Power amplifier operating characteristic simulation method and device, computer device and medium

Abstract

The present application relates to the technical field of power amplifier characteristic simulation, and discloses a power amplifier operating characteristic simulation method, device, computer equipment and medium, the method comprises the following steps: obtaining a plurality of different input data of a power amplifier, intercepting time sequence data of different lengths of continuous time periods, and dividing the time sequence data into training data and test data; training a neural network based on an attention mechanism based on the training data to obtain a power amplifier nonlinear characteristic model; testing the power amplifier nonlinear characteristic model based on the test data to obtain a power amplifier operating characteristic simulation model; obtaining real-time input data of the power amplifier, and obtaining a power amplifier operating characteristic simulation output result based on the real-time input data and the power amplifier operating characteristic simulation model, the present application significantly improves the analytical ability of the complex relationship between the input signal and the output signal, greatly improving the precision and efficiency of the power amplifier simulation.

Description

Technical Field

[0001] This invention relates to the field of power amplifier characteristic simulation technology, and more specifically to methods, apparatus, computer equipment, and media for simulating the operating characteristics of power amplifiers. Background Technology

[0002] Power amplifiers are widely used in communications, audio, and signal processing, and their performance directly affects the overall efficiency and signal quality of the system. In practical applications, power amplifiers often operate in the nonlinear region, where their output characteristics are complex and difficult to accurately simulate using traditional linear models. Traditional simulation methods mainly rely on physical models and empirical formulas, which face many challenges in handling nonlinear characteristics, easily leading to inaccurate simulation results and thus affecting system performance. As the performance requirements for power amplifiers continue to increase, traditional physical models and empirical formulas are no longer sufficient to meet the simulation needs of their complex characteristics.

[0003] With the rapid development of computer technology, especially the rise of artificial intelligence and deep learning, researchers have begun to explore how to use these emerging technologies to address the shortcomings of traditional analog methods. However, existing deep learning methods still have certain limitations in practical applications, particularly in processing variable-length input signals and real-time inference, where problems such as insufficient accuracy and low efficiency in the nonlinear region of the power amplifier due to a single input signal exist. Summary of the Invention

[0004] In view of this, the present invention provides a method, apparatus, computer equipment and medium for simulating the operating characteristics of a power amplifier, in order to solve the problems of insufficient simulation accuracy and low efficiency in the nonlinear region of power amplifiers in the prior art.

[0005] In a first aspect, the present invention provides a method for simulating the operating characteristics of a power amplifier, the method comprising:

[0006] Acquire multiple different input data from the power amplifier;

[0007] Time series data of different lengths are extracted from multiple different input data, and the time series data is divided into training data and test data.

[0008] The attention-based neural network is trained based on the training data to obtain a model with nonlinear characteristics of a power amplifier.

[0009] The power amplifier nonlinear characteristic model was tested based on the test data to obtain the power amplifier operating characteristic simulation model after the test was completed.

[0010] The system acquires real-time input data from the power amplifier and obtains the simulated output results of the power amplifier's operating characteristics based on the real-time input data and the power amplifier's operating characteristic simulation model.

[0011] The power amplifier operating characteristic simulation method provided by this invention accurately captures the complex dynamic characteristics of the power amplifier in the nonlinear region by extracting and analyzing the time-series data features of the input signal over a continuous time period, significantly improving the analytical capability of the complex relationship between the input and output signals. Automated feature extraction and modeling are achieved through deep learning algorithms, and the extracted features better reflect the nonlinear characteristics of the power amplifier, greatly improving the accuracy and efficiency of power amplifier simulation. This solves the problems of insufficient accuracy and low efficiency in existing technologies for simulating power amplifiers in the nonlinear region.

[0012] In one alternative implementation, extracting time-series data of different lengths from multiple different input data includes:

[0013] Select sliding windows of different lengths and use these windows to extract time series data of different continuous time periods from multiple input data.

[0014] The power amplifier operating characteristic simulation method provided by this invention selects sliding windows of different lengths and uses sliding windows of different lengths to extract time series data of different continuous time periods from multiple input data. This achieves the purpose of extracting time series data of adaptive length, providing conditions for subsequent training of the model using time series data. The time series data of adaptive length is suitable for modeling the characteristics of different types of power amplifiers and has low dependence on data, and can be flexibly adjusted according to the operating characteristics of different amplifiers.

[0015] In one alternative implementation, the attention-based neural network includes a Masked CNN module, a BiLSTM module, and a Length-Aware Attention module.

[0016] Training an attention-based neural network using training data yields a model with nonlinear power amplifier characteristics, including:

[0017] The training data is input into the Masked CNN module for feature extraction and local feature fusion to obtain the fused features;

[0018] The BiLSTM module was used to perform time-series feature analysis on the fused features to obtain the nonlinear characteristics of the power amplifier.

[0019] The Length-Aware Attention module is used to focus on the nonlinear characteristics of the power amplifier and output the training results of the nonlinear characteristics of the power amplifier. The neural network that outputs the training results of the nonlinear characteristics of the power amplifier is used as a model with the nonlinear characteristics of the power amplifier.

[0020] In one alternative implementation, the formula for inputting training data into the Masked CNN module for feature extraction and local feature fusion is as follows:

[0021] H cnn =CNN(x)⊙mask;

[0022] Where CNN(x) is the output obtained by passing the pre-processed signal through the CNN network, mask is the masking operation used to filter the input features, and it is related to the effective output length, H cnn This is the final output of the Masked CNN module;

[0023] The formula for performing temporal feature analysis on the fused features using the BiLSTM module is as follows:

[0024]

[0025] Where, α i Let exp(a) be the attention coefficient. i ) for a i The applied exponential function is used to convert score values ​​into positive numbers and amplify larger scores, mask. i Here, h is the masking function, T is the total length of the sequence or the number of time steps, and h is the time step. i For the fused features, a i Let be the eigenvalue, i be the current position in the sequence being calculated, and j be the position in the sequence that is traversed during the summation process of the formula.

[0026] The power amplifier operating characteristic simulation method provided by this invention inputs training data into a Masked CNN module for feature extraction and local feature fusion to obtain fused features; a BiLSTM module is used to perform temporal feature analysis on the fused features to obtain the power amplifier nonlinear features; a Length-Aware Attention module is used to focus on the power amplifier nonlinear features and output the power amplifier nonlinear characteristic training results. The neural network outputting the power amplifier nonlinear characteristic training results is used as a model with power amplifier nonlinear characteristics. The method automatically processes massive amounts of data through deep learning algorithms, reducing manual intervention and the use of empirical formulas, and improving the efficiency of model training and inference. The feature processing through the Masked CNN module, BiLSTM module, and Length-Aware Attention module significantly improves the simulation accuracy of the power amplifier nonlinear region characteristics, enabling it to better adapt to complex signal environments and reduce the errors of traditional models under extreme conditions.

[0027] In one alternative implementation, training the attention-based neural network based on training data further includes:

[0028] The backpropagation algorithm and Adam optimizer are used to optimize the parameters and minimize the loss function of a model with nonlinear characteristics of a power amplifier.

[0029] In one alternative implementation, the parameter optimization and loss function minimization of the model with power amplifier nonlinear characteristics using the backpropagation algorithm and the Adam optimizer includes:

[0030] The parameter optimization formula for the Masked CNN module in the backpropagation algorithm is as follows:

[0031]

[0032] The parameter optimization formula for the Length-Aware Attention module is as follows:

[0033]

[0034] in, This represents the calculated loss. This represents partial derivative operations;

[0035] The formula for the loss function is as follows:

[0036]

[0037] Where smoothL1(x) represents the loss function, x=|ytrue-ypred|, which represents the absolute value of the difference between the predicted value ypred and the true value ytrue, and otherwise represents the case other than |x|<1.

[0038] The power amplifier operating characteristic simulation method provided by this invention calculates the gradient of the loss function with respect to the weights of each layer in a neural network through backpropagation, thereby guiding the update of the weights. This enables the neural network to learn the mapping relationship between input data and output data, and realizes the optimization of model parameters and model adjustment of the nonlinear characteristics of the power amplifier.

[0039] In one optional implementation, the power amplifier operating characteristic simulation method further includes: acquiring the actual output result corresponding to the real-time input data, and comparing the actual output result with the simulated output result to verify the simulation accuracy of the power amplifier operating characteristic simulation model.

[0040] The power amplifier operating characteristic simulation method provided by this invention obtains the actual output result corresponding to the real-time input data, compares the actual output result with the simulated output result, and achieves the purpose of verifying the simulation accuracy of the power amplifier operating characteristic simulation model, thus providing conditions for improving the simulation accuracy of the model.

[0041] In a second aspect, the present invention provides a power amplifier operating characteristic simulation device, the device comprising:

[0042] The input data acquisition module is used to acquire multiple different input data from the power amplifier;

[0043] The training data extraction module is used to extract time series data of different lengths from multiple different input data, and divide the time series data into training data and test data.

[0044] The training module is used to train the attention-based neural network based on training data to obtain a model with nonlinear characteristics of a power amplifier.

[0045] The testing module is used to test the power amplifier nonlinear characteristic model based on the test data to obtain a power amplifier operating characteristic simulation model after the test is completed.

[0046] The simulation module is used to acquire real-time input data of the power amplifier and obtain simulation output results of the nonlinear operating characteristics of the power amplifier based on the real-time input data and the simulation model of the power amplifier's operating characteristics.

[0047] Thirdly, the present invention provides a computer device, comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the computer instructions to perform the power amplifier operating characteristic simulation method of the first aspect or any corresponding embodiment described above.

[0048] Fourthly, the present invention provides a computer-readable storage medium storing computer instructions for causing a computer to execute the power amplifier operating characteristic simulation method of the first aspect or any corresponding embodiment thereof.

[0049] Fifthly, the present invention provides a computer program product, including computer instructions for causing a computer to execute the power amplifier operating characteristic simulation method of the first aspect or any corresponding embodiment thereof. Attached Figure Description

[0050] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0051] Figure 1 This is a flowchart illustrating a method for simulating the operating characteristics of a power amplifier according to an embodiment of the present invention;

[0052] Figure 2 This is a flowchart illustrating another method for simulating the operating characteristics of a power amplifier according to an embodiment of the present invention;

[0053] Figure 3 This is a flowchart illustrating another method for simulating the operating characteristics of a power amplifier according to an embodiment of the present invention;

[0054] Figure 4 This is a schematic diagram of another neural network structure based on an attention mechanism according to an embodiment of the present invention;

[0055] Figure 5 This is a schematic diagram of the structure of a power amplifier according to an embodiment of the present invention;

[0056] Figure 6 The diagram shows the effect on an online test set using the power amplifier operating characteristic simulation method according to an embodiment of the present invention;

[0057] Figure 7 This is a structural block diagram of a power amplifier operating characteristic simulation device according to an embodiment of the present invention;

[0058] Figure 8 This is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. Detailed Implementation

[0059] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0060] Deep learning algorithms can automatically learn complex features from data without manually defining rules, thus excelling in capturing nonlinear characteristics. By constructing deep learning-based models, the complex relationships between input and output signals can be effectively extracted, thereby achieving accurate simulation of amplifier operating characteristics. This invention provides a neural network based on an attention mechanism, specifically a Masked CNN + BiLSTM + Length-Aware Attention neural network. This network achieves automated feature extraction and modeling, significantly improving the accuracy and efficiency of power amplifier simulation.

[0061] According to an embodiment of the present invention, a method for simulating the operating characteristics of a power amplifier is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0062] This embodiment provides a method for simulating the operating characteristics of a power amplifier, which can be used in computer terminals such as central processing units and servers. Figure 1 This is a flowchart of a power amplifier operating characteristic simulation method according to an embodiment of the present invention, such as... Figure 1 As shown, the process includes the following steps:

[0063] Step S101: Acquire multiple different input data from the power amplifier.

[0064] Specifically, the structural diagram of the power amplifier is as follows: Figure 5As shown, the power amplifier in this embodiment is selected as a radio frequency (RF) amplifier, including capacitors C1, C2, and C6, comparator U1, inductor L2, and resistor B1. One end of capacitor C2 is connected to the data input terminal J1 (i.e., RFInput), and the other end of capacitor C2 is connected to the input terminal of comparator U1. The output terminal of comparator U1 is connected to one end of capacitor C6 and one end of inductor L2. The other end of inductor L2 is connected to one end of resistor B1 and one end of capacitor C1. The other end of capacitor C1 is grounded, and the other end of resistor B1 is connected to an external voltage source J3 (i.e., V). DD The other end of capacitor C6 is connected to the data output terminal J2 (i.e., RFOutput). Backside paddle refers to a structure used for heat dissipation in integrated circuit (IC) packages. It is a metal area located at the bottom of the package to enhance thermal conductivity.

[0065] Input and output data of the power amplifier were collected through multiple experiments (approximately 80,000 data points were collected in this embodiment). Data cleaning was used to remove data where the power amplifier was operating in the linear region, ensuring the quality of subsequent training and testing data. After data cleaning, scatter plot analysis, statistical characteristic analysis, and numerical correlation analysis were performed to further refine the data and provide a basis for the design of the neural network model.

[0066] Step S102: Extract time series data of different lengths from multiple different input data, and divide the time series data into training data and test data.

[0067] Specifically, in the cleaned data files, based on the data analysis, continuous time-series inputs from random windows are flexibly selected as training and testing data for use as input to the neural network model. Simultaneously, masks are set within the model layers according to the window size to avoid the impact of padding values ​​on model performance. For example, a sliding window with a length of 90 to 120 is selected to extract amplitude signals of different continuous time periods as time-series data, and the time-series data is divided into training and testing data according to a ratio. In this embodiment, the data is divided into training and testing data in a 7:3 ratio.

[0068] Step S103: Train the attention-based neural network based on the training data to obtain a model with nonlinear characteristics of a power amplifier.

[0069] For example, such as Figure 4As shown, this embodiment uses a network structure of Masked CNN+BiLSTM+Length-AwareAttention to deeply explore temporal features. Deep learning technology is used to automatically extract high-level features from the preprocessed data. High-level features include the relationship between the power amplifier input and output, as well as the temporal correlation of the input signal. Figure 4 In this context, data1, data2, data3…data100 are all training data. Masked CNN represents a framework based on Faster-RCNN, which adds a fully connected segmentation network after the basic feature network. 1DPOOL represents the feature pool for storing features. Multiple LSTM (Long Short-Term Memory) networks are connected in series to form a unidirectional network. Two unidirectional networks in opposite directions form a BiLSTM. Length-Aware Attention is an attention mechanism designed to adapt to encodings based on desired length in order to generate high-quality summaries with the required length.

[0070] Step S104: Test the power amplifier nonlinear characteristic model based on the test data to obtain the power amplifier operating characteristic simulation model after the test is completed.

[0071] Specifically, the trained model with nonlinear characteristics of a power amplifier was tested using test data. The model extracts features from time-series data of different window sizes and outputs results to simulate the signal output of the amplifier. By employing a Masked CNN module and a Length-Aware Attention module, the test results are compatible with signal inputs of different lengths within a certain range, and all can achieve an error rate of less than 0.02. In contrast, simple CNN and attention cannot achieve the same length-adaptation compatibility. The model that has passed the test is used as the simulation model for the operating characteristics of the power amplifier.

[0072] Step S105: Obtain the real-time input data of the power amplifier, and obtain the simulated output results of the power amplifier's operating characteristics based on the real-time input data and the power amplifier's operating characteristic simulation model.

[0073] Specifically, real-time input data from different data acquisition groups of the power amplifier is acquired, and input signals of different lengths of continuous time periods are extracted using a sliding window for simulation. The output results of the power amplifier operating characteristic simulation model are compared with the actual output results of the power amplifier to verify the accuracy and effectiveness of the power amplifier operating characteristic simulation model.

[0074] The power amplifier operating characteristic simulation method provided in this embodiment accurately captures the complex dynamic characteristics of the power amplifier in the nonlinear region by extracting and analyzing the time-series data features of the input signal over a continuous time period, significantly improving the analytical capability of the complex relationship between the input and output signals. Automated feature extraction and modeling are achieved through deep learning algorithms, and the extracted features better reflect the nonlinear characteristics of the power amplifier, greatly improving the accuracy and efficiency of power amplifier simulation. This solves the problems of insufficient accuracy and low efficiency in existing technologies for simulating power amplifiers in the nonlinear region.

[0075] This embodiment provides a method for simulating the operating characteristics of a power amplifier, which can be used in computer terminals such as central processing units and servers. Figure 2 This is a flowchart of a power amplifier operating characteristic simulation method according to an embodiment of the present invention, such as... Figure 2 As shown, the process includes the following steps:

[0076] Step S201: Acquire multiple different input data from the power amplifier. For details, please refer to [link to relevant documentation]. Figure 1 Step S101 of the illustrated embodiment will not be described again here.

[0077] Step S202: Extract time series data of different lengths from multiple different input data, and divide the time series data into training data and test data.

[0078] Specifically, step S202 includes:

[0079] Step a. Select sliding windows of different lengths and use sliding windows of different lengths to extract time series data of different continuous time periods from multiple input data.

[0080] For example, a sliding window with a length of 90 to 120 is selected, and the amplitude signal of continuous time is extracted using the sliding window of 90 to 120 as time series data, that is, the model predicts the final output amplitude signal of this time period.

[0081] Step S203: Train the attention-based neural network based on the training data to obtain a model with nonlinear characteristics of a power amplifier.

[0082] Specifically, such as Figure 4 As shown, the neural network based on the attention mechanism is a neural network structure of Masked CNN + BiLSTM + Length-Aware Attention, including a Masked CNN module, a BiLSTM module, and a Length-Aware Attention module. The above step S203 includes:

[0083] Step S2031: Input the training data into the Masked CNN module for feature extraction and local feature fusion to obtain the fused features.

[0084] Specifically, local feature fusion is first achieved using Masked CNN (a framework based on Faster-RCNN, which adds a fully connected segmentation network after the basic feature network). The formula for inputting training data into the Masked CNN module for feature extraction and local feature fusion is as follows:

[0085] H cnn =CNN(x)⊙mask(1);

[0086] Where CNN(x) is the output obtained by the CNN network from the pre-processing signal (the pre-processing signal refers to the original data or features input into the convolutional neural network (CNN)), mask is the masking operation used to filter the input features, and it is related to the effective output length. H cnn This is the final output of the Masked CNN module;

[0087] Step S2032: Use the BiLSTM module to perform time-series feature analysis on the fused features to obtain the nonlinear features of the power amplifier.

[0088] Specifically, the formula for performing temporal feature analysis on the fused features using a BiLSTM module (BiLSTM stands for Bidirectional Long Short-Term Memory Network, which is an improved recurrent neural network) is as follows:

[0089]

[0090] Where, α i Let exp(a) be the attention coefficient. i ) for a i The applied exponential function is used to convert score values ​​into positive numbers and amplify larger scores, mask. i Here, h is the masking function, T is the total length of the sequence or the number of time steps, and h is the time step. i For the fused features, a i Let be the eigenvalue, i be the current position in the sequence being calculated, and j be the position in the sequence that is traversed during the summation process of the formula.

[0091] Step S2033: Use the Length-Aware Attention module to focus on the nonlinear features of the power amplifier and output the training results of the nonlinear characteristics of the power amplifier. Use the neural network that outputs the training results of the nonlinear characteristics of the power amplifier as a model with the nonlinear characteristics of the power amplifier.

[0092] Specifically, the Length-Aware Attention module is an attention mechanism designed to adapt to encodings based on desired length to generate high-quality summaries with the required length, i.e., to generate focused power amplifier nonlinear features. When the training results of the power amplifier nonlinear features are output, the neural network of Masked CNN+BiLSTM+Length-Aware Attention is trained to become a model with power amplifier nonlinear features.

[0093] Step S2034: The backpropagation algorithm and Adam optimizer are used to optimize the parameters and minimize the loss function of the model with nonlinear characteristics of the power amplifier.

[0094] The Adam optimizer (Adaptive Moment Estimation) is an optimization algorithm for deep learning designed to adaptively adjust the learning rate of each parameter, thereby improving the model's convergence speed and generalization ability. For example, during model training, the Adam optimizer can be used for supervised parameter optimization with an initial learning rate of 1e... -4 The learning rate was dynamically adjusted using a cosine annealing mechanism. The model was trained for 10 epochs based on approximately 80,000 training data points. After training, the trained model with nonlinear power amplifier characteristics was saved locally.

[0095] In some optional implementations, step S2034 above includes:

[0096] The parameter optimization formula for the Masked CNN module in the backpropagation algorithm is as follows:

[0097]

[0098] The parameter optimization formula for the Length-Aware Attention module is as follows:

[0099]

[0100] in, This represents the calculated loss. This represents partial derivative operations;

[0101] To improve convergence stability, this embodiment uses smooth L1 as the loss function, and the formula for the loss function is as follows:

[0102]

[0103] Where smoothL1(x) represents the loss function, x=|ytrue-ypred|, which represents the absolute value of the difference between the predicted value ypred and the true value ytrue, and otherwise represents the case other than |x|<1.

[0104] By using the smooth L1 loss function, the influence of a small number of outliers can be avoided, thus improving the final convergence performance.

[0105] The power amplifier operating characteristic simulation method provided in this embodiment calculates the gradient of the loss function with respect to the weights of each layer in the neural network through backpropagation, thereby guiding the update of the weights. This enables the neural network to learn the mapping relationship between input data and output data, and realizes the optimization of model parameters and model adjustment of the nonlinear characteristics of the power amplifier.

[0106] Step S204: Based on the test data, the model with nonlinear characteristics of the power amplifier is tested to obtain a simulated model of the power amplifier's operating characteristics after testing. For details, please refer to [link to relevant documentation]. Figure 1 Step S104 of the illustrated embodiment will not be described again here.

[0107] Step S205: Obtain the real-time input data of the power amplifier, and based on the real-time input data and the power amplifier operating characteristic simulation model, obtain the simulated output results of the power amplifier operating characteristics. For details, please refer to [link to details]. Figure 1 Step S105 of the illustrated embodiment will not be described again here.

[0108] The power amplifier operating characteristic simulation method provided in this embodiment selects sliding windows of different lengths and uses sliding windows of different lengths to extract time series data of different lengths from multiple input data. This achieves the purpose of extracting time series data of adaptive length, providing conditions for subsequent training of the model using time series data. Time series data of adaptive length is suitable for modeling the characteristics of different types of power amplifiers and has low dependence on data, and can be flexibly adjusted according to the operating characteristics of different amplifiers. The training data is input into the Masked CNN module for feature extraction and local feature fusion to obtain fused features. The BiLSTM module is used to perform temporal feature analysis on the fused features to obtain the nonlinear features of the power amplifier. The Length-Aware Attention module is used to focus the nonlinear features of the power amplifier and output the training results of the nonlinear characteristics of the power amplifier. The neural network that outputs the training results of the nonlinear characteristics of the power amplifier is used as a model with the nonlinear characteristics of the power amplifier. The massive data is automatically processed by deep learning algorithms, reducing manual intervention and the use of empirical formulas, and improving the efficiency of model training and inference. The feature processing by the Masked CNN module, BiLSTM module and Length-Aware Attention module significantly improves the simulation accuracy of the nonlinear characteristics of the power amplifier, which can better adapt to complex signal environments and reduce the error of traditional models under extreme conditions.

[0109] This embodiment provides a method for simulating the operating characteristics of a power amplifier, which can be used in the aforementioned mobile terminals, such as mobile phones and tablets. Figure 3 This is a flowchart of a power amplifier operating characteristic simulation method according to an embodiment of the present invention, such as... Figure 3 As shown, the process includes the following steps:

[0110] Step S301: Acquire multiple different input data from the power amplifier.

[0111] Step S302 involves extracting time-series data of varying lengths from multiple different input data sets, and then dividing the time-series data into training data and test data. For details, please refer to [link to relevant documentation]. Figure 2 Step S202 of the illustrated embodiment will not be described again here.

[0112] Step S303: Train the attention-based neural network based on the training data to obtain a model with nonlinear characteristics of a power amplifier. See details below. Figure 2 Step S203 of the illustrated embodiment will not be described again here.

[0113] Step S304: Based on the test data, the model with the nonlinear characteristics of the power amplifier is tested to obtain the simulated model of the power amplifier's operating characteristics after testing. For details, please refer to [link to relevant documentation]. Figure 2 Step S204 of the illustrated embodiment will not be described again here.

[0114] Step S305: Obtain the real-time input data of the power amplifier, and based on the real-time input data and the power amplifier operating characteristic simulation model, obtain the simulated output results of the power amplifier operating characteristics. For details, please refer to [link to relevant documentation]. Figure 2 Step S205 of the illustrated embodiment will not be described again here. Step S306: Obtain the actual output result corresponding to the real-time input data, and compare the actual output result with the simulated output result to verify the simulation accuracy of the power amplifier operating characteristic simulation model.

[0115] Specifically, real-time input data from different data acquisition groups of the power amplifier is acquired, and input signals of different continuous time periods are extracted using a sliding window for simulation. The output results of the power amplifier operating characteristic simulation model are compared with the actual output results of the power amplifier to verify the accuracy and effectiveness of the power amplifier operating characteristic simulation model. Figure 6 As shown, the horizontal axis "Samples" represents the number of training data samples, and the vertical axis represents the actual output "TrueAmplitude" and the simulated output "PredictedAmplitude". Figure 6 It can be seen that the simulated output results obtained by using the power amplifier operating characteristic simulation method provided in this embodiment are basically consistent with the actual output results.

[0116] The power amplifier operating characteristic simulation method provided in this embodiment obtains the actual output result corresponding to the real-time input data, compares the actual output result with the simulated output result, and achieves the purpose of verifying the simulation accuracy of the power amplifier operating characteristic simulation model, thus providing conditions for improving the simulation accuracy of the model.

[0117] This embodiment utilizes deep learning algorithms to automate feature extraction and modeling, significantly improving the accuracy and efficiency of power amplifier simulation. By extracting and analyzing the temporal characteristics of input signals over continuous time periods, this invention can accurately capture the complex dynamic characteristics of power amplifiers in nonlinear regions, significantly enhancing the analytical capabilities for complex relationships between input and output signals.

[0118] This embodiment also provides a power amplifier operating characteristic simulation device, which is used to implement the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0119] This embodiment provides a power amplifier operating characteristic simulation device, such as... Figure 7 As shown, it includes:

[0120] The input data acquisition module 701 is used to acquire multiple different input data from the power amplifier.

[0121] The training data extraction module 702 is used to extract time series data of different lengths from multiple different input data, and divide the time series data into training data and test data.

[0122] Training module 703 is used to train an attention-based neural network based on training data to obtain a model with nonlinear characteristics of a power amplifier.

[0123] The test module 704 is used to test the power amplifier nonlinear characteristic model based on the test data to obtain a power amplifier operating characteristic simulation model after the test is completed.

[0124] The simulation module 705 is used to acquire the real-time input data of the power amplifier and obtain the simulation output results of the nonlinear operating characteristics of the power amplifier based on the real-time input data and the simulation model of the power amplifier's operating characteristics.

[0125] In some alternative implementations, the training data extraction module 702 includes:

[0126] The sliding window data extraction unit is used to select sliding windows of different lengths, and to extract time series data of different lengths of continuous time periods from multiple input data using sliding windows of different lengths.

[0127] In some alternative implementations, the attention-based neural network includes a Masked CNN module, a BiLSTM module, and a Length-Aware Attention module; the training module 703 includes:

[0128] The feature extraction and fusion unit is used to input training data into the Masked CNN module for feature extraction and local feature fusion to obtain fused features.

[0129] The feature analysis unit is used to perform time-series feature analysis on the fused features using the BiLSTM module to obtain the nonlinear features of the power amplifier.

[0130] The feature focusing unit is used to focus the nonlinear features of the power amplifier using the Length-Aware Attention module and output the training results of the nonlinear characteristics of the power amplifier. The neural network that outputs the training results of the nonlinear characteristics of the power amplifier is used as a model with the nonlinear characteristics of the power amplifier.

[0131] The formula for inputting training data into the Masked CNN module for feature extraction and local feature fusion is as follows:

[0132] H cnn =CNN(x)⊙mask(1);

[0133] Where CNN(x) is the output obtained by passing the pre-processed signal through the CNN network, mask is the masking operation used to filter the input features, and it is related to the effective output length, H cnn This is the final output of the Masked CNN module;

[0134] The formula for performing temporal feature analysis on the fused features using the BiLSTM module is as follows:

[0135]

[0136] Where, α i Let exp(a) be the attention coefficient. i ) for a i The applied exponential function is used to convert score values ​​into positive numbers and amplify larger scores, mask. i Here, h is the masking function, T is the total length of the sequence or the number of time steps, and h is the time step. i For the fused features, a i Let be the eigenvalue, i be the current position in the sequence being calculated, and j be the position in the sequence that is traversed during the summation process of the formula.

[0137] The optimization unit is used to optimize parameters and minimize the loss function of a model with nonlinear characteristics of a power amplifier using the backpropagation algorithm and the Adam optimizer.

[0138] The parameter optimization formula for the Masked CNN module in the backpropagation algorithm is as follows:

[0139]

[0140] The parameter optimization formula for the Length-Aware Attention module is as follows:

[0141]

[0142] in, This represents the calculated loss. This represents partial derivative operations;

[0143] The formula for the loss function is as follows:

[0144]

[0145] Where smoothL1(x) represents the loss function, x=|ytrue-ypred|, which represents the absolute value of the difference between the predicted value ypred and the true value ytrue, and otherwise represents the case other than |x|<1.

[0146] In some alternative implementations, the power amplifier operating characteristic simulation apparatus further includes:

[0147] The simulation accuracy verification module is used to obtain the actual output results corresponding to the real-time input data, and compare the actual output results with the simulation output results to verify the simulation accuracy of the power amplifier operating characteristic simulation model.

[0148] Further functional descriptions of the above modules and units are the same as those in the corresponding embodiments described above, and will not be repeated here.

[0149] In this embodiment, the power amplifier operating characteristic simulation device is presented in the form of a functional unit. Here, a unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that execute one or more software or fixed programs, and / or other devices that can provide the above functions.

[0150] This invention also provides a computer device having the above-described features. Figure 7 The power amplifier operating characteristics simulation device shown is shown.

[0151] Please see Figure 8 , Figure 8 This is a schematic diagram of the structure of a computer device provided in an optional embodiment of the present invention, such as... Figure 8As shown, the computer device includes one or more processors 10, memory 20, and interfaces for connecting the components, including high-speed interfaces and low-speed interfaces. The components communicate with each other via different buses and can be mounted on a common motherboard or otherwise installed as needed. The processors can process instructions executed within the computer device, including instructions stored in or on memory to display graphical information of a GUI on external input / output devices (such as display devices coupled to the interfaces). In some alternative implementations, multiple processors and / or multiple buses can be used with multiple memories and multiple memory modules, if desired. Similarly, multiple computer devices can be connected, each providing some of the necessary operations (e.g., as a server array, a group of blade servers, or a multiprocessor system). Figure 8 Take a processor 10 as an example.

[0152] Processor 10 may be a central processing unit, a network processor, or a combination thereof. Processor 10 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The programmable logic device may be a complex programmable logic device (CAMP), a field-programmable gate array (FPGA), a general-purpose array logic (GDA), or any combination thereof.

[0153] The memory 20 stores instructions executable by at least one processor 10 to cause the at least one processor 10 to perform the method shown in the above embodiments.

[0154] The memory 20 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created based on the use of the computer device. Furthermore, the memory 20 may include high-speed random access memory and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some alternative embodiments, the memory 20 may optionally include memory remotely located relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0155] The memory 20 may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as flash memory, hard disk or solid-state drive; the memory 20 may also include a combination of the above types of memory.

[0156] The computer device also includes an input device 30 and an output device 40. The processor 10, memory 20, input device 30, and output device 40 can be connected via a bus or other means. Figure 8 Taking the example of a connection between China and Israel via a bus.

[0157] Input device 30 can receive input numerical or character information, and generate key signal inputs related to user settings and function control of the computer device, such as a touchscreen, keypad, mouse, trackpad, touchpad, joystick, one or more mouse buttons, trackball, joystick, etc. Output device 40 may include display devices, auxiliary lighting devices (e.g., LEDs), and haptic feedback devices (e.g., vibration motors). The aforementioned display devices include, but are not limited to, liquid crystal displays, light-emitting diodes, displays, and plasma displays. In some alternative embodiments, the display device may be a touchscreen.

[0158] This invention also provides a computer-readable storage medium. The methods described above according to embodiments of the invention can be implemented in hardware or firmware, or implemented as computer code that can be recorded on a storage medium, or implemented as computer code downloaded via a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and then stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code, which, when accessed and executed by the computer, processor, or hardware, implements the methods shown in the above embodiments.

[0159] A portion of this invention can be applied as a computer program product, such as computer program instructions, which, when executed by a computer, can invoke or provide the methods and / or technical solutions according to the invention through the operation of the computer. Those skilled in the art will understand that the forms in which computer program instructions exist in a computer-readable medium include, but are not limited to, source files, executable files, installation package files, etc. Correspondingly, the ways in which computer program instructions are executed by a computer include, but are not limited to: the computer directly executing the instructions, or the computer compiling the instructions and then executing the corresponding compiled program, or the computer reading and executing the instructions, or the computer reading and installing the instructions and then executing the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to a computer.

[0160] Although embodiments of the invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. A method for simulating the operating characteristics of a power amplifier, characterized in that, The method includes: Acquire multiple different input data from the power amplifier; Time series data of different lengths are extracted from the multiple different input data, and the time series data is divided into training data and test data. The attention-based neural network is trained based on the training data to obtain a model with nonlinear characteristics of a power amplifier; the attention-based neural network includes a Masked CNN module, a BiLSTM module, and a Length-Aware Attention module. The neural network based on the aforementioned training data is trained to obtain a model with nonlinear characteristics of a power amplifier, including: The training data is input into the Masked CNN module for feature extraction and local feature fusion to obtain fused features; The BiLSTM module is used to perform time-series feature analysis on the fused features to obtain the nonlinear characteristics of the power amplifier; The Length-Aware Attention module is used to focus on the nonlinear features of the power amplifier and output the training results of the nonlinear characteristics of the power amplifier. The neural network that outputs the training results of the nonlinear characteristics of the power amplifier is used as a model with the nonlinear characteristics of the power amplifier. Based on the test data, a power amplifier nonlinear characteristic model is tested to obtain a power amplifier operating characteristic simulation model after the test is completed. The real-time input data of the power amplifier is acquired, and the simulation output results of the power amplifier operating characteristics are obtained based on the real-time input data and the power amplifier operating characteristic simulation model.

2. The method according to claim 1, characterized in that, Extracting time-series data of different lengths from the multiple different input data includes: Select sliding windows of different lengths, and use the sliding windows of different lengths to extract time series data of different continuous time periods from multiple input data.

3. The method according to claim 1, characterized in that, The formula for inputting the training data into the Masked CNN module for feature extraction and local feature fusion is as follows: ； in, The output obtained by passing the pre-processed signal through a CNN network. This is a masking operation that filters input features; its effectiveness is related to the length of the output. This is the final output of the Masked CNN module; The formula for performing temporal feature analysis on the fused features using the BiLSTM module is as follows: ； ； in, Attention coefficient To The applied exponential function is used to convert score values ​​into positive numbers and amplify larger scores. Here, T is the masking function, and T is the total length of the sequence or the number of time steps. To analyze the fused features, Let be the eigenvalue, i be the current position in the sequence being calculated, and j be the position in the sequence that is traversed during the summation process of the formula.

4. The method according to claim 3, characterized in that, Training the attention-based neural network based on the training data further includes: The backpropagation algorithm and Adam optimizer are used to optimize the parameters and minimize the loss function of the model with nonlinear characteristics of the power amplifier.

5. The method according to claim 4, characterized in that, The step of using the backpropagation algorithm and Adam optimizer to optimize parameters and minimize the loss function of the model with nonlinear power amplifier characteristics includes: The parameter optimization formula for the Masked CNN module in the backpropagation algorithm is as follows: ； The parameter optimization formula for the Length-Aware Attention module is as follows: ； in, This represents the calculated loss. This represents partial derivative operations; The formula for the loss function is as follows: ； in, Represents the loss function. , representing the absolute value of the difference between the predicted value ypred and the true value ytrue. Indicates except Other than these.

6. The method according to claim 1, characterized in that, The method further includes: obtaining the actual output results corresponding to the real-time input data, and comparing the actual output results with the simulated output results to verify the simulation accuracy of the power amplifier operating characteristic simulation model.

7. A power amplifier operating characteristic simulation device, characterized in that, The device includes: The input data acquisition module is used to acquire multiple different input data from the power amplifier; The training data extraction module is used to extract time-series data of different lengths from the multiple different input data, and divide the time-series data into training data and test data. The training module is used to train the attention-based neural network based on the training data to obtain a model with nonlinear characteristics of a power amplifier; the attention-based neural network includes a Masked CNN module, a BiLSTM module, and a Length-Aware Attention module. The neural network based on the aforementioned training data is trained to obtain a model with nonlinear characteristics of a power amplifier, including: The training data is input into the Masked CNN module for feature extraction and local feature fusion to obtain fused features; The BiLSTM module is used to perform time-series feature analysis on the fused features to obtain the nonlinear characteristics of the power amplifier; The Length-Aware Attention module is used to focus on the nonlinear features of the power amplifier and output the training results of the nonlinear characteristics of the power amplifier. The neural network that outputs the training results of the nonlinear characteristics of the power amplifier is used as a model with the nonlinear characteristics of the power amplifier. The testing module is used to test the power amplifier nonlinear characteristic model based on the test data to obtain a power amplifier operating characteristic simulation model after the test is completed. The simulation module is used to acquire real-time input data of the power amplifier and obtain the simulation output results of the power amplifier's operating characteristics based on the real-time input data and the power amplifier operating characteristic simulation model.

8. A computer device, characterized in that, include: A memory and a processor are communicatively connected, the memory stores computer instructions, and the processor executes the computer instructions to perform the power amplifier operating characteristic simulation method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing a computer to perform the power amplifier operating characteristic simulation method according to any one of claims 1 to 6.

Images