CN114553650A - Multi-level neural network-based anti-mode coupling signal complex format analysis method - Google Patents
Multi-level neural network-based anti-mode coupling signal complex format analysis method Download PDFInfo
- Publication number
- CN114553650A CN114553650A CN202210447635.0A CN202210447635A CN114553650A CN 114553650 A CN114553650 A CN 114553650A CN 202210447635 A CN202210447635 A CN 202210447635A CN 114553650 A CN114553650 A CN 114553650A
- Authority
- CN
- China
- Prior art keywords
- neural network
- convolutional neural
- mode
- modulation format
- network model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L27/00—Modulated-carrier systems
- H04L27/0012—Modulated-carrier systems arrangements for identifying the type of modulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/08—Feature extraction
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Molecular Biology (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computing Systems (AREA)
- General Health & Medical Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Optical Communication System (AREA)
Abstract
The invention discloses an anti-mode coupling signal complex format analysis method based on a multi-level neural network, which comprises the steps of generating an unknown signal constellation diagram according to a received unknown signal; and inputting the unknown signal constellation diagram into the convolutional neural network model obtained by training, and predicting to obtain a transmission mode and a modulation format. Training to obtain a convolutional neural network model: extracting high-dimensional information characteristics from the constellation map with the label by the convolutional neural network model; according to the high-dimensional information characteristics, judging to obtain a transmission mode and a modulation format; and comparing the transmission mode and the modulation format obtained by judgment with the label, and performing parameter updating iteration on the convolutional neural network model. The invention solves the problem of coupling between modes in the mode division multiplexing, can accurately identify the modulation format of an unknown signal constellation diagram under the condition of higher coupling coefficient for the interference of the modulation format identification, reduces the interference of mode coupling to a received signal, and has more accurate modulation format identification result and stronger robustness.
Description
Technical Field
The invention relates to an anti-mode coupling signal complex format analysis method based on a multi-level neural network, and belongs to the technical field of deep learning technology and signal complex format analysis.
Background
With the continuous improvement of social informatization degree, emerging technologies such as video services, 5G and internet of things and new services such as big data services and cloud computing are emerging continuously, data services are continuously increased at an explosive speed, and existing optical fiber transmission resources are rapidly consumed. The current network flow is close to the limit of the existing transmission technology, the demand of expanding the transmission bandwidth is pressing day by day, and the development of a novel transmission technology to meet the requirement of future network development becomes an urgent task. However, the dimensions of amplitude, phase, frequency, time slot, polarization and the like of light in the optical fiber transmission network are fully utilized, and only the spatial dimension still has huge development potential. Therefore, the space division multiplexing technology based on the space dimension becomes a hot spot technology for solving the difficult problem of channel capacity.
The mode division multiplexing technology is a kind of space division multiplexing technology, that is, a technical mode that different modes are used as independent channels to carry different information by utilizing orthogonality among the modes in an optical fiber so as to enable the information to be simultaneously propagated in the optical fiber. Ideally, the different modes carrying the signal in the fiber are orthogonal to each other and no crosstalk occurs during transmission. The transmission capacity of the corresponding channel can be expanded by how many modes exist in the optical fiber, and the modes in the optical fiber can independently propagate without influencing each other. In the next generation of elastic optical network based on the modulo division multiplexing technique, a transmitting end dynamically changes parameters such as symbol rate or modulation format of a transmitted signal according to user service and system resources, and a receiving signal is unknown to a receiver.
However, in the actual few-mode optical fiber, due to the manufacturing process limitation and the external force influence, random coupling occurs in signals of each mode in the transmission process, and the transmission performance is seriously influenced. To solve the mode coupling problem, there are generally two schemes for the mode division multiplexing system. The first is to reduce the requirement of absolute orthogonality of signals in a link, tolerate a certain degree of coupling of the signals, and realize signal recovery by using a MIMO equalizer at a receiving end. However, for strong coupling, the complexity of the MIMO algorithm may increase significantly. The second is to keep the modes in the channel as orthogonal as possible to reduce the crosstalk between the modes, which is a more demanding solution for the optics on the link.
Mode coupling in a mode multiplexing system is one of the main impairments of a mode division multiplexing system, and is introduced by two devices, a mode multiplexer and a few-mode fiber. As shown in fig. 1, different modes carrying signals in the few-mode optical fiber are orthogonal to each other in an ideal case, and no crosstalk occurs during transmission. However, in an actual few-mode optical fiber, as shown in fig. 2, due to the manufacturing process limitation and the external force influence on the optical fiber during use, orthogonality of modes in the few-mode optical fiber is destroyed, and random coupling occurs in signals of each mode during transmission, which seriously affects transmission performance. The coupling between the degenerate mode and the non-degenerate mode ensures that the propagation constants of the modes are not equal any more, and the random energy migration causes crosstalk between signals, thereby influencing all code elements and leading the MIMO algorithm of a receiving end to become complex.
Disclosure of Invention
The technical problem to be solved by the invention is to overcome the defects of the prior art and provide an anti-mode coupling signal complex format analysis method based on a multi-level neural network.
In order to achieve the above object, the present invention provides a method for analyzing complex format of anti-mode coupling signal based on multi-level neural network, comprising:
generating an unknown signal constellation diagram according to the received unknown signal;
inputting an unknown signal constellation diagram into a convolutional neural network model obtained by training, and predicting to obtain a transmission mode and a modulation format;
training to obtain a convolutional neural network model, comprising:
inputting a training data set into a convolutional neural network model, wherein the training data set comprises a constellation diagram with labels;
extracting high-dimensional information characteristics from the constellation map with the label by the convolutional neural network model;
according to the high-dimensional information characteristics, judging to obtain a transmission mode and a modulation format;
comparing the transmission mode and the modulation format obtained by judgment with the label, and performing parameter updating iteration on the convolutional neural network model;
repeating the steps until a preset iteration number is reached, and obtaining a final convolution neural network model;
according to the high-dimensional information characteristics, the transmission mode and the modulation format are judged and obtained, and the method comprises the following steps:
the convolutional neural network model comprises a first stage convolutional neural network and a second stage convolutional neural network,
extracting high-dimensional information characteristics and judging a transmission mode by a first-stage convolutional neural network;
the second-stage convolutional neural network acquires parameters output by the first-stage convolutional neural network and identifies a modulation format;
the first-stage convolutional neural network and the second-stage convolutional neural network respectively comprise a first convolutional layer, a second convolutional layer, a first pooling layer, a second pooling layer, a first full-connection layer and a second full-connection layer, and the first convolutional layer, the first pooling layer, the second convolutional layer, the second pooling layer, the first full-connection layer and the second full-connection layer are sequentially connected.
Preferably, the transmission mode and the modulation format obtained by the judgment are compared with the label, and the parameter updating iteration is carried out on the convolutional neural network model, and comprises the following steps:
comparing the transmission mode and the modulation format obtained by judgment with the label to obtain the judged data distribution and the correct data distribution in the label;
calculating the mean square error of the determined data distribution and the correct data distribution in the label;
and updating parameters including neuron bias and weight in the iterative convolutional neural network model.
Preferably, the labeled constellation is generated based on the optical signal at different known coupling coefficients for different known transmission modes.
Preferably, the high-dimensional information features extracted by the first-stage convolutional neural network comprise a CCD light spot mode field diagram, an imaging frequency spectrum and a double Fourier transform sequence of a transmission signal.
Preferably, the parameters output by the first stage convolutional neural network include a signal constellation, stokes space spherical mapping parameters and high-order cumulant.
Preferably, before the unknown signal constellation diagram is input into the convolutional neural network model obtained by training, the unknown signal constellation diagram is subjected to averaging and normalization processing.
A storage medium having stored thereon a computer program which, when executed by a processor, carries out the steps of any of the methods described above.
The invention achieves the following beneficial effects:
according to the method, a multi-level convolutional neural network is constructed, the constellation diagram characteristics of transmission signals with different modulation formats in different modes when mode coupling exists are learned, the strong fitting capacity of the neural network is utilized, the influence of mode coupling in a few-mode optical fiber on a signal constellation diagram is learned, and through the concept of 'layering step by step', the first-level convolutional neural network is used for overcoming the mode coupling in the few-mode optical fiber and judging the transmission mode of an unknown signal constellation diagram; the second-stage convolutional neural network is used for outputting the modulation format in the transmission mode, so that the problem of inter-mode coupling in the mode division multiplexing is solved, the modulation format of an unknown signal constellation can be accurately identified under the condition of higher coupling coefficient for the interference of the modulation format identification, and the interference of the mode coupling on a received signal is reduced, so that the modulation format identification result is more accurate, and the robustness is stronger; after the modulation format of the received optical signal is known, a series of signal processing such as adaptive equalization, frequency offset recovery and carrier phase recovery can be conveniently carried out on the received optical signal by selecting different algorithms according to different modulation formats.
Drawings
FIG. 1 is a schematic diagram illustrating the effect of mode coupling on a transmission signal in ideal transmission;
FIG. 2 is a schematic diagram of the effect of mode coupling on a transmission signal under actual transmission;
FIG. 3 is a flow chart of the present invention;
FIG. 4 is a functional block diagram of the present invention;
FIG. 5 is a block diagram of a single layer convolutional neural network of the present invention;
fig. 6 is a flow chart of an embodiment of the present invention.
Detailed Description
The following examples are only for illustrating the technical solutions of the present invention more clearly, and the protection scope of the present invention is not limited thereby.
Example one
The method for analyzing the complex format of the anti-mode coupling signal based on the multi-level neural network comprises the following steps:
generating an unknown signal constellation diagram according to the received unknown signal;
and inputting the unknown signal constellation diagram into a convolutional neural network model obtained by training, and predicting to obtain a transmission mode and a modulation format.
Further, in this embodiment, the training to obtain the convolutional neural network model includes:
inputting a training data set into a convolutional neural network model, wherein the training data set comprises a constellation diagram with labels;
extracting high-dimensional information characteristics from the constellation map with the label by the convolutional neural network model;
according to the high-dimensional information characteristics, judging to obtain a transmission mode and a modulation format;
comparing the transmission mode and the modulation format obtained by judgment with the label, and performing parameter updating iteration on the convolutional neural network model;
and repeating the steps until the preset iteration times are reached, and obtaining the final convolutional neural network model.
Further, in this embodiment, comparing the determined transmission mode and modulation format with the label, and performing parameter update iteration on the convolutional neural network model, including:
comparing the transmission mode and the modulation format obtained by judgment with the label to obtain the judged data distribution and the correct data distribution in the label;
calculating the mean square error of the determined data distribution and the correct data distribution in the label;
and updating parameters including neuron bias and weight in the iterative convolutional neural network model.
Further, the labeled constellation diagram in this embodiment is generated according to the optical signal under different known coupling coefficients of different known transmission modes.
Further, in the present embodiment, the determining to obtain the transmission mode and the modulation format according to the high-dimensional information characteristics includes:
the convolutional neural network model comprises a first stage convolutional neural network and a second stage convolutional neural network,
extracting high-dimensional information characteristics and judging a transmission mode by a first-stage convolutional neural network;
and the second-stage convolutional neural network acquires parameters output by the first-stage convolutional neural network and identifies a modulation format.
Further, in the present embodiment, the high-dimensional information features extracted by the first-stage convolutional neural network include a CCD light spot mode field pattern, an imaging spectrum, and a double fourier transform sequence of the transmission signal.
Further, in this embodiment, the parameters output by the first-stage convolutional neural network include a signal constellation, stokes space spherical mapping parameters, and high-order cumulants.
Further, in this embodiment, the first-stage convolutional neural network and the second-stage convolutional neural network both include a first convolutional layer, a second convolutional layer, a first pooling layer, a second pooling layer, a first fully-connected layer, and a second fully-connected layer, and the first convolutional layer, the first pooling layer, the second convolutional layer, the second pooling layer, the first fully-connected layer, and the second fully-connected layer are sequentially connected.
Further, in this embodiment, before the unknown signal constellation is input into the convolutional neural network model obtained by training, the unknown signal constellation is subjected to averaging and normalization.
Electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps of any of the above methods when executing the program.
A storage medium having stored thereon a computer program which, when executed by a processor, carries out the steps of any of the methods described above.
The method proposed by the present invention is divided into a training phase and a discrimination phase as shown in fig. 3. Mode coupling in fiber optic communication systems causes the energy of optical signals transmitted between different modes to shift randomly. And in the training stage, the convolutional neural network model is supervised and learned by utilizing the training data set. The constellation in the training data set is generated at the receiving end under different transmission modes and different coupling coefficients according to the input known optical signal.
And the two-stage convolutional neural network of the convolutional neural network model respectively extracts high-dimensional information characteristics from the constellation diagram with the label and judges the transmission mode and the modulation format of the input known optical signal.
And comparing the identification result with the label, performing parameter updating iteration on the convolutional neural network model, meeting the iteration times, and completing the optimization of the convolutional neural network model.
In the discrimination stage, the receiver receives an unknown signal, which is an optical signal with unknown transmission mode and unknown modulation format. And the receiving end generates a constellation diagram according to the received unknown signal, and inputs the constellation diagram into the convolutional neural network model obtained by training. After simple preprocessing such as averaging and normalization, the constellation diagram is sent to a trained convolutional neural network model. And the first-stage convolutional neural network of the convolutional neural network model judges the transmission mode of the unknown signal according to the extracted high-dimensional information characteristics, and the second-stage convolutional neural network of the convolutional neural network model identifies the modulation format of the unknown signal according to the parameters output by the first-stage convolutional neural network, so that the complex format analysis of the unknown signal is completed.
The scheme of the invention solves the influence of the modal crosstalk on the receiving end by using a multi-stage neural network mode, as shown in fig. 4. The first-stage convolutional neural network comprises an input layer, a first hidden layer and a first output layer, the second-stage convolutional neural network comprises a second hidden layer and a second output layer, each layer is provided with a plurality of neurons, the input layer receives a large amount of nonlinear input information, the input information is transmitted, analyzed and weighed in the neuron connection of the first hidden layer and is output in the first output layer, the first hidden layer is formed by connecting a large amount of neurons between the input layer and the first output layer, and the first hidden layer is connected through a nonlinear activation function.
According to the scheme, a constellation diagram with a label is used as input of a first-stage convolutional neural network, and after the first-stage convolutional neural network carries out high-dimensional information feature extraction through a first hidden layer, a transmission mode of an unknown signal constellation diagram/training data set is output and used as input of a second-stage convolutional neural network. And analyzing and processing the high-dimensional information characteristics of the constellation diagram by using a second hidden layer in the second-stage convolutional neural network, and finally predicting the modulation format of the unknown signal constellation diagram/training data set. The unknown signals of different modes received are randomly coupled because mode coupling causes energy migration to the unknown signals received. According to the scheme of the invention, crosstalk caused by mode coupling in the received unknown signal is avoided by a mode of firstly identifying the transmission mode of the received unknown signal, and the modulation format of the received unknown signal is identified by the second layer of convolutional neural network through the high-dimensional information characteristic of the constellation diagram.
In the scheme of the present invention, the internal network structures of the first-stage convolutional neural network and the second-stage convolutional neural network are the same, and the specific structures are as shown in fig. 5, and there are 2 convolutional layers, 2 pooling layers, and 2 fully-connected layers, which are the first convolutional layer, the second convolutional layer, the first pooling layer, the second pooling layer, the first fully-connected layer, and the second fully-connected layer, respectively. The convolution layer is used for extracting high-dimensional information characteristics of the constellation diagram, convolution operation can keep the spatial relationship among pixels, a local sub-matrix of the input constellation diagram is changed into an element, and dimension reduction of input image information is completed. The pooling layer may enable sparseness of parameters and reduced data volume. The full-connection layer integrates all the extracted high-dimensional information characteristics, integrates the local information with class distinction in the convolution layer and the pooling layer, and finally gives an output result, wherein the output result comprises a transmission mode and a modulation format.
The signal complex format analysis scheme provided by the invention utilizes the two-stage convolutional neural network to eliminate crosstalk between transmission signals in different modes in the mode division multiplexing communication system, and has good robustness. Meanwhile, the convolutional neural network has strong feature extraction capability on a constellation diagram of an optical signal, and compared with the traditional identification scheme, the convolutional neural network based on machine learning has strong fitting capability. Through supervised training of the training data set, the convolutional neural network can achieve high recognition accuracy.
The modulation format of the signal changes and the algorithms associated with the modulation format in the receiver DSP also need to change. The invention can complete the identification of the modulation format of the received unknown signal, and is convenient for the subsequent digital signal processing of the optical signal.
Aiming at the problem of complex format analysis of signals in the elastic optical network based on the few-mode optical fiber, the invention solves the problem of modulation format identification in the few-mode optical fiber by utilizing the multi-level convolutional neural network, and reduces the interference of mode coupling on the received signals, so that the modulation format identification result is more accurate and the robustness is stronger. The scheme respectively provides the transmission mode and the modulation format of the optical signal through the convolutional neural network by virtue of the concept of 'layering step by step' and by virtue of the constellation diagram of the received optical signal.
Example two
As shown in fig. 6, at the transmitting end of the mode division multiplexing communication system, the transmitter Tx1, the transmitter Tx2, the transmitter Tx3, and the transmitter Tx4 respectively load the modulated optical signals on the four modes LP01, LP11a, LP11b, and LP21 through the mode multiplexer, and transmit the optical signals through the few-mode optical fiber. The optical communication network system can dynamically change various parameters such as modulation format, code element rate and the like of the transmitted optical signal at the transmitting end according to the requirements of users and the condition of a channel, thereby achieving the effect of reasonably allocating system resources. In the process of few-mode fiber transmission, random coupling can be generated in different transmission modes, so that the phenomenon of energy migration is caused. At the receiving end of the mode division multiplexing communication system, the mode demultiplexer demultiplexes the light beam into four modes of LP01, LP11a, LP11b and LP21, the light beam is input into a non-modulation format correlation algorithm and a DSP unit after passing through a receiver Rx1, a receiver Rx2, a receiver Rx3 and a receiver Rx4, and mode coupling can be introduced by the mode multiplexer and the mode demultiplexer due to incomplete energy conversion. The optical signal received by the receiver will affect the transmission performance due to mode coupling.
The receiving end needs to use the DSP unit to perform corresponding algorithm processing such as compensation or equalization on the received optical signal. The DSP unit will first perform non-modulation format dependent algorithms such as clock recovery and dispersion compensation. Then, according to the modulation format correlation algorithm scheme provided by the invention, the convolutional neural network model is utilized to identify the modulation format under the condition of mode coupling. The first convolutional neural network CNN I gives the transmission mode of the received optical signal, and the second convolutional neural network CNN II gives the modulation format of the received optical signal. After the modulation format of the received optical signal is known, different algorithms can be selected to perform a series of signal processing such as adaptive equalization, frequency offset recovery and carrier phase recovery on the received optical signal according to different modulation formats.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The above description is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, it is possible to make various improvements and modifications without departing from the technical principle of the present invention, and those improvements and modifications should be considered as the protection scope of the present invention.
Claims (7)
1. The method for analyzing the complex format of the anti-mode coupling signal based on the multi-level neural network is characterized by comprising the following steps of:
generating an unknown signal constellation diagram according to the received unknown signal;
inputting an unknown signal constellation diagram into a convolutional neural network model obtained by training, and predicting to obtain a transmission mode and a modulation format;
training to obtain a convolutional neural network model, comprising:
inputting a training data set into a convolutional neural network model, wherein the training data set comprises a constellation diagram with labels;
extracting high-dimensional information characteristics from the constellation map with the label by the convolutional neural network model;
according to the high-dimensional information characteristics, judging to obtain a transmission mode and a modulation format;
comparing the transmission mode and the modulation format obtained by judgment with the label, and performing parameter updating iteration on the convolutional neural network model;
repeating the steps until reaching the preset iteration times to obtain a final convolution neural network model;
according to the high-dimensional information characteristics, the transmission mode and the modulation format are judged and obtained, and the method comprises the following steps:
the convolutional neural network model comprises a first stage convolutional neural network and a second stage convolutional neural network,
extracting high-dimensional information characteristics and judging a transmission mode by a first-stage convolutional neural network;
the second-stage convolutional neural network acquires parameters output by the first-stage convolutional neural network and identifies a modulation format;
the first-stage convolutional neural network and the second-stage convolutional neural network respectively comprise a first convolutional layer, a second convolutional layer, a first pooling layer, a second pooling layer, a first full-connection layer and a second full-connection layer, and the first convolutional layer, the first pooling layer, the second convolutional layer, the second pooling layer, the first full-connection layer and the second full-connection layer are sequentially connected.
2. The method for resolving the anti-mode coupling signal complex format based on the multi-level neural network according to claim 1, wherein the iteration of updating the parameters of the convolutional neural network model is performed by comparing the transmission mode and the modulation format obtained by the judgment with the tags, and comprises the following steps:
comparing the transmission mode and the modulation format obtained by judgment with the label to obtain the judged data distribution and the correct data distribution in the label;
calculating the mean square error of the determined data distribution and the correct data distribution in the label;
and updating parameters including neuron bias and weight in the iterative convolutional neural network model.
3. The method according to claim 1, wherein the labeled constellation is generated according to the optical signal under different known coupling coefficients in different known transmission modes.
4. The multi-level neural network-based anti-mode coupling signal complex format resolving method as claimed in claim 1, wherein the high-dimensional information features extracted by the first-level convolutional neural network comprise a CCD light spot mode field pattern, an imaging frequency spectrum and a double Fourier transform sequence of the transmission signal.
5. The multi-level neural network-based anti-mode-coupling signal complex format parsing method as recited in claim 1, wherein the parameters output by the first-level convolutional neural network comprise a signal constellation, stokes space spherical mapping parameters and higher-order cumulants.
6. The method according to claim 1, wherein the unknown signal constellation is averaged and normalized before being input into the convolutional neural network model obtained by training.
7. Storage medium on which a computer program is stored which, when being executed by a processor, carries out the steps of the method of one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210447635.0A CN114553650B (en) | 2022-04-27 | 2022-04-27 | Multi-level neural network-based anti-mode coupling signal complex format analysis method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210447635.0A CN114553650B (en) | 2022-04-27 | 2022-04-27 | Multi-level neural network-based anti-mode coupling signal complex format analysis method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114553650A true CN114553650A (en) | 2022-05-27 |
| CN114553650B CN114553650B (en) | 2022-07-29 |
Family
ID=81667428
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210447635.0A Active CN114553650B (en) | 2022-04-27 | 2022-04-27 | Multi-level neural network-based anti-mode coupling signal complex format analysis method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114553650B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103916186A (en) * | 2014-01-26 | 2014-07-09 | 北京邮电大学 | Method for weakening mode coupling effect in optical fiber mode multiplexing |
| CN107342962A (en) * | 2017-07-03 | 2017-11-10 | 北京邮电大学 | Deep learning intelligence Analysis On Constellation Map method based on convolutional neural networks |
| CN108234370A (en) * | 2017-12-22 | 2018-06-29 | 西安电子科技大学 | Modulation mode of communication signal recognition methods based on convolutional neural networks |
| CN111614398A (en) * | 2020-05-12 | 2020-09-01 | 北京邮电大学 | Method and device for identifying modulation format and signal-to-noise ratio based on XOR neural network |
| CN112308133A (en) * | 2020-10-29 | 2021-02-02 | 成都明杰科技有限公司 | Modulation identification method based on convolutional neural network |
| CN113626960A (en) * | 2021-07-29 | 2021-11-09 | 南京信息工程大学 | Anti-mode coupling few-mode signal complex format analysis method and device |
-
2022
- 2022-04-27 CN CN202210447635.0A patent/CN114553650B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103916186A (en) * | 2014-01-26 | 2014-07-09 | 北京邮电大学 | Method for weakening mode coupling effect in optical fiber mode multiplexing |
| CN107342962A (en) * | 2017-07-03 | 2017-11-10 | 北京邮电大学 | Deep learning intelligence Analysis On Constellation Map method based on convolutional neural networks |
| CN108234370A (en) * | 2017-12-22 | 2018-06-29 | 西安电子科技大学 | Modulation mode of communication signal recognition methods based on convolutional neural networks |
| CN111614398A (en) * | 2020-05-12 | 2020-09-01 | 北京邮电大学 | Method and device for identifying modulation format and signal-to-noise ratio based on XOR neural network |
| CN112308133A (en) * | 2020-10-29 | 2021-02-02 | 成都明杰科技有限公司 | Modulation identification method based on convolutional neural network |
| CN113626960A (en) * | 2021-07-29 | 2021-11-09 | 南京信息工程大学 | Anti-mode coupling few-mode signal complex format analysis method and device |
Non-Patent Citations (1)
| Title |
|---|
| 涂超然: ""多维复用传输系统的关键技术研究"", 《中国优秀博硕士学位论文全文数据库(硕士)信息科技辑》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114553650B (en) | 2022-07-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Fan et al. | Joint optical performance monitoring and modulation format/bit-rate identification by CNN-based multi-task learning | |
| CN110336594B (en) | Deep learning signal detection method based on conjugate gradient descent method | |
| CN113626960B (en) | Anti-mode coupling few-mode signal complex format analysis method and device | |
| US20220239371A1 (en) | Methods, devices, apparatuses, and medium for optical communication | |
| Poudel et al. | MIMO detection using a deep learning neural network in a mode division multiplexing optical transmission system | |
| CN114598582A (en) | Ultra-high order signal modulation format rapid identification method based on transfer learning | |
| Lun et al. | Machine-learning-based telemetry for monitoring long-haul optical transmission impairments: methodologies and challenges | |
| CN113938188A (en) | Construction method and application of optical signal-to-noise ratio monitoring model | |
| Zhang et al. | Modulation format identification in heterogeneous fiber-optic networks using artificial neural networks and genetic algorithms | |
| Song et al. | Experimental study of machine-learning-based detection and location of eavesdropping in end-to-end optical fiber communications | |
| CN114285715B (en) | Nonlinear equalization method based on bidirectional GRU-conditional random field | |
| Guesmi et al. | Modulation formats recognition technique using artificial neural networks for radio over fiber systems | |
| Liu et al. | A data-fusion-assisted telemetry layer for autonomous optical networks | |
| Li et al. | Deep-learning-based multi-user framework for end-to-end fiber-MMW communications | |
| CN114553315A (en) | Optical fiber nonlinear equalization method and system based on CNN-birNN | |
| CN114513394A (en) | Attention machine drawing neural network-based signal modulation format identification method, system and device and storage medium | |
| CN114553650B (en) | Multi-level neural network-based anti-mode coupling signal complex format analysis method | |
| Kulandaivel et al. | Combined image Hough transform based simultaneous multi-parameter optical performance monitoring for intelligent optical networks | |
| Gao et al. | Joint baud-rate and modulation format identification based on asynchronous delay-tap plots analyzer by using convolutional neural network | |
| CN114598581B (en) | Training method, recognition method and device for double-stage detection model of probability shaping signal | |
| CN114358061A (en) | Space division multiplexing signal optical performance monitoring method and system | |
| Fan et al. | Reliable optical performance monitor: the combination of parallel framework and skip connected generative adversarial network | |
| CN113037409B (en) | Large-scale MIMO system signal detection method based on deep learning | |
| CN114337883A (en) | CNN cooperative spectrum sensing method and system based on covariance matrix Cholesky decomposition | |
| Fan et al. | Enhancing the credibility of the optical performance monitor with adversarial training |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |