CN115390112A - Electric power system Beidou positioning signal filtering method, device, equipment and storage medium - Google Patents
Electric power system Beidou positioning signal filtering method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN115390112A CN115390112A CN202211025530.2A CN202211025530A CN115390112A CN 115390112 A CN115390112 A CN 115390112A CN 202211025530 A CN202211025530 A CN 202211025530A CN 115390112 A CN115390112 A CN 115390112A
- Authority
- CN
- China
- Prior art keywords
- beidou positioning
- signal
- initial
- power system
- positioning signal
- 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.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S19/00—Satellite radio beacon positioning systems; Determining position, velocity or attitude using signals transmitted by such systems
- G01S19/38—Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system
- G01S19/39—Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system the satellite radio beacon positioning system transmitting time-stamped messages, e.g. GPS [Global Positioning System], GLONASS [Global Orbiting Navigation Satellite System] or GALILEO
- G01S19/42—Determining position
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S19/00—Satellite radio beacon positioning systems; Determining position, velocity or attitude using signals transmitted by such systems
- G01S19/01—Satellite radio beacon positioning systems transmitting time-stamped messages, e.g. GPS [Global Positioning System], GLONASS [Global Orbiting Navigation Satellite System] or GALILEO
- G01S19/13—Receivers
- G01S19/21—Interference related issues ; Issues related to cross-correlation, spoofing or other methods of denial of service
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S19/00—Satellite radio beacon positioning systems; Determining position, velocity or attitude using signals transmitted by such systems
- G01S19/01—Satellite radio beacon positioning systems transmitting time-stamped messages, e.g. GPS [Global Positioning System], GLONASS [Global Orbiting Navigation Satellite System] or GALILEO
- G01S19/13—Receivers
- G01S19/35—Constructional details or hardware or software details of the signal processing chain
- G01S19/37—Hardware or software details of the signal processing chain
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks
Abstract
The invention discloses a Beidou positioning signal filtering method, a Beidou positioning signal filtering device, beidou positioning signal filtering equipment and a storage medium of a power system. A filtering method for Beidou positioning signals of an electric power system comprises the following steps: acquiring an initial Beidou positioning signal received by a Beidou positioning receiver of the power system; inputting the initial Beidou positioning signal into a pre-configured self-adaptive RLS filter to obtain an estimated electromagnetic interference signal; inputting the estimated electromagnetic interference signal into a pre-trained neural network model to obtain a corrected target electromagnetic interference signal; and filtering a target electromagnetic interference signal from the initial Beidou positioning signal to obtain a target Beidou positioning signal. The initial Beidou positioning signal received by the Beidou positioning receiver is filtered by the self-adaptive RLS filter and the pre-trained neural network model to obtain a target electromagnetic interference signal with higher precision, and the positioning precision and the reliability of the Beidou positioning receiver are effectively improved.
Description
Technical Field
The invention relates to the technical field of power system positioning, in particular to a power system Beidou positioning signal filtering method, device, equipment and storage medium.
Background
The service fields of planning, infrastructure construction, operation and inspection, marketing, scheduling and the like of the power system have high-precision positioning requirements, so that safe and stable high-precision positioning equipment needs to be configured for the power system.
At present, the Beidou system is widely applied to a power system due to the advantages of wide coverage, high-precision positioning and high safety. However, the current Beidou satellite positioning is easily affected by electromagnetic interference around positioning equipment, so that the positioning accuracy is reduced. Therefore, in the using process, the Beidou satellite positioning signals of the positioning equipment need to be filtered to filter electromagnetic interference signals. However, when the kalman gain vector in the existing filtering mode tends to zero, the algorithm loses the capability of tracking variable channel parameters, the efficient filtering processing of the Beidou positioning signal is difficult to realize, and the high-precision positioning requirement of the power system cannot be met.
Disclosure of Invention
The invention provides a method, a device, equipment and a storage medium for filtering a Beidou positioning signal of a power system, and aims to effectively improve the filtering reliability of the Beidou positioning signal.
According to one aspect of the invention, a power system Beidou positioning signal filtering method is provided, and comprises the following steps:
acquiring an initial Beidou positioning signal received by a Beidou positioning receiver of the power system;
inputting the initial Beidou positioning signal into a pre-configured self-adaptive RLS filter to obtain an estimated electromagnetic interference signal;
inputting the estimated electromagnetic interference signal into a pre-trained neural network model to obtain a corrected target electromagnetic interference signal;
and filtering the target electromagnetic interference signal from the initial Beidou positioning signal to obtain a target Beidou positioning signal.
Optionally, the inputting the initial beidou positioning signal into a pre-configured adaptive RLS filter to obtain an estimated electromagnetic interference signal includes:
discretizing the initial Beidou positioning signal to obtain a discretized initial useful signal and an initial interference signal;
delaying the initial useful signal and the initial interference signal to obtain a reference useful signal and a reference interference signal;
and inputting the reference useful signal and the reference interference signal into a pre-configured adaptive RLS filter to obtain an estimated electromagnetic interference signal.
Optionally, before the inputting the reference useful signal and the reference interference signal into a preconfigured adaptive RLS filter to obtain an estimated electromagnetic interference signal, the method further includes:
performing self-adaptive adjustment on a forgetting factor of the self-adaptive RLS filter;
updating filter coefficients of the adaptive RLS filter;
updating an autocorrelation matrix of the adaptive RLS filter.
Optionally, the adaptively adjusting the forgetting factor of the adaptive RLS filter includes:
adaptively adjusting a forgetting factor of the adaptive RLS filter based on the following formula:
wherein λ is the forgetting factor, λ 0 A steady state value representing said forgetting factor at system steady state, b represents an adjustment rate controlling said forgetting factor, λ 1 The value is an initial value of the forgetting factor given during system transient, ζ is a threshold of a determination condition, U is the determination condition of the forgetting factor, and n represents the nth time.
Optionally, the updating the filter coefficients of the adaptive RLS filter includes:
updating filter coefficients of the adaptive RLS filter based on the following formula:
W(n)＝W(n-1)+g(n)e(n)
wherein W (n) = [ omega ] 0 (n),ω 1 (n),…,ω J-1 (n)] T W (n) is the filter weight coefficient vector at time n, ω 0 (n)、ω 1 (n) and ω J-1 (n) filtering coefficients of a 0 th stage, a 1 st stage and a J-1 st stage at the moment n respectively, g (n) is a gain coefficient, e (n) is a system error, d (n) is the reference useful signal and the reference interference signal, lambda is a forgetting factor, and P (n-1) is an autocorrelation matrix at the moment n-1.
Optionally, the updating the autocorrelation matrix of the adaptive RLS filter includes:
updating an autocorrelation matrix of the adaptive RLS filter based on the following equation:
P(n)＝[P(n-1)-g(n)d T (n)P(n-1)]/λ
wherein g (n) is a gain coefficient, d (n) is the reference useful signal and the reference interference signal, P (n-1) is an autocorrelation matrix at the time of n-1, and lambda is a forgetting factor.
Optionally, the pre-trained neural network model is a BP neural network model, and the number of neurons in each layer of the BP neural network model is obtained by calculation using a Muti-arm Bandit algorithm.
According to another aspect of the invention, a Beidou positioning signal filtering device for an electric power system is provided, which is characterized by comprising:
the acquisition module is used for executing acquisition of an initial Beidou positioning signal received by a Beidou positioning receiver of the power system;
the filtering module is used for inputting the initial Beidou positioning signal into a pre-configured self-adaptive RLS filter to obtain an estimated electromagnetic interference signal;
the correction module is used for inputting the estimated electromagnetic interference signal into a pre-trained neural network model to obtain a corrected target electromagnetic interference signal;
and the output module is used for filtering the target electromagnetic interference signal from the initial Beidou positioning signal to obtain a target Beidou positioning signal.
According to another aspect of the invention, a power system Beidou positioning signal filtering device is provided, and the device comprises:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to execute the power system Beidou positioning signal filtering method according to any embodiment of the invention.
According to another aspect of the present invention, a computer-readable storage medium is provided, where computer instructions are stored, and the computer instructions are used for causing a processor to implement the power system Beidou positioning signal filtering method according to any embodiment of the present invention when executed.
According to the technical scheme of the embodiment of the invention, the initial Beidou positioning signal received by the Beidou positioning receiver is filtered by the self-adaptive RLS filter, the estimated electromagnetic interference signal based on the initial Beidou positioning signal can be rapidly converged and output, then the estimated electromagnetic interference signal is further corrected by utilizing the pre-trained neural network model, the target electromagnetic interference signal with higher precision can be obtained, and finally the target electromagnetic interference signal is filtered in the initial Beidou positioning signal to obtain the clean Beidou positioning signal, so that the influence of the interference signal on the positioning precision of the Beidou positioning receiver is effectively reduced, and the positioning precision and the reliability of the Beidou positioning receiver are improved.
It should be understood that the statements in this section are not intended to identify key or critical features of the embodiments of the present invention, nor are they intended to limit the scope of the invention. Other features of the present invention will become apparent from the following description.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a flowchart of a filtering method for a Beidou positioning signal of an electric power system according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a Beidou positioning signal filtering device of an electric power system according to a second embodiment of the present invention;
fig. 3 is a schematic structural diagram of an apparatus according to a third embodiment of the present invention.
Detailed Description
In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the 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 invention.
It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
Example one
Fig. 1 is a flowchart of a beidou positioning signal filtering method for an electrical power system according to an embodiment of the present invention, where the embodiment is applicable to a situation where a beidou positioning signal received by a beidou positioning receiver disposed in an electrical power device in an electrical power system is subjected to filtering processing to improve positioning accuracy, and the method may be executed by a beidou positioning signal filtering device for the electrical power system, where the beidou positioning signal filtering device for the electrical power system may be implemented in a form of hardware and/or software, and the beidou positioning signal filtering device for the electrical power system may be configured in a computer device, such as a server, a workstation, a personal computer, and the like. As shown in fig. 1, the method includes:
s110, acquiring that the Beidou positioning receiver of the power system receives an initial Beidou positioning signal.
The Chinese Beidou Satellite Navigation System (BeiDou Navigation Satellite System, BDS for short) comprises a space section, a ground section and a user section, can provide high-precision, high-reliability positioning, navigation and time service for various users all day and night in a global range, has short message communication capacity, and initially has regional Navigation, positioning and time service capacities, wherein the positioning precision is decimeter and centimeter level, the speed measurement precision is 0.2 meter/second, and the time service precision is 10 nanoseconds. In the aspect of power dispatching, the Beidou-based power time synchronization application can create conditions for high-precision time applications such as power accident analysis, power early warning systems, protection systems and the like. The Beidou positioning receiver is specially used for receiving Beidou positioning signals and decoding based on the Beidou positioning signals to obtain current positioning information, time service information and the like.
Wherein, the initial big dipper positioning signal can be obtained from big dipper positioning receiver. And the Beidou positioning receiver receives satellite signals sent by the Beidou positioning satellite to obtain initial Beidou positioning signals.
And S120, inputting the initial Beidou positioning signal into a pre-configured self-adaptive RLS filter to obtain an estimated electromagnetic interference signal.
An RLS (Recursive Least Square) filter, also called a Least Square method, is a fast algorithm of a Least Square algorithm, and a Recursive Least Square adaptive filter is an optimal filter for a set of known data, and does not make assumptions on the statistical characteristics of an input sequence in a processing process, but is a purely deterministic minimization problem. In the RLS filtering algorithm, the smaller the forgetting factor is, the stronger the tracking capability to time-varying parameters is, but the sensitivity to noise can cause larger stable error; the larger the forgetting factor, the less tracking ability but less sensitive to noise, and the smaller the estimation error of the parameter when converging. The traditional RLS filtering algorithm for the fixed forgetting factor cannot achieve fast tracking speed and small positioning error at the same time, the ability of tracking variable channel parameters is lost when a gain vector tends to zero, efficient Beidou positioning signal filtering processing is difficult to achieve, and the high-precision positioning requirement of a power system cannot be met. Therefore, in the embodiment of the invention, the adaptive RLS filter is configured in advance, and the adaptive forgetting factor is continuously updated in the process of filtering the Beidou positioning signal, so that the convergence speed of the algorithm is ensured, the problems that the convergence speed is low, the network precision and the operation speed are influenced, and the correction value of the RLS algorithm error is difficult to efficiently and accurately output due to local optimization are avoided, and further the compensation of the RLS algorithm global error is realized.
In the embodiment of the invention, the obtained initial Beidou positioning signal is input into a preset adaptive RLS filter for processing, and then the estimated electromagnetic interference signal can be obtained, wherein the estimated electromagnetic interference signal is an expected calculation result output by the preset adaptive RLS filter and represents that the estimated electromagnetic interference signal is calculated and judged as the interference signal in the initial Beidou positioning signal by the adaptive RLS filter.
S130, inputting the estimated electromagnetic interference signal into a pre-trained neural network model to obtain a corrected target electromagnetic interference signal.
In the embodiment of the invention, a pre-trained neural network model is also arranged to correct the estimated electromagnetic interference signal so as to ensure the filtering accuracy of the interference signal in the Beidou positioning signal and improve the filtering accuracy of the self-adaptive RLS.
S140, filtering a target electromagnetic interference signal from the initial Beidou positioning signal to obtain a target Beidou positioning signal.
In the step, the electromagnetic interference signals in the Beidou positioning signals are filtered by using the adaptive RLS filter to obtain estimated electromagnetic interference signals, then the estimated electromagnetic interference signals are further corrected by using a pre-trained neural network model to obtain final target electromagnetic interference signals, and in the step, the target electromagnetic interference signals can be filtered in the initial Beidou positioning signals to obtain interference-free Beidou positioning signals, namely, the influence of electromagnetic interference on the positioning accuracy of the Beidou positioning receiver is effectively reduced, and the positioning accuracy of the Beidou positioning receiver is improved.
In the embodiment of the invention, the initial Beidou positioning signal received by the Beidou positioning receiver is filtered by the self-adaptive RLS filter, the estimated electromagnetic interference signal based on the initial Beidou positioning signal can be rapidly converged and output, then the estimated electromagnetic interference signal is further corrected by utilizing a pre-trained neural network model, the target electromagnetic interference signal with higher precision can be obtained, and finally the target electromagnetic interference signal is filtered in the initial Beidou positioning signal to obtain a clean Beidou positioning signal, so that the influence of the interference signal on the positioning precision of the Beidou positioning receiver is effectively reduced, and the positioning precision and the reliability of the Beidou positioning receiver are improved.
Optionally, S120 may include:
s121, discretizing the initial Beidou positioning signal to obtain a discretized initial useful signal and an initial interference signal.
In the embodiment of the present invention, it is considered that the initial beidou positioning signal x (n) received by the beidou positioning receiver is composed of two parts, which are represented as x (n) = s (n) + epsilon (n). Wherein s (n) is a discrete initial useful signal in the initial Beidou positioning signal, and epsilon (n) is a discrete initial interference signal. According to the respective characteristics, s (n) is a weak correlation signal, and epsilon (n) can be described by an Alpha stable distribution noise model and can be expressed as the following characteristic function:
ε(n)＝exp{-γ|n| α } (1)
where 1< α <2 is the eigenvalue and γ is the diffusion factor, similar to the variance in the gaussian distribution. In particular, when γ =1, the Alpha stationary distribution noise is also referred to as standard Alpha stationary distribution noise. When α =1, the Alpha distribution degenerates to cauchy distribution. When α =2, the Alpha distribution is gaussian.
And S122, delaying the initial useful signal and the initial interference signal to obtain a reference useful signal and a reference interference signal.
In the embodiment of the invention, after an initial Beidou positioning signal discretization signal acquired by a Beidou positioning receiver is subjected to delay, a reference channel signal D (n) = x (n-D) is obtained, and the channel signal comprises a reference useful signal and a reference interference signal. Where D is the delay time whose value is weakly related to the spread spectrum signal and related to the sampling frequency. D is selected to ensure that the desired signal is uncorrelated and that the reference channel signal has only a single emi signal, such that the correlated signal is the correlation of the reference channel signal with the emi signal.
And S123, inputting the reference useful signal and the reference interference signal into a pre-configured adaptive RLS filter to obtain an estimated electromagnetic interference signal.
Optionally, in the embodiment of the present invention, the power system Beidou positioning signal filtering method includes two signal channels, where the first channel is an initial Beidou positioning signal input channel, and the second channel is a reference signal (reference useful signal and reference interference signal) input channel.
The reference signal d (n) is output after passing through the adaptive RLS filter
Is the sample estimate of x (n), and is subtracted from x (n) to obtain the useful signal with a systematic error of e (n).
And multiplying the filter weight coefficients by corresponding sampling data in sequence, adopting J-level filter coefficients, and setting the initial value of the weighting coefficient to be zero. The multiplication result is sent to an adder for accumulation, and the following results can be obtained:
wherein, ω is j And (n) is a j-th stage filter coefficient.
And providing a method for dynamically adjusting the forgetting factor based on the weight error gradient. Definition of W (n) = [ omega ] 0 (n),ω 1 (n),...,ω J-1 (n)] T Is a filter weight coefficient vector at time n. Wherein, ω is 0 (n)，ω 1 (n) and ω J-1 And (n) are respectively the 0 th stage, the 1 st stage and the J-1 filtering coefficient at the moment n. Order to
For the weight error gradient, the discrimination condition is defined as:
when the system is in a steady state, W (n) is converged at a certain steady state value, and the weight error gradient
Basically unchanged and approaching zero, and the judgment condition U at the moment is also close to zero. And if the judgment condition U is larger than a certain threshold value and is not zero, the system is in a dynamic process at the moment. The constant mu is introduced on the one hand to allow the occurrence of system dynamics to be judged more quickly. Another aspect is to prevent the extreme point of the current weight error gradient value at the transition from causing unnecessary misjudgment.
In the embodiment of the invention, in the RLS filtering algorithm, the smaller the forgetting factor is, the stronger the tracking capability on time-varying parameters is, but the sensitivity to noise can cause larger stable error; the larger the forgetting factor, the less tracking ability but less sensitive to noise, and the smaller the estimation error of the parameter when converging. The traditional RLS filtering algorithm cannot achieve fast tracking speed and small positioning error at the same time, the ability of tracking variable channel parameters is lost when a gain vector tends to zero, efficient Beidou positioning signal filtering processing is difficult to achieve, and the high-precision positioning requirement of a power system cannot be met.
Further, in the embodiment of the present invention, the method further includes performing adaptive adjustment on a forgetting factor of the adaptive RLS filter; updating the filter coefficients of the adaptive RLS filter; the autocorrelation matrix of the adaptive RLS filter is updated.
The forgetting factor is adaptively adjusted, and the adaptive adjustment discriminant expression is as follows:
wherein λ is the forgetting factor, λ 0 A steady state value representing the forgetting factor at system steady state,
b represents the rate of adjustment, λ, controlling said forgetting factor 1 The value is an initial value of the forgetting factor given during system transient, ζ is a threshold of a determination condition, U is the determination condition of the forgetting factor, and n represents the nth time.
When the system is in transient state, because the smaller lambda tracking capability and the convergence speed are faster, the lambda is quickly assigned with a smaller initial value lambda 1 But at the same time it also diminishes its ability to filter out noise. Over time, λ increases exponentially to a constant value λ 0 Thereby improving the convergence speed of the algorithm.
Updating filter coefficients of the adaptive RLS filter based on the following formula:
W(n)＝W(n-1)+g(n)e(n) (6)
wherein W (n) = [ omega ] 0 (n),ω 1 (n),…,ω J-1 (n)] T W (n) is the filter weight coefficient vector at time n, ω 0 (n)、ω 1 (n) and ω J-1 (n) filtering coefficients of a 0 th stage, a 1 st stage and a J-1 st stage at the moment n respectively, g (n) is a gain coefficient, e (n) is a system error, d (n) is the reference useful signal and the reference interference signal, lambda is a forgetting factor, and P (n-1) is an autocorrelation matrix at the moment n-1.
Updating an autocorrelation matrix of the adaptive RLS filter based on the following equation:
wherein g (n) is a gain coefficient, d (n) is the reference useful signal and the reference interference signal, P (n-1) is an autocorrelation matrix at the time of n-1, and lambda is a forgetting factor.
In the embodiment of the invention, the pre-trained neural network model is a BP neural network model, and the number of neurons in each layer of the BP neural network model is calculated and obtained by utilizing a Muti-armed Bandit algorithm.
And equivalently taking the estimation error, the filter gain and the autocorrelation inverse matrix as the input of the BP neural network, thereby correcting the sample estimation value, namely the electromagnetic interference estimation signal.
The method comprises the steps of inputting sample data into an input by adopting a three-layer neural network structure comprising an input layer, a hidden layer and an output layer, setting a hidden layer neuron and an output layer neuron activation function, and then calculating an error of the output layer to construct a BP neural network, wherein the details are as follows.
Firstly, a three-layer neural network structure with t inputs and r outputs is built. Wherein, the number of hidden layer neurons is set as k, i.e. the input layer neuron vector is expressed as
Hidden layer neuron output vector representation as
The output layer output vector is represented as
The network weight between the input layer neuron and the hidden layer neuron is v ih The network weight between hidden layer neuron and output layer neuron is w hj Hidden layer neuron threshold θ h Output layer neuron threshold value delta j 。
Then, training the neural network, setting a hidden layer neuron activation function f (x), outputting a layer neuron activation function g (x), and respectively obtaining hidden layer neurons s h And output layer neurons o j Is composed of
And
the hidden layer and the output layer activation functions are respectively defined as
And
the loss function can reflect the difference between the model and actual data, and the error of the next round of training is gradually reduced by updating the weight and the bias through back propagation, so that the calculation precision is improved. To determine the error between the estimated value and the actual value, a loss function is defined as
Wherein N is the number of samples, y is the neural network training sample output, r is the dimensionality of the data,
is the desired output.
And (3) optimizing the BP neural network by using an epsilon-greedy algorithm to construct a G-BP neural network, wherein the G-BP neural network comprises the following steps.
Modeling the neuron combination selection problem of each layer as a multi-arm gambling machine problem (MAB), and deciding the number of neurons of the optimal hidden layer for the neural network according to the obtained reward; the rocker arm is defined as the combination of the number of each layer of the neurons, wherein the number of the layers of the neural network is set to be 3, the number of the neurons in each layer is divided into 3 grades between [32,128], and the combination is 9 types, namely 9 rocker arms exist. And defining the reciprocal of the loss function obtained between two training sessions of the neural network as the reward.
1) Initialization: and initializing the selection times of the neuron combinations of each layer and the reward values of the combinations, and when t is less than 9, traversing to select each neuron group and obtaining the initial reward value.
2) Selecting the number of the neurons: firstly, generating a random number mu epsilon (0,1), selecting a neuron combination with the maximum historical reward value as the number of hidden layers of the neural network when the random number mu is larger than epsilon, and otherwise, randomly selecting a neuron combination as the number of the hidden layers of the neural network;
3) Updating: the loss function value is observed between every two times of training, and the reward value and each combined selection number are updated according to the loss function value until the algorithm is finished.
And constructing a G-BP neural network according to the obtained hidden layer number and each layer of neuron number, inputting a training set into neurons of an input layer, then, positively propagating and calculating and outputting signals layer by layer until a result of an output layer exists, calculating an error of the output layer, and then, reversely propagating and updating the weight and the threshold of each layer of neurons by utilizing the error. The training is not stopped until the process is repeated until the iteration termination condition is met, and the obtained neural network parameters hardly change. And obtaining a G-BP neural network model which meets error conditions and has high accuracy, and learning the sample data based on the neural network to obtain a corrected sample estimation value, namely an electromagnetic interference signal.
Example two
Fig. 2 is a schematic structural diagram of a Beidou positioning signal filtering device of an electric power system according to a third embodiment of the present invention. As shown in fig. 2, the apparatus includes an obtaining module 21, a filtering module 22, a correcting module 23, and an output module 24:
the obtaining module 21 is configured to obtain an initial Beidou positioning signal received by a Beidou positioning receiver of the power system;
the filtering module 22 is configured to perform input of the initial Beidou positioning signal into a preconfigured adaptive RLS filter to obtain an estimated electromagnetic interference signal;
the correcting module 23 is configured to input the estimated electromagnetic interference signal into a pre-trained neural network model to obtain a corrected target electromagnetic interference signal;
and the output module 24 is configured to perform filtering of the target electromagnetic interference signal from the initial Beidou positioning signal to obtain a target Beidou positioning signal.
Optionally, the filtering module 22 includes:
the discretization submodule is used for discretizing the initial Beidou positioning signal to obtain a discretized initial useful signal and an initial interference signal;
the delay submodule is used for delaying the initial useful signal and the initial interference signal to obtain a reference useful signal and a reference interference signal;
and the estimation sub-module is used for inputting the reference useful signal and the reference interference signal into a pre-configured adaptive RLS filter to obtain an estimated electromagnetic interference signal.
The filtering module 22 further includes:
a forgetting factor updating submodule, configured to perform adaptive adjustment on a forgetting factor of the adaptive RLS filter;
a filter coefficient updating submodule for updating the filter coefficients of the adaptive RLS filter;
and the autocorrelation matrix updating submodule is used for updating the autocorrelation matrix of the adaptive RLS filter.
The forgetting factor updating submodule comprises:
a forgetting factor updating unit, configured to adaptively adjust a forgetting factor of the adaptive RLS filter based on the following formula:
wherein λ is the forgetting factor, λ 0 A steady state value representing the forgetting factor at system steady state,
b represents the rate of adjustment, λ, controlling said forgetting factor 1 The value is an initial value of the forgetting factor given during system transient, ζ is a threshold of a determination condition, U is the determination condition of the forgetting factor, and n represents the nth time.
The filter coefficient updating submodule comprises:
a filter coefficient updating unit for updating the filter coefficients of the adaptive RLS filter based on the following formula:
W(n)＝W(n-1)+g(n)e(n) (10)
wherein W (n) = [ omega ] 0 (n),ω 1 (n),…,ω J-1 (n)] T W (n) is the filter weight coefficient vector at time n, ω 0 (n)、ω 1 (n) and ω J-1 (n) filtering coefficients of a 0 th stage, a 1 st stage and a J-1 st stage at the moment n respectively, g (n) is a gain coefficient, e (n) is a system error, d (n) is the reference useful signal and the reference interference signal, lambda is a forgetting factor, and P (n-1) is an autocorrelation matrix at the moment n-1.
The autocorrelation matrix updating submodule comprises:
an autocorrelation matrix updating unit for updating the autocorrelation matrix of the adaptive RLS filter based on the following formula:
P(n)＝[P(n-1)-g(n)d T (n)P(n-1)]/λ
wherein g (n) is a gain coefficient, d (n) is the reference useful signal and the reference interference signal, P (n-1) is an autocorrelation matrix at the time of n-1, and lambda is a forgetting factor.
The pre-trained neural network model is a BP neural network model, and the number of neurons in each layer of the BP neural network model is obtained by calculation through a Muti-armed Bandit algorithm.
The Beidou positioning signal filtering device for the electric power system, provided by the embodiment of the invention, can execute the Beidou positioning signal filtering method for the electric power system, provided by any embodiment of the invention, and has corresponding functional modules and beneficial effects of the execution method.
EXAMPLE III
Fig. 3 shows a schematic structural diagram of a power system beidou positioning signal filtering device 10 that can be used to implement an embodiment of the present invention. The power system beidou locating signal filtering device is intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smart phones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the inventions described and/or claimed herein.
As shown in fig. 3, the power system beidou positioning signal filtering device 10 includes at least one processor 11, and a memory communicatively connected to the at least one processor 11, such as a Read Only Memory (ROM) 12, a Random Access Memory (RAM) 13, and the like, where the memory stores a computer program executable by the at least one processor, and the processor 11 can perform various suitable actions and processes according to the computer program stored in the Read Only Memory (ROM) 12 or the computer program loaded from the storage unit 18 into the Random Access Memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the power system beidou positioning signal filtering device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other via a bus 14. An input/output (I/O) interface 15 is also connected to bus 14.
A number of components in the electronic device 10 are connected to the I/O interface 15, including: an input unit 16 such as a keyboard, a mouse, or the like; an output unit 17 such as various types of displays, speakers, and the like; a storage unit 18 such as a magnetic disk, optical disk, or the like; and a communication unit 19 such as a network card, modem, wireless communication transceiver, etc. The communication unit 19 allows the power system beidou locating signal filtering device 10 to exchange information/data with other devices through a computer network such as the internet and/or various telecommunication networks.
The processor 11 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various processors running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, or the like. Processor 11 performs the various methods and processes described above, such as the power system beidou locating signal filtering method.
In some embodiments, the power system beidou location signal filtering method may be implemented as a computer program tangibly embodied in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and/or installed onto the power system beidou location signal filtering device 10 via the ROM 12 and/or the communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the power system beidou location signal filtering method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the power system beidou location signal filtering method by any other suitable means (e.g., by means of firmware).
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), system on a chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.
Computer programs for implementing the methods of the present invention can be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions/acts specified in the flowchart and/or block diagram block or blocks to be performed. A computer program can execute entirely on a machine, partly on a machine, as a stand-alone software package partly on a machine and partly on a remote machine or entirely on a remote machine or server.
In the context of the present invention, a computer-readable storage medium may be a tangible medium that can contain, or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. A computer readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, the computer readable storage medium may be a machine readable signal medium. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the electronic device. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic, speech, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), blockchain networks, and the Internet.
The computing system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical host and VPS service are overcome.
It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present invention may be executed in parallel, sequentially, or in different orders, and are not limited herein as long as the desired result of the technical solution of the present invention can be achieved.
The above-described embodiments should not be construed as limiting the scope of the invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. The utility model provides a power system big dipper positioning signal filtering method which is characterized by comprising:
acquiring an initial Beidou positioning signal received by a Beidou positioning receiver of the power system;
inputting the initial Beidou positioning signal into a pre-configured self-adaptive RLS filter to obtain an estimated electromagnetic interference signal;
inputting the estimated electromagnetic interference signal into a pre-trained neural network model to obtain a corrected target electromagnetic interference signal;
and filtering the target electromagnetic interference signal from the initial Beidou positioning signal to obtain a target Beidou positioning signal.
2. The power system Beidou positioning signal filtering method according to claim 1, wherein the inputting the initial Beidou positioning signal into a pre-configured adaptive RLS filter to obtain an estimated electromagnetic interference signal comprises:
discretizing the initial Beidou positioning signal to obtain a discretized initial useful signal and an initial interference signal;
delaying the initial useful signal and the initial interference signal to obtain a reference useful signal and a reference interference signal;
and inputting the reference useful signal and the reference interference signal into a pre-configured adaptive RLS filter to obtain an estimated electromagnetic interference signal.
3. The power system Beidou positioning signal filtering method according to claim 2, wherein before inputting the reference useful signal and the reference interference signal into a pre-configured adaptive RLS filter to obtain an estimated electromagnetic interference signal, the method further comprises:
carrying out self-adaptive adjustment on a forgetting factor of the self-adaptive RLS filter;
updating filter coefficients of the adaptive RLS filter;
updating an autocorrelation matrix of the adaptive RLS filter.
4. The power system Beidou positioning signal filtering method according to claim 3, wherein the adaptively adjusting the forgetting factor of the adaptive RLS filter comprises:
adaptively adjusting a forgetting factor of the adaptive RLS filter based on the following formula:
wherein λ is the forgetting factor, λ 0 Represents the steady state value of the forgetting factor when the system is in steady state, b represents the adjustment rate for controlling the forgetting factor, lambda 1 The value is an initial value of the forgetting factor given during system transient, ζ is a threshold of a determination condition, U is the determination condition of the forgetting factor, and n represents the nth time.
5. The power system Beidou positioning signal filtering method according to claim 3, wherein the updating of the filter coefficients of the adaptive RLS filter comprises:
updating filter coefficients of the adaptive RLS filter based on the following formula:
W(n)＝W(n-1)+g(n)e(n)
wherein W (n) = [ ω [ ] 0 (n)，ω 1 (n)，…，ω J-1 (n)] T W (n) is the filter weight coefficient vector at time n, ω 0 (n)、ω 1 (n) and ω J-1 (n) is respectively the 0 th stage, the 1 st stage and the J-1 st stage filter coefficient at the time n, g (n) is a gain coefficient, e (n) is a system error, d (n) is the reference useful signal and the reference interference signal, lambda is a forgetting factor, and P (n-1) is an autocorrelation matrix at the time n-1.
6. The power system Beidou positioning signal filtering method according to claim 3, wherein the updating the autocorrelation matrix of the adaptive RLS filter comprises:
updating an autocorrelation matrix of the adaptive RLS filter based on the following equation:
P(n)＝[P(n-1)-g(n)d T (n)P(n-1)]/λ
wherein g (n) is a gain coefficient, d (n) is the reference useful signal and the reference interference signal, P (n-1) is an autocorrelation matrix at the time of n-1, and lambda is a forgetting factor.
7. The power system Beidou positioning signal filtering method according to claim 1, wherein the pre-trained neural network model is a BP neural network model, and the number of neurons in each layer of the BP neural network model is calculated by a Muti-armed band algorithm.
8. The utility model provides an electric power system big dipper locating signal filter equipment which characterized in that includes:
the acquisition module is used for executing acquisition of an initial Beidou positioning signal received by a Beidou positioning receiver of the power system;
the filtering module is used for inputting the initial Beidou positioning signal into a pre-configured adaptive RLS filter to obtain an estimated electromagnetic interference signal;
the correction module is used for inputting the estimated electromagnetic interference signal into a pre-trained neural network model to obtain a corrected target electromagnetic interference signal;
and the output module is used for filtering the target electromagnetic interference signal from the initial Beidou positioning signal to obtain a target Beidou positioning signal.
9. The utility model provides an electric power system big dipper positioning signal filtering equipment which characterized in that, equipment includes:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the power system Beidou positioning signal filtering method of any of claims 1-7.
10. A computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions for causing a processor to implement the power system beidou positioning signal filtering method of any one of claims 1-7 when executed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211025530.2A CN115390112A (en) | 2022-08-25 | 2022-08-25 | Electric power system Beidou positioning signal filtering method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211025530.2A CN115390112A (en) | 2022-08-25 | 2022-08-25 | Electric power system Beidou positioning signal filtering method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115390112A true CN115390112A (en) | 2022-11-25 |
Family
ID=84121606
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211025530.2A Pending CN115390112A (en) | 2022-08-25 | 2022-08-25 | Electric power system Beidou positioning signal filtering method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115390112A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117572470A (en) * | 2024-01-15 | 2024-02-20 | 广东邦盛北斗科技股份公司 | Beidou system positioning updating method and system applied to artificial intelligence |
-
2022
- 2022-08-25 CN CN202211025530.2A patent/CN115390112A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117572470A (en) * | 2024-01-15 | 2024-02-20 | 广东邦盛北斗科技股份公司 | Beidou system positioning updating method and system applied to artificial intelligence |
| CN117572470B (en) * | 2024-01-15 | 2024-04-19 | 广东邦盛北斗科技股份公司 | Beidou system positioning updating method and system applied to artificial intelligence |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112560996B (en) | User portrait identification model training method, device, readable storage medium and product | |
| CN114065863B (en) | Federal learning method, apparatus, system, electronic device and storage medium | |
| CN113705628B (en) | Determination method and device of pre-training model, electronic equipment and storage medium | |
| CN113870334A (en) | Depth detection method, device, equipment and storage medium | |
| CN115390112A (en) | Electric power system Beidou positioning signal filtering method, device, equipment and storage medium | |
| CN115358411A (en) | Data processing method, device, equipment and medium | |
| CN116485031A (en) | Method, device, equipment and storage medium for predicting short-term power load | |
| CN115469553A (en) | Ship motion state reconstruction method, device, equipment and storage medium | |
| CN114742237A (en) | Federal learning model aggregation method and device, electronic equipment and readable storage medium | |
| CN114938232B (en) | LSTM-based simultaneous co-frequency full-duplex digital domain self-interference suppression method | |
| JP7446359B2 (en) | Traffic data prediction method, traffic data prediction device, electronic equipment, storage medium, computer program product and computer program | |
| CN116088289A (en) | System clock calibration method, device, equipment and storage medium | |
| CN115392441A (en) | Method, apparatus, device and medium for on-chip adaptation of quantized neural network model | |
| CN115759751A (en) | Enterprise risk prediction method and device, storage medium, electronic equipment and product | |
| CN115203564A (en) | Information flow recommendation method and device and computer program product | |
| CN114565961A (en) | Face detection model training method and device, electronic equipment and storage medium | |
| Kim et al. | Square root receding horizon information filters for nonlinear dynamic system models | |
| CN112231987A (en) | Ionosphere forecasting method based on VMD and Elman neural network | |
| CN112996105B (en) | Target positioning method and device based on simultaneous positioning and calibration | |
| US11614560B2 (en) | Integration of physical sensors in a data assimilation framework | |
| CN115237880A (en) | Method, device and equipment for detecting abnormity of time sequence data and storage medium | |
| CN117725834A (en) | Gradient estimation parameter optimization method and device, electronic equipment and storage medium | |
| CN115189798A (en) | Resource allocation method and device, electronic equipment and storage medium | |
| CN115618965A (en) | Federal learning method, device, equipment and medium based on edge calculation | |
| CN114444025A (en) | Rainfall interpolation model determination method, rainfall interpolation method and rainfall interpolation device |
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 |