Optical fiber performance automatic testing method, system and device based on optical power detection

Abstract

The application relates to the technical field of communication, and discloses a kind of optical fiber performance automatic test method, system and equipment based on optical power detection.The method comprises the following steps: intelligently scanning and detecting optical fiber network, generating optical fiber resource mapping data, obtaining OTDR measurement configuration table by dynamic analysis, executing optical pulse injection and signal acquisition to obtain time-domain response characteristic curve, obtaining optical fiber performance parameter set by wavelet denoising and peak value identification processing, obtaining diagnosis decision data by fault analysis using deep learning and expert rules, and finally generating optical fiber state evaluation report by digital twin modeling.The application can realize remote automatic test, intelligent fault diagnosis and visual monitoring management of optical fiber network, and improve the operation efficiency and reliability of optical fiber communication network.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of communication, and particularly relates to a fiber performance automatic testing method, system and equipment based on optical power detection. BACKGROUND

[0002] With the wide application of optical fiber communication in power systems, the operation and maintenance monitoring requirements of optical fiber communication networks are increasingly improved. The current optical fiber network maintenance mainly relies on manual on-site implementation of optical fiber jump operations in transformer station rooms to realize the cross connection between different optical fibers; manual input of optical fiber data is required to realize the statistical management of the use of optical fiber cores; manual on-site performance testing of standby cores is required to realize the safety hazard investigation of optical fiber cores. In the prior art, an OTDR tester is mainly used for optical fiber performance detection, and the performance parameters of the optical fiber are evaluated by transmitting a probe light pulse and receiving reflected light and scattered light in the optical fiber, but this method requires professional personnel to perform on-site operation and data analysis.

[0003] However, the existing optical fiber testing technology has the following deficiencies: first, due to the dispersion of the room sites, the safety management requirements for personnel access, and the number and professional level of maintenance personnel, even if a large amount of cost is invested in the operation and maintenance of the optical fiber communication network, there are still problems such as slow optical fiber jump service opening, inaccurate optical fiber resource statistics, and many optical fiber fault risks; second, the traditional OTDR test needs manual setting of test parameters, and the accuracy and reliability of the test results depend largely on the experience level of the operator; in addition, the existing technology lacks intelligent analysis and fault diagnosis capabilities for test data, and cannot timely discover and warn potential network fault risks. SUMMARY

[0004] In view of the deficiencies of the prior art, the present application provides a fiber performance automatic testing method, system and equipment based on optical power detection, which is used for realizing remote automatic testing, intelligent fault diagnosis and visual monitoring and management of optical fiber networks without relying on manual on-site operation, so as to improve the operation and maintenance efficiency and reliability of the optical fiber communication network.

[0005] In a first aspect, the application provides an optical fiber performance automatic testing method based on optical power detection, which comprises: comprehensively detecting an optical fiber network structure through optical fiber intelligent scanning to generate optical fiber resource mapping data containing optical fiber number data, optical fiber spatial position data and optical path connection relationship data; calculating test parameters of the optical fiber resource mapping data through a dynamic analysis algorithm to obtain an OTDR measurement configuration table containing wavelength selection parameters, pulse width and sampling frequency; performing optical pulse injection and signal collection on an optical fiber through parameters specified in the OTDR measurement configuration table to obtain a time-domain response characteristic curve of the optical fiber link; processing data of the time-domain response characteristic curve through a wavelet denoising and peak value recognition algorithm to obtain an optical fiber performance parameter set containing fault point coordinates, attenuation coefficients and connection losses; comprehensively analyzing the optical fiber performance parameter set through a deep learning network and an expert rule base to obtain diagnostic decision data containing fault levels, abnormal types and optimization suggestions; and visualizing the diagnostic decision data through digital twin modeling to obtain an optical fiber state evaluation report containing a topological map, a loss distribution and a health score.

[0006] In a second aspect, the application provides an optical fiber performance automatic testing system based on optical power detection, which comprises:

[0007] a detection module configured to comprehensively detect an optical fiber network structure through optical fiber intelligent scanning to generate optical fiber resource mapping data containing optical fiber number data, optical fiber spatial position data and optical path connection relationship data;

[0008] a calculation module configured to calculate test parameters of the optical fiber resource mapping data through a dynamic analysis algorithm to obtain an OTDR measurement configuration table containing wavelength selection parameters, pulse width and sampling frequency;

[0009] a collection module configured to perform optical pulse injection and signal collection on an optical fiber through parameters specified in the OTDR measurement configuration table to obtain a time-domain response characteristic curve of the optical fiber link;

[0010] a processing module configured to process data of the time-domain response characteristic curve through a wavelet denoising and peak value recognition algorithm to obtain an optical fiber performance parameter set containing fault point coordinates, attenuation coefficients and connection losses;

[0011] an analysis module configured to comprehensively analyze the optical fiber performance parameter set through a deep learning network and an expert rule base to obtain diagnostic decision data containing fault levels, abnormal types and optimization suggestions;

[0012] a conversion module configured to visualize the diagnostic decision data through digital twin modeling to obtain an optical fiber state evaluation report containing a topological map, a loss distribution and a health score.

[0013] In a third aspect, the present application provides an electronic device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the method according to the first aspect when executing the program.

[0014] In the technical scheme provided by the present application, the optical fiber network number, optical fiber spatial position data and connection relationship information can be accurately obtained through comprehensive detection by optical fiber intelligent scanning, manual recording errors are effectively avoided, and the accuracy and efficiency of resource information collection are significantly improved. Moreover, the test parameter calculation of the optical fiber resource mapping data is performed through a dynamic analysis algorithm, the intelligent configuration of the OTDR measurement parameter is realized, the best matching between the test parameter and the optical fiber characteristics is ensured, the accuracy and reliability of the test result are improved, and in the process of optical pulse injection and signal collection of the optical fiber, accurate timing control and real-time sampling technology are adopted to ensure the time resolution and integrity of the measurement data, providing high-quality original data for subsequent analysis. Through wavelet denoising and peak recognition algorithm, the data of the time domain response characteristic curve is processed, the influence of measurement noise is effectively eliminated, the fault point position and performance parameters are accurately identified, and the accuracy of fault diagnosis is improved. Deep learning network and expert rule base are adopted for comprehensive analysis, the adaptive ability of machine learning is combined with expert experience, more accurate and intelligent fault diagnosis is realized, reliable optimization suggestions are provided, and finally, digital twin modeling is performed for visual conversion, the state and performance distribution of the optical fiber network are intuitively displayed, which facilitates maintenance personnel to quickly understand and locate problems, and improves the operation and maintenance efficiency. It should be understood that the content described in the summary section is not intended to limit the key or important features of the embodiments of the present application, nor to limit the scope of the present application. Other features of the present application will become apparent through the following description. BRIEF DESCRIPTION OF DRAWINGS

[0015] The above and other features, advantages and aspects of embodiments of the present application will become more apparent by describing in detail preferred embodiments thereof with reference to the attached drawings in which:

[0016] Figure 1 An embodiment schematic diagram of the optical fiber performance automatic test method based on optical power detection in the embodiments of the present application;

[0017] Figure 2 An embodiment schematic diagram of the optical fiber performance automatic test system based on optical power detection in the embodiments of the present application;

[0018] Figure 3 A structure schematic diagram of the electronic device in the embodiments of the present application. DETAILED DESCRIPTION

[0019] To make the purpose, technical solutions, and advantages of the embodiments of this application more clear, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0020] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0021] For ease of understanding, the specific process of the embodiment of the present application is described below. Figure 1 In one embodiment of the present application, an automatic optical fiber performance testing method based on optical power detection includes:

[0022] Step S101: Perform a comprehensive inspection of the optical fiber network structure through optical fiber intelligent scanning to generate optical fiber resource mapping data including optical fiber numbering data, optical fiber spatial position data, and optical path connection relationship data;

[0023] Step S102: Calculate test parameters for the optical fiber resource mapping data using a dynamic analysis algorithm to obtain an OTDR measurement configuration table including wavelength selection parameters, pulse width, and sampling frequency;

[0024] Step S103: injecting light pulses and collecting signals into the optical fiber according to the parameters specified in the OTDR measurement configuration table to obtain a time domain response characteristic curve of the optical fiber link;

[0025] Step S104: Processing the time domain response characteristic curve using wavelet noise reduction and peak recognition algorithms to obtain a set of optical fiber performance parameters including fault point coordinates, attenuation coefficient, and connection loss;

[0026] Step S105: Comprehensively analyze the optical fiber performance parameter set using a deep learning network and an expert rule base to obtain diagnostic decision data including fault level, abnormality type, and optimization suggestions;

[0027] Step S106: Visually convert the diagnostic decision data through digital twin modeling to obtain a fiber status assessment report including topology map, loss distribution, and health score.

[0028] It is understandable that the execution subject of the present application can be an automatic optical fiber performance test system based on optical power detection, or a terminal or a server, which is not limited here. The embodiment of the present application is described by taking a server as the execution subject as an example.

[0029] Specifically, the optical fiber network structure is comprehensively detected by an optical fiber intelligent scanning technology. The optical fiber intelligent scanning technology scans the optical fiber network structure using a port recognition algorithm. The port recognition algorithm adopts a combination of image processing and deep learning. High-definition cameras are used to collect optical fiber port images. After image preprocessing and feature extraction, the images are input into a pre-trained deep convolutional neural network for recognition to obtain optical fiber numbering data. Subsequently, a grating positioning algorithm uses a distributed fiber grating sensor to spatially locate the optical fiber. The three-dimensional coordinates of the optical fiber are determined by measuring the changes in the grating reflection wavelength to form optical fiber spatial position data. Then, the optical fiber numbering data is connected and determined by an optical path tracking algorithm. The optical path tracking algorithm uses an improved depth-first search strategy to gradually track the optical signal transmission path from the starting port of the optical fiber, records each node and connection relationship, generates the initial connection relationship of the optical path, and then verifies the correlation based on the optical fiber spatial position data and the initial connection relationship of the optical path using a topology analysis algorithm. The topology analysis algorithm constructs a network connection graph based on graph theory principles, verifies the physical feasibility of node connections, eliminates incorrect connections, and ensures the accuracy of the optical path connection relationship data.

[0030] The attribute correlation algorithm is used to extract features from the optical fiber numbering data, optical fiber spatial position data, and optical path connection relationship data. Different dimensional data features are analyzed to obtain a complete resource feature set. Finally, the data aggregation algorithm is used to standardize the resource feature set to generate standardized optical fiber resource mapping data. In the second stage, the optical fiber resource mapping data is dynamically analyzed and calculated for OTDR test parameters. The path analysis algorithm divides the optical fiber resource mapping data into paragraphs based on the characteristics of the optical fiber length and type. The optical fiber is divided into different test sections, and each section is configured with an appropriate wavelength range. The dynamic threshold algorithm calculates the optimal wavelength based on the characteristics of the optical fiber grouping. The attenuation characteristics of different types of optical fibers are considered to select appropriate test wavelengths. The adaptive allocation algorithm calculates the pulse width based on the optical fiber length. Narrow pulses are selected for shorter distances to improve spatial resolution, and wide pulses are selected for longer distances to ensure measurement range. The frequency optimization algorithm determines the minimum sampling frequency based on the sampling theorem, and determines the actual sampling frequency considering the system bandwidth limitation.

[0031] Subsequently, the parameter combination algorithm optimizes and combines the wavelength, pulse width, sampling frequency and other parameters to generate a test parameter matrix, and converts the parameter matrix into a standard OTDR measurement configuration table through a format conversion algorithm. In the third stage, the optical fiber test is performed. The parameter analysis algorithm first analyzes the OTDR configuration table, extracts the test parameters to generate a control sequence, and the pulse modulation algorithm generates an optical signal with a specified wavelength and pulse width according to the control sequence. The optoelectronic converter adjusts the power of the optical signal to obtain a standardized probe signal. The real-time sampling algorithm collects the optical fiber return signal according to the configured sampling frequency, the timing processing algorithm synchronizes the sampling data in time and calibrates the amplitude, and the feature extraction algorithm fits to obtain a complete time-domain response characteristic curve. In the fourth stage, the characteristic curve is processed. The wavelet decomposition algorithm decomposes the curve into coefficients of different scales, filters out noise components through threshold processing, and the peak identification algorithm locates the feature points in the denoised data to obtain a fault point coordinate sequence.

[0032] The slope analysis algorithm calculates the attenuation coefficients of each segment of the curve, the joint loss calculation algorithm analyzes the sudden loss at the feature points, and the data fusion algorithm integrates the parameters to form a complete set of optical fiber performance parameters. In the fifth stage, fault diagnosis is performed. The feature conversion algorithm pre-processes the performance parameters, the deep learning network trains a classification model based on historical fault samples to determine the current fault level. The expert rule base matches the fault type based on the pre-set rule base, and the correlation analysis algorithm searches the historical case library to provide optimization suggestions. The multi-dimensional evaluation algorithm comprehensively evaluates and prioritizes the fault level and optimization suggestions, and the decision fusion algorithm integrates the analysis results into complete diagnostic decision data. In the final stage, visualization is performed. The topology mapping algorithm constructs a network structure model combined with spatial information, the graphics rendering algorithm generates a three-dimensional visualization effect, the interpolation calculation algorithm processes the spatial distribution of loss data, the scoring calculation algorithm quantifies the health status index, and the spatial registration algorithm associates and maps the visualization model with the state data to finally generate a complete evaluation report.

[0033] For example, a single-mode optical fiber with a length of 2000 meters is found by intelligent scanning, and the spatial coordinates are determined by grating positioning as (x=10.5m, y=15.2m, z=2.1m), and the port identification obtains the number SMF-2024-01. The dynamic analysis selects a wavelength of 1310 nm, a pulse width of 30 ns, and a sampling frequency of 100 MHz for OTDR testing. After wavelet denoising of the measured time-domain response curve, three feature points are identified at 500m, 1200m and 1800m, and the corresponding attenuation coefficients are 0.35dB / km, 0.38dB / km and 0.42dB / km, and the connection losses are 0.21dB, 0.25dB and 0.28dB. The deep learning diagnosis determines that it is of medium risk, and the expert system suggests optimizing the joint at 1800m. The digital twin model intuitively displays the loss distribution, and the health score of the optical fiber is 85 points, suggesting that the joint problem should be addressed during routine maintenance.

[0034] In the embodiments of the present application, comprehensive detection is performed through optical fiber intelligent scanning, which can accurately obtain the number of optical fiber network, spatial position data of optical fiber and connection relationship information, effectively avoid manual recording errors, significantly improve the accuracy and efficiency of resource information collection, and through dynamic analysis algorithm for test parameter calculation of optical fiber resource mapping data, intelligent configuration of OTDR measurement parameters is realized, which ensures the best matching of test parameters and optical fiber characteristics, improves the accuracy and reliability of test results, and in the process of optical pulse injection and signal collection of optical fiber, accurate timing control and real-time sampling technology are adopted, which ensures the time resolution and integrity of measurement data, provides high-quality original data for subsequent analysis, through wavelet denoising and peak recognition algorithm for data processing of time-domain response characteristic curve, the influence of measurement noise is effectively eliminated, the fault point position and performance parameters are accurately identified, the accuracy of fault diagnosis is improved, deep learning network and expert rule base are used for comprehensive analysis, the adaptive ability of machine learning and expert experience are combined, more accurate and intelligent fault diagnosis is realized, reliable optimization suggestions are provided, and finally digital twin modeling is used for visual conversion, the state and performance distribution of optical fiber network are intuitively displayed, which is convenient for maintenance personnel to quickly understand and locate problems, and improves the operation and maintenance efficiency.

[0035] In a specific embodiment, the process of step S101 can specifically include the following steps:

[0036] (1) The optical fiber network structure is scanned and detected by a port identification algorithm to obtain optical fiber number data;

[0037] (2) Three-dimensional coordinate collection is performed according to the optical fiber number data by a grating positioning algorithm to obtain optical fiber spatial position data;

[0038] (3) The optical fiber numbering data is connected and determined by an optical path tracking algorithm to obtain an initial connection relationship of the optical path;

[0039] (4) The optical path connection relationship data is obtained by topological analysis algorithm according to the optical fiber spatial position data and the initial connection relationship of the optical path;

[0040] (5) The resource feature set is obtained by attribute association algorithm according to the optical fiber numbering data, the optical fiber spatial position data and the optical path connection relationship data;

[0041] (6) The resource feature set is standardized by data aggregation algorithm to generate optical fiber resource mapping data.

[0042] Specifically, a high-definition camera is used to capture images of the optical fiber distribution frame, with an image resolution of 4096x3072 pixels. The original images are preprocessed, including grayscale conversion, histogram equalization and edge enhancement, to improve image quality and highlight fiber port features. Then, a target detection network based on deep learning is used to analyze the preprocessed images. The network uses an improved YOLOv5 architecture, and the detection model is trained by 5000 labeled samples to accurately identify the fiber port position and corresponding identification information. The port recognition algorithm outputs structured data containing port type, position coordinates and number information, forming the optical fiber numbering data. The grating positioning algorithm is based on fiber Bragg grating sensing technology. Multiple Bragg grating sensing points are pre-arranged on the optical fiber. The reflection wavelength of each sensing point changes with strain and temperature. By scanning the reflection signal in the wavelength range of 1510-1590nm with a wavelength scanner, the center wavelength value of each sensing point is obtained. Combined with the grating calibration curve, the strain value of the sensing point is calculated. The grating positioning algorithm uses the principle of triangulation, and uses the strain data of at least three known position sensing points to construct a spatial coordinate equation set to solve the three-dimensional coordinates of the optical fiber. The positioning accuracy is better than 1cm, and the spatial trajectory of the optical fiber is recorded in real time to generate the optical fiber spatial position data.

[0043] The light path tracking algorithm adopts an improved depth-first search strategy, starting from the starting port of the optical fiber and gradually detecting the connection relationship in the signal transmission direction. The algorithm maintains a set of visited ports and a queue of ports to be visited. Each time a port is taken out of the queue, the next port connected to it is determined through optical power detection, and the newly discovered port is added to the queue of ports to be visited. This process continues until the queue is empty, during which all confirmed port connection pairs are recorded, and the complete initial connection relationship of the light path is generated. The topology analysis algorithm verifies the light path connection relationship data based on graph theory. Each optical fiber port is represented as a node in the graph, and the fiber connection is represented as an edge, constructing an initial network topology graph. The algorithm first checks the connectivity of the topology graph to ensure that all nodes can reach each other through an effective path, and then verifies the physical feasibility of each connection in combination with the fiber spatial position data, including checking whether the connection distance exceeds the fiber length limit and whether the connection path has severe bends. Connections that do not meet the physical constraints are marked, and the connection relationship is adjusted through iterative optimization, and the verified light path connection relationship data is finally output.

[0044] The attribute association algorithm performs feature extraction and correlation analysis on multi-source heterogeneous data. First, the fiber number data, fiber spatial position data, and light path connection relationship data are converted into standard feature vectors, which include port type, position coordinates, connection port, transmission direction, and other key attributes. Then, the correlation matrix between different features is calculated, and feature combinations with significant correlation are identified, such as the spatial aggregation of adjacent ports and the serial number rule of consecutive ports. Based on the correlation analysis results, a core feature set is extracted to represent the characteristics of fiber resources, forming a unified resource feature set. The data aggregation algorithm standardizes and structures the resource feature set. First, the feature data of different dimensions is normalized, and all feature values are mapped to a unified numerical interval. Then, the feature information is organized according to the predefined data model, and the scattered feature data is aggregated into structured resource descriptions, including fiber basic attributes, spatial topology relationships, and connection configuration information. Finally, the standard format of the fiber resource mapping data is generated, providing a data basis for subsequent performance testing and analysis.

[0045] For example, a high-definition camera scans the ODF rack and collects a 2048x1536 resolution port image. After image enhancement, the image is sent to a trained deep learning model to identify the port location and number SMF-2024-001 to SMF-2024-120. The grating positioning system sets up a Bragg grating sensing point every 50 meters. The wavelength scanner measures the first sensing point reflection wavelength as 1550.241 nm, and the strain value is 103 micro-strain. Combined with other sensing point data, the spatial coordinate trajectory of the optical fiber is calculated. The optical path tracking starts from the starting port SMF-2024-001 and gradually traces to the termination port SMF-2024-085 through power detection, recording the complete connection path. Topology analysis finds a suspected inter-distance connection, which is corrected after verification to obtain the correct connection relationship. Attribute association analysis extracts 15 key features from the data of 120 ports, and after data aggregation, a standardized resource mapping dataset containing port attributes, spatial information, and connection relationships is generated.

[0046] In a specific embodiment, the process of performing step S102 can specifically include the following steps:

[0047] (1) Perform paragraph division on the optical fiber resource mapping data through a path analysis algorithm to obtain optical fiber feature groups containing different wavelength selection parameter ranges;

[0048] (2) Perform wavelength preselection calculation according to the optical fiber feature groups through a dynamic threshold algorithm to obtain wavelength selection parameters;

[0049] (3) Perform optical fiber length measurement on the optical fiber resource mapping data through an adaptive allocation algorithm to obtain corresponding pulse widths;

[0050] (4) Perform sampling calculation according to the wavelength selection parameters and pulse widths through a frequency optimization algorithm to obtain sampling frequencies;

[0051] (5) Integrate the wavelength selection parameters, pulse widths, and sampling frequencies through a parameter combination algorithm to obtain a test parameter matrix;

[0052] (6) Standardize the test parameter matrix through a format conversion algorithm to obtain an OTDR measurement configuration table.

[0053] Specifically, the optical fiber link in the optical fiber resource mapping data is analyzed, and the paragraphs are divided according to the characteristics such as optical fiber type, length and application scene. Different wavelength parameter ranges are used for different types of optical fibers. Single-mode optical fibers are mainly divided in the wavelength range of 1310nm and 1550nm, and multi-mode optical fibers are divided in the wavelength range of 850nm and 1300nm. The algorithm divides the optical fiber link into several test sections according to the attenuation characteristics of the optical fiber and the application requirements, and gives each section an appropriate wavelength selection range, thereby forming optical fiber feature grouping data. The dynamic threshold algorithm calculates the wavelength preselection based on the optical fiber feature grouping data, sets a dynamic wavelength selection threshold for the characteristic parameters of each optical fiber section, considers factors such as the dispersion characteristics, attenuation characteristics and nonlinear effects of the optical fiber, and determines the optimal wavelength parameters. For example, for standard single-mode optical fiber G.652, 1310nm wavelength is preferred for short-distance testing to obtain better spatial resolution, and 1550nm wavelength is selected for long-distance testing to reduce transmission loss. The algorithm gradually adjusts the wavelength parameters through iterative optimization until the test requirements are met, and finally outputs the wavelength selection parameters.

[0054] The adaptive allocation algorithm calculates the pulse width according to the optical fiber link length information recorded in the optical fiber resource mapping data. Narrower pulse width is used for shorter distance optical fiber sections to improve spatial resolution, and wider pulse width is used for longer distance optical fiber sections to ensure sufficient measurement range. The algorithm establishes a mapping relationship between the optical fiber length and the pulse width. For optical fiber sections of 0-500 meters, a 3ns pulse width is used, for 500-2000 meters, a 10ns pulse width is used, and for more than 2000 meters, a 30ns pulse width is used, and the actual signal quality is dynamically adjusted. The frequency optimization algorithm calculates the sampling frequency based on the selected wavelength parameters and pulse width, determines the minimum sampling frequency requirement according to the Nyquist sampling theorem, and optimizes the sampling frequency configuration considering the bandwidth limitation and signal processing capability of the OTDR measurement system. For a 3ns pulse width test, the sampling frequency is set to 500MHz to ensure sufficient sampling points, and for a wider pulse, the sampling frequency can be appropriately reduced, such as 100MHz for a 30ns pulse, which ensures signal integrity while improving data processing efficiency.

[0055] The parameter combination algorithm integrates key parameters such as wavelength selection parameters, pulse width, and sampling frequency, constructs a multi-dimensional parameter space for optimization analysis, and selects the optimal parameter combination scheme by evaluating the impact of different parameter combinations on test performance. For example, when using a 1310 nm wavelength and a 10 ns pulse for testing, a 200 MHz sampling frequency is used to obtain the desired measurement effect. All parameter combination information is organized into a structured test parameter matrix, which contains specific configuration information for each test segment. The format conversion algorithm converts the test parameter matrix into a standardized OTDR measurement configuration table, which uses a unified data format and unit to ensure that the test parameters can be correctly recognized and executed by the OTDR equipment. The conversion process includes data format standardization, unit unification, and parameter validity verification, and finally generates an OTDR measurement configuration table containing complete test configuration information.

[0056] For example, the path analysis algorithm analyzes a 3000-meter-long G.652 single-mode optical fiber and divides it into three segments: 0-500 meters, 500-2000 meters, and 2000-3000 meters. The dynamic threshold algorithm selects 1310 nm as the main test wavelength and 1550 nm as the auxiliary test wavelength based on the characteristics of each segment. The adaptive allocation algorithm configures pulse widths according to length segmentation, with 3 ns pulses for the first segment, 10 ns pulses for the second segment, and 30 ns pulses for the third segment. The frequency optimization algorithm accordingly configures sampling frequencies of 500 MHz, 200 MHz, and 100 MHz. The parameter combination algorithm generates a 3x3 parameter matrix containing wavelength, pulse width, and sampling frequency combinations. The format conversion algorithm converts the parameter matrix into a standard OTDR configuration table containing standardized information such as test segment number, start and end position, wavelength selection, pulse width, sampling frequency, etc., to guide subsequent OTDR measurement work.

[0057] In a specific embodiment, the process of performing step S103 can specifically include the following steps:

[0058] (1) Extracting parameters from the OTDR measurement configuration table through the parameter analysis algorithm to obtain an optical pulse injection control sequence;

[0059] (2) Generating an optical signal through the pulse modulation algorithm according to the optical pulse injection control sequence to obtain an optical pulse signal to be injected;

[0060] (3) Adjusting the power of the optical pulse signal through an optoelectronic converter to obtain a probe signal injected into the optical fiber;

[0061] (4) Collecting data from the optical fiber return signal through the real-time sampling algorithm according to the sampling frequency in the OTDR measurement configuration table to obtain raw response data;

[0062] (5) The original response data is time-synchronized and amplitude-calibrated by a time series processing algorithm to obtain standardized response data;

[0063] (6) The standardized response data is curve-fitted by a feature extraction algorithm to obtain time-domain response feature curves.

[0064] Specifically, the parameter information in the OTDR measurement configuration table is read, and the wavelength, pulse width, sampling frequency and other parameters of each test section are parsed and checked. The algorithm converts these parameters into time sequence control commands recognizable by the light source control system, including light source switching time sequence, wavelength switching sequence, pulse trigger time sequence, etc., forming a complete optical pulse injection control sequence. Each control sequence contains an accurate timestamp and corresponding control instructions to ensure accurate and controllable parameter switching during testing. The pulse modulation algorithm generates the required optical pulse signal according to the control sequence, generates continuous light of the specified wavelength through a semiconductor laser, and performs pulse modulation through an electro-optical modulator. During modulation, the algorithm precisely controls the drive voltage waveform of the modulator to ensure that the generated optical pulse has ideal time waveform and spectral characteristics. For different pulse width requirements, the algorithm automatically adjusts the rise time and fall time of the modulation signal to achieve fast switching of narrow pulses and stable output of wide pulses.

[0065] The photoelectric converter uses a high-linearity PIN photodiode for photoelectric conversion, and a precision transimpedance amplifier for amplification and power regulation of the optical signal. During conversion, the gain setting is automatically adjusted according to the fiber length and expected attenuation to ensure that the power level of the probe signal meets the measurement requirements. At the same time, the output end of the converter is equipped with an automatic gain control circuit to monitor and adjust the amplitude of the output signal in real time, maintaining the stability of the probe signal. The real-time sampling algorithm uses a high-speed analog-to-digital converter to collect data from the returned optical signal, with the sampling clock synchronized with the optical pulse injection to ensure that the sampling points accurately correspond to the signal time sequence. The algorithm sets the sampling clock according to the sampling frequency specified in the configuration table, with a data point collected every 2 nanoseconds for a 500MHz sampling frequency, recording the intensity changes of the backscattered light signal in real time. Timestamp information is recorded during sampling for subsequent data processing and analysis.

[0066] The time sequence processing algorithm firstly calibrates the time reference of the collected original response data, eliminates the sampling time sequence jitter through the reference clock signal, and ensures the time accuracy of the data points. Then, the amplitude calibration is performed, the absolute power calibration is performed by using the built-in calibration light source, and the sampling value is converted into the standardized optical power unit. The algorithm simultaneously performs zero drift compensation and linearity correction to eliminate the system error of the measurement system, and obtains accurate standardized response data. The feature extraction algorithm performs mathematical processing and curve fitting on the standardized response data. Firstly, the median filter is used to remove discrete noise points, and then the polynomial fitting method is used for smoothing processing of the data points. The algorithm determines the coefficients of the fitted curve by the least square method, generates a continuous time domain response characteristic curve, and accurately reflects the transmission characteristics of the optical fiber link.

[0067] For example, the parameter analysis algorithm extracts the test parameters from the OTDR configuration table: 1310 nm wavelength, 10 ns pulse width, 200 MHz sampling frequency, and generates an injection sequence containing 100 control instructions. The pulse modulation algorithm generates an optical pulse signal with a peak power of 100 mW and a repetition frequency of 10 kHz accordingly. The photoelectric converter adjusts the input signal to a probe power level of 20 mW. The real-time sampling algorithm collects the return signal at a frequency of 200 MHz, and obtains 1 million sampling points within 5 seconds. The time sequence processing algorithm processes the original data, and converts the sampling value into a standard optical power range of -20 dBm to -70 dBm. The feature extraction algorithm generates a smooth response curve through a 9th order polynomial fitting, and the curve shows that there is a 0.5 dB abrupt loss at 2 kilometers.

[0068] In a specific embodiment, the process of performing step S104 can specifically include the following steps:

[0069] (1) Perform multi-scale analysis on the time domain response characteristic curve by the wavelet decomposition algorithm to obtain noise characteristic coefficients;

[0070] (2) Perform signal filtering on the noise characteristic coefficients by the threshold processing algorithm to obtain denoised response data;

[0071] (3) Perform feature point positioning on the denoised response data by the peak recognition algorithm to obtain a feature point sequence containing fault point coordinates;

[0072] (4) Perform loss calculation on the feature point sequence by the slope analysis algorithm to obtain optical fiber attenuation coefficient data;

[0073] (5) Perform connection point analysis on the feature point sequence by the joint loss calculation algorithm to obtain optical fiber connection loss data;

[0074] (6) Integrate the fault point coordinates, attenuation coefficients, and connection losses by the data fusion algorithm to obtain an optical fiber performance parameter set.

[0075] Specifically, a wavelet basis function suitable for the characteristics of the optical fiber signal is selected, and the time-domain response characteristic curve is decomposed by multiple layers using db4 wavelet to decompose the original signal into different frequency components. During the decomposition process, the signal is iteratively decomposed by high-pass and low-pass filters to obtain a series of wavelet coefficients, including low-frequency approximation coefficients and high-frequency detail coefficients. The algorithm separates the trend component and the noise component in the signal by 5-layer wavelet decomposition, and generates a noise feature coefficient matrix containing different scale features. The threshold processing algorithm sets an adaptive threshold for the noise feature coefficients based on statistical principles, and uses a soft threshold method to screen the high-frequency noise coefficients. The algorithm estimates the optimal threshold based on the noise level of each layer of decomposition, and shrinks the coefficients that exceed the threshold and sets the coefficients that are less than the threshold to zero. After threshold processing, the processed coefficients are converted back to the time domain by wavelet reconstruction to obtain the denoised response data.

[0076] The peak recognition algorithm uses a gradient-based search method to detect feature points from the denoised response data. The algorithm first calculates the first-order difference of the signal and marks the sign change points of the difference as potential feature points, then screens out false peaks according to features such as peak amplitude and width. For each confirmed feature point, record its time position and amplitude information, and convert it to spatial position coordinates through the speed of light to form a feature point sequence containing fault point position information. The slope analysis algorithm performs linear regression analysis on the signal segment between the feature points to calculate the slope value of each signal segment. Since the optical power attenuation in the optical fiber follows an exponential law, the algorithm performs linear fitting on the logarithm of the signal, and the slope value directly corresponds to the attenuation coefficient of the optical fiber. Through segmented calculation and statistical analysis, the attenuation characteristics of each segment of the optical fiber are obtained, and the complete optical fiber attenuation coefficient data is generated.

[0077] The joint loss calculation algorithm is specifically designed to analyze the mutation points in the feature point sequence, and determines the connection loss by calculating the difference in signal level before and after the mutation point. The algorithm uses a local average method to reduce the influence of random fluctuations, and calculates the average power level on both sides of the feature point by selecting a window of appropriate width, and the difference between the two is the insertion loss introduced by the joint. Statistical analysis of all connection points generates optical fiber connection loss data containing position and loss value. The data fusion algorithm uses a multi-source information fusion method to comprehensively process multi-dimensional data such as fault point coordinates, attenuation coefficients, and connection losses. The algorithm establishes a unified data structure to integrate different types of performance parameters according to spatial position, and adds corresponding confidence weights. Through correlation analysis, the consistency of each parameter is verified, and abnormal data is removed, and finally a standardized set of optical fiber performance parameters is generated.

[0078] For example, after five layers of wavelet decomposition, the RMS value of the noise coefficient at the highest layer was 0.02 dB. Thresholding processing resets high-frequency coefficients below 0.05 dB to zero, improving the signal-to-noise ratio of the reconstructed signal by 12 dB. Peak identification detected five characteristic points in the processed data: at 500, 1000, 1500, 2000, and 2500 meters. Slope analysis calculated the attenuation coefficients of each fiber segment to be 0.32 dB / km, 0.35 dB / km, 0.33 dB / km, and 0.34 dB / km, respectively. Splice loss calculations revealed that the connection losses at the five characteristic points were 0.15 dB, 0.18 dB, 0.21 dB, 0.23 dB, and 0.20 dB, respectively. Data fusion generated a complete performance parameter set, identifying a potential problem point at 2000 meters with a high attenuation coefficient and significant connection loss.

[0079] In a specific embodiment, the process of executing step S105 may specifically include the following steps:

[0080] (1) Standardize the fiber performance parameter set through the feature conversion algorithm to obtain the normalized feature vector;

[0081] (2) Perform fault classification calculation on the normalized feature vector through a deep learning network to obtain the fault level;

[0082] (3) Match the fault level with the rules through the expert rule base to obtain the abnormal type;

[0083] (4) Retrieve historical cases based on the anomaly type using a correlation analysis algorithm to obtain optimization suggestions;

[0084] (5) Prioritize the fault levels and optimization suggestions through a multi-dimensional evaluation algorithm to obtain an optimization strategy sequence;

[0085] (6) The fault level, abnormality type and optimization strategy sequence are integrated through the decision fusion algorithm to obtain diagnostic decision data.

[0086] Specifically, each indicator in the set of optical fiber performance parameters is normalized to convert parameters of different dimensions into the interval [0, 1]. The specific operation includes maximum and minimum value normalization of the attenuation coefficient, z-score standardization of the connection loss data, and relative distance conversion of the fault point coordinates. The algorithm also constructs a feature descriptor, which encodes the multi-dimensional performance indicators of the optical fiber into a fixed-dimensional feature vector, including attenuation features, loss features, and location features, among other dimensions of information. The deep learning network uses a multi-layer convolutional neural network structure for fault classification, which includes 3 convolutional layers and 2 fully connected layers. The input layer receives the normalized feature vector, extracts the local correlation of optical fiber performance features through convolution operations, and the pooling layer performs feature dimension reduction and extracts main features. The fully connected layer maps the features to the fault classification space, and the output layer calculates the probability distribution of each fault level through the softmax function. The network is trained on 10,000 historical fault samples to establish the mapping relationship between the feature vector and the fault level.

[0087] The expert rule base performs inference analysis based on a pre-set optical fiber fault diagnosis rule base, which contains 200 optical fiber fault diagnosis rules covering common fault types and abnormal patterns. The algorithm uses a forward reasoning strategy, taking the fault level obtained by deep learning as a fact input, generating detailed abnormal type descriptions through rule matching and reasoning chain, including fault properties, impact range, and severity, among other information. The correlation analysis algorithm intelligently searches the historical fault case library, which contains 5,000 verified optical fiber fault handling cases. The algorithm calculates the similarity between the current abnormal type and the historical cases, measures the correlation between feature vectors using cosine similarity, and selects the case with the highest similarity as a reference. Based on the selected similar cases, the algorithm extracts their handling methods and effect evaluation to form targeted optimization suggestions.

[0088] The multi-dimensional evaluation algorithm comprehensively evaluates the fault handling scheme from multiple dimensions such as technical feasibility, implementation difficulty, and resource demand. The algorithm establishes a scoring model to score each optimization suggestion, considering factors such as repair effect, implementation cost, and time requirements. The weights of each evaluation dimension are determined by the analytic hierarchy process, the comprehensive score of the scheme is calculated, and the optimization strategies are prioritized according to the score. The decision fusion algorithm uses the Dempster-Shafer evidence theory framework to fuse multi-source information such as fault level, abnormal type, and optimization strategy. The algorithm calculates the basic probability assignment of each data source, integrates the information of multiple evidence sources through evidence synthesis rules, and generates the final decision recommendation. The fused diagnosis decision data contains complete fault diagnosis information, handling suggestions, and credibility evaluation.

[0089] For example, the feature conversion algorithm converts the original parameters into a 100-dimensional feature vector containing normalized attenuation coefficients, loss values, and position information. The deep learning network analysis shows that the fault level is level 3 (moderate fault) with a confidence of 0.92. The expert rule-based reasoning determines that the joint degradation class fault, with the impact limited to the connection point at 2000 meters. The correlation analysis retrieves 3 similar cases from the case library, suggesting the use of re-fusion scheme for processing. The multi-dimensional evaluation compares multiple processing schemes, with the re-fusion scheme scoring 85 points (out of 100), ranking first in the optimization strategy. The decision fusion generates a diagnostic report confirming the joint degradation fault and recommending re-fusion within two weeks, which is expected to reduce the loss by 0.15 dB.

[0090] In a specific embodiment, the process of performing step S106 can specifically include the following steps:

[0091] (1) Perform spatial structure analysis on the diagnostic decision data by a topology mapping algorithm to obtain a topology atlas;

[0092] (2) Construct a view based on the topology atlas by a graph rendering algorithm to obtain a three-dimensional visualized topology atlas;

[0093] (3) Perform spatial distribution processing on the loss information in the diagnostic decision data by an interpolation calculation algorithm to obtain a loss distribution;

[0094] (4) Quantify the health state of the diagnostic decision data by a scoring calculation algorithm to obtain a health score;

[0095] (5) Correlate and map the three-dimensional visualized topology atlas and the loss distribution by a spatial registration algorithm to obtain state visualized data;

[0096] (6) Integrate the state visualized data and the health score by a report generation algorithm to obtain an optical fiber state evaluation report.

[0097] Specifically, the optical fiber network structure information in the diagnostic decision data is parsed, and the optical fiber connection relationship and spatial position information are extracted. The algorithm uses a graph theory method to construct a network topology model, representing optical fiber ports as nodes and optical fiber connections as edges, while recording the three-dimensional spatial coordinate information of each node. The network structure layout is optimized by the minimum spanning tree algorithm to ensure the clarity and readability of the topology atlas, generating a network topology structure diagram containing complete connection relationships. The graph rendering algorithm visualizes the topology atlas based on the WebGL three-dimensional graphics engine, mapping the optical fiber network structure to a virtual three-dimensional space through three-dimensional modeling. The algorithm uses a geometry shader to generate a three-dimensional curve of the optical fiber path, enhancing the visual effect through texture mapping and lighting calculation. During the rendering process, the view roaming, scaling operation, and node interaction functions are realized, supporting observation of the network structure from different angles and quick positioning of the focus area.

[0098] The interpolation calculation algorithm adopts the Kriging spatial interpolation method to estimate the continuous distribution of the discrete loss measurement data. The algorithm considers the spatial correlation and calculates the loss estimation value of any position point according to the numerical value and position information of the known loss points. The spatial correlation is described by a variogram model, the interpolation parameters are optimized, and a high-precision loss distribution map is generated to intuitively display the spatial variation characteristics of the loss. The scoring calculation algorithm establishes a multi-level health evaluation index system, including transmission performance, structural integrity, and reliability dimensions. The algorithm uses a fuzzy comprehensive evaluation method to calculate the health score according to each performance index, considers the index weight and grade division, and standardizes the score result to the range of 0-100 points. At the same time, the sub-item score and the overall score are generated to quantitatively reflect the overall health status of the fiber link.

[0099] The spatial registration algorithm adopts a feature point matching method to accurately align the three-dimensional topology map and the loss distribution map. The algorithm extracts the feature points of the two data sets, calculates the spatial transformation matrix, and realizes the unified registration of the coordinate system. The registration process optimizes the transformation parameters through the iterative closest point algorithm to ensure the accuracy of the visualization effect, and generates state visualization data integrating the topology structure and loss information. The report generation algorithm adopts a templated way to build the evaluation report, and arranges and displays the state visualization data and health score information according to the standard format. The algorithm automatically generates fault diagnosis conclusions, health status evaluation and optimization suggestions, and presents the evaluation results in the form of charts, data tables, etc. The report also contains historical trend analysis and predictive maintenance suggestions to provide a basis for operation and maintenance decisions.

[0100] Taking a data center fiber network as an example, the topology mapping analysis shows that the network contains 120 fiber ports, forming a star connection structure. The graph rendering generates a three-dimensional view, clearly showing the direction and crossing relationship of each layer of fiber. The interpolation calculation shows that there is a high-loss area at 2000 meters, with a loss peak of 0.45 dB. The health scoring system gives a transmission performance score of 85 points, a structural integrity score of 92 points, and an overall health score of 88 points for the fiber segment. After spatial registration, the correspondence between the loss distribution and the physical location is intuitively displayed, highlighting the areas that need to be focused on. The final generated evaluation report records all the diagnosis and evaluation information in detail, and suggests that the high-loss area be optimized during the next maintenance.

[0101] The above describes the optical fiber performance automatic testing method based on optical power detection in the embodiments of the present application. The following describes the optical fiber performance automatic testing system based on optical power detection in the embodiments of the present application. Please refer to Figure 2 An embodiment of the optical fiber performance automatic testing system based on optical power detection in the embodiments of the present application includes:

[0102] The detection module 201 is configured to comprehensively detect the fiber network structure through intelligent fiber scanning, and generate fiber resource mapping data containing fiber number data, fiber spatial position data, and optical path connection relationship data.

[0103] The calculation module 202 is configured to calculate test parameters of the fiber resource mapping data through a dynamic analysis algorithm, and obtain an OTDR measurement configuration table containing wavelength selection parameters, pulse width, and sampling frequency.

[0104] The acquisition module 203 is configured to perform optical pulse injection and signal acquisition on the fiber according to the parameters specified in the OTDR measurement configuration table, and obtain a time-domain response characteristic curve of the fiber link.

[0105] The processing module 204 is configured to perform data processing on the time-domain response characteristic curve through a wavelet denoising and peak value recognition algorithm, and obtain a fiber performance parameter set containing fault point coordinates, attenuation coefficients, and connection losses.

[0106] The analysis module 205 is configured to comprehensively analyze the fiber performance parameter set through a deep learning network and an expert rule base, and obtain diagnostic decision data containing fault levels, abnormal types, and optimization suggestions.

[0107] The conversion module 206 is configured to perform visual conversion on the diagnostic decision data through digital twin modeling, and obtain a fiber state evaluation report containing a topology map, a loss distribution, and a health score.

[0108] Through the cooperation of the above components, comprehensive detection is performed through intelligent fiber scanning, the number, spatial position data, and connection relationship information of the fiber network can be accurately obtained, manual recording errors can be effectively avoided, the accuracy and efficiency of resource information acquisition are significantly improved, test parameter calculation is performed on the fiber resource mapping data through a dynamic analysis algorithm, intelligent configuration of OTDR measurement parameters is realized, the best matching between test parameters and fiber characteristics is ensured, the accuracy and reliability of test results are improved, precise timing control and real-time sampling technology are adopted during the process of optical pulse injection and signal acquisition on the fiber, the time resolution and integrity of measurement data are ensured, high-quality raw data is provided for subsequent analysis, the time-domain response characteristic curve is processed through a wavelet denoising and peak value recognition algorithm, the influence of measurement noise is effectively eliminated, the fault point position and performance parameters are accurately identified, the accuracy of fault diagnosis is improved, a deep learning network and an expert rule base are adopted for comprehensive analysis, the adaptive ability of machine learning and expert experience are combined, more accurate and intelligent fault diagnosis is realized, reliable optimization suggestions are provided, and finally, visual conversion is performed through digital twin modeling, the state and performance distribution of the fiber network are intuitively displayed, maintenance personnel can quickly understand and locate problems, and the operation and maintenance efficiency is improved.

[0109] Figure 3 A schematic block diagram of an electronic device 300 that can be used to implement embodiments of the present application is shown. The electronic device is intended to represent various forms of digital computers, such as laptops, desktops, tablets, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular telephones, smartphones, wearable devices, and other similar computing devices. The components shown here, their connections and relationships, and their functions, are meant to be examples only, and are not intended to limit the implementations of the present application described and / or claimed in this document.

[0110] The electronic device 300 includes a computing unit 301 that can perform various appropriate actions and processes in accordance with a computer program stored in a ROM 302 or a computer program loaded from the storage unit 308 into a RAM 303. In the RAM 303, various programs and data required for the operation of the electronic device 300 can also be stored. The computing unit 301, the ROM 302, and the RAM 303 are connected to each other through a bus 304. An I / O interface 305 is also connected to the bus 304.

[0111] Various components in the electronic device 300 are connected to the I / O interface 305, including an input unit 306, such as a keyboard, a mouse, and the like; an output unit 307, such as various types of displays, speakers, and the like; a storage unit 308, such as a magnetic disk, an optical disk, and the like; and a communication unit 309, such as a network card, a modem, a wireless communication transceiver, and the like. The communication unit 309 allows the electronic device 300 to exchange information / data with other devices through a computer network, such as the Internet, and / or various telecommunication networks.

[0112] The computing unit 301 can be various general and / or special purpose processing components with processing and computing capabilities. Some examples of the computing unit 301 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 301 performs various methods and processes described above, such as the optical fiber performance automatic testing method based on optical power detection. For example, in some embodiments, the optical fiber performance automatic testing method based on optical power detection can be implemented as a computer software program tangibly embodied in a machine-readable medium, such as the storage unit 308. In some embodiments, part or all of the computer program can be loaded and / or installed onto the electronic device 300 via the ROM 302 and / or the communication unit 309. When the computer program is loaded onto the RAM 303 and executed by the computing unit 301, one or more steps of the optical fiber performance automatic testing method based on optical power detection described above can be performed. Alternatively, in other embodiments, the computing unit 301 can be configured to perform the optical fiber performance automatic testing method based on optical power detection by other any suitable means, such as by means of firmware.

[0113] Various implementations of the systems and techniques described above can be realized in digital electronic circuitry, integrated circuitry, a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on a chip (SOC), a programmable logic device (CPLD), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0114] Program code for carrying out methods of the present application can be written in any combination of one or more programming languages. The program code can be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the program code, when executed by the processor or controller, produces a means for implementing the functions / acts specified in the flowcharts and / or block diagrams. The program code can be executed entirely on a machine, partially on a machine, partially on a machine and partially on a remote machine or entirely on a remote machine or server.

[0115] In the context of this application, a machine-readable medium can be a tangible medium that contains or stores a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include but is not limited to an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of the machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0116] To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having a display device for displaying information to the user and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the computer. Other kinds of devices can be used to provide for interaction with a user as well; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.

[0117] The systems and techniques described here can be implemented in a computing system that includes a back end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front end component (e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back end, middleware, or front end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), and the Internet.

[0118] The computer system can include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server can arise by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0119] It should be understood that the various forms of flow shown above can be re-ordered, steps added or removed, etc. For example, the steps described in this application can be performed in parallel, in series, in a different order, etc. as long as the desired results of the technology disclosed herein are achieved, and this application is not limited herein.

[0120] The specific embodiments discussed herein should not be construed as limiting the scope of the application, which is defined by the appended claims. Those skilled in the art will recognize that modifications, combinations, sub-combinations, and alternatives can be made to the specific embodiments without departing from the application disclosed herein. Any modifications, changes, and improvements made to the specific embodiments discussed herein are to be considered as being within the scope of the present application.

Claims

1. A method for automatically testing optical fiber performance based on optical power detection, characterized in that: The method comprises: Comprehensively detect the optical fiber network structure through optical fiber intelligent scanning, and generate optical fiber resource mapping data including optical fiber number data, optical fiber spatial location data, and optical path connection relationship data; Calculating test parameters of the optical fiber resource mapping data using a dynamic analysis algorithm to obtain an OTDR measurement configuration table including wavelength selection parameters, pulse width, and sampling frequency; Performing optical pulse injection and signal acquisition on the optical fiber according to the parameters specified in the OTDR measurement configuration table to obtain a time domain response characteristic curve of the optical fiber link; Processing the time domain response characteristic curve using wavelet noise reduction and peak recognition algorithms to obtain a set of optical fiber performance parameters including fault point coordinates, attenuation coefficient, and connection loss; Comprehensively analyzing the optical fiber performance parameter set through a deep learning network and an expert rule base to obtain diagnostic decision data including fault level, abnormality type, and optimization suggestions; The diagnostic decision data is visualized and converted through digital twin modeling to obtain an optical fiber status assessment report including topology map, loss distribution, and health score.

2. The optical fiber performance automatic testing method based on optical power detection according to claim 1 is characterized in that: The optical fiber network structure is comprehensively detected by optical fiber intelligent scanning to generate optical fiber resource mapping data containing optical fiber numbering data, optical fiber spatial position data, and optical path connection relationship data, including: Scan and detect the optical fiber network structure through the port identification algorithm to obtain optical fiber number data; Performing three-dimensional coordinate acquisition using a grating positioning algorithm based on the optical fiber numbering data to obtain optical fiber spatial position data; Performing connection determination on the optical fiber number data by using an optical path tracking algorithm to obtain an initial optical path connection relationship; Performing correlation verification based on the optical fiber spatial position data and the initial connection relationship of the optical path through a topology analysis algorithm to obtain optical path connection relationship data; Extracting features from the optical fiber numbering data, the optical fiber spatial position data, and the optical path connection relationship data using an attribute association algorithm to obtain a resource feature set; The resource feature set is standardized and sorted through a data aggregation algorithm to generate the optical fiber resource mapping data.

3. The optical fiber performance automatic testing method based on optical power detection according to claim 1, characterized in that: The optical fiber resource mapping data is subjected to test parameter calculation by a dynamic analysis algorithm to obtain an OTDR measurement configuration table including wavelength selection parameters, pulse width, and sampling frequency, including: Dividing the optical fiber resource mapping data into sections using a path analysis algorithm to obtain optical fiber feature groups containing different wavelength selection parameter ranges; Performing wavelength preselection calculations based on the optical fiber feature groups using a dynamic threshold algorithm to obtain wavelength selection parameters; Calculating the fiber length of the fiber resource mapping data using an adaptive allocation algorithm to obtain a corresponding pulse width; Perform sampling calculation according to the wavelength selection parameter and the pulse width through a frequency optimization algorithm to obtain a sampling frequency; Integrating the wavelength selection parameter, the pulse width, and the sampling frequency through a parameter combination algorithm to obtain a test parameter matrix; The test parameter matrix is ​​standardized through a format conversion algorithm to obtain the OTDR measurement configuration table.

4. The optical fiber performance automatic testing method based on optical power detection according to claim 1 is characterized in that: The step of injecting light pulses and collecting signals on the optical fiber according to the parameters specified in the OTDR measurement configuration table to obtain a time domain response characteristic curve of the optical fiber link includes: Extracting parameters from the OTDR measurement configuration table using a parameter parsing algorithm to obtain an optical pulse injection control sequence; generating an optical signal by a pulse modulation algorithm according to the optical pulse injection control sequence to obtain an optical pulse signal to be injected; The optical pulse signal is power-adjusted by a photoelectric converter to obtain a detection signal injected into the optical fiber; According to the sampling frequency in the OTDR measurement configuration table, data acquisition is performed on the optical fiber return signal through a real-time sampling algorithm to obtain original response data; Performing time synchronization and amplitude calibration on the original response data through a time series processing algorithm to obtain standardized response data; The standardized response data is subjected to curve fitting through a feature extraction algorithm to obtain the time domain response characteristic curve.

5. The optical fiber performance automatic testing method based on optical power detection according to claim 1, characterized in that: The time domain response characteristic curve is processed by wavelet noise reduction and peak recognition algorithm to obtain a set of optical fiber performance parameters including fault point coordinates, attenuation coefficient, and connection loss, including: Performing multi-scale analysis on the time domain response characteristic curve by wavelet decomposition algorithm to obtain noise characteristic coefficient; Performing signal filtering using a threshold processing algorithm according to the noise characteristic coefficient to obtain denoised response data; Performing feature point positioning on the denoised response data using a peak recognition algorithm to obtain a feature point sequence containing the coordinates of the fault point; Calculating the loss using a slope analysis algorithm based on the characteristic point sequence to obtain optical fiber attenuation coefficient data; Performing connection point analysis on the characteristic point sequence using a joint loss calculation algorithm to obtain optical fiber connection loss data; The fault point coordinates, the attenuation coefficient, and the connection loss are integrated through a data fusion algorithm to obtain the optical fiber performance parameter set.

6. The optical fiber performance automatic testing method based on optical power detection according to claim 1, characterized in that: The optical fiber performance parameter set is comprehensively analyzed through a deep learning network and an expert rule base to obtain diagnostic decision data including fault level, abnormality type, and optimization suggestions, including: Normalizing the optical fiber performance parameter set by a feature conversion algorithm to obtain a normalized feature vector; Performing fault classification calculation on the normalized feature vector through a deep learning network to obtain a fault level; Perform rule matching on the fault level through an expert rule base to obtain an abnormality type; According to the anomaly type, historical case retrieval is performed using a correlation analysis algorithm to obtain optimization suggestions; Prioritizing the fault levels and the optimization suggestions using a multi-dimensional evaluation algorithm to obtain an optimization strategy sequence; The fault level, the abnormality type and the optimization strategy sequence are integrated through a decision fusion algorithm to obtain the diagnosis decision data.

7. The optical fiber performance automatic testing method based on optical power detection according to claim 1, characterized in that: The diagnostic decision data is visualized and converted through digital twin modeling to obtain a fiber status assessment report containing a topology map, loss distribution, and health score, including: Performing spatial structure analysis on the diagnostic decision data using a topological mapping algorithm to obtain a topological map; According to the topological map, a view is constructed by a graphics rendering algorithm to obtain a three-dimensional visual topological map; Performing spatial distribution processing on the loss information in the diagnosis decision data by an interpolation calculation algorithm to obtain a loss distribution; quantifying the health status of the diagnostic decision data using a scoring calculation algorithm to obtain a health score; Correlation mapping is performed between the three-dimensional visualization topology map and the loss distribution through a spatial registration algorithm to obtain state visualization data; The status visualization data and the health score are integrated through a report generation algorithm to obtain the optical fiber status assessment report, which realizes visualization conversion through digital twin modeling and intuitively displays the status and performance distribution of the optical fiber network.

8. An automatic optical fiber performance test system based on optical power detection, used to implement the automatic optical fiber performance test method based on optical power detection as described in any one of claims 1 to 7, characterized in that: The optical fiber performance automatic testing system based on optical power detection includes: The detection module is used to conduct a comprehensive detection of the optical fiber network structure through optical fiber intelligent scanning, and generate optical fiber resource mapping data including optical fiber number data, optical fiber spatial position data, and optical path connection relationship data; A calculation module is used to calculate test parameters of the optical fiber resource mapping data through a dynamic analysis algorithm to obtain an OTDR measurement configuration table including wavelength selection parameters, pulse width, and sampling frequency; An acquisition module, configured to perform optical pulse injection and signal acquisition on the optical fiber according to the parameters specified in the OTDR measurement configuration table, and obtain a time domain response characteristic curve of the optical fiber link; A processing module, configured to perform data processing on the time domain response characteristic curve using a wavelet noise reduction and peak recognition algorithm to obtain a set of optical fiber performance parameters including fault point coordinates, attenuation coefficient, and connection loss; An analysis module is used to comprehensively analyze the optical fiber performance parameter set through a deep learning network and an expert rule base to obtain diagnostic decision data including fault level, abnormality type, and optimization suggestions; The conversion module is used to perform visual conversion on the diagnostic decision data through digital twin modeling to obtain an optical fiber status assessment report including a topology map, loss distribution, and health score.

9. An electronic device comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, so as to enable the at least one processor to perform the method according to any one of claims 1 to 7.

Images