Topological optical switch structure design method and system based on multi-network cascade model

Through the multi-network cascade model combined with deep learning and transmission matrix method, the topological optical switch structure design is optimized, which solves the problems of non-uniqueness and multiple degrees of freedom in the design, and realizes more accurate and efficient reverse design of structural parameters, improving optical characteristic.

CN119004798AActive Publication Date: 2024-11-22CHINA UNIV OF GEOSCIENCES (WUHAN)

Patent Information

Application Number
CN202411040014.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-31
Publication Date
2024-11-22
Estimated Expiration
2044-07-31

AI Technical Summary

Technical Problem

There are non-uniqueness and multiple degrees of freedom problems in the existing topological optical switch structure design, which leads to the traditional numerical simulation method being time-consuming and intensive in computing resources. Deep learning mainly focuses on external electromagnetic response in reverse design, and regarding the quantization of photon energy band diagrams. and prediction research is relatively small, resulting in large errors in prediction parameters.

Method used

Using the topological optical switch structure design method based on multi-network cascade model, the network is designed by one-dimensional convolution inverse design, amplitude coupling ratio prediction network and transmission spectrum forward prediction model, combined with parameter scanning and time domain finite difference method, comprehensive data is constructed The model is optimized to achieve accurate reverse design of structural parameters.

Benefits of technology

The accuracy of topological optical switch structure design is improved, and supervised learning is achieved with multi-degree of optical response data, which can obtain more stable and excellent optical characteristics, and solve the problems of non-uniqueness and multi-degree of freedom.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119004798A_ABST
    Figure CN119004798A_ABST
Patent Text Reader

Abstract

The invention discloses a topological optical switch structure design method and system based on a multi-network cascade model, and relates to the field of topological optical switch structure design. The topological optical switch structure design method based on the multi-network cascade model mainly comprises the following steps: constructing a one-dimensional convolution reverse design network, an amplitude coupling ratio prediction network, a mathematical model based on a transmission matrix method and a transmission spectrum forward prediction model; carrying out independent training on each sub-model, carrying out cascade connection on the trained sub-models, enabling the output of each network to become the input of the next network, obtaining a multi-network cascade connection model, carrying out overall training on the multi-network cascade connection model, and obtaining an optimized one-dimensional convolution reverse design network; and according to the target transmission spectrum data, using the optimized one-dimensional convolution reverse design network to obtain target structure parameters. By implementing the topological optical switch structure design method and system based on the multi-network cascade model provided by the invention, the accuracy of topological optical switch structure design can be improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of topological optical switch structure design, and more specifically, to a topological optical switch structure design method and a topological optical switch structure design system based on a multi-network cascade model. Background Art

[0002] Optical switches are one of the important components for modern optical networks to develop towards higher speed and larger capacity. Whether it is long-distance optical signal switching or on-chip optical interconnection, optical switches are key optical devices.

[0003] Topological optical switches have the characteristics of edge states, which can achieve precise control of photon transmission, and thus have potential application value in optical communications, optical computing, and quantum information processing. In the field of topological photonics, the reverse design of the structural parameters of topological optical switches is a very challenging task, which not only needs to consider the functional realization of photonic devices, but also needs to solve the inherent non-uniqueness and multi-degree-of-freedom problems in the design process.

[0004] For simple topological optical switch structures, traditional numerical simulation methods often require a lot of time and computing resources, and often require fine-tuning the geometric structure and iterative simulation to gradually approach the target response. This process relies heavily on previous design experience, and due to the limitations of computer hardware and simulation time, the final design result may only be a local optimal structure.

[0005] Unlike traditional methods based on physical models and strategies, deep learning (DL) is a data-driven method. The photonics community has also benefited from the rapid development of deep learning technology, and many photonic device reverse designs have been intelligently implemented. Deep learning provides a new way to solve forward prediction and reverse design related to spectral response. Well-trained deep learning models can directly establish a mapping from structural parameter design to the optical properties of the target photonic device, and vice versa.

[0006] However, in the design process of topological optical switch devices, on the one hand, optical topology judgment needs to consider the interaction between structural parameters and electromagnetic waves. The transmission spectrum response and photon energy band jointly determine the performance of the topological optical switch. How to generate a reverse design method that meets the performance constraints of the optical switch under such high degrees of freedom is currently relatively scarce. On the other hand, the current deep learning reverse design of optical devices mainly focuses on external electromagnetic responses, such as transmission spectra, reflection spectra, and absorption spectra. There are few studies on the quantification and prediction of photon energy band diagrams. How to quantify the energy band diagram into data that the neural network can learn is a key issue.

[0007] In summary, the electromagnetic response in the existing inverse design of photonic devices corresponds to a variety of structural parameters, and the few constraints used lead to large errors in the predicted parameters. The existing reverse design of micro-ring resonator (MRR) optical switches has problems of non-uniqueness and multiple degrees of freedom. Summary of the invention

[0008] The purpose of the present invention is to provide a topological optical switch structure design method and a topological optical switch structure design system based on a multi-network cascade model, which can improve the accuracy of topological optical switch structure design.

[0009] The present invention provides a topological optical switch structure design method based on a multi-network cascade model, comprising the following steps:

[0010] S1: Using parameter scanning method and finite-difference time-domain method, a comprehensive data set is obtained, which includes transmission spectrum data, structural parameter data, amplitude coupling ratio data and photon band image data;

[0011] S2: Construct a one-dimensional convolution inverse design network, an amplitude coupling ratio prediction network, a mathematical model based on the transfer matrix method, and a transmission spectrum forward prediction model; the one-dimensional convolution inverse design network is used to predict the structural parameter data according to the transmission spectrum data; the amplitude coupling ratio prediction network is used to predict the amplitude coupling ratio data according to the structural parameter data; the mathematical model based on the transfer matrix method is used to calculate the photon band image data according to the structural parameter data and the amplitude coupling ratio data; the transmission spectrum forward prediction model is used to predict the transmission spectrum data according to the photon band image data;

[0012] S3: Using the comprehensive data set, the one-dimensional convolutional inverse design network, the amplitude coupling ratio prediction network and the transmission spectrum forward prediction model are trained independently to obtain the trained one-dimensional convolutional inverse design network, the trained amplitude coupling ratio prediction network and the trained transmission spectrum forward prediction model;

[0013] S4: Based on the trained one-dimensional convolutional inverse design network, the trained amplitude coupling ratio prediction network, the mathematical model based on the transfer matrix method and the trained transmission spectrum forward prediction model, a multi-network cascade model is obtained; based on the comprehensive data set, the multi-network cascade model is trained as a whole using the loss function to obtain an optimized one-dimensional convolutional inverse design network;

[0014] S5: According to the target transmission spectrum data, the target structure parameters are obtained using the optimized one-dimensional convolution inverse design network.

[0015] Furthermore, the one-dimensional convolutional inverse design network of the topological optical switch structure design method based on the multi-network cascade model includes a one-dimensional convolutional neural network, which is used to learn the mapping relationship between the transmission spectrum and the structural parameters. The one-dimensional convolutional neural network includes a convolutional layer and a fully connected layer; the amplitude coupling ratio prediction network takes the output of the one-dimensional convolutional inverse design network as input and outputs amplitude coupling ratio data. The amplitude coupling ratio prediction network is a deep fully connected neural network. The amplitude coupling ratio prediction network includes a 512×64×16×16×3 fully connected layer, and each neuron in the fully connected layer is connected to all neurons in the previous layer; the mathematical model based on the transfer matrix method receives the one-dimensional convolutional inverse design network. The structural parameters of the network output and the amplitude coupling ratio prediction network output amplitude coupling ratio data are calculated to calculate and generate the photon band image; the transmission spectrum forward prediction model includes a photon band encoder and a band-transmission spectrum decoder; the photon band encoder is used to receive the photon band image of size 267×200 calculated by the transfer matrix method, and encode it into a one-dimensional band image code with a length of 8192; the photon band encoder includes a convolutional layer and a fully connected layer; the band-transmission spectrum decoder is used to receive the one-dimensional band image code of 8192 output by the photon band encoder, and decode it back to a one-dimensional transmission spectrum data with a length of 501; the band-transmission spectrum decoder includes a convolutional layer and a fully connected layer.

[0016] Furthermore, the mathematical model based on the transmission matrix method of the topological optical switch structure design method based on the multi-network cascade model predicts the amplitude coupling ratio data of the network output according to the structural parameters and amplitude coupling ratio of the one-dimensional convolution inverse design network output, and uses the transmission matrix method and Bloch theorem to obtain the eigenvalue according to the eigenvalue equation, discards each eigenvalue that does not have a unit mode, and then scans the Bloch wave vector k x and phase, we get the photon energy band image, as shown in the formula:

[0017]

[0018]

[0019]

[0020]

[0021] Among them, M x is the transmission matrix representing the coupling relationship of the microring resonator coupling array in the x direction, M y is the transmission matrix representing the coupling relationship of the microring resonator coupling array in the y direction, k and τ are the amplitude coupling ratio and amplitude transmission ratio between the field ring and the connecting ring, respectively, and both satisfy |k2 +τ 2 =1, φ is the phase shift produced when the optical path is one quarter of the circumference of the micro-ring. det(S) is The determinant of k x is the Bloch wave vector, b' is the input amplitude at the coupling point between the adjacent connecting ring and the field ring, and d' is the output amplitude at the coupling point between the adjacent connecting ring and the field ring.

[0022] Furthermore, the loss function of the above-mentioned topological optical switch structure design method based on the multi-network cascade model is as follows:

[0023]

[0024] Among them, L δ (y,f(x)) is the loss function, y is the true parameter, f(x) is the predicted parameter, and δ is the parameter of Huber Loss.

[0025] The present invention also provides a topological optical switch structure design system, comprising the following modules:

[0026] A comprehensive data set acquisition module is configured to: obtain a comprehensive data set by using a parameter scanning method and a finite difference time domain method, wherein the comprehensive data set includes transmission spectrum data, structural parameter data, amplitude coupling ratio data, and photon energy band image data;

[0027] The sub-model construction module is configured as follows: constructing a one-dimensional convolution inverse design network, an amplitude coupling ratio prediction network, a mathematical model based on the transfer matrix method, and a transmission spectrum forward prediction model; the one-dimensional convolution inverse design network is used to predict structural parameter data according to transmission spectrum data; the amplitude coupling ratio prediction network is used to predict amplitude coupling ratio data according to structural parameter data; the mathematical model based on the transfer matrix method is used to calculate photon band image data according to structural parameter data and amplitude coupling ratio data; the transmission spectrum forward prediction model is used to predict transmission spectrum data according to photon band image data;

[0028] The sub-model training module is configured as follows: using a comprehensive data set, independently training the one-dimensional convolutional inverse design network, the amplitude coupling ratio prediction network, and the transmission spectrum forward prediction model, respectively, to obtain a trained one-dimensional convolutional inverse design network, a trained amplitude coupling ratio prediction network, and a trained transmission spectrum forward prediction model;

[0029] The model training and optimization module is configured as follows: a multi-network cascade model is obtained based on the trained one-dimensional convolution inverse design network, the trained amplitude coupling ratio prediction network, the mathematical model based on the transfer matrix method and the trained transmission spectrum forward prediction model; based on the comprehensive data set, the multi-network cascade model is trained as a whole using the loss function to obtain an optimized one-dimensional convolution inverse design network;

[0030] The structural inverse design module is configured as follows: according to the target transmission spectrum data, the target structural parameters are obtained by using the optimized one-dimensional convolutional inverse design network.

[0031] Furthermore, the one-dimensional convolutional inverse design network of the topological optical switch structure design system includes a one-dimensional convolutional neural network, which is used to learn the mapping relationship between the transmission spectrum and the structural parameters, and the one-dimensional convolutional neural network includes a convolutional layer and a fully connected layer; the amplitude coupling ratio prediction network takes the output of the one-dimensional convolutional inverse design network as input, and outputs amplitude coupling ratio data, and the amplitude coupling ratio prediction network is a deep fully connected neural network, and the amplitude coupling ratio prediction network includes a 512×64×16×16×3 fully connected layer, and each neuron in the fully connected layer is connected to all neurons in the previous layer; the mathematical model based on the transfer matrix method receives the output of the one-dimensional convolutional inverse design network The structural parameters and amplitude coupling ratio prediction network output the amplitude coupling ratio data to calculate and generate the photon band image; the transmission spectrum forward prediction model includes a photon band encoder and a band-transmission spectrum decoder; the photon band encoder is used to receive the photon band image of size 267×200 calculated by the transfer matrix method, and encode it into a one-dimensional band image code with a length of 8192; the photon band encoder includes a convolutional layer and a fully connected layer; the band-transmission spectrum decoder is used to receive the one-dimensional band image code of 8192 output by the photon band encoder, and decode it back to a one-dimensional transmission spectrum data with a length of 501; the band-transmission spectrum decoder includes a convolutional layer and a fully connected layer.

[0032] Furthermore, the mathematical model based on the transfer matrix method of the topological optical switch structure design system predicts the amplitude coupling ratio data of the network output according to the structural parameters and amplitude coupling ratio of the one-dimensional convolution inverse design network output, and uses the transfer matrix method and Bloch theorem to obtain the eigenvalue according to the eigenvalue, discards each eigenvalue that does not have a unit mode, and then scans the Bloch wave vector k x and phase, we get the photon energy band image, as shown in the formula:

[0033]

[0034]

[0035]

[0036]

[0037] Among them, M x is the transmission matrix representing the coupling relationship of the microring resonator coupling array in the x direction, M yis the transmission matrix representing the coupling relationship of the microring resonator coupling array in the y direction, k and τ are the amplitude coupling ratio and amplitude transmission ratio between the field ring and the connecting ring, respectively, and both satisfy |k 2 +τ 2 =1, φ is the phase shift produced when the optical path is one quarter of the circumference of the micro-ring. det(S) is The determinant of k x is the Bloch wave vector, b' is the input amplitude at the coupling point between the adjacent connecting ring and the field ring, and d' is the output amplitude at the coupling point between the adjacent connecting ring and the field ring.

[0038] Furthermore, the loss function of the above topological optical switch structure design system is as follows:

[0039]

[0040] Among them, L δ (y,f(x)) is the loss function, y is the true parameter, f(x) is the predicted parameter, and δ is the parameter of Huber Loss.

[0041] The implementation of the topological optical switch structure design method and topological optical switch structure design system based on the multi-network cascade model provided by the present invention has the following beneficial effects:

[0042] The present invention draws on the idea of ​​cascade model and makes innovative improvements on the basis of traditional deep learning cascade network. It uses advanced deep learning architecture to connect multiple sub-models in a specific order and manner to form a more powerful and complex overall model. Specifically, the present invention proposes to use a multi-network cascaded deep learning model for structural reverse design in combination with the design goal of topological optical switch performance parameters. The model consists of a reverse design model, an amplitude coupling ratio prediction model and a transmission spectrum forward prediction model. Its training and optimization process integrates multi-dimensional data sets such as transmission spectrum, structural parameters, amplitude coupling ratio and photon energy band, so that the entire model can learn and process more complex data, so that it can combine multi-degree-of-freedom optical response data to achieve more accurate and efficient supervised learning, thereby obtaining optical characteristics with more stable transmission and better switching performance, solving the non-uniqueness problem and multi-degree-of-freedom problem in the structural design of topological optical switches. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] The present invention will be further described below with reference to the accompanying drawings and embodiments, in which:

[0044] Figure 1 It is a flow chart of a topological optical switch structure design method based on a multi-network cascade model provided by the present invention;

[0045] Figure 2 It is a schematic diagram of the micro-ring array structure provided by the present invention;

[0046] Figure 3 It is a schematic diagram of a multi-network cascade model provided by the present invention;

[0047] Figure 4 It is a flow chart of a multi-network cascade model of a topological optical switch provided by the present invention;

[0048] Figure 5 It is the overall training flow chart of the cascade model provided by the present invention;

[0049] Figure 6 It is a comparison chart of the overall training loss of the cascade model provided by the present invention;

[0050] Figure 7 It is a comparison diagram of the predicted transmission spectrum dB graph provided by the present invention;

[0051] Figure 8 It is a comparison diagram of the transmission spectrum simulation results of the structural parameters predicted by the direct inverse model provided by the present invention and the inverse model after multi-network cascading. DETAILED DESCRIPTION

[0052] In order to have a clearer understanding of the technical features, purposes and effects of the present invention, specific embodiments of the present invention are now described in detail with reference to the accompanying drawings.

[0053] Figure 1 A schematic diagram of a topological optical switch structure design method based on a multi-network cascade model of this embodiment is shown. In this embodiment, the topological optical switch structure design method based on a multi-network cascade model includes the following steps:

[0054] S1: Using parameter scanning method and finite-difference time-domain method, a comprehensive data set is obtained, which includes transmission spectrum data, structural parameter data, amplitude coupling ratio data and photon band image data;

[0055] S2: Construct a one-dimensional convolution inverse design network, an amplitude coupling ratio prediction network, a mathematical model based on the transfer matrix method, and a transmission spectrum forward prediction model; the one-dimensional convolution inverse design network is used to predict the structural parameter data according to the transmission spectrum data; the amplitude coupling ratio prediction network is used to predict the amplitude coupling ratio data according to the structural parameter data; the mathematical model based on the transfer matrix method is used to calculate the photon band image data according to the structural parameter data and the amplitude coupling ratio data; the transmission spectrum forward prediction model is used to predict the transmission spectrum data according to the photon band image data;

[0056] Specifically, the one-dimensional convolutional inverse design network of the topological optical switch structure design method based on the multi-network cascade model includes a one-dimensional convolutional neural network, which is used to learn the mapping relationship between the transmission spectrum and the structural parameters. The one-dimensional convolutional neural network includes a convolutional layer and a fully connected layer; the amplitude coupling ratio prediction network takes the output of the one-dimensional convolutional inverse design network as input and outputs the amplitude coupling ratio data. The amplitude coupling ratio prediction network is a deep fully connected neural network. The amplitude coupling ratio prediction network includes a 512×64×16×16×3 fully connected layer, and each neuron in the fully connected layer is connected to all neurons in the previous layer; the mathematical model based on the transfer matrix method receives the one-dimensional convolutional inverse design. The network outputs structural parameters and amplitude coupling ratios to predict the amplitude coupling ratio data output by the network, and calculate and generate the photon band image; the transmission spectrum forward prediction model includes a photon band encoder and a band-transmission spectrum decoder; the photon band encoder is used to receive the photon band image of size 267×200 calculated by the transfer matrix method, and encode it into a one-dimensional band image code of length 8192; the photon band encoder includes a convolutional layer and a fully connected layer; the band-transmission spectrum decoder is used to receive the one-dimensional band image code of 8192 output by the photon band encoder, and decode it back to a one-dimensional transmission spectrum data of length 501; the band-transmission spectrum decoder includes a convolutional layer and a fully connected layer;

[0057] Specifically, the mathematical model based on the transmission matrix method of the topological optical switch structure design method based on the multi-network cascade model predicts the amplitude coupling ratio data of the network output according to the one-dimensional convolution inverse design network output structural parameters and amplitude coupling ratio, and uses the transmission matrix method and Bloch theorem to obtain the eigenvalue according to the eigenvalue equation, discards each eigenvalue that does not have a unit mode, and then scans the Bloch wave vector k x and phase, we get the photon energy band image, as shown in the formula:

[0058]

[0059]

[0060]

[0061]

[0062] Among them, M x is the transmission matrix representing the coupling relationship of the microring resonator coupling array in the x direction, M y is the transmission matrix representing the coupling relationship of the microring resonator coupling array in the y direction, k and τ are the amplitude coupling ratio and amplitude transmission ratio between the field ring and the connecting ring, respectively, and both satisfy |k 2+τ 2 =1, φ is the phase shift produced when the optical path is one quarter of the circumference of the micro-ring. det(S) is The determinant of k x is the Bloch wave vector, b' is the input amplitude at the coupling point between the adjacent connecting ring and the field ring, and d' is the output amplitude at the coupling point between the adjacent connecting ring and the field ring;

[0063] S3: Using the comprehensive data set, the one-dimensional convolutional inverse design network, the amplitude coupling ratio prediction network and the transmission spectrum forward prediction model are trained independently to obtain the trained one-dimensional convolutional inverse design network, the trained amplitude coupling ratio prediction network and the trained transmission spectrum forward prediction model;

[0064] S4: Based on the trained one-dimensional convolutional reverse design network, the trained amplitude coupling ratio prediction network, the mathematical model based on the transfer matrix method and the trained transmission spectrum forward prediction model, a multi-network cascade model is obtained; based on the comprehensive data set, the multi-network cascade model is trained as a whole using the loss function to obtain an optimized one-dimensional convolutional reverse design network;

[0065] Specifically, the loss function of the topological optical switch structure design method based on the multi-network cascade model is as follows:

[0066]

[0067] Among them, L δ (y,f(x)) is the loss function, y is the true parameter, f(x) is the predicted parameter, and δ is the parameter of Huber Loss;

[0068] S5: According to the target transmission spectrum data, the target structure parameters are obtained using the optimized one-dimensional convolution inverse design network.

[0069] The present invention also provides a topological optical switch structure design system, comprising the following modules:

[0070] A comprehensive data set acquisition module is configured to: obtain a comprehensive data set by using a parameter scanning method and a finite difference time domain method, wherein the comprehensive data set includes transmission spectrum data, structural parameter data, amplitude coupling ratio data, and photon energy band image data;

[0071] The sub-model construction module is configured as follows: constructing a one-dimensional convolution inverse design network, an amplitude coupling ratio prediction network, a mathematical model based on the transfer matrix method, and a transmission spectrum forward prediction model; the one-dimensional convolution inverse design network is used to predict structural parameter data according to transmission spectrum data; the amplitude coupling ratio prediction network is used to predict amplitude coupling ratio data according to structural parameter data; the mathematical model based on the transfer matrix method is used to calculate photon band image data according to structural parameter data and amplitude coupling ratio data; the transmission spectrum forward prediction model is used to predict transmission spectrum data according to photon band image data;

[0072] Specifically, the one-dimensional convolutional inverse design network of the topological optical switch structure design system includes a one-dimensional convolutional neural network, which is used to learn the mapping relationship between the transmission spectrum and the structural parameters. The one-dimensional convolutional neural network includes a convolutional layer and a fully connected layer; the amplitude coupling ratio prediction network takes the output of the one-dimensional convolutional inverse design network as input and outputs the amplitude coupling ratio data. The amplitude coupling ratio prediction network is a deep fully connected neural network. The amplitude coupling ratio prediction network includes a 512×64×16×16×3 fully connected layer, and each neuron in the fully connected layer is connected to all neurons in the previous layer; the mathematical model based on the transfer matrix method receives the output of the one-dimensional convolutional inverse design network. The amplitude coupling ratio data output by the structure parameter and amplitude coupling ratio prediction network is used to calculate and generate the photon band image; the transmission spectrum forward prediction model includes a photon band encoder and a band-transmission spectrum decoder; the photon band encoder is used to receive the photon band image of size 267×200 calculated by the transfer matrix method, and encode it into a one-dimensional band image code of length 8192; the photon band encoder includes a convolutional layer and a fully connected layer; the band-transmission spectrum decoder is used to receive the one-dimensional band image code of 8192 output by the photon band encoder, and decode it back to a one-dimensional transmission spectrum data of length 501; the band-transmission spectrum decoder includes a convolutional layer and a fully connected layer;

[0073] Specifically, the mathematical model based on the transmission matrix method of the topological optical switch structure design system predicts the amplitude coupling ratio data of the network output according to the structural parameters and amplitude coupling ratio of the one-dimensional convolution inverse design network output, and uses the transmission matrix method and Bloch theorem to obtain the eigenvalue according to the eigenvalue equation, discards each eigenvalue that does not have a unit mode, and then scans the Bloch wave vector k x and phase, we get the photon energy band image, as shown in the formula:

[0074]

[0075]

[0076]

[0077]

[0078] Among them, M x is the transmission matrix representing the coupling relationship of the microring resonator coupling array in the x direction, M y is the transmission matrix representing the coupling relationship of the microring resonator coupling array in the y direction, k and τ are the amplitude coupling ratio and amplitude transmission ratio between the field ring and the connecting ring, respectively, and both satisfy |k 2 +τ 2 =1, φ is the phase shift produced when the optical path is one quarter of the circumference of the micro-ring. det(S) is The determinant of k x is the Bloch wave vector, b' is the input amplitude at the coupling point between the adjacent connecting ring and the field ring, and d' is the output amplitude at the coupling point between the adjacent connecting ring and the field ring;

[0079] The sub-model training module is configured as follows: using a comprehensive data set, independently training the one-dimensional convolutional inverse design network, the amplitude coupling ratio prediction network, and the transmission spectrum forward prediction model, respectively, to obtain a trained one-dimensional convolutional inverse design network, a trained amplitude coupling ratio prediction network, and a trained transmission spectrum forward prediction model;

[0080] The model training and optimization module is configured as follows: a multi-network cascade model is obtained based on the trained one-dimensional convolution inverse design network, the trained amplitude coupling ratio prediction network, the mathematical model based on the transfer matrix method and the trained transmission spectrum forward prediction model; based on the comprehensive data set, the multi-network cascade model is trained as a whole using the loss function to obtain an optimized one-dimensional convolution inverse design network;

[0081] Specifically, the loss function of the above topological optical switch structure design system is as follows:

[0082]

[0083] Among them, L δ (y,f(x)) is the loss function, y is the true parameter, f(x) is the predicted parameter, and δ is the parameter of Huber Loss;

[0084] The structural inverse design module is configured as follows: according to the target transmission spectrum data, the target structural parameters are obtained by using the optimized one-dimensional convolutional inverse design network.

[0085] In some embodiments, the above-mentioned topological optical switch structure design method based on the multi-network cascade model can also be implemented in the following manner.

[0086] In this embodiment, the structural model of the topological microring array used is as follows: Figure 2 As shown, it consists of a 3×3 micro-ring array and input and output waveguides. The black ring in the figure is the field ring, the gray ring is the coupling ring, one input waveguide is connected to the middle field ring on the left end of the array, one output waveguide is symmetrical to it, and the other is connected to the field ring on the top right side of the array; the area in the frame is the modulation area, in which the micro-rings are thermo-optically modulated micro-rings; the structural parameter is the field ring radius R 1 , coupling ring radius R 2 and the coupling spacing g between the field ring and the coupling ring;

[0087] Specifically, the field ring radius R 1 The coupling ring radius R 2 The structural parameters are uniformly generated within the range of 1.3μm to 1.9μm with an accuracy of 0.02μm, and the coupling spacing g between the field ring and the coupling ring is uniformly generated within the range of 0.02μm to 0.12μm with an accuracy of 0.01μm;

[0088] Specifically, a parameter scanning method was used to generate 10571 simulated transmission spectra in the two-dimensional FDTD model. Each transmission spectrum consisted of 501 data points, and the wavelength range of the transmission spectrum was 1500-1600nm. The ratio of the training set to the test set was 8:2.

[0089] Specifically, the established multi-network cascade model is as follows: Figure 3 As shown in the figure, it consists of a one-dimensional convolution inverse design model, an amplitude coupling ratio prediction model, a photon energy band calculation module based on the transfer matrix method, and a transmission spectrum forward prediction model. The input and output of the overall model are both transmission spectrum data. The error between the predicted transmission spectrum and the true transmission spectrum is used to calculate the loss function and perform back propagation. This ensures a one-to-one correspondence between the predicted transmission spectrum and the true transmission spectrum, eliminating the impact of non-uniqueness on the prediction accuracy. In addition, the multi-network cascade model integrates multi-dimensional data sets such as transmission spectrum, structural parameters, amplitude coupling ratio, and photon energy band, which can further improve the accuracy of the model.

[0090] Specifically, in order to enhance the expressive power of the network, the weights of each layer of the network are weighted and summed to complete the nonlinear transformation. The activation function uses the ReLU activation function, which is the most commonly used activation function in deep neural networks. It has the advantages of fast calculation speed and anti-gradient disappearance. Its expression is:

[0091] Relu(x)=max(0,x) (1)

[0092] Specifically, the loss function is used to measure the difference between the model output and the true value. Huber Loss is a loss function used for regression problems. It combines the advantages of mean square error (MSE) and mean absolute error (MAE). This embodiment will use it to calculate the prediction error of all models. Its definition is as follows:

[0093]

[0094] Where y is the true parameter, f(x) is the predicted parameter, and δ is the parameter of Huber Loss. When the predicted deviation is less than or equal to δ, Huber Loss uses MSE to reduce the model's sensitivity to small deviations; when the predicted deviation is greater than δ, it switches to MAE to reduce the sensitivity to large deviations (such as outliers). It is a loss function with parameters used to solve regression problems.

[0095] Specifically, in order to evaluate the reliability of the model, this embodiment will calculate the mean relative error (MRE) and the accuracy rate of the network; MRE is the average value of the relative difference between the predicted value and the actual value, and its expression is:

[0096]

[0097] Where n is the sample size, y i is the true value, is the predicted value.

[0098] The opposite is the concept of accuracy. In this embodiment, for regression problems using minimum-maximum normalization, the accuracy is calculated as follows:

[0099]

[0100] Where N is the sample size, y i is the true value, is the predicted value, and the latter two are normalized values.

[0101] Specifically, the forward prediction model consists of an energy band image encoder and an energy band-transmission spectrum decoder. The coupling ratio prediction model and the transmission spectrum forward prediction model transmit data through the photon energy band. The specific architecture of the above model is as follows:

[0102] One-dimensional convolutional reverse design network: This network inputs one-dimensional transmission spectrum data with a length of 501 and outputs one-dimensional structural parameter combination data with a length of 3. This network learns the complex mapping relationship between transmission spectrum and structural parameters through a one-dimensional convolutional neural network to achieve the function of reverse design.

[0103] Specifically, the Pytorch framework in Python is used to build and train the model, and a 1D-CNN consisting of a convolutional layer and a fully connected layer is adopted. First, the transmission spectrum data with a length of 501 is input, and then it passes through four one-dimensional convolutional layers and a pooling layer, and is accelerated by batchnorm1d in the middle, and then sent to the fully connected layer for processing, and finally a structural parameter of size 3 is obtained;

[0104] Amplitude coupling ratio prediction network: This network takes the output of the one-dimensional convolutional inverse design network as input, i.e., one-dimensional structural parameter combination data of length 3, and generates amplitude coupling ratio data of length 1; this network builds a model through a deep fully connected neural network to accurately predict the required coupling ratio;

[0105] Specifically, a fully connected layer of 512×64×16×16×3 is used, and each neuron is connected to all neurons in the previous layer; through these linear layers, the model gradually extracts key features in the data and finally obtains the coupling ratio k;

[0106] MATLAB mathematical model based on transfer matrix method: After the amplitude coupling ratio prediction network, a MATLAB mathematical model based on transfer matrix method is introduced into the model chain; the model receives the structural parameters and amplitude coupling ratio output by the aforementioned network, calculates and generates a photon band image; the mathematical model converts the prediction results of the aforementioned neural network into a photon band image, providing input for the subsequent encoder;

[0107] Specifically, the transmission matrix representing the coupling relationship of the optical microring array in the x and y directions can be expressed as:

[0108]

[0109]

[0110] The above formula can be used to solve the projected energy band of periodic lattices, and can also be used to calculate the projected energy band of finite light microring arrays;

[0111] Combining formulas (5), (6) and Bloch's theorem, we can simplify it to get x and M y The eigenvalue equations of the underlying periodic lattice are expressed as:

[0112]

[0113] Find the eigenvalue of formula (7) and transform the eigenvalue equation into:

[0114]

[0115] Discard each eigenvalue that does not have a unit mode, and then scan k x The projected band diagram of the underlying periodic lattice can be obtained by using the phase;

[0116] Photon band encoder: This encoder receives the photon band image of size 267×200 calculated by the transfer matrix method and encodes it into a one-dimensional band image code of length 8192. The encoder is designed to generate an efficient intermediate feature representation to associate the complex band image data with the transmission spectrum data.

[0117] Specifically, the band image encoder model is mainly constructed by convolutional layers and fully connected layers, which are used to convert the two-dimensional band image into a one-dimensional code. The size of the initial band image is 267×200 pixels. The image size is reduced to 50×66 through four convolutional layers and pooling layers, and then converted into a one-dimensional code of 8192 through a flattening layer. The flattening layer arranges the pixels in the image in a one-dimensional order so that the subsequent fully connected layer can process them. Next, the one-dimensional code is gradually reduced in dimension through four linear layers, and finally a one-dimensional code of size 501 is obtained.

[0118] Energy band-transmission spectrum decoder: Finally, the decoder receives the output of the energy band-transmission spectrum encoder, i.e., the one-dimensional energy band image encoding of length 8192, and decodes it back to the one-dimensional transmission spectrum data of length 501; the purpose of the decoder is to reconstruct the original transmission spectrum information and complete the data conversion process of the entire model;

[0119] The specific multi-network cascade model process is as follows Figure 4 As shown in the figure, the training process is divided into two stages. First, each sub-model is trained independently, and then these sub-models are integrated to train the entire cascade model. In the initial stage, a comprehensive data set including transmission spectrum, structural parameters, amplitude coupling ratio and photon energy band data needs to be generated, and necessary preprocessing operations are performed on the transmission spectrum and photon energy band data. Next, each sub-model is trained. The inverse design model is responsible for mapping the transmission spectrum of the topological optical switch to its corresponding structural parameters. The amplitude coupling ratio prediction model outputs the corresponding amplitude coupling ratio according to the input structural parameters. The transfer matrix method calculation module is based on The photon energy band is calculated and output according to the structural parameters and the amplitude coupling ratio; the forward prediction model takes the photon energy band as input and predicts the corresponding transmission spectrum; at this stage, all trained sub-models will be properly saved; then, the trained sub-models will be cascaded to train the overall cascade model. During the training of the overall cascade model, the inverse design model will undergo secondary training to optimize the performance; after the training is completed, the overall model and the inverse design model will be saved; by loading the saved inverse design model file and inputting the target transmission spectrum, the structural parameters that meet the requirements of the ideal optical properties can be quickly predicted;

[0120] Finally, the predicted structural parameters are input into the FDTD simulation software to generate the transmission spectrum, which is then compared and verified with the original prediction results to evaluate the accuracy and reliability of the model.

[0121] Specifically, the overall training process of the cascade model is as follows: Figure 5 As shown; by directly calling each sub-model file, the cascade model is constructed according to the input-output relationship of each model. Among them, the link between the amplitude coupling ratio prediction model and the forward model needs to calculate the photon energy band through MATLAB. This step is achieved by using Python to call the transfer matrix method to generate the MATLAB file of the photon energy band, so that the cascade model is constructed.

[0122] Specifically, during the overall training process, the number of MATLAB parallel processes is set to 20, and 20 independent computing processes will be started at the same time to perform the photon energy band calculation task, which will significantly improve the processing speed of computationally intensive tasks; the loss function of the overall model calculates the Huber Loss between the input transmission spectrum and the predicted transmission spectrum, and passes the error to the Adam optimizer to optimize the encoder parameters to ensure that the training process can converge stably; during the training process, the learning rate is reduced from the original 10E-4 to 10E-5. After multiple iterative training, the model will continuously adjust the parameters until the error of the predicted transmission spectrum tends to be stable, thereby optimizing the model performance;

[0123] exist Figure 6 (a) shows the overall training loss change of the multi-network cascade model, where the dark curve depicts the error on the training set, while the light curve reflects the performance on the test set; after 500 iterations of rigorous training, the loss value of the cascaded overall model on the test set has significantly dropped to 0.00943, and the prediction accuracy of the model has also increased from 89.3% to 91.3%; the training loss of the sub-reverse design model is shown in Figure 6 As shown in (b), the loss value on the test set is reduced to 0.00026, and the accuracy is improved from 96.6% to 98.4%. Table 1 shows the comparison results of the network prediction accuracy;

[0124] Table 1 Error comparison before and after overall training of multi-network cascade model

[0125] Training Method Overall cascade model prediction accuracy Prediction accuracy of the reverse design model Not cascaded 89.3% 96.6% After cascading 91.3% 98.4%

[0126] Figure 7 The dB graph of the transmission spectrum predicted by the model training is shown, where the dark solid line represents the true transmission spectrum and the light dashed line represents the predicted transmission spectrum. It can be observed that the prediction overlap is higher in the flat area of ​​the transmission spectrum, and the prediction effect is also improved in the steep area of ​​the transmission spectrum.

[0127] The training effect of the cascaded overall model is verified by FDTD simulation, which can more accurately evaluate the model performance. To ensure the rationality of the results, this study first screened a transmission spectrum from the test data set, and used the direct inverse model and the overall trained sub-inverse model to predict the structural parameters of this spectrum. Table 2 shows the structural parameter results predicted by the two models.

[0128] Table 2 Structural parameter prediction results

[0129]

[0130] The training effect of the cascaded overall model is verified by FDTD simulation, which can more accurately evaluate the model performance. To ensure the rationality of the results, a transmission spectrum is first selected from the test data set, and the direct inverse model and the overall trained sub-inverse model are used to predict the structural parameters of this spectrum. Table 2 shows the structural parameter results and average relative errors predicted by the two models. It can be clearly seen that the error of the sub-inverse model after overall training is lower than that of the direct inverse model, which is controlled within 0.25E-2. Subsequently, the predicted structural parameter combinations are substituted into the FDTD simulation to obtain the transmission spectrum. The comparison of the transmission spectrum simulation results is shown in Table 2. Figure 8 As shown in the figure, the dark solid line, dark dashed line and light dashed line represent the real transmission spectrum, the simulated transmission spectrum of the structural parameters predicted by the direct inverse model and the simulated transmission spectrum of the structural parameters predicted by the sub-inverse model after overall training respectively; by observing the transmission spectrum comparison chart, it can be found that the transmission spectrum obtained in the simulation by the structural parameters predicted by the sub-inverse model after overall training has a higher consistency with the real transmission spectrum; for the topological optical switch structure, even a slight deviation in the structural parameters will cause a significant deviation in the transmission spectrum, so a more accurate deep learning model is needed to ensure the accuracy and reliability of the prediction results;

[0131] It can be proved that the use of multi-network cascade model can effectively eliminate the interference caused by non-uniqueness problems and effectively assist in training the sub-inverse model, making the sub-inverse model more accurate;

[0132] Based on the principles of deep learning and transfer matrix method, the present invention proposes a multi-network cascade model. By cascading, the advantages of multiple models are integrated into a unified framework to achieve more accurate prediction, which is suitable for solving the non-uniqueness and multi-degree-of-freedom problems in the reverse design of topological optical switches. It mainly includes the design and training of a one-dimensional convolution inverse design model, an amplitude coupling ratio prediction model, a forward prediction model and an overall model. In the process of constructing the cascade model, each sub-model is firstly trained to ensure that each sub-model has achieved a high accuracy rate on the training set, and then these sub-models are cascaded according to the design order of the cascade network, so that the output of each network becomes the next network. The input of the network is a multi-network cascade model; the photon energy band used to connect the amplitude coupling ratio prediction model and the forward prediction model is calculated by the transfer matrix method; the forward prediction model is trained using an encoder network, and the photon energy band and transmission spectrum that are difficult to form a mapping relationship are converted into network coding for indirect training, which improves the accuracy of the forward prediction model; finally, the multi-network cascade model is trained as a whole and simulated and verified in FDTD. The simulation results show that there is a high degree of consistency between the spectrum predicted by the model and the original spectrum; in addition, after the multi-network cascade model is trained, the accuracy of the cascade model after overall training is 91.3%, of which the accuracy of the inverse design model is 98.4%.

[0133] The embodiments of the present invention are described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific implementation modes, which are merely illustrative rather than restrictive. Under the guidance of the present invention, ordinary technicians in this field can also make many forms without departing from the scope of protection of the present invention and the claims, all of which are within the protection of the present invention.

Claims

1. A topological optical switch structure design method based on a multi-network cascade model, characterized in that: The following steps are involved: S1: using a parameter scanning method and a finite difference time domain method, a comprehensive data set is obtained, wherein the comprehensive data set includes transmission spectrum data, structural parameter data, amplitude coupling ratio data and photon band image data; S2: constructing a one-dimensional convolution inverse design network, an amplitude coupling ratio prediction network, a mathematical model based on the transfer matrix method, and a transmission spectrum forward prediction model; the one-dimensional convolution inverse design network is used to predict structural parameter data based on transmission spectrum data; The amplitude coupling ratio prediction network is used to predict the amplitude coupling ratio data according to the structural parameter data; the mathematical model based on the transfer matrix method is used to calculate the photon band image data according to the structural parameter data and the amplitude coupling ratio data; the transmission spectrum forward prediction model is used to predict the transmission spectrum data according to the photon band image data; S3: using the comprehensive data set, independently training the one-dimensional convolutional inverse design network, the amplitude coupling ratio prediction network and the transmission spectrum forward prediction model, respectively, to obtain a trained one-dimensional convolutional inverse design network, a trained amplitude coupling ratio prediction network and a trained transmission spectrum forward prediction model; S4: obtaining a multi-network cascade model according to the trained one-dimensional convolution inverse design network, the trained amplitude coupling ratio prediction network, the mathematical model based on the transfer matrix method and the trained transmission spectrum forward prediction model; and performing overall training on the multi-network cascade model using a loss function according to the comprehensive data set to obtain an optimized one-dimensional convolution inverse design network; S5: According to the target transmission spectrum data, the optimized one-dimensional convolution inverse design network is used to obtain the target structure parameters.

2. The topological optical switch structure design method based on a multi-network cascade model according to claim 1 is characterized in that: The one-dimensional convolutional inverse design network includes a one-dimensional convolutional neural network, which is used to learn the mapping relationship between the transmission spectrum and the structural parameters, and the one-dimensional convolutional neural network includes a convolutional layer and a fully connected layer; the amplitude coupling ratio prediction network takes the output of the one-dimensional convolutional inverse design network as input and outputs amplitude coupling ratio data, and the amplitude coupling ratio prediction network is a deep fully connected neural network, and the amplitude coupling ratio prediction network includes a 512×64×16×16×3 fully connected layer, and each neuron in the fully connected layer is connected to all neurons in the previous layer; the mathematical model based on the transfer matrix method receives the structural parameters and amplitude coupling ratio output by the one-dimensional convolutional inverse design network. The amplitude coupling ratio prediction network outputs the amplitude coupling ratio data, calculates and generates a photon band image; the transmission spectrum forward prediction model includes a photon band encoder and a band-transmission spectrum decoder; the photon band encoder is used to receive a photon band image with a size of 267×200 calculated by the transfer matrix method, and encodes it into a one-dimensional band image code with a length of 8192; the photon band encoder includes a convolutional layer and a fully connected layer; the band-transmission spectrum decoder is used to receive the one-dimensional band image code of 8192 output by the photon band encoder, and decode it back to a one-dimensional transmission spectrum data with a length of 501; the band-transmission spectrum decoder includes a convolutional layer and a fully connected layer.

3. The topological optical switch structure design method based on a multi-network cascade model according to claim 1 is characterized in that: The mathematical model based on the transfer matrix method predicts the amplitude coupling ratio data of the network output according to the structural parameters and amplitude coupling ratio output by the one-dimensional convolution inverse design network, and obtains the eigenvalue according to the eigenvalue by using the transfer matrix method and Bloch theorem, and discards each eigenvalue that does not have a unit mode, and then obtains the eigenvalue by scanning the Bloch wave vector k. x and phase, we get the photon energy band image, as shown in the formula: Among them, M x is the transmission matrix representing the coupling relationship of the microring resonator coupling array in the x direction, M y is the transmission matrix representing the coupling relationship of the microring resonator coupling array in the y direction, k and τ are the amplitude coupling ratio and amplitude transmission ratio between the field ring and the connecting ring, respectively, and both satisfy |k 2 +τ 2 =1, φ is the phase shift produced when the optical path is one quarter of the circumference of the micro-ring; det(S) is The determinant of k x is the Bloch wave vector, b' is the input amplitude at the coupling point between the adjacent connecting ring and the field ring, and d' is the output amplitude at the coupling point between the adjacent connecting ring and the field ring.

4. The topological optical switch structure design method based on a multi-network cascade model according to claim 1 is characterized in that: The loss function is as follows: Among them, L δ (y,f(x)) is the loss function, y is the true parameter, f(x) is the predicted parameter, and δ is the parameter of Huber Loss.

5. A topological optical switch structure design system, characterized in that: The topological optical switch structure design system includes the following modules: A comprehensive data set acquisition module is configured to: obtain a comprehensive data set using a parameter scanning method and a finite difference time domain method, wherein the comprehensive data set includes transmission spectrum data, structural parameter data, amplitude coupling ratio data, and photon energy band image data; A sub-model construction module is configured to: construct a one-dimensional convolution inverse design network, an amplitude coupling ratio prediction network, a mathematical model based on a transfer matrix method, and a transmission spectrum forward prediction model; the one-dimensional convolution inverse design network is used to predict structural parameter data based on transmission spectrum data; The amplitude coupling ratio prediction network is used to predict the amplitude coupling ratio data according to the structural parameter data; the mathematical model based on the transfer matrix method is used to calculate the photon band image data according to the structural parameter data and the amplitude coupling ratio data; the transmission spectrum forward prediction model is used to predict the transmission spectrum data according to the photon band image data; The sub-model training module is configured to: use the comprehensive data set to independently train the one-dimensional convolution inverse design network, the amplitude coupling ratio prediction network and the transmission spectrum forward prediction model, respectively, to obtain a trained one-dimensional convolution inverse design network, a trained amplitude coupling ratio prediction network and a trained transmission spectrum forward prediction model; The model training and optimization module is configured to obtain a multi-network cascade model according to the trained one-dimensional convolution inverse design network, the trained amplitude coupling ratio prediction network, the mathematical model based on the transfer matrix method and the trained transmission spectrum forward prediction model; According to the comprehensive data set, the multi-network cascade model is trained as a whole using a loss function to obtain an optimized one-dimensional convolutional inverse design network; The structural inverse design module is configured to obtain target structural parameters according to target transmission spectrum data using the optimized one-dimensional convolution inverse design network.

6. A topological optical switch structure design system according to claim 5, characterized in that: The one-dimensional convolutional inverse design network includes a one-dimensional convolutional neural network, which is used to learn the mapping relationship between the transmission spectrum and the structural parameters, and the one-dimensional convolutional neural network includes a convolutional layer and a fully connected layer; the amplitude coupling ratio prediction network takes the output of the one-dimensional convolutional inverse design network as input and outputs amplitude coupling ratio data, and the amplitude coupling ratio prediction network is a deep fully connected neural network, and the amplitude coupling ratio prediction network includes a 512×64×16×16×3 fully connected layer, and each neuron in the fully connected layer is connected to all neurons in the previous layer; the mathematical model based on the transfer matrix method receives the structural parameters and amplitude coupling ratio output by the one-dimensional convolutional inverse design network. The amplitude coupling ratio prediction network outputs the amplitude coupling ratio data, calculates and generates a photon band image; the transmission spectrum forward prediction model includes a photon band encoder and a band-transmission spectrum decoder; the photon band encoder is used to receive a photon band image with a size of 267×200 calculated by the transfer matrix method, and encodes it into a one-dimensional band image code with a length of 8192; the photon band encoder includes a convolutional layer and a fully connected layer; the band-transmission spectrum decoder is used to receive the one-dimensional band image code of 8192 output by the photon band encoder, and decode it back to a one-dimensional transmission spectrum data with a length of 501; the band-transmission spectrum decoder includes a convolutional layer and a fully connected layer.

7. A topological optical switch structure design system according to claim 5, characterized in that: The mathematical model based on the transfer matrix method predicts the amplitude coupling ratio data of the network output according to the structural parameters and amplitude coupling ratio output by the one-dimensional convolution inverse design network, and obtains the eigenvalue according to the eigenvalue by using the transfer matrix method and Bloch theorem, and discards each eigenvalue that does not have a unit mode, and then obtains the eigenvalue by scanning the Bloch wave vector k. x and phase, we get the photon energy band image, as shown in the formula: Among them, M x is the transmission matrix representing the coupling relationship of the microring resonator coupling array in the x direction, M y is the transmission matrix representing the coupling relationship of the microring resonator coupling array in the y direction, k and τ are the amplitude coupling ratio and amplitude transmission ratio between the field ring and the connecting ring, respectively, and both satisfy |k 2 +τ 2 =1, φ is the phase shift produced when the optical path is one quarter of the circumference of the micro-ring; det(S) is The determinant of k x is the Bloch wave vector, b' is the input amplitude at the coupling point between the adjacent connecting ring and the field ring, and d' is the output amplitude at the coupling point between the adjacent connecting ring and the field ring.

8. A topological optical switch structure design system according to claim 5, characterized in that: The loss function is as follows: Among them, L δ (y,f(x)) is the loss function, y is the true parameter, f(x) is the predicted parameter, and δ is the parameter of Huber Loss.

Citation Information

Patent Citations

  • Method and apparatus for determining structural parameters of surface plasmon waveguide systems

    CN109117575A

  • Radar target Doppler image classification and identification method based on one-dimensional convolutional neural network

    CN111220958A

  • Grating optical filter structure optimization method based on neural network

    CN112926157A

  • Photon energy band prediction transmission spectrum model training and prediction method, medium and equipment

    CN117313531A

  • Method and system for reverse design of micro-nano structure based on deep neural network

    US20220398351A1

Cited By

  • Design method and system of grating coupler, computer equipment and storage medium

    CN119808571A

  • Intelligent optical computing non-linear convolution chip system, method and architecture

    CN119940421A