Constant temperature control method and device of navigation antenna, navigation antenna and storage medium

Abstract

The invention discloses a constant temperature control method and device of a navigation antenna, the navigation antenna and a storage medium. Historical operation data of each execution unit of the navigation antenna and historical environment temperature outside an antenna housing are input into an antenna temperature prediction model; when the confidence coefficient is greater than a confidence coefficient threshold value, determining a temperature correction coefficient based on the confidence coefficient of the first temperature predicted in a plurality of temperature control periods, so as to correct the first temperature to obtain a second temperature; and in the next temperature control period, the temperature regulator is controlled to work according to the second temperature and the preset target temperature so as to regulate the temperature in the antenna housing to the target temperature, so that the temperature of the marine antenna in the next temperature control period is predicted through the historical data, and the predicted temperature is corrected. The temperature of the next temperature control period can be determined in advance and adjusted in time, the interior of the antenna housing is in a constant-temperature state, and the performance of the marine antenna is guaranteed.

Description

Technical Field

[0001] The present invention relates to the technical field of navigation antenna control, and in particular to a constant temperature control method and device for a navigation antenna, a navigation antenna and a storage medium. Background Art

[0002] Since ships need to go out to sea and stay away from the shore, they cannot communicate with mobile base stations. Therefore, ships need to communicate via satellites, that is, ships need to be equipped with navigation antennas to communicate with satellites.

[0003] like Figure 1 The figure shows a schematic diagram of the structure of a marine antenna, in which a reflective surface 1, a feed source 2, an orthogonal mode coupler 3, a frequency converter 4, an antenna mainboard 5, a posture motor 6 and a posture determination device 7 are integrated in a radome 8. The marine antenna is mounted on a ship and is located in a complex working environment at sea. The temperature of the marine antenna has a great influence on the electrical and mechanical properties. For example, in terms of electrical properties, a high temperature environment will cause frequency deviation and decreased directivity, affecting the communication quality. In terms of mechanical properties, high or low temperatures will cause deformation of the first reflective surface 1, and low temperatures will also cause the plastic and metal in the antenna to become brittle.

[0004] In the prior art, a temperature sensor is usually arranged in the antenna cover to detect the temperature. When it is detected that the temperature exceeds the range, the temperature is adjusted so that the navigation antenna is in a constant temperature environment in the antenna cover. However, the temperature adjustment by detecting the temperature by the temperature sensor is a post-adjustment behavior, and the constant temperature control cannot be performed in advance, resulting in the navigation antenna in the antenna cover being in an environment with large temperature fluctuations, affecting the performance of the navigation antenna. Summary of the invention

[0005] The present invention provides a constant temperature control method and device for a navigation antenna, a navigation antenna and a storage medium, so as to predict the temperature of the navigation antenna in advance and perform constant temperature control in time, thereby reducing temperature fluctuations in a radome.

[0006] In a first aspect, the present invention provides a constant temperature control method for a navigation antenna, wherein a plurality of execution units of the navigation antenna are arranged in a radome and provided with a temperature regulator, comprising:

[0007] Acquire historical operation data of multiple execution units of the navigation antenna and the historical ambient temperature outside the antenna cover, wherein the historical operation data includes operation data of each execution unit in a current temperature control cycle and multiple historical temperature control cycles before the current temperature control cycle;

[0008] Inputting the historical ambient temperature and the historical operation data into a pre-trained antenna temperature prediction model to obtain a first temperature in the antenna cover and a confidence level of the first temperature when the temperature regulator is not started in the next temperature control cycle;

[0009] Determining whether the confidence level is greater than a preset confidence level threshold;

[0010] If yes, determining a temperature correction coefficient based on the confidence of the first temperature predicted by a plurality of temperature control cycles;

[0011] Correcting the first temperature based on the temperature correction coefficient to obtain a second temperature;

[0012] In the next temperature control cycle, the temperature regulator is controlled to operate according to the second temperature and a preset target temperature, so as to adjust the temperature in the antenna cover to the target temperature.

[0013] Optionally, the execution unit of the navigation antenna includes a reflector, a feed source, an orthogonal mode coupler, a frequency converter, an antenna mainboard, a posture motor, and a posture determination device, and obtaining historical operation data of multiple execution units of the navigation antenna and a historical ambient temperature outside the radome includes:

[0014] Obtaining a pitch angle curve and an angular velocity curve of the reflecting surface;

[0015] Obtaining a voltage curve, a current curve, and a power curve of the feed source;

[0016] Acquiring a temperature curve of the orthogonal mode coupler;

[0017] Obtaining a power curve, an input frequency curve, and an output frequency curve of the frequency converter;

[0018] Obtaining a power curve of the antenna mainboard;

[0019] Obtaining a power curve and a speed curve of the posture motor;

[0020] Obtaining a power curve of the posture determination device;

[0021] A historical ambient temperature curve outside the radome is obtained.

[0022] Optionally, the antenna temperature prediction model includes a feature extraction network, a feature fusion network, an antenna operation state matching network, and a temperature prediction network connected in sequence, the historical operation data is input into a pre-trained antenna temperature prediction model, and the first temperature in the antenna cover and the confidence of the first temperature are predicted in the antenna temperature prediction model when the temperature regulator is not started in the next temperature control cycle, including:

[0023] Inputting historical operating data of the reflector, feed, orthogonal mode coupler, frequency converter, antenna mainboard, posture motor and posture determination device and historical ambient temperature curve outside the radome into the feature extraction network;

[0024] Extract features from the historical operation data and the historical ambient temperature curve in the feature extraction network to obtain a first operation feature graph and a first ambient temperature feature graph of the reflector, feed source, orthogonal mode coupler, frequency converter, antenna mainboard, posture motor, and posture determination device;

[0025] fusing the first operation feature graph and the first ambient temperature feature graph in the feature fusion network to obtain a first fused feature graph;

[0026] In the antenna operation state matching network, the first fused feature map is matched with a feature map sample in a preset state feature library to obtain a feature pair and a matching degree of the feature pair, wherein the feature pair includes the first fused feature map and a first feature map sample, and the first feature map sample is a feature map of a determined antenna operation state;

[0027] determining the antenna operating state associated with the first feature graph sample in the feature pair as the target operating state of the navigation antenna in the next temperature control cycle;

[0028] Predicting, in the temperature prediction network, a first temperature in the radome and a probability of the first temperature when the temperature regulator is not started in the next temperature control period based on the target operating state;

[0029] A weighted sum of the probability of the first temperature and the probability of the target operating state is calculated as the confidence of the first temperature.

[0030] Optionally, determining a temperature correction coefficient based on a confidence level of the first temperature predicted by a plurality of temperature control cycles includes:

[0031] Acquire multiple third temperatures in the antenna cover detected in a current temperature control cycle and multiple historical temperature control cycles;

[0032] Calculating the temperature adjustment deviation rate of the temperature regulator in multiple temperature control cycles based on the multiple third temperatures and the preset target temperature;

[0033] The confidence of the first temperature predicted by multiple temperature control cycles and multiple temperature adjustment deviation rates are used to calculate a weighted average value as a temperature correction coefficient.

[0034] Optionally, correcting the first temperature based on the temperature correction coefficient to obtain a second temperature includes:

[0035] calculating a product of the first temperature and the temperature correction coefficient as a temperature compensation value;

[0036] The second temperature is obtained by calculating the sum of the temperature compensation value and the first temperature.

[0037] Optionally, controlling the temperature regulator to operate according to the second temperature and a preset target temperature in the next temperature control cycle to adjust the temperature in the antenna cover to the target temperature includes:

[0038] Calculating the difference between the second temperature and the target temperature, and taking the absolute value of the difference to obtain an absolute value of the temperature difference;

[0039] Determine whether the difference is greater than a value of 0;

[0040] If yes, the target cooling capacity is calculated by using the absolute value of the temperature difference and the preset volume of the antenna cover, and the temperature regulator is controlled to cool according to the target cooling capacity;

[0041] If not, the target heating amount is calculated using the absolute value of the temperature difference and the preset volume of the antenna cover, and the temperature regulator is controlled to heat according to the target heating amount.

[0042] Optionally, the antenna temperature prediction model is trained by the following steps:

[0043] Acquire a training data set, wherein each data sample in the training data set includes operation curve samples of a reflector, a feed source, an orthogonal mode coupler, a frequency converter, an antenna mainboard, a posture motor, and a posture determination device, and a temperature curve sample outside the antenna cover, and each data sample is annotated with a real operation state and a real temperature;

[0044] Constructing a state feature library, wherein the state feature library includes feature graph samples and antenna operation states associated with the feature graph samples;

[0045] Constructing an antenna temperature prediction model including a feature extraction network, a feature fusion network, an antenna operation state matching network and a temperature prediction network connected in sequence;

[0046] Extract data samples and input them into the antenna temperature prediction model, extract features from the data samples in the feature extraction network, and obtain a second operation feature graph and a second ambient temperature feature graph of the reflector, feed source, orthogonal mode coupler, frequency converter, antenna mainboard, posture motor, and posture determination device;

[0047] fusing the second operation feature graph and the second ambient temperature feature graph in the feature fusion network to obtain a second fused feature graph;

[0048] In the antenna operation state matching network, the second fused feature map is matched with the feature map samples in the state feature library to obtain a predicted feature pair and a matching degree of the predicted feature pair, the predicted feature pair includes the second fused feature map and the target feature map sample, and the target feature map sample is a feature map of the determined antenna operation state;

[0049] Determining the antenna operating state associated with the target feature map sample in the feature pair as the predicted operating state of the navigation antenna in the next temperature control cycle;

[0050] Predicting, in the temperature prediction network, a predicted temperature in the radome and a probability of the predicted temperature when the temperature regulator is not started in the next temperature control period based on the predicted operating state;

[0051] Calculating a total loss value based on the predicted temperature, the probability, the actual temperature, the predicted operating state, the actual operating state, and a matching degree of the predicted feature pair;

[0052] Determine whether the training stop condition is met;

[0053] If so, determining that the antenna temperature prediction model has completed training;

[0054] If not, the total loss value is used to adjust the network parameters of the feature fusion network, the antenna operation status matching network and the temperature prediction network, and the process returns to the step of extracting data samples and inputting them into the antenna temperature prediction model.

[0055] In a second aspect, the present invention provides a constant temperature control device for a navigation antenna, wherein a plurality of execution units of the navigation antenna are arranged in a radome and provided with a temperature regulator, comprising:

[0056] A historical operation data and ambient temperature acquisition module, used to acquire historical operation data of multiple execution units of the navigation antenna and the historical ambient temperature outside the antenna cover, wherein the historical operation data includes operation data of each execution unit in a current temperature control cycle and multiple historical temperature control cycles before the current temperature control cycle;

[0057] a temperature prediction module, used to input the historical ambient temperature and the historical operation data into a pre-trained antenna temperature prediction model to obtain a first temperature in the antenna cover and a confidence level of the first temperature when the temperature regulator is not started in the next temperature control cycle;

[0058] A confidence determination module, used to determine whether the confidence is greater than a preset confidence threshold, and if so, execute a temperature correction coefficient determination module;

[0059] a temperature correction coefficient determination module, configured to determine a temperature correction coefficient based on a confidence level of the first temperature predicted by a plurality of temperature control cycles;

[0060] A temperature correction module, configured to correct the first temperature based on the temperature correction coefficient to obtain a second temperature;

[0061] The temperature regulating module is used to control the operation of the temperature regulator according to the second temperature and a preset target temperature in the next temperature control cycle, so as to regulate the temperature in the antenna cover to the target temperature.

[0062] In a third aspect, the present invention provides a navigation antenna, the navigation antenna comprising:

[0063] at least one processor; and

[0064] a memory communicatively connected to the at least one processor; wherein,

[0065] 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 constant temperature control method for the navigation antenna as described in any one of the first aspects of the present invention.

[0066] In a fourth aspect, the present invention provides a computer-readable storage medium storing computer instructions, wherein the computer instructions are used to enable a processor to implement the constant temperature control method for a navigation antenna as described in any one of the first aspects of the present invention when executed.

[0067] The embodiment of the present invention obtains historical operation data of each execution unit of the navigation antenna in the radome and the historical ambient temperature outside the radome, and inputs them into the antenna temperature prediction model to obtain the first temperature in the radome when the temperature regulator is not started in the next temperature control period and the confidence of the first temperature, determines the temperature correction coefficient when the confidence is greater than a preset confidence threshold, corrects the first temperature based on the temperature correction coefficient to obtain the second temperature, controls the temperature regulator to work according to the second temperature and the preset target temperature in the next temperature control period, so as to adjust the temperature in the radome to the target temperature, realizes the prediction of the temperature of the navigation antenna in the next temperature control period in advance through historical data, corrects the temperature and performs temperature regulation, can determine the temperature of the navigation antenna in the next temperature control period in advance and timely perform temperature regulation, the temperature in the radome has little fluctuation and is in a constant temperature state, that is, each execution unit of the navigation antenna is in a constant temperature environment, and the performance of the navigation antenna is guaranteed.

[0068] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended 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

[0069] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0070] Figure 1 It is a schematic diagram of the structure of a marine antenna;

[0071] Figure 2 This is a flow chart of a constant temperature control method for a navigation antenna provided in Embodiment 1 of the present invention;

[0072] Figure 3 is a flow chart of a constant temperature control method for a navigation antenna provided in Embodiment 2 of the present invention;

[0073] Figure 4 It is a schematic diagram of the network structure of the antenna temperature prediction model;

[0074] Figure 5 It is a structural schematic diagram of a constant temperature control device for a navigation antenna provided in Embodiment 3 of the present invention;

[0075] Figure 6 It is a structural schematic diagram of a navigation antenna provided in Embodiment 4 of the present invention. DETAILED DESCRIPTION

[0076] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0077] Embodiment 1

[0078] Figure 2 This is a flow chart of a constant temperature control method for a navigation antenna provided in the first embodiment of the present invention. This embodiment can be applied to adjusting the temperature in the antenna cover of the navigation antenna so that each execution unit of the navigation antenna in the antenna cover is in a constant temperature environment. The method can be executed by a constant temperature control device of the navigation antenna. The constant temperature control device of the navigation antenna can be implemented in the form of hardware and / or software and can be configured in the navigation antenna, such as in the processor of the navigation antenna. Figure 2 As shown, the constant temperature control method of the navigation antenna includes:

[0079] S201, obtaining historical operating data of multiple execution units of the navigation antenna and the historical ambient temperature outside the antenna cover, wherein the historical operating data includes operating data of each execution unit in a current temperature control cycle and multiple historical temperature control cycles before the current temperature control cycle.

[0080] like Figure 1 The figure shows a schematic diagram of the structure of a marine antenna, in which a reflector 1, a feed source 2, an orthogonal mode coupler 3, a frequency converter 4, an antenna mainboard 5, a posture motor 6 and a posture determination device 7 are integrated in a radome 8. Of course, the marine antenna may also include other execution units. The present embodiment does not limit the execution units of the marine antenna. In addition, the marine antenna of the present embodiment may also include a temperature regulator, which may be arranged in the radome 8 for cooling or heating. For example, the temperature regulator may include a heating resistor for heating, and also include a refrigerant circulation system for cooling.

[0081] The temperature control cycle can be a cycle for temperature adjustment. For example, the duration of the temperature control cycle can be 30 seconds or 1 minute, etc. The current temperature control cycle can be the cycle in which the current time is located, the historical temperature control cycle can be the temperature control cycle before the current temperature control cycle, and the next temperature control cycle can be the first temperature control cycle after the current temperature control cycle.

[0082] The historical operation data of each execution unit of the navigation antenna can be at least one of electrical parameters, temperature, and radio frequency data. The electrical parameters can reflect the heating state of each execution unit, such as the operating voltage, current, power, etc. can reflect the heating state of the execution unit. The temperature and radio frequency data can reflect the operation state or operation mode of each execution unit. For example, the radiation frequency of the antenna can reflect the operation state or operation mode of the navigation antenna. The historical operation data of different execution units can be different. The historical operation data of each execution unit can be obtained through the recorded operation log. The historical ambient temperature outside the antenna cover can be detected by a temperature sensor.

[0083] S202: Inputting historical ambient temperature and historical operation data into a pre-trained antenna temperature prediction model to obtain a first temperature in the antenna cover and a confidence level of the first temperature when the temperature regulator is not started in the next temperature control period.

[0084] This embodiment can pre-train an antenna temperature prediction model, which is used to input historical operating data of each execution unit in the current cycle and before the current cycle and the historical ambient temperature outside the antenna cover, and predict the first temperature inside the antenna cover in the next temperature control cycle and the confidence level of the first temperature, wherein the first temperature is the temperature inside the antenna cover when the temperature regulator is not started in the next temperature control cycle, and the first temperature reflects the total heat generated by each execution unit of the navigation antenna when the operating state is entered in the next temperature control cycle.

[0085] Among them, the antenna temperature prediction model can be trained by the actual ambient temperature outside the antenna cover of the navigation antenna, the actual operation data of each execution unit and the actual temperature inside the antenna cover. The training method can refer to the supervised training method of the neural network model, which will not be described in detail here.

[0086] S203: Determine whether the confidence level is greater than a preset confidence level threshold.

[0087] Among them, the confidence level indicates the reliability of the first temperature predicted by the temperature prediction model being close to the actual temperature. When the confidence level is greater than the confidence threshold, it can be determined that the predicted first temperature can be used for temperature regulation, and S204 can be executed. When the confidence level is less than or equal to the confidence threshold, it is determined that the predicted first temperature may be significantly different from the actual temperature and cannot be used for temperature regulation. The temperature inside the antenna cover detected in the current temperature control cycle can be determined as the basis for temperature regulation in the next temperature control cycle, that is, the second temperature.

[0088] S204: Determine a temperature correction coefficient based on the confidence level of the first temperature predicted by multiple temperature control cycles.

[0089] In one embodiment, the deviation rate between the adjusted temperature and the target temperature of multiple historical temperature control cycles can be obtained, and the confidence and deviation rate of the first temperature predicted by multiple temperature control cycles can be used to calculate the weighted average as the temperature correction coefficient. Alternatively, the weighted sum can be calculated as the temperature correction coefficient, or the average value of the deviation rate can be directly calculated as the temperature correction coefficient.

[0090] S205 . Correct the first temperature based on the temperature correction coefficient to obtain a second temperature.

[0091] Specifically, the product of the first temperature and the temperature correction coefficient may be calculated, and the sum of the product and the first temperature may be further calculated to obtain the second temperature, which is the basis for temperature regulation in the next temperature control cycle.

[0092] S206: Control the temperature regulator to operate according to the second temperature and the preset target temperature in the next temperature control cycle to adjust the temperature inside the antenna cover to the target temperature.

[0093] In one embodiment, the difference between the second temperature and the target temperature can be calculated, and the absolute value of the difference is taken to obtain the absolute value of the temperature difference, and it is determined whether the difference is greater than the value 0. If so, it is determined that the temperature in the antenna cover in the next temperature control cycle may be greater than the target temperature, and the target cooling capacity is calculated using the absolute value of the temperature difference and the preset volume of the antenna cover, and the temperature regulator is controlled to cool according to the target cooling capacity. If not, it is determined that the temperature in the antenna cover in the next temperature control cycle may be lower than the target temperature, and the target heating amount is calculated using the absolute value of the temperature difference and the preset volume of the antenna cover, and the temperature regulator is controlled to heat according to the target heating amount. This embodiment does not limit the cooling and heating methods of the temperature regulator, and can refer to the cooling and heating methods in the prior art. For example, heating can be achieved through a heating resistor, and cooling can be achieved through refrigerant circulation cooling, wherein the target temperature can be the target temperature of constant temperature control.

[0094] The embodiment of the present invention obtains historical operation data of each execution unit of the navigation antenna in the radome and the historical ambient temperature outside the radome, and inputs them into the antenna temperature prediction model to obtain the first temperature in the radome when the temperature regulator is not started in the next temperature control period and the confidence of the first temperature, determines the temperature correction coefficient when the confidence is greater than a preset confidence threshold, corrects the first temperature based on the temperature correction coefficient to obtain the second temperature, controls the temperature regulator to work according to the second temperature and a preset target temperature in the next temperature control period, so as to adjust the temperature in the radome to the target temperature, realizes the advance prediction of the temperature of the navigation antenna in the next temperature control period through historical data, corrects the temperature and performs temperature regulation, can determine the temperature of the navigation antenna in the next temperature control period in advance and timely perform temperature regulation, realizes advance constant temperature control, the temperature in the radome is in a constant temperature state, that is, each execution unit of the navigation antenna is in a constant temperature environment, and the performance of the navigation antenna is guaranteed.

[0095] Embodiment 2

[0096] Figure 3 This is a flow chart of a constant temperature control method for a navigation antenna provided in the second embodiment of the present invention. The embodiment of the present invention is optimized on the basis of the above-mentioned first embodiment. Figure 3 As shown, the constant temperature control method of the navigation antenna includes:

[0097] S301, obtaining historical operation data of multiple execution units of the navigation antenna and the historical ambient temperature outside the antenna cover, wherein the historical operation data includes operation data of each execution unit in a current temperature control cycle and multiple historical temperature control cycles before the current temperature control cycle.

[0098] like Figure 1The figure shows the structure diagram of the navigation antenna. The reflector 1, feed source 2, orthogonal mode coupler 3, frequency converter 4, antenna mainboard 5, attitude motor 6 and attitude determination device 7 in the navigation antenna are integrated in the radome 8, which can be read from the operation log of the navigation antenna:

[0099] The pitch angle curve and angular velocity curve of the reflector, the pitch angle and angular velocity of the reflector in the radome, not only reflect the operating status of the navigation antenna (searching for satellites, attitude changes), but also reflect the impact of the disturbance of the air in the radome on the temperature when the reflector rotates at different pitch angles and angular velocities;

[0100] Obtaining the voltage curve, current curve and power curve of the feed source reflects the heating state of the feed source;

[0101] The temperature curve of the orthogonal mode coupler reflects the heating state of the orthogonal mode coupler;

[0102] The power curve, input frequency curve and output frequency curve of the frequency converter, wherein the power curve can reflect the heating state of the frequency converter, and the input frequency curve and the output frequency curve can reflect the operating state of the navigation antenna (high frequency working state, medium frequency working state or low frequency working state);

[0103] The power curve of the antenna mainboard reflects the heating status of the mainboard;

[0104] The power curve and speed curve of the attitude motor reflect the heating state of the motor and the operating state of the navigation antenna (searching for satellites, attitude changes);

[0105] The power curve of the posture determination device reflects the heating status of the posture determination device;

[0106] The historical ambient temperature curve outside the antenna cover reflects the temperature changes of the external environment in which the marine antenna is located, such as the temperature in different sea areas and at different times.

[0107] S302, inputting the historical operation data of the reflector, feed source, orthogonal mode coupler, frequency converter, antenna mainboard, posture motor and posture determination equipment and the historical ambient temperature curve outside the antenna cover into the feature extraction network.

[0108] like Figure 4 The network structure diagram of the antenna temperature prediction model is shown. The antenna temperature prediction model of this embodiment includes a feature extraction network, a feature fusion network, an antenna operation state matching network and a temperature prediction network connected in sequence. The antenna temperature prediction model can be trained by the following steps:

[0109] S1. Obtain a training data set. Each data sample in the training data set includes operation curve samples of the reflector, feed, orthogonal mode coupler, inverter, antenna mainboard, attitude motor, attitude determination device, and temperature curve samples outside the antenna cover. Each data sample is marked with the actual operation status and actual temperature.

[0110] For various marine antennas, the operating data of each execution unit during multiple temperature control cycles and the ambient temperature outside the antenna cover can be recorded according to the temperature control cycle. For example, the operating data of execution units such as the reflector, feed source, orthogonal mode coupler, inverter, antenna mainboard, attitude motor, and attitude determination device are recorded to obtain the operating curve of each execution unit and the temperature curve outside the antenna cover as operating curve samples and temperature curve samples, and the actual temperature inside the antenna cover in each temperature control cycle is detected, and the operating curve samples and temperature curve samples of each temperature control cycle are annotated with the actual temperature and the actual operating status of the marine antenna, where the operating status can be a classification of the state or mode of the marine antenna.

[0111] S2. Construct a state feature library, which includes feature graph samples and antenna operation states associated with the feature graph samples.

[0112] In this embodiment, a state feature library can be pre-configured, which includes feature map samples of the navigation antenna in different antenna operating states. Each feature map sample is obtained by extracting and merging the feature maps of the operating curves of each execution unit and the temperature curve outside the antenna cover in different operating states of the navigation antenna.

[0113] S3. Construct an antenna temperature prediction model including a feature extraction network, a feature fusion network, an antenna operation status matching network and a temperature prediction network connected in sequence.

[0114] like Figure 4 As shown, the feature extraction network may include a reflection surface feature extraction subnetwork, a feed source feature extraction subnetwork, an orthogonal mode coupler feature extraction subnetwork, a frequency converter feature extraction subnetwork, an antenna mainboard feature extraction subnetwork, a posture motor feature extraction subnetwork, a posture determination device feature extraction subnetwork, and an ambient temperature feature extraction subnetwork. The output layer of each feature extraction subnetwork is connected to the input layer of the feature fusion network, and the feature fusion network, the antenna operation status matching network, and the temperature prediction network are connected in sequence.

[0115] S4. Extract data samples and input them into the antenna temperature prediction model. Extract features from the feature extraction network data samples to obtain the second operating characteristic graph of the reflecting surface, feed source, orthogonal mode coupler, frequency converter, antenna mainboard, posture motor, and posture determination device, as well as the second ambient temperature characteristic graph.

[0116] like Figure 4As shown in the figure, the operation curve samples of the reflector, feed, orthogonal mode coupler, frequency converter, antenna mainboard, posture motor, and posture determination equipment (Curve 1, Curve 2, Curve 3, Curve 4, Curve 5, Curve 6, Curve 7) are respectively input into the reflecting surface feature extraction subnetwork, the feed source feature extraction subnetwork, the orthogonal mode coupler feature extraction subnetwork, the inverter feature extraction subnetwork, the antenna mainboard feature extraction subnetwork, the posture motor feature extraction subnetwork, and the posture determination device feature extraction subnetwork to obtain the second operation characteristic graph (F1, F2, F3, F4, F5, F6, F7) of the reflecting surface, the feed source, the orthogonal mode coupler, the inverter, the antenna mainboard, the posture motor, and the posture determination device. The temperature curve sample Curve8 is input into the ambient temperature feature extraction subnetwork to obtain the second ambient temperature characteristic graph F8, wherein the second operation characteristic graph (F1, F2, F3, F4, F5, F6, F7) and the second ambient temperature characteristic graph F8 are feature graphs of the same scale.

[0117] S5. Fusing the second operation feature map and the second ambient temperature feature map in a feature fusion network to obtain a second fused feature map.

[0118] Specifically, in the feature fusion network, the second operation feature graph (F1, F2, F3, F4, F5, F6, F7) and the second ambient temperature feature graph F8 can be fused according to the weights of the current neurons to obtain a second fused feature graph F.

[0119] S6. In the antenna operation state matching network, the second fused feature map is matched with the feature map samples in the state feature library to obtain predicted feature pairs and the matching degree of the predicted feature pairs. The predicted feature pairs include the second fused feature map and the target feature map samples. The target feature map samples are feature maps of the determined antenna operation state.

[0120] In one embodiment, the matching degree of the second fused feature map and each feature map sample in the state feature library can be calculated (for example, the cosine similarity is calculated) to obtain the target feature map sample with the highest matching degree with the second fused feature map F, and the target feature map sample F_sample and the second fused feature map F are used to generate a predicted feature pair (F, F_sample).

[0121] S7. Determine the antenna operation state associated with the target feature map sample in the feature alignment as the predicted operation state of the navigation antenna in the next temperature control cycle.

[0122] Specifically, each feature map sample in the state feature library is associated with an antenna operating state, and the antenna operating state associated with the target feature map sample in the feature pair can be determined as the predicted operating state of the navigation antenna in the next temperature control cycle, that is, the navigation antenna will operate in the predicted operating state in the next temperature control cycle.

[0123] S8. Predicting the predicted temperature in the antenna cover and the probability of the predicted temperature when the temperature regulator is not started in the next temperature control period based on the predicted operating state in the temperature prediction network.

[0124] Assume that the predicted temperature is T1, and the probability of predicted temperature T1 is P1.

[0125] S9. Calculate the total loss value based on the predicted temperature, probability, true temperature, predicted operating state, true operating state, and the matching degree of the predicted feature pairs.

[0126] In one embodiment, the predicted operating state and the actual operating state can be used to calculate a first loss value, which represents the deviation of the operating state matching between the feature fusion network and the antenna operating state matching network. The predicted temperature and the actual temperature can be used to calculate a second loss value, which represents the deviation of the temperature prediction network from the temperature prediction. Then, the first product of the first loss value and the matching degree is calculated, the second product of the second loss value and the probability is calculated, and the sum of the first product and the second product is calculated as the total loss value.

[0127] S10: Determine whether the training stop condition is met.

[0128] The training stop condition may be that the total loss value is less than a preset value, or the number of iterative training times reaches a preset number. If the training stop condition is met, execute S11; if the training stop condition is not met, execute S12.

[0129] S11, determining that the antenna temperature prediction model has completed training.

[0130] S12, using the total loss value to adjust the network parameters of the feature fusion network, the antenna operation status matching network, and the temperature prediction network, and returning to S4.

[0131] Specifically, the echelon can be calculated according to the total loss value, and the random echelon descent, batch echelon descent and other algorithms can be used to adjust the fusion weights of each feature map in the feature fusion network, and adjust the network parameters of the antenna operation state matching network and the temperature prediction network.

[0132] During training, this embodiment first uses the predicted operating state and the actual operating state to calculate the first loss value, and uses the predicted temperature and the actual temperature to calculate the second loss value. Then, the first product of the first loss value and the matching degree is calculated, the second product of the second loss value and the probability is calculated, and the sum of the first product and the second product is calculated as the total loss value. The calculated total loss value focuses on measuring the deviations of feature fusion, operating state matching, and temperature prediction. Through the total loss value, the model can be constrained to learn the ability to accurately perform feature fusion, operating state matching, and temperature prediction.

[0133] After the antenna temperature prediction model is trained, the historical operating data of the reflector, feed, orthogonal mode coupler, inverter, antenna mainboard, posture motor, and posture determination equipment and the historical ambient temperature curve outside the antenna cover can be input into the feature extraction network, such as Figure 4 As shown, the operating curves (Curve1', Curve 2', Curve 3', Curve 4', Curve 5', Curve 6', Curve 7') of the reflector, feed, orthogonal mode coupler, inverter, antenna mainboard, posture motor, and posture determination device can be respectively input into the reflector feature extraction subnetwork, feed feature extraction subnetwork, orthogonal mode coupler feature extraction subnetwork, inverter feature extraction subnetwork, antenna mainboard feature extraction subnetwork, posture motor feature extraction subnetwork, and posture determination device feature extraction subnetwork, and the temperature curve Curve8 is input into the ambient temperature feature extraction subnetwork.

[0134] S303. Extract features from historical operating data and historical ambient temperature curves in the feature extraction network to obtain a first operating characteristic graph and a first ambient temperature characteristic graph of the reflecting surface, feed source, orthogonal mode coupler, inverter, antenna mainboard, posture motor, and posture determination device.

[0135] Specifically, Figure 4 As shown, feature extraction is performed in the corresponding feature extraction subnetworks respectively to obtain the first operation characteristic graphs (F1', F2', F3', F4', F5', F6', F7') of the reflector, feed, orthogonal mode coupler, frequency converter, antenna mainboard, posture motor, and posture determination device, as well as the first ambient temperature characteristic graph F8', wherein the first operation characteristic graph (F1', F2', F3', F4', F5', F6', F7') and the first ambient temperature characteristic graph F8' are feature graphs of the same scale.

[0136] S304: Fusing the first operation feature graph and the first ambient temperature feature graph in a feature fusion network to obtain a first fused feature graph.

[0137] Specifically, in the feature fusion network, the first operation feature map (F1', F2', F3', F4', F5', F6', F7') and the first ambient temperature feature map F8' can be fused according to the weights of neurons to obtain a first fused feature map F'.

[0138] S305. In the antenna operation state matching network, the first fused feature map is matched with the feature map samples in the preset state feature library to obtain feature pairs and the matching degree of the feature pairs, wherein the feature pair includes the first fused feature map and the first feature map sample, and the first feature map sample is the feature map of the determined antenna operation state.

[0139] Specifically, the matching degree between the first fused feature map F' and each feature map sample in the state feature library can be calculated (for example, cosine similarity can be calculated) to obtain the first feature map sample with the highest matching degree with the first fused feature map F', and the first feature map sample F_target and the first fused feature map F' are used to generate a feature pair (F', F_target, match), where match is the matching degree between the first feature map sample F_target and the first fused feature map F'.

[0140] S306: Determine the antenna operating state associated with the first feature graph sample in the feature pair as the target operating state of the navigation antenna in the next temperature control cycle.

[0141] Specifically, each feature graph sample in the state feature library is associated with an antenna operating state, and the antenna operating state associated with the first feature graph sample in the feature pair can be determined as the target operating state of the navigation antenna in the next temperature control cycle, that is, the navigation antenna will operate in the target operating state in the next temperature control cycle.

[0142] S307 . Predicting, in the temperature prediction network, a first temperature in the antenna cover and a probability of the first temperature when the temperature regulator is not started in the next temperature control period based on the target operating state.

[0143] Assuming that the first temperature is T0, the probability that the first temperature is T0 is P0.

[0144] S308. Calculate a weighted sum of the probability of the first temperature and the probability of the target operating state as the confidence of the first temperature.

[0145] That is, calculate the product of probability P0 and matching degree match.

[0146] S309: Determine whether the confidence level is greater than a preset confidence level threshold.

[0147] Among them, the confidence level indicates the reliability of the first temperature predicted by the temperature prediction model being close to the actual temperature. When the confidence level is greater than the confidence threshold, it can be determined that the predicted first temperature can be used for temperature regulation, and S310 can be executed. When the confidence level is less than or equal to the confidence threshold, it is determined that the predicted first temperature may be significantly different from the actual temperature and cannot be used for temperature regulation. The temperature inside the antenna cover detected in the current temperature control cycle can be determined as the first temperature of the next temperature control cycle.

[0148] S310: Acquire multiple third temperatures inside the antenna cover detected in a current temperature control cycle and multiple historical temperature control cycles.

[0149] In this embodiment, the temperature sensor can detect multiple temperatures inside the antenna cover within a temperature control cycle, and take the average value of the multiple temperatures as the third temperature of the temperature control cycle, to obtain the third temperature inside the antenna cover for multiple temperature control cycles. The third temperature is the actual temperature inside the antenna cover after the temperature regulator performs temperature adjustment.

[0150] S311, calculating the temperature adjustment deviation rate of the temperature regulator in multiple temperature control cycles based on multiple third temperatures and the preset target temperature.

[0151] Among them, the target temperature can be a pre-set constant temperature, which is the ideal working temperature of the marine antenna. The difference between the third temperature after adjustment in each temperature control cycle and the target temperature can be calculated, and the ratio of the difference to the target temperature can be calculated to obtain the temperature adjustment deviation rate of the temperature regulator in each temperature control cycle. The temperature adjustment deviation rate may be caused by the deviation of the temperature regulator and the antenna temperature prediction model from the prediction of the first temperature. For example, the first temperature predicted by the antenna temperature prediction model may be lower or higher than the actual temperature, resulting in insufficient adjustment of the temperature regulator, and / or the first temperature is relatively accurate but the temperature regulator itself is not adjusted properly.

[0152] S312: Calculate a weighted average value of the confidence of the first temperature predicted by multiple temperature control cycles and multiple temperature adjustment deviation rates as a temperature correction coefficient.

[0153] Since the confidence of the first temperature reflects the credibility of the first temperature, the confidence of the first temperature predicted by multiple temperature control cycles and the weighted average of multiple temperature adjustment deviation rates can be used as the temperature correction coefficient. The temperature correction coefficient can correct the impact of the antenna temperature prediction model on the inaccurate prediction of the first temperature.

[0154] S313: Calculate the product of the first temperature and the temperature correction coefficient as the temperature compensation value.

[0155] It should be noted that the temperature correction coefficient can be a positive number or a negative number, and the temperature compensation value can be a positive value or a negative value.

[0156] S314: Calculate the sum of the temperature compensation value and the first temperature to obtain a second temperature.

[0157] The second temperature may be greater than the first temperature or may be less than the first temperature.

[0158] Exemplarily, assuming that the third temperature of the current temperature control cycle and the previous multiple historical temperature control cycles are all deviated from the target temperature, it may be caused by the deviation of the first temperature predicted by multiple historical temperature control cycles. For example, the first temperature predicted by multiple historical temperature control cycles is too low, and the temperature is still lower than the target temperature after temperature correction, then the calculated temperature compensation value is a negative value, and the second temperature obtained by calculating the sum of the temperature compensation value and the first temperature is lower than the first temperature, that is, the predicted temperature of the navigation antenna in the next temperature control cycle when the temperature regulator is not started is lower, and the temperature difference between the second temperature and the target temperature is larger, which prompts the temperature regulator to generate more heat to increase the temperature inside the antenna cover, so as to compensate for the defect that the first temperature predicted by the antenna temperature prediction model is lower than the actual temperature.

[0159] S315, controlling the temperature regulator to operate according to the second temperature and the preset target temperature in the next temperature control cycle, so as to adjust the temperature inside the antenna cover to the target temperature.

[0160] In one embodiment, the difference between the second temperature and the target temperature can be calculated, and the absolute value of the difference is taken to obtain the absolute value of the temperature difference, and it is determined whether the difference is greater than the value 0. If so, it is determined that the temperature inside the antenna cover in the next temperature control cycle may be greater than the target temperature, and the target cooling capacity is calculated using the absolute value of the temperature difference and the preset volume of the antenna cover, and the temperature regulator is controlled to cool according to the target cooling capacity. If not, it is determined that the temperature inside the antenna cover in the next temperature control cycle may be lower than the target temperature, and the target heating amount is calculated using the absolute value of the temperature difference and the preset volume of the antenna cover, and the temperature regulator is controlled to heat according to the target heating amount, wherein the target temperature can be the target temperature of constant temperature control.

[0161] The embodiment of the present invention obtains historical operation data of each execution unit of the navigation antenna in the radome and the historical ambient temperature outside the radome, and inputs them into the antenna temperature prediction model to obtain the first temperature in the radome when the temperature regulator is not started in the next temperature control period and the confidence of the first temperature, determines the temperature correction coefficient when the confidence is greater than a preset confidence threshold, corrects the first temperature based on the temperature correction coefficient to obtain the second temperature, controls the temperature regulator to work according to the second temperature and a preset target temperature in the next temperature control period, so as to adjust the temperature in the radome to the target temperature, realizes the advance prediction of the temperature of the navigation antenna in the next temperature control period through historical data, corrects the temperature and performs temperature regulation, can determine the temperature of the navigation antenna in the next temperature control period in advance and timely perform temperature regulation, realizes advance constant temperature control, the temperature in the radome is in a constant temperature state, that is, each execution unit of the navigation antenna is in a constant temperature environment, and the performance of the navigation antenna is guaranteed.

[0162] Furthermore, multiple third temperatures detected in the antenna cover during the current temperature control cycle and multiple historical temperature control cycles are obtained, and the temperature adjustment deviation rate of the temperature regulator in multiple temperature control cycles is calculated based on the multiple third temperatures and the preset target temperature. The confidence of the first temperature predicted by multiple temperature control cycles and the weighted average of the multiple temperature adjustment deviation rates are used as the temperature correction coefficient. The product of the first temperature and the temperature correction coefficient is calculated as the temperature compensation value. The sum of the temperature compensation value and the first temperature is calculated to obtain the second temperature, so as to prompt the temperature regulator to generate more heat to increase the temperature in the antenna cover, or generate more cold to reduce the temperature in the antenna cover, so as to compensate for the defect that the first temperature predicted by the antenna temperature prediction model is smaller or higher than the actual temperature, so that the constant temperature control in the antenna cover is more detailed, and it is ensured that each execution unit of the navigation antenna in the antenna cover operates in a constant temperature environment.

[0163] Embodiment 3

[0164] Figure 5 This is a schematic diagram of the structure of a constant temperature control device for a navigation antenna provided in the third embodiment of the present invention. Figure 5 As shown, the constant temperature control device of the navigation antenna includes:

[0165] The historical operation data and ambient temperature acquisition module 501 is used to acquire the historical operation data of multiple execution units of the navigation antenna and the historical ambient temperature outside the antenna cover, wherein the historical operation data includes the operation data of each execution unit in the current temperature control cycle and multiple historical temperature control cycles before the current temperature control cycle;

[0166] The temperature prediction module 502 is used to input the historical ambient temperature and the historical operation data into a pre-trained antenna temperature prediction model to obtain a first temperature in the antenna cover and a confidence level of the first temperature when the temperature regulator is not started in the next temperature control cycle;

[0167] A confidence determination module 503 is used to determine whether the confidence is greater than a preset confidence threshold, and if so, execute a temperature correction coefficient determination module 504;

[0168] A temperature correction coefficient determination module 504, configured to determine a temperature correction coefficient based on the confidence of the first temperature predicted by a plurality of temperature control cycles;

[0169] A temperature correction module 505, configured to correct the first temperature based on the temperature correction coefficient to obtain a second temperature;

[0170] The temperature regulating module 506 is used to control the temperature regulator to operate according to the second temperature and a preset target temperature in the next temperature control cycle, so as to regulate the temperature in the antenna cover to the target temperature.

[0171] Optionally, the execution unit of the navigation antenna includes a reflector, a feed source, an orthogonal mode coupler, a frequency converter, an antenna mainboard, a posture motor, and a posture determination device, and the historical operation data and ambient temperature acquisition module 501 includes:

[0172] A reflecting surface operation data acquisition unit, used for acquiring a pitch angle curve and an angular velocity curve of the reflecting surface;

[0173] A feed source operation data acquisition unit, used to acquire a voltage curve, a current curve and a power curve of the feed source;

[0174] An orthogonal mode coupler operation data acquisition unit, used for acquiring a temperature curve of the orthogonal mode coupler;

[0175] A frequency converter operation data acquisition unit, used to acquire a power curve, an input frequency curve and an output frequency curve of the frequency converter;

[0176] A mainboard operation data acquisition unit, used to acquire a power curve of the antenna mainboard;

[0177] A motor operation data acquisition unit, used to acquire a power curve and a speed curve of the posture motor;

[0178] A posture determination device operation data acquisition unit, used to acquire a power curve of the posture determination device;

[0179] The historical ambient temperature acquisition unit is used to acquire the historical ambient temperature curve outside the antenna cover.

[0180] Optionally, the antenna temperature prediction model includes a feature extraction network, a feature fusion network, an antenna operation state matching network, and a temperature prediction network connected in sequence, the historical operation data is input into a pre-trained antenna temperature prediction model, and the first temperature in the antenna cover and the confidence of the first temperature are predicted in the antenna temperature prediction model when the temperature regulator is not started in the next temperature control cycle, including:

[0181] A historical data input unit, used to input the historical operation data of the reflector, feed source, orthogonal mode coupler, frequency converter, antenna mainboard, posture motor and posture determination device and the historical ambient temperature curve outside the antenna cover into the feature extraction network;

[0182] A feature graph extraction unit is used to extract features from the historical operation data and the historical ambient temperature curve in the feature extraction network, respectively, to obtain a first operation feature graph and a first ambient temperature feature graph of the reflecting surface, the feed source, the orthogonal mode coupler, the frequency converter, the antenna mainboard, the posture motor, and the posture determination device;

[0183] A feature graph fusion unit, configured to fuse the first operation feature graph and the first ambient temperature feature graph in the feature fusion network to obtain a first fused feature graph;

[0184] a feature matching unit, configured to match the first fused feature graph with a feature graph sample in a preset state feature library in the antenna operation state matching network to obtain a feature pair and a matching degree of the feature pair, wherein the feature pair includes the first fused feature graph and a first feature graph sample, and the first feature graph sample is a feature graph of a determined antenna operation state;

[0185] a target operating state determining unit, configured to determine the antenna operating state associated with the first feature map sample in the feature pair as the target operating state of the navigation antenna in the next temperature control cycle;

[0186] a temperature prediction unit, configured to predict, in the temperature prediction network, a first temperature in the radome and a probability of the first temperature when the temperature regulator is not started in the next temperature control period based on the target operating state;

[0187] The temperature confidence calculation unit is used to calculate a weighted sum of the probability of the first temperature and the probability of the target operating state as the confidence of the first temperature.

[0188] Optionally, the temperature correction coefficient determination module 504 includes:

[0189] A temperature acquisition unit in the antenna cover, used to acquire a plurality of third temperatures in the antenna cover detected in a current temperature control cycle and a plurality of historical temperature control cycles;

[0190] a deviation rate calculation unit, configured to calculate a temperature adjustment deviation rate of the temperature regulator in a plurality of temperature control cycles based on the plurality of third temperatures and a preset target temperature;

[0191] The correction coefficient calculation unit is used to calculate a weighted average value using the confidence of the first temperature predicted by multiple temperature control cycles and multiple temperature adjustment deviation rates as the temperature correction coefficient.

[0192] Optionally, the temperature correction module 505 includes:

[0193] a temperature compensation value calculation unit, configured to calculate a product of the first temperature and the temperature correction coefficient as a temperature compensation value;

[0194] The temperature sum calculation unit is used to calculate the sum of the temperature compensation value and the first temperature to obtain a second temperature.

[0195] Optionally, the temperature adjustment module 506 includes:

[0196] a temperature difference absolute value calculation unit, used for calculating the difference between the second temperature and the target temperature, and taking the absolute value of the difference to obtain the absolute value of the temperature difference;

[0197] A difference judgment unit, used to judge whether the difference is greater than a value of 0, and if so, execute the cooling control unit, and if not, execute the heating control unit;

[0198] a refrigeration control unit, configured to calculate a target refrigeration capacity by using the absolute value of the temperature difference and the preset volume of the antenna cover, and to control the temperature regulator to refrigerate according to the target refrigeration capacity;

[0199] A heating control unit is used to calculate a target heating amount by using the absolute value of the temperature difference and the preset volume of the antenna cover, and control the temperature regulator to heat according to the target heating amount.

[0200] Optionally, the antenna temperature prediction model is trained by a training module, and the training module is specifically used for:

[0201] Acquire a training data set, wherein each data sample in the training data set includes operation curve samples of a reflector, a feed source, an orthogonal mode coupler, a frequency converter, an antenna mainboard, a posture motor, and a posture determination device, and a temperature curve sample outside the antenna cover, and each data sample is annotated with a real operation state and a real temperature;

[0202] Constructing a state feature library, wherein the state feature library includes feature graph samples and antenna operation states associated with the feature graph samples;

[0203] Constructing an antenna temperature prediction model including a feature extraction network, a feature fusion network, an antenna operation state matching network and a temperature prediction network connected in sequence;

[0204] Extract data samples and input them into the antenna temperature prediction model, extract features from the data samples in the feature extraction network, and obtain a second operation feature graph and a second ambient temperature feature graph of the reflector, feed source, orthogonal mode coupler, frequency converter, antenna mainboard, posture motor, and posture determination device;

[0205] fusing the second operation feature graph and the second ambient temperature feature graph in the feature fusion network to obtain a second fused feature graph;

[0206] In the antenna operation state matching network, the second fused feature map is matched with the feature map samples in the state feature library to obtain a predicted feature pair and a matching degree of the predicted feature pair, the predicted feature pair includes the second fused feature map and the target feature map sample, and the target feature map sample is a feature map of the determined antenna operation state;

[0207] Determining the antenna operating state associated with the target feature map sample in the feature pair as the predicted operating state of the navigation antenna in the next temperature control cycle;

[0208] Predicting, in the temperature prediction network, a predicted temperature in the radome and a probability of the predicted temperature when the temperature regulator is not started in the next temperature control period based on the predicted operating state;

[0209] Calculating a total loss value based on the predicted temperature, the probability, the actual temperature, the predicted operating state, the actual operating state, and a matching degree of the predicted feature pair;

[0210] Determine whether the training stop condition is met;

[0211] If so, determining that the antenna temperature prediction model has completed training;

[0212] If not, the total loss value is used to adjust the network parameters of the feature fusion network, the antenna operation status matching network and the temperature prediction network, and the process returns to the step of extracting data samples and inputting them into the antenna temperature prediction model.

[0213] The constant temperature control device for a navigation antenna provided in an embodiment of the present invention can execute the constant temperature control method for a navigation antenna provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0214] Embodiment 4

[0215] Figure 6FIG. 4 is a schematic diagram showing the structure of a marine antenna 40 that can be used to implement an embodiment of the present invention. Figure 6 As shown, the navigation antenna 40 includes at least one processor 41, and a memory connected to the at least one processor 41, such as a read-only memory (ROM) 42, a random access memory (RAM) 43, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 41 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 42 or the computer program loaded from the storage unit 48 to the random access memory (RAM) 43. In the RAM 43, various programs and data required for the operation of the navigation antenna 40 can also be stored. The processor 41, the ROM 42, and the RAM 43 are connected to each other through a bus 44. An input / output (I / O) interface 45 is also connected to the bus 44.

[0216] A number of components in the marine antenna 40 are connected to the I / O interface 45, including: an input unit 46, such as a temperature sensor, etc.; an output unit 47, such as various types of displays, speakers, etc.; a storage unit 48, such as a disk, an optical disk, etc.; and a communication unit 49, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 49 allows the marine antenna 40 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0217] The processor 41 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 41 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special 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 41 executes the various methods and processes described above, such as a constant temperature control method for a navigation antenna.

[0218] In some embodiments, the constant temperature control method of the navigation antenna can be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 48. In some embodiments, part or all of the computer program can be loaded and / or installed on the navigation antenna 40 via the ROM 42 and / or the communication unit 49. When the computer program is loaded into the RAM 43 and executed by the processor 41, one or more steps of the constant temperature control method of the navigation antenna described above can be performed. Alternatively, in other embodiments, the processor 41 can be configured to execute the constant temperature control method of the navigation antenna in any other appropriate manner (for example, by means of firmware).

[0219] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations 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 can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0220] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0221] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, 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 disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0222] The systems and techniques described herein may 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 with a graphical user interface or a web browser through which a user can interact with implementations 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 may 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.

[0223] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0224] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0225] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A constant temperature control method for a navigation antenna, characterized in that: The plurality of execution units of the navigation antenna are arranged in the antenna cover and are provided with a temperature regulator, including: Acquire historical operation data of multiple execution units of the navigation antenna and the historical ambient temperature outside the antenna cover, wherein the historical operation data includes operation data of each execution unit in a current temperature control cycle and multiple historical temperature control cycles before the current temperature control cycle; Inputting the historical ambient temperature and the historical operation data into a pre-trained antenna temperature prediction model to obtain a first temperature in the antenna cover and a confidence level of the first temperature when the temperature regulator is not started in the next temperature control cycle; Determining whether the confidence level is greater than a preset confidence level threshold; If yes, determining a temperature correction coefficient based on the confidence of the first temperature predicted by a plurality of temperature control cycles; Correcting the first temperature based on the temperature correction coefficient to obtain a second temperature; In the next temperature control cycle, the temperature regulator is controlled to operate according to the second temperature and a preset target temperature, so as to adjust the temperature in the antenna cover to the target temperature.

2. The method according to claim 1, characterized in that The execution unit of the navigation antenna includes a reflector, a feed source, an orthogonal mode coupler, a frequency converter, an antenna mainboard, a posture motor, and a posture determination device. The historical operation data of the multiple execution units of the navigation antenna and the historical ambient temperature outside the radome are obtained, including: Obtaining a pitch angle curve and an angular velocity curve of the reflecting surface; Obtaining a voltage curve, a current curve, and a power curve of the feed source; Acquiring a temperature curve of the orthogonal mode coupler; Obtaining a power curve, an input frequency curve, and an output frequency curve of the frequency converter; Obtaining a power curve of the antenna mainboard; Obtaining a power curve and a speed curve of the posture motor; Obtaining a power curve of the posture determination device; A historical ambient temperature curve outside the radome is obtained.

3. The method according to claim 2, characterized in that The antenna temperature prediction model includes a feature extraction network, a feature fusion network, an antenna operation state matching network, and a temperature prediction network connected in sequence, the historical operation data is input into a pre-trained antenna temperature prediction model, and the first temperature in the antenna cover and the confidence of the first temperature are predicted in the antenna temperature prediction model when the temperature regulator is not started in the next temperature control cycle, including: Inputting historical operating data of the reflector, feed, orthogonal mode coupler, frequency converter, antenna mainboard, posture motor and posture determination device and historical ambient temperature curve outside the radome into the feature extraction network; Extract features from the historical operation data and the historical ambient temperature curve in the feature extraction network to obtain a first operation feature graph and a first ambient temperature feature graph of the reflector, feed source, orthogonal mode coupler, frequency converter, antenna mainboard, posture motor, and posture determination device; fusing the first operation feature graph and the first ambient temperature feature graph in the feature fusion network to obtain a first fused feature graph; In the antenna operation state matching network, the first fused feature map is matched with a feature map sample in a preset state feature library to obtain a feature pair and a matching degree of the feature pair, wherein the feature pair includes the first fused feature map and a first feature map sample, and the first feature map sample is a feature map of a determined antenna operation state; determining the antenna operating state associated with the first feature graph sample in the feature pair as the target operating state of the navigation antenna in the next temperature control cycle; Predicting, in the temperature prediction network, a first temperature in the radome and a probability of the first temperature when the temperature regulator is not started in the next temperature control period based on the target operating state; A weighted sum of the probability of the first temperature and the probability of the target operating state is calculated as the confidence of the first temperature.

4. The method according to claim 1, characterized in that Determining a temperature correction coefficient based on the confidence of the first temperature predicted by a plurality of temperature control cycles includes: Acquire multiple third temperatures in the antenna cover detected in a current temperature control cycle and multiple historical temperature control cycles; Calculating the temperature adjustment deviation rate of the temperature regulator in multiple temperature control cycles based on the multiple third temperatures and the preset target temperature; The confidence of the first temperature predicted by multiple temperature control cycles and multiple temperature adjustment deviation rates are used to calculate a weighted average value as a temperature correction coefficient.

5. The method according to claim 1, characterized in that Correcting the first temperature based on the temperature correction coefficient to obtain a second temperature includes: calculating a product of the first temperature and the temperature correction coefficient as a temperature compensation value; The second temperature is obtained by calculating the sum of the temperature compensation value and the first temperature.

6. The method according to claim 1, characterized in that Controlling the temperature regulator to operate according to the second temperature and a preset target temperature in the next temperature control cycle to adjust the temperature in the antenna cover to the target temperature includes: Calculating the difference between the second temperature and the target temperature, and taking the absolute value of the difference to obtain an absolute value of the temperature difference; Determine whether the difference is greater than a value of 0; If yes, the target cooling capacity is calculated by using the absolute value of the temperature difference and the preset volume of the antenna cover, and the temperature regulator is controlled to cool according to the target cooling capacity; If not, the target heating amount is calculated using the absolute value of the temperature difference and the preset volume of the antenna cover, and the temperature regulator is controlled to heat according to the target heating amount.

7. The method according to claim 3, characterized in that The antenna temperature prediction model is trained by the following steps: Acquire a training data set, wherein each data sample in the training data set includes operation curve samples of a reflector, a feed source, an orthogonal mode coupler, a frequency converter, an antenna mainboard, a posture motor, and a posture determination device, and a temperature curve sample outside the antenna cover, and each data sample is annotated with a real operation state and a real temperature; Constructing a state feature library, wherein the state feature library includes feature graph samples and antenna operation states associated with the feature graph samples; Constructing an antenna temperature prediction model including a feature extraction network, a feature fusion network, an antenna operation state matching network and a temperature prediction network connected in sequence; Extract data samples and input them into the antenna temperature prediction model, extract features from the data samples in the feature extraction network, and obtain a second operation feature graph and a second ambient temperature feature graph of the reflector, feed source, orthogonal mode coupler, frequency converter, antenna mainboard, posture motor, and posture determination device; fusing the second operation feature graph and the second ambient temperature feature graph in the feature fusion network to obtain a second fused feature graph; In the antenna operation state matching network, the second fused feature map is matched with the feature map samples in the state feature library to obtain a predicted feature pair and a matching degree of the predicted feature pair, the predicted feature pair includes the second fused feature map and the target feature map sample, and the target feature map sample is a feature map of the determined antenna operation state; Determining the antenna operating state associated with the target feature map sample in the feature pair as the predicted operating state of the navigation antenna in the next temperature control cycle; Predicting, in the temperature prediction network, a predicted temperature in the radome and a probability of the predicted temperature when the temperature regulator is not started in the next temperature control period based on the predicted operating state; Calculating a total loss value based on the predicted temperature, the probability, the actual temperature, the predicted operating state, the actual operating state, and a matching degree of the predicted feature pair; Determine whether the training stop condition is met; If so, determining that the antenna temperature prediction model has completed training; If not, the total loss value is used to adjust the network parameters of the feature fusion network, the antenna operation status matching network and the temperature prediction network, and the process returns to the step of extracting data samples and inputting them into the antenna temperature prediction model.

8. A constant temperature control device for a navigation antenna, characterized in that: The plurality of execution units of the navigation antenna are arranged in the antenna cover and are provided with a temperature regulator, including: A historical operation data and ambient temperature acquisition module, used to acquire historical operation data of multiple execution units of the navigation antenna and the historical ambient temperature outside the antenna cover, wherein the historical operation data includes operation data of each execution unit in a current temperature control cycle and multiple historical temperature control cycles before the current temperature control cycle; a temperature prediction module, used to input the historical ambient temperature and the historical operation data into a pre-trained antenna temperature prediction model to obtain a first temperature in the antenna cover and a confidence level of the first temperature when the temperature regulator is not started in the next temperature control cycle; A confidence determination module, used to determine whether the confidence is greater than a preset confidence threshold, and if so, execute a temperature correction coefficient determination module; a temperature correction coefficient determination module, configured to determine a temperature correction coefficient based on a confidence level of the first temperature predicted by a plurality of temperature control cycles; A temperature correction module, configured to correct the first temperature based on the temperature correction coefficient to obtain a second temperature; The temperature regulating module is used to control the operation of the temperature regulator according to the second temperature and a preset target temperature in the next temperature control cycle, so as to regulate the temperature in the antenna cover to the target temperature.

9. A navigation antenna, characterized in that: The navigation antenna 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 constant temperature control method for a navigation antenna according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the constant temperature control method for a navigation antenna according to any one of claims 1 to 7 when executed.

Images