Maritime antenna communication circuit test method and device, and storage medium

Abstract

The invention discloses a maritime antenna communication circuit testing method and device and a storage medium. The method comprises the steps that first background infrared image data are collected from a communication circuit board on the front face, and second background infrared image data are collected from the communication circuit board on the back face; constructing various maritime data for the ship; inputting various maritime data into a test case to test the maritime antenna; acquiring first operation infrared image data of the communication circuit board on the front side, and acquiring second operation infrared image data of the communication circuit board on the back side; subtracting the first background infrared image data from the first operation infrared image data to obtain first temperature image data; subtracting the second background infrared image data from the second operation infrared image data to obtain second temperature image data; and classifying the operation state of the communication circuit board according to the multi-frame circuit design drawing, the first temperature image data and the second temperature image data. According to the embodiment of the invention, the thermal stability test efficiency of the communication circuit of the maritime antenna is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of computer vision, and in particular, to a test method, device, and storage medium for a marine antenna communication circuit. Background Art

[0002] A marine antenna is one of the devices for a ship to communicate with the outside world during navigation at sea, and its stable operation is related to the safety of the ship.

[0003] Some marine antennas are equipped with radomes, which will pose a certain obstacle to the heat dissipation of the marine antennas. Therefore, the communication circuits of these marine antennas will be tested for thermal stability during the production design stage.

[0004] Currently, the test for the thermal stability of the communication circuit of a marine antenna is mainly to use test cases to control the marine antenna to repeatedly transmit and receive fixed signals, and use thermography technology combined with neural networks to detect the thermal stability of the communication circuit of the marine antenna.

[0005] However, the marine environment is complex, and the communication mode of the marine antenna, and this test mode is one-sided and prone to omissions, resulting in low test efficiency. Summary of the Invention

[0006] In view of this, the present invention provides a test method, device, and storage medium for a marine antenna communication circuit to improve the efficiency of testing the thermal stability of the communication circuit of a marine antenna.

[0007] The first aspect of the present invention provides a test method for a marine antenna communication circuit, which is applied to an automatic optical device, and the method includes:

[0008] When the communication circuit board of the marine antenna is fixed to the automatic optical device, collect first background infrared image data on the front of the communication circuit board and collect second background infrared image data on the back of the communication circuit board;

[0009] In a scenario of simulating a ship carrying the marine antenna sailing at sea, construct various marine data for the ship;

[0010] Input various marine data into a preset test case to test the marine antenna;

[0011] During the test, collect first running infrared image data on the front of the communication circuit board and collect second running infrared image data on the back of the communication circuit board;

[0012] Subtract the first background infrared image data from the first running infrared image data to obtain first temperature image data;

[0013] Subtract the second background infrared image data from the second running infrared image data to obtain second temperature image data;

[0014] Query multiple frames of circuit design diagrams drawn for the communication circuit board;

[0015] Classify the operating state of the communication circuit board based on multiple frames of the circuit design diagrams, the first temperature image data, and the second temperature image data.

[0016] The second aspect of the present invention provides a test device for a maritime antenna communication circuit, which is applied to an automatic optical device. The device includes:

[0017] A background infrared image data acquisition module, configured to collect first background infrared image data from the front of the communication circuit board and second background infrared image data from the back of the communication circuit board when the communication circuit board of the maritime antenna is fixed to the automatic optical device;

[0018] A maritime data construction module, configured to construct various maritime data for the ship in a scenario where the ship carrying the maritime antenna sails at sea;

[0019] A test case invocation module, configured to input various maritime data into a preset test case to test the maritime antenna;

[0020] A running infrared image data acquisition module, configured to collect first running infrared image data from the front of the communication circuit board and second running infrared image data from the back of the communication circuit board during the test;

[0021] A first temperature image data generation module, configured to subtract the first background infrared image data from the first running infrared image data to obtain first temperature image data;

[0022] A second temperature image data generation module, configured to subtract the second background infrared image data from the second running infrared image data to obtain second temperature image data;

[0023] A circuit design diagram query module, configured to query multiple frames of circuit design diagrams drawn for the communication circuit board;

[0024] An operating state classification module, configured to classify the operating state of the communication circuit board based on multiple frames of the circuit design diagrams, the first temperature image data, and the second temperature image data.

[0025] The third aspect of the present invention provides an automatic optical device, which includes:

[0026] At least one processor; and

[0027] A memory communicatively connected to the at least one processor; wherein,

[0028] The memory stores a computer program executable by the at least one processor, and when the computer program is executed by the at least one processor, the at least one processor is enabled to execute the test method for the maritime antenna communication circuit as described in the first aspect above.

[0029] A fourth aspect of the present invention provides a computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, the test method for the maritime antenna communication circuit as described in the first aspect above is implemented.

[0030] A fifth aspect of the present invention provides a computer program product including a computer program, and when the computer program is executed by a processor, the test method for the maritime antenna communication circuit as described in the first aspect above is implemented.

[0031] In this embodiment, when the communication circuit board of the maritime antenna is fixed to the automatic optical device, a first background infrared image data is collected from the front of the communication circuit board, and a second background infrared image data is collected from the back of the communication circuit board; in a scenario of simulating a ship carrying a maritime antenna sailing at sea, various maritime data are constructed for the ship; various maritime data are input into a preset test case to test the maritime antenna; during the test, a first running infrared image data is collected from the front of the communication circuit board, and a second running infrared image data is collected from the back of the communication circuit board; the first running infrared image data is subtracted from the first background infrared image data to obtain a first temperature image data; the second running infrared image data is subtracted from the second background infrared image data to obtain a second temperature image data; multiple frames of circuit design diagrams drawn for the communication circuit board are queried; the classification running states of the communication circuit board are determined based on the multiple frames of circuit design diagrams, the first temperature image data, and the second temperature image data. This embodiment conducts simulation tests based on the scenario of a ship carrying a maritime antenna sailing at sea, which can improve the flexibility of the test case, thereby improving the test coverage rate, conducting a more comprehensive test on the communication circuit of the maritime antenna, and moreover, taking the circuit design diagram as a priori knowledge and combining the infrared image data on the front and back can effectively increase the amount of information, thereby improving the accuracy of classifying the running states of the communication circuit board, and overall improving the efficiency of the thermal stability test on the communication circuit of the maritime antenna.

[0032] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present invention, nor is it used to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] To more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the accompanying drawings required for the description of the embodiments. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other accompanying drawings can also be obtained based on these drawings.

[0034] Figure 1 It is a flowchart of a test method for a maritime antenna communication circuit provided in Embodiment 1 of the present invention.

[0035] Figure 2 It is a schematic structural diagram of a circuit classification network provided in Embodiment 1 of the present invention.

[0036] Figure 3 It is a schematic structural diagram of a convolution module provided in Embodiment 1 of the present invention.

[0037] Figure 4 It is a schematic structural diagram of a head structure provided in Embodiment 1 of the present invention.

[0038] Figure 5 It is a schematic structural diagram of a test device for a maritime antenna communication circuit provided in Embodiment 2 of the present invention.

[0039] Figure 6 It is a schematic structural diagram of an automatic optical device provided in Embodiment 3 of the present invention. Detailed implementation manners

[0040] In order to enable those skilled in the art to better understand the solutions of the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0041] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above accompanying drawings are used to distinguish similar objects, and do not necessarily need to describe a specific order or sequence. It should be understood that such used data can be interchanged under appropriate circumstances so that the embodiments of the present invention described here can cover sequences other than those illustrated or described here. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units does not necessarily need to be limited to those clearly listed steps or units, but may include other steps or units not clearly listed or inherent to these processes, methods, products, or devices.

[0042] Example 1

[0043] Refer to Figure 1 , which shows a flowchart of a test method for a maritime antenna communication circuit provided in Example 1 of the present invention. This method can be executed by a test device for a maritime antenna communication circuit. The test device for the maritime antenna communication circuit can be implemented in the form of hardware and / or software, and the test device for the maritime antenna communication circuit can be applied to an Automated Optical Inspection (AOI) device. As Figure 1 shown, the method includes:

[0044] Step 101, when the communication circuit board of the maritime antenna is fixed to the automated optical device, collect first background infrared image data from the front of the communication circuit board and collect second background infrared image data from the back of the communication circuit board.

[0045] A first infrared camera and a second infrared camera can be configured in the AOI device. The first infrared camera is located above the AOI device, and its imaging range faces downward. The first infrared camera is located below the AOI device, and its imaging range faces upward.

[0046] The communication circuit of the maritime antenna is mainly distributed on the communication circuit board. When the communication circuit board of the maritime antenna is fixed to the AOI device, on the one hand, use the first infrared camera to collect infrared image data from the front of the communication circuit board and crop the area where the communication circuit board is located to obtain the first background infrared image data. On the other hand, use the second infrared camera to collect infrared image data from the back of the communication circuit board and crop the area where the communication circuit board is located to obtain the second background infrared image data.

[0047] Since the communication circuit (especially electronic components) is unevenly distributed on the communication circuit board, during the operation of the maritime antenna, there are certain differences in the temperature distribution on the front and back of the communication circuit board.

[0048] Step 102, in a scenario where a ship is simulated to carry a maritime antenna and sail at sea, construct various maritime data for the ship.

[0049] In the AOI device, simulation testing can be performed on the maritime antenna, that is, use prior knowledge to simulate the scenario where a ship carries a maritime antenna and sails at sea, continuously simulate the changing environment at sea, and in this scenario, construct various maritime data for the ship.

[0050] In an embodiment of the present invention, the maritime data includes attitude data, meteorological data, and communication data (mainly simulating spectrum information); then, step 102 can include the following steps:

[0051] Step 1021: Generate the initial meteorological data of the marine environment, the initial attitude data of the ship, and the initial communication data of the maritime antenna respectively.

[0052] During the initialization process, the meteorological data of the initial time step of the marine environment, the attitude data of the initial time step of the ship, and the communication data of the initial time step of the maritime antenna can be constructed respectively in random, regular, or other ways. Or the historical real meteorological data, attitude data, and communication data can be set as the initial meteorological data of the marine environment, the initial attitude data of the ship, and the initial communication data of the maritime antenna. This embodiment does not limit this.

[0053] In one way, the model of the maritime antenna can be queried, and the original geographical positions (i.e., longitude and latitude) recorded by all ships of this model during sea voyages can be queried.

[0054] Since the original geographical positions are too dense, the original geographical positions can be downsampled according to a preset sampling ratio (such as 10000, etc.) to obtain a relatively sparse target geographical position.

[0055] Use methods such as K-means (K-Means) and DBSCAN (Density-Based Spatial Clustering of Applications with Noise) to cluster the target geographical positions to obtain multiple geographical regions.

[0056] Select the meteorological data as the initial meteorological data of the marine environment according to the meteorological probability of various meteorological data appearing at the center points of the geographical regions. This is historical real meteorological data, and subsequent simulation degrees can be maintained starting from this.

[0057] Randomly select the initial attitude data of the ship within a preset attitude range, where the attitude range is fitted based on the empirical values of the ship's attitude during historical voyages. Subsequent simulation degrees can be maintained starting from this.

[0058] Randomly select the initial communication data of the maritime antenna within a preset signal range, where the signal range is fitted based on the empirical values of the signals of the maritime antenna during historical communications. Subsequent simulation degrees can be maintained starting from this.

[0059] Step 1022: Extract meteorological features from the meteorological data, extract attitude features from the attitude data of the ship, and extract signal features from the communication data respectively.

[0060] In this embodiment, meteorological features can be extracted from the meteorological data, attitude features can be extracted from the attitude data of the ship, and signal features can be extracted from the communication data based on the way of sequence statistics.

[0061] Among them, the meteorological features, attitude features, and signal features may include, but are not limited to, statistical values (minimum value, maximum value, median value, average value, quantile value), time features (the time at which a certain statistical value is located), waveform features (such as wave peaks, wave troughs, residuals, etc.), and so on.

[0062] Step 1023: Construct the meteorological data for the next time step of the marine environment based on the meteorological features.

[0063] In this embodiment, the meteorological data for the next time step of the marine environment can be constructed under the condition of the meteorological features of the marine environment at the current time step.

[0064] In a specific implementation, the first behavior tree and the first generative adversarial network can be loaded.

[0065] Among them, the first behavior tree has multiple first branches that simulate marine meteorological patterns, and each first branch has multiple first leaf nodes that represent meteorological conversion actions. The so-called meteorological conversion actions refer to the actions of converting the meteorological conditions of the marine environment. For example, converting from a wind force of level 10 to a wind force of level 5, converting from a wave height of level 7 to a wave height of level 4, and so on.

[0066] In addition, the first generative adversarial network has a first generator and a first discriminator. The first generator is constructed using the mode of the decoder Decoder to enable it to have the function of predicting a sequence in a directional manner.

[0067] Then, the meteorological features can be input into the first behavior tree to match the first leaf nodes, and the meteorological conversion actions of the marine environment at the next time step can be obtained.

[0068] Using the meteorological conversion actions as the direction, the meteorological features and the meteorological conversion actions are input into the first generator to construct the meteorological data for the next time step of the marine environment.

[0069] Step 1024: Construct the attitude data for the next time step of the ship based on the attitude features and the meteorological features.

[0070] In this embodiment, the navigation of the ship is affected by the meteorological conditions of the marine environment. The meteorological data for the next time step of the marine environment can be constructed under the conditions of the meteorological features of the marine environment and the attitude features of the ship at the current time step.

[0071] In a specific implementation, the second behavior tree and the second generative adversarial network can be loaded.

[0072] Among them, the second behavior tree has multiple second branches that simulate the ship's attitude patterns, and each second branch has multiple second leaf nodes that represent meteorological conversion actions. The so-called meteorological conversion actions refer to the actions of converting the navigation attitude of the ship.

[0073] In addition, the second generative adversarial network has a second generator, which is constructed using the mode of the decoder (Decoder), enabling it to have the function of predicting the sequence in the directional manner.

[0074] Input the attitude feature and the meteorological feature into the second row of the behavior tree to match the second leaf node, and obtain the attitude conversion action of the ship at the next time step.

[0075] Taking the attitude conversion action as the direction, input the attitude feature, the meteorological feature, and the attitude conversion action into the second generator to construct the attitude data of the ship at the next time step.

[0076] Furthermore, the first row of the behavior tree and the second row of the behavior tree both belong to the behavior tree, which is a tree-like structure. Each time it is updated, it starts from the root node of the tree and determines the state transition to be operated and the actual action according to the type and state of the child nodes. In the behavior tree, each node has an execution state, and after each execution is completed, it passes the execution result to the parent node. Cooperating with various internal special nodes, a pattern with certain complex behaviors (such as the maritime meteorological pattern, the attitude pattern of ship navigation, etc.) can be realized.

[0077] Based on the basic node (BaseNode), the behavior tree sets some special nodes to be used for assembling the logic, and the design is as follows:

[0078] Action: Define a specific behavior, such as the meteorological conversion action, the attitude conversion action, etc.

[0079] Composite: Implement organizing a group of behaviors and determine the branch direction. For example, Sequence, Selector, Parallel, etc.

[0080] Decorator: Define a constraint acting on the behavior. For example, execute the child node NUM (NUM is a positive integer) times, change the return state of the child node, etc.

[0081] Condition: Define a condition for returning success or failure. For example, the duration of the meteorological condition, the duration of the navigation, etc.

[0082] Step 1025: Construct the communication data of the maritime antenna at the next time step according to the attitude feature, the meteorological feature, and the signal feature.

[0083] In this embodiment, the signal of the maritime antenna is affected by the meteorological conditions of the maritime environment and the attitude of the ship's navigation. The communication data of the maritime antenna at the next time step can be constructed under the conditions of the meteorological feature of the maritime environment, the attitude feature of the ship, and the signal feature of the maritime antenna at the current time step.

[0084] In a specific implementation, a third generative adversarial network is loaded; the third generative adversarial network includes a third generator and a third discriminator. The third generator is constructed using the mode of a decoder (Decoder) to enable it to have the function of predicting a sequence in a directional manner.

[0085] Input the attitude feature, meteorological feature, and signal feature into the control program of the maritime antenna to generate a gain operation for the next time step.

[0086] Using the gain operation as the direction, input the attitude feature, meteorological feature, signal feature, and gain operation into the third generator to construct communication data for the next time step for the maritime antenna.

[0087] In this embodiment, a behavior tree and a generative adversarial network are used to iteratively construct attitude data, meteorological data, and communication data, which meet the requirements of testing in terms of simulation. Moreover, various marine environments and various navigation operations of ships can be continuously simulated, greatly improving the test coverage rate.

[0088] Step 103: Input various maritime data into a preset test case to test the maritime antenna.

[0089] In this embodiment, various maritime data can be input into a preset test case, and the test case runs based on various maritime data to test the maritime antenna.

[0090] Step 104: During the testing process, collect first running infrared image data from the front of the communication circuit board and second running infrared image data from the back of the communication circuit board.

[0091] During the testing process, the maritime antenna operates, and the communication circuit board generates heat. At this time, on the one hand, call the first infrared camera to continuously collect infrared image data from the front of the communication circuit board and crop the area where the communication circuit board is located to obtain the first running infrared image data. On the other hand, call the second infrared camera to continuously collect infrared image data from the back of the communication circuit board and crop the area where the communication circuit board is located to obtain the second running infrared image data.

[0092] Step 105: Subtract the first background infrared image data from the first running infrared image data to obtain the first temperature image data.

[0093] In this embodiment, the first running infrared image data and the first background infrared image data can be subjected to a differential operation, that is, subtract the first background infrared image data from the first running infrared image data to obtain the first temperature image data. At this time, the first temperature image data represents the temperature rise on the front side of the communication circuit board during operation.

[0094] Step 106: Subtract the second background infrared image data from the second running infrared image data to obtain the second temperature image data.

[0095] In this embodiment, the second running infrared image data and the second background infrared image data can be subjected to a differential operation, that is, subtract the second background infrared image data from the second running infrared image data to obtain the second temperature image data. At this time, the second temperature image data characterizes the temperature rise on the back surface of the communication circuit board during operation.

[0096] Step 107: Query multiple frames of circuit design diagrams drawn for the communication circuit board.

[0097] The communication circuit board of the maritime antenna is a multi-layer circuit board structure. For each layer of the circuit board, a circuit design diagram as realistic as possible can be simulated according to the distribution of the real circuit (including electronic components), rather than constructing a schematic diagram of the circuit distribution.

[0098] In actual applications, the circuit design diagram is binary image data, and the pixel value of the circuit design diagram is 1 or 0. 1 represents the communication circuit in the communication circuit board, and 0 represents the structure other than the communication circuit in the communication circuit board.

[0099] Generally, the heat generation of the communication circuit board mainly concentrates on the circuit (including electronic components). Therefore, the circuit design diagram can be used as prior knowledge for thermal stability testing to assist in detecting abnormal operating states such as short circuits, overloads, unreasonable layouts, and improper wiring.

[0100] Step 108: Classify the operating states of the communication circuit board based on multiple frames of circuit design diagrams, the first temperature image data, and the second temperature image data.

[0101] In actual applications, the operating states of the communication circuit board can be classified based on multiple frames of circuit design diagrams, the first temperature image data, and the second temperature image data by means of deep learning, machine learning, etc., to obtain the operating states.

[0102] Generally, the operating states of the communication circuit board include normal operating states and multiple abnormal operating states.

[0103] In an embodiment of the present invention, Step 108 may include the following steps:

[0104] Step 1081: Load the circuit classification network.

[0105] In this embodiment, the circuit classification network can be constructed and trained based on deep learning in an offline environment. As Figure 2 shown, the circuit classification network has a backbone network Backbone and multiple head networks Head.

[0106] Among them, the backbone network Backbone is responsible for extracting features from multiple frames of circuit design diagrams, the first temperature image data, and the second temperature image data, and each head network Head is responsible for the classification task of the operating state of a communication circuit board.

[0107] During training, using multiple frames of circuit design diagrams, the first temperature image data, and the second temperature image data collected from the communication circuit boards of maritime antennas in history as samples, and the labeled operating states of the communication circuit boards of maritime antennas as labels Label, cross-entropy is selected as the loss function, and the circuit classification network is trained in a supervised manner.

[0108] Furthermore, the training is divided into two stages. In the first stage, the backbone network Backbone is trained using the macro classification method. At this time, the backbone network Backbone and the head structure Head responsible for the normal state are regarded as a complete binary classification network for training. During this period, the parameters of the backbone network Backbone and the head network Head responsible for the normal state are updated. In the second stage, each head network Head is trained using the micro classification method. At this time, the backbone network Backbone and each head network Head responsible for the abnormal state are regarded as a complete binary classification network for training. During this period, the parameters of the backbone network Backbone are maintained unchanged, and the parameters of each head network Head responsible for the abnormal state are updated.

[0109] Step 1082: Stack multiple frames of circuit design diagrams to obtain a circuit distribution diagram.

[0110] In practical applications, pixels can be used to stack multiple frames of circuit design diagrams to obtain a circuit distribution diagram. During this process, the pixel values of the same position in multiple frames of circuit design diagrams are accumulated as the pixel values of the circuit distribution diagram.

[0111] If the circuit design diagram is binary image data and the number of frames of the circuit design diagram is n, then each pixel point of the circuit distribution diagram has a pixel value of 2n dimensions. At this time, the circuit distribution diagram can be regarded as grayscale image data with a gray level of 2n.

[0112] Step 1083: Input the circuit distribution diagram, the first temperature image data, and the second temperature image data into the backbone network to jointly extract the target temperature image features.

[0113] In this embodiment, as Figure 2 shown, input the circuit distribution diagram, the first temperature image data, and the second temperature image data into the backbone network Backbone for interaction and fusion, so as to extract the target temperature image features.

[0114] In one design, as Figure 2As shown, the backbone network Backbone includes the first convolutional module ConvModule_1, the second convolutional module ConvModule_2, the third convolutional module ConvModule_3, the fourth convolutional module ConvModule_4, the first attention layer Attention_1, and the second attention layer Attention_2.

[0115] Among them, the first convolutional module ConvModule_1, the second convolutional module ConvModule_2, the third convolutional module ConvModule_3, and the fourth convolutional module ConvModule_4 are all encapsulated structures related to convolutional layers, used to extract features of image data.

[0116] Exemplarily, as Figure 3 shown, the first convolutional module ConvModule_1, the second convolutional module ConvModule_2, the third convolutional module ConvModule_3, and the fourth convolutional module ConvModule_4 all sequentially include a convolutional layer (Convolutional Layer, Conv), a batch normalization layer (Batch Normalization, BN), and a rectified linear unit (Rectified Linear Unit, ReLU).

[0117] Among them, the convolutional layer can provide a convolutional operation, the batch normalization layer can provide a batch normalization operation, and the rectified linear unit can provide an activation operation.

[0118] In this design, the circuit distribution map is input into the first convolutional module ConvModule_1 to extract circuit image features.

[0119] The first temperature image data is input into the second convolutional module ConvModule_2 to extract the first candidate temperature image features.

[0120] The second temperature image data is input into the third convolutional module ConvModule_3 to extract the second candidate temperature image features.

[0121] The circuit image features and the first candidate temperature image features are input into the first attention layer Attention_1 to be fused into the third candidate temperature image features.

[0122] The circuit image features and the second candidate temperature image features are input into the second attention layer Attention_2 to be fused into the fourth candidate temperature image features.

[0123] Among them, the attention mechanisms provided by the first attention layer Attention_1 and the second attention layer Attention_2 can help improve the understanding ability of the backbone network Backbone for the communication circuit, capture the internal regularity of the temperature distribution for the communication circuit, and fuse the global features (reflecting the macroscopic structure of the temperature distribution) and the local detail features (reflecting the subtle changes of the communication circuit), thereby improving the generalization performance and the classification accuracy.

[0124] Concatenate the third candidate temperature image feature and the fourth candidate temperature image feature to obtain the concatenated temperature image feature.

[0125] Input the fifth candidate temperature image feature into the fourth convolution module ConvModule_4 to extract the target temperature image feature.

[0126] Step 1084: Input the target temperature image feature into multiple head networks respectively to calculate the state probabilities of various operating states for the communication circuit board.

[0127] In this embodiment, as Figure 2 shown, input the target temperature image feature into multiple head networks Head respectively, and independently calculate the state probabilities of various operating states for the communication circuit board according to the target temperature image feature in each head network Head.

[0128] In one design, as Figure 4 shown, each head network Head includes a first convolutional layer Conv_1, a second convolutional layer Conv_2, and a fully connected layer FC.

[0129] Among them, the first convolutional layer Conv_1 and the second convolutional layer Conv_2 are both convolutional layers, which can provide convolutional operations, and the fully connected layer FC can provide fully connected operations.

[0130] In each head network, input the target temperature image feature into the first convolutional layer Conv_1, the second convolutional layer Conv_2, and the fully connected layer FC in sequence for processing to obtain the temperature classification image feature.

[0131] Use functions such as Sigmoid to activate the temperature classification image feature to obtain the state probability that the communication circuit board belongs to the specified operating state.

[0132] Step 1085: Determine the operating state of the communication circuit board according to multiple state probabilities.

[0133] In practical applications, compare the state probabilities of each operating state, and the operating state with the highest state probability can be selected as the operating state of the communication circuit board.

[0134] Write the operating state of the communication circuit board into the test report for the reference of the testers.

[0135] In this embodiment, when the communication circuit board of the maritime antenna is fixed to the automatic optical device, the first background infrared image data is collected from the front of the communication circuit board, and the second background infrared image data is collected from the back of the communication circuit board; in the scenario of simulating a ship carrying the maritime antenna sailing at sea, various maritime data are constructed for the ship; various maritime data are input into a preset test case to test the maritime antenna; during the test, the first running infrared image data is collected from the front of the communication circuit board, and the second running infrared image data is collected from the back of the communication circuit board; the first running infrared image data is subtracted from the first background infrared image data to obtain the first temperature image data; the second running infrared image data is subtracted from the second background infrared image data to obtain the second temperature image data; multiple frames of circuit design diagrams drawn for the communication circuit board are queried; the classified operating states of the communication circuit board are determined based on the multiple frames of circuit design diagrams, the first temperature image data, and the second temperature image data. This embodiment conducts simulation tests based on the scenario of a ship carrying a maritime antenna sailing at sea, which can improve the flexibility of the test case, thereby increasing the test coverage rate, comprehensively testing the communication circuit of the maritime antenna, and moreover, using the circuit design diagram as prior knowledge and combining the infrared image data on the front and back can effectively increase the amount of information, thereby improving the accuracy of classifying the operating states of the communication circuit board, and overall improving the efficiency of the thermal stability test of the communication circuit of the maritime antenna.

[0136] Embodiment 2

[0137] See Figure 5 , which shows a schematic structural diagram of a test device for a communication circuit of a maritime antenna provided in Embodiment 2 of the present invention. Applied to an automatic optical device, as Figure 5 shown, the device includes:

[0138] A background infrared image data acquisition module 501, configured to collect first background infrared image data from the front of the communication circuit board and second background infrared image data from the back of the communication circuit board when the communication circuit board of the maritime antenna is fixed to the automatic optical device;

[0139] A maritime data construction module 502, configured to construct various maritime data for the ship in the scenario of simulating a ship carrying the maritime antenna sailing at sea;

[0140] A test case calling module 503, configured to input various maritime data into a preset test case to test the maritime antenna;

[0141] Run the infrared image data acquisition module 504 to collect first running infrared image data of the communication circuit board from the front and second running infrared image data of the communication circuit board from the back during the test;

[0142] The first temperature image data generation module 505 is used to subtract the first background infrared image data from the first running infrared image data to obtain first temperature image data;

[0143] The second temperature image data generation module 506 is used to subtract the second background infrared image data from the second running infrared image data to obtain second temperature image data;

[0144] The circuit design diagram query module 507 is used to query multiple frames of circuit design diagrams drawn for the communication circuit board;

[0145] The running state classification module 508 is used to classify the running state of the communication circuit board based on multiple frames of the circuit design diagrams, the first temperature image data, and the second temperature image data.

[0146] In an embodiment of the present invention, the maritime data includes attitude data, meteorological data, and communication data; the maritime data construction module 502 includes:

[0147] The initial data generation module is used to respectively generate initial meteorological data of the marine environment, initial attitude data of the ship, and initial communication data of the maritime antenna;

[0148] The data feature extraction module is used to extract meteorological features from the meteorological data, attitude features from the attitude data of the ship, and signal features from the communication data;

[0149] The meteorological data construction module is used to construct meteorological data for the next time step of the marine environment based on the meteorological features;

[0150] The attitude data construction module is used to construct attitude data for the next time step of the ship based on the attitude features and the meteorological features;

[0151] The communication data construction module is used to construct communication data for the next time step of the maritime antenna based on the attitude features, the meteorological features, and the signal features.

[0152] In an embodiment of the present invention, the initial data generation module includes:

[0153] The model query module is used to query the model of the maritime antenna;

[0154] An original geographical location query module for querying the original geographical locations recorded by all the ships of the said model during sea voyages;

[0155] A target geographical location sampling module for downsampling the original geographical locations to obtain target geographical locations;

[0156] A geographical area clustering module for clustering the target geographical locations to obtain multiple geographical areas;

[0157] A meteorological data initialization module for selecting the meteorological data as the initial meteorological data of the sea environment according to the meteorological probabilities of various meteorological data appearing at the center points of the geographical areas;

[0158] An attitude data initialization module for randomly selecting the initial attitude data of the ship within a preset attitude range;

[0159] A communication data initialization module for randomly selecting the initial communication data of the maritime antenna within a preset signal range.

[0160] In an embodiment of the present invention, the meteorological data construction module is further used for:

[0161] Loading a first behavior tree and a first generative adversarial network; the first behavior tree has multiple first branches simulating maritime meteorological patterns, and each of the first branches has multiple first leaf nodes representing meteorological conversion actions; the first generative adversarial network has a first generator;

[0162] Inputting the meteorological features into the first behavior tree to match the first leaf nodes to obtain the meteorological conversion actions of the sea environment at the next time step;

[0163] Inputting the meteorological features and the meteorological conversion actions into the first generator to construct the meteorological data of the sea environment at the next time step;

[0164] The attitude data construction module is further used for:

[0165] Loading a second behavior tree and a second generative adversarial network; the second behavior tree has multiple second branches simulating the ship attitude patterns, and each of the second branches has multiple second leaf nodes representing attitude conversion actions; the second generative adversarial network has a second generator;

[0166] Inputting the attitude features and the meteorological features into the second behavior tree to match the second leaf nodes to obtain the attitude conversion actions of the ship at the next time step;

[0167] Input the attitude feature, the meteorological feature, and the attitude conversion action into the second generator to construct the attitude data of the ship for the next time step;

[0168] The communication data construction module is further configured to:

[0169] Load a third generative adversarial network; the third generative adversarial network has a third generator;

[0170] Input the attitude feature, the meteorological feature, and the signal feature into the control program of the maritime antenna to generate the gain operation for the next time step;

[0171] Input the attitude feature, the meteorological feature, the signal feature, and the gain operation into the third generator to construct the communication data of the maritime antenna for the next time step.

[0172] In an embodiment of the present invention, the operating state classification module 508 includes:

[0173] A circuit classification network loading module, configured to load a circuit classification network; the circuit classification network has a backbone network and multiple head networks;

[0174] A circuit design diagram superposition module, configured to superpose multiple frames of the circuit design diagrams to obtain a circuit distribution diagram;

[0175] A target temperature image feature extraction module, configured to input the circuit distribution diagram, the first temperature image data, and the second temperature image data into the backbone network to jointly extract target temperature image features;

[0176] A state probability calculation module, configured to input the target temperature image features into multiple head networks respectively to calculate the state probabilities of various operating states for the communication circuit board;

[0177] An operating state determination module, configured to determine the operating state of the communication circuit board according to multiple state probabilities.

[0178] In an embodiment of the present invention, the backbone network includes a first convolutional module, a second convolutional module, a third convolutional module, a fourth convolutional module, a first attention layer, and a second attention layer;

[0179] The target temperature image feature extraction module is further configured to:

[0180] Input the circuit distribution diagram into the first convolutional module to extract circuit image features;

[0181] Input the first temperature image data into the second convolutional module to extract first candidate temperature image features;

[0182] Input the second temperature image data into the third convolutional module to extract second candidate temperature image features;

[0183] Input the circuit image features and the first candidate temperature image features into the first attention layer to fuse them into third candidate temperature image features;

[0184] Input the circuit image features and the second candidate temperature image features into the second attention layer to fuse them into fourth candidate temperature image features;

[0185] Concatenate the third candidate temperature image features and the fourth candidate temperature image features into fifth candidate temperature image features;

[0186] Input the fifth candidate temperature image features into the fourth convolutional module to extract target temperature image features.

[0187] In one embodiment of the present invention, each of the head networks includes a first convolutional layer, a second convolutional layer, and a fully connected layer;

[0188] The state probability calculation module is further configured to:

[0189] In each of the head networks, input the target temperature image features into the first convolutional layer, the second convolutional layer, and the fully connected layer in sequence for processing to obtain temperature classification image features;

[0190] Activate the temperature classification image features to obtain the state probability that the communication circuit board belongs to a specified operating state.

[0191] In one embodiment of the present invention, each of the first convolutional module, the second convolutional module, the third convolutional module, and the fourth convolutional module sequentially includes a convolutional layer, a batch normalization layer, and a rectified linear unit;

[0192] The pixel value of the circuit design diagram is 1 or 0, where 1 represents the communication circuit in the communication circuit board, and 0 represents the structure other than the communication circuit in the communication circuit board.

[0193] The test device for a maritime antenna communication circuit provided by an embodiment of the present invention can execute the test method for a maritime antenna communication circuit provided by any embodiment of the present invention, and has corresponding functional modules and beneficial effects for executing the test method for a maritime antenna communication circuit.

[0194] Embodiment III

[0195] See Figure 6, showing a schematic structural diagram of an automatic optical device provided by an embodiment of the present invention. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or claimed herein.

[0196] As Figure 6 shown, the automatic optical 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, etc. The memory stores a computer program executable by the at least one processor. The processor 11 can perform various appropriate 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 automatic optical 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 the bus 14.

[0197] Multiple components in the automatic optical device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disc, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the automatic optical device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0198] The processor 11 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the test method for a maritime antenna communication circuit.

[0199] In some embodiments, the test method of the maritime antenna communication circuit can 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 can be loaded and / or installed onto the automatic optical device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the test method of the maritime antenna communication circuit described above can be executed. Alternatively, in other embodiments, the processor 11 can be configured to execute the test method of the maritime antenna communication circuit by any other suitable means (e.g., by means of firmware).

[0200] The various embodiments of the systems and techniques described above in this document can be implemented in digital electronic circuitry, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special-purpose or general-purpose programmable processor that receives data and instructions from a storage system, at least one input device, and at least one output device, and transmits the data and instructions to the storage system, the at least one input device, and the at least one output device.

[0201] The 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 can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when the computer programs are executed by the processor, the functions / operations specified in the flowchart and / or block diagram are implemented. The computer programs can be executed entirely on the machine, partially on the machine, as a stand-alone software package partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0202] In the context of the present invention, a computer-readable storage medium can 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. The computer-readable storage medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, the computer-readable storage medium can be a machine-readable signal medium. More specific examples of the machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer disk, 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 portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0203] To provide for interaction with a user, the systems and techniques described herein can be implemented on an automated optical device that has: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the automated optical device. Other kinds of devices can also be used to provide for interaction with the 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 can be received in any form (including acoustic input, speech input, or tactile input).

[0204] The systems and techniques described herein can be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer having a graphical user interface or a web browser through which the user can interact with an implementation of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend 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: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0205] A computing system may include a client and a server. The client and the server are generally far from each other and usually interact via a communication network. The client-server relationship is created by computer programs running on respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or a cloud host, which is a host product in the cloud computing service system, solving the defects of difficult management and weak business scalability existing in traditional physical hosts and VPS services.

[0206] Embodiment 4

[0207] The embodiment of the present invention also provides a computer program product, which includes a computer program. When the computer program is executed by a processor, it implements the test method for the maritime antenna communication circuit provided in any embodiment of the present invention.

[0208] In the process of implementing the computer program product, the computer program code for performing the operations of the present invention can be written in one or more programming languages or combinations thereof. The programming languages include object-oriented programming languages such as Java, Smalltalk, C++, and also include conventional procedural programming languages such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, executed as an independent software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network - including a local area network (LAN) or a wide area network (WAN) - or can be connected to an external computer (for example, by using an Internet service provider to connect through the Internet).

[0209] It should be understood that the various forms of the processes shown above can be used, with steps reordered, added, or deleted. For example, the steps recited in the present invention can be executed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved, and no limitation is imposed herein.

[0210] The above specific embodiments do not constitute a limitation to the protection scope of the present invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention shall be included within the protection scope of the present invention.

Claims

1. A method for testing a maritime antenna communication circuit, characterized in that: Applied to an automated optical device, the method comprises: When a communication circuit board of the maritime antenna is fixed to the automatic optical device, first background infrared image data is collected from the front of the communication circuit board, and second background infrared image data is collected from the back of the communication circuit board; In a scenario simulating a ship carrying the maritime antenna sailing on the sea, constructing a variety of maritime data for the ship; Inputting various maritime data into preset test cases to test the maritime antenna; During the test, first operation infrared image data is collected from the front side of the communication circuit board, and second operation infrared image data is collected from the back side of the communication circuit board; Subtracting the first background infrared image data from the first operation infrared image data to obtain first temperature image data; Subtracting the second background infrared image data from the second operating infrared image data to obtain second temperature image data; Querying a plurality of frames of circuit design drawings drawn for the communication circuit board; The operation status of the communication circuit board is classified according to the multiple frames of the circuit design diagram, the first temperature image data and the second temperature image data.

2. The method according to claim 1, characterized in that: The maritime data includes attitude data, meteorological data and communication data; the multiple maritime data constructed for the ship include: Generating initial meteorological data of the marine environment, initial attitude data of the ship and initial communication data of the maritime antenna respectively; respectively extracting meteorological features from the meteorological data, extracting attitude features from the attitude data of the ship, and extracting signal features from the communication data; constructing meteorological data of the next time step for the marine environment according to the meteorological characteristics; constructing attitude data of the ship at the next time step according to the attitude characteristics and the meteorological characteristics; The communication data of the next time step is constructed for the maritime antenna according to the attitude characteristics, the meteorological characteristics and the signal characteristics.

3. The method according to claim 2, characterized in that The generating of the initial meteorological data of the marine environment, the initial attitude data of the ship and the initial communication data of the maritime antenna respectively comprises: Query the model of the maritime antenna; Query the original geographical locations recorded by all the ships of the model when sailing at sea; Downsampling the original geographical location to obtain a target geographical location; Clustering the target geographical locations to obtain multiple geographical areas; Selecting the meteorological data as initial meteorological data for the marine environment according to the meteorological probability of various meteorological data appearing at the center point of the geographical area; Randomly selecting initial posture data of the ship within a preset posture range; The initial communication data of the maritime antenna is randomly selected within a preset signal range.

4. The method according to claim 3, characterized in that The step of constructing meteorological data of the next time step for the marine environment according to the meteorological characteristics comprises: Loading a first behavior tree and a first generative adversarial network; the first behavior tree has a plurality of first branches simulating marine weather patterns, each of the first branches has a plurality of first leaf nodes representing weather conversion actions; the first generative adversarial network has a first generator; Input the meteorological feature into the first behavior tree to match the first leaf node, and obtain the meteorological conversion action of the marine environment at the next time step; Inputting the meteorological characteristics and the meteorological conversion action into the first generator to construct meteorological data for the marine environment at the next time step; The step of constructing the posture data of the ship at the next time step according to the posture feature and the meteorological feature comprises: A second behavior tree and a second generative adversarial network are loaded; the second behavior tree has a plurality of second branches simulating the ship posture mode, each of the second branches has a plurality of second leaf nodes representing posture conversion actions; the second generative adversarial network has a second generator; Inputting the posture feature and the meteorological feature into the second behavior tree to match the second leaf node, and obtaining the posture conversion action of the ship at the next time step; Inputting the attitude feature, the meteorological feature and the attitude conversion action into the second generator to construct attitude data of the ship at the next time step; The step of constructing the communication data of the next time step for the maritime antenna according to the attitude feature, the meteorological feature and the signal feature comprises: Loading a third generative adversarial network; the third generative adversarial network having a third generator; Inputting the attitude feature, the meteorological feature and the signal feature into the control program of the maritime antenna to generate a gain operation for the next time step; The attitude feature, the meteorological feature, the signal feature and the gain operation are input into the third generator to construct the communication data of the next time step for the maritime antenna.

5. The method according to any one of claims 1 to 4, characterized in that The step of classifying the operation status of the communication circuit board according to the plurality of frames of the circuit design diagram, the first temperature image data and the second temperature image data comprises: Loading a circuit classification network; the circuit classification network has a backbone network and multiple head networks; Superimposing multiple frames of the circuit design diagram to obtain a circuit distribution diagram; Inputting the circuit distribution diagram, the first temperature image data and the second temperature image data into the backbone network to jointly extract target temperature image features; Inputting the target temperature image features into the plurality of head networks respectively to calculate the state probabilities of various operating states of the communication circuit board; The operating state of the communication circuit board is determined according to a plurality of the state probabilities.

6. The method according to claim 5, characterized in that The backbone network includes a first convolution module, a second convolution module, a third convolution module, a fourth convolution module, a first attention layer and a second attention layer; The step of inputting the circuit distribution diagram, the first temperature image data and the second temperature image data into the backbone network to jointly extract target temperature image features comprises: Inputting the circuit distribution map into the first convolution module to extract circuit image features; Inputting the first temperature image data into the second convolution module to extract first candidate temperature image features; Inputting the second temperature image data into the third convolution module to extract second candidate temperature image features; Inputting the circuit image feature and the first candidate temperature image feature into the first attention layer and fusing them into a third candidate temperature image feature; Inputting the circuit image feature and the second candidate temperature image feature into the second attention layer and fusing them into a fourth candidate temperature image feature; splicing the third candidate temperature image feature and the fourth candidate temperature image feature into a fifth candidate temperature image feature; The fifth candidate temperature image feature is input into the fourth convolution module to extract the target temperature image feature.

7. The method according to claim 6, characterized in that Each of the head networks includes a first convolutional layer, a second convolutional layer and a fully connected layer; The step of inputting the target temperature image features into the plurality of head networks to calculate the probability of various operating states of the communication circuit board includes: In each of the head networks, the target temperature image features are sequentially input into the first convolution layer, the second convolution layer and the fully connected layer for processing to obtain temperature classification image features; The temperature classification image feature is activated to obtain the state probability that the communication circuit board belongs to the specified operating state.

8. The method according to claim 6, characterized in that The first convolution module, the second convolution module, the third convolution module and the fourth convolution module each include a convolution layer, a batch normalization layer and a linear rectification unit in sequence; The pixel value of the circuit design diagram is 1 or 0, 1 represents the communication circuit in the communication circuit board, and 0 represents the structure other than the communication circuit in the communication circuit board.

9. An automatic optical device, characterized in that: The automatic optical device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, 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 so that the at least one processor can execute the test method for the maritime antenna communication circuit according to any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method for testing a maritime antenna communication circuit according to any one of claims 1 to 8 is implemented.

Images