Lamp strip service life prediction method and system based on multi-source data fusion

Abstract

The invention relates to the technical field of lamp strip life prediction, and discloses a lamp strip life prediction method and system based on multi-source data fusion, and the method comprises the steps: obtaining a plurality of test lamp strip segments based on a to-be-predicted lamp strip, constructing a lamp strip data fusion model, carrying out the life test of the plurality of test lamp strip segments through a lamp strip monitoring index set, and obtaining a target life matching database, and according to the current monitoring moment, the target life matching database and the lamp strip data fusion model, carrying out life prediction on the to-be-predicted lamp strip to obtain a current predicted lamp strip life value and a historical predicted lamp strip life value, and carrying out historical environment correction on the current predicted lamp strip life value by using the historical predicted lamp strip life value to obtain a target predicted lamp strip life value. According to the invention, the stability and environmental adaptability of lamp strip life prediction can be improved, and the prediction deviation caused by environmental sudden change is reduced.

Description

Technical Field

[0001] This invention relates to the field of LED strip life prediction technology, and in particular to an LED strip life prediction method and system based on multi-source data fusion. Background Technology

[0002] As a key component in industrial lighting and automation systems, the reliability of LED strips directly affects the stability and safety of the production environment. Accurate life prediction enables preventive maintenance, avoiding lighting interruptions or production losses caused by sudden LED strip failure. Especially in factories with continuous operations or precision manufacturing scenarios, life prediction technology plays an important role in ensuring seamless system operation and improving overall equipment efficiency.

[0003] Traditional methods for predicting the lifespan of LED strip lights typically rely on static thresholds for a single operating parameter. This approach has drawbacks, such as ignoring the dynamic influence of multiple factors in the actual working environment, including temperature and humidity. This makes the predictions susceptible to transient fluctuations and unable to adapt to long-term performance evolution, resulting in low accuracy. Summary of the Invention

[0004] This invention provides a method for predicting the lifespan of LED strips based on multi-source data fusion and a computer-readable storage medium. Its main purpose is to improve the stability and environmental adaptability of LED strip lifespan prediction and reduce prediction deviations caused by sudden environmental changes.

[0005] To achieve the above objectives, the present invention provides a method for predicting the lifespan of LED strips based on multi-source data fusion, comprising:

[0006] The light strip to be predicted and the set of light strip monitoring indicators are determined. Multiple test light strip segments are obtained based on the light strip to be predicted. The set of light strip monitoring indicators includes multiple light strip monitoring indicators.

[0007] A light strip data fusion model is constructed, which includes: a data monitoring unit, a feature statistics unit, and a data storage unit;

[0008] Life tests were conducted on multiple test light strip segments using a set of light strip monitoring indicators to obtain a target life matching database. The target life matching database includes multiple target life matching datasets, and each target life matching dataset corresponds one-to-one with a test light strip segment.

[0009] Receive a lifetime prediction command, determine the current monitoring time based on the lifetime prediction command, and perform lifetime prediction on the light strip to be predicted according to the current monitoring time, the target lifetime matching database and the light strip data fusion model, to obtain the current predicted lifespan value and the historical predicted lifespan value of the light strip.

[0010] By using historical predicted LED strip lifespan values ​​to correct the current predicted LED strip lifespan value for historical environmental factors, the target predicted LED strip lifespan value is obtained.

[0011] Based on the target predicted lifespan value, the lifespan prediction of the light strip is completed based on multi-source data fusion.

[0012] Optionally, the step of using a set of LED strip monitoring indicators to perform life tests on multiple LED strip segments to obtain a target life matching database includes:

[0013] Perform the following operation on each of the multiple test light strip segments:

[0014] Determine the working environment of the test light strip segment, and construct the test light strip environment vector based on the working environment of the test light strip;

[0015] Based on the LED strip monitoring index set, life data analysis was performed on the test LED strip segment to obtain the LED strip life matching dataset.

[0016] The test LED strip environment vector is used to label the LED strip lifespan matching dataset to obtain the target lifespan matching dataset;

[0017] The target life matching dataset corresponding to each test light strip segment is compiled to obtain the target life matching database.

[0018] Optionally, the step of performing lifespan data analysis on the test LED strip segment based on the LED strip monitoring index set to obtain an LED strip lifespan matching dataset includes:

[0019] Data monitoring is performed on the test light strip segment based on the light strip monitoring index set to obtain multiple test light strip parameter sequences, in which the test light strip parameter sequences correspond one-to-one with the light strip monitoring indexes;

[0020] Based on feature analysis of multiple test light strip parameter sequences, multiple test light strip operation feature groups are obtained, in which the test light strip operation feature groups correspond one-to-one with the test light strip parameter sequences;

[0021] The lifespan of the test LED strip segment is measured to obtain the test LED strip lifespan value;

[0022] The lifespan values ​​of the test LED strips are used to match the operating characteristic groups of multiple test LED strips to obtain LED strip lifespan matching data.

[0023] If the test light strip life value is not less than the preset light strip life threshold, then return to the step of monitoring the test light strip segment based on the light strip monitoring index set until the test light strip life value is less than the light strip life threshold.

[0024] If the test LED strip lifespan value is less than the LED strip lifespan threshold, then the LED strip lifespan matching data is summarized to obtain the LED strip lifespan matching dataset.

[0025] Optionally, the step of performing feature analysis based on multiple test light strip parameter sequences to obtain multiple test light strip operating feature groups includes:

[0026] For each of the multiple test LED strip parameter sequences, perform the following operation:

[0027] Mathematical statistical feature analysis was performed on the parameter sequence of the test LED strip to obtain the short-term operating feature group of the test LED strip.

[0028] Determine the total sequence of historical light strip parameters based on the test light strip parameter sequence;

[0029] The test light strip parameter sequence is added to the historical light strip parameter sequence to obtain the total test light strip parameter sequence;

[0030] Mathematical statistical feature analysis was performed on the total sequence of test LED strip parameters to obtain the long-term operating characteristic group of the test LED strip.

[0031] The short-term LED strip operation characteristic group and the long-term LED strip operation characteristic group are combined to obtain the test LED strip operation characteristic group;

[0032] By summarizing the test light strip operation feature groups corresponding to each test light strip parameter sequence, multiple test light strip operation feature groups are obtained.

[0033] Optionally, the step of predicting the lifespan of the light strip to be predicted based on the current monitoring time, the target lifespan matching database, and the light strip data fusion model to obtain the current predicted lifespan value and the historical predicted lifespan value includes:

[0034] Determine the target light strip environment for the light strip to be predicted;

[0035] Based on the data monitoring unit and the set of light strip monitoring indicators in the light strip data fusion model, data monitoring is performed on the light strip to be predicted to obtain multiple target light strip parameter sequences. Among them, the target light strip parameter sequences in the multiple target light strip parameter sequences correspond one-to-one with the light strip monitoring indicators.

[0036] By using the feature statistics unit to perform feature statistics on the parameter sequences of multiple target light strips, multiple short-term operational feature groups of targets are obtained.

[0037] Based on the current monitoring time, read the total sequence of multiple historical monitoring parameters and the historical predicted lifespan value of the light strip from the data storage unit;

[0038] By supplementing multiple target light strip parameter sequences with multiple historical monitoring parameter sequences, multiple current monitoring parameter sequences are obtained.

[0039] By using the feature statistics unit to perform feature statistics on the total sequence of multiple current monitoring parameters, multiple long-term operating feature groups of targets are obtained.

[0040] By merging multiple short-term and long-term target operation characteristic groups, multiple current light strip operation characteristic groups are obtained.

[0041] Based on the current monitoring time, environmental parameters of the target light strip environment are acquired to obtain the current light strip environment vector;

[0042] The predicted lifespan of the current LED strip is calculated based on multiple current LED strip operating feature groups, the current LED strip environment vector, and the target lifespan matching database.

[0043] Optionally, the step of calculating the current predicted lifespan value of the light strip based on multiple current light strip operating feature groups, the current light strip environment vector, and the target lifespan matching database includes:

[0044] For each target lifetime matching dataset in the target lifetime matching database, perform the following operation:

[0045] Obtain the target light strip environment vector corresponding to the target lifetime matching dataset;

[0046] Extract target lifetime matching data sequentially from the target lifetime matching dataset, and record the extracted target lifetime matching data as the comparison lifetime matching data;

[0047] The lifespan values ​​of the comparison light strips and multiple sets of operation characteristics of the comparison light strips were identified in the comparison lifespan matching data.

[0048] Calculate the similarity of comparative features based on multiple current light strip operation feature groups and multiple comparative light strip operation feature groups;

[0049] The similarity scores of the comparative features corresponding to each comparative lifetime matching data are summarized to obtain the comparative feature similarity set;

[0050] The optimal feature similarity is identified in the set of comparative feature similarities, and the lifespan value of the comparative light strip in the target lifespan matching data corresponding to the optimal feature similarity is recorded as the optimal light strip lifespan value.

[0051] The optimal LED strip lifespan value and the target LED strip environment vector are merged to obtain the optimal LED strip fusion data;

[0052] The optimal LED strip fusion dataset is obtained by summing up the optimal LED strip fusion dataset corresponding to each target lifetime matching dataset;

[0053] The current predicted lifespan value of the light strip is obtained by weighted calculation based on the optimal light strip fusion dataset and the current light strip environment vector.

[0054] Optionally, the step of calculating the similarity of comparison features based on multiple current light strip operation feature groups and multiple comparison light strip operation feature groups includes:

[0055] A current light strip operation feature matrix is ​​constructed based on multiple current light strip operation feature groups, and a comparison light strip operation feature matrix is ​​constructed based on multiple comparison light strip operation feature groups.

[0056] The similarity of the comparative features is calculated based on the current LED strip operation feature matrix and the comparative LED strip operation feature matrix. The similarity of the comparative features is expressed as follows:

[0057] ,

[0058] in, Indicates the similarity of contrasting features. This indicates the row number of the current LED strip's operating characteristic matrix or the row number of the LED strip's operating characteristic matrix being compared. This indicates the number of columns in the current LED strip's operating characteristic matrix or the number of columns in the comparison LED strip's operating characteristic matrix. This represents an exponential function with the natural constant as its base. This indicates taking the absolute value. The first element in the comparison light strip operation feature matrix refers to the first element. line, number Column matrix elements, This represents the first element in the current LED strip operation feature matrix. line, number Columns of matrix elements.

[0059] Optionally, the step of using historical predicted LED strip lifespan values ​​to perform historical environment correction on the current predicted LED strip lifespan value to obtain the target predicted LED strip lifespan value includes:

[0060] Obtain the historical average LED strip environment vector;

[0061] The historical extended lifespan value of the light strip is calculated based on multiple current light strip operation feature groups, historical average light strip environment vectors, and target lifespan matching database.

[0062] Obtain the total historical monitoring duration and the current monitoring duration;

[0063] The target predicted lifespan of the light strip is calculated based on the total historical monitoring duration, the current monitoring duration, the historical predicted lifespan of the light strip, the historical extended lifespan of the light strip, and the current predicted lifespan of the light strip.

[0064] Optionally, the target predicted lifespan value of the light strip is expressed as:

[0065] ,

[0066] in, This represents the target predicted lifespan value of the LED strip. This indicates the historical predicted lifespan of the LED strip. This indicates the total duration of historical monitoring. Indicates the current monitoring duration. This indicates the historical lifespan value of the LED strip. This indicates the current predicted lifespan of the LED strip.

[0067] To achieve the above objectives, the present invention also provides a light strip life prediction system based on multi-source data fusion, comprising:

[0068] The fusion model construction module is used to determine the light strip to be predicted and the light strip monitoring index set. Based on the light strip to be predicted, multiple test light strip segments are obtained. The light strip monitoring index set includes multiple light strip monitoring indicators. The light strip data fusion model is constructed, which includes: a data monitoring unit, a feature statistics unit, and a data storage unit.

[0069] The matching data acquisition module is used to perform life tests on multiple test light strip segments using the light strip monitoring index set to obtain a target life matching database. The target life matching database includes multiple target life matching datasets, and each target life matching dataset corresponds one-to-one with a test light strip segment.

[0070] The current lifespan prediction module is used to receive lifespan prediction instructions, determine the current monitoring time based on the lifespan prediction instructions, and predict the lifespan of the light strip to be predicted based on the current monitoring time, the target lifespan matching database and the light strip data fusion model, so as to obtain the current predicted lifespan value and the historical predicted lifespan value of the light strip.

[0071] The historical environment correction module is used to correct the current predicted lifespan of the light strip using historical predicted lifespan values, so as to obtain the target predicted lifespan value of the light strip.

[0072] To address the above problems, the present invention also provides an electronic device, the electronic device comprising:

[0073] Memory, storing at least one instruction;

[0074] The processor executes the instructions stored in the memory to implement the above-described method for predicting the lifespan of light strips based on multi-source data fusion.

[0075] To address the aforementioned problems, the present invention also provides a computer-readable storage medium storing at least one instruction, which is executed by a processor in an electronic device to implement the above-described method for predicting the lifespan of LED strips based on multi-source data fusion.

[0076] To address the problems described in the background art, this invention first constructs a light strip data fusion model. This step, through the integration of a multi-unit collaborative framework, achieves real-time acquisition, feature analysis, and efficient storage of multi-source data. Compared to existing technologies where data processing is fragmented or lacks a fusion mechanism, this step improves the overall integrity and automation level of data processing, providing a reliable computational foundation for lifespan prediction. Next, this scheme utilizes a light strip monitoring index set to conduct lifespan tests on multiple test light strip segments, obtaining a target lifespan matching database. This step, by introducing environmental vector labeling and lifespan data analysis, constructs a historical database containing environmental factors. Compared to existing technologies that often ignore the impact of changes in the working environment, this step enables the prediction model to dynamically match environmental conditions, thereby enhancing the adaptability and accuracy of lifespan prediction. Furthermore, based on the current monitoring time, the target lifespan matching database, and the light strip data fusion... The integrated model predicts the lifespan of the LED strip under test, obtaining the current predicted lifespan value and historical predicted lifespan values. This step, by fusing real-time monitoring data and historical parameter sequences, achieves dynamic and continuous lifespan assessment. Compared with existing technologies that predict based solely on instantaneous data, this step provides a more comprehensive perspective on performance evolution and reduces the volatility of prediction results. Finally, this scheme uses historical predicted lifespan values ​​to correct the current predicted lifespan value for historical environments, obtaining the target predicted lifespan value. This step, through an environmental correction formula, offsets prediction biases caused by sudden environmental changes. Compared with existing technologies that handle environmental factors crudely or lack correction mechanisms, this step improves the stability and reliability of predictions, ensuring consistency of lifespan values ​​under different environments. Therefore, this invention can improve the stability and environmental adaptability of LED strip lifespan prediction and reduce prediction biases caused by sudden environmental changes. Attached Figure Description

[0077] Figure 1 This is a flowchart illustrating a method for predicting the lifespan of LED strips based on multi-source data fusion, provided in an embodiment of the present invention.

[0078] Figure 2 This is a functional block diagram of a LED strip life prediction system based on multi-source data fusion provided in an embodiment of the present invention.

[0079] Figure 3 This is a schematic diagram of the structure of an electronic device that implements the LED strip life prediction method based on multi-source data fusion, according to an embodiment of the present invention.

[0080] Explanation of reference numerals in the attached figures:

[0081] 10. Electronic device; 11. Processor; 12. Memory; 13. Bus.

[0082] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0083] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0084] This application provides a method for predicting the lifespan of LED strips based on multi-source data fusion. The execution entity of this method includes, but is not limited to, at least one of the following electronic devices that can be configured to execute the method provided in this application: a server, a terminal, etc. In other words, the method for predicting the lifespan of LED strips based on multi-source data fusion can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes, but is not limited to, a single server, a server cluster, a cloud server, or a cloud server cluster.

[0085] Reference Figure 1 The diagram shown is a flowchart illustrating a method for predicting the lifespan of LED strips based on multi-source data fusion, according to an embodiment of the present invention. In this embodiment, the method for predicting the lifespan of LED strips based on multi-source data fusion includes:

[0086] S1. Determine the light strip to be predicted and the set of light strip monitoring indicators. Based on the light strip to be predicted, obtain multiple test light strip segments. The set of light strip monitoring indicators includes multiple light strip monitoring indicators.

[0087] Understandably, the "light strip to be predicted" refers to a light strip whose lifespan needs to be predicted, such as a light strip in a factory or industrial lighting system. The "light strip monitoring index set" refers to a collection of multiple light strip monitoring indicators. These indicators refer to the types of data that need to be collected when subsequently collecting data on the light strip to be predicted. These indicators include, but are not limited to, light strip illumination duration, light strip operating current, and light strip operating voltage. The "test light strip segment" refers to a light strip of the same model as the light strip to be predicted. This test light strip segment is used for subsequent lifespan testing to construct a target lifespan matching database.

[0088] S2. Construct a light strip data fusion model, which includes: a data monitoring unit, a feature statistics unit, and a data storage unit.

[0089] It should be explained that the light strip data fusion model refers to the core processing framework that fuses the data of the light strip to be predicted in order to perform lifespan prediction. This light strip data fusion model is integrated into a computer system or embedded device used to perform lifespan prediction. The data monitoring unit refers to the functional module that collects operational data of the light strip to be predicted. This data monitoring unit includes sensors for collecting various types of data (such as lighting duration, current, and voltage) defined by the light strip monitoring index set. The feature statistics unit refers to the calculation module that performs feature analysis on the data of the light strip to be predicted (the data collected by the data monitoring unit, such as the parameter sequences of multiple subsequent target light strips). The data storage unit refers to the database that stores the data analyzed by the feature statistics unit (such as the subsequent predicted lifespan values ​​of the target light strips and the total sequence of multiple current monitoring parameters) for subsequent retrieval of historical data.

[0090] S3. Use the LED strip monitoring index set to conduct life tests on multiple LED strip segments to obtain a target life matching database. The target life matching database includes multiple target life matching datasets, and each target life matching dataset corresponds one-to-one with a test LED strip segment.

[0091] It is clear that the target lifespan matching database refers to a database composed of multiple target lifespan matching datasets. The target lifespan matching dataset refers to a collection of test data obtained after a lifespan test of a specific test light strip segment. The detailed method for obtaining this target lifespan matching data will be explained in subsequent embodiments.

[0092] In detail, the process of using a set of LED strip monitoring indicators to perform life tests on multiple LED strip segments to obtain a target life matching database includes:

[0093] Perform the following operation on each of the multiple test light strip segments:

[0094] Determine the working environment of the test light strip segment, and construct the test light strip environment vector based on the working environment of the test light strip;

[0095] Based on the LED strip monitoring index set, life data analysis was performed on the test LED strip segment to obtain the LED strip life matching dataset.

[0096] The test LED strip environment vector is used to label the LED strip lifespan matching dataset to obtain the target lifespan matching dataset;

[0097] The target life matching dataset corresponding to each test light strip segment is compiled to obtain the target life matching database.

[0098] It should be explained that the "test LED strip working environment" refers to the actual working conditions of the test LED strip segment during subsequent data monitoring. This working environment is artificially constructed, and the parameters within it must be kept constant. The "test LED strip environment vector" refers to a numerical vector composed of environmental parameters of the test LED strip working environment, which includes, but is not limited to, temperature, humidity, and vibration intensity. The "LED strip lifespan matching dataset" refers to the dataset obtained after lifespan data analysis; the method for obtaining this dataset will be explained in subsequent embodiments. The "target lifespan matching dataset" refers to the labeled LED strip lifespan matching dataset. Labeling the LED strip lifespan matching dataset using the test LED strip environment vector means binding the test LED strip environment vector to the LED strip lifespan matching dataset to establish a correspondence between them, facilitating environmental matching during subsequent prediction.

[0099] In detail, the step of analyzing the lifespan data of the test LED strip segment based on the LED strip monitoring index set to obtain an LED strip lifespan matching dataset includes:

[0100] Data monitoring is performed on the test light strip segment based on the light strip monitoring index set to obtain multiple test light strip parameter sequences, in which the test light strip parameter sequences correspond one-to-one with the light strip monitoring indexes;

[0101] Based on feature analysis of multiple test light strip parameter sequences, multiple test light strip operation feature groups are obtained, in which the test light strip operation feature groups correspond one-to-one with the test light strip parameter sequences;

[0102] The lifespan of the test LED strip segment is measured to obtain the test LED strip lifespan value;

[0103] The lifespan values ​​of the test LED strips are used to match the operating characteristic groups of multiple test LED strips to obtain LED strip lifespan matching data.

[0104] If the test light strip life value is not less than the preset light strip life threshold, then return to the step of monitoring the test light strip segment based on the light strip monitoring index set until the test light strip life value is less than the light strip life threshold.

[0105] If the test LED strip lifespan value is less than the LED strip lifespan threshold, then the LED strip lifespan matching data is summarized to obtain the LED strip lifespan matching dataset.

[0106] It should be explained that the test light strip parameter sequence refers to the numerical sequence of a certain light strip monitoring index collected over a period of time. The test light strip operation characteristic group refers to the feature set of a certain light strip monitoring index throughout the entire process of the test light strip segment. The method of obtaining the test light strip operation characteristic group will be detailed in subsequent embodiments. The test light strip lifetime value refers to the lifetime value measured by the test light strip segment during data monitoring. The detailed steps for lifetime detection of the test light strip segment are as follows: detect the luminous flux maintenance rate of the test light strip segment, and record the ratio of the luminous flux maintenance rate to the initial maintenance rate of the test light strip segment as the test light strip lifetime value. When the test light strip lifetime value is equal to 1, it indicates that the test light strip segment has not been used and has a good lifetime. The initial maintenance rate refers to the luminous flux maintenance rate of the test light strip segment before data monitoring. The LED strip lifespan matching data refers to the set consisting of the test LED strip lifespan value and multiple test LED strip operating characteristic groups. Matching the test LED strip lifespan value with multiple test LED strip operating characteristic groups means placing the test LED strip lifespan value and multiple test LED strip operating characteristic groups into the same set. The LED strip lifespan threshold is a critical value used to determine whether a test LED strip segment is nearing the end of its lifespan. When the test LED strip lifespan threshold is lower than this threshold, it indicates that the optical performance of the test LED strip segment has degraded to an unacceptable level, posing a risk of failure and requiring replacement or maintenance. This LED strip lifespan threshold can be set according to industry standards, such as: L70 standard (luminous flux maintenance rate drops to 70% of the initial maintenance rate, i.e., the LED strip lifespan threshold is 0.7) and L80 standard (luminous flux maintenance rate drops to 80% of the initial maintenance rate, i.e., the LED strip lifespan threshold is 0.8).

[0107] In detail, the feature analysis based on multiple test light strip parameter sequences yields multiple test light strip operating feature groups, including:

[0108] For each of the multiple test LED strip parameter sequences, perform the following operation:

[0109] Mathematical statistical feature analysis was performed on the parameter sequence of the test LED strip to obtain the short-term operating feature group of the test LED strip.

[0110] Determine the total sequence of historical light strip parameters based on the test light strip parameter sequence;

[0111] The test light strip parameter sequence is added to the historical light strip parameter sequence to obtain the total test light strip parameter sequence;

[0112] Mathematical statistical feature analysis was performed on the total sequence of test LED strip parameters to obtain the long-term operating characteristic group of the test LED strip.

[0113] The short-term LED strip operation characteristic group and the long-term LED strip operation characteristic group are combined to obtain the test LED strip operation characteristic group;

[0114] By summarizing the test light strip operation feature groups corresponding to each test light strip parameter sequence, multiple test light strip operation feature groups are obtained.

[0115] It should be explained that the "short-term test light strip operation characteristic group" refers to the feature set used to describe the parameter changes of the test light strip parameter sequence. This short-term test light strip operation characteristic group includes mathematical statistical parameters such as the average, maximum, minimum, and standard deviation of the test light strip parameter sequence. The "historical light strip parameter total sequence" refers to the numerical set composed of all test light strip parameter sequences of light strip monitoring indicators obtained throughout the entire data monitoring process. If this is the first time the light strip to be predicted is being monitored, then the historical light strip parameter total sequence is an empty set. This historical light strip parameter total sequence reflects the performance changes of the test light strip segment throughout the entire data monitoring process. The "test light strip parameter total sequence" refers to the historical light strip parameter total sequence after supplementing the test light strip parameter sequence. Since a single test light strip parameter sequence can only reflect the local operating status of the test light strip segment within a specific monitoring period, it is necessary to merge the test light strip parameter sequence with historical data (i.e., the historical light strip parameter total sequence) to form a complete data sequence (i.e., the test light strip parameter total sequence) that can reflect the overall performance evolution of the light strip from the start of operation to the current moment. The long-term LED strip operation feature group refers to a set of features used to describe the parameter changes in the total sequence of LED strip parameters. The structure of this long-term LED strip operation feature group is the same as that of the short-term LED strip operation feature group. The aforementioned merging of the short-term and long-term LED strip operation feature groups means placing them into the same set; this combined set constitutes the LED strip operation feature group.

[0116] S4. Receive the lifespan prediction command, determine the current monitoring time based on the lifespan prediction command, and predict the lifespan of the light strip to be predicted based on the current monitoring time, the target lifespan matching database, and the light strip data fusion model, so as to obtain the current predicted lifespan value and the historical predicted lifespan value of the light strip.

[0117] Understandably, the lifespan prediction command refers to a command initiated manually to predict the lifespan of the light strip to be predicted, or a command initiated automatically by the control center through polling to predict the lifespan of the light strip to be predicted. The current monitoring time refers to the time when the lifespan prediction command was generated.

[0118] In detail, the step of predicting the lifespan of the light strip to be predicted based on the current monitoring time, the target lifespan matching database, and the light strip data fusion model to obtain the current predicted lifespan value and the historical predicted lifespan value includes:

[0119] Determine the target light strip environment for the light strip to be predicted;

[0120] Based on the data monitoring unit and the set of light strip monitoring indicators in the light strip data fusion model, data monitoring is performed on the light strip to be predicted to obtain multiple target light strip parameter sequences. Among them, the target light strip parameter sequences in the multiple target light strip parameter sequences correspond one-to-one with the light strip monitoring indicators.

[0121] By using the feature statistics unit to perform feature statistics on the parameter sequences of multiple target light strips, multiple short-term operational feature groups of targets are obtained.

[0122] Based on the current monitoring time, read the total sequence of multiple historical monitoring parameters and the historical predicted lifespan value of the light strip from the data storage unit;

[0123] By supplementing multiple target light strip parameter sequences with multiple historical monitoring parameter sequences, multiple current monitoring parameter sequences are obtained.

[0124] By using the feature statistics unit to perform feature statistics on the total sequence of multiple current monitoring parameters, multiple long-term operating feature groups of targets are obtained.

[0125] By merging multiple short-term and long-term target operation characteristic groups, multiple current light strip operation characteristic groups are obtained.

[0126] Based on the current monitoring time, environmental parameters of the target light strip environment are acquired to obtain the current light strip environment vector;

[0127] The predicted lifespan of the current LED strip is calculated based on multiple current LED strip operating feature groups, the current LED strip environment vector, and the target lifespan matching database.

[0128] It should be explained that the target light strip environment refers to the actual environment in which the light strip to be predicted is located. For example, if the light strip to be predicted is installed in the lighting system of a factory workshop, then the target light strip environment is the actual environmental conditions of that factory workshop (including temperature, humidity, etc.). The current light strip environment vector refers to a numerical vector composed of the environmental parameters of the target light strip environment. The structure of the current light strip environment vector is the same as the structure of the test light strip environment vector mentioned above.

[0129] It is clear that the target light strip parameter sequence refers to the set of values ​​of a certain light strip monitoring indicator of the light strip to be predicted over a period of time, as monitored by the data monitoring unit. The steps for monitoring the light strip to be predicted based on the data monitoring unit and the light strip monitoring indicator set are the same as the steps for monitoring the test light strip segment based on the light strip monitoring indicator set. The target short-term operating feature group refers to a feature set used to describe the parameter changes of a certain target light strip parameter sequence. The method for obtaining this target short-term operating feature group is the same as the method for obtaining the test short-term light strip operating feature group, and the aforementioned feature statistics unit is used to perform the calculation steps involved in the feature statistics. The historical monitoring parameter total sequence refers to the set of all target light strip parameter sequences of the light strip to be predicted under a certain light strip monitoring indicator obtained in previous data monitoring (the current monitoring parameter total sequence in the previous data monitoring can be used as the historical monitoring parameter total sequence in the current data monitoring). The current total monitoring parameter sequence refers to the total historical monitoring parameter sequence after being supplemented by the target light strip parameter sequence. Supplementing multiple total historical monitoring parameter sequences with multiple target light strip parameter sequences means supplementing the target light strip parameter sequence into the total historical monitoring parameter sequence with the same data monitoring indicators.

[0130] Furthermore, the historical predicted LED strip lifespan value refers to the current predicted LED strip lifespan value obtained in the previous data monitoring, meaning that this historical predicted LED strip lifespan value is derived iteratively from the current predicted LED strip lifespan values ​​in each data monitoring process. The target long-term operating characteristic group refers to the feature set of a certain current monitoring parameter sequence obtained after feature statistics. The acquisition method and structure of this target long-term operating characteristic group are the same as those of the target short-term operating characteristic group. The current LED strip operating characteristic group refers to the numerical set of the merged target short-term operating characteristic group and the target long-term operating characteristic group, wherein the merged target short-term operating characteristic group and the target long-term operating characteristic group have the same data monitoring indicators.

[0131] Specifically, the step of calculating the current predicted lifespan value of the light strip based on multiple current light strip operating feature groups, the current light strip environment vector, and the target lifespan matching database includes:

[0132] For each target lifetime matching dataset in the target lifetime matching database, perform the following operation:

[0133] Obtain the target light strip environment vector corresponding to the target lifetime matching dataset;

[0134] Extract target lifetime matching data sequentially from the target lifetime matching dataset, and record the extracted target lifetime matching data as the comparison lifetime matching data;

[0135] The lifespan values ​​of the comparison light strips and multiple sets of operation characteristics of the comparison light strips were identified in the comparison lifespan matching data.

[0136] Calculate the similarity of comparative features based on multiple current light strip operation feature groups and multiple comparative light strip operation feature groups;

[0137] The similarity scores of the comparative features corresponding to each comparative lifetime matching data are summarized to obtain the comparative feature similarity set;

[0138] The optimal feature similarity is identified in the set of comparative feature similarities, and the lifespan value of the comparative light strip in the target lifespan matching data corresponding to the optimal feature similarity is recorded as the optimal light strip lifespan value.

[0139] The optimal LED strip lifespan value and the target LED strip environment vector are merged to obtain the optimal LED strip fusion data;

[0140] The optimal LED strip fusion dataset is obtained by summing up the optimal LED strip fusion dataset corresponding to each target lifetime matching dataset;

[0141] The current predicted lifespan value of the light strip is obtained by weighted calculation based on the optimal light strip fusion dataset and the current light strip environment vector.

[0142] It should be explained that the target LED strip environment vector refers to the test LED strip environment vector corresponding to the target lifespan matching dataset. The comparison LED strip lifespan value refers to the test LED strip lifespan value in the comparison lifespan matching data. The multiple comparison LED strip operating feature groups refer to multiple test LED strip operating feature groups in the comparison lifespan matching data. The comparison feature similarity refers to a numerical value that quantifies the similarity between multiple current LED strip operating feature groups and multiple comparison LED strip operating feature groups. The larger the comparison feature similarity, the higher the similarity between the multiple current LED strip operating feature groups and the multiple comparison LED strip operating feature groups, meaning that the comparison LED strip lifespan value corresponding to the multiple comparison LED strip operating feature groups is more likely to match the lifespan value of the multiple current LED strip operating feature groups (i.e., the currently predicted LED strip lifespan value). The optimal feature similarity refers to the comparison feature similarity with the largest value in the comparison feature similarity set. The optimal LED strip fusion data refers to the set composed of the optimal LED strip lifespan value and the target LED strip environment vector. Since environmental factors can affect the lifespan of the LED strip to be predicted, it is also necessary to introduce the current LED strip environment vector and weight the lifespan values ​​of each optimal LED strip in the optimal LED strip fusion dataset based on the similarity between the current LED strip environment vector and the environment vectors of each target LED strip in the optimal LED strip fusion dataset. The weighted value is the current predicted lifespan value of the LED strip.

[0143] Furthermore, based on the weighted calculation using the optimal LED strip fusion dataset and the current LED strip environment vector, the formula for calculating the current predicted LED strip lifespan is as follows:

[0144] ,

[0145] in, This represents the current predicted lifespan value of the LED strip, and A represents the number of optimal LED strip fusion data points in the optimal LED strip fusion dataset. Let cosine be the vector function, and let its output value represent the vector similarity between two vectors. This represents the sum of the similarities of all vectors. This represents the current LED strip environment vector. Represents the th element in the optimal light strip fusion dataset. The target light strip environment vector contained in the optimal light strip fusion data. Indicates the first The optimal lifespan value of the LED strip contained in the optimal LED strip fusion data.

[0146] Specifically, the step of calculating the similarity of comparative features based on multiple current light strip operation feature groups and multiple comparative light strip operation feature groups includes:

[0147] A current light strip operation feature matrix is ​​constructed based on multiple current light strip operation feature groups, and a comparison light strip operation feature matrix is ​​constructed based on multiple comparison light strip operation feature groups.

[0148] The similarity of the comparative features is calculated based on the current LED strip operation feature matrix and the comparative LED strip operation feature matrix. The similarity of the comparative features is expressed as follows:

[0149] ,

[0150] in, Indicates the similarity of contrasting features. This indicates the row number of the current LED strip's operating characteristic matrix or the row number of the LED strip's operating characteristic matrix being compared. This indicates the number of columns in the current LED strip's operating characteristic matrix or the number of columns in the comparison LED strip's operating characteristic matrix. This represents an exponential function with the natural constant as its base. This indicates taking the absolute value. The first element in the comparison light strip operation feature matrix refers to the first element. line, number Column matrix elements, This represents the first element in the current LED strip operation feature matrix. line, number Columns of matrix elements.

[0151] It should be explained that the current LED strip operation feature matrix refers to a matrix composed of multiple current LED strip operation feature groups, wherein each current LED strip operation feature group is a matrix row, and multiple matrix rows constitute the current LED strip operation feature matrix. The comparison LED strip operation feature matrix refers to a matrix composed of multiple comparison LED strip operation feature groups, and the comparison LED strip operation feature matrix is ​​constructed in the same way as the current LED strip operation feature matrix.

[0152] S5. Use historical predicted light strip life values ​​to correct the current predicted light strip life value for historical environment, and obtain the target predicted light strip life value.

[0153] It is clear that the target predicted lifespan value of the LED strip refers to the current predicted lifespan value after correction. In the actual lifespan prediction process, environmental factors can significantly affect the prediction results. The actual factory environment can change due to external factors such as seasonal factors, sudden weather changes, or adjustments in production activities. In this case, the current LED strip environment vector will also change. The current predicted lifespan value is a predicted value calculated based on the current environment vector (i.e., the current LED strip environment vector). However, the environment in which the LED strip was in previous data monitoring may not be exactly the same as the current environment. Therefore, the current predicted lifespan value will deviate from the actual lifespan value. It is necessary to correct the current predicted lifespan value by combining it with the previously obtained lifespan values ​​of the LED strip (i.e., historical predicted lifespan values).

[0154] In detail, the step of using historical predicted LED strip lifespan values ​​to perform historical environment correction on the current predicted LED strip lifespan value to obtain the target predicted LED strip lifespan value includes:

[0155] Obtain the historical average LED strip environment vector;

[0156] The historical extended lifespan value of the light strip is calculated based on multiple current light strip operation feature groups, historical average light strip environment vectors, and target lifespan matching database.

[0157] Obtain the total historical monitoring duration and the current monitoring duration;

[0158] The target predicted lifespan of the light strip is calculated based on the total historical monitoring duration, the current monitoring duration, the historical predicted lifespan of the light strip, the historical extended lifespan of the light strip, and the current predicted lifespan of the light strip.

[0159] It should be explained that the historical average LED strip environment vector refers to the average vector of the historical LED strip environment vectors recorded during all data monitoring processes (this average vector is the average of the values ​​in each historical LED strip environment vector). The historical LED strip environment vector refers to the current LED strip environment vector recorded during a specific data prediction of the LED strip. The historical continuous LED strip lifetime value refers to the lifetime value corresponding to multiple current LED strip operating characteristic groups under the historical average LED strip environment vector. The calculation steps for this historical continuous LED strip lifetime value are the same as those described above for calculating the current predicted LED strip lifetime value based on multiple current LED strip operating characteristic groups, the current LED strip environment vector, and the target lifetime matching database, and will not be repeated here. This historical continuous LED strip lifetime value represents the LED strip lifetime value if the environmental factors during the current data monitoring of the LED strip are the same as the previous environmental factors (i.e., the historical average LED strip environment vector is the same as the current LED strip environment vector).

[0160] Furthermore, the total historical monitoring duration refers to the sum of the total monitoring time for the light strip to be predicted. The current monitoring duration refers to the duration of a single data monitoring session for the light strip to be predicted.

[0161] Specifically, the target predicted LED strip lifespan value is expressed as follows:

[0162] ,

[0163] in, This represents the target predicted lifespan value of the LED strip. This indicates the historical predicted lifespan of the LED strip. This indicates the total duration of historical monitoring. Indicates the current monitoring duration. This indicates the historical lifespan value of the LED strip. This indicates the current predicted lifespan of the LED strip.

[0164] It is clear that in the above formula for calculating the predicted lifespan of the target LED strip, The term represents the proportion of the historical continuous lifespan value of the light strip. The larger this term is, the longer the light strip to be predicted has worked under the historical average light strip environment vector, that is, the higher the calculation weight of the historical continuous lifespan value of the light strip. The term represents the proportion of the current predicted lifespan value of the light strip. The larger the term, the longer the light strip to be predicted will work under the current light strip environment vector, that is, the higher the calculation weight of the current predicted lifespan value of the light strip.

[0165] S6. Based on the target predicted lifespan value of the light strip, complete the prediction of the light strip lifespan based on multi-source data fusion.

[0166] Understandably, after obtaining the target predicted LED strip lifespan value, it needs to be stored in the data storage unit for later retrieval. Simultaneously, the target predicted LED strip lifespan value needs to be sent to the control center, where maintenance personnel will perform subsequent operations, such as LED strip maintenance or replacement.

[0167] To address the problems described in the background art, this invention first constructs a light strip data fusion model. This step, through the integration of a multi-unit collaborative framework, achieves real-time acquisition, feature analysis, and efficient storage of multi-source data. Compared to existing technologies where data processing is fragmented or lacks a fusion mechanism, this step improves the overall integrity and automation level of data processing, providing a reliable computational foundation for lifespan prediction. Next, this scheme utilizes a light strip monitoring index set to conduct lifespan tests on multiple test light strip segments, obtaining a target lifespan matching database. This step, by introducing environmental vector labeling and lifespan data analysis, constructs a historical database containing environmental factors. Compared to existing technologies that often ignore the impact of changes in the working environment, this step enables the prediction model to dynamically match environmental conditions, thereby enhancing the adaptability and accuracy of lifespan prediction. Furthermore, based on the current monitoring time, the target lifespan matching database, and the light strip data fusion... The integrated model predicts the lifespan of the LED strip under test, obtaining the current predicted lifespan value and historical predicted lifespan values. This step, by fusing real-time monitoring data and historical parameter sequences, achieves dynamic and continuous lifespan assessment. Compared with existing technologies that predict based solely on instantaneous data, this step provides a more comprehensive perspective on performance evolution and reduces the volatility of prediction results. Finally, this scheme uses historical predicted lifespan values ​​to correct the current predicted lifespan value for historical environments, obtaining the target predicted lifespan value. This step, through an environmental correction formula, offsets prediction biases caused by sudden environmental changes. Compared with existing technologies that handle environmental factors crudely or lack correction mechanisms, this step improves the stability and reliability of predictions, ensuring consistency of lifespan values ​​under different environments. Therefore, this invention can improve the stability and environmental adaptability of LED strip lifespan prediction and reduce prediction biases caused by sudden environmental changes.

[0168] like Figure 2 The diagram shown is a functional block diagram of a LED strip life prediction system based on multi-source data fusion provided in an embodiment of the present invention.

[0169] The LED strip life prediction system 100 based on multi-source data fusion described in this invention can be installed in an electronic device. Depending on the functions implemented, the LED strip life prediction system 100 may include a fusion model construction module 101, a matching data acquisition module 102, a current life prediction module 103, and a historical environment correction module 104. The module described in this invention can also be called a unit, which refers to a series of computer program segments that can be executed by the processor of an electronic device and can perform a fixed function, and which are stored in the memory of the electronic device.

[0170] The fusion model construction module 101 is used to determine the light strip to be predicted and the light strip monitoring index set, obtain multiple test light strip segments based on the light strip to be predicted, wherein the light strip monitoring index set includes multiple light strip monitoring indicators, and construct a light strip data fusion model, wherein the light strip data fusion model includes: a data monitoring unit, a feature statistics unit and a data storage unit.

[0171] The matching data acquisition module 102 is used to perform life tests on multiple test light strip segments using a light strip monitoring index set to obtain a target life matching database. The target life matching database includes multiple target life matching datasets, and each target life matching dataset corresponds one-to-one with a test light strip segment.

[0172] The current lifespan prediction module 103 is used to receive a lifespan prediction instruction, determine the current monitoring time based on the lifespan prediction instruction, and predict the lifespan of the light strip to be predicted according to the current monitoring time, the target lifespan matching database and the light strip data fusion model, so as to obtain the current predicted lifespan value and the historical predicted lifespan value of the light strip.

[0173] The historical environment correction module 104 is used to correct the current predicted lifespan of the light strip using historical predicted lifespan values ​​to obtain the target predicted lifespan value of the light strip.

[0174] In detail, the modules in the LED strip life prediction system 100 based on multi-source data fusion described in this embodiment of the invention employ the same methods as described above. Figure 1 The method used is the same as the one described above for predicting the lifespan of LED strips based on multi-source data fusion, and it can produce the same technical effect, so it will not be repeated here.

[0175] like Figure 3 The diagram shown is a schematic representation of an electronic device for implementing a method for predicting the lifespan of LED strips based on multi-source data fusion, according to an embodiment of the present invention.

[0176] The electronic device 1 may include a processor 10, a memory 11 and a bus 12, and may also include a computer program stored in the memory 11 and capable of running on the processor 10, such as a program for predicting the lifespan of a light strip based on multi-source data fusion.

[0177] The memory 11 includes at least one type of readable storage medium, such as flash memory, portable hard drive, multimedia card, card-type memory (e.g., SD or DX memory), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 11 can be an internal storage unit of the electronic device 1, such as a portable hard drive. In other embodiments, the memory 11 can be an external storage device of the electronic device 1, such as a plug-in portable hard drive, smart media card (SMC), secure digital card (SD), flash card, etc., equipped on the electronic device 1. Furthermore, the memory 11 includes both internal storage units and external storage devices of the electronic device 1. The memory 11 can be used not only to store application software and various types of data installed on the electronic device 1, such as the code of a lamp strip life prediction method program based on multi-source data fusion, but also to temporarily store data that has been output or will be output.

[0178] In some embodiments, the processor 10 may be composed of integrated circuits, such as a single packaged integrated circuit or multiple integrated circuits with the same or different functions, including combinations of one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and various control chips. The processor 10 is the control unit of the electronic device, connecting various components of the entire electronic device through various interfaces and lines. It executes programs or modules stored in the memory 11 (e.g., a lamp strip life prediction method program based on multi-source data fusion) and calls data stored in the memory 11 to perform various functions of the electronic device 1 and process data.

[0179] The bus 12 can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus 12 can be divided into an address bus, a data bus, a control bus, etc. The bus 12 is configured to realize the connection and communication between the memory 11 and at least one processor 10, etc.

[0180] Figure 3 Only electronic devices with components are shown; it will be understood by those skilled in the art that... Figure 3 The structure shown does not constitute a limitation on the electronic device 1, and may include fewer or more components than shown, or combine certain components, or have different component arrangements.

[0181] For example, although not shown, the electronic device 1 may also include a power supply (such as a battery) to power the various components. Preferably, the power supply can be logically connected to the at least one processor 10 through a power management device, thereby enabling functions such as charging management, discharging management, and power consumption management. The power supply may also include one or more DC or AC power supplies, recharging devices, power fault detection circuits, power converters or inverters, power status indicators, and other arbitrary components. The electronic device 1 may also include various sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be described in detail here.

[0182] Furthermore, the electronic device 1 may also include a network interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a Wi-Fi interface, a Bluetooth interface, etc.), which is typically used to establish communication connections between the electronic device 1 and other electronic devices.

[0183] Optionally, the electronic device 1 may further include a user interface, which may be a display, an input unit (such as a keyboard), and optionally, a standard wired interface or a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen, etc. The display may also be appropriately referred to as a screen or display unit, used to display information processed in the electronic device 1 and to display a visual user interface.

[0184] The program for predicting the lifespan of a light strip based on multi-source data fusion, stored in the memory 11 of the electronic device 1, is a combination of multiple instructions. When run in the processor 10, it can achieve the following:

[0185] The light strip to be predicted and the set of light strip monitoring indicators are determined. Multiple test light strip segments are obtained based on the light strip to be predicted. The set of light strip monitoring indicators includes multiple light strip monitoring indicators.

[0186] A light strip data fusion model is constructed, which includes: a data monitoring unit, a feature statistics unit, and a data storage unit;

[0187] Life tests were conducted on multiple test light strip segments using a set of light strip monitoring indicators to obtain a target life matching database. The target life matching database includes multiple target life matching datasets, and each target life matching dataset corresponds one-to-one with a test light strip segment.

[0188] Receive a lifetime prediction command, determine the current monitoring time based on the lifetime prediction command, and perform lifetime prediction on the light strip to be predicted according to the current monitoring time, the target lifetime matching database and the light strip data fusion model, to obtain the current predicted lifespan value and the historical predicted lifespan value of the light strip.

[0189] By using historical predicted LED strip lifespan values ​​to correct the current predicted LED strip lifespan value for historical environmental factors, the target predicted LED strip lifespan value is obtained.

[0190] Based on the target predicted lifespan value, the lifespan prediction of the light strip is completed based on multi-source data fusion.

[0191] Specifically, the processor 10's implementation method for the above instructions can be found in [reference needed]. Figures 1 to 3 The descriptions of the relevant steps in the corresponding embodiments are not repeated here.

[0192] Furthermore, if the modules / units integrated in the electronic device 1 are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. The computer-readable storage medium can be volatile or non-volatile. For example, the computer-readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, or a read-only memory (ROM).

[0193] The present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor of an electronic device, can perform the following:

[0194] The light strip to be predicted and the set of light strip monitoring indicators are determined. Multiple test light strip segments are obtained based on the light strip to be predicted. The set of light strip monitoring indicators includes multiple light strip monitoring indicators.

[0195] A light strip data fusion model is constructed, which includes: a data monitoring unit, a feature statistics unit, and a data storage unit;

[0196] Life tests were conducted on multiple test light strip segments using a set of light strip monitoring indicators to obtain a target life matching database. The target life matching database includes multiple target life matching datasets, and each target life matching dataset corresponds one-to-one with a test light strip segment.

[0197] Receive a lifetime prediction command, determine the current monitoring time based on the lifetime prediction command, and perform lifetime prediction on the light strip to be predicted according to the current monitoring time, the target lifetime matching database and the light strip data fusion model, to obtain the current predicted lifespan value and the historical predicted lifespan value of the light strip.

[0198] By using historical predicted LED strip lifespan values ​​to correct the current predicted LED strip lifespan value for historical environmental factors, the target predicted LED strip lifespan value is obtained.

[0199] Based on the target predicted lifespan value, the lifespan prediction of the light strip is completed based on multi-source data fusion.

[0200] In the embodiments provided by this invention, it should be understood that the disclosed devices, systems, and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative, and actual implementations may have other classification methods.

[0201] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0202] Furthermore, the functional modules in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in the form of hardware plus software functional modules.

[0203] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0204] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A method for predicting the lifespan of LED strip lights based on multi-source data fusion, characterized in that, The method includes: The light strip to be predicted and the set of light strip monitoring indicators are determined. Multiple test light strip segments are obtained based on the light strip to be predicted. The set of light strip monitoring indicators includes multiple light strip monitoring indicators. A light strip data fusion model is constructed, which includes: a data monitoring unit, a feature statistics unit, and a data storage unit; Life tests were conducted on multiple test light strip segments using a set of light strip monitoring indicators to obtain a target life matching database. The target life matching database includes multiple target life matching datasets, and each target life matching dataset corresponds one-to-one with a test light strip segment. Receive a lifetime prediction command, determine the current monitoring time based on the lifetime prediction command, and perform lifetime prediction on the light strip to be predicted according to the current monitoring time, the target lifetime matching database and the light strip data fusion model, to obtain the current predicted lifespan value and the historical predicted lifespan value of the light strip. By using historical predicted LED strip lifespan values ​​to correct the current predicted LED strip lifespan value for historical environmental factors, the target predicted LED strip lifespan value is obtained. Based on the target predicted lifespan value, the lifespan prediction of the light strip is completed based on multi-source data fusion.

2. The method for predicting the lifespan of LED strips based on multi-source data fusion as described in claim 1, characterized in that, The method involves using a set of LED strip monitoring indicators to perform life tests on multiple LED strip segments, resulting in a target lifespan matching database, including: Perform the following operation on each of the multiple test light strip segments: Determine the working environment of the test light strip segment, and construct the test light strip environment vector based on the working environment of the test light strip; Based on the LED strip monitoring index set, life data analysis was performed on the test LED strip segment to obtain the LED strip life matching dataset. The test LED strip environment vector is used to label the LED strip lifespan matching dataset to obtain the target lifespan matching dataset; The target life matching dataset corresponding to each test light strip segment is compiled to obtain the target life matching database.

3. The method for predicting the lifespan of LED strips based on multi-source data fusion as described in claim 2, characterized in that, The process involves analyzing the lifespan data of the test LED strip segment based on the LED strip monitoring index set to obtain an LED strip lifespan matching dataset, including: Data monitoring is performed on the test light strip segment based on the light strip monitoring index set to obtain multiple test light strip parameter sequences, in which the test light strip parameter sequences correspond one-to-one with the light strip monitoring indexes; Based on feature analysis of multiple test light strip parameter sequences, multiple test light strip operation feature groups are obtained, in which the test light strip operation feature groups correspond one-to-one with the test light strip parameter sequences; The lifespan of the test LED strip segment is measured to obtain the test LED strip lifespan value; The lifespan values ​​of the test LED strips are used to match the operating characteristic groups of multiple test LED strips to obtain LED strip lifespan matching data. If the test light strip life value is not less than the preset light strip life threshold, then return to the step of monitoring the test light strip segment based on the light strip monitoring index set until the test light strip life value is less than the light strip life threshold. If the test LED strip lifespan value is less than the LED strip lifespan threshold, then the LED strip lifespan matching data is summarized to obtain the LED strip lifespan matching dataset.

4. The method for predicting the lifespan of LED strips based on multi-source data fusion as described in claim 3, characterized in that, The feature analysis based on multiple test light strip parameter sequences yields multiple test light strip operation feature groups, including: For each of the multiple test LED strip parameter sequences, perform the following operation: Mathematical statistical feature analysis was performed on the parameter sequence of the test LED strip to obtain the short-term operating feature group of the test LED strip. Determine the total sequence of historical light strip parameters based on the test light strip parameter sequence; The test light strip parameter sequence is added to the historical light strip parameter sequence to obtain the total test light strip parameter sequence; Mathematical statistical feature analysis was performed on the total sequence of test LED strip parameters to obtain the long-term operating characteristic group of the test LED strip. The short-term LED strip operation characteristic group and the long-term LED strip operation characteristic group are combined to obtain the test LED strip operation characteristic group; By summarizing the test light strip operation feature groups corresponding to each test light strip parameter sequence, multiple test light strip operation feature groups are obtained.

5. The method for predicting the lifespan of LED strips based on multi-source data fusion as described in claim 4, characterized in that, The process of predicting the lifespan of the light strip to be predicted based on the current monitoring time, the target lifespan matching database, and the light strip data fusion model, to obtain the current predicted lifespan value and the historical predicted lifespan value, includes: Determine the target light strip environment for the light strip to be predicted; Based on the data monitoring unit and the set of light strip monitoring indicators in the light strip data fusion model, data monitoring is performed on the light strip to be predicted to obtain multiple target light strip parameter sequences. Among them, the target light strip parameter sequences in the multiple target light strip parameter sequences correspond one-to-one with the light strip monitoring indicators. By using the feature statistics unit to perform feature statistics on the parameter sequences of multiple target light strips, multiple short-term operational feature groups of targets are obtained. Based on the current monitoring time, read the total sequence of multiple historical monitoring parameters and the historical predicted lifespan value of the light strip from the data storage unit; By supplementing multiple target light strip parameter sequences with multiple historical monitoring parameter sequences, multiple current monitoring parameter sequences are obtained. By using the feature statistics unit to perform feature statistics on the total sequence of multiple current monitoring parameters, multiple long-term operating feature groups of targets are obtained. By merging multiple short-term and long-term target operation characteristic groups, multiple current light strip operation characteristic groups are obtained. Based on the current monitoring time, environmental parameters of the target light strip environment are acquired to obtain the current light strip environment vector; The predicted lifespan of the current LED strip is calculated based on multiple current LED strip operating feature groups, the current LED strip environment vector, and the target lifespan matching database.

6. The method for predicting the lifespan of LED strips based on multi-source data fusion as described in claim 5, characterized in that, The calculation of the current predicted lifespan value of the light strip based on multiple current light strip operating feature groups, the current light strip environment vector, and the target lifespan matching database includes: For each target lifetime matching dataset in the target lifetime matching database, perform the following operation: Obtain the target light strip environment vector corresponding to the target lifetime matching dataset; Extract target lifetime matching data sequentially from the target lifetime matching dataset, and record the extracted target lifetime matching data as the comparison lifetime matching data; The lifespan values ​​of the comparison light strips and multiple sets of operation characteristics of the comparison light strips were identified in the comparison lifespan matching data. Calculate the similarity of comparative features based on multiple current light strip operation feature groups and multiple comparative light strip operation feature groups; The similarity scores of the comparative features corresponding to each comparative lifetime matching data are summarized to obtain the comparative feature similarity set; The optimal feature similarity is identified in the set of comparative feature similarities, and the lifespan value of the comparative light strip in the target lifespan matching data corresponding to the optimal feature similarity is recorded as the optimal light strip lifespan value. The optimal LED strip lifespan value and the target LED strip environment vector are merged to obtain the optimal LED strip fusion data; The optimal LED strip fusion dataset is obtained by summing up the optimal LED strip fusion dataset corresponding to each target lifetime matching dataset; The current predicted lifespan value of the light strip is obtained by weighted calculation based on the optimal light strip fusion dataset and the current light strip environment vector.

7. The method for predicting the lifespan of LED strips based on multi-source data fusion as described in claim 6, characterized in that, The step of calculating the similarity of comparative features based on multiple current light strip operation feature groups and multiple comparative light strip operation feature groups includes: A current light strip operation feature matrix is ​​constructed based on multiple current light strip operation feature groups, and a comparison light strip operation feature matrix is ​​constructed based on multiple comparison light strip operation feature groups. The similarity of the comparative features is calculated based on the current LED strip operation feature matrix and the comparative LED strip operation feature matrix. The similarity of the comparative features is expressed as follows: ， in, Indicates the similarity of contrasting features. This indicates the row number of the current LED strip's operating characteristic matrix or the row number of the LED strip's operating characteristic matrix being compared. This indicates the number of columns in the current LED strip's operating characteristic matrix or the number of columns in the comparison LED strip's operating characteristic matrix. This represents an exponential function with the natural constant as its base. This indicates taking the absolute value. The first element in the comparison light strip operation feature matrix refers to the first element. line, number Column matrix elements, This represents the first element in the current LED strip operation feature matrix. line, number Columns of matrix elements.

8. The method for predicting the lifespan of LED strips based on multi-source data fusion as described in claim 7, characterized in that, The step of using historical predicted LED strip lifespan values ​​to correct the current predicted LED strip lifespan value for historical environmental factors, and obtaining the target predicted LED strip lifespan value, includes: Obtain the historical average LED strip environment vector; The historical extended lifespan value of the light strip is calculated based on multiple current light strip operation feature groups, historical average light strip environment vectors, and target lifespan matching database. Obtain the total historical monitoring duration and the current monitoring duration; The target predicted lifespan of the light strip is calculated based on the total historical monitoring duration, the current monitoring duration, the historical predicted lifespan of the light strip, the historical extended lifespan of the light strip, and the current predicted lifespan of the light strip.

9. The method for predicting the lifespan of LED strips based on multi-source data fusion as described in claim 8, characterized in that, The target predicted lifespan value of the light strip is expressed as: ， in, This represents the target predicted lifespan value of the LED strip. This indicates the historical predicted lifespan of the LED strip. This indicates the total duration of historical monitoring. Indicates the current monitoring duration. This indicates the historical lifespan value of the LED strip. This indicates the current predicted lifespan of the LED strip.

10. A light strip life prediction system based on multi-source data fusion, characterized in that, The system includes: The fusion model construction module is used to determine the light strip to be predicted and the light strip monitoring index set. Based on the light strip to be predicted, multiple test light strip segments are obtained. The light strip monitoring index set includes multiple light strip monitoring indicators. The light strip data fusion model is constructed, which includes: a data monitoring unit, a feature statistics unit, and a data storage unit. The matching data acquisition module is used to perform life tests on multiple test light strip segments using the light strip monitoring index set to obtain a target life matching database. The target life matching database includes multiple target life matching datasets, and each target life matching dataset corresponds one-to-one with a test light strip segment. The current lifespan prediction module is used to receive lifespan prediction instructions, determine the current monitoring time based on the lifespan prediction instructions, and predict the lifespan of the light strip to be predicted based on the current monitoring time, the target lifespan matching database and the light strip data fusion model, so as to obtain the current predicted lifespan value and the historical predicted lifespan value of the light strip. The historical environment correction module is used to correct the current predicted lifespan of the light strip using historical predicted lifespan values, so as to obtain the target predicted lifespan value of the light strip.

Images