A method and system for measuring fiber optic parameters based on holmium laser fiber

Abstract

The present invention discloses a method and system for measuring optical fiber parameters based on holmium laser optical fiber, which belongs to the field of optical fiber measurement technology, and specifically includes: simulation optimization of preliminary optical fiber arrangement scheme, precise adjustment of optical fiber far-end angle and brightness, detailed scheme of multi-parameter measurement, and intelligent performance evaluation and overall optimization strategy based on deep learning; adjusting optical fiber arrangement through multi-dimensional simulation, optimizing optical fiber far-end setting in combination with experimental verification, so as to achieve basic improvement of optical fiber performance; adopting multi-parameter measurement method to comprehensively record optical fiber performance data, and using deep learning model for intelligent evaluation, so as to ensure that optical fiber performance meets preset standards; for indicators that do not meet the standards in the evaluation, the present invention further provides an overall optimization scheme to achieve comprehensive optimization and performance improvement of optical fiber system, so as to improve the accuracy and efficiency of optical fiber system design and manufacturing.

Description

Technical Field

[0001] The invention belongs to the technical field of optical fiber measurement, and in particular to an optical fiber parameter measurement method and system based on holmium laser optical fiber. Background Art

[0002] Optical fiber is the medium for transmitting optical signals. In optical fiber communication systems, the transmission performance of optical fiber directly affects the stability and efficiency of the entire system. The selection, layout and remote processing of optical fiber have a significant impact on the transmission performance. Therefore, accurate measurement of optical fiber transmission parameters is particularly important. However, traditional measurement methods often ignore the impact of optical fiber type, array arrangement, and remote angle and brightness on transmission performance, resulting in inaccurate measurement results.

[0003] For example, the Chinese patent application with publication number CN106338308A discloses a distributed multi-parameter sensing system based on an ultrashort fiber grating array, including: a scanning laser light source, a modulation amplifier unit, a circulator, an ultrashort fiber grating array, a matching interferometer, a reflected light detection unit, and a signal processing unit. The beneficial effect of this technical solution is: providing a distributed multi-parameter sensing system based on an ultrashort fiber grating array, introducing an ultrashort fiber grating array US-wFBG, and solving the problem that traditional interference-type distributed sensing cannot measure static physical quantities. The sensing system combines the advantages of optical coherent detection and wavelength detection, and simultaneously realizes the measurement of distributed disturbances and quasi-distributed static quantities such as temperature and strain signals.

[0004] For example, a Chinese patent application with publication number CN117571053A discloses an optical fiber pulmonary artery and blood viscosity detection sensor and a preparation method thereof, comprising: a hollow core optical fiber whose core is filled with polydimethylsiloxane (PDMS), and a single crystal gold film with a periodic nanopore array structure grown on the end face of the optical fiber; the preparation method mainly grows a single crystal gold nanofilm with adjustable sensitivity having an ordered nanopore array by a solution method, plasma etching, and the like; the sensor greatly improves the sensitivity of pulmonary artery detection by adjusting the nanopore diameter and the nanopore spacing, and can detect pulmonary artery pressure and blood viscosity by a highly sensitive optical detection method, and can achieve the characteristics of simultaneous detection of multiple parameters, high sensitivity, high reliability, multiple measurement ranges, repeatable preparation, low power consumption, easy to form a sensor network, not easy to cause infection, safe and non-toxic, etc.

[0005] The above existing technologies all have the following problems: 1) high cost and complexity; 2) limitations in application areas; 3) restrictions on sensitivity adjustment. Summary of the invention

[0006] In view of the shortcomings of the prior art, the present invention proposes a method and system for measuring optical fiber parameters based on holmium laser optical fiber, including simulation optimization of the preliminary optical fiber arrangement scheme, precise adjustment of the optical fiber far-end angle and brightness, a detailed scheme for multi-parameter measurement, and intelligent performance evaluation and overall optimization strategy based on deep learning; the optical fiber arrangement is adjusted through multi-dimensional simulation, and the optical fiber far-end setting is optimized in combination with experimental verification to achieve a basic improvement in optical fiber performance; a multi-parameter measurement method is used to comprehensively record optical fiber performance data, and a deep learning model is used for intelligent evaluation to ensure that the optical fiber performance meets the preset standards; for indicators that do not meet the standards in the evaluation, the present invention further provides an overall optimization scheme to achieve comprehensive optimization and performance improvement of the optical fiber system, thereby improving the accuracy and efficiency of the design and manufacture of the optical fiber system.

[0007] To achieve the above object, the present invention provides the following technical solutions:

[0008] A method for measuring optical fiber parameters based on holmium laser optical fiber, comprising:

[0009] Step S1: setting a preliminary optical fiber arrangement plan, and performing a multi-dimensional simulation on the preliminary optical fiber arrangement plan, adjusting and optimizing the preliminary optical fiber arrangement plan according to the simulation results, obtaining an optimal optical fiber arrangement plan, and drawing an optical fiber arrangement diagram;

[0010] Step S2: Based on the optimal fiber arrangement plan, set the fiber remote angle adjustment mechanism and formulate a brightness improvement plan, verify the effects of angle and brightness adjustment through experiments, obtain the optimal parameter settings of fiber remote angle and brightness, and generate a remote optimization plan;

[0011] Step S3: Formulate a multi-parameter measurement plan, perform multi-parameter measurement on the optical fiber under the optimal optical fiber arrangement plan and the remote optimization plan, and record the optical fiber parameter data;

[0012] Step S4: Establish an intelligent evaluation model based on deep learning, use the intelligent evaluation model to evaluate the measured optical fiber parameter data, and compare and analyze the evaluation results with the preset standards to determine whether the optical fiber performance meets the standards;

[0013] Step S5: Based on the comparative analysis results, identify the optical fiber performance indicators that do not meet the standards, and formulate and implement an overall optimization plan for the optical fiber performance indicators that do not meet the standards.

[0014] Specifically, the specific steps of step S1 include:

[0015] S1.1: Design a preliminary fiber layout plan based on demand and environmental data, and draw a preliminary fiber layout diagram;

[0016] S1.2: Use optical simulation software to establish a simulation model of the optical fiber array, and combine the transmission characteristics of light in the optical fiber to perform multi-dimensional simulation of the preliminary optical fiber arrangement plan;

[0017] S1.3: Based on the simulation results, calculate the light transmission characteristics in the optical fiber. The formula is:

[0018] ;

[0019] in, It indicates the power at a distance d from the light source when the fiber temperature is T. d indicates the distance from the fiber input end to the measurement point. T indicates the current fiber temperature. represents the initial power, is the absorption attenuation coefficient, represents the scattering attenuation coefficient, is the coupling attenuation coefficient, represents the temperature influence coefficient, Indicates the rated operating temperature of the optical fiber. Represents an exponential function.

[0020] Specifically, the specific steps of step S1 also include:

[0021] S1.4: Based on the calculated optical transmission characteristics, identify performance bottlenecks, use optimization strategies to adjust and optimize the initial fiber layout plan based on the identified problems, and re-perform multi-dimensional simulation to obtain optimized optical transmission characteristics ;

[0022] S1.5: Setting the optimization strategy convergence threshold ;

[0023] like , then return to step S1.4 to continue optimization;

[0024] like , then the optimal optical fiber arrangement solution is obtained;

[0025] S1.6: Use CAD software to draw the optimal fiber layout diagram and mark the parameters.

[0026] Specifically, the specific steps of step S2 include:

[0027] S2.1: Integrate the fiber arrangement, transmission environment and far-end angle data, establish a database, and use machine learning algorithms to train the database data, build a prediction model, and combine the reinforcement learning algorithm to dynamically adjust the predicted far-end angle to obtain the optimal far-end angle;

[0028] S2.2: Use physical optics software to establish a fiber transmission simulation model, use artificial intelligence-driven simulation methods to evaluate the effects of different light source parameters, fiber materials and coatings on brightness, and use a multi-objective optimization algorithm to find the optimal solution set in the simulation environment and develop a brightness improvement plan. The formula of the multi-objective optimization algorithm is:

[0029] ;

[0030] in, Representation strategy Performance function About parameters The gradient of represents strategy, which refers to the combination of light source parameters, optical fiber materials and coating parameters. N represents the number of simulation experiments. represents the number of time steps of the ith simulation experiment, K represents the total number of parameters, express The gradient weight of represents the action taken by simulation experiment i at time step t, represents the state of simulation experiment i at time step t, Represents external environment information, represents the jth parameter, Indicates in status and external environmental information Next select action The logarithmic probability of The gradient of represents the total brightness of the entire experimental trajectory, represents the state of optical signal transmission in the optical fiber and the corresponding action in the i-th simulation experiment, represents the discount factor, represents the weight adjustment coefficient, It means that the simulation experiment i has a time step of The instant brightness increment on represents the weight coefficient of the baseline term, Indicates in status Expected brightness under .

[0031] Specifically, the specific steps of step S2 also include:

[0032] S2.3: Integrate the laser interferometer and the robotic arm, write the control script, guide the robotic arm to automatically install the fiber array according to the optimal fiber arrangement plan, and automatically call the brightness and angle adjustment mechanism for preliminary calibration. At the same time, use a high-resolution camera to visually inspect the installation results;

[0033] S2.4: Use the Internet of Things method to collect the test data of the optical fiber far end angle and brightness in real time, and perform preprocessing and feature extraction;

[0034] S2.5: Use deep learning algorithms to build an analysis model, input the feature-extracted data into the analysis model, and obtain the optimal parameter combination;

[0035] S2.6: Generate an optimized far-end angle and brightness configuration scheme based on the best parameter combination, use an intelligent recommendation method to recommend the best parameter combination based on historical data, and automatically push the optimization scheme to the control system through an automated script to guide the actual adjustment of the fiber array;

[0036] S2.7: Continuously monitor the operating status of the system, collect feedback data, regularly update the analysis model and optimization plan, and use active learning technology to selectively update the analysis model based on feedback data;

[0037] The specific steps of S2.3 include:

[0038] S2.31: Determine the optimal fiber layout, including the position, angle and spacing of the fibers, calibrate the laser interferometer and the robotic arm, and write the control script, including the motion control of the robotic arm, the data reading and processing of the laser interferometer, and the calling of the brightness and angle adjustment mechanism;

[0039] S2.32: The robot arm moves from a preset starting position to a fiber grabbing point according to the optimal fiber arrangement plan, grabs the fiber using the end effector of the robot arm, and moves the fiber to a designated installation position;

[0040] S2.33: The robot arm places the optical fiber accurately at the installation position and releases the optical fiber;

[0041] S2.34: Automatically call the brightness and angle adjustment mechanism to adjust the brightness and angle of the optical fiber according to the parameters in the optimal optical fiber arrangement plan;

[0042] S2.35: Use a high-resolution camera to take pictures of the installed optical fiber array and use image processing technology to check whether the position, angle, and spacing of the optical fibers meet the requirements. If any problems are found, reinstall or adjust them.

[0043] Specifically, the specific steps of step S4 include:

[0044] S4.1: Obtain the optical fiber parameter data in step S3, perform automatic anomaly detection, extract optical fiber performance characteristics from the optical fiber parameter data after anomaly detection, and obtain optical fiber performance characteristic data;

[0045] S4.2: Load the deep learning model, use the fiber performance characteristic data to train and optimize the deep learning model, and integrate the trained deep learning model with the system module to generate an intelligent evaluation model;

[0046] S4.3: Input the real-time measured fiber parameter data into the intelligent evaluation model to generate the evaluation result X, and compare the evaluation result with the preset fiber performance standard For comparative analysis, if , the early warning mechanism is automatically triggered and early warning information is sent;

[0047] S4.4: Use the evaluation results and warning information as feedback to guide fiber maintenance, upgrades, or retrain models to form a closed-loop optimization system.

[0048] Specifically, the multi-dimensional simulation in step S1 includes simulating the light emission angle, light spot uniformity, and energy distribution; the optical fiber arrangement scheme includes the setting of the number, spacing, heat distribution, angle, and intersection between optical fibers.

[0049] Specifically, the optimization strategy in S1.4 includes adjusting the spacing between optical fibers, changing the arrangement angle of the optical fibers, and optimizing the angle and brightness setting of the far end of the optical fibers.

[0050] A fiber parameter measurement system based on holmium laser fiber, comprising: a fiber arrangement optimization module, a remote parameter optimization module, a multi-parameter measurement module, an intelligent evaluation module, and an optimization module;

[0051] The optical fiber arrangement optimization module is responsible for designing and optimizing the optical fiber arrangement scheme;

[0052] The remote parameter optimization module further adjusts the angle and brightness of the remote end of the optical fiber based on the optimal optical fiber arrangement solution;

[0053] The multi-parameter measurement module is used to perform multi-parameter measurement on the optical fiber and collect optical fiber parameter data under the optimal optical fiber arrangement scheme and the remote optimization scheme;

[0054] The intelligent evaluation module is used to use a deep learning model to intelligently evaluate the optical fiber parameter data, and compare and analyze it with the preset standard to determine whether the optical fiber performance meets the standard;

[0055] The optimization module is used to identify and optimize the optical fiber performance indicators that do not meet the standards based on the comparative analysis results.

[0056] Compared with the prior art, the present invention has the following beneficial effects:

[0057] 1. The present invention proposes a method for measuring optical fiber parameters based on holmium laser optical fiber. By initially setting and adjusting the optical fiber arrangement scheme through multi-dimensional simulation, the scientific nature and optimization of the optical fiber layout are ensured, the optical fiber transmission efficiency and the rationality of the overall layout are directly improved, and the installation and maintenance costs are reduced. The optical fiber far-end angle and brightness optimization further implemented based on the optimal arrangement effectively improves the visual expression of the optical fiber system. The implementation of the multi-parameter measurement scheme provides a solid foundation for the comprehensive evaluation of optical fiber performance, and data-driven analysis ensures the accuracy of the evaluation.

[0058] 2. The present invention proposes a method for measuring optical fiber parameters based on holmium laser optical fiber. From preliminary arrangement to multi-dimensional simulation adjustment, and then to precise adjustment of the far-end angle and brightness, each step aims to reduce loss and enhance brightness, thereby improving the overall efficiency of the optical fiber system. In addition, through the introduction of deep learning intelligent evaluation models, not only efficient and accurate evaluation of optical fiber performance is achieved, but also performance shortcomings can be quickly located, effectively shortening the product development cycle and reducing the defective rate. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Figure 1 A schematic diagram of a method for measuring optical fiber parameters based on holmium laser optical fiber according to the present invention;

[0060] Figure 2 This is a principle flow chart of a method for measuring optical fiber parameters based on holmium laser optical fiber of the present invention;

[0061] Figure 3 This is a flowchart for realizing an optimal optical fiber arrangement scheme of an optical fiber parameter measurement method based on holmium laser optical fiber of the present invention;

[0062] Figure 4 This is a flowchart of a remote optimization solution for a method for measuring optical fiber parameters based on holmium laser optical fiber according to the present invention;

[0063] Figure 5 This is a fiber transmission framework diagram of a fiber parameter measurement method based on holmium laser fiber of the present invention;

[0064] Figure 6 This is an architecture diagram of an optical fiber parameter measurement system based on holmium laser optical fiber of the present invention. DETAILED DESCRIPTION

[0065] Example 1

[0066] See also Figure 1 and Figure 2 The present invention provides an embodiment: a method for measuring optical fiber parameters based on holmium laser optical fiber, which is applicable to the medical field, comprising the following steps:

[0067] Step S1: setting a preliminary optical fiber arrangement plan, and performing a multi-dimensional simulation on the preliminary optical fiber arrangement plan, adjusting and optimizing the preliminary optical fiber arrangement plan according to the simulation results, obtaining an optimal optical fiber arrangement plan, and drawing an optical fiber arrangement diagram;

[0068] The optical fiber layout diagram should include: the location, direction, and connection method information of each optical fiber segment.

[0069] The multi-dimensional simulation in step S1 includes simulating the light emission angle, light spot uniformity, and energy distribution; the optical fiber arrangement scheme includes the setting of the number, spacing, heat distribution, angle, and intersection between optical fibers.

[0070] Step S2: Based on the optimal fiber arrangement plan, set the fiber remote angle adjustment mechanism and formulate a brightness improvement plan, verify the effects of angle and brightness adjustment through experiments, obtain the optimal parameter settings of fiber remote angle and brightness, and generate a remote optimization plan;

[0071] When developing a brightness enhancement plan, it is necessary to consider using special coatings, reflective materials or optical elements to enhance light intensity.

[0072] Step S3: Formulate a multi-parameter measurement plan, perform multi-parameter measurement on the optical fiber under the optimal optical fiber arrangement plan and the remote optimization plan, and record the optical fiber parameter data;

[0073] Among them, multiple parameters include: transmission loss, bandwidth, dispersion, and polarization mode dispersion.

[0074] Furthermore, the specific steps of step S3 include:

[0075] S3.1: Based on the optimal fiber arrangement plan and remote optimization plan, formulate a multi-parameter measurement plan, including the types of measurement parameters and measurement frequency;

[0076] S3.2: Build a fiber optic parameter measurement system, including sensors, data acquisition equipment, and analysis software;

[0077] S3.3: Implement a multi-parameter measurement scheme on the fiber array and record fiber parameter data in real time;

[0078] S3.4: preprocessing the optical fiber parameter data, including filtering, denoising and data format conversion;

[0079] S3.5: Input the preprocessed data into the intelligent evaluation model for performance evaluation.

[0080] Step S4: Establish an intelligent evaluation model based on deep learning, use the intelligent evaluation model to evaluate the measured optical fiber parameter data, and compare and analyze the evaluation results with the preset standards to determine whether the optical fiber performance meets the standards;

[0081] Step S5: Based on the comparative analysis results, identify the optical fiber performance indicators that do not meet the standards, and formulate and implement an overall optimization plan for the optical fiber performance indicators that do not meet the standards.

[0082] Among them, the overall optimization plan includes: redesigning the optical fiber path, adjusting the far end angle, and replacing materials.

[0083] Furthermore, the specific steps of step S5 include:

[0084] S5.1: Identify the fiber performance indicators that do not meet the standards based on the comparative analysis results of the intelligent evaluation model;

[0085] S5.2: Develop an overall optimization plan for performance indicators that do not meet the standards, including fiber materials, layout adjustments, and system upgrade strategies;

[0086] S5.3: Implement the overall optimization plan and re-measure and evaluate the optimized fiber array;

[0087] S5.4: Repeat steps S5.1 to S5.3 until the optical fiber performance fully meets the standards;

[0088] S5.5: Deploy the final optimized fiber array into actual applications and conduct long-term performance monitoring and maintenance.

[0089] Example 2

[0090] See also Figure 3 and Figure 5 ,exist Figure 5 middle, represents the distance between any two optical fibers, represents the angle between any two optical fibers. In this embodiment, the specific steps of step S1 include:

[0091] S1.1: Needs Analysis and Goal Setting:

[0092] (1) Clarify the project requirements and goals, including transmission distance, bandwidth requirements, and signal loss limitations;

[0093] (2) Determine the basic parameters of the optical fiber, including the fiber diameter and numerical aperture;

[0094] (3) Collect on-site environmental data, including spatial layout, available paths, and obstacle locations;

[0095] S1.2: Design a preliminary optical fiber arrangement plan based on the requirements and environmental data, and use CAD software to draw a preliminary optical fiber arrangement diagram. The process of drawing a diagram using CAD software is the prior art content in this field, and is not an inventive solution of this application, and will not be described in detail here;

[0096] S1.3: Use optical simulation software to establish a simulation model of the optical fiber array, consider the transmission characteristics of light in the optical fiber in the simulation model, and perform multi-dimensional simulation on the preliminary optical fiber arrangement scheme, wherein the transmission characteristics include light scattering, absorption, and refraction, and the multi-dimensional simulation includes simulation analysis of light emission angle, light spot uniformity, and energy distribution parameters. The process of using optical simulation software to establish a simulation model of the optical fiber array is the prior art content in this field, and is not the inventive solution of the present application, and will not be elaborated here;

[0097] S1.4: Based on the simulation results, calculate the optical transmission characteristics in the optical fiber. The formula is:

[0098] ;

[0099] in, It indicates the power at a distance d from the light source when the fiber temperature is T. d indicates the distance from the fiber input end to the measurement point. T indicates the current fiber temperature. represents the initial power, is the absorption attenuation coefficient, represents the scattering attenuation coefficient, is the coupling attenuation coefficient, represents the temperature influence coefficient, Indicates the rated operating temperature of the optical fiber. represents the exponential function;

[0100] Among them, the optical transmission characteristics include transmission loss, refractive index distribution, and mode propagation conditions. However, the calculation formulas for transmission loss, refractive index distribution, and mode propagation conditions are prior art contents in this field and are not the creative solutions of this application, so they will not be elaborated here.

[0101] It should be noted that due to the absorption effect of optical fiber materials on light, scattering problems inside or on the surface of optical fiber, optical fiber connection, bending or interface mismatch problems, different degrees of attenuation of optical fiber will be caused, affecting the transmission power of optical fiber. Therefore, in order to solve the above problems, the present invention, based on the prior art, not only takes into account , , The impact on optical fiber materials also introduces The factor enhances the accuracy of the calculation, allowing the formula to more fully describe the change in power as the distance d increases under different temperature conditions, especially when complex media are involved, such as those containing absorption, scattering and coupling effects. In addition, by adjusting , , , parameters, the formula can flexibly adapt to power measurement in different environments and conditions.

[0102] The optimization strategies in S1.4 include adjusting the spacing between optical fibers, changing the arrangement angle of optical fibers, and optimizing the angle and brightness settings at the far end of the optical fibers.

[0103] S1.5: Based on the calculated optical transmission characteristics, identify performance bottlenecks, use optimization strategies to adjust and optimize the initial fiber layout plan based on the identified problems, and re-perform multi-dimensional simulation to obtain optimized optical transmission characteristics ,Among them, the performance bottleneck issues include uneven light spots and large energy loss;

[0104] Furthermore, the indicators for measuring the unevenness of the light spot include:

[0105] (1) Spot shape: Ideally, the spot should be circular or nearly circular with clear edges. If the spot shape is irregular, such as elliptical, polygonal, or obviously uneven, it can be considered as uneven spot.

[0106] (2) Light intensity distribution: The light intensity distribution within the light spot should be relatively uniform, that is, the light intensity difference in each area should not be too large. The intensity distribution diagram of the light spot is measured using a beam profiler, and the degree of unevenness of the light spot is quantified by calculating the uniformity indicators of the light intensity distribution, such as the standard deviation and the coefficient of variation. The calculation formulas for the standard deviation and the coefficient of variation are the prior art content in this field and are not the inventive solution of the present application, and are not elaborated here.

[0107] (3) M² factor: The M² factor reflects the difference between the divergence angle of the light beam and the ideal light beam. The larger the M² value, the worse the beam quality and the more uneven the light spot. Generally speaking, an M² value close to 1 indicates a good beam quality and a more uniform light spot. The calculation formula of the M² value is the prior art content in this field and is not an inventive solution of the present application, so it will not be elaborated here.

[0108] The assessment of energy loss includes the following aspects:

[0109] (1) Transmission loss: The transmission loss of ordinary optical fiber is usually between 0.2 and 0.3 dB / km, while the transmission loss of low-loss optical fiber can be reduced to below 0.1 dB / km. If the actual measured transmission loss is much higher than 0.1 dB / km, it means that the energy loss is large;

[0110] (2) Additional loss: If the optical fiber has obvious bends, structural unevenness or material defects, the additional loss will increase significantly, resulting in large energy loss.

[0111] S1.6: Setting the optimization strategy convergence threshold ;

[0112] like , then return to step S1.5 to continue optimization;

[0113] like , then the optimal optical fiber arrangement solution is obtained;

[0114] S1.7: Use CAD software to draw the optimal fiber layout diagram, mark the parameters, and write technical documents. The marked parameters include fiber type, length, path direction, and connector location. The technical documents include design principles, simulation results, optimization process, and submit the final fiber layout diagram.

[0115] like Figure 4 As shown, the specific steps of step S2 include:

[0116] S2.1: Integrate the fiber arrangement, transmission environment and far-end angle data, establish a database, and use machine learning algorithms to train the database data, build a prediction model, and combine the reinforcement learning algorithm to dynamically adjust the predicted far-end angle to obtain the optimal far-end angle;

[0117] Furthermore, the specific steps of S2.1 include:

[0118] S2.11: Obtain the fiber arrangement, transmission environment and remote angle data, and integrate these data into a unified database to obtain database data and ensure data integrity and consistency. The fiber arrangement data records the laying path, length, bending radius, and physical parameters of the connection point of the optical fiber. The transmission environment data includes environmental factors that affect the transmission performance of the optical fiber, such as temperature, humidity, air pressure, and electromagnetic interference. The remote angle data records the angle information of the optical fiber end or receiving end, as well as transmission performance data, such as optical power and bit error rate.

[0119] S2.12: Design the database structure, including data tables, fields, and indexes, use SQL database to store data, and clean, convert, and normalize the collected raw data so that data of different dimensions can be compared and calculated in the same model;

[0120] S2.13: Select a neural network prediction model, use database data to train the neural network prediction model, and optimize the prediction performance by adjusting the parameters of the neural network prediction model;

[0121] S2.14: Based on the prediction of the far-end angle by the neural network prediction model, a reinforcement learning algorithm is introduced to dynamically adjust the prediction results, including setting a reward function to give positive or negative rewards according to the improvement or decline of transmission performance, so as to guide the reinforcement learning algorithm to optimize the strategy;

[0122] S2.15: Continuously iterate the optimization strategy through interaction with the environment to obtain the optimal distal angle;

[0123] S2.16: Deploy the trained neural network prediction model and reinforcement learning algorithm to actual application scenarios, monitor transmission performance data in real time, and fine-tune or retrain model parameters as needed;

[0124] S2.17: Collect user feedback and new transmission environment data to continuously optimize the performance and adaptability of the neural network prediction model.

[0125] S2.2: Use physical optics software to establish a fiber transmission simulation model, use artificial intelligence-driven simulation methods to evaluate the effects of different light source parameters, fiber materials and coatings on brightness, and use a multi-objective optimization algorithm to find the optimal solution set in the simulation environment and develop a brightness improvement plan. The formula of the multi-objective optimization algorithm is:

[0126] ;

[0127] in, Representation strategy Performance function About parameters The gradient of represents strategy, which refers to the combination of light source parameters, optical fiber materials and coating parameters. N represents the number of simulation experiments. represents the number of time steps of the ith simulation experiment, K represents the total number of parameters, express The gradient weight of represents the action taken by simulation experiment i at time step t, represents the state of simulation experiment i at time step t, Represents external environment information, represents the jth parameter, Indicates in status and external environmental information Next select action The logarithmic probability of The gradient of represents the total brightness of the entire experimental trajectory, represents the state of optical signal transmission in the optical fiber and the corresponding action in the i-th simulation experiment, represents the discount factor, represents the weight adjustment coefficient, It means that the simulation experiment i has a time step of The instant brightness increment on represents the weight coefficient of the baseline term, Indicates in status Expected brightness under

[0128] Among them, the process of establishing a fiber optic transmission simulation model using physical optics software and the artificial intelligence-driven simulation method are both prior art contents in this field, and are not the creative solutions of this application, and will not be elaborated here.

[0129] It should be noted that the present invention is modified on the basis of the prior art, by using different weights To balance the importance of multiple objectives, a comprehensive optimal solution can be found in terms of brightness improvement, cost reduction, and energy consumption reduction; through the policy gradient method, the policy parameters can be automatically adjusted To adapt to different fiber configurations and environmental conditions, it can automatically find the optimal solution even in a changing environment; it also takes into account future rewards and uses discount factors and weight To evaluate long-term benefits, avoid short-sighted decisions, and ensure optimal long-term performance; The term considers the state value function, which helps to evaluate the expected performance under different states. The value of can balance the trade-off between immediate reward and expected future performance; at the same time, it allows multiple simulation instances to be processed in parallel, speeds up calculations, reduces the time required for the optimization process, and improves the robustness of the method.

[0130] S2.3: Integrate the laser interferometer and the robotic arm, write the control script, guide the robotic arm to automatically install the fiber array according to the optimal fiber arrangement plan, and automatically call the brightness and angle adjustment mechanism for preliminary calibration. At the same time, use a high-resolution camera to visually inspect the installation results;

[0131] Furthermore, the specific steps of S2.3 include:

[0132] S2.31: Determine the optimal fiber layout, including the position, angle and spacing of the fibers, calibrate the laser interferometer and the robotic arm, and write the control script, including the motion control of the robotic arm, the data reading and processing of the laser interferometer, and the calling of the brightness and angle adjustment mechanism;

[0133] S2.32: The robot moves from the preset starting position to the fiber grabbing point according to the optimal fiber arrangement plan, grabs the fiber using the end effector of the robot, and moves the fiber to the specified installation position. During the movement, the laser interferometer measures the position and angle of the fiber in real time to ensure that it is consistent with the preset value.

[0134] S2.33: The robot arm places the optical fiber accurately at the installation position and releases the optical fiber;

[0135] S2.34: Automatically call the brightness and angle adjustment mechanism to adjust the brightness and angle of the optical fiber according to the preset parameters;

[0136] S2.35: Use a high-resolution camera to take pictures of the installed optical fiber array and use image processing technology to check whether the position, angle, and spacing of the optical fibers meet the requirements. If any problems are found, reinstall or adjust them.

[0137] S2.4: The test data of the angle and brightness of the optical fiber far end are collected in real time by using the Internet of Things method, and preprocessed and feature extracted. The feature extraction in the present invention adopts a contour extraction algorithm, and the calculation process of the contour extraction algorithm is the prior art content in this field, which is not the inventive solution of the present application and will not be described in detail here;

[0138] S2.5: Use a deep learning algorithm to build an analysis model, input the feature-extracted data into the analysis model, and obtain the best parameter combination, wherein the process of using a deep learning algorithm to build a model is the prior art content in this field, and is not an inventive solution of this application, and is not described in detail here;

[0139] S2.6: Based on the optimal parameter combination, an optimized far-end angle and brightness configuration scheme is generated, and an intelligent recommendation method is used to recommend the optimal parameter combination according to historical data, and the optimization scheme is automatically pushed to the control system through an automated script to guide the actual adjustment of the optical fiber array. The calculation process of the intelligent recommendation method is the prior art content in this field, and is not an inventive solution of the present application, and will not be described in detail here;

[0140] S2.7: Continuously monitor the operating status of the system, collect feedback data, regularly update the analysis model and optimization plan, and use active learning technology to selectively update the analysis model based on feedback data.

[0141] The specific steps of step S4 include:

[0142] S4.1: Obtain the optical fiber parameter data in step S3, perform automatic anomaly detection, extract optical fiber performance characteristics from the optical fiber parameter data after anomaly detection, and obtain optical fiber performance characteristic data;

[0143] S4.2: Load the deep learning model, use the optical fiber performance characteristic data to train and optimize the deep learning model, and integrate the trained deep learning model with the system module to generate an intelligent evaluation model, wherein the training and optimization process of the deep learning model is the prior art content in this field, and is not the inventive solution of this application, and will not be described in detail here;

[0144] S4.3: Input the real-time measured fiber parameter data into the intelligent evaluation model to generate the evaluation result X, and compare the evaluation result with the preset fiber performance standard For comparative analysis, if , the early warning mechanism is automatically triggered and early warning information is sent;

[0145] S4.4: Use the evaluation results and warning information as feedback to guide fiber maintenance, upgrades, or retrain models to form a closed-loop optimization system.

[0146] For example, assuming that a cold light source device is connected to an optical fiber, and local lighting is performed at the other end of the optical fiber during surgery, the arrangement and performance of the optical fiber directly affect the lighting effect and the smooth progress of the surgery. The use of this technical solution can ensure that the optical fiber array provides stable and uniform lighting during surgery, thereby improving the accuracy and safety of the surgery. Specifically, it can be summarized as follows: During the operation, the brightness and angle of the optical fiber array are monitored in real time to ensure that it operates in the best state. Through the Internet of Things technology, the real-time data of the optical fiber array is transmitted to the control center for real-time analysis and adjustment; if the brightness or angle of the optical fiber array is found to be deviant during the operation, the system will automatically start the adjustment mechanism , by fine-tuning the position and angle of the optical fiber, the optimal lighting state is quickly restored to ensure the smooth progress of the operation; after the operation, the operating data of the optical fiber array is automatically recorded, including parameters such as brightness, angle, and temperature; through the long-term accumulated surgical data, combined with deep learning technology, the performance of the optical fiber array is deeply analyzed to find potential problems and room for improvement, so as to continuously optimize the design and control strategy of the optical fiber array and improve the overall level of surgical lighting; in summary, this technical solution can realize the efficient, stable and intelligent application of optical fiber arrays in surgical lighting by integrating advanced physical optics simulation, artificial intelligence simulation, Internet of Things technology, deep learning algorithm and automated control technology.

[0147] For example, assuming that long-distance optical transmission is carried out underground by using optical fibers, in the underground environment, the arrangement and performance of the optical fiber array directly affect the stability and speed of data transmission. By simulating the optical fiber arrangement schemes and remote optimization schemes under different underground environments, the performance of the optical fiber array can be predicted and optimized in advance, reducing the risks and losses in actual operations, and improving the application effect of the optical fiber array in underground communications.

[0148] Example 3

[0149] See also Figure 6 Another embodiment provided by the present invention is a fiber parameter measurement system based on holmium laser fiber, comprising:

[0150] Optical fiber arrangement optimization module, remote parameter optimization module, multi-parameter measurement module, intelligent evaluation module, optimization module;

[0151] The fiber layout optimization module is responsible for designing and optimizing the fiber layout plan to ensure the efficiency and performance of the fiber array;

[0152] The remote parameter optimization module further adjusts the angle and brightness of the remote end of the optical fiber based on the optimal optical fiber arrangement solution to improve the overall performance;

[0153] Multi-parameter measurement module, used to perform multi-parameter measurement on optical fiber and collect optical fiber parameter data under the optimal optical fiber arrangement scheme and remote optimization scheme;

[0154] Intelligent evaluation module, which uses deep learning models to intelligently evaluate fiber parameter data and compares and analyzes it with preset standards to determine whether the fiber performance meets the standards;

[0155] The optimization module is used to identify and optimize fiber performance indicators that do not meet the standards based on the comparative analysis results, and provide feedback to continuously improve the system.

[0156] The optical fiber arrangement optimization module includes: preliminary scheme design unit, simulation and optimization unit;

[0157] The preliminary scheme design unit is responsible for proposing a preliminary optical fiber arrangement scheme;

[0158] The simulation and optimization unit is used to perform multi-dimensional simulation on the preliminary plan, adjust and optimize the plan according to the simulation results, obtain the optimal arrangement plan, and draw the optical fiber arrangement diagram.

[0159] The remote parameter optimization module includes: an angle adjustment mechanism unit, a scheme design unit, and a parameter determination unit;

[0160] An angle adjustment mechanism unit, used to design and set the angle adjustment mechanism of the optical fiber far end;

[0161] The scheme design unit is used to formulate a brightness improvement scheme and find the optimal parameter settings through experimental verification;

[0162] The parameter determination unit is used to perform experiments, verify the effects of angle and brightness adjustment, determine the best parameters, and generate a remote optimization solution.

[0163] The multi-parameter measurement module includes: measurement scheme design unit and data acquisition unit;

[0164] Measurement scheme design unit, used to develop detailed multi-parameter measurement schemes;

[0165] The data acquisition unit is used to perform measurement and collect various parameter data of the optical fiber according to the measurement plan.

[0166] The intelligent evaluation module includes: model building unit, data evaluation unit, and comparative analysis unit;

[0167] A model building unit, used to build an intelligent evaluation model based on deep learning;

[0168] A data evaluation unit, used for evaluating optical fiber parameter data according to an intelligent evaluation model;

[0169] The comparison and analysis unit is used to compare and analyze the evaluation results with the preset standards to judge the performance of the optical fiber.

[0170] The embodiments of the present invention are described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific implementation modes, which are merely illustrative rather than restrictive. Under the guidance of the present invention, ordinary technicians in the field may also change, modify, replace and modify the above-mentioned embodiments without departing from the purpose and scope of protection of the present invention, and all of these are within the protection of the present invention.

Claims

1. A method for measuring optical fiber parameters based on holmium laser optical fiber, characterized in that: include: Step S1: setting a preliminary optical fiber arrangement plan, and performing a multi-dimensional simulation on the preliminary optical fiber arrangement plan, adjusting and optimizing the preliminary optical fiber arrangement plan according to the simulation results, obtaining an optimal optical fiber arrangement plan, and drawing an optical fiber arrangement diagram; Step S2: Based on the optimal fiber arrangement plan, set the fiber remote angle adjustment mechanism and formulate a brightness improvement plan, verify the effects of angle and brightness adjustment through experiments, obtain the optimal parameter settings of fiber remote angle and brightness, and generate a remote optimization plan; Step S3: Formulate a multi-parameter measurement plan, perform multi-parameter measurement on the optical fiber under the optimal optical fiber arrangement plan and the remote optimization plan, and record the optical fiber parameter data; Step S4: Establish an intelligent evaluation model based on deep learning, use the intelligent evaluation model to evaluate the measured optical fiber parameter data, and compare and analyze the evaluation results with the preset standards to determine whether the optical fiber performance meets the standards; Step S5: Based on the comparative analysis results, identify the optical fiber performance indicators that do not meet the standards, and formulate and implement an overall optimization plan for the optical fiber performance indicators that do not meet the standards.

2. The method for measuring optical fiber parameters based on holmium laser optical fiber according to claim 1, characterized in that: The specific steps of step S1 include: S1.1: Design a preliminary fiber layout plan based on demand and environmental data, and draw a preliminary fiber layout diagram; S1.2: Use optical simulation software to establish a simulation model of the optical fiber array, and perform multi-dimensional simulation of the preliminary optical fiber arrangement scheme based on the transmission characteristics of light in the optical fiber; S1.3: Based on the simulation results, calculate the light transmission characteristics in the optical fiber. The formula is: ； in, It indicates the power at a distance d from the light source when the fiber temperature is T. d indicates the distance from the fiber input end to the measurement point. T indicates the current fiber temperature. represents the initial power, is the absorption attenuation coefficient, represents the scattering attenuation coefficient, is the coupling attenuation coefficient, represents the temperature influence coefficient, Indicates the rated operating temperature of the optical fiber. Represents an exponential function.

3. A method for measuring optical fiber parameters based on holmium laser optical fiber as claimed in claim 2, characterized in that: The specific steps of step S1 also include: S1.4: Based on the calculated optical transmission characteristics, identify performance bottlenecks, use optimization strategies to adjust and optimize the initial fiber layout plan based on the identified problems, and re-perform multi-dimensional simulation to obtain optimized optical transmission characteristics ; S1.5: Setting the optimization strategy convergence threshold ; like , then return to step S1.4 to continue optimization; like , then the optimal optical fiber arrangement solution is obtained; S1.6: Use CAD software to draw the optimal fiber layout diagram and mark the parameters.

4. The method for measuring optical fiber parameters based on holmium laser optical fiber according to claim 3, characterized in that: The specific steps of step S2 include: S2.1: Integrate the fiber arrangement, transmission environment and far-end angle data, establish a database, and use machine learning algorithms to train the database data, build a prediction model, and combine the reinforcement learning algorithm to dynamically adjust the predicted far-end angle to obtain the optimal far-end angle; S2.2: Use physical optics software to establish a fiber transmission simulation model, use artificial intelligence-driven simulation methods to evaluate the effects of different light source parameters, fiber materials and coatings on brightness, and use a multi-objective optimization algorithm to find the optimal solution set in the simulation environment and develop a brightness improvement plan. The formula of the multi-objective optimization algorithm is: ； in, Representation strategy Performance function About parameters The gradient of represents strategy, which refers to the combination of light source parameters, optical fiber materials and coating parameters. N represents the number of simulation experiments. represents the number of time steps of the ith simulation experiment, K represents the total number of parameters, express The gradient weight of represents the action taken by simulation experiment i at time step t, represents the state of simulation experiment i at time step t, Represents external environment information, represents the jth parameter, Indicates in status and external environmental information Next select action The logarithmic probability of The gradient of represents the total brightness of the entire experimental trajectory, represents the state of optical signal transmission in the optical fiber and the corresponding action in the i-th simulation experiment, represents the discount factor, represents the weight adjustment coefficient, It means that the simulation experiment i has a time step of The instant brightness increment on represents the weight coefficient of the baseline term, Indicates in status Expected brightness under .

5. The method for measuring optical fiber parameters based on holmium laser optical fiber according to claim 4, characterized in that: The specific steps of step S2 also include: S2.3: Integrate the laser interferometer and the robotic arm, write the control script, guide the robotic arm to automatically install the fiber array according to the optimal fiber arrangement plan, and automatically call the brightness and angle adjustment mechanism for preliminary calibration. At the same time, use a high-resolution camera to visually inspect the installation results; S2.4: Use the Internet of Things method to collect the test data of the optical fiber far end angle and brightness in real time, and perform preprocessing and feature extraction; S2.5: Use deep learning algorithms to build an analysis model, input the feature-extracted data into the analysis model, and obtain the optimal parameter combination; S2.6: Generate an optimized far-end angle and brightness configuration scheme based on the best parameter combination, use an intelligent recommendation method to recommend the best parameter combination based on historical data, and automatically push the optimization scheme to the control system through an automated script to guide the actual adjustment of the fiber array; S2.7: Continuously monitor the operating status of the system, collect feedback data, regularly update the analysis model and optimization plan, and use active learning technology to selectively update the analysis model based on feedback data; The specific steps of S2.3 include: S2.31: Determine the optimal fiber layout, including the position, angle and spacing of the fibers, calibrate the laser interferometer and the robotic arm, and write the control script, including the motion control of the robotic arm, the data reading and processing of the laser interferometer, and the calling of the brightness and angle adjustment mechanism; S2.32: The robot arm moves from a preset starting position to a fiber grabbing point according to the optimal fiber arrangement plan, grabs the fiber using the end effector of the robot arm, and moves the fiber to a designated installation position; S2.33: The robot arm places the optical fiber accurately at the installation position and releases the optical fiber; S2.34: Automatically call the brightness and angle adjustment mechanism to adjust the brightness and angle of the optical fiber according to the parameters in the optimal optical fiber arrangement plan; S2.35: Use a high-resolution camera to take pictures of the installed optical fiber array and use image processing technology to check whether the position, angle, and spacing of the optical fibers meet the requirements. If any problems are found, reinstall or adjust them.

6. A method for measuring optical fiber parameters based on holmium laser optical fiber as claimed in claim 5, characterized in that: The specific steps of step S4 include: S4.1: Obtain the optical fiber parameter data in step S3, perform automatic anomaly detection, extract optical fiber performance characteristics from the optical fiber parameter data after anomaly detection, and obtain optical fiber performance characteristic data; S4.2: Load the deep learning model, use the fiber performance characteristic data to train and optimize the deep learning model, and integrate the trained deep learning model with the system module to generate an intelligent evaluation model; S4.3: Input the real-time measured fiber parameter data into the intelligent evaluation model to generate the evaluation result X, and compare the evaluation result with the preset fiber performance standard For comparative analysis, if , the early warning mechanism is automatically triggered and early warning information is sent; S4.4: Use the evaluation results and warning information as feedback to guide fiber maintenance, upgrades, or retrain models to form a closed-loop optimization system.

7. The method for measuring optical fiber parameters based on holmium laser optical fiber according to claim 6, characterized in that: The multi-dimensional simulation in step S1 includes simulating the light emission angle, light spot uniformity, and energy distribution; the optical fiber arrangement scheme includes the setting of the number, spacing, heat distribution, angle, and intersection between optical fibers.

8. The method for measuring optical fiber parameters based on holmium laser optical fiber according to claim 7, characterized in that: The optimization strategy in S1.4 includes adjusting the spacing between optical fibers, changing the arrangement angle of the optical fibers, and optimizing the angle and brightness setting of the far end of the optical fibers.

9. An optical fiber parameter measurement system based on holmium laser fiber, which is used to implement an optical fiber parameter measurement method based on holmium laser fiber as claimed in any one of claims 1 to 8, characterized in that: include: Optical fiber arrangement optimization module, remote parameter optimization module, multi-parameter measurement module, intelligent evaluation module, optimization module; The optical fiber arrangement optimization module is responsible for designing and optimizing the optical fiber arrangement scheme; The remote parameter optimization module further adjusts the angle and brightness of the remote end of the optical fiber based on the optimal optical fiber arrangement solution; The multi-parameter measurement module is used to perform multi-parameter measurement on the optical fiber and collect optical fiber parameter data under the optimal optical fiber arrangement scheme and the remote optimization scheme; The intelligent evaluation module is used to use a deep learning model to intelligently evaluate the optical fiber parameter data, and compare and analyze it with the preset standard to determine whether the optical fiber performance meets the standard; The optimization module is used to identify and optimize the optical fiber performance indicators that do not meet the standards based on the comparative analysis results.

Images