A Data-Driven Switching Gain State Estimation Method for Connected Vehicles

Abstract

This invention relates to a data-driven switching gain state estimation method for connected vehicles. The method includes: collecting system data from various subsystems within the connected vehicle to construct a nonlinear network system as a state-space model; collecting process data and establishing a data-driven switching gain state observer; defining error data and constructing an error system; setting stable operating conditions for the nonlinear network system based on constant quantities and the gain matrix; and operating the nonlinear network system under stable conditions to achieve data-driven switching gain state estimation for the connected vehicle. By collecting a large amount of system data from various subsystems within the connected vehicle for extraction, insight, and prediction, the method emphasizes both data quantity and quality, enabling the connected vehicle to exhibit adaptive and flexible characteristics. Because a data-driven switching gain state observer is established, real-time monitoring and switching gain control of the network system can be performed to improve the efficiency and quality of network data transmission and ensure the stability of the connected vehicle's operation.

Description

Technical Field

[0001] This invention relates to the field of connected vehicle automation control technology, and in particular to a data-driven switching gain state estimation method for connected vehicles. Background Technology

[0002] Connected vehicles utilize modern communication technologies, automatic control technologies, onboard self-sensing technologies, and cloud computing platforms to achieve information exchange and sharing between vehicles, between vehicles and roads, between vehicles and people, and between vehicles and cloud platforms. Through sensors, cameras, GPS, and onboard terminals installed on the vehicles, they collect information about the vehicle's own status and the external environment, and transmit this information to other vehicles, traffic management systems, or cloud platforms via a network system. Currently, connected vehicles are widely used in daily life, making a significant contribution to the development of a networked information society. The development of connected vehicles is rapid due to the increasing demand for road transportation tools from users and the growing requirements for convenient driving, which traditional vehicles can no longer meet. Connected vehicles primarily exchange information such as vehicle location, speed, direction of travel, and roadside infrastructure directly through the network, improving driving safety and reducing traffic accidents. It is worth noting that during network information transmission, it is essential to strengthen the control of system stability, which requires the design of comprehensive data communication system control methods to ensure the effectiveness of data transmission between connected vehicles.

[0003] With the development of intelligent connected vehicle technology, the transmission of data via networks not only faces privacy challenges such as the leakage of personal information, but also needs to address new safety issues such as the increasing number of intelligent connected vehicles losing control during operation. Furthermore, due to incomplete environmental perception and road planning decisions, as well as cost factors, it is not possible to effectively handle various issues affecting driving safety.

[0004] Therefore, traditional connected vehicles often experience unstable network transmissions in the face of unexpected situations on the road, which can affect driving safety. Summary of the Invention

[0005] Based on this, in order to solve the above technical problems, a data-driven switching gain state estimation method for connected vehicles is provided, which can improve the transmission speed and quality of network data under unstable network transmission conditions.

[0006] A method for estimating the switching gain state of connected vehicles driven by data, the method comprising:

[0007] System data from each subsystem in a connected vehicle are collected separately, and a nonlinear network system is constructed as a state-space model based on the system data.

[0008] Collect process data generated during the operation of each subsystem in the state-space model;

[0009] Determine the observability constant, and based on the observability constant, the state-space model, and the process data, establish a data-driven switching gain state observer;

[0010] Define error data, and construct an error system for the data-driven switching gain state observer based on the error data;

[0011] Determine the constant quantity for the convergence of the nonlinear network system, determine the gain matrix under data-driven switching gain state observer based on the data-driven method, and set the stable operating conditions of the nonlinear network system according to the constant quantity and the gain matrix.

[0012] The nonlinear network system operates under the stable operating conditions to achieve data-driven switching gain state estimation for connected vehicles.

[0013] In one embodiment, system data from each subsystem of the connected vehicle are collected, and a nonlinear network system is constructed as a state-space model based on the system data, including:

[0014] Determine the system state and input data parameters of each subsystem in each connected vehicle, and determine the forward component corresponding to the system state;

[0015] Obtain vector-valued continuous functions and unknown Euclidean matrix spaces;

[0016] Based on the vector-valued continuous function and the unknown Euclidean matrix space, the system state, input data parameters, and forward components are used as system data to construct a nonlinear network system composed of the various subsystems with unknown parameters as a state-space model.

[0017] In one embodiment, an observability constant is determined, and based on the observability constant, the state-space model, and the process data, a data-driven switching gain state observer is established, including:

[0018] Obtain the gain matrix, and establish a state observer under the conventional model based on the gain matrix and the state space model;

[0019] Determine the observability constant, and establish a data-driven switching gain state observer based on the state observer using the process data;

[0020] The data-driven switching gain state observer satisfies the observability constant.

[0021] In one embodiment, error data is defined, and an error system is constructed for the data-driven switched gain state observer based on the error data, including:

[0022] Define error data, and determine the error representation of the nonlinear network system under the data-driven switched gain state observer based on the error data;

[0023] The error representation of the linear network system is adjusted to be equivalently represented as an error system, thus completing the construction of the error system of the data-driven switching gain state observer.

[0024] In one embodiment, a constant quantity for the convergence of the nonlinear network system is determined, a gain matrix under data-driven switching gain state observer is determined based on the data-driven switching gain state observer, and stable operating conditions of the nonlinear network system are set according to the constant quantity and the gain matrix, including:

[0025] Given that the data-driven switching gain state observer satisfies the observability constant, design initial constants and initial matrices;

[0026] The constants for convergence of the nonlinear network system are determined based on the initial constants, and the gain matrix under data-driven conditions is determined based on the initial matrix.

[0027] The stable operating conditions of the nonlinear network system are set based on the constants and the gain matrix.

[0028] In one embodiment, the method further includes:

[0029] Stability analysis of the nonlinear network system was performed using Lyapunov functions, and the analysis results were obtained.

[0030] The nonlinear network system is adjusted based on the analysis results.

[0031] In one embodiment, the stability analysis of the nonlinear network system is performed using Lyapunov functions, including:

[0032] The initial matrix is ​​calculated using Schur's complement lemma, and the calculated matrix is ​​then substituted into the gain matrix to obtain the target matrix;

[0033] Set the switching time and switching period, and use the Lyapunov function to perform stability analysis on the nonlinear network system based on the switching time and switching period.

[0034] In one embodiment, the method further includes:

[0035] Determine the switching sequence, and for the switching sequence, perform stability analysis using the Lyapunov function based on the initial matrix;

[0036] During the stability analysis, the Lyapunov function decreases with a minimum exponential convergence rate, indicating that the nonlinear network system is stable.

[0037] A data-driven switching gain state estimation system for connected vehicles, the system comprising:

[0038] The model building module is used to collect system data from each subsystem in a connected vehicle and construct a nonlinear network system as a state-space model based on the system data.

[0039] The process data collection module is used to collect process data generated during the operation of each subsystem in the state space model.

[0040] An observer establishment module is used to determine the observability constant and, based on the observability constant, the state-space model, and the process data, establish a data-driven switching gain state observer.

[0041] An error construction module is used to define error data and construct an error system for the data-driven switching gain state observer based on the error data.

[0042] The operating condition setting module is used to determine the constant quantity for the convergence of the nonlinear network system, determine the gain matrix under data driving based on the data-driven switching gain state observer, and set the stable operating conditions of the nonlinear network system according to the constant quantity and the gain matrix.

[0043] The gain state estimation module is used by the nonlinear network system to achieve data-driven switching gain state estimation of connected vehicles under the stable operating conditions.

[0044] The aforementioned data-driven switching gain state estimation method for connected vehicles extracts, understands, and predicts data by collecting a large amount of system data from various subsystems within the connected vehicle. It emphasizes both data quantity and quality, enabling connected vehicles to exhibit adaptive and flexible characteristics. Furthermore, the establishment of a data-driven switching gain state observer allows for real-time monitoring and control of the switching gain of the network system, thereby improving the efficiency and quality of network data transmission and ensuring the stability of connected vehicle operation. Attached Figure Description

[0045] Figure 1 This is a diagram illustrating the application environment of a data-driven switching gain state estimation method for connected vehicles in one embodiment.

[0046] Figure 2This is a flowchart illustrating a data-driven switching gain state estimation method for connected vehicles in one embodiment.

[0047] Figure 3 This is a data-driven switching gain switching control structure diagram of a nonlinear network system in one embodiment;

[0048] Figure 4 This is a block diagram of a data-driven switching gain state estimation system for connected vehicles in one embodiment;

[0049] Figure 5 This is an internal structure diagram of the back-end control center in one embodiment. Detailed Implementation

[0050] 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.

[0051] Data-driven control is a business decision-making and action approach based on lean analytics and data closed-loop principles. Its core lies in utilizing massive amounts of data for extraction, insight, and prediction. It emphasizes both data volume and quality, exhibiting adaptive and flexible characteristics, and employs machine learning algorithms for pattern recognition and prediction. Compared to traditional driven methods, data-driven approaches do not rely on predefined models. When the system is disrupted by external environmental or internal factors, it can switch to a pre-defined controller, improving the stability of the control system and achieving better dynamic performance.

[0052] The connected vehicle data-driven switching gain state estimation method provided in this application embodiment can be applied to, for example... Figure 1 The application environment shown. For example... Figure 1As shown, the application environment includes a back-end control center 110 and various connected vehicles 120. The back-end control center 110 communicates with each connected vehicle 120 via a network. The back-end control center 110 can collect system data from the subsystems of each connected vehicle and construct a nonlinear network system as a state-space model based on the system data. The back-end control center 110 can collect process data generated during the operation of each subsystem in the state-space model. The back-end control center 110 can determine observability constants and establish a data-driven switching gain state observer based on the observability constants, the state-space model, and the process data. The back-end control center 110 can define error data and construct an error system for the data-driven switching gain state observer based on the error data. The back-end control center 110 can determine the constants for convergence of the nonlinear network system, determine the gain matrix under data-driven conditions based on the data-driven switching gain state observer, and set stable operating conditions for the nonlinear network system based on the constants and the gain matrix. The back-end control center 110 can operate the nonlinear network system under stable operating conditions to achieve data-driven switching gain state estimation for connected vehicles. The back-end control center 110 can be, but is not limited to, various personal computers, laptops, and other devices.

[0053] In one embodiment, such as Figure 2 As shown, a method for estimating the switching gain state of connected vehicles driven by data is provided, including the following steps:

[0054] Step 202: Collect system data from each subsystem of the connected vehicle, and construct a nonlinear network system as a state-space model based on the system data.

[0055] A state-space model of the nonlinear network system of connected vehicles can be established at the back-end control center. Specifically, in one embodiment, a data-driven switching gain state estimation method for connected vehicles may further include the process of constructing a state-space model. The specific process includes: determining the system state and input data parameters of each subsystem in each connected vehicle, and determining the forward component corresponding to the system state; obtaining a vector-valued continuous function and an unknown Euclidean matrix space; and based on the vector-valued continuous function and the unknown Euclidean matrix space, using the system state, input data parameters, and forward components as system data, constructing a nonlinear network system composed of various subsystems with unknown parameters as a state-space model.

[0056] The back-end control center first establishes a nonlinear network system consisting of M interrelated subsystems in the connected vehicle, in the following form:

[0057]

[0058] in, x represents z The forward component, Let n be the state of the z-th subsystem of the connected vehicle at time k. z Let z be the state dimension of the z-th subsystem; Let m be the input amount of the data packet in the z-th subsystem of the connected vehicle at time k. z The amount of data input to the z-th subsystem; and Let s be the number of data points obtained by the z-th subsystem of the connected vehicle through sensor measurements. z Let be the dimension of the measurement data obtained for the z-th subsystem. and It is a vector-valued continuous function; and They represent n z ×m z In an unknown Euclidean matrix space, for formula (1), if the z-th subsystem can receive information from the o-th subsystem, then... otherwise

[0059] Next, the back-end control center can design a nonlinear network system consisting of M interrelated subsystems with unknown exact parameters, where continuous functions exist. Make and For all and It holds true, and we assume ||d z (x z )||≤ε||x z ||, then we have:

[0060]

[0061] Where ε is a constant that satisfies the nonlinear network model. and B z , It is unknown.

[0062] Step 204: Collect process data generated during the operation of each subsystem in the state-space model.

[0063] The collected process data can be represented as follows:

[0064]

[0065] And assume achievable

[0066]

[0067] Step 206: Determine the observability constants, and based on the observability constants, state-space model, and process data, establish a data-driven switching gain state observer.

[0068] Specifically, establishing a data-driven switching gain state observer can include two processes: establishing a state observer under a conventional model and establishing a data-driven state observer using collected process data.

[0069] In one embodiment, a data-driven switching gain state estimation method for connected vehicles may further include the process of establishing a data-driven switching gain state observer. The specific process includes: obtaining the gain matrix, establishing a state observer under a conventional model based on the gain matrix and the state space model; determining the observability constant, and establishing a data-driven switching gain state observer based on the state observer using process data; wherein the data-driven switching gain state observer satisfies the observability constant.

[0070] The establishment of a state observer under the conventional model can be represented as follows:

[0071]

[0072] Where σ∈{1,2}, yes The estimated value, and It is the gain matrix.

[0073] Next, the back-end control center establishes a data-driven state observer based on the collected process data, which can be specifically represented as:

[0074]

[0075] in, and It is a row with full rank. It satisfies the following formula:

[0076]

[0077] Next, it is necessary to ensure the observability of formula (4):

[0078]

[0079] in, As a constant for the observability of connected vehicle systems.

[0080] Step 208: Define error data and construct an error system based on the error data to drive the data-driven switching gain state observer.

[0081] In one embodiment, a data-driven switching gain state estimation method for connected vehicles may further include a process of constructing an error system. The specific process includes: defining error data and determining the error representation of the nonlinear network system under the data-driven switching gain state observer based on the error data; adjusting the error representation of the linear network system to form an equivalent representation of the error system, thereby completing the construction of the error system of the data-driven switching gain state observer.

[0082] Define error Therefore, under the data-driven switching gain state observer, the error system of the connected vehicle system can be expressed as:

[0083]

[0084] in,

[0085] Specifically, definition and The error system formula (5) can be equivalently expressed as:

[0086]

[0087] in,

[0088] Step 210: Determine the constants for convergence of the nonlinear network system, determine the gain matrix under data-driven switching gain state observer, and set the stable operating conditions of the nonlinear network system according to the constants and the gain matrix.

[0089] In one embodiment, a data-driven switching gain state estimation method for connected vehicles may further include a process of setting stable operating conditions for a nonlinear network system. The specific process includes: designing initial constants and an initial matrix when the data-driven switching gain state observer satisfies the observability constant; determining the constants for convergence of the nonlinear network system based on the initial constants, and determining the gain matrix under data-driven conditions based on the initial matrix; and setting stable operating conditions for the nonlinear network system based on the constants and the gain matrix.

[0090] In this embodiment, the conditions for the stable operation of the connected vehicle system are designed as follows:

[0091] Assuming the observable row of the data-driven switching gain state observer holds, the design constant ε > 0. τ>0, 0<μ σ <1 and matrix σ∈{1,2} makes

[0092]

[0093] P1≥(1-μ2) τ P2, P2≥(1-μ1) τ P1, (8)

[0094] in, μ σ It is a constant that ensures the convergence of the connected vehicle system.

[0095]

[0096] The data-driven gain matrix is:

[0097]

[0098] Step 212: The nonlinear network system operates under stable conditions to achieve data-driven switching gain state estimation for connected vehicles.

[0099] In one embodiment, the provided method for estimating the state of data-driven switching gain of connected vehicles may further include a process of performing stability analysis on the network. The specific process includes: performing stability analysis on the nonlinear network system using Lyapunov functions to obtain analysis results; and adjusting the nonlinear network system based on the analysis results.

[0100] Specifically, in this embodiment, when performing stability analysis, the initial matrix can be calculated using Schur's complement lemma, and the calculated matrix can be substituted into the gain matrix to obtain the target matrix; the switching time and switching period are set, and the stability analysis of the nonlinear network system is performed using Lyapunov functions based on the switching time and switching period.

[0101] When analyzing the stability of nonlinear network systems for connected vehicles, equation (7) can be calculated using Schur's complement lemma, yielding the following result.

[0102] Substituting formula (9) into formula (10) yields:

[0103]

[0104] in,

[0105] Next, the switching time k can be designed. n and switching period k n +τ, choosing the Lyapunov function Make: Based on the above assumption ||d z (x z )‖≤ε‖x z || Can be given We can obtain:

[0106] in,

[0107] Based on the designed stable operating conditions of the system, we know that:

[0108] ΔV σ (k n )≤-μ σ V σ (k n (13)

[0109] Therefore, we can conclude that:

[0110] V1(k n +τ)≤(1-μ1)V1(k n +τ-1)≤(1-μ1) 2 V1(k n +τ-2)≤…≤(1-μ1) τ V1(k n (14)

[0111] Using the same method, we can obtain:

[0112] V2(k n +τ)≤(1-μ2) τ V2(k n ),(15)

[0113]

[0114] V2(k n +τ)≤V1(k n (17)

[0115] The above analysis shows that the Lyapunov function in the system decreases based on the minimum exponential μ2 convergence rate.

[0116] In another embodiment, the provided method for estimating the switching gain state of connected vehicle data-driven systems may further include a stability analysis process, which specifically includes: determining a switching sequence; for the switching sequence, performing stability analysis using a Lyapunov function based on an initial matrix; during the stability analysis, the Lyapunov function decreases with a minimum exponential convergence rate, indicating that the nonlinear network system is stable.

[0117] Where, for the switching sequence 0≤k n <k n +τ<k n +2τ<…<k n +mτ. Combining formulas (8), (13), (14), and (17), we can obtain:

[0118] V2(k n +mτ)≤V1(k n +(m-1)τ)≤(1-μ1) τ V1(k n +(m-2)τ))≤V2(k n +(m-3)τ))≤(1-μ2) τ V2(k n +(m-4)τ))≤V1(k n +(m-5)τ))≤…≤V σ (k n ),σ={1,2}, (18)

[0119] This indicates that the Lyapunov function decreases with a minimum exponential convergence rate regardless of whether a switch occurs. Therefore, the estimation error converges to 0, meaning the system is globally asymptotically stable.

[0120] In one embodiment, a data-driven switching gain switching control structure diagram for a nonlinear network system is provided as follows: Figure 3 As shown: Under the action of the driver, each connected vehicle starts to work, and collects system data from each unknown subsystem in each connected vehicle through sensors; extracts the process data generated by each unknown subsystem, and then establishes a data-driven switching gain state observer, thereby realizing data-driven switching gain state estimation of connected vehicles through the network.

[0121] It should be understood that although the steps in the flowchart above are shown sequentially as indicated by 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 flowchart above may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the sub-steps or stages of other steps.

[0122] In one embodiment, such as Figure 4 As shown, a data-driven switching gain state estimation system for connected vehicles is provided, comprising: a model building module 410, a process data collection module 420, an observer establishment module 430, an error construction module 440, an operating condition setting module 450, and a gain state estimation module 460, wherein:

[0123] The model building module 410 is used to collect system data of each subsystem in the connected vehicle and build a nonlinear network system as a state space model based on the system data.

[0124] The process data collection module 420 is used to collect process data generated during the operation of each subsystem in the state-space model.

[0125] The observer establishment module 430 is used to determine the observability constant and establish a data-driven switching gain state observer based on the observability constant, state-space model, and process data.

[0126] Error construction module 440 is used to define error data and construct an error system based on the error data to drive the data switching gain state observer.

[0127] The operating condition setting module 450 is used to determine the constants for the convergence of the nonlinear network system, determine the gain matrix under data-driven switching gain state observer based on the data-driven method, and set the stable operating conditions of the nonlinear network system according to the constants and the gain matrix.

[0128] The gain state estimation module 460 is used to realize the gain state estimation of connected vehicle data-driven switching under stable operating conditions in nonlinear network systems.

[0129] In one embodiment, the model building module 410 is further used to determine the system state and input data parameters of each subsystem in each connected vehicle, and to determine the forward component corresponding to the system state; to obtain the vector-valued continuous function and the unknown Euclidean matrix space; and based on the vector-valued continuous function and the unknown Euclidean matrix space, to construct a nonlinear network system composed of each subsystem with unknown parameters as a state space model, using the system state, input data parameters, and forward component as system data.

[0130] In one embodiment, the observer establishment module 430 is further configured to obtain the gain matrix, establish a state observer under the conventional model based on the gain matrix and the state space model, determine the observability constant, and establish a data-driven switching gain state observer based on the state observer using process data; wherein the data-driven switching gain state observer satisfies the observability constant.

[0131] In one embodiment, the error construction module 440 is further configured to define error data and determine the error representation of the nonlinear network system under the data-driven switched gain state observer based on the error data; adjust the error representation of the linear network system to an equivalent representation as an error system, and complete the construction of the error system of the data-driven switched gain state observer.

[0132] In one embodiment, the operating condition setting module 450 is further configured to design initial constants and an initial matrix when the data-driven switching gain state observer satisfies the observability constant; determine the constants for convergence of the nonlinear network system based on the initial constants, and determine the gain matrix under data-driven conditions based on the initial matrix; and complete the setting of stable operating conditions for the nonlinear network system based on the constants and the gain matrix.

[0133] In one embodiment, the provided connected vehicle data-driven switching gain state estimation system further includes a stability analysis module, which is used to perform stability analysis on the nonlinear network system using Lyapunov functions to obtain analysis results; and adjust the nonlinear network system based on the analysis results.

[0134] In one embodiment, the stability analysis module is also used to calculate the initial matrix using Schur's complement lemma, and substitute the calculated matrix into the gain matrix to obtain the target matrix; set the switching time and switching period, and use the Lyapunov function to perform stability analysis on the nonlinear network system based on the switching time and switching period.

[0135] In one embodiment, the stability analysis module is also used to determine the switching sequence. For the switching sequence, stability analysis is performed using a Lyapunov function based on the initial matrix. During the stability analysis, the Lyapunov function decreases with a minimum exponential convergence rate, indicating that the nonlinear network system is stable.

[0136] In one embodiment, a backend control center is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 5 As shown, the back-end control center includes a processor, memory, network interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The network interface of the back-end control center is used for communication with external terminals via a network connection. When executed by the processor, the computer program implements a data-driven switching gain state estimation method for connected vehicles. The display screen of the back-end control center can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad mounted on the back-end control center's casing, or an external keyboard, touchpad, or mouse.

[0137] Those skilled in the art will understand that Figure 5The structure shown is merely a block diagram of a portion of the structure related to the solution of this application and does not constitute a limitation on the back-end control center on which the solution of this application is applied. A specific back-end control center may include more or fewer components than shown in the figure, or combine certain components, or have different component arrangements.

[0138] In one embodiment, a background control center is provided, including a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the steps of a data-driven switching gain state estimation method for connected vehicles.

[0139] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps of a data-driven switching gain state estimation method for connected vehicles.

[0140] 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, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0141] 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.

[0142] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. 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 patent application should be determined by the appended claims.

Claims

1. A method for estimating the state of data-driven switching gain in connected vehicles, characterized in that, The method includes: System data from each subsystem in a connected vehicle is collected separately. A nonlinear network system is constructed as a state-space model based on the system data. This includes: determining the system state and input data parameters of each subsystem in each connected vehicle, and determining the forward component corresponding to the system state; obtaining a vector-valued continuous function and an unknown Euclidean matrix space; and constructing a nonlinear network system composed of the subsystems with unknown parameters as a state-space model, using the system state, input data parameters, and forward components as system data based on the vector-valued continuous function and the unknown Euclidean matrix space. Collect process data generated during the operation of each subsystem in the state-space model; Determine the observability constant, and based on the observability constant, the state-space model, and the process data, establish a data-driven switching gain state observer, including: obtaining a gain matrix, establishing a state observer under a conventional model based on the gain matrix and the state-space model; determining the observability constant, and establishing a data-driven switching gain state observer based on the state observer using the process data; wherein the data-driven switching gain state observer satisfies the observability constant. Defining error data and constructing an error system for the data-driven switched gain state observer based on the error data includes: defining error data and determining the error representation of the nonlinear network system under the data-driven switched gain state observer based on the error data; adjusting the error representation of the nonlinear network system to an equivalent representation as the error system, thereby completing the construction of the error system of the data-driven switched gain state observer. Determine the constant quantity for the convergence of the nonlinear network system, determine the gain matrix under data-driven switching gain state observer based on the data-driven method, and set the stable operating conditions of the nonlinear network system according to the constant quantity and the gain matrix. The nonlinear network system operates under the stable operating conditions to achieve data-driven switching gain state estimation for connected vehicles.

2. The method for estimating the data-driven switching gain state of connected vehicles according to claim 1, characterized in that, Determine the constant quantity for convergence of the nonlinear network system, determine the gain matrix under data-driven switching gain state observer based on the data-driven method, and set the stable operating conditions of the nonlinear network system according to the constant quantity and the gain matrix, including: Given that the data-driven switching gain state observer satisfies the observability constant, design initial constants and initial matrices; The constants for convergence of the nonlinear network system are determined based on the initial constants, and the gain matrix under data-driven conditions is determined based on the initial matrix. The stable operating conditions of the nonlinear network system are set based on the constants and the gain matrix.

3. The method for estimating the data-driven switching gain state of connected vehicles according to claim 2, characterized in that, The method further includes: Stability analysis of the nonlinear network system was performed using Lyapunov functions, and the analysis results were obtained. The nonlinear network system is adjusted based on the analysis results.

4. The method for estimating the data-driven switching gain state of connected vehicles according to claim 3, characterized in that, Stability analysis of the nonlinear network system is performed using Lyapunov functions, including: The initial matrix is ​​calculated using Schur's complement lemma, and the calculated matrix is ​​then substituted into the gain matrix to obtain the target matrix; Set the switching time and switching period, and use the Lyapunov function to perform stability analysis on the nonlinear network system based on the switching time and switching period.

5. The method for estimating the data-driven switching gain state of connected vehicles according to claim 4, characterized in that, The method further includes: Determine the switching sequence, and for the switching sequence, perform stability analysis using the Lyapunov function based on the initial matrix; During the stability analysis, the Lyapunov function decreases with a minimum exponential convergence rate, indicating that the nonlinear network system is stable.

6. A data-driven switching gain state estimation system for connected vehicles, characterized in that, The system includes: The model building module is used to collect system data from the subsystems of each connected vehicle, and to construct a nonlinear network system as a state-space model based on the system data. This includes: determining the system state and input data parameters of each subsystem in each connected vehicle, and determining the forward component corresponding to the system state; obtaining a vector-valued continuous function and an unknown Euclidean matrix space; and, based on the vector-valued continuous function and the unknown Euclidean matrix space, using the system state, input data parameters, and forward components as system data, constructing a nonlinear network system composed of the various subsystems with unknown parameters as a state-space model. The process data collection module is used to collect process data generated during the operation of each subsystem in the state space model. An observer establishment module is used to determine an observability constant and, based on the observability constant, the state-space model, and the process data, establish a data-driven switching gain state observer, including: obtaining a gain matrix; establishing a state observer under a conventional model based on the gain matrix and the state-space model; determining the observability constant; and establishing a data-driven switching gain state observer based on the state observer using the process data; wherein the data-driven switching gain state observer satisfies the observability constant. An error construction module is used to define error data and construct an error system for the data-driven switched gain state observer based on the error data. This includes: defining error data and determining the error representation of the nonlinear network system under the data-driven switched gain state observer based on the error data; adjusting the error representation of the nonlinear network system to an equivalent representation of the error system, thus completing the construction of the error system for the data-driven switched gain state observer. The operating condition setting module is used to determine the constant quantity for the convergence of the nonlinear network system, determine the gain matrix under data driving based on the data-driven switching gain state observer, and set the stable operating conditions of the nonlinear network system according to the constant quantity and the gain matrix. The gain state estimation module is used by the nonlinear network system to achieve data-driven switching gain state estimation of connected vehicles under the stable operating conditions.

Images