Lightweight power cable material characteristic database and analysis platform

Abstract

The invention, which relates to the technical field of power cable material characteristic data analysis, discloses a lightweight power cable material characteristic database and analysis platform comprising a compression configuration initialization module, a sudden change time section identification module, a compression influence evaluation module, a compression strategy adjustment module and a strategy adaptive optimization module. Identifying a mutation point existing in the stored fatigue data through a behavior identification method, determining a time range corresponding to the mutation point by taking the mutation point as a center, and calibrating the time range as a mutation time section; and analyzing the fatigue data of the lightweight power cable in the abrupt change time section, and evaluating the influence degree of the storage compression strategy of the current fatigue data on the fatigue life prediction accuracy. According to the method, the problem of key information loss in the compression process of the fatigue data of the lightweight power cable in the abrupt change section is solved, and accurate evaluation and adaptive optimization of the compression strategy are realized, so that the accuracy of life prediction and the intelligent level of data management are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of power cable material property data analysis, and in particular to a lightweight power cable material property database and analysis platform. Background Art

[0002] Lightweight power cable is a cable specially designed to reduce weight while maintaining or improving conductivity, mechanical strength and environmental resistance. It is widely used in high-end fields that are sensitive to weight, such as aerospace, electric vehicles, high-speed trains and intelligent manufacturing. The core lies in the use of new lightweight and high-strength materials, such as aluminum alloy conductors, carbon nanotube conductors, composite polymer insulation materials, etc., to reduce the overall mass and improve energy efficiency and reliability. The material characteristic data of lightweight power cables refers to the detailed parameters used to describe these cable materials in terms of electricity (such as conductivity, dielectric constant), mechanics (such as tensile strength, fatigue resistance), thermal (such as high temperature resistance, thermal expansion coefficient) and environmental adaptability (such as corrosion resistance, moisture resistance). These data directly determine the application adaptability and reliability of the cable. However, due to the large differences in the performance requirements of cable materials in different application scenarios, and the characteristics of the materials are affected by many factors (such as alloy composition, nanomaterial structure, manufacturing process), traditional laboratory measurement and empirical material selection methods can no longer meet the needs of modern efficient research and development. Therefore, it is particularly important to establish a database and analysis platform for the material properties of lightweight power cables. Through advanced database storage technology, massive material data can be systematically managed, and combined with artificial intelligence, big data analysis and simulation computing technology, material performance can be deeply mined, optimized and matched, and trend predicted, thereby accelerating the research and development of new lightweight power cables, improving the accuracy and reliability of material selection, and ultimately promoting the development and industrial application of lightweight power cable technology.

[0003] The existing lightweight power cable material property database and analysis technology mainly rely on multi-level data storage architecture and intelligent analysis engine to achieve efficient data management and material optimization. First, at the database storage layer, the platform adopts a hybrid storage architecture that combines relational databases (such as MySQL, PostgreSQL) with NoSQL databases (such as MongoDB, Cassandra), where relational databases are mainly used to store structured basic material information (such as material composition, manufacturing process, supplier data, etc.), while NoSQL databases are used to store massive amounts of experimental data, simulation results, and material microstructure images and other unstructured data. At the same time, the platform also combines distributed storage technology (such as Hadoop HDFS, ApacheParquet) to support efficient reading, writing and management of large-scale data. Secondly, at the data processing and analysis layer, the platform integrates AI-driven machine learning algorithms (such as random forests, support vector machines SVM, deep neural networks DNN), which can learn the influencing factors of material performance from historical data, and predict the material properties under specific formulas or process conditions through regression analysis and optimization algorithms. In addition, based on finite element analysis (FEA) and computational materials science methods (such as density functional theory DFT and molecular dynamics simulation MD), the platform can conduct virtual simulation tests of power cables in different working environments to evaluate the stability of materials under high temperature, high pressure, vibration and other conditions. Finally, at the decision support layer, the platform presents the analysis results through visualization tools (such as Tableau, Power BI, Matplotlib), and provides an intelligent material selection recommendation system based on a multi-objective optimization algorithm to help R&D personnel quickly screen the optimal material combination, reduce experimental costs, and accelerate the development and industrial application of new lightweight power cables.

[0004] The prior art has the following deficiencies: In long-term high-voltage power equipment, lightweight power cables need to withstand repeated bending, stretching or compression. These cyclic loads will cause microcracks to gradually form and expand inside the material, ultimately affecting the fatigue life of the cable. In order to accurately evaluate the fatigue performance of the material, the database needs to store a large amount of fatigue test data for a long time and restore the complete fatigue curve when querying. However, due to the large amount of data and limited storage space, the database usually compresses and stores fatigue data. However, during the fatigue process, the material performance does not decay uniformly, but there are mutation points (such as the rapid crack expansion stage). These key points are crucial for accurately predicting fatigue life. If the database uses a fixed ratio compression algorithm when compressing data and fails to identify these mutation points, key fatigue information may be lost during data recovery, resulting in the misjudgment of the material performance degradation trend. The existing lightweight power cable material property database and analysis technology lack the ability to identify and compress mutation points in the fatigue curve. Differentiated processing capabilities cannot ensure that the fatigue data still has the key feature integrity to support life prediction after compression, so as to maintain the accuracy of key data. As a result, when engineers query the fatigue curve, the data provided by the database may have increased fatigue life prediction errors, thereby affecting the actual use evaluation of the material. In turn, this will lead to an increase in the demand for experimental verification. Engineers will need to conduct additional experiments to correct database data, increasing R&D costs, and ultimately affecting the optimized design and promotion and application of new materials, delaying the development of new lightweight cables.

[0005] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention

[0006] The purpose of the present invention is to provide a lightweight power cable material property database and analysis platform to solve the problems in the above-mentioned background technology.

[0007] In order to achieve the above-mentioned object, the present invention provides the following technical solutions: a lightweight power cable material property database and analysis platform, including a compression configuration initialization module, a mutation time segment identification module, a compression impact assessment module, a compression strategy adjustment module and a strategy adaptive optimization module; The compression configuration initialization module analyzes the fatigue behavior characteristics of lightweight power cables and establishes corresponding fatigue data storage compression configuration strategies based on material type, service conditions and historical fatigue data; The mutation time segment identification module identifies the mutation points in the stored fatigue data through the behavior recognition method, and determines the corresponding time range with the mutation point as the center, and marks it as the mutation time segment; The compression impact assessment module analyzes the fatigue data of lightweight power cables in the mutation time section and evaluates the impact of the current fatigue data storage compression strategy on the accuracy of fatigue life prediction; The compression strategy adjustment module adjusts the data compression strategy for the mutation time segment according to the evaluation results and different impact levels; The strategy adaptive optimization module combines the fatigue life prediction results and experimental verification feedback to track and backtrack the storage strategy of the mutation time segment, adjust and update the compression processing logic according to the prediction error, and continuously monitor the changing trend of the fatigue performance of lightweight power cables.

[0008] Preferably, in the mutation time segment identification module, based on the changing trend of the stored lightweight power cable fatigue data, a behavior recognition method including first-order derivative mutation detection, curvature change analysis and local fitting residual abnormality recognition is adopted to detect the nonlinear change points existing in the fatigue curve to determine the position of the mutation point, and with the mutation point as the center, combined with the data sampling period and the performance change density, the time window of a preset range is extended forward and backward, and the covered time range is calibrated as the mutation time segment.

[0009] Preferably, in the compression impact assessment module, a fatigue life prediction model is constructed based on the fatigue data of the lightweight power cable in the mutation time section, and life prediction is performed on the original fatigue data before compression and the compressed and restored fatigue data respectively, to generate life assessment analysis information, and preprocessing is performed after generation; life prediction result information and model fitting modulus information are extracted from the preprocessed life assessment analysis information, and analyzed after extraction to generate a prediction offset sensitivity index and a compression restoration error index respectively; a compression impact assessment model is constructed for the generated prediction offset sensitivity index and compression restoration error index, and a compression influence coefficient is generated by weighted summation; a pre-set compression influence coefficient threshold interval is determined, and after determination, it is compared with the generated compression influence coefficient, and the degree of influence of the current fatigue data storage compression strategy on the accuracy of fatigue life prediction is evaluated according to the comparison result.

[0010] Preferably, the acquisition logic of the prediction offset sensitivity index is as follows: The life prediction result information is extracted from the preprocessed life assessment analysis information, including the fatigue life prediction values ​​generated by taking the original fatigue data before compression as the input of the fatigue life prediction model at different times in the mutation time segment and the fatigue life prediction values ​​generated by taking the fatigue data after compression and restoration as the input of the fatigue life prediction model, and they are calibrated as and , Indicates that within the mutation time period The fatigue life prediction value generated by using the original fatigue data before time compression as the input of the fatigue life prediction model, Indicates that within the mutation time period The fatigue life prediction value generated by using the fatigue data after compression and restoration as the input of the fatigue life prediction model is , is a positive integer; Calculate the prediction offset sensitivity index. The specific calculation formula is as follows: In the formula, is the prediction offset sensitivity index.

[0011] Preferably, the logic for obtaining the compression-restoration error index is as follows: The model fitting modulus information is extracted from the preprocessed life assessment analysis information, including the equivalent modulus values ​​recorded in the original fatigue data before compression at different times in the mutation time segment, the equivalent modulus values ​​recorded in the fatigue data after compression restoration, and the theoretical modulus values ​​obtained by fitting the life prediction model, and are calibrated as , and , Indicates that within the mutation time period The equivalent modulus value recorded in the original fatigue data before compression, Indicates that within the mutation time period The equivalent modulus value recorded in the fatigue data after compression and restoration at each moment, Indicates that within the mutation time period The theoretical modulus value obtained by fitting the life prediction model at any time, , is a positive integer; Calculate the compression restoration error index. The specific calculation formula is as follows: In the formula, is the compression-reduction error index, Indicates Moment The maximum value between 1 and Indicates Moment The maximum value between 0 and 1.

[0012] Preferably, the generated prediction deviation sensitivity index and compression-reduction error index Construct a compression impact assessment model and generate the compression impact coefficient through weighted summation. The specific calculation formula is as follows: In the formula, is the compression influence coefficient, and The prediction offset sensitivity index is and compression-reduction error index The non-zero weight coefficient of .

[0013] Preferably, a preset compression influence coefficient threshold interval is determined , and after determination, the generated compression influence coefficient A comparison is made, and the influence of the current fatigue data storage compression strategy on the fatigue life prediction accuracy is evaluated based on the comparison results. The specific comparison analysis is as follows: like ,The current storage compression strategy of fatigue data ,has a low impact on the accuracy of fatigue life prediction; like ,The current storage compression strategy of fatigue data ,has a moderate impact on the accuracy of fatigue life prediction; like ,The current storage compression strategy of fatigue data has a high impact on the ,accuracy of fatigue life prediction.

[0014] Preferably, in the compression strategy adjustment module, according to the evaluation results and for different impact levels, the data compression strategy for the mutation time segment is adjusted, specifically including: If the evaluation result is low impact, the adjustment of the data compression strategy for the mutation time segment is as follows: keep the current compression strategy unchanged and maintain the original compression parameter configuration; If the evaluation result is a medium impact, the data compression strategy for the mutation time segment is adjusted as follows: the compression ratio in the current compression parameter is reduced to within the preset reduction range of the original value, and the redundant data verification mechanism is enabled to enhance the restoration accuracy; If the assessment result is a high impact, the specific adjustments to the data compression strategy for the mutation time segment are: replace it with an accuracy-first compression algorithm, enable lossless compression mode, and turn off the automatic inheritance function of compression parameters.

[0015] In the above technical solution, the technical effects and advantages provided by the present invention are: 1. The present invention introduces a mutation time segment identification module and uses behavioral identification methods such as first-order derivative mutation detection, curvature change analysis, and local fitting residual identification to accurately locate performance mutation points in fatigue data and construct a dynamic time window for calibration, thereby realizing the automatic identification of nonlinear behavioral characteristics of lightweight power cables during service. Compared with the existing technology that relies on fixed rules or average strategies for data compression, this solution can ensure that in the key sections where fatigue performance changes sharply, the data compression strategy can timely identify risk areas and focus on them, avoiding the problem of misjudgment of life caused by the destruction of key information by the compression process from the source, and greatly improving the intelligence and precision control capabilities of database compression processing.

[0016] 2. The present invention establishes a dual evaluation mechanism consisting of a prediction offset sensitivity index and a compression restoration error index, combines the output results of the life prediction model with the physical modulus fidelity to construct a compression impact evaluation model, and generates a compression impact coefficient through weighted calculation. This technical path can not only evaluate the impact of the compression strategy on the accuracy of life prediction from the dual dimensions of "prediction layer" and "physical layer", but also realizes the quantitative comparison of the effects of different compression schemes, so that the system can clearly judge the adaptability level of the current strategy. By setting the threshold interval of the compression impact coefficient, the degree of strategy impact is divided into three levels: low, medium, and high, and the corresponding compression adjustment action is triggered, which realizes differentiated and hierarchical control of fatigue data compression strategy, thereby effectively improving the credibility of the model output and the robustness of the compression strategy.

[0017] 3. The present invention further introduces a strategy adaptive optimization module, which is based on the error comparison results between fatigue life prediction results and experimental verification feedback, combined with the historical compression strategy execution effect of the mutation section for tracking and backtracking, to achieve automatic optimization and adjustment of compression parameters and algorithms. The platform continuously monitors the fatigue performance change trend of cable materials during service, dynamically perceives changes in material behavior patterns, and self-updates the compression strategy accordingly, effectively avoiding the adaptation failure problem caused by the long-term static nature of the strategy. This module establishes a closed-loop mechanism of "evaluation-feedback-update", which enables the system to have long-term self-evolution and strategy adaptability, greatly enhancing the intelligence level, data fidelity and engineering application scalability of the lightweight power cable material property database and analysis platform. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0019] Figure 1 It is a module schematic diagram of the lightweight power cable material property database and analysis platform of the present invention. DETAILED DESCRIPTION

[0020] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these example embodiments are provided so that the description of the present disclosure will be more comprehensive and complete, and the concept of the example embodiments will be fully conveyed to those skilled in the art.

[0021] The present invention provides Figure 1 The lightweight power cable material property database and analysis platform shown includes a compression configuration initialization module, a mutation time segment identification module, a compression impact assessment module, a compression strategy adjustment module, and a strategy adaptive optimization module; The compression configuration initialization module analyzes the fatigue behavior characteristics of lightweight power cables and establishes corresponding fatigue data storage compression configuration strategies based on material types, service conditions and historical fatigue data to initialize the database compression processing conditions of fatigue data that match the fatigue characteristics of this type of material. In order to analyze the fatigue behavior characteristics of lightweight power cables and establish a matching compression configuration strategy, the platform can extract multi-dimensional feature data including material type, mechanical properties, service environment parameters (such as temperature, humidity, load type, stress cycle frequency) and past fatigue curves by calling the material database and historical fatigue test data interface, and build a material fatigue behavior classifier based on rule models and machine learning models. The classifier can classify the fatigue curves of different materials into types such as slow decay, mutation expansion, and multi-stage turning, and preset the data compression configuration parameters corresponding to each type of fatigue behavior, such as the upper limit of the compression ratio, mutation detection threshold, sampling frequency range, etc. Based on the analysis results, the platform generates the corresponding compression configuration file for the target material in the database, and automatically binds it to the subsequent data writing process to guide the compression processing behavior of fatigue data during storage, thereby realizing personalized compression initialization driven by fatigue characteristics.

[0022] Since the fatigue behavior of lightweight power cables is subject to the complex coupling of material properties and operating conditions, there are significant differences in the performance attenuation patterns of different types of materials during the fatigue process. If a unified compression configuration strategy is adopted, it will be difficult to take into account both storage efficiency and fatigue life prediction accuracy. Especially when there are sudden behaviors such as crack extension, the fixed compression algorithm is prone to cause key data loss, which in turn affects subsequent life modeling and material evaluation. By actively analyzing the fatigue behavior characteristics of materials and historical data during the system initialization phase and establishing compression configuration parameters that match them, a "compression adaptability model" can be built in advance, so that the database has differentiated processing capabilities before receiving new data. This configuration strategy not only improves the system's adaptability to a variety of materials, but also provides a basic framework for subsequent mutation point identification, compression impact assessment, and dynamic strategy optimization, ensuring that the intelligent compression logic of the entire system has a priori pertinence and scalability.

[0023] The mutation time segment identification module identifies the mutation points in the stored fatigue data through the behavior recognition method, and determines the corresponding time range with the mutation point as the center, and marks it as the mutation time segment; In this embodiment, in the mutation time segment identification module, based on the changing trend of the stored lightweight power cable fatigue data, a behavior recognition method including first-order derivative mutation detection, curvature change analysis and local fitting residual abnormality recognition is adopted to detect the nonlinear change points in the fatigue curve to determine the position of the mutation point, and with the mutation point as the center, combined with the data sampling period and performance change density, the time window of a preset range is extended forward and backward, and the covered time range is calibrated as a mutation time segment for differentiated processing of subsequent compression strategies and key data retention control.

[0024] In the mutation time segment identification module, the platform first preprocesses the stored lightweight power cable fatigue data, including outlier removal, sampling frequency unification and trend smoothing operations, to ensure that the data quality meets the analysis requirements. Subsequently, the platform constructs a fatigue curve with time or number of cycles as the horizontal axis and performance indicators (such as stress, strain, stiffness or conductivity) as the vertical axis, and traverses the entire curve area in a sliding window manner. In each sliding window, the software system sequentially executes a multi-dimensional behavior recognition algorithm, including local derivative calculation of the data, curvature estimation and fitting error analysis, to extract the change characteristic indicators of each position. The platform sets a set of adaptive thresholds to compare the characteristic indicators of each position. When the first-order derivative of a certain position jumps, the curvature changes sharply, or the fitting residual increases significantly, the system marks the position as a potential mutation point. Subsequently, the platform further performs stability verification, eliminates pseudo mutations caused by local noise interference, and finally determines the exact position of the mutation point in the fatigue data, providing a data basis for the subsequent construction of mutation time segments and evaluation of compression strategies.

[0025] "First-order derivative mutation detection" refers to the continuous calculation of the first-order derivative (i.e., the rate of change of performance) of the fatigue curve in the time or cycle dimension, and observing whether there are jumps, reversals, or sudden changes in slope in the local range. This mutation usually indicates that the material performance begins to degrade rapidly or enters the nonlinear crack growth stage. "Curvature change analysis" uses the second-order derivative of the curve (or based on the geometric curvature formula) to capture the degree of bending of the data shape. By calculating the local curvature value of each point and comparing it with the mean of the surrounding section, it is determined whether there is a sharp deformation inflection point. The appearance of high curvature points in the fatigue curve usually indicates that the material is unstable or the damage mechanism has a sudden change. "Local fitting residual abnormal identification" refers to the use of polynomial fitting, spline interpolation and other methods to model the trend of local data fragments, and calculate the residual between the original data and the fitting curve. When the residual is significantly larger than the normal fluctuation range in a certain window, it indicates that there is an abnormal deviation trend in the area, which is usually related to sudden damage or sudden changes in material performance. The three complement each other and can effectively improve the accuracy and anti-interference ability of mutation point detection, which is especially suitable for dealing with the nonlinear degradation characteristics of lightweight power cable materials in complex fatigue environments.

[0026] After the mutation point is identified, the platform uses the mutation point as the segment center and automatically constructs the mutation time segment in software by combining the data sampling period and performance change density. In specific implementation, the platform first calculates the number of data points per unit time based on the data sampling frequency recorded in the database to determine the minimum scalable granularity under the time dimension. Then, the platform dynamically evaluates the change density of the area based on the performance change rate before and after the mutation point (such as strain increment, modulus drop rate, residual stress fluctuation amplitude), and determines the data length that needs to be expanded outward before and after the mutation based on the set change threshold. The platform sets an initial time window (such as a fixed time value or number of cycles) and then superimposes the change density analysis results to adjust the window, thereby forming an extended time segment that includes the mutation point itself and can fully cover the data characteristics before and after the mutation. Finally, the platform marks the data range in the time window as a "mutation time segment" and stores it in the metadata table together with the mutation point position as the focus of subsequent compression strategy evaluation and storage control.

[0027] During the service of lightweight power cables, the degradation of their fatigue performance often does not occur in isolation at a certain point, but forms a continuous change process before and after the mutation point, such as the transition from crack initiation to expansion to stability. These stages often show a continuous but accelerated change trend. If only the mutation point is identified without expanding its affected section, it is easy to simplify or discard the key data before and after the mutation point during compression processing, thereby damaging the fatigue life prediction model's overall understanding of the behavior of the mutation stage. By combining the sampling period and the density of performance changes to intelligently expand the mutation section, it can not only more accurately envelop the key behavior area of ​​fatigue degradation, but also improve the accuracy of subsequent compression evaluation and strategy allocation, ensuring that the database can provide targeted protection for these "high-value data areas" during compression processing. This method enables the platform to have the ability to "move from point identification to segment modeling", enhances the system's prediction robustness and the controllability of the compression strategy, and is an indispensable part of realizing intelligent compression processing.

[0028] The compression impact assessment module analyzes the fatigue data of lightweight power cables in the mutation time section and evaluates the impact of the current fatigue data storage compression strategy on the accuracy of fatigue life prediction; In this embodiment, in the compression impact assessment module, a fatigue life prediction model is constructed based on the fatigue data of the lightweight power cable in the mutation time section, and life prediction is performed on the original fatigue data before compression and the compressed and restored fatigue data respectively, to generate life assessment analysis information, and preprocessing is performed after generation; life prediction result information and model fitting modulus information are extracted from the preprocessed life assessment analysis information, and analyzed after extraction to generate a prediction offset sensitivity index and a compression restoration error index respectively; a compression impact assessment model is constructed for the generated prediction offset sensitivity index and compression restoration error index, and a compression influence coefficient is generated by weighted summation; a pre-set compression influence coefficient threshold interval is determined, and after determination, it is compared with the generated compression influence coefficient, and the degree of influence of the current fatigue data storage compression strategy on the accuracy of fatigue life prediction is evaluated according to the comparison result.

[0029] In the compression impact assessment module, the platform first constructs a fatigue life prediction model based on the fatigue data of lightweight power cables in the mutation time segment. This process can call the historical fatigue test database through the software, extract structural characteristics and performance indicators including stress amplitude, strain amplitude, number of cycles, equivalent modulus, etc., and combine the actual life results collected by the test as labels, and use regression algorithms (such as polynomial regression, SN curve fitting, Coffin-Manson model expansion algorithm, or curve fitting based on neural network) to establish a fatigue life prediction model. After the model is built, the platform uses the original fatigue data before compression and the compressed and restored data as inputs respectively. The input dimensions include the same indicator features used for model training mentioned above. After the model prediction process, the corresponding fatigue life prediction values ​​or life decay trends are output respectively for subsequent difference evaluation. This process can be automatically executed through the modeling engine module of the platform, and the batch output of prediction results can be realized in combination with the model parameter visualization interface.

[0030] Since the performance degradation behavior of lightweight power cables in the mutation time section has a significant impact on their fatigue life, if the compressed data loses key information, it will directly interfere with the accuracy of life prediction. In order to determine whether the current compression strategy weakens the life prediction ability, it is necessary to use the prediction model to independently predict the data before and after compression, and compare the deviation or stability between the prediction results. Through this process, the "potential prediction error caused by compression" can be converted into a "quantifiable evaluation indicator", providing a direct basis for the subsequent compression impact assessment. This method integrates the life prediction model into the compression evaluation logic, realizing the upgrade from "data accuracy" evaluation to "functional impact" evaluation, which has higher technical value and practical significance.

[0031] The purpose of preprocessing after generating life assessment analysis information is to eliminate data noise, standardize data dimensions, enhance the stability and comparability of parameter calculations, and ensure that the two exponential parameters calculated subsequently have a consistent data basis under different compression states. The preprocessing process can be completed automatically by the software, and mainly includes the following steps: First, normalization processing is performed to uniformly map all indicators (such as modulus, stress, life value, etc.) to a standard scale (such as 0 to 1) to avoid the influence of numerical dimension differences on the calculation results; second, outlier detection and correction are performed to eliminate local sampling anomalies based on statistical outlier detection or sliding window variance method; third, interpolation or resampling processing is performed to ensure that the time points of the data before and after compression are aligned to avoid error superposition caused by inconsistent time dimensions; fourth, the model fitting residuals are smoothed to reduce the impact of jump points caused by data compression in the prediction curve. These processes can be completed through the built-in data cleaning module of the platform and are automatically triggered before model evaluation.

[0032] After the life assessment and analysis information is preprocessed, the platform can perform structured extraction of various contents in the information through the built-in data parsing and label separation module. Specifically, the platform classifies and identifies the life assessment and analysis information by field or data label, and distinguishes the life prediction value sequence and fitting modulus sequence generated by the pre-compression and compression restoration data input into the fatigue life prediction model respectively. For the life prediction result information, the platform identifies it as the direct output result of the model, and extracts the fatigue life prediction value (such as remaining life, total life or life decay rate, etc.) corresponding to each moment according to the time node; for the model fitting modulus information, the platform calls the model internal state data or fitting parameter output to extract the elastic modulus value that fits the corresponding fatigue state, which usually comes from the intermediate prediction variable or residual regression term in the model fitting process. The extraction process adopts field mapping and data path identification mechanism to support the unified parsing of structured data and semi-structured model output, ensuring that the life prediction value corresponds to the modulus value one by one and is automatically associated with the subsequent index calculation logic. The entire extraction process can be achieved through the software's automatic data label matching and field diversion rules without manual intervention.

[0033] In order to determine the pre-set compression influence coefficient threshold interval, the platform can construct multiple groups of compression influence coefficient samples based on the historical fatigue test data set and the performance of life prediction errors under various compression strategies, and divide the intervals by combining the supervised classification method. The specific implementation method is that the platform first simulates compression and life prediction of data under different material types, load conditions and compression algorithm conditions through the software system, calculates the corresponding prediction offset sensitivity index and compression restoration error index, and generates the compression influence coefficient of the historical samples through the weighted model. Subsequently, the platform combines the actual life error level of each group of samples and labels them as mild, moderate or severe impact according to the actual engineering impact degree. Based on this labeled data set, the platform uses cluster analysis, decision tree segmentation or quantile partitioning algorithms to automatically learn the distribution law of the compression influence coefficient, and determine the coefficient value interval range corresponding to mild impact, moderate impact and severe impact. This process can periodically perform model self-training in the background, so that the threshold interval has the ability to adaptively update, ensuring that the effective discrimination ability is always maintained under the evolution of different materials and compression strategies. The entire threshold interval setting logic can be implemented through data-driven software algorithms without manual settings.

[0034] In this embodiment, the logic for obtaining the prediction offset sensitivity index is as follows: The life prediction result information is extracted from the preprocessed life assessment analysis information, including the fatigue life prediction values ​​generated by taking the original fatigue data before compression as the input of the fatigue life prediction model at different times in the mutation time segment and the fatigue life prediction values ​​generated by taking the fatigue data after compression and restoration as the input of the fatigue life prediction model, and they are calibrated as and , Indicates that within the mutation time period The fatigue life prediction value generated by using the original fatigue data before time compression as the input of the fatigue life prediction model, Indicates that within the mutation time period The fatigue life prediction value generated by using the fatigue data after compression and restoration as the input of the fatigue life prediction model is , is a positive integer; In order to achieve real-time acquisition of fatigue life prediction values ​​generated by original fatigue data before compression and fatigue data after compression and restoration at different time points in the mutation time segment, the platform can synchronously pass the fatigue data to the life prediction model module through the built-in data tracking and model calling mechanism while the fatigue data flows into the database. The specific implementation method is: when the platform detects that the fatigue data of the mutation time segment has been calibrated and archived, the system will automatically call the original fatigue data before compression, and extract the corresponding data fragments as model input at set time intervals, and generate the life prediction value at the mth moment in real time; at the same time, the platform will call the data after compression and restoration at the same time point as the second set of inputs of the model to generate the corresponding compression and restoration prediction value. Both types of life prediction values ​​are uniformly output through the life prediction model module, structured and saved, and automatically associated according to the timestamp. Among them, the life prediction value refers to the remaining life, total life or fatigue damage degree of the material calculated by the model after the fatigue performance parameters (such as equivalent modulus, stress amplitude, strain response, etc.) are input at the current moment, which can be expressed in the standard unit of "number of cycles" or "service time". The platform can ensure the and The real-time acquisition and recording are consistent and responsive, thus providing a continuously updated data basis for the calculation of the subsequent prediction offset sensitivity index.

[0035] Calculate the prediction offset sensitivity index. The specific calculation formula is as follows: In the formula, is the prediction offset sensitivity index.

[0036] Using the prediction offset sensitivity index The calculation formula is designed to evaluate the direct impact of the compression strategy on the accuracy of life prediction by finely quantifying the overall deviation between the fatigue life prediction results before and after compression. Indicated in At each moment, the absolute difference between the life prediction values ​​generated by the data before compression and the data after compression and restoration reflects the disturbance intensity of the compression behavior on the life prediction result of a single point. It plays a normalization role, avoiding the relative impact of the error being masked when the life value is large, and preventing the denominator from being zero by adding 1; the overall square of the ratio can amplify the impact of points with large deviation values ​​on the overall evaluation results, and increase the sensitivity to high-risk compression errors; taking the average of all moments can measure the breadth and persistence of the compression impact, reflecting its overall interference level in the entire mutation time segment; the outermost natural logarithm operation is used to compress the fluctuation range of the index, so that The values ​​are numerically smoother and more convergent while retaining the ability to respond to drastic changes. Through this calculation method, the platform can obtain a quantitative indicator of the compression effect that combines local sensitivity with overall stability.

[0037] Forecast drift sensitivity index The value of directly reflects the overall consistency of the fatigue life prediction results before and after compression in the mutation time segment, and it is positively correlated with "the impact of the current fatigue data storage compression strategy on the accuracy of fatigue life prediction". Specifically, when When the value is small, it means that the prediction results of the compressed and restored data and the original data after inputting into the fatigue life prediction model are highly close, and the compression process has little interference on the accuracy of life prediction, indicating that the current compression strategy has little effect on the prediction performance; on the contrary, when When the value is large, it means that there is a significant deviation between the prediction results before and after compression, indicating that the compression behavior loses or distorts key fatigue information in the mutation section, resulting in a significant deviation in life prediction. It is assessed that the compression strategy has a significant impact on the accuracy of life prediction. It can be used as an important metric to determine the quality and risk level of compression strategies.

[0038] In this embodiment, the logic for obtaining the compression and restoration error index is as follows: The model fitting modulus information is extracted from the preprocessed life assessment analysis information, including the equivalent modulus values ​​recorded in the original fatigue data before compression at different times in the mutation time segment, the equivalent modulus values ​​recorded in the fatigue data after compression restoration, and the theoretical modulus values ​​obtained by fitting the life prediction model, and are calibrated as , and , Indicates that within the mutation time period The equivalent modulus value recorded in the original fatigue data before compression, Indicates that within the mutation time period The equivalent modulus value recorded in the fatigue data after compression and restoration at each moment, Indicates that within the mutation time period The theoretical modulus value obtained by fitting the life prediction model at any time, , is a positive integer; In the mutation time section, the platform can process the original fatigue data before compression, the compression restoration data and the fitting results of the life prediction model in real time through the fatigue data monitoring and analysis system to obtain two key parameters: equivalent modulus value and theoretical modulus value. Specifically, the equivalent modulus value refers to the material stiffness index obtained by recording the stress response and strain response of a specified sampling position (such as the stress concentration area of ​​the conductor layer material) at each moment during the fatigue test, and using the stress-strain relationship in the elastic stage to perform numerical ratio calculation. Its unit is usually GPa, which can dynamically reflect the mechanical properties of the material in the current state; the platform extracts these two original variables in real time through the stress-strain data channel and performs ratio calculation to obtain the equivalent modulus value corresponding to the original data before compression. The equivalent modulus value after compression restoration is obtained by repeating the above stress-strain solution logic after restoring the compressed data. The platform inputs the restored stress and strain sequence into the modulus calculation module to obtain the modulus value corresponding to the original data structure for comparative analysis of its fidelity. The theoretical modulus value is a theoretical calculation result obtained by fitting the fatigue behavior of the material through the built-in life prediction model of the platform. During the model training phase, the platform uses historical fatigue test data to establish a life-modulus evolution relationship model (such as a modulus attenuation function based on the number of cycles, stress amplitude, etc.). After inputting the relevant working condition parameters in the mutation time segment (such as the current loading frequency, temperature, and load amplitude), the model can output the equivalent modulus value that the material should have in theory at each moment, as a reference value for evaluating whether the compressed and restored data deviates from the physical evolution trend. Through the platform's multi-channel data synchronization mechanism and model inference engine, the above three types of data can be dynamically acquired and structured archived moment by moment within the mutation time segment for subsequent error index calculation and strategy evaluation.

[0039] Calculate the compression restoration error index. The specific calculation formula is as follows: In the formula, is the compression-reduction error index, Indicates Moment The maximum value between 1 and Indicates Moment The maximum value between 0 and 1.

[0040] The compression-reduction error index The calculation formula of combines two types of key modulus difference calculation structures to comprehensively evaluate the dual effects of compression reduction treatment on the physical consistency of fatigue data in the mutation time segment and the credibility of model fitting. represents the compression reduction modulus Fitting modulus to life prediction model The relative square error between the two is used to measure whether the restored data deviates from the mechanical response trend expected by the material fatigue behavior model. The square term amplifies the larger deviation value, making it occupy a higher weight in the overall average, and the denominator is calculated through the maximum function This ensures that when the modulus value is small, the error is not amplified abnormally, which enhances the stability of the model fitness evaluation; the second term of the formula It is used to evaluate the compression reduction modulus and the original physical response modulus The logarithmic relative deviation between them, where the logarithmic function is used to smooth high-frequency errors to avoid mutations caused by local fluctuations on the overall error index. At the same time, the absolute value operation ensures that all deviations are positive inputs, reflecting the degree of consistency destruction of the compression restoration on the fidelity of the original data. Overall, this formula maintains a high sensitivity to severe data distortion and takes into account the stable response ability to continuity errors through the combination of "square difference + logarithmic difference", so that the compression restoration error index can fully reflect the comprehensive impact of the compression strategy on the quality of fatigue data.

[0041] Compression-Reduction Error Index There is a positive correlation between the value of and the "influence of the storage compression strategy of the current fatigue data on the accuracy of fatigue life prediction". When the value is small, it means that the difference between the equivalent modulus after compression reduction and the original modulus is small, and it is highly consistent with the theoretical modulus fitted by the life prediction model, indicating that the compression process has little effect on the physical integrity of the fatigue data and the fit of the model, and the life prediction results maintain a high accuracy. The compression strategy can be regarded as a low-impact strategy; when When the value is large, it indicates that the compression restoration data has a significant deviation in the mechanical response level, which not only fails to accurately restore the original modulus characteristics, but also significantly deviates from the model prediction trend, which can easily lead to distortion of life prediction results and reduced accuracy, indicating that the current compression strategy has a great interference with fatigue life prediction and is a high-impact strategy. Therefore, It can serve as an important basis for quantitatively judging the impact of compression strategy on the reliability of life prediction and provide support for subsequent strategy adjustment and optimization.

[0042] In this embodiment, the generated prediction offset sensitivity index and compression-reduction error index Construct a compression impact assessment model and generate the compression impact coefficient through weighted summation. The specific calculation formula is as follows: In the formula, is the compression influence coefficient, and The prediction offset sensitivity index is and compression-reduction error index The non-zero weight coefficient of .

[0043] The compression impact assessment model is implemented through the platform's built-in parameter fusion module. The system obtains the predicted offset sensitivity index and compression-reduction error index After that, the two indexes are linearly combined according to the preset weighting strategy to generate a compression impact coefficient for comprehensively determining the impact of the compression strategy. Among them, the two non-zero weight coefficients and Corresponding to and The evaluation contribution reflects the importance the system places on the two dimensions of "prediction accuracy deviation" and "physical and fitting distortion". The weight value is obtained by the platform during the model training phase through regression analysis or cross-validation optimization of a large number of historical samples to ensure that the model is consistent with the actual situation under different material types and working conditions. It can accurately reflect the actual impact of the compression strategy on fatigue life prediction. The platform supports the adaptive adjustment strategy of these two weights, so that they can be flexibly set according to the sensitive points of the current application scenario (such as the focus on prediction stability or physical consistency), while ensuring , to avoid distortion or bias affecting the credibility of the comprehensive index. The entire process is completed automatically by the software system without human intervention.

[0044] In this embodiment, the preset compression influence coefficient threshold interval is determined , and after determination, the generated compression influence coefficient A comparison is made, and the influence of the current fatigue data storage compression strategy on the fatigue life prediction accuracy is evaluated based on the comparison results. The specific comparison analysis is as follows: like ,The current storage compression strategy of fatigue data ,has a low impact on the accuracy of fatigue life prediction; This means that the fatigue data after compression and restoration are highly matched with the original data in terms of physical consistency and model prediction stability. The compression process does not cause loss or distortion of key information, and the life prediction model can still maintain accurate output when processing restored data. In this case, it means that the current compression strategy has good fidelity performance and prediction compatibility, and can be regarded as a low-impact strategy. It will not cause obvious interference to subsequent data analysis, model training or material evaluation. The platform can continue to use this compression parameter or algorithm for long-term data compression, which has high availability and stability.

[0045] like ,The current storage compression strategy of fatigue data ,has a moderate impact on the accuracy of fatigue life prediction; This situation shows that the compressed and restored data has a certain degree of difference in physical response or model fitting compared to the original data, but it has not reached a destructive or unacceptable level. The life prediction results may have a slight offset, but the overall trend is still of reference significance. This shows that the current compression strategy has achieved a balance between accuracy and compression efficiency, and is suitable for scenarios with moderate requirements for prediction accuracy but limited storage resources. The platform can flexibly decide whether to adjust the compression strategy locally according to different task objectives, or adopt differentiated compression processing solutions to reduce the cumulative impact of moderate offsets.

[0046] like ,The current storage compression strategy of fatigue data has a high impact on the ,accuracy of fatigue life prediction.

[0047] This situation shows that the compressed and restored data has shown significant deviations in the two dimensions of physical modulus restoration and life prediction fitting, resulting in a decrease in the prediction accuracy of the model, which may misjudge the fatigue life trend, bringing the risk of distorted evaluation results or even wrong decisions. This high impact reflects that the current compression strategy fails to effectively retain key data features in the mutation section and is not suitable as a standard compression method in the material database. At this time, the platform should immediately trigger the adjustment mechanism of the compression strategy, trace back the data quality, and reconfigure the compression parameters or switch to a high-precision compression scheme to ensure the reliability of fatigue data and the effectiveness of subsequent analysis.

[0048] The compression strategy adjustment module adjusts the data compression strategy for the mutation time segment according to the evaluation results and different impact levels; In this embodiment, in the compression strategy adjustment module, according to the evaluation results, the data compression strategy of the mutation time segment is adjusted according to different impact levels, specifically including: If the evaluation result is low impact, the adjustment of the data compression strategy for the mutation time segment is as follows: keep the current compression strategy unchanged and maintain the original compression parameter configuration; When the platform assessment result is a low impact level, the system determines that the current compression and restoration strategy has achieved a high degree of consistency in retaining the key features of fatigue data, and the prediction results are accurate and reliable, so there is no need to modify the existing compression strategy. In this case, the software platform uses the judgment logic in the compression strategy control module to call the processing path of "impact level = low", automatically skips the compression parameter modification process, keeps the current compression algorithm unchanged, and locks the current compression parameter configuration file. During the data scheduling process, the module can also label the section as "compression stable" as a basis for automatic inheritance of future compression strategy templates. This setting helps save computing resources and avoids the decrease in compression efficiency caused by excessive adjustments, while ensuring the compression stability and consistency of areas where the assessment accuracy has reached the standard.

[0049] If the evaluation result is a medium impact, the data compression strategy for the mutation time segment is adjusted as follows: the compression ratio in the current compression parameter is reduced to within the preset reduction range of the original value, and the redundant data verification mechanism is enabled to enhance the restoration accuracy; When the compression impact is judged to be medium, the platform will automatically adjust the compression ratio parameter corresponding to the mutation time segment to the preset safety threshold (such as 80% to 90% of the original value) through the parameter scheduling interface. This range can be configured in advance as a dynamic table in the system. Before the policy is updated, the software platform first calls the predefined medium impact processing template in the "Compression Policy Template Management Module" to numerically reduce the current compression ratio and synchronously update the policy mapping table; then the system enables the "Redundant Data Verification Module" to improve the robustness of data restoration by adding mirror points or periodic error check bits to specific sampling points during the compression process, ensuring that key sections are still controllable under high compression conditions. The core of this strategy is to improve prediction accuracy without significantly sacrificing compression efficiency. It is suitable for typical scenarios where data accuracy and storage pressure need to be balanced.

[0050] If the assessment result is a high impact, the specific adjustments to the data compression strategy for the mutation time segment are: replace it with an accuracy-first compression algorithm, enable lossless compression mode, and turn off the automatic inheritance function of compression parameters to ensure the complete retention of key fatigue information.

[0051] In the case of a high impact assessment, the system will determine that the current compression strategy has seriously affected the restoration quality and prediction reliability of fatigue data, and a strong intervention level strategy replacement must be performed. In this case, the software platform automatically switches the compression engine to "accuracy priority mode", calls high-precision or lossless compression algorithms (such as point-by-point difference compression, data mirroring compression, etc.), and switches the compression method of the mutation segment from standard mode to lossless compression channel. In the system compression parameter scheduling logic, by disabling the "parameter automatic inheritance switch", the current high-impact compression parameters are prevented from being used in adjacent or subsequent data segments to avoid mistransmission and misjudgment. This strategy can maximize the retention of physical response curves near key mutation points, ensuring the reliability of the database in high-precision demand scenarios such as fatigue life prediction and crack propagation modeling. It is a necessary protection measure for high-risk data segments.

[0052] The strategy adaptive optimization module combines the fatigue life prediction results and experimental verification feedback to track and backtrack the storage strategy of the mutation time segment, adjust and update the compression processing logic according to the prediction error, and continuously monitor the changing trend of the fatigue performance of lightweight power cables, so that the storage strategy has adaptive optimization capabilities.

[0053] The implementation of the strategy adaptive optimization module relies on the platform's multi-source data fusion and strategy dynamic scheduling mechanism, which mainly includes three key steps: the first step is to continuously generate life prediction results for the data of the mutation time segment through the life prediction module, and compare it with the actual experimental verification data to automatically calculate the historical prediction error; the error can be archived as the "strategy execution effect score" of a specific segment and bound to the specific compression parameter configuration through the strategy tracking interface. The second step is that the platform calls the strategy backtracking mechanism based on the score to quickly retrieve the historical segments using the same compression strategy. Once it is found that the prediction error of multiple segments under this strategy exceeds the set threshold, the reconfiguration process of the compression processing logic is triggered. The system will update the parameters in the original compression template in real time, or replace the compression strategy with a version with stronger error control capability. The third step is that the built-in fatigue behavior trend analysis module of the platform is responsible for continuously monitoring the fatigue performance change trend of the cable in long-term operation. If a mutation is detected in parameters such as the modulus drop rate and the strain abnormality frequency, the system will automatically determine that the material service state has changed, and re-plan the storage strategy configuration in combination with the historical strategy and the current performance characteristics to ensure that it is updated synchronously with the dynamic evolution of the material state.

[0054] The setting of the strategy adaptive optimization module is to solve the fundamental limitation of the traditional compression strategy of "static configuration and inability to self-correct". In the existing platform, even if the initial setting of the compression strategy is reasonable, if the compression effect and model prediction error are not continuously monitored during the actual operation, it may cause the local data to continue to deteriorate and the system cannot perceive it, thereby affecting the stability of the life prediction and the credibility of the data quality of the entire database. By introducing the strategy adaptive optimization mechanism, the platform can establish a closed-loop logic of "prediction accuracy feedback" and "compression strategy evolution", which not only realizes the a posteriori correction and self-evolution of the compression scheme, but also can adapt to the changes in the behavior pattern of lightweight power cables due to fatigue accumulation in the service environment. In addition, incorporating the changing trend of fatigue performance into the strategy judgment basis can further enhance the system's response ability to the aging behavior of sudden materials, and make data compression and model prediction work together, so as to achieve an intelligent balance between data quality control, compression efficiency and prediction accuracy.

[0055] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0056] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center by wired or wireless (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a tape), an optical medium (for example, a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0057] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0058] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0059] In the several embodiments provided in the present application, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0060] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0061] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0062] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. Lightweight power cable material property database and analysis platform, characterized by: It includes compression configuration initialization module, mutation time segment identification module, compression impact assessment module, compression strategy adjustment module and strategy adaptive optimization module; The compression configuration initialization module analyzes the fatigue behavior characteristics of lightweight power cables and establishes corresponding fatigue data storage compression configuration strategies based on material type, service conditions and historical fatigue data; The mutation time segment identification module identifies the mutation points in the stored fatigue data through the behavior recognition method, and determines the corresponding time range with the mutation point as the center, and marks it as the mutation time segment; The compression impact assessment module analyzes the fatigue data of lightweight power cables in the mutation time section and evaluates the impact of the current fatigue data storage compression strategy on the accuracy of fatigue life prediction; The compression strategy adjustment module adjusts the data compression strategy for the mutation time segment according to the evaluation results and different impact levels; The strategy adaptive optimization module combines the fatigue life prediction results and experimental verification feedback to track and backtrack the storage strategy of the mutation time segment, adjust and update the compression processing logic according to the prediction error, and continuously monitor the changing trend of the fatigue performance of lightweight power cables.

2. The lightweight power cable material property database and analysis platform according to claim 1 is characterized in that: In the mutation time segment identification module, based on the changing trend of the stored lightweight power cable fatigue data, a behavioral recognition method including first-order derivative mutation detection, curvature change analysis and local fitting residual abnormality recognition is adopted to detect the nonlinear change points in the fatigue curve to determine the position of the mutation point. With the mutation point as the center, combined with the data sampling period and performance change density, the time window of the preset range is extended forward and backward, and the covered time range is calibrated as the mutation time segment.

3. The lightweight power cable material property database and analysis platform according to claim 2 is characterized in that: In the compression impact assessment module, a fatigue life prediction model is constructed based on the fatigue data of lightweight power cables in the mutation time section, and life prediction is performed on the original fatigue data before compression and the compressed and restored fatigue data respectively to generate life assessment analysis information, which is then preprocessed after generation; life prediction result information and model fitting modulus information are extracted from the preprocessed life assessment analysis information, and analyzed after extraction to generate a prediction offset sensitivity index and a compression restoration error index respectively; a compression impact assessment model is constructed for the generated prediction offset sensitivity index and compression restoration error index, and a compression influence coefficient is generated by weighted summation; a pre-set compression influence coefficient threshold range is determined, and compared with the generated compression influence coefficient after determination, and the degree of influence of the current fatigue data storage compression strategy on the accuracy of fatigue life prediction is evaluated according to the comparison result.

4. The lightweight power cable material property database and analysis platform according to claim 3 is characterized in that: The acquisition logic of the prediction offset sensitivity index is as follows: The life prediction result information is extracted from the preprocessed life assessment analysis information, including the fatigue life prediction values ​​generated by taking the original fatigue data before compression as the input of the fatigue life prediction model at different times in the mutation time segment and the fatigue life prediction values ​​generated by taking the fatigue data after compression and restoration as the input of the fatigue life prediction model, and they are calibrated as and , Indicates that within the mutation time period The fatigue life prediction value generated by using the original fatigue data before time compression as the input of the fatigue life prediction model, Indicates that within the mutation time period The fatigue life prediction value generated by using the fatigue data after compression and restoration as the input of the fatigue life prediction model is , is a positive integer; Calculate the prediction offset sensitivity index. The specific calculation formula is as follows: In the formula, is the prediction offset sensitivity index.

5. The lightweight power cable material property database and analysis platform according to claim 4 is characterized in that: The logic for obtaining the compression and restoration error index is as follows: The model fitting modulus information is extracted from the preprocessed life assessment analysis information, including the equivalent modulus values ​​recorded in the original fatigue data before compression at different times in the mutation time segment, the equivalent modulus values ​​recorded in the fatigue data after compression restoration, and the theoretical modulus values ​​obtained by fitting the life prediction model, and are calibrated as , and , Indicates that within the mutation time period The equivalent modulus value recorded in the original fatigue data before compression, Indicates that within the mutation time period The equivalent modulus value recorded in the fatigue data after compression and restoration at each moment, Indicates that within the mutation time period The theoretical modulus value obtained by fitting the life prediction model at any time, , is a positive integer; Calculate the compression restoration error index. The specific calculation formula is as follows: In the formula, is the compression-reduction error index, Indicates Moment The maximum value between 1 and Indicates Moment The maximum value between 0 and 1.

6. The lightweight power cable material property database and analysis platform according to claim 5 is characterized in that: Sensitivity index to generated prediction deviation and compression-reduction error index Construct a compression impact assessment model and generate the compression impact coefficient through weighted summation. The specific calculation formula is as follows: In the formula, is the compression influence coefficient, and The prediction offset sensitivity index is and compression-reduction error index The non-zero weight coefficient of .

7. The lightweight power cable material property database and analysis platform according to claim 6 is characterized in that: Determine the preset compression impact coefficient threshold interval , and after determination, the generated compression influence coefficient A comparison is made, and the influence of the current fatigue data storage compression strategy on the fatigue life prediction accuracy is evaluated based on the comparison results. The specific comparison analysis is as follows: like ,The current storage compression strategy of fatigue data ,has a low impact on the accuracy of fatigue life prediction; like ,The current storage compression strategy of fatigue data ,has a moderate impact on the accuracy of fatigue life prediction; like ,The current storage compression strategy of fatigue data has a high impact on the ,accuracy of fatigue life prediction.

8. The lightweight power cable material property database and analysis platform according to claim 7 is characterized in that: In the compression strategy adjustment module, according to the evaluation results and different impact levels, the data compression strategy for the mutation time segment is adjusted, including: If the evaluation result is low impact, the adjustment of the data compression strategy for the mutation time segment is as follows: keep the current compression strategy unchanged and maintain the original compression parameter configuration; If the evaluation result is a medium impact, the data compression strategy for the mutation time segment is adjusted as follows: the compression ratio in the current compression parameter is reduced to within the preset reduction range of the original value, and the redundant data verification mechanism is enabled to enhance the restoration accuracy; If the assessment result is a high impact, the specific adjustments to the data compression strategy for the mutation time segment are: replace it with an accuracy-first compression algorithm, enable lossless compression mode, and turn off the automatic inheritance function of compression parameters.

Images