A method for compensating for optical fiber transmission impairment by fast random kernel transformation

Abstract

The application discloses a kind of fast random convolution kernel transformation optical fiber transmission non-linear compensation methods, belong to optical fiber communication technical field.Adopt multiple random convolution kernel to carry out convolution transformation extraction time sequence characteristics to signal, can be aimed at the signal damage characteristics of transmission system, carry out non-linear damage compensation;Through convolution kernel weight setting, multiplication in the convolution operation process is converted into addition, realize efficient and fast convolution transformation;Through the setting of different expansion coefficients, multiscale extraction signal's time sequence characteristics, so as to extract the long-term time sequence dependence of signal, help signal damage compensation and signal identification of receiving signal;After fast random convolution kernel transformation, only a simple linear classifier can be used to carry out non-linear compensation to damaged signal, avoid the structure design of multilayer neural network and a large amount of calculation overhead.The application is suitable for optical fiber communication technical field, realizes low complexity, high accuracy damage compensation, improves the communication quality of optical communication system.

Description

Technical Field

[0001] The present invention relates to a transmission impairment equalization method for an orbital angular momentum mode multiplexing (OAM-MDM) direct modulation and direct detection (IM / DD) optical fiber transmission system based on fast random convolution kernel transformation, and specifically to a fiber transmission impairment compensation method based on fast random convolution kernel transformation, belonging to the technical field of optical fiber communication. Background Art

[0002] With the continuous development of modern fiber-optic communication systems and the increasing demand for system transmission capacity, traditional modulation techniques based on amplitude, phase, and frequency multiplexing in single-mode fiber (SMF) are gradually failing to meet these requirements. Against this backdrop, space-division multiplexing (SDM) using multi-core fiber (MCF) or multimode fiber (MMF) has attracted the attention of numerous researchers and has been extensively and intensively studied. Since its introduction in 1992, research on OAM beams has rapidly advanced. OAM exhibits infinite dimensions in Hilbert space, offering broad application prospects. For a long time after its introduction, research on OAM beams in communications was limited to free-space transmission systems. This was because the structure of conventional optical fibers restricts the propagation of OAM beams, making them considered unsuitable for optical fiber communications. It was not until the introduction of optical fibers with vortex structures that research on OAM beam transmission in optical fibers began to emerge. Through continuous research and development, these fibers have evolved into ring-core fibers (RCFs) and graded-index ring-core fibers (GIRCFs), which support a wider range of OAM modes. As the capacity of OAM-MDM optical fiber transmission systems increases, the corresponding offline digital signal processing becomes more critical. Therefore, in order to meet the system's bit error rate (BER) performance requirements, it is necessary to study the offline digital signal processing portion of OAM-MDM optical fiber communication systems and appropriately apply better-performing algorithms.

[0003] In OAM-MDM fiber-optic communication systems, system capacity and transmission distance are limited by numerous transmission impairments, the most significant of which is nonlinear impairment, particularly nonlinear impairment caused by optoelectronic devices such as spatial light modulators (SLMs) and photodiodes. Spatial light modulators contain numerous nonlinear materials, such as liquid crystals, nonlinear polymers, and photorefractive materials, which can lead to severe nonlinear impairments. Digital signal processing is typically the preferred approach to mitigate nonlinear impairments. Digital signal processing algorithms, such as Volterra series-based nonlinear equalization (VNE), equalize distorted signals by fitting a nonlinear mathematical model of the system. However, in OAM-MDM systems, the nonlinear impairments of the entire system are highly complex due to the nonlinear coupling of multiple optoelectronic devices. Furthermore, mode coupling within the system also imparts a highly random nature to the nonlinear impairments. Consequently, VNE is ineffective in compensating for impairments in such optical fiber communication systems. Furthermore, to address the difficulty of traditional digital signal processing algorithms in extracting temporal features from signals, deep convolutional neural networks have been proposed for transmission impairment compensation in optical fiber communication systems. However, their deep network design results in slow training convergence, high computational complexity, and significant computational resource consumption. In summary, it is necessary to study a fiber transmission damage compensation method based on fast random convolution kernel transformation. Summary of the Invention

[0004] Aiming at the problem that nonlinear damage caused by graded-index ring-core fiber (GIRCF), spatial light modulator (SLM), Mach-Zehnder modulator (MZM) and photoelectric balanced detector (PD) in OAM mode multiplexing optical transmission systems causes serious signal damage and poor bit error rate performance, the main purpose of the present invention is to provide a fiber transmission damage compensation method based on fast random convolution kernel transformation. The method extracts rich timing features of the received signal through random convolution kernel transformation with diverse weights, expansion coefficients and biases, and inputs them into a linear classifier to perform high-precision signal classification, thereby achieving nonlinear damage compensation for the signal and effective signal equalization, improving the system's bit error rate performance and improving the quality of large-capacity and high-speed fiber-optic communications.

[0005] The purpose of the present invention is achieved through the following technical solutions:

[0006] The present invention discloses a method for compensating optical fiber transmission damage using a fast random convolution kernel transform, comprising the following steps:

[0007] Step 1: Signal transmission and acquisition of the Orbital Angular Momentum Mode Multiplexing (OAM-MDM) Direct Modulation and Direct Detection (IM / DD) fiber transmission system;

[0008] The G-channel signal multiplexing is subjected to orbital angular momentum mode modulation. For the i-th transmission signal, an arbitrary waveform generator (AWG) is used to generate a modulated electrical signal. After the modulated electrical signal passes through a Mach-Zehnder modulator (MZM), it is loaded onto a Gaussian beam. The Gaussian beam is irradiated onto a spatial light modulator and modulated into a topological charge satisfying |l| = k i vortex beam.

[0009] The G-path vortex beam is sent into a graded-index ring-core fiber for transmission after mode multiplexing, and then splits into G paths. After passing through the spiral phase plate (VPP) corresponding to the G block, it is converted back into a Gaussian beam and then converted into an electrical signal after passing through a photodetector (PD). The electrical signal is captured and collected by an oscilloscope.

[0010] Step 2: Perform preliminary digital signal processing on the signals collected in step 1 and define the data set;

[0011] The signal collected in step 1 is processed by low-pass filtering, resampling and matched filtering digital signal processing and is recorded as {S i},i=1,2,...,G, where S i =[x i,1 ,x i,2 ,...,x i,N ], N is the length of the signal sequence. The sliding window length is set to l win . Take the received signal of each channel as the feature vector and the symbol sequence as the label, l win Each group is packaged into a feature vector sequence and a label sequence. The feature vector sequence of the i-th path is:

[0012]

[0013] where X i (j) represents X i The jth row of Nl, j = 1, 2, ..., Nl input +1.

[0014] The symbol label sequence of the i-th path is: M is the modulation order of the signal.

[0015] The feature vector sequence and the label sequence are taken as the data set (X i ,Y i ), select the first 40% as the training data set (X i (k),Y i (k)), k=1,2,...,0.4N, and the last 60% are selected as the application data set (X i (p),Y i (p)),p=1,2,...,0.6N.

[0016] Step 3: Use a classification model based on fast random convolution kernel transformation to classify and identify the signal;

[0017] For all convolution kernels, set their characteristic parameters: length and weight.

[0018] First, the length of all convolution kernels is l kenel Fixed to 9;

[0019] In order to reduce the amount of computation while maintaining accuracy, the weights of the convolution kernels are restricted to {1, -2}, and the 6 weights of each convolution kernel are restricted to 1 and the 3 weights are restricted to -2. Under this restriction, there are 84 possible values ​​for the weights of the convolution kernels. K convolution kernels are selected from them. K is an integer less than or equal to 84 and greater than 1. The e-th convolution kernel is represented as

[0020]

[0021] For a convolution kernel, set the bias and expansion coefficient of the random convolution transformation to be performed.

[0022] The dilation coefficient d of each convolution kernel e Used to expand the convolution kernel on a time scale. For each convolution kernel, four expansion coefficients are selected. The expansion coefficients are randomly selected from the expansion coefficient set D. The expansion coefficient set D is defined as:

[0023] D={floor(2 0 ),floor(2 1 ),...,floor(2 max )},

[0024] in l win is the length of the input feature vector.

[0025] The bias b of each convolution kernel e Determined by the output of the convolution kernel. Extract the mean from the quantiles of the convolution output of multiple randomly selected training samples. For the randomly selected samples, calculate the convolution output W e *X i The quartile of (k) is randomly selected from the three quartiles as the bias. The quartiles are the values ​​at the 25%, 50%, and 75% positions after the convolution output data is sorted from large to small.

[0026] For a given feature vector X of a training dataset i (k), and all convolution kernels W e , and its corresponding expansion coefficient d e and bias b e Perform random convolution kernel convolution transformation, expressed as:

[0027]

[0028] After the convolution operation with the random convolution kernel, the proportion of positive values ​​(PPV) is calculated as the feature.

[0029]

[0030] Where I(·) is the characteristic function. i (k) The PPV calculated after performing 4 expansion coefficients with K convolution kernels and the bias output corresponding to each convolution kernel and the symbolic label sequence Y of the training dataset i (k) Input to the ridge regression linear classifier CLF to train the linear classifier.

[0031] Step 4: Use the random convolution kernel and linear classifier in step 3 to compensate for transmission damage of the received optical fiber communication signal;

[0032] The feature vector sequence in the application data set is convolved with the random convolution kernel in step 3 to calculate the PPV feature, which is then input into the linear classifier CLF trained in step 3 to obtain the corresponding symbol sequence after transmission loss compensation. Symbol sequence after transmission impairment compensation and the symbolic labels Y in the application dataset i (p) performs bit mapping and compares the mapped bit sequences one by one to calculate the bit error rate. Transmission impairment compensation using random convolution kernel transforms achieves low-complexity, high-accuracy impairment compensation, effectively alleviating the effects of transmission impairments on orbital angular momentum mode-division multiplexing signals during optical fiber transmission and improving the communication quality of optical communication systems.

[0033] Beneficial effects

[0034] 1. The present invention discloses a method for optical fiber transmission damage using fast random convolution kernel transformation, which uses a variety of random convolution kernels to perform convolution transformation on the signal to extract timing characteristics. It can compensate for the signal transmission damage more precisely according to the signal damage characteristics of the transmission system. Compared with the traditional damage compensation algorithm, the bit error rate after processing is lower, achieving effective equalization and damage compensation, and can improve the quality of large-capacity and high-speed optical fiber communications.

[0035] 2. The present invention discloses a method for optical fiber transmission damage based on fast random convolution kernel transformation, which can convert multiplication in the convolution operation process into addition through the convolution kernel weight setting, thereby achieving efficient and fast convolution transformation and avoiding the huge computational overhead when training deep convolutional networks.

[0036] 3. The present invention discloses a method for optical fiber transmission damage based on fast random convolution kernel transformation. By setting different expansion coefficients, it can extract the timing characteristics of the signal at multiple scales, thereby extracting the long-term timing dependence of the signal, which is helpful for damage compensation and signal recognition of the received signal.

[0037] 4. The present invention discloses a method for optical fiber transmission damage using a fast random convolution kernel transformation. After the fast random convolution kernel transformation, only a simple linear classifier is needed to compensate for the transmission damage of the damaged signal, thus avoiding the structural design of a multi-layer neural network and a large amount of computational overhead. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Exemplary embodiments of the present invention will be described in detail below with reference to the accompanying drawings, so that those skilled in the art will understand the above and other features and advantages of the present invention more clearly. In the accompanying drawings:

[0039] Figure 1 This is a flow chart of a method for compensating optical fiber transmission damage using a fast random convolution kernel transformation disclosed in the present invention;

[0040] Figure 2 A schematic diagram of a fast convolution kernel transformation of a method for compensating optical fiber transmission damage using a fast random convolution kernel transformation disclosed in the present invention;

[0041] Figure 3 The OAM-MDM IM / DD optical fiber transmission system experimental device disclosed in this embodiment;

[0042] Figure 4 This is a comparison chart of the bit error rates of a 32GBaud PAM8 signal without equalization, after fast random convolution kernel transformation, and after VNE compensation under different received optical powers in the embodiment;

[0043] Figure (a) shows the comparison of the bit error rates of a 32GBaud PAM8 signal without equalization, after fast random convolution kernel compensation, and after VNE compensation when |l| = 3; Figure (b) shows the comparison of the bit error rates of a 32GBaud PAM8 signal without equalization, after fast random convolution kernel compensation, and after VNE compensation when |l| = 2. DETAILED DESCRIPTION

[0044] The present invention will be described in detail below with reference to the accompanying drawings and embodiments. The technical problems solved by the technical solution of the present invention and the beneficial effects thereof are also described. It should be noted that the described embodiments are only intended to facilitate understanding of the present invention and do not serve to limit the present invention in any way.

[0045] In this example, an OAM-MDM IM / DD optical fiber communication system experimental platform is built to transmit 32GBaud PAM8 (8th order pulse amplitude modulation) signals multiplexed by two OAM modes. The experimental setup is as follows: Figure 3 As shown in the figure. In the signal transmission section, a digital signal processor generates a modulated signal, which is sent by an arbitrary waveform generator (AWG) to a Mach-Zehnder modulator (MZM). The MZM modulates the signal onto an optical carrier. In the OAM multiplexing section, the signal is split into two paths by an optical coupler (OC). After passing through an erbium-doped fiber amplifier (EDFA) and a polarization controller (PC), each beam is injected into a spatial light modulator (SLM) via a collimator (Col) and linear polarization (LP). The two spatial light modulators modulate the beams in different OAM modes, namely, topological charge numbers |l| = 2 and |l| = 3. The two OAM beams with |l| = 2 and |l| = 3 are then combined using a polarization beam combiner (PBC). The combined beam is converted to circular polarization by a quarter-wave plate (QWP) and then transmitted through a 2.3 km GIRCF. In the OAM demultiplexing section, the transmitted optical beams are first separated by a beam splitter (BS), then demultiplexed into Gaussian beams by a vortex phase plate (VPP) with opposite topological charges. These beams are then coupled into a single-mode fiber (SMF). In the signal receiving section, the two beams are amplified by an EDFA and converted into electrical signals by a photon detector (PD). For PAM signals, the BER is calculated after low-pass filtering, resampling, clock recovery, impairment compensation, and signal decoding.

[0046] Since some active optoelectronic devices are used in optical fiber communication systems, such as spatial light modulators and Mach-Zehnder modulators, these active optoelectronic devices have their own nonlinearities and interact with each other in the system to produce nonlinear effects, which deteriorates the system bit error rate performance and reduces the communication quality. This embodiment discloses a method for compensating optical fiber transmission damage using a fast random convolution kernel transform, such as Figure 1 As shown, it includes the following steps:

[0047] Step 1: Orbital angular momentum mode multiplexing direct modulation and direct detection optical fiber transmission and signal acquisition;

[0048] Two signals are multiplexed for orbital angular momentum mode modulation. For the i-th transmission signal, a Keysight 8194A arbitrary waveform generator (AWG) generates a modulated PAM8 signal. The sampling frequency is set to 96 GSa / s, the peak-to-peak value of the output electrical signal is set to 150 mV, the baud rate is 32 GBaud, and the signal rate is 96 Gbps. After passing through a Mach-Zehnder modulator (MZM), the modulated electrical signal is loaded onto a Gaussian beam. The Gaussian beam is then irradiated by a spatial light modulator and modulated into a vortex beam with topological charges satisfying |l| = 2 and |l| = 3. After mode multiplexing, these two vortex beams are transmitted through a graded-index ring-core fiber. There, they are split into two paths and converted back into Gaussian beams after passing through two corresponding spiral phase plates. These signals are then converted into electrical signals by a photodetector and captured by an oscilloscope.

[0049] Step 2: Perform preliminary digital signal processing on the signals collected in step 1 and define the data set;

[0050] The signal collected in step 1 is processed by low-pass filtering, resampling, and matched filtering digital signal processing and is recorded as {S i},i=1,2,...,G, where S i =[x i,1 ,x i,2 ,...,x i,N ], N is the signal sequence length, set to 65536. The sliding window length is set to l win =40. The received signal of each channel is used as the feature vector and the symbol sequence is used as the label. win Each group is packaged into a feature vector sequence and a label sequence. The feature vector sequence of the i-th path is:

[0051]

[0052] where X i (j) represents X i The jth row of Nl, j = 1, 2, ..., Nl input +1.

[0053] The symbol label sequence of the i-th path is: M is the modulation order of the signal.

[0054] The feature vector sequence and the label sequence are taken as the data set (X i ,Y i ), select the first 40% or the first 26214 as the training data set (X i (k),Y i (k)), k=1,2,...,0.4N, and the last 60% or 39322 samples are selected as the application data set (X i(p),Y i (p)),p=1,2,...,0.6N.

[0055] Step 3: Use a classification model based on fast random convolution kernel transformation to classify and identify the signal

[0056] For all convolution kernels, set their characteristic parameters: length and weight.

[0057] First, the length of all convolution kernels is l kenel Fixed to 9;

[0058] In order to reduce the amount of computation while maintaining accuracy, the weights of the convolution kernels are limited to {1, -2}, and the 6 weights of each convolution kernel are limited to 1 and the 3 weights are limited to -2. Under this restriction, 60 convolution kernels are selected from the convolution kernels. The e-th convolution kernel is represented as

[0059] For a convolution kernel, set the bias and expansion coefficient of the random convolution transformation to be performed.

[0060] The dilation coefficient d of each convolution kernel e Used to expand the convolution kernel on a time scale. For each convolution kernel, four expansion coefficients are selected. The expansion coefficients are randomly selected from the expansion coefficient set D. The expansion coefficient set D is defined as:

[0061] D={floor(2 0 ),floor(2 1 ),...,floor(2 max )},

[0062] in l win is the length of the input feature vector.

[0063] The bias b of each convolution kernel e The convolution kernel output is determined by the result. The mean is extracted from the quantiles of the convolution output of multiple randomly selected training samples. For the randomly selected samples, the convolution output W is calculated. e *X i The quartile of (k) is randomly selected from the three quartiles as the bias. The quartiles are the values ​​at the 25%, 50%, and 75% positions after the convolution output data is sorted from large to small.

[0064] For a given feature vector X of a training dataset i (k), and all convolution kernels W e , and its corresponding expansion coefficient d e and bias b e Perform random convolution kernel convolution transformation, expressed as:

[0065]

[0066] After the convolution operation with the random convolution kernel, the proportion of positive values ​​(PPV) is calculated as the feature.

[0067]

[0068] Where I(·) is the characteristic function. i (k) The PPV calculated after performing 4 expansion coefficients with K convolution kernels and the bias output corresponding to each convolution kernel and the symbolic label sequence Y of the training dataset i (k) Input to the ridge regression linear classifier CLF to train the linear classifier.

[0069] Step 4: Use the random convolution kernel and linear classifier in step 3 to perform damage compensation on the received optical fiber communication signal.

[0070] The feature vector sequence in the application data set is convolved with the random convolution kernel in step 3 to calculate the PPV feature, which is then input into the linear classifier CLF trained in step 3 to obtain the corresponding symbol sequence after damage compensation. Symbol sequence after damage compensation and the symbolic labels Y in the application dataset i (p) Perform bit mapping and compare the mapped bit sequences one by one to calculate the bit error rate. Figure 4 This paper presents a comparison of the bit error rate (BER) between a fast convolution kernel-based impairment compensation method and a VNE at different received optical powers (ROPs) when |l|==2 or 3 (the left figure shows |l|=2, and the right figure shows |l|=3). The training data length is 26214, and the test data length is 39322. The experimental results show that the fast convolution kernel-based impairment compensation method performs better than the Volterra-based method. For |l|=2, the fast convolution kernel-based impairment compensation method achieves a 2.7dB receiver sensitivity gain compared to the Volterra-based method; for |l|=3, the fast convolution kernel-based impairment compensation method achieves a 2.6dB receiver sensitivity gain compared to the Volterra-based method. This demonstrates a significant improvement in BER performance.

[0071] The above specific description further illustrates the purpose, technical solutions and beneficial effects of the invention in detail. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for compensating optical fiber transmission damage using a fast random convolution kernel transform, characterized in that: The following steps are included: Step 1: Signal transmission and acquisition of the orbital angular momentum mode multiplexing direct modulation and direct detection optical fiber transmission system; Step 2: Perform preliminary digital signal processing on the signals collected in step 1 and define the data set; Step 3: Use a classification model based on fast random convolution kernel transformation to classify and identify the signal; For all convolution kernels, set their characteristic parameters: length and weight; First, the length of all convolution kernels is l kenel Fixed to 9; In order to reduce the amount of computation while maintaining accuracy, the weight values ​​of the convolution kernel are restricted to {1, -2}, and the 6 weights of each convolution kernel are restricted to 1 and the 3 weights are restricted to -2. Under this restriction, there are 84 possible values ​​of the convolution kernel weights. K convolution kernels are selected from them; K is an integer less than or equal to 84 and greater than 1. The e-th convolution kernel is represented as For a convolution kernel, set the bias and expansion coefficient of the random convolution transformation to be performed; The dilation coefficient d of each convolution kernel e Used to expand the convolution kernel on a time scale; for each convolution kernel, four expansion coefficients are selected; the expansion coefficients are randomly taken from the expansion coefficient set D; the expansion coefficient set D is defined as: D={floor(2 0 ),floor(2 1 ),...,floor(2 max )}, in l win is the length of the input feature vector; The bias b of each convolution kernel e Determined by the output result of the convolution kernel; Extract the mean from the quantiles of the convolution output of multiple randomly selected training samples; for the randomly selected samples, calculate the convolution output W e *X i (k) quartile, one of the three quartiles is randomly selected as the bias; the quartiles are the values ​​at the 25%, 50%, and 75% positions after the convolution output data is sorted from large to small; For a given feature vector X of a training dataset i (k), and all convolution kernels W e , and its corresponding expansion coefficient d e and bias b e Perform random convolution kernel convolution transformation, expressed as: After the random convolution kernel convolution operation, the positive value ratio PPV is calculated as the feature; Where I(·) is the indicator function; l input Represents the input feature vector X i (k) length; input feature vector X i (k) The PPV calculated after performing 4 expansion coefficients with K convolution kernels and the bias output corresponding to each convolution kernel and the symbolic label sequence Y of the training dataset i (k) Input to the ridge regression linear classifier CLF to train the linear classifier; Step 4: Use the random convolution kernel and linear classifier in step 3 to compensate for the transmission damage of the received optical fiber communication signal.

2. The optical fiber transmission damage compensation method using fast random convolution kernel transformation according to claim 1, characterized in that: The implementation method of step one is: Performing orbital angular momentum mode modulation on G-channel signal multiplexing; generating a modulated electrical signal using an arbitrary waveform generator for the i-th transmission signal; After the modulated electrical signal passes through the Mach-Zehnder modulator, it is loaded onto the Gaussian beam; the Gaussian beam is irradiated onto the spatial light modulator and modulated into a topological charge satisfying |l| = k i vortex beam; The above-mentioned G-path vortex beam is sent into the graded-index ring-core fiber for transmission after mode multiplexing, and then splits the G-path. After passing through the spiral phase plate corresponding to the G block, it is converted back into a Gaussian beam, and then converted into an electrical signal after passing through a photodetector. The electrical signal is captured and collected by an oscilloscope.

3. The optical fiber transmission damage compensation method using fast random convolution kernel transformation according to claim 2, characterized in that: The implementation method of step 2 is: The signal collected in step 1 is processed by low-pass filtering, resampling and matched filtering digital signal processing and is recorded as {S i },i=1,2,...,G, where S i =[x i,1 ,x i,2 ,...,x i,N ], N is the length of the signal sequence; the sliding window length is set to l win ; Take the received signal of each channel as the feature vector and the symbol sequence as the label, l win Each group is packaged into a feature vector sequence and a label sequence; the feature vector sequence of the i-th path is: where X i (j) represents X i The jth row of Nl, j = 1, 2, ..., Nl input +1; The symbol label sequence of the i-th path is: M is the modulation order of the signal; The feature vector sequence and the label sequence are taken as the data set (X i ,Y i ), and select the first 40% as the training data set (X i (k),Y i (k)), k=1,2,...,0.4N, and the last 60% are selected as the application data set (X i (p),Y i (p)),p=1,2,...,0.6N.

4. The optical fiber transmission damage compensation method using fast random convolution kernel transformation according to claim 3, characterized in that: The implementation method of step four is: The feature vector sequence in the application data set is convolved with the random convolution kernel in step 3 to calculate the PPV feature, which is then input into the linear classifier CLF trained in step 3 to obtain the corresponding symbol sequence after transmission loss compensation. Symbol sequence after transmission impairment compensation and the symbolic labels Y in the application dataset i (p) performs bit mapping and compares the mapped bit sequences one by one to calculate the bit error rate; low-complexity and high-accuracy damage compensation is achieved through random convolution kernel transformation transmission damage compensation processing, effectively alleviating the impact of transmission damage on orbital angular momentum mode division multiplexing signals during optical fiber transmission, and improving the communication quality of optical communication systems.

Images