Attenuation compensation control method and system for microwave transceiver system
By applying deep learning-based artificial intelligence technology in microwave transceiver systems, we can capture the dynamic characteristics of temperature changes and intelligently generate temperature compensation coefficients, and solve the problem of gain fluctuation in high and low temperature environments of microwave transceiver systems, and achieve high-precision attenuation compensation Control ensures the stability of the system and communication quality.
Patent Information
- Application Number
- CN202411181861.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-27
- Publication Date
- 2024-11-29
- Estimated Expiration
- 2044-08-27
AI Technical Summary
The gain fluctuations in existing microwave transceiver systems lead to signal attenuation and distortion in high and low temperature environments, and the traditional temperature compensation method has limited effect and is difficult to accurately control.
Using artificial intelligence technology based on deep learning, we capture the dynamic characteristics of temperature changes through real-time monitoring and data analysis, and use global context cluster analysis to mine the global change characteristic mode of temperature, and intelligently generate temperature compensation coefficients to achieve attenuation compensation control.
It significantly improves the accuracy and real-time performance of attenuation compensation, reduces signal attenuation and distortion caused by temperature changes, and ensures the stability and communication quality of the microwave transmission and reception system.
Smart Images

Figure CN118713693B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of microwave control, and more specifically, to an attenuation compensation control method and system for a microwave transceiver system. Background Art
[0002] With the rapid development of communication technology, microwave transceiver systems play an increasingly important role in radar, communication, scientific research and industrial applications. Microwave transmission is an ideal choice for long-distance communication and high-speed data transmission due to its high frequency, short wavelength and ability to penetrate the ionosphere.
[0003] In practical applications, temperature is one of the key factors affecting the performance of microwave transceiver systems. Since the physical properties of electronic devices change significantly with temperature, especially in high and low temperature environments, changes in electron mobility will cause gain fluctuations in power devices, which in turn affects the gain stability and transmission quality of the entire system. If this gain fluctuation is not compensated, it will directly lead to signal attenuation and may even cause signal distortion or interruption, seriously affecting the reliability and efficiency of communications.
[0004] Traditional temperature compensation methods mainly rely on hardware design, such as automatic gain control circuits (AGC) and temperature compensation attenuators. AGC samples the output signal and feeds it back to the input to stabilize the input signal with large fluctuations, but its core part, the gain variable amplifier, often introduces nonlinear distortion. The temperature compensation attenuator achieves compensation based on the correspondence between the pre-defined temperature variable and the attenuation. Although it is simple and effective, its compensation effect is limited and difficult to control accurately under complex and changing environmental conditions.
[0005] Therefore, an optimized attenuation compensation control method and system of a microwave transceiver system are needed to solve the above technical problems. Summary of the invention
[0006] In order to solve the above technical problems, the present application is proposed. The embodiment of the present application provides an attenuation compensation control method and system for a microwave transceiver system, which uses artificial intelligence technology based on deep learning to monitor and analyze the temperature of the microwave transceiver system in real time, captures the dynamic characteristics of temperature changes within a local time scale, and mines the global change characteristic pattern of temperature through global context clustering analysis, so as to intelligently generate a temperature compensation coefficient, thereby realizing attenuation compensation control of the microwave transceiver system, which can significantly improve the accuracy and real-time performance of attenuation compensation, reduce signal attenuation and distortion caused by temperature changes, and ensure the stability and communication quality of the microwave transceiver system.
[0007] According to one aspect of the present application, there is provided an attenuation compensation control method for a microwave transceiver system, comprising:
[0008] Obtaining a time series of the real-time temperature of the microwave transceiver system collected by a temperature sensor;
[0009] Performing time series encoding based on the local time scale on the time series of the real-time temperature to obtain a sequence of implicitly associated feature vectors of the local time series of the real-time temperature;
[0010] Inputting the sequence of the real-time temperature local time series implicit association feature vectors into a global context-based saliency optimization module to obtain a sequence of enhanced real-time temperature local time series implicit association feature vectors;
[0011] Performing time series clustering analysis on the sequence of the enhanced real-time temperature local time series implicit correlation feature vectors to obtain a real-time temperature time series clustering representation feature vector;
[0012] Based on the real-time temperature time series clustering representation feature vector, a temperature compensation coefficient decoding value is generated.
[0013] According to another aspect of the present application, an attenuation compensation control system of a microwave transceiver system is provided, comprising:
[0014] A data acquisition module, used to acquire the time series of the real-time temperature of the microwave transceiver system collected by the temperature sensor;
[0015] A real-time temperature time series encoding module, used for performing time series encoding on the time series of the real-time temperature based on a local time scale to obtain a sequence of implicitly associated feature vectors of the local time series of the real-time temperature;
[0016] A saliency optimization module, used for inputting the sequence of the real-time temperature local time series implicit association feature vectors into the saliency optimization module based on the global context to obtain a sequence of enhanced real-time temperature local time series implicit association feature vectors;
[0017] A real-time temperature time series clustering analysis module, used for performing time series clustering analysis on the sequence of the enhanced real-time temperature local time series implicit correlation feature vectors to obtain a real-time temperature time series clustering representation feature vector;
[0018] The temperature compensation coefficient decoding value generation module is used to generate a temperature compensation coefficient decoding value based on the real-time temperature time series clustering representation feature vector.
[0019] The present application has at least the following technical effects: Compared with the prior art, the present application provides an attenuation compensation control method and system for a microwave transceiver system, which uses deep learning-based artificial intelligence technology to perform real-time monitoring and data analysis on the temperature of the microwave transceiver system, captures the dynamic characteristics of temperature changes within a local time scale, and uses global context clustering analysis to mine the global temperature change characteristic pattern, thereby intelligently generating a temperature compensation coefficient, thereby realizing attenuation compensation control of the microwave transceiver system, which can significantly improve the accuracy and real-time performance of the attenuation compensation, reduce signal attenuation and distortion caused by temperature changes, and ensure the stability and communication quality of the microwave transceiver system. BRIEF DESCRIPTION OF THE DRAWINGS
[0020] By describing the embodiments of the present application in more detail in conjunction with the accompanying drawings, the above and other purposes, features and advantages of the present application will become more apparent. The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation of the present application. In the accompanying drawings, the same reference numerals generally represent the same components or steps.
[0021] Figure 1 is a flow chart of an attenuation compensation control method of a microwave transceiver system according to an embodiment of the present application;
[0022] Figure 2 A system architecture diagram of an attenuation compensation control method for a microwave transceiver system according to an embodiment of the present application;
[0023] Figure 3 is a flowchart of sub-step S3 of the attenuation compensation control method of the microwave transceiver system according to an embodiment of the present application;
[0024] Figure 4 4 is a block diagram of an attenuation compensation control system of a microwave transceiver system according to an embodiment of the present application. DETAILED DESCRIPTION
[0025] Below, the exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application, and it should be understood that the present application is not limited to the exemplary embodiments described here.
[0026] As shown in this application and claims, unless the context clearly indicates an exception, the words "a", "an", "an" and / or "the" do not refer to the singular and may also include the plural. Generally speaking, the terms "include" and "comprise" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.
[0027] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, any number of different modules can be used and run on the user terminal and / or server. The modules are only illustrative, and different aspects of the system and method can use different modules.
[0028] Flowcharts are used in the present application to illustrate the operations performed by the system according to the embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed accurately in order. On the contrary, various steps may be processed in reverse order or simultaneously as required. Meanwhile, other operations may also be added to these processes, or a certain step or several steps of operations may be removed from these processes.
[0029] Below, the exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application, and it should be understood that the present application is not limited to the exemplary embodiments described here.
[0030] Traditional temperature compensation methods mainly rely on hardware design, such as automatic gain control circuits (AGC) and temperature compensation attenuators. AGC samples the output signal and feeds it back to the input to stabilize the input signal with large fluctuations, but its core part, the gain variable amplifier, often introduces nonlinear distortion. The temperature compensation attenuator achieves compensation based on the correspondence between the predefined temperature variable and the attenuation. Although it is simple and effective, its compensation effect is limited and difficult to accurately control under complex and changeable environmental conditions. Therefore, an optimized attenuation compensation control method and system for microwave transceiver systems are needed to solve the above problems.
[0031] In the technical solution of the present application, an attenuation compensation control method for a microwave transceiver system is proposed. Figure 1 The present invention is a flowchart of an attenuation compensation control method of a microwave transceiver system according to an embodiment of the present application. Figure 2 : is a system architecture diagram of the attenuation compensation control method of the microwave transceiver system according to an embodiment of the present application. Figure 1 and Figure 2As shown, the attenuation compensation control method of the microwave transceiver system according to the embodiment of the present application includes the steps of: S1, obtaining the time series of the real-time temperature of the microwave transceiver system collected by the temperature sensor; S2, performing time series encoding based on the local time scale on the time series of the real-time temperature to obtain a sequence of local time series implicitly associated feature vectors of the real-time temperature; S3, inputting the sequence of local time series implicitly associated feature vectors of the real-time temperature into a significance optimization module based on the global context to obtain a sequence of enhanced local time series implicitly associated feature vectors of the real-time temperature; S4, performing time series clustering analysis on the sequence of enhanced local time series implicitly associated feature vectors of the real-time temperature to obtain a real-time temperature time series clustering representation feature vector; S5, generating a temperature compensation coefficient decoding value based on the real-time temperature time series clustering representation feature vector.
[0032] In particular, the S1 obtains the time series of the real-time temperature of the microwave transceiver system collected by the temperature sensor. The temperature sensor is a device used to measure the temperature of the environment or an object, which can convert the temperature into an electrical signal or a digital signal for monitoring, control or recording.
[0033] In particular, the S2 performs temporal coding based on the local time scale on the time series of the real-time temperature to obtain a sequence of implicitly associated feature vectors of the local time series of the real-time temperature. In particular, in a specific example of the present application, the time series of the real-time temperature is segmented at a predetermined time scale and then passed through a sequence encoder based on the 1D_CNN model to obtain a sequence of implicitly associated feature vectors of the local time series of the real-time temperature. Considering that the time series data of the real-time temperature often contains a large number of timestamps and corresponding observations, directly processing the entire time series data may result in low computational efficiency due to the large amount of data, and it is also difficult to effectively capture subtle changes within the local time range. Therefore, in the technical solution of the present application, the time series of the real-time temperature is further segmented into multiple shorter time windows at a predetermined time scale, and then a sequence encoder based on the 1D_CNN model is used to perform temporal coding on the temperature data in each time window, and through a one-dimensional sliding convolution operation, the dynamic change characteristics of the temperature in each local time window are captured to achieve fine-grained temperature feature extraction, thereby obtaining a sequence of implicitly associated feature vectors of the local time series of the real-time temperature. Among them, the 1D_CNN model is a convolutional neural network model used to process one-dimensional data. 1D_CNN is mainly used to process sequence data, such as time series data, signal data, text data, etc.
[0034] In particular, in S3, the sequence of the real-time temperature local time series implicitly associated feature vectors is input into a saliency optimization module based on a global context to obtain a sequence of enhanced real-time temperature local time series implicitly associated feature vectors. Considering that in the time series of the real-time temperature, the temperature changes in different local time periods may have different importance, for example, the feature representation during the period of rapid temperature change may be more critical to the calculation of the compensation coefficient. Therefore, in order to make the network focus on the temperature change information that is more critical to the calculation of the temperature compensation coefficient, in the technical solution of the present application, a saliency optimization module based on a global context is introduced to perform feature enhancement processing on the sequence of the real-time temperature local time series implicitly associated feature vectors. Specifically, the saliency optimization module learns and considers the global context information of the entire sequence, and assigns weights to each real-time temperature local time series implicitly associated feature vector based on its relevance and importance, so as to highlight the key temperature change features, while suppressing irrelevant or minor features, so as to improve the pertinence and effectiveness of subsequent data analysis and processing, thereby obtaining a more refined and representative sequence of enhanced real-time temperature local time series implicitly associated feature vectors. In particular, in a specific example of the present application, such as Figure 3 As shown, the S3 includes: S31, extracting the maximum value of each real-time temperature local time series implicit association feature vector in the sequence of the real-time temperature local time series implicit association feature vector to obtain a real-time temperature time series salient feature vector composed of each maximum value; S32, extracting the average value of each real-time temperature local time series implicit association feature vector in the sequence of the real-time temperature local time series implicit association feature vector to obtain a real-time temperature time series global feature vector composed of each average value; S33, performing one-dimensional convolution encoding, nonlinear activation and linear transformation on the real-time temperature time series salient feature vector and the real-time temperature time series global feature vector respectively to obtain a real-time temperature time series salient feature context association activation feature vector and a real-time temperature time series global feature context association activation feature vector; S34, based on the real-time temperature time series salient feature context association activation feature vector and the real-time temperature time series global feature context association activation feature vector, performing weighted enhancement processing on the sequence of the real-time temperature local time series implicit association feature vectors to obtain the sequence of enhanced real-time temperature local time series implicit association feature vectors.
[0035] Specifically, the S31 and S32 extract the maximum value of each real-time temperature local time series implicit correlation feature vector in the sequence of the real-time temperature local time series implicit correlation feature vector to obtain a real-time temperature time series prominent feature vector composed of each maximum value; and extract the average value of each real-time temperature local time series implicit correlation feature vector in the sequence of the real-time temperature local time series implicit correlation feature vector to obtain a real-time temperature time series global feature vector composed of each average value. The real-time temperature time series prominent feature vector represents the key features in each local time series feature vector, which helps to capture important information in the data; the real-time temperature time series global feature vector represents the average feature of the entire sequence, which helps to understand the features of the data globally.
[0036] Specifically, the S33 performs one-dimensional convolution encoding, nonlinear activation and linear transformation on the real-time temperature time series salient feature vector and the real-time temperature time series global feature vector to obtain the real-time temperature time series salient feature context-associated activation feature vector and the real-time temperature time series global feature context-associated activation feature vector. Specifically, the real-time temperature time series salient feature vector and the real-time temperature time series global feature vector are respectively subjected to one-dimensional convolution encoding to capture local patterns and features in the sequence; after the convolution operation, a nonlinear activation function (such as ReLU, Sigmoid, etc.) is applied to introduce nonlinear characteristics; after the nonlinear activation, a linear transformation (such as a fully connected layer) is performed to map the convolved features to a higher dimensional space.
[0037] Specifically, the S34 performs weighted enhancement processing on the sequence of the real-time temperature local time series implicit association feature vectors based on the real-time temperature time series prominent feature context associated activation feature vector and the real-time temperature time series global feature context associated activation feature vector to obtain the sequence of enhanced real-time temperature local time series implicit association feature vectors. Specifically, in an embodiment of the present application, first, the real-time temperature time series salient feature context associated activation feature vector and the real-time temperature time series global feature context associated activation feature vector are calculated by adding the real-time temperature time series salient-global feature context associated activation feature vector by position to obtain the real-time temperature time series salient-global feature context associated activation feature vector; then, the real-time temperature time series salient-global feature context associated activation feature vector is subjected to nonlinear activation based on the tanh activation function and nonlinear activation based on the sigmoid activation function to obtain a first activation result and a second activation result, and the first activation result and the second activation result are point multiplied by position to obtain a real-time temperature time series salient-global feature context associated weight feature vector; then, the eigenvalues of each position in the real-time temperature time series salient-global feature context associated weight feature vector are used as weights, and the sequence of the real-time temperature local time series implicit associated feature vectors is point multiplied by position and then added to the sequence of the real-time temperature local time series implicit associated feature vectors by position to obtain the sequence of the enhanced real-time temperature local time series implicit associated feature vectors.
[0038] In summary, in the above embodiment, the sequence of the real-time temperature local time series implicit association feature vectors is input into the global context-based significance optimization module to obtain a sequence of enhanced real-time temperature local time series implicit association feature vectors, including: processing the sequence of the real-time temperature local time series implicit association feature vectors with the following significance optimization formula to obtain the sequence of enhanced real-time temperature local time series implicit association feature vectors, wherein the significance optimization formula is:
[0039]
[0040]
[0041]
[0042]
[0043]
[0044] in, is the sequence of implicitly associated feature vectors of the local time series of real-time temperature, is the global characteristic vector of real-time temperature series, is the real-time temperature time series salient feature vector, It means taking the average value, Indicates taking the maximum value, represents a one-dimensional convolution operation, express Activation function, and are the first weight matrix and the second weight matrix for linear transformation, and They are respectively the real-time temperature time series global feature context associated activation feature vector and the real-time temperature time series salient feature context associated activation feature vector, It means the sum of corresponding elements. express function, express Activation function, represents dot product, It is a sequence of implicitly associated feature vectors of the enhanced real-time temperature local time series.
[0045] Specifically, in other specific examples of the present application, the sequence of the real-time temperature local time series implicitly associated feature vectors can also be input into the global context-based significance optimization module in other ways to obtain a sequence of enhanced real-time temperature local time series implicitly associated feature vectors, for example: input the sequence of the real-time temperature local time series implicitly associated feature vectors; input the sequence of the real-time temperature local time series implicitly associated feature vectors into the global context significance optimization module; in the optimization module, integrate the global context information with the local time series data to improve the representation ability and correlation of the feature vector; through the global context significance optimization module, enhance the sequence of the real-time temperature local time series implicitly associated feature vectors; to obtain the sequence of enhanced real-time temperature local time series implicitly associated feature vectors.
[0046] In particular, the S4 performs a time series clustering analysis on the sequence of the enhanced real-time temperature local time series implicitly associated feature vectors to obtain the real-time temperature time series clustering representation feature vector. In particular, in a specific example of the present application, the sequence of the enhanced real-time temperature local time series implicitly associated feature vectors is input into the feature distribution reverse mask clustering analysis engine to obtain the real-time temperature time series clustering representation feature vector. Specifically, in order to dig out the global pattern and law of temperature change, it is necessary to further perform feature integration on the sequence of the enhanced real-time temperature local time series implicitly associated feature vectors. In the technical solution of the present application, in order to further realize the purification and optimization of features in the process of feature integration, a feature distribution reverse mask clustering analysis engine is introduced to perform feature pattern recognition and clustering integration on the sequence of the enhanced real-time temperature local time series implicitly associated feature vectors to obtain the real-time temperature time series clustering representation feature vector. Among them, the feature distribution reverse mask clustering analysis engine evaluates the correlation between each enhanced real-time temperature local time series implicitly associated feature vector and the overall feature of the full time domain based on the distribution characteristics of each enhanced real-time temperature local time series implicitly associated feature vector, identifies unnecessary elements therein, and enhances unnecessary feature information through a reverse mask mechanism, and then calculates the difference between the sequence of the enhanced real-time temperature local time series implicitly associated feature vector and the unnecessary feature information to filter out irrelevant features in the sequence of the enhanced real-time temperature local time series implicitly associated feature vector, thereby achieving feature purification and optimization. Through this clustering method, not only can the global pattern and law of temperature change be excavated, but also the discrimination and expression ability of the feature vector can be effectively enhanced to support more accurate temperature compensation control.
[0047] In an embodiment of the present application, the process of inputting the sequence of the enhanced real-time temperature local time series implicitly associated feature vectors into the feature distribution reverse mask clustering analysis engine to obtain the real-time temperature time series cluster representation feature vector includes: clustering the sequence of the enhanced real-time temperature local time series implicitly associated feature vectors to obtain a cluster center vector; calculating the semantic correlation coefficient between each enhanced real-time temperature local time series implicitly associated feature vector in the sequence of the enhanced real-time temperature local time series implicitly associated feature vectors and the cluster center vector to obtain a sequence of semantic correlation coefficients; taking the inverse of each semantic correlation coefficient in the sequence of semantic correlation coefficients to obtain a sequence of semantic anti-correlation coefficients; and normalizing the sequence of semantic anti-correlation coefficients using a Sigmoid function. The method comprises the following steps: obtaining a sequence of semantic anti-correlation weight coefficients; taking each semantic anti-correlation weight coefficient in the sequence of semantic anti-correlation weight coefficients as a weight, weighting each enhanced real-time temperature local timing implicit association feature vector in the sequence of enhanced real-time temperature local timing implicit association feature vectors to obtain a sequence of suppressed real-time temperature local timing implicit association feature vectors; calculating the positional difference between the sequence of enhanced real-time temperature local timing implicit association feature vectors and the sequence of suppressed real-time temperature local timing implicit association feature vectors to obtain a sequence of optimized real-time temperature local timing implicit association feature vectors; calculating the positional mean vector of the sequence of optimized real-time temperature local timing implicit association feature vectors to obtain the real-time temperature timing cluster representation feature vector.
[0048] Among them, calculating the semantic correlation coefficient between each enhanced real-time temperature local time series implicit association feature vector in the sequence of the enhanced real-time temperature local time series implicit association feature vector and the cluster center vector to obtain a sequence of semantic correlation coefficients, including: calculating the vector product between the transposed vector of the enhanced real-time temperature local time series implicit association feature vector and the cluster center vector to obtain a semantic correlation factor; calculating the product between the length of the enhanced real-time temperature local time series implicit association feature vector and the length of the cluster center vector to obtain a scale correlation factor; dividing the semantic correlation factor by the scale correlation factor to obtain the semantic correlation coefficient.
[0049] In summary, in the above embodiment, the sequence of the enhanced real-time temperature local time series implicitly associated feature vectors is input into the feature distribution reverse mask clustering analysis engine to obtain the real-time temperature time series cluster representation feature vector, including: processing the sequence of the enhanced real-time temperature local time series implicitly associated feature vectors with the following reverse mask aggregation formula to obtain the real-time temperature time series cluster representation feature vector, wherein the reverse mask aggregation formula is:
[0050]
[0051]
[0052]
[0053]
[0054]
[0055]
[0056]
[0057]
[0058] in, is the sequence of implicitly associated feature vectors of the enhanced real-time temperature local time series, , , and are respectively the first enhanced real-time temperature local time series implicit association feature vector, the second enhanced real-time temperature local time series implicit association feature vector, the i-th enhanced real-time temperature local time series implicit association feature vector and the N-th enhanced real-time temperature local time series implicit association feature vector in the sequence of the enhanced real-time temperature local time series implicit association feature vector, The value of is the number of enhanced real-time temperature local time series implicit correlation feature vectors in the sequence of enhanced real-time temperature local time series implicit correlation feature vectors, represents the transpose of the eigenvector, is the cluster center vector, represents the length of the vector, Indicates the The semantic correlation coefficient between the implicit association feature vector of the enhanced real-time temperature local time series and the cluster center vector, For the The semantic anti-correlation coefficient, For the semantic anti-correlation weight coefficients, represents an exponential function with a natural constant as base, is a sequence of implicitly correlated eigenvectors that suppress the local temporal sequence of real-time temperature. , , and are respectively the first real-time temperature local timing implicit association feature vector, the second real-time temperature local timing implicit association feature vector, the i-th real-time temperature local timing implicit association feature vector and the N-th real-time temperature local timing implicit association feature vector in the sequence of real-time temperature local timing implicit association feature vectors, is a sequence of implicitly associated feature vectors that optimizes the local timing of real-time temperature, , , and They are the first optimized real-time temperature local timing implicit correlation feature vector, the second optimized real-time temperature local timing implicit correlation feature vector, the i-th optimized real-time temperature local timing implicit correlation feature vector and the N-th optimized real-time temperature local timing implicit correlation feature vector, A feature vector is represented by clustering of the real-time temperature time series.
[0059] In particular, the S5 generates a temperature compensation coefficient decoded value based on the real-time temperature time series cluster representation feature vector. In particular, in a specific example of the present application, the real-time temperature time series cluster representation feature vector is input into a temperature compensation coefficient generator based on a decoder to obtain the temperature compensation coefficient decoded value. Specifically, in the technical solution of the present application, the temperature compensation coefficient generator based on the decoder can use the feature information in the real-time temperature time series cluster representation feature vector to generate a temperature compensation coefficient decoded value matching the current temperature state through a decoding process. In addition, the decoder is trained through back propagation and optimization algorithms to minimize the error between the predicted temperature compensation coefficient and the actual demand, ensuring that the generated temperature compensation coefficient has high accuracy and adaptability. In practical applications, the temperature compensation coefficient decoded value will be used in real time to adjust the attenuation parameters of the microwave transceiver system to offset the gain fluctuation caused by temperature changes. Through this intelligent adaptive control, the signal attenuation and distortion caused by temperature changes can be dynamically compensated, thereby maintaining the stability and communication quality of the microwave transceiver system, especially in extreme or rapidly changing temperature environments, and its advantages are more obvious.
[0060] In the technical solution of the present application, the sequence of enhanced real-time temperature local timing implicit correlation feature vectors expresses the one-dimensional local timing correlation characteristics of the real-time temperature value of the microwave transceiver system. Therefore, after performing significance optimization based on global context and feature distribution reverse mask clustering, the real-time temperature timing clustering representation feature vector obtained will also have the prior-posteriori decoding regression causal association missing based on timing feature distribution enhancement and reverse mask clustering relative to the sequence of enhanced real-time temperature local timing implicit correlation feature vectors, resulting in outlier class inference mapping deviation, thereby affecting the accuracy of the temperature compensation coefficient decoding value obtained by the temperature compensation coefficient generator based on the decoder input of the real-time temperature timing clustering representation feature vector.
[0061] Preferably, inputting the real-time temperature time series cluster representation feature vector into a decoder-based temperature compensation coefficient generator to obtain the temperature compensation coefficient decoded value comprises:
[0062] The real-time temperature time series clustering representation feature vector is subjected to feature convergence optimization using the following formula to obtain an optimized real-time temperature time series clustering representation feature vector, wherein the formula is:
[0063]
[0064]
[0065] in, is the real-time temperature time series clustering representation feature vector, is the unit eigenvector, is the weight of the hyperparameter, is the first feature vector of the real-time temperature time series cluster representation eigenvalues, represents the real-time temperature time series clustering distribution representation value, The power function that calculates the eigenvalues of each position in the eigenvector is exponentially represented by the distribution characterization value of the real-time temperature time series cluster representation, It means point multiplication by position. It means to make a difference by position. It means adding by position. is the optimized real-time temperature time series clustering representation feature vector, is the characteristic mean of the characteristic vector represented by the real-time temperature time series clustering, and They are respectively the maximum eigenvalue and the minimum eigenvalue of the eigenvalue vector represented by the real-time temperature time series clustering.
[0066] The optimized real-time temperature time series clustering representation feature vector is input into the decoder-based temperature compensation coefficient generator to obtain the temperature compensation coefficient decoding value.
[0067] That is, the eigenvalue-based probability information distribution planning of the real-time temperature time series clustering representation feature vector is performed through the Bernoulli probability modulation distribution of the real-time temperature time series clustering representation feature vector relative to the eigenvalue distribution, and the probability reverse mapping of the probability characteristics of the real-time temperature time series clustering representation feature vector as a whole is used as an extended coverage of the set mapping space of the real-time temperature time series clustering representation feature vector to independently understand the interaction path between the intuitive probability information distribution and the abstract probability space mapping of the real-time temperature time series clustering representation feature vector, so as to improve the accuracy of the temperature compensation coefficient decoding value obtained by the temperature compensation coefficient generator based on the decoder input of the optimized real-time temperature time series clustering representation feature vector by avoiding the counterfactual reasoning mapping of the outlier feature distribution of the real-time temperature time series clustering representation feature vector to the decoding probability.
[0068] In summary, the attenuation compensation control method of the microwave transceiver system according to the embodiment of the present application is explained, which uses artificial intelligence technology based on deep learning to monitor and analyze the temperature of the microwave transceiver system in real time, captures the dynamic characteristics of temperature changes in the local time scale, and mines the global change characteristic pattern of temperature through global context clustering analysis, so as to intelligently generate temperature compensation coefficients, thereby realizing attenuation compensation control of the microwave transceiver system. In this way, the accuracy and real-time performance of attenuation compensation can be significantly improved, the signal attenuation and distortion caused by temperature changes can be reduced, and the stability and communication quality of the microwave transceiver system can be ensured.
[0069] Furthermore, an attenuation compensation control system of a microwave transceiver system is also provided.
[0070] Figure 4 FIG. 1 is a block diagram of an attenuation compensation control system of a microwave transceiver system according to an embodiment of the present application. Figure 4As shown, the attenuation compensation control system 300 of the microwave transceiver system according to the embodiment of the present application includes: a data acquisition module 310, which is used to acquire the time series of the real-time temperature of the microwave transceiver system collected by the temperature sensor; a real-time temperature time series encoding module 320, which is used to perform time series encoding based on the local time scale on the time series of the real-time temperature to obtain a sequence of real-time temperature local time series implicit correlation feature vectors; a significance optimization module 330, which is used to input the sequence of real-time temperature local time series implicit correlation feature vectors into a significance optimization module based on the global context to obtain a sequence of enhanced real-time temperature local time series implicit correlation feature vectors; a real-time temperature time series clustering analysis module 340, which is used to perform time series clustering analysis on the sequence of enhanced real-time temperature local time series implicit correlation feature vectors to obtain a real-time temperature time series clustering representation feature vector; a temperature compensation coefficient decoding value generation module 350, which is used to generate a temperature compensation coefficient decoding value based on the real-time temperature time series clustering representation feature vector.
[0071] As described above, the attenuation compensation control system 300 of the microwave transceiver system according to the embodiment of the present application can be implemented in various wireless terminals, such as a server with an attenuation compensation control algorithm of the microwave transceiver system. In a possible implementation, the attenuation compensation control system 300 of the microwave transceiver system according to the embodiment of the present application can be integrated into the wireless terminal as a software module and / or a hardware module. For example, the attenuation compensation control system 300 of the microwave transceiver system can be a software module in the operating system of the wireless terminal, or can be an application developed for the wireless terminal; of course, the attenuation compensation control system 300 of the microwave transceiver system can also be one of the many hardware modules of the wireless terminal.
[0072] Alternatively, in another example, the attenuation compensation control system 300 of the microwave transceiver system and the wireless terminal may also be separate devices, and the attenuation compensation control system 300 of the microwave transceiver system may be connected to the wireless terminal via a wired and / or wireless network, and transmit interactive information in accordance with an agreed data format. The various embodiments of the present disclosure have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Without departing from the scope and spirit of the described embodiments, many modifications and changes are obvious to those of ordinary skill in the art. The choice of terms used herein is intended to best explain the principles of the embodiments, practical applications, or improvements to the technology in the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein.
Claims
1. An attenuation compensation control method for a microwave transceiver system, characterized in that: include: Obtaining a time series of the real-time temperature of the microwave transceiver system collected by a temperature sensor; Performing time series encoding based on the local time scale on the time series of the real-time temperature to obtain a sequence of implicitly associated feature vectors of the local time series of the real-time temperature; Inputting the sequence of the real-time temperature local time series implicit association feature vectors into a global context-based saliency optimization module to obtain a sequence of enhanced real-time temperature local time series implicit association feature vectors; Performing time series clustering analysis on the sequence of the enhanced real-time temperature local time series implicit correlation feature vectors to obtain a real-time temperature time series clustering representation feature vector; Based on the real-time temperature time series cluster representation feature vector, a temperature compensation coefficient decoding value is generated, and the temperature compensation coefficient decoding value is used to adjust the attenuation parameter of the microwave transceiver system in real time to offset the gain fluctuation caused by temperature change; Performing temporal coding based on a local time scale on the time series of the real-time temperature to obtain a sequence of implicitly associated feature vectors of the local time series of the real-time temperature includes: The time series of the real-time temperature is divided into predetermined time scales and then passed through a sequence encoder based on a 1D_CNN model to obtain a sequence of implicitly associated feature vectors of the local time series of the real-time temperature; Inputting the sequence of the real-time temperature local time series implicit association feature vectors into a global context-based saliency optimization module to obtain a sequence of enhanced real-time temperature local time series implicit association feature vectors, including: Extracting the maximum value of each real-time temperature local time series implicit correlation feature vector in the sequence of the real-time temperature local time series implicit correlation feature vector to obtain a real-time temperature time series prominent feature vector composed of each maximum value; Extracting the average value of each real-time temperature local time series implicit correlation feature vector in the sequence of the real-time temperature local time series implicit correlation feature vector to obtain a real-time temperature time series global feature vector composed of each average value; Respectively performing one-dimensional convolution encoding, nonlinear activation and linear transformation on the real-time temperature time series salient feature vector and the real-time temperature time series global feature vector to obtain a real-time temperature time series salient feature context-associated activation feature vector and a real-time temperature time series global feature context-associated activation feature vector; Based on the real-time temperature time series prominent feature context associated activation feature vector and the real-time temperature time series global feature context associated activation feature vector, weighted enhancement processing is performed on the sequence of the real-time temperature local time series implicit association feature vectors to obtain the sequence of enhanced real-time temperature local time series implicit association feature vectors; Based on the real-time temperature time series prominent feature context associated activation feature vector and the real-time temperature time series global feature context associated activation feature vector, a weighted enhancement process is performed on the sequence of the real-time temperature local time series implicit association feature vectors to obtain the sequence of the enhanced real-time temperature local time series implicit association feature vectors, including: Calculate the positional addition of the real-time temperature time series salient feature context associated activation feature vector and the real-time temperature time series global feature context associated activation feature vector to obtain a real-time temperature time series salient-global feature context associated activation feature vector; The real-time temperature time series prominence-global feature context associated activation feature vector is respectively activated by a nonlinear activation based on a tanh activation function and a nonlinear activation based on a sigmoid activation function to obtain a first activation result and a second activation result, and the first activation result and the second activation result are multiplied by position points to obtain a real-time temperature time series prominence-global feature context associated weight feature vector; Taking the feature values of each position in the real-time temperature time series prominent-global feature context association weight feature vector as the weight, multiplying the sequence of the real-time temperature local time series implicit association feature vector by position and then adding the sequence of the real-time temperature local time series implicit association feature vector by position to obtain the sequence of the enhanced real-time temperature local time series implicit association feature vector; Performing a time series clustering analysis on the sequence of the enhanced real-time temperature local time series implicitly associated feature vectors to obtain a real-time temperature time series clustering representation feature vector, including: Inputting the sequence of the enhanced real-time temperature local time series implicitly associated feature vectors into a feature distribution reverse mask clustering analysis engine to obtain the real-time temperature time series clustering representation feature vector; Inputting the sequence of the enhanced real-time temperature local time series implicit association feature vectors into the feature distribution reverse mask clustering analysis engine to obtain the real-time temperature time series cluster representation feature vector, including: Clustering the sequence of implicitly associated feature vectors of the enhanced real-time temperature local time series to obtain a cluster center vector; Calculating the semantic correlation coefficient between each enhanced real-time temperature local time series implicit correlation feature vector in the sequence of enhanced real-time temperature local time series implicit correlation feature vectors and the cluster center vector to obtain a sequence of semantic correlation coefficients; Taking the reciprocal of each semantic correlation coefficient in the sequence of semantic correlation coefficients to obtain a sequence of semantic anti-correlation coefficients; Using a Sigmoid function to normalize the sequence of semantic anti-correlation coefficients to obtain a sequence of semantic anti-correlation weight coefficients; Using each semantic anti-correlation weight coefficient in the sequence of semantic anti-correlation weight coefficients as a weight, weighting each enhanced real-time temperature local time series implicit association feature vector in the sequence of enhanced real-time temperature local time series implicit association feature vectors to obtain a sequence of suppressed real-time temperature local time series implicit association feature vectors; Calculating the positional difference between the sequence of the enhanced real-time temperature local time series implicitly associated feature vectors and the sequence of the suppressed real-time temperature local time series implicitly associated feature vectors to obtain a sequence of the optimized real-time temperature local time series implicitly associated feature vectors; The position-wise mean vector of the sequence of implicitly associated feature vectors of the optimized real-time temperature local time series is calculated to obtain the real-time temperature time series cluster representation feature vector.
2. The attenuation compensation control method of a microwave transceiver system according to claim 1, characterized in that: Calculating the semantic correlation coefficient between each enhanced real-time temperature local time series implicit correlation feature vector in the sequence of enhanced real-time temperature local time series implicit correlation feature vectors and the cluster center vector to obtain a sequence of semantic correlation coefficients, including: Calculating the vector product between the transposed vector of the enhanced real-time temperature local time series implicit association feature vector and the cluster center vector to obtain a semantic association factor; Calculating the product of the length of the enhanced real-time temperature local time series implicit correlation feature vector and the length of the cluster center vector to obtain a scale correlation factor; The semantic relevance factor is divided by the scale relevance factor to obtain the semantic relevance coefficient.
3. The attenuation compensation control method of a microwave transceiver system according to claim 2, characterized in that: Based on the real-time temperature time series cluster representation feature vector, a temperature compensation coefficient decoding value is generated, including: The real-time temperature time series clustering representation feature vector is input into a decoder-based temperature compensation coefficient generator to obtain the temperature compensation coefficient decoding value.
4. An attenuation compensation control system for a microwave transceiver system, used to execute the attenuation compensation control method for a microwave transceiver system as claimed in claim 1, characterized in that: include: A data acquisition module, used to acquire the time series of the real-time temperature of the microwave transceiver system collected by the temperature sensor; A real-time temperature time series encoding module, used for performing time series encoding on the time series of the real-time temperature based on a local time scale to obtain a sequence of implicitly associated feature vectors of the local time series of the real-time temperature; A saliency optimization module, used for inputting the sequence of the real-time temperature local time series implicit association feature vectors into the saliency optimization module based on the global context to obtain a sequence of enhanced real-time temperature local time series implicit association feature vectors; A real-time temperature time series clustering analysis module, used for performing time series clustering analysis on the sequence of the enhanced real-time temperature local time series implicit correlation feature vectors to obtain a real-time temperature time series clustering representation feature vector; The system also includes: a temperature compensation coefficient decoding value generation module, which is used to generate a temperature compensation coefficient decoding value based on the real-time temperature time series cluster representation feature vector. The temperature compensation coefficient decoding value will be used in real time to adjust the attenuation parameter of the microwave transceiver system to offset the gain fluctuation caused by temperature changes.
Citation Information
Patent Citations
Receiving level calibration method of receiver and receiving level calibration system thereof
CN106160889A
Ultra-wideband large dynamic receiving system based on photon nonlinear compensation
CN117675026A
Method and apparatus for improving data reception performance in communication system
CN118383000A
Microwave radio frequency system's digital compensating circuit of radio frequency gain
CN208028858U
Novel millimeter wave large-dynamic high-linearity logarithmic detector
CN215641523U
