State estimation method and device, equipment and storage medium

Abstract

The invention discloses a state estimation method and device, equipment and a storage medium, and relates to the technical field of system security. The method comprises the following steps: modeling a target system, and generating a linear Gaussian time-invariant model of the target system; generating a local state estimation value of the target system through a Kalman estimator based on the linear Gaussian time-invariant model; and based on the local state estimation value, generating a global state estimation value of the target system through a weighted least square method based on an elastic network. By generating the global state estimation value, when the target system is attacked and the state monitoring of the system is damaged, the system state can be recovered through the global state estimation value, the error caused by the attack is overcome, and the stability and robustness of the system are effectively improved.

Description

Technical Field

[0001] The present application relates to the field of system safety technology, and in particular to a state estimation method, apparatus, device and storage medium. Background Art

[0002] In the past few years, many researchers have explored the security issues of cyber-physical systems from the perspective of control theory. For example, by using the principle of separation of estimation and control, the design of a resilient output feedback controller is simplified to the design of a resilient state estimator. Therefore, when certain sensors are attacked, how to ensure that the system can recover state information through these attacked measurement data becomes a key issue. This problem is called secure state estimation, and it is the primary security issue to consider when designing control systems.

[0003] Therefore, there is an urgent need for a solution that allows the system to recover state information through these attacked measurement data.

[0004] The above contents are only used to assist in understanding the technical solution of the present application and do not constitute an admission that the above contents are prior art. Summary of the invention

[0005] The main purpose of the present application is to provide a state estimation method, device, equipment and storage medium, aiming to solve the technical problem that the system cannot restore state information due to an attack.

[0006] To achieve the above object, the present application proposes a state estimation method, which comprises:

[0007] Modeling the target system and generating a linear Gaussian time-invariant model of the target system;

[0008] Based on the linear Gaussian time-invariant model, generating a local state estimate of the target system through a Kalman estimator;

[0009] Based on the local state estimation value, a global state estimation value of the target system is generated by a weighted least square method based on an elastic network.

[0010] In one embodiment, the step of modeling the target system to generate a linear Gaussian time-invariant model of the target system includes:

[0011] Determine the state variables and observed variables of the target system;

[0012] Based on the state variables, establishing a state equation of the target system;

[0013] Based on the observed variables, establishing an observation equation of the target system;

[0014] According to the state equation and the observation equation, a linear Gaussian time-invariant model of the target system is obtained.

[0015] In one embodiment, the step of generating a local state estimate of the target system by a Kalman estimator based on the linear Gaussian time-invariant model comprises:

[0016] Setting a Kalman estimator at the sensor end in the linear Gaussian time-invariant model;

[0017] The Kalman estimator generates a local state estimation value of the target system according to the historical data of the target system.

[0018] In one embodiment, the step of generating a global state estimate of the target system based on the local state estimate by a weighted least squares method based on an elastic network comprises:

[0019] A global estimation fusion algorithm is obtained through a weighted least square method based on elastic network;

[0020] The local state estimation values ​​are fused through the global estimation fusion algorithm to obtain the global state estimation value of the target system.

[0021] In one embodiment, the step of generating a local state estimate of the target system according to historical data of the target system by the Kalman estimator includes:

[0022] Initializing the Kalman estimator to determine an initial state estimate and a priori error covariance matrix of the Kalman estimator;

[0023] Determining sensor parameters of the sensor according to the sensor where the Kalman estimator is located;

[0024] Obtaining a Kalman filter gain of the Kalman estimator according to the prior error covariance matrix and sensor parameters;

[0025] Perform prediction calculation based on initial state estimation, prior error covariance matrix and historical data to generate predicted state estimation value and predicted error covariance matrix of target system;

[0026] An update calculation is performed based on the predicted state estimate, the prediction error covariance matrix and the Kalman filter gain to generate a local state estimate of the target system.

[0027] In one embodiment, the step of obtaining a global estimation fusion algorithm by using a weighted least squares method based on an elastic network includes:

[0028] Obtaining a noise estimation error and an attack estimation error of the target system at a current moment;

[0029] A global estimation fusion algorithm is generated by performing weighted constraints on the noise estimation error and the attack estimation error.

[0030] In one embodiment, after the step of obtaining the noise estimation errors and attack estimation errors of all sensors in the historical data of the target system, the step further includes:

[0031] When a target system is attacked, the estimated error of the target system is controlled within a preset region, where the preset region is determined based on the true error of noise in historical data of the attacked sensor.

[0032] In addition, to achieve the above purpose, the present application also proposes a state estimation device, the state estimation device comprising:

[0033] A system modeling module is used to model the target system and generate a linear Gaussian time-invariant model of the target system;

[0034] A local estimation module, used for generating a local state estimation value of the target system through a Kalman estimator based on the linear Gaussian time-invariant model;

[0035] The global estimation module is used to generate a global state estimation value of the target system based on the local state estimation value by using a weighted least square method based on an elastic network.

[0036] In addition, to achieve the above objectives, the present application also proposes a state estimation device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the state estimation method described above.

[0037] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the state estimation method described above are implemented.

[0038] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the steps of the state estimation method described above are implemented.

[0039] One or more technical solutions proposed in this application have at least the following technical effects:

[0040] The present application proposes a state estimation method, device, equipment and storage medium, which models the target system and generates a linear Gaussian time-invariant model of the target system; based on the linear Gaussian time-invariant model, generates a local state estimation value of the target system through a Kalman estimator; based on the local state estimation value, generates a global state estimation value of the target system through a weighted least squares method based on an elastic network. The present application generates a global state estimation value based on the historical data of the target system through a Kalman estimator. When the target system is attacked and the state monitoring of the system is damaged, the system state can be restored through the global state estimation value, overcoming the error caused by the attack and effectively improving the stability and robustness of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0042] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0043] Figure 1 A schematic diagram of a flow chart provided for the first embodiment of the state estimation method of the present application;

[0044] Figure 2 This is a schematic diagram of the module structure of the state estimation device according to an embodiment of the present application;

[0045] Figure 3 Schematic diagram of the device structure of the hardware operating environment involved in the state estimation method in the embodiment of the present application.

[0046] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0047] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0048] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0049] The main solution of the embodiment of the present application is: modeling the target system to generate a linear Gaussian time-invariant model of the target system; based on the linear Gaussian time-invariant model, generating a local state estimate of the target system through a Kalman estimator; based on the local state estimate, generating a global state estimate of the target system through a weighted least squares method based on an elastic network.

[0050] In the past few years, many researchers have explored the security issues of cyber-physical systems from the perspective of control theory. For example, by using the principle of separation of estimation and control, the design of a resilient output feedback controller is simplified to the design of a resilient state estimator. Therefore, when certain sensors are attacked, how to ensure that the system can recover state information through these attacked measurement data becomes a key issue. This problem is called secure state estimation, and it is the primary security issue to consider when designing control systems.

[0051] Therefore, there is an urgent need for a solution that allows the system to recover state information through these attacked measurement data.

[0052] This application generates a global state estimation value. When the target system is attacked and its state is damaged, the global state estimation value can be used to restore the system state, overcome the error caused by the attack, and effectively improve the stability and robustness of the system.

[0053] It should be noted that the execution subject of this embodiment may be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device capable of realizing the above functions, a state estimation device, etc. The following takes the state estimation device as an example to illustrate this embodiment and the following embodiments.

[0054] Based on this, the present application embodiment provides a state estimation method, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the state estimation method of the present application.

[0055] In this embodiment, the state estimation method includes steps S10 to S30:

[0056] Step S10, modeling the target system to generate a linear Gaussian time-invariant model of the target system.

[0057] It should be noted that the target system may refer to the cyber-physical fusion system, a multi-dimensional complex system that integrates advanced perception, computing, communication and control technologies. Through the organic integration and deep collaboration of these technologies, it realizes the mutual mapping, timely interaction and efficient coordination of elements such as people, machines, objects, environment and information in the physical space and cyber space, so as to achieve on-demand response, rapid iteration and dynamic optimization of resource allocation and operation within the system.

[0058] In addition, it should be noted that the linear Gaussian time-invariant model is a model that combines the linear time-invariant system and the Gaussian (normal) distribution characteristics. In this model, the relationship between the input and output of the system is linear, and the noise or error terms in the system obey the Gaussian distribution.

[0059] Linear time-invariant system is an important type of signal processing system with two core characteristics. The first is linearity, that is, the output of the system is a linear function of the input signal; the second is time invariance, that is, the output of the system is only related to the shape of the input signal but not to time. That is, if the input signal is delayed by a certain time t0, the output signal will also be delayed by t0 accordingly, but the shape of the signal remains unchanged.

[0060] The Gaussian distribution, also known as the normal distribution, is described by a bell-shaped curve where the area under the curve represents the probability, the highest point of the curve is the mean (μ), and the width of the curve is determined by the standard deviation (σ).

[0061] Specifically, first determine the state variables and observation variables of the target system; then, based on the state variables, establish the state equation of the target system, and based on the observation variables, establish the observation equation of the target system. The state equation is used to describe the evolution of the state variables of the target system over time, and the observation equation is used to describe the relationship between the state variables and the observation variables of the target system; the state equation and the observation equation constitute a linear Gaussian time-invariant model of the target system.

[0062] Step S20: Based on the linear Gaussian time-invariant model, generate a local state estimation value of the target system through a Kalman estimator.

[0063] It should be noted that the Kalman estimator is also called the Kalman filter, which is an efficient recursive filter (autoregressive filter) that can estimate the state of a dynamic system from a series of measurement data containing statistical noise. The working principle of the Kalman filter can be summarized in two main steps: prediction and update. In the prediction step, it uses the system's state equation to predict the next state. In the update step, it uses new measurements to correct this prediction to obtain a more accurate state estimate. These two steps are repeated to achieve continuous tracking and estimation of the system state.

[0064] In addition, it should be noted that the local state estimation value refers to the state estimation value of a sensor in the target system.

[0065] Specifically, a Kalman estimator is first set at the sensor end in the linear Gaussian time-invariant model: there are several sensors in the target system, and each sensor needs to be set with a local estimator for processing its measurement data. In this embodiment, the Kalman estimator is set at the sensor end as a local estimator of the sensor to process the measurement data. Then, the Kalman estimator generates a local state estimation value of the sensor in the target system according to the historical data of the target system.

[0066] Step S30: Based on the local state estimation value, a global state estimation value of the target system is generated by a weighted least square method based on an elastic network.

[0067] It should be noted that the global state estimation value refers to the state estimation value obtained by fusing the state estimation values ​​of all sensors of the target system. When the target system is attacked, the system recovers the system through the global state estimation value.

[0068] Specifically, a global estimation fusion algorithm is first obtained by a weighted least square method based on an elastic network; then the local state estimation values ​​are fused by the global estimation fusion algorithm to obtain a global state estimation value of the target system.

[0069] This embodiment uses the above scheme to model the target system and generate a linear Gaussian time-invariant model of the target system; then based on the linear Gaussian time-invariant model, a local state estimate of the target system is generated through a Kalman estimator; finally, based on the local state estimate, a global state estimate of the target system is generated through a weighted least squares method based on an elastic network. By generating a global state estimate, when the target system is attacked and the state monitoring of the system is damaged, the system state can be restored through the global state estimate, the error caused by the attack can be overcome, and the stability and robustness of the system can be effectively improved.

[0070] Based on the above implementation scheme, in a feasible implementation scheme, the above step S10 may include steps S11 to S14:

[0071] Step S11, determining the state variables and observation variables of the target system.

[0072] It should be noted that the state variables are key parameters that describe the internal dynamics of the system.

[0073] In addition, it should be noted that the observed variable is a parameter that can be measured by external devices such as sensors, and is a system output obtained by measuring the sensor.

[0074] Step S12: establishing a state equation of the target system based on the state variables.

[0075] It should be noted that the state equation is used to describe the evolution of the state variables of the target system over time.

[0076] Step S13: establishing the observation equation of the target system based on the observed variables.

[0077] It should be noted that the observation equation is used to describe the relationship between the state variables of the target system and the observation variables.

[0078] Step S14, obtaining a linear Gaussian time-invariant model of the target system according to the state equation and the observation equation.

[0079] Specifically, firstly, the state variables and observation variables of the target system are clarified. The state variables are the key parameters that describe the internal dynamics of the system, while the observation variables are the parameters that can be measured by external devices such as sensors. Then, based on the state variables, the state equation of the target system is established, and based on the observation variables, the observation equation of the target system is established. Finally, the state space equation representation of the linear Gaussian time-invariant model is composed of the state equation and the observation equation.

[0080] Specifically, the expression of the state equation is:

[0081] x(t+1)=Ax(t)+ω(t)

[0082] Among them, x(t+1) is the state variable of the target system at time t+1; x(t) is the state variable of the target system at time t; A is the state transfer matrix, which describes the evolution of the state of the target system over time; ω(t) is the process noise, which is usually assumed to be zero-mean Gaussian white noise, whose covariance matrix is ​​Q, and obeys the Gaussian distribution of (0,Q).

[0083] Specifically, the expression of the observation equation is:

[0084] y(t)=C(x)+v(t)+a(t)

[0085] Among them, y(t) is the observed variable of the target system at time t; C is the observation matrix, which describes how the state variable is converted into observable output; ν(t) is the measurement noise, which is usually assumed to be zero-mean Gaussian white noise, whose covariance matrix is ​​R and obeys the Gaussian distribution of (0, R); a(t) is the attack vector.

[0086] Based on the above implementation scheme, in a feasible implementation scheme, the above step S20 may include steps S21 to S22:

[0087] Step S21, setting a Kalman estimator at the sensor end in the linear Gaussian time-invariant model.

[0088] Specifically, there are many sensors in the target system, and each sensor needs to be provided with a local estimator to process its measurement data. In this embodiment, the Kalman estimator is used as the local estimator of the sensor to process the measurement data.

[0089] Step S22: Generate a local state estimation value of the target system according to the historical data of the target system through the Kalman estimator.

[0090] It should be noted that the historical data of the target system refers to the measurement values ​​and related state estimation information collected by the sensors in the target system at various time points in the past.

[0091] Specifically, a Kalman estimator is set at the sensor end of the target system as a local estimator of the sensor to process measurement data, and the Kalman estimator generates a local state estimation value of the system according to historical data measured by the target system.

[0092] Based on the above implementation scheme, in a feasible implementation scheme, the above step S30 may include steps S31 to S32:

[0093] Step S31, obtaining a global estimation fusion algorithm by using a weighted least squares method based on an elastic network.

[0094] It should be noted that the global estimation fusion algorithm refers to an algorithm for generating a global state estimation value by fusing local state estimation values, and is used to correct the errors accumulated by the Kalman estimator due to the deviations injected by the attacker.

[0095] Specifically, the noise estimation errors and attack estimation errors of all sensors in the historical data of the target system are obtained; the noise estimation errors and attack estimation errors are weightedly constrained by a weighted least squares method based on an elastic network to generate a global estimation fusion algorithm.

[0096] Specifically, the expression of the global estimation fusion algorithm is:

[0097]

[0098] in, is a cost function, to find the global state estimate The goal is to minimize the value of this cost function.

[0099] in, Used to calculate the global state estimate, is the local state estimate of the ith sensor at time t, is the global state estimate of the target system.

[0100] Where W is a weighting matrix, which is the error covariance matrix of the target system in the absence of an attack; α, β, and γ are constants, α+β=1, and α∈(0,1] and β∈[0,1]. Parameters γ, α, and β can be configured according to actual conditions to achieve optimal performance. represents the noise estimation error, which is the estimation error caused by system noise, It refers to the noise estimation error of the mth sensor at time t; represents the attack estimation error, which is the estimation error caused by the bias injected by the attacker, It refers to the attack estimation error of the mth sensor at time t.

[0101] Step S32: fusing the local state estimation values ​​through the global estimation fusion algorithm to obtain the global state estimation value of the target system.

[0102] Specifically, according to the Kalman optimal estimation principle, the deviation injected by the attacker will accumulate over time, eventually leading to a huge estimation error. Therefore, in order to offset the cumulative error brought by the Kalman estimator, the global state estimation is obtained by using the weighted least squares method based on the elastic network by utilizing the local state estimation value.

[0103] Based on the above implementation scheme, in a feasible implementation scheme, the above step S22 may include steps S221 to S225:

[0104] Step S221, initializing the Kalman estimator to determine the initial state estimate and initial error covariance matrix of the Kalman estimator.

[0105] Step S222: Determine the sensor parameters of the sensor according to the sensor where the Kalman estimator is located.

[0106] Step S223: obtaining the Kalman filter gain of the Kalman estimator according to the initial error covariance matrix and the sensor parameters.

[0107] Step S224, performing prediction calculation based on the initial state estimation, the initial error covariance matrix and the historical data to generate a priori state estimation value and a priori error covariance matrix of the target system.

[0108] Step S225, performing update calculation based on the prior state estimate, the prior error covariance matrix and the Kalman filter gain to generate a local state estimate of the target system.

[0109] Specifically, the Kalman estimator is initialized to determine the initial state estimate and initial error covariance matrix of the Kalman estimator. First, the initial value of the state estimate needs to be set. This value can be set based on some prior knowledge. If there is no prior information, it can be simply set to zero. Next, the initial value P of the error covariance matrix needs to be set. i (1|0)=Σ, this matrix represents the uncertainty of the initial state estimate.

[0110] Specifically, according to the sensor where the Kalman estimator is located, the sensor parameters of the sensor are determined, and the sensor parameters include a state transfer matrix A, a control input matrix B, an observation matrix C, a process noise covariance matrix Q and an observation noise covariance matrix R.

[0111] Specifically, the Kalman filter gain of the Kalman estimator is obtained according to the initial error covariance matrix and the sensor parameters. The calculation formula for calculating the Kalman filter gain is:

[0112]

[0113] Among them, K i (t) is the Kalman filter gain of the i-th sensor at time t, which is a weight factor used to determine the relative importance of the measured value and the predicted value in the final estimation; P i (t|t-1) is the prior error covariance matrix, which represents the uncertainty of the state estimate predicted based on the previous information before time t. The initial value P i (1|0)=Σ;C i is the observation matrix in the sensor parameters of the i-th sensor; R is the observation noise covariance matrix, which represents the uncertainty or noise in the measurement process.

[0114] Specifically, a prediction calculation is performed based on the initial state estimate, the initial error covariance matrix and the historical data to generate the prior state estimate and the prior error covariance matrix of the target system. The calculation formula for the prediction calculation is:

[0115]

[0116] P i (t+1|t)=AP i (t)A T +Q

[0117] in, is the prior state estimate, using the state transfer matrix A and the state estimate at the previous moment To predict the current state Initial Value P i(t+1|t) is the prior error covariance matrix, which represents the prediction of the uncertainty of the state estimate at time t+1 before the data at time t+1 is observed, where Q is the process noise covariance matrix, which describes the uncertainty in the state transfer process.

[0118] Specifically, an update calculation is performed based on the predicted state estimate, the prediction error covariance matrix and the Kalman filter gain to generate a local state estimate of the target system. The calculation formula for calculating the local state estimate is:

[0119]

[0120] P i (t) = P i (t|t-1)-K i (t)C i P i (t|t-1)

[0121] in, is the state estimation value, i.e., the local state estimation value, which is the state estimation value of the i-th sensor at time t and is the best estimation of the current state based on all historical measurement data; y i (t) is the observed value at time t; K i (t) is the Kalman filter gain of the i-th sensor at time t; C i is the observation matrix of the i-th sensor.

[0122] Among them, P i (t) is the error covariance matrix, which is the error covariance matrix of the i-th sensor at time t, and is used to measure the uncertainty of state estimation; P i (t|t-1) is the prior error covariance matrix, which represents the prediction of the uncertainty of the state estimate at time t before the data at time t is observed.

[0123] Based on the above implementation scheme, in a feasible implementation scheme, the above step S31 may include steps S311 to S312:

[0124] Step S311, obtaining the noise estimation error and attack estimation error of the target system at the current moment. Step S312, generating a global estimation fusion algorithm by weighted constraint on the noise estimation error and attack estimation error.

[0125] It should be noted that the noise estimation error refers to the estimation error caused by the target system noise.

[0126] In addition, it should be noted that the attack estimation error refers to the estimation error caused by the deviation injected by the attacker.

[0127] Specifically, the device first obtains the noise estimation error and attack estimation error of the target system at the current moment through sensors. is the noise estimation error, which represents the estimation error caused by system noise, is the attack estimation error, which represents the estimation error caused by the bias injected by the attacker.

[0128] Then, by performing weighted constraints on the noise estimation error and the attack estimation error, the expression of the weighted constraint is:

[0129]

[0130] Among them, α, β and γ are constants, α+β=1, and α∈(0,1] and β∈[0,1]. The parameters γ, α and β can be configured according to the actual situation to achieve the best performance. represents the noise estimation error, which is the estimation error caused by system noise, It refers to the noise estimation error of the mth sensor at time t; represents the attack estimation error, which is the estimation error caused by the bias injected by the attacker, It refers to the attack estimation error of the mth sensor at time t.

[0131] This application introduces It is used to control the impact of the deviation injected by the attacker on the estimation error, effectively improving the security and robustness of the system. The parameters γ, α, and β can be configured according to actual conditions to achieve optimal performance.

[0132] Based on the above implementation scheme, in a feasible implementation scheme, after the above step S311, step S313 is also included:

[0133] Step S313, when the target system is attacked, the estimated error of the target system is controlled within a preset area, where the preset area is determined according to the real error of the noise in the historical data of the attacked sensor.

[0134] Specifically, when the target system is not attacked, the result of the global state estimation is consistent with the result of the optimal Kalman estimator.

[0135] When the target system is attacked, the estimated error of the target system is controlled within a preset area, which is determined based on the real error of noise in the historical data of the attacked sensor. The range of the preset area is:

[0136]

[0137] Among them, the function G i (φ1,…,φ m) represents the set {φ1,…,φ m Each element in} is the i-th minimum value of the corresponding item; φ i is the true error of the i-th sensor caused by noise; p represents the number of attacked sensors; is the global state estimate; x(t) is the actual observation value of the target system; m is the number of sensors in the target system; W is the weighting matrix, which is the error covariance matrix of the system in the absence of an attack.

[0138] The present application controls the estimation error of the target system within a preset area, and limits the estimation error within a certain range when the system is attacked, thereby limiting the impact of the worst-case scenario that may be caused by the attack, and can improve the security and robustness of the system.

[0139] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the state estimation method of the present application. More simple transformations based on this technical concept are all within the scope of protection of the present application.

[0140] This application also provides a state estimation device, please refer to Figure 2 , the state estimation device comprises:

[0141] The system modeling module 201 is used to model the target system and generate a linear Gaussian time-invariant model of the target system;

[0142] A local estimation module 202, configured to generate a local state estimation value of the target system through a Kalman estimator based on the linear Gaussian time-invariant model;

[0143] The global estimation module 203 is used to generate a global state estimation value of the target system based on the local state estimation value by using a weighted least square method based on an elastic network.

[0144] The state estimation device provided by the present application adopts the state estimation method in the above embodiment, which can solve the technical problem that the system cannot restore state information due to attack. Compared with the prior art, the beneficial effects of the state estimation device provided by the present application are the same as the beneficial effects of the state estimation method provided by the above embodiment, and other technical features in the state estimation device are the same as the features disclosed in the above embodiment method, which will not be repeated here.

[0145] The present application provides a state estimation device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the state estimation method in the above-mentioned embodiment one.

[0146] Reference below Figure 3 , which shows a schematic diagram of the structure of a state estimation device suitable for implementing an embodiment of the present application. The state estimation device in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable App Displays), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 3 The state estimation device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0147] like Figure 3 As shown, the state estimation device may include a processing device 1001 (e.g., a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read On ly Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. Various programs and data required for the operation of the state estimation device are also stored in RAM1004. The processing device 1001, ROM1002, and RAM1004 are connected to each other via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems may be connected to the I / O interface 1006: input devices 1007 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 1003 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 1009. The communication device 1009 may allow the state estimation device to communicate with other devices wirelessly or by wire to exchange data. Although the state estimation device with various systems is shown in the figure, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems may be implemented or have instead.

[0148] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0149] The state estimation device provided by the present application adopts the state estimation method in the above embodiment, which can solve the technical problem that the system cannot restore state information due to attack. Compared with the prior art, the beneficial effects of the state estimation device provided by the present application are the same as the beneficial effects of the state estimation method provided by the above embodiment, and other technical features in the state estimation device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0150] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0151] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0152] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, wherein the computer-readable program instructions are used to execute the state estimation method in the above-mentioned embodiment.

[0153] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM: Random Access Memory), a read-only memory (ROM: Read On ly Memory), an erasable programmable read-only memory (EPROM: Erasable Programmab le Read On ly Memory or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM: CD-Read On ly Memory), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency: Radio Frequency), etc., or any suitable combination of the above.

[0154] The computer-readable storage medium may be included in the state estimation device; or may exist independently without being assembled into the state estimation device.

[0155] The above-mentioned computer-readable storage medium carries one or more programs. When the above-mentioned one or more programs are executed by the state estimation device, the state estimation device: models the target system to generate a linear Gaussian time-invariant model of the target system; based on the linear Gaussian time-invariant model, generates a local state estimation value of the target system through a Kalman estimator; based on the local state estimation value, generates a global state estimation value of the target system through a weighted least squares method based on an elastic network.

[0156] The computer program code for performing the operation of the present application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "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 an independent software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, using an Internet service provider to connect through the Internet).

[0157] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0158] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0159] The readable storage medium provided by the present application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned state estimation method, and can solve the technical problem that the system cannot restore state information due to being attacked. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided by the present application are the same as the beneficial effects of the state estimation method provided by the above-mentioned embodiment, and will not be repeated here.

[0160] The present application also provides a computer program product, including a computer program, which implements the steps of the state estimation method as described above when executed by a processor.

[0161] The computer program product provided by this application can solve the technical problem that the system cannot restore state information due to an attack. Compared with the prior art, the beneficial effects of the computer program product provided by this application are the same as the beneficial effects of the state estimation method provided by the above embodiment, which will not be repeated here.

[0162] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A state estimation method, characterized in that: The method comprises: Modeling the target system to generate a linear Gaussian time-invariant model of the target system; Based on the linear Gaussian time-invariant model, generating a local state estimate of the target system through a Kalman estimator; Based on the local state estimation value, a global state estimation value of the target system is generated by a weighted least square method based on an elastic network.

2. The method according to claim 1, characterized in that The step of modeling the target system and generating a linear Gaussian time-invariant model of the target system comprises: Determine the state variables and observed variables of the target system; Based on the state variables, establishing a state equation of the target system; Based on the observed variables, establishing an observation equation of the target system; According to the state equation and the observation equation, a linear Gaussian time-invariant model of the target system is obtained.

3. The method according to claim 1, characterized in that The step of generating a local state estimation value of the target system by a Kalman estimator based on the linear Gaussian time-invariant model comprises: Setting a Kalman estimator at the sensor end in the linear Gaussian time-invariant model; The Kalman estimator generates a local state estimation value of the target system according to the historical data of the target system.

4. The method according to claim 1, characterized in that The step of generating a global state estimation value of the target system based on the local state estimation value by a weighted least square method based on an elastic network comprises: A global estimation fusion algorithm is obtained through a weighted least square method based on elastic network; The local state estimation values ​​are fused through the global estimation fusion algorithm to obtain the global state estimation value of the target system.

5. The method according to claim 3, characterized in that The step of generating a local state estimation value of the target system according to the historical data of the target system by the Kalman estimator comprises: Initializing the Kalman estimator to determine an initial state estimate and an initial error covariance matrix of the Kalman estimator; Determining sensor parameters of the sensor according to the sensor where the Kalman estimator is located; Obtaining a Kalman filter gain of the Kalman estimator according to the initial error covariance matrix and sensor parameters; Perform prediction calculation based on initial state estimation, initial error covariance matrix and historical data to generate a priori state estimation value and a priori error covariance matrix of the target system; An update calculation is performed based on the priori state estimation value, the priori error covariance matrix and the Kalman filter gain to generate a local state estimation value of the target system.

6. The method according to claim 4, characterized in that The step of obtaining a global estimation fusion algorithm by using a weighted least squares method based on an elastic network comprises: Obtaining a noise estimation error and an attack estimation error of the target system at a current moment; A global estimation fusion algorithm is generated by performing weighted constraints on the noise estimation error and the attack estimation error.

7. The method according to claim 6, characterized in that After the step of obtaining the noise estimation errors and attack estimation errors of all sensors in the historical data of the target system, the following step is further included: When a target system is attacked, the estimated error of the target system is controlled within a preset region, where the preset region is determined based on the true error of noise in historical data of the attacked sensor.

8. A state estimation device, characterized in that: The device comprises: A system modeling module is used to model the target system and generate a linear Gaussian time-invariant model of the target system; A local estimation module, used for generating a local state estimation value of the target system through a Kalman estimator based on the linear Gaussian time-invariant model; The global estimation module is used to generate a global state estimation value of the target system based on the local state estimation value by using a weighted least square method based on an elastic network.

9. A state estimation device, characterized in that: The device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the state estimation method according to any one of claims 1 to 7.

10. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the state estimation method according to any one of claims 1 to 7 are implemented.

Images