Optical fiber sensor optimization method, device, equipment and medium

Abstract

The invention relates to an optical fiber sensor optimization method and device, equipment and a medium thereof. The method comprises the following steps: acquiring an original optical signal of an optical fiber sensor, extracting target characteristic wavelength data through spectral analysis, and filtering temperature-induced material aging noise to obtain an optical characteristic deviation index; taking the index as input, quantizing signal attenuation through an adaptive calibration algorithm, and establishing an adaptive mapping relation in combination with real-time environmental parameters to determine signal calibration parameters; the calibration parameters and the sensor space layout data are fused, a signal distortion key area is analyzed, a coverage deviation value is calculated, and an optimized layout scheme is generated after the coverage deviation value reaches the standard; and extracting layout key features to construct a correlation model to determine a dynamic compensation mechanism, and generating a comprehensive performance evaluation report if a trigger condition reaches the standard. The method can improve the monitoring precision, the operation stability and the working condition adaptation capability of the optical fiber sensor.

Description

Technical Field

[0001] This invention belongs to the field of sensing and monitoring technology, and in particular relates to methods, devices, equipment and media for optimizing fiber optic sensors. Background Technology

[0002] With the deep application of fiber optic sensing technology in key areas such as industrial measurement and control, infrastructure monitoring, and environmental sensing, its monitoring accuracy, stability, and adaptability have become core bottlenecks restricting system performance upgrades. Existing fiber optic sensors are susceptible to temperature-induced material aging and multi-source environmental interference in complex service environments, leading to noise superposition and increased characteristic deviations in the original optical signal, resulting in signal attenuation and distortion. Simultaneously, traditional sensor layout designs rely heavily on empirical configuration, lacking linkage optimization with signal calibration parameters. This makes it difficult to accurately cover critical areas of signal distortion, and the lack of dynamic compensation mechanisms based on operating conditions prevents monitoring protocol parameters from adaptively adjusting as needed. Ultimately, this results in insufficient overall sensor network performance and limited long-term operational reliability. Summary of the Invention

[0003] Therefore, it is necessary to provide an optimization method, device, equipment, and medium for fiber optic sensors that can improve the monitoring accuracy, operational stability, and adaptability to operating conditions of fiber optic sensors, addressing the aforementioned technical problems.

[0004] In a first aspect, this application provides a method for optimizing fiber optic sensors, including:

[0005] The original optical signal of the fiber optic sensor is acquired, and characteristic wavelength data is extracted from the original optical signal using spectral analysis and temperature-induced material aging signal noise is filtered out to obtain the optical characteristic deviation index.

[0006] Based on the optical characteristic deviation index, the signal attenuation degree is quantified by an adaptive calibration algorithm and a matching mapping relationship is established with environmental parameters to determine the signal calibration parameters.

[0007] By combining signal calibration parameters and spatial layout data, the key areas of signal distortion are analyzed, and the signal coverage deviation value of the key areas of signal distortion is calculated. If the signal coverage deviation value meets the preset threshold, a sensor spatial layout scheme is generated.

[0008] Key feature parameters are extracted from the sensor spatial layout scheme to construct an association model and determine the dynamic compensation mechanism. If the dynamic compensation mechanism meets the preset trigger threshold, a comprehensive performance evaluation report is generated.

[0009] In one embodiment, the raw optical signal of the fiber optic sensor is acquired, and characteristic wavelength data is extracted from the raw optical signal using spectral analysis and temperature-induced material aging signal noise is filtered out to obtain optical characteristic deviation indicators, including:

[0010] Acquire the raw optical signal generated by the fiber optic sensor; the raw optical signal contains information on multiple wavelengths.

[0011] Based on the original optical signal, spectral analysis is performed to extract characteristic wavelength data and obtain a preliminary wavelength feature set.

[0012] A filtering algorithm was used to remove temperature-induced material aging-related signal noise from the wavelength feature set, and preliminary optical property deviation indices were calculated.

[0013] If the initial optical characteristic deviation index exceeds the preset threshold range, a second feature extraction of wavelength offset data is performed on the filtered wavelength feature set. Based on the wavelength offset data, a deviation correction model is constructed, and the final optical characteristic deviation index is output.

[0014] In one embodiment, the optical characteristic deviation index is calculated using the following formula:

[0015]

[0016] in, Indicators representing deviations in optical properties. Indicates the number of characteristic wavelengths. Indicates the first Measured values ​​of each characteristic wavelength Indicates the first Standard reference values ​​for each characteristic wavelength, This indicates the number of frequency segments in the filtering algorithm. Indicates the first Signal strength after noise filtering in each frequency band Indicates the first The original signal strength before noise filtering in each frequency band.

[0017] In one embodiment, signal calibration parameters are determined by quantifying the signal attenuation level based on optical characteristic deviation indicators using an adaptive calibration algorithm and establishing an adaptive mapping relationship with environmental parameters, including:

[0018] Based on the optical characteristic deviation index, an adaptive calibration algorithm is used to calculate the signal amplitude attenuation rate and phase offset, and the signal attenuation quantization value is obtained by coupling.

[0019] By combining the signal attenuation quantization value with the real-time acquired environmental parameters, an adaptation mapping relationship is established, the calibration factor is dynamically adjusted, and the signal attenuation compensation coefficient is determined.

[0020] The signal attenuation compensation coefficient is input into the preset signal processing model, and the signal calibration parameters are generated by iterative optimization based on the preset calibration error convergence condition; the signal processing model is jointly constructed by the adaptive filtering algorithm and the linear regression mapping algorithm.

[0021] In one embodiment, by combining signal calibration parameters and spatial layout data to analyze key areas of signal distortion, the signal coverage deviation value of the key areas of signal distortion is calculated. If the signal coverage deviation value meets a preset threshold, a sensor spatial layout scheme is generated, including:

[0022] A multi-source data fusion algorithm is used to correlate and fuse signal calibration parameters and current spatial layout data of sensors. By optimizing the coordinate mapping and coverage area, the sensor position distribution is remapped to obtain preliminary optimized sensor position distribution data.

[0023] Based on the sensor location distribution data, a preset historical signal distortion pattern database is called to analyze the distortion patterns during signal transmission and identify key areas of signal distortion where signal attenuation exceeds the limit and data transmission is unstable. The key areas of signal distortion include the area boundary coordinates and the quantification value of the distortion degree.

[0024] Based on the key areas of signal distortion, combined with the sensor's maximum coverage radius and installation constraints, a sensor spatial adjustment objective function is constructed.

[0025] The objective function is solved using the gradient descent algorithm to generate the sensor space adjustment matrix, resulting in the adjusted sensor layout scheme. The sensor space adjustment matrix includes the sensor translation distance and angle adjustment parameters.

[0026] Calculate the signal coverage deviation value of each monitoring point in the sensor layout scheme, and judge the signal coverage deviation value based on the preset threshold.

[0027] If the signal coverage deviation is lower than the preset threshold, the adjusted sensor layout scheme will be output as the final optimized sensor space layout scheme.

[0028] If the signal coverage deviation value is higher than the preset threshold, the weight coefficient of the sensor spatial adjustment objective function is corrected based on the spatial distribution characteristics of the current signal coverage deviation value, and a new sensor spatial layout scheme is recalculated until the preset threshold is met.

[0029] In one embodiment, the sensor space adjustment objective function is expressed using the following formula:

[0030]

[0031] in, Represents the objective function value. , Indicates the number of critical regions of signal distortion. Indicates the first Quantitative values ​​of the degree of distortion in key distortion regions. Indicates the first Signal coverage deviation values ​​in key distortion areas Indicates the standard threshold for signal coverage deviation. Indicates the total number of sensors. Indicates the first The actual coverage radius after adjustment of each sensor Indicates the sensor's maximum rated coverage radius. Indicates the first The and the first The center spacing of each sensor has been adjusted. Indicates the minimum value. , , This represents the weighting coefficient.

[0032] In one embodiment, key feature parameters are extracted from the sensor spatial layout scheme to construct an association model and determine a dynamic compensation mechanism. If the dynamic compensation mechanism meets a preset trigger threshold, a comprehensive performance evaluation report is generated, including:

[0033] Obtain the initial configuration data for the sensor spatial layout scheme; the initial configuration data includes the spatial distribution parameters of each sensor and the monitoring range information of each sensor.

[0034] Based on spatial distribution parameters, a finite element stress simulation algorithm is used to construct a stress distribution simulation matrix for the sensor installation area. Preliminary stress distribution results are obtained through numerical iteration calculations. The stress distribution results include the boundary coordinates of high stress regions and uniform stress regions, as well as the corresponding stress quantization values.

[0035] Key characteristic parameters extracted from stress distribution results are cross-referenced with monitoring range information to construct a correlation model and determine the dynamic compensation mechanism.

[0036] If the quantitative indicators of the triggering conditions of the dynamic compensation mechanism meet the preset threshold, the updated monitoring protocol parameters are dynamically adjusted according to the adaptation mapping relationship between key feature parameters and sampling frequency. The monitoring protocol parameters include the adjusted sampling frequency, data caching strategy, and transmission priority configuration.

[0037] Multi-source data from fiber optic sensor networks are collected, and an adaptation performance evaluation index system is constructed using the analytic hierarchy process (AHP) in conjunction with monitoring protocol parameters. A comprehensive performance evaluation report is generated through weighted calculations. The comprehensive performance evaluation report includes quantitative scores for each index, overall adaptation level, and optimization suggestions.

[0038] Secondly, this application also provides a fiber optic sensor optimization device, the device comprising:

[0039] The characteristic deviation extraction module is used to acquire the original optical signal of the fiber optic sensor, extract characteristic wavelength data from the original optical signal using spectral analysis, and filter out temperature-induced material aging signal noise to obtain the optical characteristic deviation index.

[0040] The signal calibration parameter module is used to quantify the signal attenuation level based on optical characteristic deviation index through an adaptive calibration algorithm and establish an adaptive mapping relationship with environmental parameters to determine the signal calibration parameters.

[0041] The sensor layout generation module is used to analyze the key areas of signal distortion by combining signal calibration parameters and spatial layout data, calculate the signal coverage deviation value of the key areas of signal distortion, and generate a sensor spatial layout scheme if the signal coverage deviation value meets the preset threshold.

[0042] The comprehensive performance evaluation module is used to extract key feature parameters from the sensor spatial layout scheme, build an association model, and determine the dynamic compensation mechanism. If the dynamic compensation mechanism meets the preset trigger threshold, a comprehensive performance evaluation report is generated.

[0043] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the method described above.

[0044] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the aforementioned method.

[0045] The aforementioned fiber optic sensor optimization method, apparatus, computer equipment, and storage medium first acquire the raw optical signal collected by the fiber optic sensor. Then, using spectral analysis, characteristic wavelength data related to the monitoring target is extracted from the raw optical signal. Simultaneously, temperature-induced material aging signal noise is selectively filtered out. Based on the processed characteristic wavelength data, an optical characteristic deviation index is calculated. Using this optical characteristic deviation index as input, an adaptive calibration algorithm quantifies the signal attenuation level. Real-time environmental parameters are simultaneously introduced to establish a dynamic adaptation mapping relationship. The calibration factor is adjusted through this mapping relationship to ultimately determine the signal calibration parameters. The signal calibration parameters are then correlated and fused with the sensor's current spatial layout data. Based on the fused data, key distortion areas in the signal transmission process are analyzed, and the signal coverage deviation value for these areas is calculated. If the deviation value is lower than a preset threshold, an optimized sensor spatial layout scheme is generated. Key characteristic parameters are extracted from the generated sensor spatial layout scheme, and a correlation model between the characteristic parameters and monitoring requirements is constructed. A dynamic compensation mechanism is determined through this model. If the triggering condition quantification index of this dynamic compensation mechanism meets a preset threshold, a comprehensive performance evaluation report containing performance quantification data and optimization suggestions is generated. This method effectively improves the purity of optical signals and the accuracy of optical characteristic deviation indicators by specifically filtering out temperature-induced material aging noise. Based on the adaptation mapping relationship between deviation indicators and environmental parameters, the signal calibration parameters are made more consistent with actual working conditions, reducing the impact of environmental interference on signal quality. By combining calibration parameters to optimize the sensor spatial layout, key areas of signal distortion can be accurately avoided, improving the effectiveness and rationality of monitoring coverage. Through dynamic compensation mechanisms and comprehensive performance evaluation, dynamic adaptation of sensor operating status and quantitative feedback of performance are achieved, providing data support for subsequent operation and maintenance and optimization, and improving the overall monitoring accuracy, operational stability and adaptability of fiber optic sensors. Attached Figure Description

[0046] To more clearly illustrate the technical solutions in the embodiments or related technologies of this application, the accompanying drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0047] Figure 1 A flowchart of the fiber optic sensor optimization method provided in an embodiment of the present invention;

[0048] Figure 2 This is a structural block diagram of the fiber optic sensor optimization device provided in an embodiment of the present invention. Detailed Implementation

[0049] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0050] In one embodiment, such as Figure 1 As shown, this application provides a fiber optic sensor optimization method, which may include the following steps:

[0051] Step S101: Obtain the original optical signal of the fiber optic sensor, extract characteristic wavelength data from the original optical signal using spectral analysis, and filter out temperature-induced material aging signal noise to obtain optical characteristic deviation index.

[0052] Specifically, the process begins by acquiring raw optical signals generated when monitoring target objects (such as industrial equipment, infrastructure, and environmental media) using fiber optic sensors. These signals contain light intensity information across multiple wavelengths and are contaminated with temperature-induced material aging-related noise. Subsequently, spectral analysis is performed on the raw optical signals to identify characteristic wavelengths strongly correlated with the monitored target parameters (such as strain, concentration, and temperature), forming a wavelength feature set. A wavelet filtering algorithm is then used to suppress noise in this wavelength feature set, specifically removing temperature-induced material aging signal noise. Based on the filtered characteristic wavelength data, the relative deviation between the measured values ​​and standard reference values ​​for each characteristic wavelength is calculated. This deviation is then calculated by coupling a weighted average with a noise suppression effect quantification factor to obtain an optical characteristic deviation index that reflects the optical performance of the fiber optic sensor deviating from the standard state.

[0053] Step S102: Based on the optical characteristic deviation index, the signal attenuation degree is quantified by an adaptive calibration algorithm and an adaptive mapping relationship is established with the environmental parameters to determine the signal calibration parameters.

[0054] Furthermore, an adaptive Kalman filter calibration algorithm is employed based on optical characteristic deviation indices. By adjusting the filter gain coefficient in real time, the amplitude attenuation rate and phase shift during signal transmission are calculated separately. These two parameters are then fused using a nonlinear coupling model to obtain the quantized signal attenuation value. Simultaneously, key environmental parameters such as temperature and humidity are collected and monitored in real time to establish a dynamic adaptation mapping relationship between the quantized signal attenuation value and environmental parameters. This mapping relationship uses environmental parameters as independent variables and the signal attenuation correction coefficient as the dependent variable, and the mapping function is determined through statistical regression analysis. Based on this mapping relationship, the weight allocation of calibration factors is dynamically adjusted. The adjusted calibration factors are then combined with the quantized signal attenuation value to calculate signal calibration parameters that can compensate for environmental interference and signal attenuation.

[0055] Step S103: Combine signal calibration parameters and spatial layout data to analyze the key areas of signal distortion, calculate the signal coverage deviation value of the key areas of signal distortion, and generate a sensor spatial layout scheme if the signal coverage deviation value meets the preset threshold.

[0056] Specifically, the current spatial layout data of the sensors is first acquired, including the three-dimensional installation coordinates, spacing, installation tilt angle, and rated coverage radius of each sensor. A multi-source data fusion algorithm is then used to correlate and fuse this spatial layout data with the determined signal calibration parameters to obtain a fused dataset. Based on this fused dataset, a preset historical signal distortion pattern database is accessed. A pattern matching algorithm is used to analyze the signal transmission path and distortion patterns under the current layout, identifying key signal distortion areas where signal attenuation exceeds the standard and data transmission is unstable. These areas include boundary coordinates and quantified distortion levels. A signal propagation path loss model is used to calculate the signal coverage deviation value (defined as the absolute value of the difference between the actual signal strength and the standard signal strength at the monitoring point) for each monitoring point within this key area. This deviation value is compared with a preset threshold. If the deviation value is lower than the preset threshold, an optimized sensor spatial layout scheme is generated based on the current layout adjustment logic. If the deviation value does not meet the preset threshold, the data is re-fused and the layout parameters are adjusted until the deviation value meets the standard.

[0057] Step S104: Extract key feature parameters from the sensor spatial layout scheme, construct an association model, and determine the dynamic compensation mechanism. If the dynamic compensation mechanism meets the preset trigger threshold, generate a comprehensive performance evaluation report.

[0058] Specifically, key feature parameters are extracted from the generated sensor spatial layout scheme, including sensor spacing, actual coverage radius, peak stress distribution, and monitoring range overlap rate. These key feature parameters are cross-compared with the sensor's monitoring performance requirements (such as sampling accuracy, transmission delay threshold, and energy consumption limitations) to construct a "layout feature-monitoring requirement" correlation model. This model quantifies the compatibility between feature parameters and monitoring performance, thereby determining a dynamic compensation mechanism. This mechanism includes adjustment rules for monitoring protocol parameters (such as adjustment logic for sampling frequency, caching strategy, and transmission priority). A preset trigger threshold for the dynamic compensation mechanism is set (such as quantitative indicators like stress change rate ≥ 0.5 MPa / s and signal transmission delay ≥ 10 ms). If the actual monitored operating parameters meet this trigger threshold, the compensation mechanism is activated to adjust the monitoring protocol parameters. Simultaneously, multi-source operating data of the fiber optic sensor network (such as signal strength, bit error rate, and energy consumption data) are collected. Combined with the adjusted monitoring protocol parameters, a comprehensive performance evaluation report is generated through quantitative calculation, including scores for various performance indicators, overall compatibility level, and targeted optimization suggestions.

[0059] The aforementioned fiber optic sensor optimization method first acquires the original optical signal from the fiber optic sensor. Target characteristic wavelength data is extracted through spectral analysis, and temperature-induced material aging noise is filtered out to obtain an optical characteristic deviation index. Using this index as input, an adaptive calibration algorithm quantifies signal attenuation, and an adaptation mapping relationship is established with real-time environmental parameters to determine signal calibration parameters. The calibration parameters are then fused with sensor spatial layout data to analyze key areas of signal distortion and calculate coverage deviation values. Once the target is met, an optimized layout scheme is generated. Key layout features are extracted to construct a correlation model to determine a dynamic compensation mechanism. When trigger conditions are met, a comprehensive performance evaluation report is generated. This method improves signal purity and the accuracy of deviation indices through targeted noise filtering, and the calibration parameters are aligned with actual operating conditions to reduce environmental interference. Optimized layouts can accurately avoid distortion areas, improving monitoring coverage effectiveness. Dynamic compensation and performance evaluation achieve dynamic adaptation to operating conditions and quantitative feedback, providing data support for operation and maintenance, and overall improving sensor monitoring accuracy, operational stability, and adaptability to operating conditions.

[0060] In one embodiment, acquiring the raw optical signal from the fiber optic sensor, extracting characteristic wavelength data from the raw optical signal using spectral analysis, and filtering out temperature-induced material aging signal noise to obtain an optical characteristic deviation index may include the following steps:

[0061] Step S201: Obtain the raw optical signal generated by the fiber optic sensor; the raw optical signal contains multiple wavelength information.

[0062] Step S202: Perform spectral analysis based on the original optical signal to extract characteristic wavelength data and obtain a preliminary wavelength feature set.

[0063] Step S203: A filtering algorithm is used to remove temperature-induced material aging-related signal noise from the wavelength feature set, and a preliminary optical property deviation index is calculated.

[0064] Step S204: If the preliminary optical characteristic deviation index exceeds the preset threshold range, perform secondary feature extraction on the filtered wavelength feature set to extract wavelength offset data, construct a deviation correction model based on the wavelength offset data, and output the final optical characteristic deviation index.

[0065] Specifically, firstly, the system acquires raw optical signals generated during the monitoring of target objects (such as industrial equipment structures, environmental media, and infrastructure components) using fiber optic sensors. These raw optical signals contain information such as light intensity and phase across multiple wavelengths and carry physical quantity mapping data related to the monitored target. Based on these raw optical signals, spectral analysis is performed using spectral scanning and wavelength filtering algorithms. By identifying the correlation strength between different wavelengths and monitored target parameters (such as strain, concentration, and vibration frequency), several sets of wavelength data with the highest correlation are selected as characteristic wavelength data and integrated to form a preliminary wavelength feature set. For the temperature-induced material aging signal noise mixed in this wavelength feature set, a wavelet filtering algorithm is used for targeted filtering. By setting a filtering threshold for a specific frequency band, noise components related to temperature changes and material aging are separated and eliminated, retaining the effective characteristic wavelength signals. For the noise-filtered characteristic wavelength data, the relative deviation between the measured value and the preset standard reference value of each characteristic wavelength is calculated, and then a preliminary optical characteristic deviation index is obtained by weighted averaging. A threshold range for optical characteristic deviation is preset, which is determined according to the monitoring accuracy requirements of the sensor, hardware performance parameters, and actual application scenario requirements. The preliminary optical characteristic deviation index is compared with this threshold range. If the preliminary optical characteristic deviation index exceeds the threshold range, a secondary feature extraction is performed on the noise-filtered wavelength feature set, focusing on collecting wavelength offset data such as the offset direction and offset amplitude of each characteristic wavelength. A linear regression correction model is constructed based on this wavelength offset data, and the preliminary optical characteristic deviation index is input into the model for correction calculation, outputting the final optical characteristic deviation index. If the preliminary optical characteristic deviation index does not exceed the preset threshold range, the preliminary optical characteristic deviation index is directly used as the final result.

[0066] This embodiment ensures the accuracy and reliability of the optical characteristic deviation index: by clarifying the wavelength selection criteria in spectral analysis, the extracted characteristic wavelength data is highly correlated with the monitoring target, laying a high-quality data foundation for deviation calculation; a targeted wavelet filtering algorithm is used to accurately remove temperature-induced material aging noise, avoiding irrelevant interference from contaminating the characteristic signal and improving signal purity; by setting a threshold range and triggering a secondary correction mechanism, the deviation that may be generated by a single calculation method is effectively corrected, solving the problem of the initial index exceeding the reasonable range and preventing distorted data from flowing into subsequent stages; throughout the process, the input data, processing methods, and output results of each step are clear, the data flow is closed-loop and traceable, and the final output optical characteristic deviation index can truly and accurately reflect the actual optical performance state of the fiber optic sensor, providing accurate and reliable input support for subsequent core stages such as signal calibration parameter determination and sensor spatial layout optimization, ensuring the effectiveness and feasibility of the overall optimization scheme.

[0067] In one embodiment, the optical characteristic deviation index can be calculated using the following formula:

[0068]

[0069] in, Indicators representing deviations in optical properties. Indicates the number of characteristic wavelengths. Indicates the first Measured values ​​of each characteristic wavelength Indicates the first Standard reference values ​​for each characteristic wavelength, This indicates the number of frequency segments in the filtering algorithm. Indicates the first Signal strength after noise filtering in each frequency band Indicates the first The original signal strength before noise filtering in each frequency band.

[0070] The calculation formula in this embodiment couples the average relative deviation of the measured values ​​of multiple characteristic wavelengths from the standard reference values ​​with the quantitative results of the correlation between the signal strength before and after noise filtering in each frequency segment of the filtering algorithm. This fully utilizes the statistical characteristics of multi-characteristic wavelength data, avoiding the randomness of results caused by single-wavelength data, and incorporates the quantitative evaluation of noise suppression effect. This allows the optical characteristic deviation index to not only reflect the degree of wavelength shift but also the purity of the signal after noise filtering. It significantly improves the accuracy and reliability of the index in representing the actual optical performance of the fiber optic sensor. This provides scientific and accurate data support for subsequent core steps such as determining signal calibration parameters and optimizing sensor spatial layout based on this index, effectively ensuring the feasibility and optimization effect of the overall fiber optic sensor optimization scheme.

[0071] In one embodiment, determining signal calibration parameters by quantifying the signal attenuation level based on optical characteristic deviation indicators using an adaptive calibration algorithm and establishing an adaptive mapping relationship with environmental parameters may include the following steps:

[0072] Step S301: Based on the optical characteristic deviation index, an adaptive calibration algorithm is used to calculate the signal amplitude attenuation rate and phase offset, and the signal attenuation quantization value is obtained by coupling.

[0073] Preferably, the obtained optical characteristic deviation index is used as the core input, and an adaptive Kalman filter calibration algorithm is employed to perform signal attenuation analysis. This algorithm iteratively updates the filter gain matrix in real time, and based on the inherent correlation between the optical characteristic deviation index and signal attenuation, calculates the amplitude attenuation rate (defined as the ratio of the actual signal amplitude to the standard signal amplitude) and phase shift (defined as the difference between the actual signal phase and the standard signal phase) during signal transmission. By constructing a nonlinear coupling model, the amplitude attenuation rate and phase shift are fused and calculated according to their respective weights in relation to signal distortion, ultimately obtaining a quantified signal attenuation value that comprehensively and quantitatively reflects the overall signal attenuation level. This quantified value provides core data support for determining subsequent compensation coefficients.

[0074] Step S302: Establish an adaptation mapping relationship by combining the signal attenuation quantization value with the real-time acquired environmental parameters, dynamically adjust the calibration factor, and determine the signal attenuation compensation coefficient.

[0075] Step S303: Input the signal attenuation compensation coefficient into the preset signal processing model, and generate signal calibration parameters by iterative optimization based on the preset calibration error convergence condition; the signal processing model is jointly constructed by the adaptive filtering algorithm and the linear regression mapping algorithm.

[0076] Furthermore, a signal processing model jointly constructed by an adaptive filtering algorithm and a linear regression mapping algorithm is pre-defined. The adaptive filtering algorithm dynamically suppresses residual noise in the real-time signal, while the linear regression mapping algorithm establishes a quantitative correlation between the compensation coefficients and calibration parameters. The determined signal attenuation compensation coefficients are input into this signal processing model, and a pre-defined calibration error convergence condition is set. The calibration parameters in the model are iteratively adjusted with the goal of minimizing the calibration error. After each iteration, the current calibration error is calculated. If the error does not meet the convergence condition, the model parameters are adjusted based on the error feedback, and the iteration continues. If the error meets the convergence condition, the iteration stops, and the final signal calibration parameters are output. These parameters can be directly used for subsequent signal distortion correction and sensor layout optimization.

[0077] Specifically, using optical characteristic deviation as the core input, an adaptive Kalman filter calibration algorithm is employed. By dynamically adjusting the filter gain in real time, the amplitude attenuation rate and phase shift of the signal during transmission are calculated separately. The calculation results of these two parameters are then fused through a nonlinear coupling model to obtain a quantized signal attenuation value that comprehensively reflects the degree of signal attenuation. Simultaneously, key environmental parameters such as temperature and humidity are collected in real time. Based on statistical regression analysis, a dynamic adaptation mapping relationship between the "quantized signal attenuation value and environmental parameters" is established. This mapping relationship uses the change in environmental parameters as the independent variable and the calibration factor adjustment coefficient as the dependent variable. The weight allocation of the calibration factor is dynamically adjusted according to the real-time fluctuations of the environmental parameters to calculate and determine the signal attenuation compensation coefficient. This signal attenuation compensation coefficient is input into a preset signal processing model. This model is jointly constructed by the adaptive filtering algorithm and the linear regression mapping algorithm, possessing the ability to dynamically adapt to signal changes. Subsequently, with the goal of minimizing the calibration error, based on preset calibration error convergence conditions (such as iteration error ≤...),... The model parameters are iteratively optimized until the convergence condition is met, and finally signal calibration parameters that can accurately compensate for signal attenuation and environmental interference are generated.

[0078] This embodiment couples amplitude attenuation rate and phase offset through an adaptive calibration algorithm, enabling the signal attenuation quantization value to more comprehensively reflect the signal distortion state and avoid the limitations of single parameter evaluation. By combining real-time environmental parameters to establish an adaptive mapping relationship, the signal attenuation compensation coefficient can be dynamically adjusted according to the operating conditions, significantly improving the adaptability to environmental interference. Iterative optimization is performed based on the jointly constructed signal processing model and calibration error convergence conditions to ensure that the generated signal calibration parameters have high accuracy and stability, effectively compensating for attenuation and distortion during signal transmission.

[0079] In one embodiment, by combining signal calibration parameters and spatial layout data to analyze key areas of signal distortion, the signal coverage deviation value of the key areas of signal distortion is calculated. If the signal coverage deviation value meets a preset threshold, a sensor spatial layout scheme is generated, which may include the following steps:

[0080] Step S401: A multi-source data fusion algorithm is used to correlate and fuse the signal calibration parameters and the current spatial layout data of the sensors. By optimizing the coordinate mapping and coverage area, the sensor position distribution is remapped to obtain preliminary optimized sensor position distribution data.

[0081] Step S402: Based on the sensor location distribution data, call the preset historical signal distortion pattern database to analyze the distortion pattern in the signal transmission process and determine the key signal distortion areas where the signal attenuation exceeds the standard and the data transmission is unstable; the key signal distortion areas include the area boundary coordinates and the distortion degree quantification value.

[0082] Step S403: Based on the key areas of signal distortion, combined with the sensor's maximum coverage radius and installation constraints, construct the sensor spatial adjustment objective function.

[0083] Step S404: Solve the objective function using the gradient descent algorithm to generate the sensor space adjustment matrix, and obtain the adjusted sensor layout scheme; the sensor space adjustment matrix includes the sensor translation distance and angle adjustment parameters.

[0084] Preferably, the objective function for adjusting the sensor space is used as the solution object, and the gradient descent algorithm is employed for optimization calculation. First, the sensor adjustment parameter vector (including the initial translation distance and angle parameters of each sensor) is initialized, and the algorithm iteration step size and convergence condition (such as absolute gradient value ≤) are set. (Or the number of iterations reaches a preset upper limit); then, the gradient value of the objective function under the current parameter vector is calculated, and the parameter update direction is determined according to the gradient direction. The translation distance (x, y, z three-dimensional directions) and angle adjustment parameters (azimuth and pitch angles) of each sensor are adjusted according to the set step size. The gradient calculation and parameter update steps are repeated until the objective function value converges to the minimum value or meets the convergence condition. The iteration stops and a sensor space adjustment matrix is ​​generated. This matrix clearly records the three-dimensional translation distance (unit: m) and angle adjustment parameters (unit: °) of each sensor. Based on the matrix, the coordinates and angles of the initially optimized sensor position distribution data are corrected, and finally the adjusted sensor layout scheme is obtained. The scheme includes the final installation coordinates, spacing, and angle parameters of all sensors.

[0085] Step S405: Calculate the signal coverage deviation value of each monitoring point in the sensor layout scheme, and judge the signal coverage deviation value based on the preset threshold.

[0086] Furthermore, for all preset monitoring points within the sensor monitoring area (including key monitoring locations and uniformly distributed regular monitoring locations), the three-dimensional coordinate data of each monitoring point is acquired. Based on the obtained sensor layout scheme, the signal propagation path loss model is invoked, and combined with signal calibration parameters, the actual signal reception strength of each monitoring point is calculated. The actual signal strength of each monitoring point is compared with the preset standard signal strength, and the signal coverage deviation value (unit: dB) of all monitoring points is calculated according to the formula "signal coverage deviation value = |actual signal strength - standard signal strength|". A preset signal coverage deviation threshold (determined according to monitoring accuracy requirements and sensor performance parameters) is used to judge the deviation value of each monitoring point, and the number and distribution range of monitoring points with deviation values ​​exceeding the standard are counted. If the signal coverage deviation value of all monitoring points is lower than the preset threshold, or the proportion of monitoring points exceeding the standard is lower than the set proportion, then the current layout scheme is determined to meet the requirements; if the requirements are not met, the objective function weight coefficient is adjusted.

[0087] Step S406: If the signal coverage deviation value is lower than the preset threshold, the adjusted sensor layout scheme is output as the final optimized sensor space layout scheme.

[0088] Step S407: If the signal coverage deviation value is higher than the preset threshold, the weight coefficient of the sensor spatial adjustment objective function is corrected based on the spatial distribution characteristics of the current signal coverage deviation value, and a new sensor spatial layout scheme is recalculated until the preset threshold is met.

[0089] Specifically, a multi-source data fusion algorithm is employed to correlate and fuse signal calibration parameters with the current spatial layout data of the sensors (including three-dimensional installation coordinates, spacing, tilt angle, and rated coverage radius). Coordinate mapping technology and coverage optimization algorithms are used to remap the sensor's position distribution, outputting preliminary optimized sensor position distribution data. Based on this data, a pre-set historical signal distortion pattern database is invoked. Pattern matching and pattern analysis algorithms are used to extract distortion features during signal transmission, identifying key areas of signal distortion where signal attenuation exceeds limits and data transmission is unstable. These areas explicitly include boundary coordinates (unit: m) and a quantified value of distortion severity (dimensionless, ranging from 0 to 1). Combining the location information and quantified value of the key signal distortion areas, the maximum rated coverage radius of the sensors and installation space constraints (such as physical boundaries of the installation area and equipment interference limitations) are simultaneously incorporated to construct a system that "minimizes distortion impact and maximizes coverage effectiveness." The objective function for sensor spatial adjustment is defined as follows: A gradient descent algorithm is used to iteratively solve this objective function, generating a sensor spatial adjustment matrix containing the translation distance (in meters) and angle adjustment parameters (in degrees) of each sensor. Based on this matrix, the adjusted sensor layout scheme is output. Using a signal propagation path loss model, the signal coverage deviation value (defined as the absolute value of the difference between the actual signal strength and the standard signal strength at the monitoring point, in dB) for each monitoring point in this layout scheme is calculated and compared with a preset threshold. If the signal coverage deviation value is lower than the preset threshold, the adjusted sensor layout scheme is directly output as the final optimized scheme. If the signal coverage deviation value is higher than the preset threshold, the weight coefficients of each constraint term in the sensor spatial adjustment objective function are corrected based on the spatial distribution characteristics of the current deviation value (such as the concentrated location of high-deviation areas and the distribution of deviation amplitude). The objective function construction, solution, and deviation calculation process are then re-executed until the generated layout scheme meets the signal coverage deviation threshold requirement.

[0090] This embodiment ensures comprehensive and reliable input data for layout optimization through multi-source data fusion, and the use of a historical distortion pattern library enables precise location of critical distortion areas. The objective function incorporates sensor hardware parameters and installation constraints, ensuring the engineering feasibility of the layout scheme. The application of the gradient descent algorithm improves the efficiency and accuracy of solving layout adjustment parameters. The iterative correction mechanism effectively solves the problem of excessive coverage deviation that may occur in a single optimization, ensuring that the signal coverage effect of the final layout scheme meets the standards. The overall process dynamically optimizes the sensor position and angle, accurately avoids critical signal distortion areas, and significantly improves the monitoring coverage effectiveness and signal transmission stability of the sensor network.

[0091] In one embodiment, the objective function for sensor space adjustment can be expressed using the following formula:

[0092]

[0093] in, Represents the objective function value. , Indicates the number of critical regions of signal distortion. Indicates the first Quantitative values ​​of the degree of distortion in key distortion regions. Indicates the first Signal coverage deviation values ​​in key distortion areas Indicates the standard threshold for signal coverage deviation. Indicates the total number of sensors. Indicates the first The actual coverage radius after adjustment of each sensor Indicates the sensor's maximum rated coverage radius. Indicates the first The and the first The center spacing of each sensor has been adjusted. Indicates the minimum value. , , This represents the weighting coefficient.

[0094] In this embodiment, the sensor spatial adjustment objective function systematically optimizes the layout scheme by weightedly fusing three core optimization objectives: the first objective focuses on minimizing the impact of distortion by using the quantified value of the distortion degree in key signal distortion areas and the relative value of coverage deviation; the second objective constrains the deviation between the actual coverage radius of the sensor and the maximum rated coverage radius to ensure sufficient monitoring coverage; and the third objective avoids installation interference and coverage overlap waste by optimizing the center-to-center spacing between sensors. The formula integrates requirements such as distortion suppression, coverage assurance, and installation adaptation into a unified optimization objective, providing a clear solution direction for the gradient descent algorithm. This ensures that the generated sensor spatial adjustment matrix can accurately correct the sensor position and angle, maximizing the reduction of signal distortion and improving the effectiveness of monitoring coverage while meeting installation constraints. This lays an optimized hardware layout foundation for the stable and efficient operation of the sensor network.

[0095] In one embodiment, key feature parameters are extracted from the sensor spatial layout scheme to construct an association model and determine a dynamic compensation mechanism. If the dynamic compensation mechanism meets a preset trigger threshold, a comprehensive performance evaluation report is generated, which may include the following steps:

[0096] Step S501: Obtain the initial configuration data of the sensor spatial layout scheme; the initial configuration data includes the spatial distribution parameters of each sensor and the monitoring range information of each sensor.

[0097] Step S502: Based on the spatial distribution parameters, a finite element stress simulation algorithm is used to construct a stress distribution simulation matrix for the sensor installation area. Preliminary stress distribution results are obtained through numerical iteration calculation. The stress distribution results include the boundary coordinates of high stress regions and uniform stress regions, as well as the corresponding stress quantization values.

[0098] Step S503: Extract key feature parameters from the stress distribution results and cross-compare them with the monitoring range information to construct a correlation model and determine the dynamic compensation mechanism.

[0099] Step S504: If the quantitative indicators of the triggering conditions of the dynamic compensation mechanism meet the preset threshold, the updated monitoring protocol parameters are dynamically adjusted according to the adaptation mapping relationship between key feature parameters and sampling frequency. The monitoring protocol parameters include the adjusted sampling frequency, data caching strategy, and transmission priority configuration.

[0100] Step S505: Collect multi-source data from the fiber optic sensor network, and construct an adaptation performance evaluation index system using the analytic hierarchy process (AHP) in conjunction with monitoring protocol parameters. Generate a comprehensive performance evaluation report through weighted calculation. The comprehensive performance evaluation report includes quantitative scores for each index, overall adaptation level, and optimization suggestions.

[0101] Specifically, the initial configuration data for the sensor spatial layout scheme is first obtained. This data includes the spatial distribution parameters (3D installation coordinates, spacing, tilt angle) and monitoring range information (rated coverage radius, monitoring angle threshold) of each sensor. Based on the spatial distribution parameters, a finite element stress simulation algorithm is used to mechanically model the sensor installation area, constructing a stress distribution simulation matrix. This matrix is ​​solved through numerical iteration to obtain preliminary stress distribution results. These results clearly include the boundary coordinates (unit: m) of high stress areas and uniform stress areas, as well as the corresponding quantified stress values ​​(unit: MPa). Key characteristic parameters such as stress peak value, stress change rate, and proportion of high stress areas are extracted from the stress distribution results. These parameters are cross-compared with the sensor monitoring range information, and a "stress characteristic-" model is constructed through statistical analysis. The monitoring range is associated with a model that quantifies the compatibility between the two and determines a dynamic compensation mechanism (including compensation triggering conditions and parameter adjustment logic). A preset threshold for the triggering conditions of the dynamic compensation mechanism is established (e.g., stress change rate ≥ 0.5 MPa / s, stress peak ≥ 80% of rated withstand stress). If the actual monitored operating parameters meet this threshold, the updated monitoring protocol parameters are dynamically adjusted based on the preset compatibility mapping relationship between key characteristic parameters and sampling frequency (higher stress levels require higher sampling frequency compatibility). These parameters include the adjusted sampling frequency (unit: Hz) and data caching strategy (e.g., caching period, caching capacity). The system allocates data and configures transmission priorities (based on the importance of the monitoring area); it collects multi-source operational data from the fiber optic sensor network (including real-time signal strength, transmission delay, bit error rate, and energy consumption data), and combines this data with updated monitoring protocol parameters. It then uses the analytic hierarchy process (AHP) to construct an adaptation performance evaluation index system (including three primary indicators: signal acquisition accuracy, transmission stability, and energy consumption control efficiency, as well as several secondary indicators). By assigning preset weights to each indicator and performing weighted calculations, a comprehensive performance evaluation report is generated. This report includes quantitative scores for each indicator (out of 100), an overall adaptation level (excellent / good / medium / poor), and targeted optimization suggestions.

[0102] This embodiment accurately obtains the stress distribution characteristics of the installation area through finite element stress simulation, providing a core mechanical basis for the establishment of a dynamic compensation mechanism. The cross-comparison of key characteristic parameters and monitoring range ensures the pertinence of the dynamic compensation mechanism, enabling the monitoring protocol parameters to be flexibly adjusted according to stress conditions, effectively improving the sensor network's adaptability to complex mechanical environments. The performance evaluation index system constructed by the analytic hierarchy process (AHP) achieves quantitative feedback of multi-dimensional performance, and the generated evaluation report provides data support for subsequent operation and maintenance optimization. The overall process not only ensures the mechanical safety and monitoring effectiveness of the sensor layout, but also improves the operational stability and condition adaptability of the sensor network through dynamic adjustment and quantitative evaluation, further perfecting the full-process optimization system of fiber optic sensors.

[0103] In one embodiment, such as Figure 2 As shown, this application also provides a fiber optic sensor optimization device, which may include:

[0104] The characteristic deviation extraction module 601 is used to acquire the original optical signal of the fiber optic sensor, extract characteristic wavelength data from the original optical signal using spectral analysis, and filter out temperature-induced material aging signal noise to obtain the optical characteristic deviation index.

[0105] The signal calibration parameter module 602 is used to determine the signal calibration parameters by quantifying the signal attenuation degree based on the optical characteristic deviation index through an adaptive calibration algorithm and establishing an adaptive mapping relationship with the environmental parameters.

[0106] The sensor layout generation module 603 is used to analyze the key areas of signal distortion by combining signal calibration parameters and spatial layout data, calculate the signal coverage deviation value of the key areas of signal distortion, and generate a sensor spatial layout scheme if the signal coverage deviation value meets the preset threshold.

[0107] The comprehensive performance evaluation module 604 is used to extract key feature parameters from the sensor spatial layout scheme, construct an association model, and determine the dynamic compensation mechanism. If the dynamic compensation mechanism meets the preset trigger threshold, a comprehensive performance evaluation report is generated.

[0108] The aforementioned fiber optic sensor optimization device includes a characteristic deviation extraction module, which serves as the starting point for data processing. This module acquires the raw optical signals collected by the fiber optic sensor, uses spectral analysis to filter out characteristic wavelength data relevant to the monitoring target, and specifically filters out temperature-induced material aging noise. Based on the processed characteristic wavelength data, it calculates an optical characteristic deviation index that reflects the sensor's optical performance deviating from its standard state. The signal calibration parameter module uses this optical characteristic deviation index as its core input, employs an adaptive calibration algorithm to quantify the attenuation during signal transmission, and synchronously introduces real-time acquired environmental parameters to establish a dynamic adaptation mapping relationship. By adjusting the calibration factor weights, it determines signal calibration parameters that can compensate for environmental interference and signal attenuation. The sensor layout generation module... The system receives signal calibration parameters and current sensor spatial layout data (including 3D coordinates, spacing, coverage radius, etc.). It analyzes key areas of signal distortion through multi-source data fusion, calculates the signal coverage deviation in these areas, and generates an optimized sensor spatial layout scheme if the deviation meets a preset threshold. The comprehensive performance evaluation module extracts key feature parameters (such as stress distribution and coverage overlap rate) from the generated sensor spatial layout scheme, constructs a correlation model between these feature parameters and monitoring requirements to determine a dynamic compensation mechanism. If the quantification index of the compensation mechanism's trigger condition meets a preset threshold, it collects multi-source operating data from the sensor network, constructs a performance evaluation index system based on monitoring protocol parameters, and generates a comprehensive performance evaluation report containing quantification scores, adaptation levels, and optimization suggestions through weighted calculations. In this device, the characteristic deviation extraction module provides a precise data foundation for subsequent calibration work, the signal calibration parameter module improves calibration accuracy by dynamically adapting to environmental parameters, the sensor layout generation module optimizes the layout based on calibration parameters, and the comprehensive performance evaluation module forms a feedback loop through the dynamic compensation mechanism and quantification evaluation. The modules complement each other and the data flow is smooth, which effectively solves the problems of signal noise interference, calibration and working conditions disconnect, unreasonable layout and lack of quantitative evaluation of performance of traditional sensors. It improves the accuracy of monitoring data, operation stability and adaptability to complex working conditions of fiber optic sensors, and provides systematic technical support for the actual deployment and operation and maintenance optimization of sensors.

[0109] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0110] In one embodiment, a computer device is provided, including a memory and a processor, the memory storing a computer program, the processor executing the computer program to implement the steps of the fiber optic sensor optimization method as described above.

[0111] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps in the above method embodiments.

[0112] For the device embodiments, since they basically correspond to the method embodiments, the relevant parts can be referred to in the description of the method embodiments. The device embodiments described above are merely illustrative. The components described as separate parts may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this disclosure according to actual needs. Those skilled in the art can understand and implement this without creative effort.

[0113] The above-described embodiments are merely illustrative of several implementation methods of the embodiments of this application, and their descriptions are relatively specific and detailed. However, they should not be construed as limiting the scope of the patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the embodiments of this application, and these modifications and improvements all fall within the protection scope of the embodiments of this application.

Claims

1. A fiber optic sensor optimization method, characterized in that, The method includes: The original optical signal of the fiber optic sensor is acquired, and characteristic wavelength data is extracted from the original optical signal using spectral analysis and temperature-induced material aging signal noise is filtered out to obtain optical characteristic deviation index. Based on the optical characteristic deviation index, the signal attenuation degree is quantified by an adaptive calibration algorithm and an adaptive mapping relationship is established with environmental parameters to determine the signal calibration parameters. By combining the signal calibration parameters and spatial layout data, the key areas of signal distortion are analyzed, and the signal coverage deviation value of the key areas of signal distortion is calculated. If the signal coverage deviation value meets the preset threshold, a sensor spatial layout scheme is generated. Key feature parameters are extracted from the sensor spatial layout scheme to construct an association model and determine the dynamic compensation mechanism. If the dynamic compensation mechanism meets the preset trigger threshold, a comprehensive performance evaluation report is generated.

2. The method according to claim 1, characterized in that, The process involves acquiring the raw optical signal from the fiber optic sensor, extracting characteristic wavelength data from the raw optical signal using spectral analysis, and filtering out temperature-induced material aging signal noise to obtain optical characteristic deviation indicators, including: Acquire the raw optical signal generated by the fiber optic sensor; the raw optical signal contains multiple wavelength information. Based on the original optical signal, spectral analysis is performed to extract characteristic wavelength data and obtain a preliminary wavelength feature set; A filtering algorithm is used to remove temperature-induced material aging-related signal noise from the wavelength feature set, and a preliminary optical property deviation index is calculated. If the preliminary optical characteristic deviation index exceeds the preset threshold range, a second feature extraction of wavelength offset data is performed on the filtered wavelength feature set. Based on the wavelength offset data, a deviation correction model is constructed, and the final optical characteristic deviation index is output.

3. The method according to claim 2, characterized in that, The optical characteristic deviation index is calculated using the following formula: in, Indicators representing deviations in optical properties. Indicates the number of characteristic wavelengths. Indicates the first Measured values ​​of each characteristic wavelength Indicates the first Standard reference values ​​for each characteristic wavelength, This indicates the number of frequency segments in the filtering algorithm. Indicates the first Signal strength after noise filtering in each frequency band Indicates the first The original signal strength before noise filtering in each frequency band.

4. The method according to claim 1, characterized in that, The process of determining signal calibration parameters by quantifying the signal attenuation level using an adaptive calibration algorithm based on the optical characteristic deviation index and establishing an adaptive mapping relationship with environmental parameters includes: Based on the aforementioned optical characteristic deviation index, an adaptive calibration algorithm is used to calculate the signal amplitude attenuation rate and phase offset, and then coupled to obtain the signal attenuation quantization value. By combining the quantized signal attenuation value with the real-time acquired environmental parameters, an adaptation mapping relationship is established, the calibration factor is dynamically adjusted, and the signal attenuation compensation coefficient is determined. The signal attenuation compensation coefficient is input into a preset signal processing model, and the signal calibration parameters are generated by iterative optimization based on the preset calibration error convergence condition; the signal processing model is jointly constructed by an adaptive filtering algorithm and a linear regression mapping algorithm.

5. The method according to claim 1, characterized in that, The process involves analyzing key areas of signal distortion using the signal calibration parameters and spatial layout data, calculating the signal coverage deviation value of these key areas, and generating a sensor spatial layout scheme if the signal coverage deviation value meets a preset threshold. This includes: A multi-source data fusion algorithm is used to correlate and fuse the signal calibration parameters and the current spatial layout data of the sensors. By optimizing the coordinate mapping and coverage area, the sensor position distribution is remapped to obtain preliminary optimized sensor position distribution data. Based on the sensor location distribution data, a preset historical signal distortion pattern database is called to analyze the distortion patterns during signal transmission and determine the key signal distortion areas where signal attenuation exceeds the standard and data transmission is unstable; the key signal distortion areas include the area boundary coordinates and the distortion degree quantification value; Based on the key areas of signal distortion, combined with the sensor's maximum coverage radius and installation constraints, a sensor spatial adjustment objective function is constructed. The objective function is solved using the gradient descent algorithm to generate a sensor space adjustment matrix, resulting in an adjusted sensor layout scheme. The sensor space adjustment matrix includes sensor translation distance and angle adjustment parameters. Calculate the signal coverage deviation value of each monitoring point in the sensor layout scheme, and judge the signal coverage deviation value based on a preset threshold; If the signal coverage deviation value is lower than the preset threshold, the adjusted sensor layout scheme is output as the final optimized sensor space layout scheme. If the signal coverage deviation value is higher than the preset threshold, the weight coefficient of the sensor spatial adjustment objective function is corrected based on the spatial distribution characteristics of the current signal coverage deviation value, and a new sensor spatial layout scheme is recalculated until the preset threshold is met.

6. The method according to claim 5, characterized in that, The objective function for adjusting the sensor space is expressed by the following formula: in, Represents the objective function value. , Indicates the number of critical regions of signal distortion. Indicates the first Quantitative values ​​of the degree of distortion in key distortion regions. Indicates the first Signal coverage deviation values ​​in key distortion areas Indicates the standard threshold for signal coverage deviation. Indicates the total number of sensors. Indicates the first The actual coverage radius after adjustment of each sensor Indicates the sensor's maximum rated coverage radius. Indicates the first The and the first The center spacing of each sensor has been adjusted. Indicates the minimum value. , , This represents the weighting coefficient.

7. The method according to claim 1, characterized in that, The process involves extracting key feature parameters from the sensor spatial layout scheme, constructing an association model, and determining a dynamic compensation mechanism. If the dynamic compensation mechanism meets a preset trigger threshold, a comprehensive performance evaluation report is generated, including: Obtain the initial configuration data of the sensor spatial layout scheme; the initial configuration data includes the spatial distribution parameters of each sensor and the monitoring range information of each sensor; Based on the spatial distribution parameters, a stress distribution simulation matrix for the sensor installation area is constructed using a finite element stress simulation algorithm. Preliminary stress distribution results are obtained through numerical iterative calculations. The stress distribution results include the boundary coordinates of high stress regions and uniform stress regions, as well as the corresponding quantized stress values. Key feature parameters extracted from the stress distribution results are cross-compared with the monitoring range information to construct an association model and determine the dynamic compensation mechanism. If the quantitative index of the triggering condition of the dynamic compensation mechanism meets the preset threshold, the updated monitoring protocol parameters are dynamically adjusted according to the adaptation mapping relationship between the key feature parameters and the sampling frequency; the monitoring protocol parameters include the adjusted sampling frequency, data caching strategy and transmission priority configuration. Multi-source data from the fiber optic sensor network are collected, and an adaptation performance evaluation index system is constructed using the analytic hierarchy process (AHP) in conjunction with the monitoring protocol parameters. A comprehensive performance evaluation report is generated through weighted calculation. The comprehensive performance evaluation report includes quantitative scores for each index, overall adaptation level, and optimization suggestions.

8. A fiber optic sensor optimization device, characterized in that, The device includes: The characteristic deviation extraction module is used to acquire the original optical signal of the fiber optic sensor, extract characteristic wavelength data from the original optical signal using spectral analysis, and filter out temperature-induced material aging signal noise to obtain optical characteristic deviation index. The signal calibration parameter module is used to quantify the signal attenuation degree based on the optical characteristic deviation index through an adaptive calibration algorithm and establish an adaptive mapping relationship with environmental parameters to determine the signal calibration parameters. The sensor layout generation module is used to analyze the key areas of signal distortion by combining the signal calibration parameters and spatial layout data, calculate the signal coverage deviation value of the key areas of signal distortion, and generate a sensor spatial layout scheme if the signal coverage deviation value meets a preset threshold. The comprehensive performance evaluation module is used to extract key feature parameters from the sensor spatial layout scheme, construct an association model, and determine the dynamic compensation mechanism. If the dynamic compensation mechanism meets the preset trigger threshold, a comprehensive performance evaluation report is generated.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 7.

Images