CN108549221B - Filtering method and related device of linear stochastic system - Google Patents
Filtering method and related device of linear stochastic system Download PDFInfo
- Publication number
- CN108549221B CN108549221B CN201810293455.5A CN201810293455A CN108549221B CN 108549221 B CN108549221 B CN 108549221B CN 201810293455 A CN201810293455 A CN 201810293455A CN 108549221 B CN108549221 B CN 108549221B
- Authority
- CN
- China
- Prior art keywords
- filtering
- observation value
- noise
- linear
- value expression
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
- G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
- G05B13/04—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators
- G05B13/042—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators in which a parameter or coefficient is automatically adjusted to optimise the performance
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
- Arrangements For Transmission Of Measured Signals (AREA)
Abstract
The application discloses a filtering method of a linear stochastic system, which comprises the following steps: adding a noise superposition term to the linear random system to obtain a noise superposition linear random system; constructing and processing an observation value expression according to a noise superposition linear random system to obtain an observation value expression; and according to the optimal filtering method, filtering by taking the noise superposition linear random system and the observed value expression as parameters to obtain a filtering result. By adding the noise superposition item to the linear random system, the linear random system is not only interfered by the system noise at the last moment, but also interfered by the system noise at the current moment, so that the environment of noise interference in the actual situation can be fitted more completely, the precision of subsequent filtering can be further improved, and the filtering processing is more accurate. The application also discloses a linear stochastic system filtering device, another filtering device and a computer readable storage medium, which have the beneficial effects.
Description
Technical Field
The present application relates to the field of automation control, and in particular, to a filtering method, a filtering apparatus, another filtering apparatus, and a computer-readable storage medium for a linear stochastic system.
Background
With the continuous development of information technology, control, communication and computer technologies are continuously integrated into information processing and mechanical device operation at different levels in the current industrial systems. After the technologies are applied, random control can be realized on the automatic control system, and a random control system is obtained. Wherein the stochastic control system is a dynamic system affected by stochastic factors. In continuous research, three aspects of stochastic control systems are mainly improved, namely modeling, filtering and stochastic adaptive control.
Generally, in the modeling process, a linear random system is mainly constructed, the fitting of a random state is realized, and then the filtering operation is performed according to the linear random system. However, as the detection accuracy increases, it is gradually found that noise and interference in the actual environment are particularly complex, and as the application develops, the design requirements of the system become more complex, so that the prior art cannot meet the designed filtering accuracy requirements.
Therefore, how to solve the filtering problem of the linear stochastic system in the case of complex noise interference is a key issue that is of interest to those skilled in the art.
Disclosure of Invention
The purpose of the present application is to provide a filtering method, a filtering apparatus, another filtering apparatus, and a computer-readable storage medium for a linear stochastic system, in which a noise superposition term is added to the linear stochastic system, so that the linear stochastic system is not only interfered by system noise at a previous time, but also interfered by system noise at a current time, and thus, an environment of noise interference in an actual situation can be fitted more completely, and further, the accuracy of subsequent filtering can be improved, and filtering processing is more accurate.
In order to solve the above technical problem, the present application provides a filtering method for a linear stochastic system, including:
adding a noise superposition term to the linear random system to obtain a noise superposition linear random system; wherein, the linear stochastic system is obtained by modeling;
constructing an observation value expression according to the noise superposition linear random system to obtain an observation value expression;
and according to an optimal filtering method, filtering by taking the noise superposition linear random system and the observation value expression as parameters to obtain a filtering result.
Optionally, the constructing and processing of the observation value expression according to the noise superposition linear stochastic system to obtain an observation value expression includes:
carrying out initial expression construction processing according to the noise superposition linear random system to obtain an initial observation value expression;
adding a communication constraint item to the initial observation value expression to obtain a communication constraint observation value expression;
and adding a packet loss coefficient item to the communication constraint observation value expression to obtain the observation value expression.
Optionally, adding a communication constraint term to the initial observation value expression to obtain a communication constraint observation value expression, including:
and adding a Markov communication constraint term to the initial observation value expression to obtain the communication constraint observation value expression.
Optionally, according to an optimal filtering method, filtering the noise superposition linear stochastic system and the observation value expression as parameters to obtain a filtering result, including:
according to an optimal filtering method, constructing an optimal filtering equation by taking the noise superposition linear random system and the observation value expression as parameters;
and determining an error covariance matrix according to the initial condition and the optimal filtering equation, and performing repeated iterative calculation on the optimal filtering equation and the determined error covariance matrix to obtain a filtering result.
The present application further provides a filtering apparatus of a linear stochastic system, including:
the noise superposition module is used for adding a noise superposition item to the linear random system to obtain a noise superposition linear random system; wherein, the linear stochastic system is obtained by modeling;
the observation value acquisition module is used for constructing and processing an observation value expression according to the noise superposition linear random system to obtain an observation value expression;
and the filtering module is used for filtering the noise superposition linear stochastic system and the observation value expression as parameters according to an optimal filtering method to obtain a filtering result.
Optionally, the observation value obtaining module includes:
the initial construction unit is used for carrying out initial expression construction processing according to the noise superposition linear random system to obtain an initial observation value expression;
the communication constraint unit is used for adding a communication constraint item to the initial observation value expression to obtain a communication constraint observation value expression;
and the packet loss constraint unit is used for adding a packet loss coefficient item to the communication constraint observation value expression to obtain the observation value expression.
Optionally, the communication constraint unit is specifically configured to add a markov communication constraint term to the initial observation value expression to obtain the communication constraint observation value expression.
Optionally, the filtering module includes:
an optimal filtering equation obtaining unit, configured to construct an optimal filtering equation by using the noise superposition linear stochastic system and the observation value expression as parameters according to an optimal filtering method;
and the iterative filtering calculation unit is used for determining an error covariance matrix according to the initial condition and the optimal filtering equation and performing repeated iterative calculation on the optimal filtering equation and the determined error covariance matrix to obtain a filtering result.
The present application further provides a filtering apparatus of a linear stochastic system, including:
a memory for storing a computer program;
a processor for implementing the steps of the filtering method as described above when executing the computer program.
The present application also provides a computer-readable storage medium having stored thereon a computer program which, when being executed by a processor, carries out the steps of the filtering method as described above.
The filtering method of the linear stochastic system provided by the application comprises the following steps: adding a noise superposition term to the linear random system to obtain a noise superposition linear random system; wherein, the linear stochastic system is obtained by modeling; constructing an observation value expression according to the noise superposition linear random system to obtain an observation value expression; and according to an optimal filtering method, filtering by taking the noise superposition linear random system and the observation value expression as parameters to obtain a filtering result.
By adding the noise superposition item to the linear random system, the linear random system is not only interfered by the system noise at the previous moment but also interfered by the system noise at the current moment, or the linear random system is not only interfered by the system noise at the current moment but also interfered by the system noise at the next moment.
Moreover, the observation expression obtained by the embodiment can simulate the situation of the signal after the channel transmission. Especially, the data communication quantity of the system is reduced by adding communication constraint, the filtering precision is ensured, and the energy consumption of the system can be reduced.
The present application further provides a filtering apparatus for a linear stochastic system, another filtering apparatus, and a computer-readable storage medium, which have the above beneficial effects and are not described herein again.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, it is obvious that the drawings in the following description are only embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
Fig. 1 is a flowchart of a filtering method of a linear stochastic system according to an embodiment of the present disclosure;
fig. 2 is a flowchart of an observation value expression obtaining process of the filtering method according to the embodiment of the present application;
fig. 3 is a flowchart of a filtering process of a filtering method according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of a filtering apparatus of a linear stochastic system according to an embodiment of the present disclosure;
fig. 5 is a process diagram of a filtering method of a linear stochastic system according to an embodiment of the present disclosure.
Detailed Description
The core of the application is to provide a filtering method, a filtering device, another filtering device and a computer readable storage medium of a linear stochastic system, and by adding a noise superposition item to the linear stochastic system, the linear stochastic system is not only interfered by system noise at the last moment, but also interfered by the system noise at the current moment, so that the environment of noise interference in an actual situation can be fitted more completely, the precision of subsequent filtering can be further improved, and the filtering processing is more accurate.
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
Typically, the linear stochastic system includes at least a sensor network, a shared transmission channel, and a remote filter, and embodiments of the present application also extend to this structure. Therefore, when the filtering accuracy of the whole system is reduced, the three parts are adjusted to improve the filtering accuracy, but the accuracy problem cannot be well solved no matter how to adjust the subsequent process under the complex noise interference environment. Furthermore, analysis shows that in a complex noise interference environment, the environmental noise is generally complicated by superposed noise, and modeling in the prior art is generally only a noise term, so that the noise environment cannot be well simulated, and further the subsequent filtering precision is reduced.
Referring to fig. 1, fig. 1 is a flowchart illustrating a filtering method of a linear stochastic system according to an embodiment of the present disclosure.
The present implementation provides a filtering method for a linear stochastic system, which may include:
s101, adding a noise superposition item to the linear random system to obtain a noise superposition linear random system; wherein, the linear random system is obtained by modeling treatment;
the method comprises the following steps of adding a noise superposition item to the linear random system to obtain a superposed linear random system. The linear stochastic system is obtained by modeling. Generally, filtering processing is performed on a linear stochastic system firstly, modeling processing is performed on the system, accordingly, the step can also be regarded as modeling processing performed on the system, and a noise superposition term is added to the linear stochastic system obtained through general modeling, so that the fitted system is not only interfered by system noise at the last moment, but also by the system noise at the current moment, and random noise in actual situations is reflected more completely. Therefore, the filtering precision can be improved through the noise superposition linear stochastic system obtained in the step, and a more accurate filtering result is obtained.
Furthermore, modeling of linear stochastic systems in the prior art typically uses a standard form of modeling for computational convenience, i.e., includes only noise terms at a single instant. The standard form can facilitate the calculation process when simulating calculation. However, the single noise term is only a simple abstraction of random noise in the actual situation, and a linear random system cannot be fitted to the actual situation completely. Compared with the linear stochastic system in the prior art, the noise superposition linear stochastic system in the step completely fits the actual situation, so that the filtering precision is improved, and a more accurate filtering result can be obtained.
The added noise superposition term needs different setting modes according to different specific formula expression forms of the linear random system, but always adds the system noise at the current moment on the basis of the system noise at the previous moment by the random linear system. Or adding the system noise of the next moment on the basis of receiving the system noise of the current moment. In a word, the noise superposition term at another moment is added on the basis of the noise of the existing linear random system, so that the linear random system can completely fit the random phenomenon in the actual situation.
Specifically, the noise superposition linear stochastic system obtained in this step can be represented by the following formula:
where k is 0, 1.. denotes the time of discrete time, m denotes the number of sensors, x (k) denotes the n-dimensional system state, y1(k)…ym(k) Representing the measurements of the m sensors. w (k) represents system noise, v1(k)…vm(k) Representing sensor measurement noise. A (k), B1(k),B2(k+1),c1(k),...,cm(k) A system parameter matrix representing the appropriate dimensions. Wherein, B2(k +1) w (k +1) is a noise superposition term added in the present formula.
S102, carrying out observed value expression construction processing according to a noise superposition linear random system to obtain an observed value expression;
on the basis of step S101, this step aims to perform observation expression construction processing according to the noise superposition stochastic system obtained in the previous step, and obtain an observation expression.
The observation value expression is an expression of a signal received by the filter, and because a certain loss exists in the process of signal transmission in a channel and the physical limitation is received, the signal received by the filter is not a signal directly transmitted by a system, the observation value expression needs to be constructed according to a selected condition, and then the filtering condition of the filter in an actual condition can be tested according to the observation value expression.
Further, the observation value expression constructing process in this step is mainly based on the expression after signal transmission constructed according to the noise superimposed linear random system, specifically, what kind of constraints are added to the transmission signal may be selected according to the actual situation, including but not limited to communication channel constraints and/or data packet loss constraints.
And S103, filtering by taking the noise superposition linear random system and the observed value expression as parameters according to the optimal filtering method to obtain a filtering result.
On the basis of step S102, this step aims to perform filtering processing on the noise-superimposed linear stochastic system and the observation expression obtained in the above step according to an optimal filtering method, so as to obtain a filtering result.
The step is mainly to perform filtering processing, and there are many filtering methods in the field, but the expression form in the embodiment meets the requirement of the optimal filtering method, and the optimal filtering method can obtain a good filtering effect, so the step selects the optimal filtering method to perform filtering to obtain a filtering result.
In summary, in this embodiment, by adding the noise superposition term to the linear random system, the linear random system is not only interfered by the system noise at the previous time but also interfered by the system noise at the current time, or the linear random system is not only interfered by the system noise at the current time but also interfered by the system noise at the next time, so that the environment of noise interference in an actual situation can be fitted more completely, the accuracy of subsequent filtering can be further improved, and the filtering process is more accurate.
Referring to fig. 2, fig. 2 is a flowchart of an observation value expression obtaining process of a filtering method according to an embodiment of the present application.
Based on the previous embodiment, this embodiment mainly provides a specific description of how to construct an observation value expression in the previous embodiment, and other parts are substantially the same as those in the previous embodiment, and the same parts may refer to the previous embodiment, which is not described herein again.
The embodiment may include:
s201, performing initial expression construction processing according to a noise superposition linear random system to obtain an initial observation value expression;
s202, adding a communication constraint item to the initial observation value expression to obtain a communication constraint observation value expression;
and S203, adding a packet loss coefficient item to the communication constraint observation value expression to obtain an observation value expression.
In this embodiment, communication constraint and packet loss constraint are mainly added to the expression in the process of constructing the observation value expression, that is, the communication constraint item added in step S202 and the packet loss coefficient item added in step S203, so as to finally obtain the observation value expression capable of fitting the actual transmission condition.
In step S202, a communication constraint term is added to the initial observation value expression, so as to obtain a communication constraint observation value expression. The reason is that in practical situations, the channel is physically limited and cannot have such a large communication amount, so that a corresponding communication constraint needs to be added to the expression of the observation value to reduce the communication amount and reduce the energy consumption of data transmission.
Optionally, in step S202, a markov communication constraint term may be added to the initial observation value expression to obtain a communication constraint observation value expression.
The Markov communication constraint is specifically characterized in that only one measuring value of a sensor can occupy a shared channel at each moment, and the selection rule of the sensor at each moment is based on a given Markov state transition probability matrix. Therefore, when the state prediction is performed during the filtering process, only the markov state probability transition matrix is known, and the measurement value of the specific sensor is not known to occupy the shared channel.
Specifically, the expression can be made according to the following formula:
wherein the content of the first and second substances,
measurement information received for the remote filter; gamma is a weight coefficient between 0 and 1; { theta (k) } is a specified Markov chain, takes the value of an integer between 1 and m and indicates that the observation data of the first sensor is selected at the k moment for transmission;iis an m-dimensional diagonal matrix, only the ith element of the diagonal is 1, and the other elements are 0; i ismIs an m-dimensional unit matrix.
In general, the communication constraint may be a Markov communication constraint, i.e., only one sensor's measurement information may be transmitted to the remote filter at a time, and the sensor scheduling sequence follows a Markov chain { θ (k) }.
Step S203 is mainly to add a packet loss coefficient item to the communication constraint observation value expression to obtain the observation expression. And the packet loss coefficient item is a coefficient item simulating the packet loss condition.
Specifically, a corresponding packet loss coefficient term is added on the basis of the above formula to obtain an observation expression, which is expressed as follows:
where α (k) is used to describe whether packet loss occurs at time k. If packet loss occurs, α (k) is 0, otherwise it is 1. Y is gamma and ImThe product of (a).
Wherein the probability of data packet loss obeys bernoulli distribution.
Therefore, the observation expression obtained by the embodiment can simulate the situation of the signal after the channel transmission. Especially, the data communication quantity of the system is reduced by adding communication constraint, the filtering precision is ensured, and the energy consumption of the system can be reduced.
Referring to fig. 3, fig. 3 is a flowchart illustrating a filtering process of a filtering method according to an embodiment of the present disclosure.
Based on the previous embodiment, this embodiment mainly aims at a specific description of how to perform filtering in the previous embodiment, other parts are substantially the same as those in the previous embodiment, and the same parts may refer to the previous embodiment, which is not described herein again.
The embodiment may include:
s301, constructing an optimal filtering equation by using a noise superposition linear random system and an observed value expression as parameters according to an optimal filtering method;
the step aims to construct an optimal filtering equation according to an optimal filtering method and a noise superposition linear random system and an observed value expression.
Specifically, the optimal filtering equation can be expressed as follows:
wherein g (k) ═ gT(k,1),...,gT(k,m)]T
Where K (k), F (k) are two key gain parameters, and the expressions include P (k).
Where K (k) is the filter gain, F (k) is the prediction gain, and e (k) is the innovation at time k for modifying the filter value.
Is a parameter matrix.
S302, determining an error covariance matrix according to the initial condition and the optimal filtering equation, and performing repeated iterative computation on the optimal filtering equation and the determined error covariance matrix to obtain a filtering result.
On the basis of step S301, this step aims to perform iterative computation according to initial conditions and an optimal filtering equation to obtain a final filtering result.
Specifically, the determined error covariance matrix can be expressed according to the following formula:
wherein the content of the first and second substances,
is a parameter matrix, Re(k) A covariance matrix representing e (k), by which the filtered value at time k +1 can be calculated from P (k) and thus P (k + 1).
The embodiment of the application provides a filtering method of a linear stochastic system, which can add a noise superposition item to the linear stochastic system, so that the linear stochastic system is not only interfered by system noise at the last moment but also interfered by system noise at the current moment, or the linear stochastic system is not only interfered by the system noise at the current moment but also interfered by the system noise at the next moment, therefore, the environment of noise interference in the actual situation can be fitted more completely, the precision of subsequent filtering can be further improved, and the filtering processing is more accurate.
In the following, a filtering apparatus of a linear stochastic system provided by an embodiment of the present application is introduced, and a filtering apparatus of a linear stochastic system described below and a filtering method of a linear stochastic system described above may be referred to correspondingly.
Referring to fig. 4, fig. 4 is a schematic structural diagram of a filtering apparatus of a linear stochastic system according to an embodiment of the present disclosure.
The embodiment provides a filtering apparatus for a linear stochastic system, which may include:
the noise superposition module 100 is configured to add a noise superposition term to the linear random system to obtain a noise superposition linear random system; wherein, the linear random system is obtained by modeling treatment;
an observed value obtaining module 200, configured to perform observed value expression construction processing according to a noise superposition linear random system to obtain an observed value expression;
and the filtering module 300 is configured to perform filtering processing by using the noise superposition linear stochastic system and the observation value expression as parameters according to an optimal filtering method, so as to obtain a filtering result.
Optionally, the observation value obtaining module 200 may include:
the initial construction unit is used for carrying out initial expression construction processing according to the noise superposition linear random system to obtain an initial observation value expression;
the communication constraint unit is used for adding a communication constraint item to the initial observation value expression to obtain a communication constraint observation value expression;
and the packet loss constraint unit is used for adding a packet loss coefficient item to the communication constraint observation value expression to obtain the observation value expression.
Optionally, the communication constraint unit may be further configured to add a markov communication constraint term to the initial observation value expression to obtain a communication constraint observation value expression.
Optionally, the filtering module 300 may include:
an optimal filtering equation obtaining unit, configured to construct an optimal filtering equation by using the noise superposition linear stochastic system and the observation value expression as parameters according to an optimal filtering method;
and the iterative filtering calculation unit is used for determining an error covariance matrix according to the initial condition and the optimal filtering equation and performing repeated iterative calculation on the optimal filtering equation and the determined error covariance matrix to obtain a filtering result.
The embodiment of the present application further provides a filtering apparatus for a linear stochastic system, which may include
A memory for storing a computer program;
a processor for implementing the steps of the filtering method as described in the above embodiments when executing the computer program.
The embodiments of the present application further provide a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the filtering method as in the above embodiments are implemented.
Based on all the above embodiments, there can also be the following embodiments. The system provided in the implementation is a 3-order system, and the specific implementation steps are as follows:
step one, communication constraint analysis modeling:
for the following 3 rd order linear stochastic system:
wherein the content of the first and second substances,
c1(k)＝[0.5 1 0.6],c2(k)＝[1 0.5 1.5],c3(k)＝[0.8 1.3 1]；
definition v (k) ═ v1(k),v2(k),v3(k)]TW (k) and v (k) are white gaussian noise with independent variance q (k) 0.1 and r (k) 0.1I3In which I3Is a 3 rd order identity matrix. The mean and variance of the initial state x (0) are x0＝[2 1 1.5]T，Px(0)＝I3。
Referring to fig. 5, fig. 5 is a process diagram of a filtering method of a linear stochastic system according to an embodiment of the present disclosure.
As shown in FIG. 5, assume that there are 3 sensors measuring the system signal, corresponding to three measurement values y1(k)、y2(k)、y3(k) In that respect The communication constraint is a markov protocol, i.e. only one sensor measurement value can occupy the shared channel at each moment, and the selection rule of the sensor at each moment is based on a given markov state transition probability matrix. When the remote filter carries out state prediction, only the remote filter carries out state predictionKnowing the markov state probability transition matrix, it is not known that the measurement values of that particular sensor occupy the shared channel.
Setting Markov state transition probability matrix
Initial probability distribution of pi1(0)＝0.1、π2(0)＝0.2、π3(0)＝0.7。
Under the constraint of Markov communication, constructing a sensor network measurement value expression in the following form:
wherein, gamma is 0.8,
θ (k) is the state of the Markov chain that satisfies the Markov state transition matrix, and has a value range of {1,2,3} representing which sensor measurement value is selected at each time,
representing the signal that the remote filter can receive.
The second step is that: analyzing and modeling data packet loss:
in the remote transmission of the shared channel, data packet loss occurs randomly, and the probability of data packet loss obeys bernoulli distribution, that is, the packet loss probability at time k is 1-q (k), and q (k) represents the probability that a data packet at time k is successfully transmitted to a remote filter, where in the embodiment, q (k) is assumed to be 0.9, and a measurement value expression in the following form is constructed:
where α (k) ═ 1 represents successful transmission of the packet, and α (k) ═ 0 represents packet loss.
Thirdly, obtaining an optimal filtering value of the linear stochastic system state:
the optimum filter value satisfies the following equation:
wherein the content of the first and second substances,
the augmentation coefficient matrix is obtained by combining the original system coefficient matrix and the probability model.
Fourthly, solving an estimation error covariance matrix under the minimum mean square error index:
and then, according to the initial condition, repeatedly and iteratively carrying out the calculation of the third step and the calculation of the fourth step to obtain a filtering result.
The embodiments are described in a progressive manner in the specification, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. The device disclosed by the embodiment corresponds to the method disclosed by the embodiment, so that the description is simple, and the relevant points can be referred to the method part for description.
Those of skill would further appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative components and steps have been described above generally in terms of their functionality in order to clearly illustrate this interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. A software module may reside in Random Access Memory (RAM), memory, Read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
The filtering method, the filtering apparatus, another filtering apparatus, and the computer-readable storage medium of a linear stochastic system provided in the present application are described in detail above. The principles and embodiments of the present application are explained herein using specific examples, which are provided only to help understand the method and the core idea of the present application. It should be noted that, for those skilled in the art, it is possible to make several improvements and modifications to the present application without departing from the principle of the present application, and such improvements and modifications also fall within the scope of the claims of the present application.
Claims (3)
1. A filtering apparatus for a linear stochastic system, comprising:
the noise superposition module is used for adding a noise superposition item at another moment on the basis of the noise of the linear random system to obtain a noise superposition linear random system; wherein, the linear stochastic system is obtained by modeling; wherein the linear stochastic system comprises a sensor network, a shared transmission channel, and a remote filter;
the observation value acquisition module is used for constructing and processing an observation value expression according to the noise superposition linear random system to obtain an observation value expression;
the filtering module is used for filtering the noise superposition linear random system and the observation value expression as parameters according to an optimal filtering method to obtain a filtering result;
wherein the observation value acquisition module includes: the initial construction unit is used for carrying out initial expression construction processing according to the noise superposition linear random system to obtain an initial observation value expression; the communication constraint unit is used for adding a communication constraint item to the initial observation value expression to obtain a communication constraint observation value expression; and the packet loss constraint unit is used for adding a packet loss coefficient item to the communication constraint observation value expression to obtain the observation value expression.
2. The filtering device according to claim 1, wherein the communication constraint unit is specifically configured to add a markov communication constraint term to the initial observation expression to obtain the communication constraint observation expression.
3. The filtering apparatus according to claim 2, wherein the filtering module comprises:
an optimal filtering equation obtaining unit, configured to construct an optimal filtering equation by using the noise superposition linear stochastic system and the observation value expression as parameters according to an optimal filtering method;
and the iterative filtering calculation unit is used for determining an error covariance matrix according to the initial condition and the optimal filtering equation and performing repeated iterative calculation on the optimal filtering equation and the determined error covariance matrix to obtain a filtering result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810293455.5A CN108549221B (en) | 2018-03-30 | 2018-03-30 | Filtering method and related device of linear stochastic system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810293455.5A CN108549221B (en) | 2018-03-30 | 2018-03-30 | Filtering method and related device of linear stochastic system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108549221A CN108549221A (en) | 2018-09-18 |
| CN108549221B true CN108549221B (en) | 2020-11-10 |
Family
ID=63514114
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810293455.5A Active CN108549221B (en) | 2018-03-30 | 2018-03-30 | Filtering method and related device of linear stochastic system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108549221B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPS6158338A (en) * | 1984-08-29 | 1986-03-25 | Nec Corp | Spread spectrum phase encoding power communication system |
| CN103336525A (en) * | 2013-06-18 | 2013-10-02 | 哈尔滨工程大学 | Convenient UKF (Unscented Kalman Filter) filtering method for high weights of stochastic system |
| CN103888100A (en) * | 2014-03-29 | 2014-06-25 | 北京航空航天大学 | Method for filtering non-Gaussian linear stochastic system based on negentropy |
| CN103941692A (en) * | 2014-04-21 | 2014-07-23 | 南京师范大学 | Random switching system H8 filtering information processing method based on resident probabilistic information method |
-
2018
- 2018-03-30 CN CN201810293455.5A patent/CN108549221B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPS6158338A (en) * | 1984-08-29 | 1986-03-25 | Nec Corp | Spread spectrum phase encoding power communication system |
| CN103336525A (en) * | 2013-06-18 | 2013-10-02 | 哈尔滨工程大学 | Convenient UKF (Unscented Kalman Filter) filtering method for high weights of stochastic system |
| CN103888100A (en) * | 2014-03-29 | 2014-06-25 | 北京航空航天大学 | Method for filtering non-Gaussian linear stochastic system based on negentropy |
| CN103941692A (en) * | 2014-04-21 | 2014-07-23 | 南京师范大学 | Random switching system H8 filtering information processing method based on resident probabilistic information method |
Non-Patent Citations (4)
| Title |
|---|
| Optimal filtering for systems with finite-step autocorrelated process noises, random one-step sensor delay and missing measurements;Dongyan Chen 等;《Commun Nonlinear Sci Numer Simulat》;20150828;全文 * |
| Passive filter design for periodic stochastic systems with quantized measurements and randomly occurring nonlinearities;Yong Xu 等;《Journal of the Franklin Institute》;20151130;全文 * |
| 噪声相关时多通道带乘性噪声系统最优滤波;褚东升 等;《青岛海洋大学学报》;20010930;全文 * |
| 时滞随机双线性系统控制与观测器设计;陈云 等;《Proceedings of the 33rd Chinese Control Conference》;20140730;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108549221A (en) | 2018-09-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110275148B (en) | Sea clutter amplitude distribution parameter estimation method and system | |
| CN111046027B (en) | Missing value filling method and device for time series data | |
| KR20200031163A (en) | Neural network structure creation method and device, electronic device, storage medium | |
| CN109379240B (en) | Internet of vehicles flow prediction model construction method and device and electronic equipment | |
| CN112949820B (en) | Cognitive anti-interference target detection method based on generation of countermeasure network | |
| CN112992267B (en) | Single-cell transcription factor regulation network prediction method and device | |
| CN111667843B (en) | Voice wake-up method and system for terminal equipment, electronic equipment and storage medium | |
| CN115688288B (en) | Aircraft pneumatic parameter identification method and device, computer equipment and storage medium | |
| CN110222734B (en) | Bayesian network learning method, intelligent device and storage device | |
| CN114564345A (en) | Server abnormity detection method, device, equipment and storage medium | |
| CN114240779A (en) | Point cloud denoising method, device, equipment and storage medium | |
| CN108549221B (en) | Filtering method and related device of linear stochastic system | |
| CN107607129B (en) | Data calibration method and device and electronic equipment | |
| CN114298299A (en) | Model training method, device, equipment and storage medium based on course learning | |
| CN114049530A (en) | Hybrid precision neural network quantization method, device and equipment | |
| CN116647405B (en) | Multipath QUIC abnormal flow detection method, system and equipment | |
| CN113726545A (en) | Network traffic generation method and device for generating countermeasure network based on knowledge enhancement | |
| CN111258222A (en) | Self-adaptive state estimation method of autoregressive moving average system and closed-loop control system | |
| CN110866043A (en) | Data preprocessing method and device, storage medium and terminal | |
| CN115859048A (en) | Noise processing method and device for partial discharge signal | |
| CN114692529A (en) | CFD high-dimensional response uncertainty quantification method and device, and computer equipment | |
| CN110619624B (en) | Image decomposition method and device | |
| CN112016956A (en) | BP neural network-based ore grade estimation method and device | |
| CN113255921A (en) | Measurement system, method, device and equipment | |
| CN113468771B (en) | Vibration estimation method using structure intrinsic parameters |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |