CN112964941A - Phased array antenna test method, device, equipment and medium - Google Patents
Phased array antenna test method, device, equipment and medium Download PDFInfo
- Publication number
- CN112964941A CN112964941A CN202110314440.4A CN202110314440A CN112964941A CN 112964941 A CN112964941 A CN 112964941A CN 202110314440 A CN202110314440 A CN 202110314440A CN 112964941 A CN112964941 A CN 112964941A
- Authority
- CN
- China
- Prior art keywords
- neural network
- phased array
- array antenna
- hopfield neural
- test
- 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.)
- Granted
Links
- 238000010998 test method Methods 0.000 title abstract description 4
- 238000013528 artificial neural network Methods 0.000 claims abstract description 97
- 238000012360 testing method Methods 0.000 claims abstract description 66
- 238000000034 method Methods 0.000 claims abstract description 49
- 239000000523 sample Substances 0.000 claims abstract description 45
- 238000005457 optimization Methods 0.000 claims abstract description 23
- 238000005259 measurement Methods 0.000 claims abstract description 13
- 238000013524 data verification Methods 0.000 claims abstract description 6
- 230000006870 function Effects 0.000 claims description 44
- 210000002569 neuron Anatomy 0.000 claims description 34
- 239000011159 matrix material Substances 0.000 claims description 23
- 238000005183 dynamical system Methods 0.000 claims description 9
- 230000008569 process Effects 0.000 claims description 8
- 238000013507 mapping Methods 0.000 claims description 7
- 230000008859 change Effects 0.000 claims description 5
- 238000012804 iterative process Methods 0.000 claims description 4
- 239000002356 single layer Substances 0.000 claims description 4
- 238000005070 sampling Methods 0.000 claims description 3
- 238000004590 computer program Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 238000013461 design Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 239000000463 material Substances 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- PPTYJKAXVCCBDU-UHFFFAOYSA-N Rohypnol Chemical compound N=1CC(=O)N(C)C2=CC=C([N+]([O-])=O)C=C2C=1C1=CC=CC=C1F PPTYJKAXVCCBDU-UHFFFAOYSA-N 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 239000003990 capacitor Substances 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000000977 initiatory effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005312 nonlinear dynamic Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000946 synaptic effect Effects 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R29/00—Arrangements for measuring or indicating electric quantities not covered by groups G01R19/00 - G01R27/00
- G01R29/08—Measuring electromagnetic field characteristics
- G01R29/10—Radiation diagrams of antennas
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Electromagnetism (AREA)
- Variable-Direction Aerials And Aerial Arrays (AREA)
Abstract
The invention discloses a phased array antenna test method, a device, equipment and a medium, wherein the method comprises the following steps: determining a position point sequence and a test task sequence of a phased array antenna probe; controlling the phased array antenna probe to move to the coordinate position of the target test point; carrying out automatic test on the target position; scanning the target test point of each phased array antenna probe according to a predefined neural network optimization algorithm to obtain collected data; and performing data verification on all the acquired data after the scanning is finished to obtain the sampled data after the measurement is finished. The embodiment of the invention can improve the scanning test efficiency of the large phased array antenna probe and can be widely applied to the technical field of antenna measurement.
Description
Technical Field
The invention relates to the technical field of antenna measurement, in particular to a phased array antenna test method, a phased array antenna test device, phased array antenna test equipment and a phased array antenna test medium.
Background
The test process of the phased array antenna is complex, and the scheme adopted for scanning each test point by the phased array antenna probe at present is often determined manually or an optimized route is obtained according to an approximate algorithm. Firstly, the artificially determined method has too large artificial subjectivity factor, and different scanning sequence methods need to be set for each different phased array, so that the preset procedure is complicated and the intelligence degree is not high. Meanwhile, if the method set by people is not the optimal or suboptimal scanning route, the overall testing time of the system may be increased, and the testing efficiency may be reduced. Secondly, the approximate algorithm principle is that each antenna node is firstly constructed into a weighted completely undirected graph G, any vertex r in the G is selected as a root node, then a required minimum spanning tree T is found out by using a primum (Prim) algorithm, then a vertex table L obtained according to a traversal sequence is obtained by traversing the minimum spanning tree T in the previous sequence, and finally the root node r is added to the tail of the vertex table L to form a loop H according to the sequence of the vertices in the L. The approximation algorithm is a progressive optimal path solving method, the solving speed is high, but the approximation algorithm cannot solve the optimal solution. In summary, the two methods currently in use still cannot solve the problem of fast scan test of the large phased array antenna probe well.
Disclosure of Invention
In view of this, embodiments of the present invention provide a method, an apparatus, a device, and a medium for testing a phased array antenna, so as to improve the scan testing efficiency of a large phased array antenna probe.
One aspect of the present invention provides a phased array antenna testing method, including:
determining a position point sequence and a test task sequence of a phased array antenna probe;
controlling the phased array antenna probe to move to the coordinate position of the target test point;
carrying out automatic test on the target position;
scanning the target test point of each phased array antenna probe according to a predefined neural network optimization algorithm to obtain collected data;
and performing data verification on all the acquired data after the scanning is finished to obtain the sampled data after the measurement is finished.
Optionally, the determining a sequence of position points and a sequence of test tasks for a phased array antenna probe includes:
dividing the whole phased array antenna node into a plurality of area blocks;
constructing a plurality of area blocks according to a neural network optimization algorithm to obtain an area block route;
traversing a plurality of nodes in each area block according to the area block route and a neural network optimization algorithm to construct a sub-area block route of each area block, wherein a node in a next sub-area block closest to the last point of the probe traversal route in each sub-area block becomes an initial point of probe traversal of the next sub-area block;
and constructing a traversing route of the phased array antenna probe according to the area block route and the sub-area block route.
Optionally, the neural network optimization algorithm is a Hopfield neural network;
each neuron in the Hopfield neural network is used as input and output, and the Hopfield neural network is a single-layer fully-connected recursive network;
the weight of the Hopfield neural network is calculated when the network is built, and the weight of the Hopfield neural network is kept unchanged in the network iteration process;
controlling the stability of the Hopfield neural network in an iterative process through an improved energy function;
and when the Hopfield neural network is operated to a stable state, the state set of each neuron is used as the solution of the PA-TSP.
Optionally, the method further comprises:
treating the Hopfield neural network as a nonlinear dynamical system, wherein the state set of the nonlinear dynamical system changes along with the change of time;
expressing the output state and the output state increment of the nonlinear dynamical system through differential equations;
and completing the nonlinear mapping of the output state by a symmetric sigmoid hyperbolic tangent function.
Optionally, the method further comprises:
abstracting and equivalently converting a network structure of the Hopfield neural network into an amplifying electronic circuit;
simulating the nonlinear saturation characteristics of the neurons of the Hopfield neural network according to the amplifying electronic circuit, enabling each neuron to be equivalent to an electronic amplifier element, enabling the input of each neuron to be equivalent to the input voltage of an electronic element, and enabling the output of each neuron to be equivalent to the output voltage of the electronic element;
wherein the input information of each electronic element comprises external current input and feedback connection information between the electronic element and other electronic elements.
Optionally, the method further comprises:
replacing the original energy function by the energy entropy;
constructing a permutation matrix complying with a PA-TSP rule, and controlling the state set of the neuron output to meet the permutation matrix;
each row element of the permutation matrix has only one 1, and other elements are all 0;
each column of elements of the permutation matrix has only one 1, and other elements are all 0;
the number of elements 1 in the permutation matrix is equal to the number of phased array antenna nodes that have been visited.
Optionally, the method further comprises the step of solving the PA-TSP problem according to the optimized Hopfield neural network, the step comprising:
initializing an initial value and a weight of the Hopfield neural network;
calculating the distance between each region block node;
initializing an input state of the Hopfield neural network;
calculating the increment of the input state according to the optimized Hopfield neural network;
updating the input state of the Hopfield neural network at the next time instant according to a first order Euler method;
updating the output state of the Hopfield neural network at the next moment according to the hyperbolic tangent function;
and calculating an energy function, and determining the output state set of the Hopfield neural network as a set of PA-TSP optimal route nodes until the energy function tends to be stable.
Another aspect of the embodiments of the present invention provides a phased array antenna testing apparatus, including:
the determining module is used for determining a position point sequence and a test task sequence of the phased array antenna probe;
the control module is used for controlling the phased array antenna probe to move to the coordinate position of the target test point;
the test module is used for carrying out automatic test on the target position;
the sampling module is used for scanning the target test point of each phased array antenna probe according to a predefined neural network optimization algorithm to acquire acquired data;
and the checking module is used for carrying out data checking on all the acquired data after the scanning is finished to obtain the sampled data after the measurement is finished.
Another aspect of the embodiments of the present invention provides an electronic device, including a processor and a memory;
the memory is used for storing programs;
the processor executes the program to implement the method as described above.
Another aspect of the embodiments of the present invention provides a computer-readable storage medium storing a program, the program being executed by a processor to implement the method as described above.
The embodiment of the invention also discloses a computer program product or a computer program, which comprises computer instructions, and the computer instructions are stored in a computer readable storage medium. The computer instructions may be read by a processor of a computer device from a computer-readable storage medium, and the computer instructions executed by the processor cause the computer device to perform the foregoing method.
The method comprises the steps of firstly determining a position point sequence and a test task sequence of a phased array antenna probe; then controlling the phased array antenna probe to move to the coordinate position of the target test point; carrying out automatic test on the target position; then scanning the target test point of each phased array antenna probe according to a predefined neural network optimization algorithm to obtain collected data; and finally, performing data verification on all the acquired data after the scanning is finished to obtain the sampled data after the measurement is finished. The embodiment of the invention can improve the scanning test efficiency of the large phased array antenna probe.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, 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 illustrating measurement control of a phased array antenna according to an embodiment of the present invention;
FIG. 2 is an equivalent circuit diagram of a Hopfield neural network according to an embodiment of the present invention;
fig. 3 is a flowchart for solving the PA-TSP problem based on the optimized Hopfield neural network algorithm according to the embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
The phased array antenna is composed of antenna units (radiation units) arranged according to a certain rule, signal power, a synthesis network and a set of control system. Wherein each antenna in the phased array has a phase shifter for changing the phase of the radiated signal from each antenna element. And the variation of the signal amplitude between the antenna elements is realized by a power weighting and distributing network. The phased array antenna can be divided into a linear array antenna and a planar array antenna, and the embodiment of the invention takes a planar array as an example. The planar phased array antenna refers to an array antenna with antenna units distributed on a plane, and antenna beams can be subjected to phased scanning in both azimuth and elevation directions. Most three-dimensional coordinate phased array radars employ planar phased array antennas.
The mechanical control array antenna technology is an important field in the modern radar technology, and has unique function in solving new problems faced by radars. The mechanical control array antenna technology is generally applied to the fields of arrival, communication, electronic warfare, navigation and the like.
The invention improves the problem that the efficiency of scanning each test point by the conventional large phased array antenna probe is low, and provides a method for quantizing the stable state of the model for the energy function better, thereby measuring the stability of the network with higher efficiency.
To solve the problems in the prior art, an embodiment of the present invention provides a phased array antenna testing method, as shown in fig. 1, the method includes the following steps:
determining a position point sequence and a test task sequence of a phased array antenna probe;
controlling the phased array antenna probe to move to the coordinate position of the target test point;
carrying out automatic test on the target position;
scanning the target test point of each phased array antenna probe according to a predefined neural network optimization algorithm to obtain collected data;
and performing data verification on all the acquired data after the scanning is finished to obtain the sampled data after the measurement is finished.
Optionally, the determining a sequence of position points and a sequence of test tasks for a phased array antenna probe includes:
dividing the whole phased array antenna node into a plurality of area blocks;
constructing a plurality of area blocks according to a neural network optimization algorithm to obtain an area block route;
traversing a plurality of nodes in each area block according to the area block route and a neural network optimization algorithm to construct a sub-area block route of each area block, wherein a node in a next sub-area block closest to the last point of the probe traversal route in each sub-area block becomes a convenient starting point of a probe of the next sub-area block;
and constructing a traversing route of the phased array antenna probe according to the area block route and the sub-area block route.
Optionally, the neural network optimization algorithm is a Hopfield neural network;
each neuron in the Hopfield neural network is used as input and output, and the Hopfield neural network is a single-layer fully-connected recursive network;
the weight of the Hopfield neural network is calculated when the network is built, and the weight of the Hopfield neural network is kept unchanged in the network iteration process;
controlling the stability of the Hopfield neural network in an iterative process through an improved energy function;
and when the Hopfield neural network is operated to a stable state, the state set of each neuron is used as the solution of the PA-TSP.
Optionally, the method further comprises:
treating the Hopfield neural network as a nonlinear dynamical system, wherein the state set of the nonlinear dynamical system changes along with the change of time;
expressing the output state and the output state increment of the nonlinear dynamical system through differential equations;
and completing the nonlinear mapping of the output state by a symmetric sigmoid hyperbolic tangent function.
Optionally, the method further comprises:
abstracting and equivalently converting a network structure of the Hopfield neural network into an amplifying electronic circuit;
simulating the nonlinear saturation characteristics of the neurons of the Hopfield neural network according to the amplifying electronic circuit, enabling each neuron to be equivalent to an electronic amplifier element, enabling the input of each neuron to be equivalent to the input voltage of an electronic element, and enabling the output of each neuron to be equivalent to the output voltage of the electronic element;
wherein the input information of each electronic element comprises external current input and feedback connection information between the electronic element and other electronic elements.
Optionally, the method further comprises:
replacing the original energy function by the energy entropy;
constructing a permutation matrix complying with a PA-TSP rule, and controlling the state set of the neuron output to meet the permutation matrix;
each row element of the permutation matrix has only one 1, and other elements are all 0;
each column of elements of the permutation matrix has only one 1, and other elements are all 0;
the number of elements 1 in the permutation matrix is equal to the number of phased array antenna nodes that have been visited.
Optionally, the method further comprises the step of solving the PA-TSP problem according to the optimized Hopfield neural network, the step comprising:
initializing an initial value and a weight of the Hopfield neural network;
calculating the distance between each region block node;
initializing an input state of the Hopfield neural network;
calculating the increment of the input state according to the optimized Hopfield neural network;
updating the input state of the Hopfield neural network at the next time instant according to a first order Euler method;
updating the output state of the Hopfield neural network at the next moment according to the hyperbolic tangent function;
and calculating an energy function, and determining the output state set of the Hopfield neural network as a set of PA-TSP optimal route nodes until the energy function tends to be stable.
The following describes the implementation of the present invention in further detail with reference to the attached drawings.
Fig. 1 is a flow chart of phased array antenna measurement control. The large phased array antenna test flow is as follows: the method comprises the following steps: a phased array antenna system main control computer position point sequence and a test task sequence; step two: controlling the probe to move to the coordinate position of the corresponding unit, and sending a positioning signal to the main control computer after the probe is in place; step three: the main control computer starts the automatic test of the position point after receiving the trigger; step four: scanning each test point of the phased array antenna probe according to a predefined neural network optimization algorithm, and controlling a receiver to collect data; step five: and judging whether the current column is sampled or not, if so, entering a data verification stage until the measurement is finished after all data are sampled, and exporting the sampled data. Wherein, the detailed design rule of the step four neural network optimization algorithm is as follows.
Assuming that the phased array is W rows and Z columns, the neural network algorithm on which the optimization algorithm is based is the Hopfield Neural Network (HNN). The optimized Hopfield neural network algorithm has the following characteristics: 1, each neuron is input and output, and a single-layer full-connection recursive network is formed; 2, the weight of the network is different from that of other neural networks and is obtained by supervised or unsupervised repeated learning, but the weight of the network is calculated according to a certain rule when the network is built, and the weight of the network is not changed in the whole network iteration process, so that an objective function needs to be reasonably selected for optimization; 3, the state of the network changes along with the change of time, and the output state of each neuron at the time t is related to the time t-1; and 4, introducing an improved energy function for judging the stability of the network in the iterative process. Specifically, the energy entropy is used in designing the energy function, and the stability of the energy function value is judged by using the size of the entropy value, so that the stability of network iteration, namely whether the network converges or not, is further judged. The final solution to the PA-TSP problem is the set of states of the individual neurons when the network is running to stability.
Firstly, the Hopfield neural network is regarded as a nonlinear dynamics system, the state set of the system changes along with the change of time, and the output state variable set V of the system is made to be
V＝{vi(t)|i＝1,2,3…n}
Where t is a continuous time variable. The output state and the output state increment of the system can be expressed by the following differential equations
Wherein F takes a symmetric sigmoid hyperbolic tangent function tanh (x) to complete the nonlinear mapping of the output state
Wherein, tanh (x) represents a hyperbolic tangent function; the following is the network architecture design of Hopfield. The Hopfield neural network structure can be abstractly equivalent to an amplifying electronic circuit for simulating the nonlinear saturation characteristics of neurons. Wherein each neuron is equivalent to an electronic amplifier element, the input and output of each neuron are equivalent to the input voltage and output voltage of an electronic element, the input information of each electronic element comprises a constant external current input, and the feedback connections of other electronic elements. Wherein u isiRepresenting the input voltage, v, of the electronic componentiRepresenting the output voltage and op amp i representing the ith neuron. Fig. 2 is an equivalent circuit diagram of a Hopfield neural network. As can be seen from fig. 2, according to kirchhoff's current law, the current relationship of the Hopfield neural network equivalent circuit is:
wherein C represents a capacitance, uiRepresenting the input voltage, v, of the amplifying electronic componentiRepresenting the output voltage, i representing the ith neuron, and a resistance Ri0And a capacitor CiParallel connection for simulating the time delay characteristic of biological neuron, resistance Rij(j 0,1,2 … n) to simulate synaptic characteristics, bias current IiCorresponding to the threshold value.
Let TijThe weight value representing the connection between the neurons is then
The current relationship of the above equation can be simplified as:
wherein R isiAn input resistance representing an input of the amplifier;
input voltage uiAnd uiIncremental differential equations, i.e. state equations of Hopfield neural networks, in which the output voltage viThe non-linear mapping rule is satisfied: i.e. vi＝fi(ui)。
The method comprises the steps that after the state equation definition of the Hopfiled neural network is completed, an energy equation of a defined model is used for measuring whether the model tends to be stable in the iteration process, and the stability in the iteration process of the model is better measured by replacing an original energy function with an energy entropy. Therefore, the energy function E based on the energy entropy is defined as follows:
wherein, TijRepresenting the weight of the connection between the neurons; v. ofiRepresents the output voltage of the ith neuron; v. ofjRepresenting the input voltage of the jth branch in the electronic circuit; lg represents the log base 10 log, i.e. log10；lgTijvivjRepresenting the weights and input voltages v of the connections between neuronsjAnd an output voltage viTaking the log logarithm with the base 10 as the product of the two; riRepresenting the input resistance of the amplifier input. f. of-1(vi) Representing the output voltage viAnd an input voltage uiThe inverse function satisfying the non-linear mapping rule, i.e. equal to the input voltage uiI.e. ui＝f-1(vi)；
Indicating input voltage 0 to viIntegral value within the interval.
And (3) obtaining the state equation and the energy function of the optimized Hopfield neural network model according to the above formulas (1) and (2). The above abstraction sum is then translated into the TSP problem.
To satisfy the PA-TSP rule, a permutation matrix complying with the PA-TSP rule is designed. In the iterative optimization process of the neural network, the state set output by each neuron only needs to meet the rule of the permutation matrix, namely (1) each row of the matrix has one and only one 1, and the rest elements are 0 (one antenna node can be accessed only once); (2) each column of the matrix has only one 1, and the rest elements are 0 (only one antenna node can be accessed at one time); (3) the number of 1 in all elements of the matrix is n (n antenna nodes are visited in total); only if the above three conditions are satisfied, the set of output states is a solution to the PA-TSP problem, and the present invention only needs to find the least costly solution among the solutions.
Therefore, for the PA-TSP problem, it is considered on the basis of the energy function of the above equation (2) Hopfield neural network: (1) the rules of the permutation matrix; (2) n! The solution representing the shortest route is favored in the legal routes. Therefore, the PA-TSP energy function based on the optimized neural network algorithm is solved by combining the design as follows.
Wherein, A and D represent weight values, the first two terms represent that the constraint conditions of the PA-TSP permutation matrix are satisfied, and the last term comprises an optimization objective function term. dxyRepresenting the distance from the antenna node x to the antenna node y (which can also be considered as the distance from the divided area block x to another area block y), the last term in equation (3) contains the path length information of the valid solution in the neural network output. Therefore, based on equation (3), the dynamic equation of equation (1) can be optimized to
Wherein,
finally, the updating of the PA-TSP input state under the optimized Hopfield recurrent neural network model can be updated by a first-order Euler method, and the expression is
Wherein, Uxi(t +1) represents the input state of the neural network at time t; u shapexi(t) represents the input state of the neural network at time t, Uxi(t +1) is Uxi(t) an update status at the next time; initializing the input state of the neural network to
Wherein, deltaxyE (-1,1) represents a random term, U0Representing the initial voltage.
And the updated expression of the output state is
Wherein the non-linear mapping of the output state is a hyperbolic tangent function
In summary, the PA-TSP problem solving based on the optimized Hopfield neural network is briefly described as follows. FIG. 3 is a flow chart for solving the PA-TSP problem based on an optimized Hopfield neural network algorithm.
Initializing initial values of the Hopfield neural network (e.g., input voltage U)0Iteration times) and a weight a';
secondly, the distance d between m area block points is calculated firstlyxy；
Initiating input state U of neural networkxi(t)；
Fourthly, calculating the increment of the input state by utilizing the optimized Hopfiled neural network dynamic equation (4)
Using first order Euler method to update input state U of neural network at next momentxi(t+1)；
Updating output state V of neural network at next moment by hyperbolic tangent functionxi(t)；
Calculating an energy function E until the output state set of the neural network is a set of PA-TSP optimal route nodes when the energy function tends to be stable;
checking whether the output state set meets the PA-TSP permutation matrix rule and whether the energy function E is stable, and if not, repeating the step three to the step eight;
ninthly, obtaining an optimal traversal route L1 of the large phased array area block, and repeating the steps of (i) and (v) according to the obtained route in the order of the area blocks to obtain an optimal traversal route L2 of each antenna node in each area block.
Another aspect of the embodiments of the present invention provides a phased array antenna testing apparatus, including:
the determining module is used for determining a position point sequence and a test task sequence of the phased array antenna probe;
the control module is used for controlling the phased array antenna probe to move to the coordinate position of the target test point;
the test module is used for carrying out automatic test on the target position;
the sampling module is used for scanning the target test point of each phased array antenna probe according to a predefined neural network optimization algorithm to acquire acquired data;
and the checking module is used for carrying out data checking on all the acquired data after the scanning is finished to obtain the sampled data after the measurement is finished.
Another aspect of the embodiments of the present invention provides an electronic device, including a processor and a memory;
the memory is used for storing programs;
the processor executes the program to implement the method as described above.
Another aspect of the embodiments of the present invention provides a computer-readable storage medium storing a program, the program being executed by a processor to implement the method as described above.
The embodiment of the invention also discloses a computer program product or a computer program, which comprises computer instructions, and the computer instructions are stored in a computer readable storage medium. The computer instructions may be read by a processor of a computer device from a computer-readable storage medium, and the computer instructions executed by the processor cause the computer device to perform the foregoing method.
In alternative embodiments, the functions/acts noted in the block diagrams may occur out of the order noted in the operational illustrations. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality/acts involved. Furthermore, the embodiments presented and described in the flow charts of the present invention are provided by way of example in order to provide a more thorough understanding of the technology. The disclosed methods are not limited to the operations and logic flows presented herein. Alternative embodiments are contemplated in which the order of various operations is changed and in which sub-operations described as part of larger operations are performed independently.
Furthermore, although the present invention is described in the context of functional modules, it should be understood that, unless otherwise stated to the contrary, one or more of the described functions and/or features may be integrated in a single physical device and/or software module, or one or more functions and/or features may be implemented in a separate physical device or software module. It will also be appreciated that a detailed discussion of the actual implementation of each module is not necessary for an understanding of the present invention. Rather, the actual implementation of the various functional modules in the apparatus disclosed herein will be understood within the ordinary skill of an engineer, given the nature, function, and internal relationship of the modules. Accordingly, those skilled in the art can, using ordinary skill, practice the invention as set forth in the claims without undue experimentation. It is also to be understood that the specific concepts disclosed are merely illustrative of and not intended to limit the scope of the invention, which is defined by the appended claims and their full scope of equivalents.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The logic and/or steps represented in the flowcharts or otherwise described herein, e.g., an ordered listing of executable instructions that can be considered to implement logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device.
More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium could even be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, via for instance optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner if necessary, and then stored in a computer memory.
It should be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
While embodiments of the invention have been shown and described, it will be understood by those of ordinary skill in the art that: various changes, modifications, substitutions and alterations can be made to the embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the claims and their equivalents.
While the preferred embodiments of the present invention have been illustrated and described, it will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (10)
1. A phased array antenna testing method, comprising:
determining a position point sequence and a test task sequence of a phased array antenna probe;
controlling the phased array antenna probe to move to the coordinate position of the target test point;
carrying out automatic test on the target position;
scanning the target test point of each phased array antenna probe according to a predefined neural network optimization algorithm to obtain collected data;
and performing data verification on all the acquired data after the scanning is finished to obtain the sampled data after the measurement is finished.
2. The method of claim 1, wherein determining the sequence of position points and the sequence of test tasks for the phased array antenna probe comprises:
dividing the whole phased array antenna node into a plurality of area blocks;
constructing a plurality of area blocks according to a neural network optimization algorithm to obtain an area block route;
traversing a plurality of nodes in each area block according to the area block route and a neural network optimization algorithm to construct a sub-area block route of each area block, wherein a node in a next sub-area block closest to the last point of the probe traversal route in each sub-area block becomes a convenient starting point of a probe of the next sub-area block;
and constructing a traversing route of the phased array antenna probe according to the area block route and the sub-area block route.
3. The phased array antenna testing method of claim 1, wherein the neural network optimization algorithm is a Hopfield neural network;
each neuron in the Hopfield neural network is used as input and output, and the Hopfield neural network is a single-layer fully-connected recursive network;
the weight of the Hopfield neural network is calculated when the network is built, and the weight of the Hopfield neural network is kept unchanged in the network iteration process;
controlling the stability of the Hopfield neural network in an iterative process through an improved energy function;
and when the Hopfield neural network is operated to a stable state, the state set of each neuron is used as the solution of the PA-TSP.
4. A method for testing a phased array antenna according to claim 3, the method further comprising:
treating the Hopfield neural network as a nonlinear dynamical system, wherein the state set of the nonlinear dynamical system changes along with the change of time;
expressing the output state and the output state increment of the nonlinear dynamical system through differential equations;
and completing the nonlinear mapping of the output state by a symmetric sigmoid hyperbolic tangent function.
5. The phased array antenna testing method of claim 4, further comprising:
abstracting and equivalently converting a network structure of the Hopfield neural network into an amplifying electronic circuit;
simulating the nonlinear saturation characteristics of the neurons of the Hopfield neural network according to the amplifying electronic circuit, enabling each neuron to be equivalent to an electronic amplifier element, enabling the input of each neuron to be equivalent to the input voltage of an electronic element, and enabling the output of each neuron to be equivalent to the output voltage of the electronic element;
wherein the input information of each electronic element comprises external current input and feedback connection information between the electronic element and other electronic elements.
6. The phased array antenna testing method of claim 5, further comprising:
replacing the original energy function by the energy entropy;
constructing a permutation matrix complying with a PA-TSP rule, and controlling the state set of the neuron output to meet the permutation matrix;
each row element of the permutation matrix has only one 1, and other elements are all 0;
each column of elements of the permutation matrix has only one 1, and other elements are all 0;
the number of elements 1 in the permutation matrix is equal to the number of phased array antenna nodes that have been visited.
7. The phased array antenna testing method of claim 6, further comprising the step of solving the PA-TSP problem according to the optimized Hopfield neural network, the step comprising:
initializing an initial value and a weight of the Hopfield neural network;
calculating the distance between each region block node;
initializing an input state of the Hopfield neural network;
calculating the increment of the input state according to the optimized Hopfield neural network;
updating the input state of the Hopfield neural network at the next time instant according to a first order Euler method;
updating the output state of the Hopfield neural network at the next moment according to the hyperbolic tangent function;
and calculating an energy function, and determining the output state set of the Hopfield neural network as a set of PA-TSP optimal route nodes until the energy function tends to be stable.
8. A phased array antenna test apparatus, comprising:
the determining module is used for determining a position point sequence and a test task sequence of the phased array antenna probe;
the control module is used for controlling the phased array antenna probe to move to the coordinate position of the target test point;
the test module is used for carrying out automatic test on the target position;
the sampling module is used for scanning the target test point of each phased array antenna probe according to a predefined neural network optimization algorithm to acquire acquired data;
and the checking module is used for carrying out data checking on all the acquired data after the scanning is finished to obtain the sampled data after the measurement is finished.
9. An electronic device comprising a processor and a memory;
the memory is used for storing programs;
the processor executing the program realizes the method according to any one of claims 1-7.
10. A computer-readable storage medium, characterized in that the storage medium stores a program, which is executed by a processor to implement the method according to any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110314440.4A CN112964941B (en) | 2021-03-24 | 2021-03-24 | Phased array antenna test method, device, equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110314440.4A CN112964941B (en) | 2021-03-24 | 2021-03-24 | Phased array antenna test method, device, equipment and medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112964941A true CN112964941A (en) | 2021-06-15 |
| CN112964941B CN112964941B (en) | 2021-12-21 |
Family
ID=76278427
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110314440.4A Active CN112964941B (en) | 2021-03-24 | 2021-03-24 | Phased array antenna test method, device, equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112964941B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115060985A (en) * | 2022-06-21 | 2022-09-16 | 北京电磁方圆科技有限公司 | Method and device for testing multi-channel antenna |
| CN115915164A (en) * | 2022-12-05 | 2023-04-04 | 广东省电信规划设计院有限公司 | Communication indoor distribution system design method and device based on 5G technology |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100085242A1 (en) * | 2008-10-07 | 2010-04-08 | Sungkyunkwan University Foundation For Corporate Collaboration | Method of sensor network localization through reconstruction of radiation pattern |
| CN107390039A (en) * | 2017-08-22 | 2017-11-24 | 湖南卫导信息科技有限公司 | A kind of method of quick test Antenna Array Pattern |
| CN109271695A (en) * | 2018-09-07 | 2019-01-25 | 中南大学 | Multiple target antenna design method neural network based |
| CN109298251A (en) * | 2018-10-31 | 2019-02-01 | 浙江奇赛其自动化科技有限公司 | A kind of radiation pattern measuring system based on unmanned aerial vehicle platform |
| CN110427669A (en) * | 2019-07-20 | 2019-11-08 | 中国船舶重工集团公司第七二四研究所 | A kind of neural network model calculation method of phase-array scanning radiation beam |
| CN112505434A (en) * | 2020-11-24 | 2021-03-16 | 中国电子科技集团公司第三十八研究所 | Method for testing passive array antenna beam scanning characteristics |
-
2021
- 2021-03-24 CN CN202110314440.4A patent/CN112964941B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100085242A1 (en) * | 2008-10-07 | 2010-04-08 | Sungkyunkwan University Foundation For Corporate Collaboration | Method of sensor network localization through reconstruction of radiation pattern |
| CN107390039A (en) * | 2017-08-22 | 2017-11-24 | 湖南卫导信息科技有限公司 | A kind of method of quick test Antenna Array Pattern |
| CN109271695A (en) * | 2018-09-07 | 2019-01-25 | 中南大学 | Multiple target antenna design method neural network based |
| CN109298251A (en) * | 2018-10-31 | 2019-02-01 | 浙江奇赛其自动化科技有限公司 | A kind of radiation pattern measuring system based on unmanned aerial vehicle platform |
| CN110427669A (en) * | 2019-07-20 | 2019-11-08 | 中国船舶重工集团公司第七二四研究所 | A kind of neural network model calculation method of phase-array scanning radiation beam |
| CN112505434A (en) * | 2020-11-24 | 2021-03-16 | 中国电子科技集团公司第三十八研究所 | Method for testing passive array antenna beam scanning characteristics |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115060985A (en) * | 2022-06-21 | 2022-09-16 | 北京电磁方圆科技有限公司 | Method and device for testing multi-channel antenna |
| CN115915164A (en) * | 2022-12-05 | 2023-04-04 | 广东省电信规划设计院有限公司 | Communication indoor distribution system design method and device based on 5G technology |
| CN115915164B (en) * | 2022-12-05 | 2024-04-30 | 广东省电信规划设计院有限公司 | 5G technology-based communication indoor distribution system design method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112964941B (en) | 2021-12-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112964941B (en) | Phased array antenna test method, device, equipment and medium | |
| CN111860982A (en) | Wind power plant short-term wind power prediction method based on VMD-FCM-GRU | |
| Ahmadi et al. | Learning fuzzy cognitive maps using imperialist competitive algorithm | |
| CN108764475A (en) | The Gyro Random error compensating method and system of genetic wavelet neural network | |
| Askari et al. | Political optimizer based feedforward neural network for classification and function approximation | |
| CN110796233A (en) | Self-adaptive compression method of deep residual convolution neural network based on transfer learning | |
| Huang et al. | A data-driven method for hybrid data assimilation with multilayer perceptron | |
| Chen et al. | The optimal design and application of LSTM neural network based on the hybrid coding PSO algorithm | |
| Skolik et al. | Robustness of quantum reinforcement learning under hardware errors | |
| CN113850438A (en) | Public building energy consumption prediction method, system, equipment and medium | |
| Ekinci et al. | Pattern search ameliorated arithmetic optimization algorithm for engineering optimization and infinite impulse response system identification | |
| CN117878903A (en) | VMD-TCN-GRU short-term load prediction method and system based on balance optimizer algorithm | |
| US11556770B2 (en) | Auto weight scaling for RPUs | |
| CN111461308A (en) | Memristive neural network and weight training method | |
| Chen et al. | Radar emitter signals identification with a optimal recurrent type 2 wavelet fuzzy neural network | |
| CN113722951B (en) | Scatterer three-dimensional finite element grid optimization method based on neural network | |
| CN114492199A (en) | Method and system for analyzing performance of voltage transformer, electronic equipment and medium | |
| CN114742091A (en) | Method, system and medium for identifying radar individual radiation based on convolution block attention | |
| Aksu et al. | Training the multifeedback-layer neural network using the Particle Swarm Optimization algorithm | |
| Sarıkaya et al. | Training Sigma-Pi neural networks with the grey wolf optimization algorithm | |
| CN117992844B (en) | Photoelectric radar signal sorting method based on improved wolf algorithm | |
| CN118013290B (en) | Ionosphere TEC forecasting method, ionosphere TEC forecasting system, computer equipment and ionosphere TEC forecasting medium | |
| Vecoven et al. | Cellular neuromodulation in artificial networks | |
| Gao et al. | Time series identifying and modeling with neural networks | |
| Nagahamulla et al. | Artificial neural network ensembles in time series forecasting: an application of rainfall forecasting in Sri Lanka |
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 |