computer program code for performing the operations of the embodiments of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a Local Area Network (LAN) or a Wide Area Network (WAN), or it can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0109] The foregoing has described specific embodiments of this application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps described in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0110] In the description of the embodiments of this application, the terms "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of the embodiments of this application. In the embodiments of this application, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in a suitable manner in any one or more embodiments or examples. Furthermore, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in the embodiments of this application, as well as the features of different embodiments or examples.

[0111] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of embodiments of this application, "multiple" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0112] Any process or method description in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing custom logic functions or processes, and the scope of preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order according to the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0113] Depending on the context, the word "if" as used here can be interpreted as "when," "when," "in response to determination," or "in response to detection." Similarly, depending on the context, the phrase "if determination" or "if detection (of the stated condition or event)" can be interpreted as "when determination," "in response to determination," "when detection (of the stated condition or event)," or "in response to detection (of the stated condition or event)."

[0114] It should be noted that the terminals involved in the embodiments of this application may include, but are not limited to, personal computers (PCs), personal digital assistants (PDAs), wireless handheld devices, tablet computers, mobile phones, MP3 players, MP4 players, etc.

[0115] In the embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual couplings, direct couplings, or communication connections may be through some interfaces; indirect couplings or communication connections between devices or units may be electrical, mechanical, or other forms.

[0116] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in the form of hardware plus software functional units.

[0117] The integrated units implemented as software functional units described above can be stored in a computer-readable storage medium. These software functional units, stored in a storage medium, include several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor to execute some steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0118] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present application should be included within the scope of protection of the present application.

Claims

1. A cooperative control method for heavy-load train groups based on sparse data resistance, characterized in that, The cooperative control method is based on a pseudo-partial derivative linear driving model, which is obtained by performing dynamic linearization along the iteration domain on the nonlinear dynamic model of the heavy-haul train group. The cooperative control method includes: Obtain control command information for each train in the heavy-load train group at the current moment. The control command information includes traction / control force command, pseudo-partial derivative estimate, distributed cooperative tracking error, and communication transmission status information. When the communication connectivity status information is determined to be in a sparse interruption state, the pseudo-partial derivative estimate and the distributed cooperative tracking error are updated respectively to obtain the updated distributed cooperative tracking error and the updated pseudo-partial derivative estimate. Based on the updated pseudo-partial derivative estimate and the updated distributed cooperative tracking error, the traction / control force command of each train in the heavy-load train group at the next moment is obtained, and the control command information is updated to obtain the updated control command information. The updated control command information is sent to the traction and braking actuator of the heavy-haul train group.

2. The collaborative control method according to claim 1, characterized in that, The determination that the communication connectivity status information is in a sparse interruption state includes: When the value corresponding to the communication connectivity status information is equal to the preset interruption value, the communication connectivity status information is determined to be a data sparse interruption state.

3. The collaborative control method according to claim 1, characterized in that, The process of updating the pseudo-partial derivative estimate includes: At the current moment, obtain the first increment corresponding to the unit mass traction force / control force of each train in the heavy-haul train group, and the second increment corresponding to the speed of each train in the train group; Based on the speed and pseudo-partial derivative estimates of each train in the heavy-haul train group at the current moment, the first increment and the second increment are weighted to obtain the updated pseudo-partial derivative estimates.

4. The collaborative control method according to claim 3, characterized in that, Also includes: At the current moment, if the estimated value of the pseudo-partial derivative of each train is less than or equal to the parameter reset threshold, or the first increment of each train is less than or equal to the parameter reset threshold, or the sign of the pseudo-partial derivative of each train is inconsistent with the sign of the preset initial value of the pseudo-partial derivative, then the estimated value of the pseudo-partial derivative of each train is reset.

5. The collaborative control method according to claim 1, characterized in that, Before updating the distributed cooperative tracking error, the method involves obtaining the communication adjacency matrix of the heavy-haul train group. Obtain the virtual reference train of the heavy-haul train group; Based on the communication adjacency matrix, obtain the target train corresponding to each distributed system tracking error to be updated, and obtain the set of trains adjacent to the target train; The weighted difference between the speed of the target train and the speed of each train in the train set is calculated to determine the coordination value between the target train and its adjacent trains. The difference between the speed of the target train and the speed of the virtual reference train is also calculated to determine the coordination value between the target train and the heavy-haul train group. The updated distributed cooperative tracking error is obtained by summing the cooperative value between the target train and its adjacent trains and the cooperative value between the target train and the heavy-haul train group.

6. The cooperative control method according to claim 1, characterized in that, Based on the updated pseudo-partial derivative estimate and the updated distributed cooperative tracking error, the traction / control force command for each train in the heavy-haul train group at the next moment is obtained, including: Based on model-free adaptive iterative learning control, a preset adjustable step size parameter and a preset positive weighting factor are called to perform weighting processing on the updated pseudo-partial derivative estimate, the updated distributed system tracking error, and the communication transmission status information to obtain the correction amount of the model-free adaptive iterative learning control. Based on the sum of the traction / control force command at the current moment and the correction amount, the traction / control force command at the next moment is obtained.

7. A cooperative control device for heavy-load train groups based on sparse data resistance, characterized in that, include: The instruction acquisition module is used to acquire the control instruction information of each train in the heavy-load train group at the current moment. The control instruction information includes traction / control force instructions, pseudo-partial derivative estimates, distributed cooperative tracking errors, and communication transmission status information. The data sparse interruption determination and processing module is used to update the pseudo-partial derivative estimate and the distributed cooperative tracking error respectively when the communication connectivity status information is determined to be a data sparse interruption state, so as to obtain the updated distributed cooperative tracking error and the updated pseudo-partial derivative estimate. The control command update module is used to obtain the traction / control force command of each train in the heavy-load train group at the next moment based on the updated pseudo-partial derivative estimate and the updated distributed cooperative tracking error, and to update the control command information to obtain the updated control command information. The control command execution module is used to send the updated control command information to the traction and braking actuator of the heavy-haul train group.

8. The cooperative control device according to claim 7, characterized in that, The collaborative control device also includes: The dynamic modeling and model linearization module is used to construct a nonlinear dynamic model of a heavy-haul train based on each train in the heavy-haul train group, and to perform dynamic linearization processing along the iteration domain on the nonlinear dynamic model to establish a linear data-driven model with pseudo-partial derivatives. The nonlinear dynamic model is used to characterize the additional disturbances of the heavy-haul train group; the linear data-driven model based on pseudo-partial derivatives is used as the technical basis for model-free adaptive iterative learning control.

9. An electronic device, characterized in that, include: At least one processor; as well as At least one memory communicatively connected to the processor, wherein: The memory stores program instructions that can be executed by the processor, and the processor can execute the heavy-load train group cooperative control method based on anti-sparse data as described in any one of claims 1 to 6 by calling the program instructions.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause the computer to execute the heavy-haul train group cooperative control method based on anti-sparse data as described in any one of claims 1 to 6.

Images