A method and system for predicting the service life of a laser power supply

Abstract

The present invention discloses a method and system for predicting the life of a laser power supply, belonging to the field of power supply life prediction. The method includes: obtaining a plurality of historical operating parameters and a plurality of real-time operating parameters; determining a first set of operating influence characteristics based on the plurality of historical operating parameters, screening the first set of operating influence characteristics to determine a second set of operating influence characteristics; constructing a life prediction model, synchronizing the second set of operating influence characteristics to the life prediction model to obtain a predicted life value; performing a life prediction evaluation on the laser power supply, performing feedback optimization on the life prediction model to generate an optimized life prediction model; and performing adaptive life prediction on the laser power supply through the optimized life prediction model. This application solves the technical problems of low accuracy and poor adaptability in predicting the life of a laser power supply in the prior art, and achieves the technical effects of improving the accuracy and adaptability of predicting the life of a laser power supply.

Description

Technical Field

[0001] The present invention relates to the field of power supply life prediction, and particularly to a method and system for predicting the life of a laser power supply. Background Art

[0002] As a core component of laser processing equipment, the life of a laser power supply directly affects the reliability and production efficiency of the equipment. Accurately predicting the life of a laser power supply is of great significance for equipment maintenance, production planning, and cost control. However, the existing prediction of the life of a laser power supply only depends on the usage time of the power supply and cannot comprehensively reflect the operating state of the equipment, making it difficult to capture the performance changes of the laser power supply under different working conditions and resulting in low accuracy of the prediction results. In addition, the existing prediction models usually adopt fixed feature sets and prediction strategies and lack the ability to self-adjust according to new data and prediction results, resulting in insufficient adaptability of the prediction models when facing changes in equipment status. Therefore, the accuracy of predicting the life of a laser power supply in the prior art is not high and the adaptability is poor. Summary of the Invention

[0003] This application provides a method and system for predicting the life of a laser power supply, aiming to solve the technical problems of low accuracy and poor adaptability in predicting the life of a laser power supply in the prior art.

[0004] In view of the above problems, this application provides a method and system for predicting the life of a laser power supply.

[0005] In the first aspect disclosed in this application, a method for predicting the life of a laser power supply is provided. The method includes: retrieving the operation data record log of the laser power supply to obtain a plurality of historical operation parameters; performing real-time acquisition on the laser power supply through a data sensing unit to obtain a plurality of real-time operation parameters; performing impact analysis based on the plurality of historical operation parameters to determine a first set of operation impact characteristics, performing correlation analysis based on the plurality of real-time operation parameters in combination with the first set of operation impact characteristics, screening the first set of operation impact characteristics according to the analysis results to determine a second set of operation impact characteristics; constructing a life prediction model, synchronizing the second set of operation impact characteristics to the life prediction model to obtain a predicted life value; performing life prediction evaluation on the laser power supply based on the predicted life value, performing feedback optimization on the life prediction model according to the evaluation results to generate an optimized life prediction model; and performing adaptive life prediction on the laser power supply through the optimized life prediction model.

[0006] Another aspect disclosed in this application provides a laser power supply life prediction system, which includes: a historical data acquisition module for retrieving the operation data record log of the laser power supply to obtain multiple historical operation parameters; a real-time data acquisition module for performing real-time acquisition of the laser power supply through a data sensing unit to obtain multiple real-time operation parameters; a feature analysis and screening module for performing impact analysis based on multiple historical operation parameters to determine a first set of operation impact features, performing correlation analysis based on multiple real-time operation parameters in combination with the first set of operation impact features, and screening the first set of operation impact features according to the analysis results to determine a second set of operation impact features; a prediction model construction module for constructing a life prediction model, synchronizing the second set of operation impact features to the life prediction model to obtain a predicted life value; a prediction evaluation and optimization module for performing life prediction evaluation on the laser power supply based on the predicted life value, and performing feedback optimization on the life prediction model according to the evaluation results to generate an optimized life prediction model; and a life prediction execution module for performing adaptive life prediction on the laser power supply through the optimized life prediction model.

[0007] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0008] By retrieving the operation data record log of the laser power supply to obtain multiple historical operation parameters, historical information is provided for subsequent analysis and model training; real-time acquisition of the laser power supply is performed through a data sensing unit to obtain multiple real-time operation parameters, and by obtaining the current operation status information of the laser power supply, it is ensured that the prediction model can be analyzed based on the latest equipment conditions; impact analysis is performed based on multiple historical operation parameters to determine a first set of operation impact features, correlation analysis is performed based on multiple real-time operation parameters in combination with the first set of operation impact features, and the first set of operation impact features is screened according to the analysis results to determine a second set of operation impact features. Through the comprehensive analysis of historical data and real-time data, the most representative and predictive features are selected, improving the accuracy and efficiency of subsequent predictions; a life prediction model is constructed, the second set of operation impact features is synchronized to the life prediction model to obtain a predicted life value, providing a basis for subsequent optimization; life prediction evaluation is performed on the laser power supply based on the predicted life value, and feedback optimization is performed on the life prediction model according to the evaluation results to generate an optimized life prediction model. By evaluating the prediction results, the model is optimized, improving the accuracy and reliability of the prediction model; adaptive life prediction of the laser power supply is performed through the optimized life prediction model, realizing the adaptive prediction of the model, enabling the prediction results to be continuously adjusted as the equipment status and environment change, and improving the long-term accuracy and adaptability of the prediction. The technical solution solves the technical problems of low accuracy and poor adaptability in the life prediction of laser power supplies in the prior art, and achieves the technical effect of improving the accuracy and self-adaptability of the life prediction of laser power supplies.

[0009] The above description is only an overview of the technical solution of the present application. In order to be able to more clearly understand the technical means of the present application, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features and advantages of the present application more obvious and understandable, the following specifically illustrates the specific implementation manners of the present application. Brief Description of the Drawings

[0010] Figure 1 FIG. is a schematic flow chart of a method for predicting the life of a laser power supply provided by an embodiment of the present application;

[0011] Figure 2 FIG. is a schematic structural diagram of a system for predicting the life of a laser power supply provided by an embodiment of the present application.

[0012] Description of the reference numerals: historical data acquisition module 11, real-time data acquisition module 12, feature analysis and screening module 13, prediction model construction module 14, prediction evaluation and optimization module 15, life prediction execution module 16. Detailed Description of the Preferred Embodiments

[0013] The general idea of the technical solution provided by the present application is as follows:

[0014] An embodiment of the present application provides a method and system for predicting the life of a laser power supply. By fusing historical data and real-time data, combining dynamic feature analysis and model optimization, the accuracy and adaptability of the prediction are improved, and the adaptive prediction of the life of the laser power supply is realized.

[0015] First, by retrieving historical operating parameters and real-time operating parameters, a comprehensive data foundation is established. On this basis, multi-level feature analysis and screening are carried out, including the impact analysis of historical operating parameters and the correlation analysis of real-time operating parameters, so as to determine the most representative second set of operating impact features, effectively improving the pertinence and accuracy of subsequent predictions. Subsequently, a life prediction model is constructed, and through the evaluation and feedback optimization of the prediction results, a more accurate life prediction optimization model is generated. Then, the life prediction optimization model is used for adaptive life prediction, so that the prediction results can be continuously adjusted as the device state and environment change.

[0016] After introducing the basic principle of the present application, the following will specifically introduce various non-limiting implementation manners of the present application in conjunction with the drawings of the specification.

[0017] Embodiment 1, as Figure 1 shown, an embodiment of the present application provides a method for predicting the life of a laser power supply, the method comprising:

[0018] S1: Retrieving the operation data record log of the laser power supply to obtain a plurality of historical operating parameters.

[0019] Specifically, during the operation of the laser power supply, various sensors and monitoring devices inside it will record in real time various parameters reflecting the operating state, such as voltage, current, temperature, optical power, usage duration, etc., and store these parameter data in the operating data record log. By accessing and reading the operating data record log, historical operating parameters for a period of time can be obtained to describe the past operating state and performance of the laser power supply, comprehensively reflecting the operating conditions of the laser power supply under different periods and different working conditions, laying a good data foundation for accurately predicting the lifespan.

[0020] S2: Perform real-time acquisition on the laser power supply through the data sensing unit to obtain multiple real-time operating parameters.

[0021] Specifically, the data sensing unit is a hardware module used to collect the operating data of the laser power supply in real time, and it is usually connected to the control system of the laser power supply. Various types of sensors are integrated inside the data sensing unit, such as voltage sensors, current sensors, temperature sensors, optical power sensors, etc., which can detect various operating indicators of the laser power supply in real time. At the same time, the data sensing unit has the functions of data processing and communication, can preliminarily process the collected data, and transmit it to the host computer or server by wired or wireless means. The data sensing unit samples the operating state of the laser power supply at a certain frequency to obtain a series of real-time operating parameters reflecting its current working conditions.

[0022] Perform real-time acquisition on the laser power supply through the data sensing unit to obtain multiple real-time operating parameters reflecting its current operating state, providing important data support for the lifespan prediction of the laser power supply.

[0023] S3: Conduct impact analysis based on the multiple historical operating parameters to determine the first set of operating impact characteristics. Conduct correlation analysis based on the multiple real-time operating parameters in combination with the first set of operating impact characteristics, and screen the first set of operating impact characteristics according to the analysis results to determine the second set of operating impact characteristics.

[0024] Specifically, first, an impact analysis is conducted based on multiple historical operating parameters. The so-called impact analysis refers to studying the correlation and causal relationship between each historical operating parameter and the life of the laser power supply through statistical methods and machine learning algorithms, so as to determine the degree of influence of each parameter on the life. Through the impact analysis, a subset of parameters that is highly correlated with the life is selected from numerous historical operating parameters, called the first operating impact feature set, which reflects the key factors affecting the life of the laser power supply and is the key object for subsequent prediction. On this basis, further combined with real-time operating parameters, a correlation analysis is carried out on the first operating impact feature set. The correlation analysis refers to studying the mutual relationship between real-time operating parameters and each feature quantity in the first operating impact feature set, and judging the similarity and consistency of the parameters during the dynamic change process. By calculating the correlation coefficient between real-time operating parameters and each feature quantity, the change trend and law are found, and based on this, the first operating impact feature set is further screened and optimized to obtain the second operating impact feature set. The second operating impact feature set not only retains the factors with significant influence on the life, but also takes into account the dynamic characteristics of these factors in actual operation, and has higher representativeness and applicability.

[0025] Through the impact analysis and correlation analysis, the dimensionality reduction and feature extraction of operating parameters are achieved, and a set of key feature sets that can effectively reflect the life of the laser power supply, that is, the second operating impact feature set, is obtained. The complementary nature of historical data and real-time data is fully utilized, taking into account both long-term influencing factors and short-term dynamic changes, providing the optimal input for the subsequent life prediction model, thereby improving the prediction accuracy and reliability.

[0026] S4: Construct a life prediction model, synchronize the second operating impact feature set to the life prediction model, and obtain the predicted life value.

[0027] Specifically, first, according to the data type and distribution characteristics of the second operation impact feature set, select a suitable machine learning algorithm or deep learning framework, such as support vector machine, random forest, neural network, etc. Then, construct a training set and a test set based on the historical operation parameters and the corresponding life data, where the training set is used for model learning and fitting, and the test set is used for model verification and evaluation. Next, use the training set data to train and optimize the selected algorithm model, and adjust the hyperparameters and structure of the model so that it can capture the intrinsic connection between the features and the life as accurately as possible. After that, use the test set data to test and evaluate the trained model, and measure the performance and generalization ability of the model by calculating the error and correlation indicators between the predicted life and the actual life. When the life prediction model is built, it can be applied to the actual life prediction task. Specifically, the obtained second operation impact feature set is input into the trained model, and the model automatically calculates and outputs the corresponding predicted life value, which reflects the remaining use time of the laser power supply in the current state.

[0028] S5: Performing lifetime prediction evaluation on the laser power source based on the predicted lifetime value, performing feedback optimization on the lifetime prediction model according to the evaluation result, and generating a lifetime prediction optimization model.

[0029] Specifically, first, based on the life cycle experiment of the laser power supply, its real failure life data is obtained as a reference standard for evaluating the life prediction model. The so-called life cycle experiment refers to an accelerated aging test of the laser power supply sample in an environment similar to the actual working conditions, recording the whole process data from the initial state to the final failure, and taking the cumulative working time at the time of failure as its real life. Then, the predicted life value of the life prediction model on the same sample is compared with the real life value, and the error between the two, that is, the prediction error value, is calculated. By analyzing the distribution characteristics and change trends of the prediction error value, the prediction deviation and stability of the current model are judged. If the prediction error value exceeds the preset acceptable range, it means that the performance of the current model is not ideal and needs to be optimized and improved in a targeted manner. For example, adjust the structure and parameters of the model, such as increasing or decreasing the number of hidden layers, the number of neurons, changing the activation function and the loss function, etc.; select a better feature subset and eliminate redundant or irrelevant features; introduce new data sources to expand the number and diversity of training samples; improve the training method of the model, such as using cross-validation, ensemble learning and other techniques. Through continuous iterative optimization, a life prediction model with better performance and stronger generalization ability is obtained, namely, the life prediction optimization model.

[0030] Through life cycle experimental data and prediction error analysis, the constructed life prediction model is comprehensively evaluated and optimized, which not only improves the prediction accuracy and robustness of the model, but also enhances the model's ability to adapt to complex working conditions.

[0031] S6: Perform adaptive life prediction on the laser power supply through the optimized life prediction model.

[0032] Specifically, in an online monitoring manner, continuously collect various parameter data during the operation of the laser power supply and transmit it to the optimized life prediction model. The optimized life prediction model first preprocesses and extracts features from the received real-time data to obtain a feature vector that matches the model input. Then, based on the learned feature-life mapping relationship, the optimized life prediction model calculates the predicted life value corresponding to the current feature vector as the evaluation result of the current health state of the laser power supply, realizing the adaptive life prediction of the laser power supply.

[0033] Through the optimized life prediction model, perform real-time and online life prediction on the laser power supply, realize continuous evaluation and tracking of the remaining life of the laser power supply, and improve the accuracy and adaptability of the life prediction of the laser power supply.

[0034] Furthermore, the embodiments of the present application further include:

[0035] Clean the multiple historical operation parameters to generate multiple historical operation standard parameters;

[0036] Perform statistical analysis based on the multiple historical operation standard parameters to determine the parameter distribution characteristics;

[0037] Perform univariate analysis on the multiple historical operation standard parameters according to the parameter distribution characteristics to generate a first analysis result;

[0038] Perform multivariate analysis on the multiple historical operation standard parameters according to the parameter distribution characteristics to generate a second analysis result;

[0039] Select influencing features according to the first analysis result and the second analysis result to determine the first set of operation influencing features.

[0040] In a feasible implementation manner, first, data cleaning is performed on multiple historical operation parameters to generate multiple historical operation standard parameters. Among them, data cleaning includes checking and processing problems such as outliers and missing values in the historical operation parameters to ensure the accuracy and consistency of the data. After completing the data cleaning, the data is standardized by methods such as min-max standardization and z-score standardization to eliminate the differences in dimension and numerical range between different parameters. The standardized parameters are historical operation standard parameters, laying a foundation for subsequent analysis. Secondly, statistical analysis is performed on the obtained multiple historical operation standard parameters. Statistical analysis includes calculating various statistics of each parameter, such as mean, median, standard deviation, etc., to describe the central tendency and dispersion degree of the parameters; drawing frequency distribution diagrams and probability density curves of the parameters to analyze the distribution type of the parameters; calculating the correlation coefficient matrix between the parameters to reveal the correlation between the parameters. Through statistical analysis, the inherent statistical characteristics of the historical operation standard parameters are accurately characterized, providing a basis for subsequent modeling analysis.

[0041] Next, make full use of the parameter distribution characteristics and perform univariate analysis on each parameter. Univariate analysis mainly includes methods such as correlation analysis, regression analysis, variance analysis, and information theory analysis. By calculating the correlation coefficient between the parameter and the lifespan, judge the strength and direction of the correlation between each parameter and the lifespan. For example, establish a regression model between the parameter and the lifespan, fit the functional relationship between each parameter and the lifespan, evaluate the goodness of fit and significance of the model, compare the mean differences of the parameters at different lifespan levels, and judge whether the influence of the parameter on the lifespan is significant. Through univariate analysis, a subset of parameters with relatively high correlation with the lifespan can be initially screened out, revealing the influence law of each parameter on the lifespan, providing a basis for further multivariate analysis, and thus obtaining the first analysis result. Then, on the basis of univariate analysis, further consider the interaction and combined effects between the parameters, and comprehensively evaluate the influence law of multiple parameters on the lifespan of the laser power supply. Utilize the parameter distribution characteristics and adopt various common multivariate analysis methods, such as multiple regression, principal component analysis, partial least squares regression, etc., to establish a multivariate relationship model between the parameters and the lifespan. Compared with univariate analysis, multivariate analysis considers the correlation and interaction between the parameters, overcomes the limitations of univariate analysis, can reveal the internal structure and combined mode between the parameters, and discovers the most critical combination of influencing factors. The relationship model between the parameter combination and the lifespan obtained by multivariate analysis reflects the comprehensive influence law of multiple parameters on the lifespan, which is the second analysis result. Subsequently, combining the first analysis result and the second analysis result, preferentially select the parameters that are highly correlated with the lifespan and have a significant influence on the lifespan, and avoid selecting redundant parameters, thereby determining the first set of operation influence characteristics.

[0042] Furthermore, the embodiments of the present application further include:

[0043] Align the multiple real-time operating parameters in time according to the multiple historical operating parameters to generate multiple real-time aligned operating parameters;

[0044] Sort the multiple real-time aligned operating parameters in descending order according to the first set of operating influence characteristics to construct an operating parameter influence list;

[0045] Perform weighted calculation on the first set of operating influence characteristics based on the operating parameter influence list to generate multiple weight correlation coefficients, where the multiple weight correlation coefficients include multiple correlation directions and multiple correlation levels;

[0046] Add the multiple correlation directions and the multiple correlation levels to the analysis result.

[0047] In a feasible implementation manner, first, align the multiple real-time operating parameters in time according to the multiple historical operating parameters to generate multiple real-time aligned operating parameters. Specifically, time alignment means that if there are deviations or inconsistencies in the timestamps of the real-time operating parameters and the historical operating parameters, appropriate processing is required to ensure that when performing correlation analysis, the real-time data at each time point can be accurately matched and corresponded to the corresponding historical data. Through time alignment, the differences in sampling frequency, time accuracy, etc. between the real-time data and the historical data are eliminated to achieve synchronization and consistency, providing a unified time benchmark for subsequent correlation calculations. Then, sort the multiple real-time aligned operating parameters in descending order according to the first set of operating influence characteristics to construct an operating parameter influence list. The operating parameter influence list is used to quantitatively describe the influence intensity of each influence characteristic on the parameters under the current operating condition, providing a basis for subsequent weighted analysis. Specifically, the real-time aligned operating parameters are sorted in descending order according to the importance score or weight size of each characteristic in the first set of operating influence characteristics. The characteristic with the greatest influence intensity is ranked at the front, and the characteristic with the smallest influence intensity is ranked at the end.

[0048] Next, based on the operating parameter impact list, weighted calculation is performed on the first operating impact feature set to generate multiple weight correlation coefficients. During the calculation process, features with greater impact intensity are assigned higher weights, and features with smaller impact intensity are assigned lower weights. For example, according to the sorting positions of the features in the impact list, methods such as exponential decay and power-law decay are used to allocate weights, so that features with a higher ranking obtain higher weights. Then, weighted correlation calculation is performed between each real-time aligned operating parameter and each impact feature to obtain multiple weight correlation coefficients. Among them, each weight correlation coefficient contains two important attributes: the correlation direction and the correlation level. The correlation direction indicates the positive or negative correlation relationship between the impact feature and the operating parameter; the correlation level indicates the strength of the correlation between the impact feature and the operating parameter, for example, it is divided into strong correlation, medium correlation, weak correlation, etc. After that, the calculated multiple correlation directions and multiple correlation levels are added to the analysis result to obtain the analysis result.

[0049] Furthermore, the embodiments of the present application further include:

[0050] Calculating the weight coefficient of the first operating impact feature set based on the operating parameter impact list in combination with the expert scoring method;

[0051] Obtaining a correlation coefficient matrix by calculating the correlation coefficients of the first operating impact feature set using statistical analysis methods;

[0052] Multiplying the weight coefficient of the first operating impact feature set by the correlation coefficient matrix to generate the multiple weight correlation coefficients;

[0053] Dividing the correlation direction according to the positive and negative values of the multiple weight correlation coefficients to generate multiple correlation directions;

[0054] Dividing the correlation level according to the absolute values of the multiple weight correlation coefficients to generate multiple correlation levels;

[0055] Adding the multiple correlation directions and the multiple correlation levels to the multiple weight correlation coefficients.

[0056] In a preferred embodiment, first, according to the sorting positions of the features in the operating parameter impact list, experts in the relevant field are invited to score the importance of each feature in the first operating impact feature set. Then, expert scoring methods such as the Delphi method or the analytic hierarchy process are used to synthesize the scoring results of multiple experts to obtain the weight coefficient of each feature, which not only considers the objective sorting driven by data but also incorporates the subjective judgment of expert experience, and can more comprehensively reflect the actual importance of each feature. Then, statistical methods such as the Pearson correlation coefficient and the Spearman rank correlation coefficient are used to calculate the correlation coefficients between the features in the first operating impact feature set. All the calculated correlation coefficients are arranged according to the feature correspondence to form a correlation coefficient matrix, which comprehensively describes the correlation structure within the feature set. Next, matrix multiplication is performed on the obtained weight coefficient and the obtained correlation coefficient matrix, considering both the importance of the features and the correlation between the features. The obtained weight correlation coefficient can more accurately reflect the comprehensive impact degree of each feature on the life of the laser power supply.

[0057] After that, for each weight correlation coefficient, if its value is greater than zero, it is determined to be positively correlated; if its value is less than zero, it is determined to be negatively correlated; if its value is equal to zero, it is determined to be uncorrelated, so as to clearly distinguish the impact direction between each feature and the life of the laser power supply, providing an important qualitative basis for subsequent life prediction. Next, the correlation levels are divided. For example, the threshold method is used to divide the correlation levels. Two thresholds a and b are preset (where 0 < a < b < 1). When the absolute value of the weight correlation coefficient is less than a, it is determined to be weakly correlated; when the absolute value is greater than or equal to a and less than b, it is determined to be moderately correlated; when the absolute value is greater than or equal to b, it is determined to be strongly correlated. Subsequently, the obtained multiple correlation directions and the obtained multiple correlation levels are associated with the corresponding weight correlation coefficients, providing a comprehensive and rich information basis for subsequent feature screening and model construction.

[0058] Furthermore, the embodiments of the present application further include:

[0059] Performing positive correlation screening on the first operating impact feature set based on the multiple correlation directions to generate a first screened feature set;

[0060] Performing strong correlation screening on the first operating impact feature set based on the multiple correlation levels to generate a second screened feature set;

[0061] Performing data intersection extraction according to the first screened feature set and the second screened feature set to obtain a screened feature intersection;

[0062] Performing screening on the first operating impact feature set based on the screened feature intersection to determine the second operating impact feature set.

[0063] In a feasible implementation, first, analyze the correlation directions corresponding to the weight correlation coefficients. Select the features with a positive correlation, that is, the features for which the laser power supply life increases correspondingly as the eigenvalue increases, to form the first screened feature set, which includes all the features that are positively correlated with the laser power supply life. At the same time, select the features with a strong correlation, that is, the features that are highly correlated with the laser power supply life, to form the second screened feature set, which includes all the features that are strongly correlated with the laser power supply life regardless of their correlation directions. Subsequently, perform an intersection operation on the obtained first screened feature set and the obtained second screened feature set to obtain a feature subset that satisfies both the positive correlation and strong correlation conditions, and obtain the screened feature intersection. Through intersection extraction, the feature range is further narrowed, the most representative and predictive features are retained, the feature dimension is effectively reduced, redundant information is reduced, and the efficiency and accuracy of the subsequent prediction model are improved. After that, use the obtained screened feature intersection as the screening basis to finally screen the original first operating influence feature set, and retain the features that are both in the first operating influence feature set and in the screened feature intersection to form the second operating influence feature set, ensuring that the finally selected features not only have a strong positive correlation but also have an important position in the original feature set, providing high-quality input features for the subsequent life prediction model, thereby improving the accuracy and reliability of the laser power supply life prediction.

[0064] Further, the embodiments of the present application further include:

[0065] Conduct a life cycle experiment based on the laser power supply to determine the actual life value of the laser power supply;

[0066] Perform a difference calculation on the actual life value and the predicted life value to obtain a prediction error value;

[0067] Judge whether the prediction error value is within the confidence interval;

[0068] If the prediction error value is not within the confidence interval, then perform a deviation evaluation on the predicted life value to generate the evaluation result;

[0069] Based on the evaluation result, synchronize the predicted life value to the feedback mechanism to obtain a feedback adjustment parameter set;

[0070] Dynamically feedback and optimize the life prediction model according to the feedback adjustment parameter set to generate multiple feedback optimization results;

[0071] Perform anti-verification on the multiple feedback optimization results. When the verification passes, update the life prediction model according to the multiple feedback optimization results to generate the life prediction optimization model.

[0072] In a feasible implementation, first, an accelerated life test is carried out on the laser power supply. Specifically, on the basis of simulating the actual working conditions, the environmental stress (such as temperature, humidity, current density, etc.) is appropriately increased to accelerate the aging process of the laser power supply. By recording the whole process data of the laser power supply from the initial state to the final failure, its actual life value is determined. Then, the obtained actual life value is compared with the predicted life value output by the life prediction model, and the difference between the two is calculated, that is, the prediction error value, which intuitively reflects the accuracy level of the current life prediction model and provides a quantitative basis for subsequent model evaluation and optimization. Subsequently, a confidence interval is preset, for example, an acceptable error range determined based on historical data and expert experience. The obtained prediction error value is compared with this confidence interval to determine whether the error is within the acceptable range, providing a decision-making basis for whether model optimization is needed subsequently.

[0073] When the prediction error value exceeds the confidence interval, it indicates that there is a significant deviation in the prediction result of the current model. At this time, an in-depth deviation assessment is carried out on the predicted life value, and the possible reasons for the error are analyzed, such as improper feature selection, unreasonable model structure, inappropriate parameter settings, etc. Through the assessment, a detailed assessment result is generated, providing targeted guidance for subsequent model optimization. Then, the assessment result is input into a pre-designed feedback mechanism. Based on the assessment result and combined with the difference between the predicted life value and the actual life value, this feedback mechanism generates parameters for adjusting the model to form a feedback adjustment parameter set, including adjustment coefficients for feature weights, modification suggestions for model structure, updated values for learning rates, etc. After that, the original life prediction model is systematically optimized using the obtained feedback adjustment parameter set, including adjusting feature weights, modifying model structure, updating learning parameters, etc. Through multiple rounds of optimization, multiple feedback optimization results are generated, and each result represents an improvement of the model in a certain aspect or to a certain extent. Thereafter, strict anti-verification is carried out on the generated multiple feedback optimization results. Specifically, an independent verification data set is used to evaluate the performance of each feedback optimization result to check whether it actually improves the prediction accuracy and generalization ability of the model. If the anti-verification passes, that is, the feedback optimization result actually improves the model performance, the optimization measures are adopted to update the original life prediction model to generate a new life prediction optimized model. If the anti-verification fails, it indicates that there are problems in the optimization process, and the optimization strategy is readjusted.

[0074] By continuously evaluating and dynamically optimizing the life prediction model of the laser power supply, the prediction accuracy and adaptability of the model are continuously improved, so that the model always maintains a high prediction performance, adapts to the life prediction requirements under different working conditions and environmental conditions, and thus provides a more accurate and reliable basis for the reliability assessment and maintenance decision-making of the laser power supply.

[0075] Furthermore, the embodiments of the present application further include:

[0076] Based on the evaluation results and in combination with the predicted life value, perform deviation backtracking to determine multiple error data sources;

[0077] Construct the feedback mechanism, and the feedback mechanism receives the predicted life value according to the data collection period;

[0078] Identify the predicted life value according to the multiple error data sources, and synchronize the identification result to the feedback mechanism;

[0079] Through the feedback mechanism and in combination with the identification result, perform deep learning to calculate and obtain multiple feedback adjustment parameters;

[0080] Construct simulation operation environment information, and based on the simulation operation environment information, perform cyclic feedback on the multiple feedback adjustment parameters to obtain the feedback adjustment parameter set.

[0081] In a preferred implementation manner, first, deeply analyze the evaluation results, and in combination with the predicted life value, trace the potential causes leading to the prediction deviation. Through deviation backtracking, determine multiple possible error data sources, including but not limited to: data quality problems (such as noise, outliers, missing values, etc.), insufficient model complexity (such as underfitting phenomenon), improper feature selection (such as omission of key features or excessive redundant features), unreasonable parameter settings, etc. Through comprehensive error source analysis, it provides a clear direction and basis for subsequent model adjustment. Then, design a flexible and efficient feedback mechanism that can regularly receive the latest predicted life value according to the preset data collection period based on the actual operation situation and data collection strategy of the laser power supply. Through periodic data reception, ensure that the feedback mechanism can timely capture the changes in the performance of the prediction model and provide a real-time basis for subsequent dynamic adjustment.

[0082] Then, based on the identified multiple error data sources, each predicted life value is identified. Specifically, multi-dimensional tags are added to each predicted life value, and these tags correspond to different error data sources respectively, indicating which factors may affect the predicted value. For example, the identification results include "poor data quality", "insufficient feature representativeness", "incompatible model complexity", etc. The multi-dimensional identification not only helps to understand the reliability of each predicted value, but also provides precise guidance for subsequent model adjustment. After the identification is completed, the identification results are synchronized to the constructed feedback mechanism for subsequent adjustment. Subsequently, the accumulated identification results in the feedback mechanism are systematically analyzed and learned. By mining the potential patterns and rules in the identification results, the key factors affecting the prediction accuracy are identified, and multiple feedback adjustment parameters are generated, including the adjustment coefficients of feature weights, the optimization suggestions for model structure, the dynamically updated values of learning rates, etc. After that, a simulation environment highly similar to the actual operating environment of the laser power supply is constructed, that is, the simulation operating environment information, which includes various factors that may affect the life of the laser power supply, such as workload, environmental temperature, humidity, etc. Then, the obtained multiple feedback adjustment parameters are applied to this simulation environment to observe their impact on the prediction results. Through multiple rounds of cyclic feedback and adjustment, these parameters are continuously optimized until the best prediction effect is obtained in the simulation environment. After that, the parameters optimized through cyclic feedback are integrated into a set of feedback adjustment parameters, which includes various adjustment parameters that have been fully verified and optimized.

[0083] By automating the entire process from error analysis to parameter optimization, the source of prediction errors is accurately located, and the optimal adjustment strategy is quickly found through intelligent algorithms and virtual verification, greatly improving the efficiency and accuracy of model optimization, enhancing the adaptability of the prediction model to various complex working conditions, and providing strong support for the life prediction of laser power supplies.

[0084] In summary, the laser power supply life prediction method provided by the embodiments of this application has the following technical effects:

[0085] Retrieve the operation data record log of the laser power supply to obtain multiple historical operation parameters, which provides reference information for long-term operation for subsequent analysis and helps identify long-term factors affecting the lifespan. Through real-time acquisition of the laser power supply by the data sensing unit, multiple real-time operation parameters are obtained to capture the immediate performance of the device, which helps discover short-term factors and sudden changes that may affect the lifespan. Based on the analysis of multiple historical operation parameters, determine the first set of operation influence characteristics. Based on the multiple real-time operation parameters combined with the first set of operation influence characteristics, perform correlation analysis, and screen the first set of operation influence characteristics according to the analysis results to determine the second set of operation influence characteristics. Through the comprehensive analysis of historical and real-time data, screen out the most representative and predictive features, improve the accuracy and efficiency of subsequent predictions, and ensure that the model focuses on the most relevant influencing factors. Construct a lifespan prediction model, synchronize the second set of operation influence characteristics to the lifespan prediction model to obtain a predicted lifespan value, which provides a basis for subsequent model evaluation and optimization. Based on the predicted lifespan value, conduct a lifespan prediction evaluation on the laser power supply, and feedback and optimize the lifespan prediction model according to the evaluation results to generate an optimized lifespan prediction model, and perform feedback optimization on the model to improve the accuracy and reliability of the prediction model, enabling the model to continuously learn and improve. Through the optimized lifespan prediction model, perform adaptive lifespan prediction on the laser power supply to achieve the adaptive prediction of the model, enabling the prediction results to be dynamically adjusted as the device state and environment change, and improving the long-term accuracy and adaptability of the prediction.

[0086] Embodiment 2, based on the same inventive concept as the method for predicting the lifespan of a laser power supply in the foregoing embodiment, as Figure 2 shown, the embodiment of the present application provides a system for predicting the lifespan of a laser power supply, and the system includes:

[0087] A historical data acquisition module 11, configured to retrieve the operation data record log of the laser power supply to obtain multiple historical operation parameters;

[0088] A real-time data acquisition module 12, configured to perform real-time acquisition of the laser power supply through a data sensing unit to obtain multiple real-time operation parameters;

[0089] A feature analysis and screening module 13, configured to perform influence analysis based on the multiple historical operation parameters to determine a first set of operation influence characteristics, perform correlation analysis based on the multiple real-time operation parameters combined with the first set of operation influence characteristics, and screen the first set of operation influence characteristics according to the analysis results to determine a second set of operation influence characteristics;

[0090] A prediction model construction module 14, configured to construct a lifespan prediction model, synchronize the second set of operation influence characteristics to the lifespan prediction model, and obtain a predicted lifespan value;

[0091] The prediction and evaluation optimization module 15 is used to perform life prediction and evaluation on the laser power supply based on the predicted life value, and feedback and optimize the life prediction model according to the evaluation results to generate an optimized life prediction model;

[0092] The life prediction execution module 16 is used to perform adaptive life prediction on the laser power supply through the optimized life prediction model.

[0093] Furthermore, the feature analysis and screening module 13 includes the following execution steps:

[0094] Clean the data of the multiple historical operating parameters to generate multiple historical operating standard parameters;

[0095] Perform statistical analysis based on the multiple historical operating standard parameters to determine the parameter distribution characteristics;

[0096] Perform univariate analysis on the multiple historical operating standard parameters according to the parameter distribution characteristics to generate a first analysis result;

[0097] Perform multivariate analysis on the multiple historical operating standard parameters according to the parameter distribution characteristics to generate a second analysis result;

[0098] Select influence features according to the first analysis result and the second analysis result to determine the first set of operating influence features.

[0099] Furthermore, the feature analysis and screening module 13 also includes the following execution steps:

[0100] Align the multiple real-time operating parameters in time according to the multiple historical operating parameters to generate multiple real-time aligned operating parameters;

[0101] Sort the multiple real-time aligned operating parameters in descending order according to the first set of operating influence features to construct an operating parameter influence list;

[0102] Perform weighted calculation on the first set of operating influence features based on the operating parameter influence list to generate multiple weight correlation coefficients, and the multiple weight correlation coefficients include multiple correlation directions and multiple correlation levels;

[0103] Add the multiple correlation directions and the multiple correlation levels to the analysis result.

[0104] Furthermore, the feature analysis and screening module 13 also includes the following execution steps:

[0105] Calculate the weight coefficients of the first set of operating influence features based on the operating parameter influence list in combination with the expert scoring method;

[0106] By using statistical analysis method to calculate the correlation coefficients of the first set of operation influence characteristics, a correlation coefficient matrix is obtained;

[0107] Based on the multiplication of the weight coefficients of the first set of operation influence characteristics and the correlation coefficient matrix, a plurality of weighted correlation coefficients are generated;

[0108] According to the positive and negative values of the plurality of weighted correlation coefficients, the correlation directions are divided to generate a plurality of correlation directions;

[0109] According to the absolute values of the plurality of weighted correlation coefficients, the correlation levels are divided to generate a plurality of correlation levels;

[0110] The plurality of correlation directions and the plurality of correlation levels are added to the plurality of weighted correlation coefficients.

[0111] Further, the feature analysis and screening module 13 further includes the following execution steps:

[0112] Based on the plurality of correlation directions, positive correlation screening is performed on the first set of operation influence characteristics to generate a first screening feature set;

[0113] Based on the plurality of correlation levels, strong correlation screening is performed on the first set of operation influence characteristics to generate a second screening feature set;

[0114] According to the first screening feature set and the second screening feature set, data intersection extraction is performed to obtain a screening feature intersection;

[0115] Based on the screening feature intersection, screening is performed on the first set of operation influence characteristics to determine the second set of operation influence characteristics.

[0116] Further, the prediction evaluation and optimization module 15 includes the following execution steps:

[0117] Based on the laser power supply, a life cycle experiment is carried out to determine the actual life value of the laser power supply;

[0118] The difference between the actual life value and the predicted life value is calculated to obtain a prediction error value;

[0119] It is judged whether the prediction error value is within the confidence interval;

[0120] If the prediction error value is not within the confidence interval, deviation evaluation is performed on the predicted life value to generate the evaluation result;

[0121] Based on the evaluation result, the predicted life value is synchronized to the feedback mechanism to obtain a feedback adjustment parameter set;

[0122] According to the feedback adjustment parameter set, dynamic feedback optimization is performed on the life prediction model to generate a plurality of feedback optimization results;

[0123] Perform anti-verification on the multiple feedback optimization results. When the verification passes, update the life prediction model according to the multiple feedback optimization results to generate the optimized life prediction model.

[0124] Furthermore, the prediction evaluation optimization module 15 further includes the following execution steps:

[0125] Based on the evaluation results and in combination with the predicted life values, perform deviation backtracking to determine multiple error data sources;

[0126] Construct the feedback mechanism, and the feedback mechanism receives the predicted life values according to the data collection period;

[0127] Identify the predicted life values according to the multiple error data sources, and synchronize the identification results to the feedback mechanism;

[0128] Through the feedback mechanism and in combination with the identification results, perform deep learning to calculate and obtain multiple feedback adjustment parameters;

[0129] Construct simulated operating environment information, and perform cyclic feedback on the multiple feedback adjustment parameters based on the simulated operating environment information to obtain the set of feedback adjustment parameters.

[0130] Any step of the method described above can be stored as computer instructions or programs in an unrestricted computer memory and can be called and recognized by an unrestricted computer processor to implement any method in the embodiments of the present application, and no redundant restrictions are made here.

[0131] Furthermore, the first or second described above may not only represent an order relationship, but may also represent a certain specific concept, and / or refer to the selection of multiple elements individually or in whole. Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the scope of the present application. In this way, if these modifications and variations of the present application fall within the scope of the present application and its equivalent technologies, the present application is intended to include these changes and variations.

Claims

1. A method for predicting the life of a laser power supply, characterized in that: The method comprises: Retrieve the operation data record log of the laser power supply to obtain multiple historical operation parameters; The laser power supply is collected in real time through the data sensing unit to obtain multiple real-time operating parameters; Performing an impact analysis based on the multiple historical operating parameters to determine a first operating impact feature set, performing a correlation analysis based on the multiple real-time operating parameters combined with the first operating impact feature set, screening the first operating impact feature set according to the analysis result, and determining a second operating impact feature set; constructing a life prediction model, synchronizing the second operation impact feature set to the life prediction model, and obtaining a predicted life value; Performing a life prediction evaluation on the laser power supply based on the predicted life value, performing feedback optimization on the life prediction model according to the evaluation result, and generating a life prediction optimization model; Performing adaptive lifetime prediction on the laser power supply by using the lifetime prediction optimization model; Based on the multiple real-time operating parameters combined with the first operating impact feature set, a correlation analysis is performed, the method comprising: Time-aligning the multiple real-time operating parameters according to the multiple historical operating parameters to generate multiple real-time aligned operating parameters; Sorting the multiple real-time alignment operation parameters in descending order according to the first operation impact feature set to construct an operation parameter impact list; Performing weighted calculation on the first operation impact feature set based on the operation parameter impact list to generate a plurality of weight correlation coefficients, wherein the plurality of weight correlation coefficients include a plurality of correlation directions and a plurality of correlation levels; The plurality of correlation directions and the plurality of correlation levels are added to the analysis result.

2. A laser power supply life prediction method as claimed in claim 1, characterized in that: Performing an impact analysis based on the multiple historical operating parameters to determine a first operating impact feature set, the method comprising: Performing data cleaning on the multiple historical operation parameters to generate multiple historical operation standard parameters; Performing statistical analysis based on the plurality of historical operating standard parameters to determine parameter distribution characteristics; Performing univariate analysis on the plurality of historical operating standard parameters according to the parameter distribution characteristics to generate a first analysis result; Performing a multivariate analysis on the plurality of historical operating standard parameters according to the parameter distribution characteristics to generate a second analysis result; Influencing features are selected according to the first analysis result and the second analysis result to determine the first operation influencing feature set.

3. A laser power supply life prediction method as claimed in claim 1, characterized in that: Performing weighted calculation on the first operation impact feature set based on the operation parameter impact list to generate a plurality of weight correlation coefficients, the method comprising: Calculating a weight coefficient of the first operation impact feature set based on the operation parameter impact list combined with an expert scoring method; By calculating the correlation coefficient of the first operation influencing feature set using a statistical analysis method, a correlation coefficient matrix is ​​obtained; Multiplying the weight coefficient based on the first operation influencing feature set by the correlation coefficient matrix to generate the plurality of weight correlation coefficients; Dividing the relevant directions according to the positive and negative values ​​of the plurality of weighted correlation coefficients to generate a plurality of relevant directions; Dividing the correlation levels according to the absolute values ​​of the plurality of weight correlation coefficients to generate a plurality of correlation levels; The plurality of correlation directions and the plurality of correlation levels are added to the plurality of weight correlation coefficients.

4. A method for predicting the life of a laser power supply according to claim 3, characterized in that: The first operation impact feature set is screened according to the analysis result to determine a second operation impact feature set, the method comprising: Performing positive correlation screening on the first operation impact feature set based on the multiple correlation directions to generate a first screening feature set; Performing strong correlation screening on the first operation impact feature set based on the multiple correlation levels to generate a second screening feature set; Perform data intersection extraction according to the first screening feature set and the second screening feature set to obtain a screening feature intersection; The first operation influencing feature set is screened based on the screening feature intersection to determine the second operation influencing feature set.

5. A method for predicting the life of a laser power supply according to claim 1, characterized in that: Based on the predicted life value, a life prediction evaluation is performed on the laser power supply, and according to the evaluation result, the life prediction model is feedback optimized to generate a life prediction optimization model, the method comprising: Conduct life cycle experiments based on laser power supplies to determine the actual life value of the laser power supply; The actual life value is calculated to be different from the predicted life value to obtain a prediction error value; Determining whether the prediction error value is within a confidence interval; If the prediction error value is not within the confidence interval, performing a deviation assessment on the predicted life value to generate the assessment result; Based on the evaluation result, synchronizing the predicted life value to a feedback mechanism to obtain a feedback adjustment parameter set; Performing dynamic feedback optimization on the life prediction model according to the feedback adjustment parameter set to generate multiple feedback optimization results; The plurality of feedback optimization results are reversely verified, and when the verification is passed, the life prediction model is updated according to the plurality of feedback optimization results to generate the life prediction optimization model.

6. A method for predicting the life of a laser power supply according to claim 5, characterized in that: Based on the evaluation result, the predicted life value is synchronized to a feedback mechanism to obtain a feedback adjustment parameter set, the method comprising: Based on the evaluation result and the predicted life value, deviation backtracking is performed to determine multiple error data sources; Constructing the feedback mechanism, wherein the feedback mechanism receives the predicted life value according to a data collection cycle; Marking the predicted life value according to the multiple error data sources, and synchronizing the marking result to the feedback mechanism; Perform deep learning by combining the feedback mechanism with the identification result to calculate and obtain multiple feedback adjustment parameters; Constructing simulation operation environment information, and performing cyclic feedback on the plurality of feedback adjustment parameters based on the simulation operation environment information to obtain the feedback adjustment parameter set.

7. A laser power supply life prediction system, characterized in that: A system for implementing a laser power supply life prediction method according to any one of claims 1 to 6, comprising: A historical data acquisition module, wherein the historical data acquisition module is used to retrieve the operation data record log of the laser power supply to obtain multiple historical operation parameters; A real-time data acquisition module, which is used to collect data from the laser power supply in real time through a data sensing unit to obtain multiple real-time operating parameters; a feature analysis and screening module, the feature analysis and screening module being used to perform an impact analysis based on the multiple historical operating parameters to determine a first operating impact feature set, perform a correlation analysis based on the multiple real-time operating parameters in combination with the first operating impact feature set, screen the first operating impact feature set according to the analysis result, and determine a second operating impact feature set; A prediction model building module, wherein the prediction model building module is used to build a life prediction model, synchronize the second operation impact feature set to the life prediction model, and obtain a predicted life value; A prediction evaluation optimization module, wherein the prediction evaluation optimization module is used to perform a life prediction evaluation on the laser power supply based on the predicted life value, and to perform feedback optimization on the life prediction model according to the evaluation result to generate a life prediction optimization model; A life prediction execution module is used to perform adaptive life prediction on the laser power supply through the life prediction optimization model.

Images