Miniled module life prediction method and device based on operation data driving and storage medium

Abstract

The application provides a Miniled module life prediction method and device based on operation data driving and a storage medium, relates to the technical field of display, and first collects multi-source operation data and full-cycle historical life correlation data of a MiniLED module, then constructs a life consumption interaction network with a target life influence factor as a core node and a dynamic interaction relationship between factors as a flexible connection edge, then inputs the multi-source operation data into the network, performs cross-dimension dynamic interaction coupling with the full-cycle historical life correlation data, generates real-time historical interaction coupling results, dynamically adapts node response modes to generate an adaptive life consumption rate, and finally generates a residual life prediction result according to the adaptive life consumption rate and current comprehensive performance state data of the module, and reversely inputs subsequent actual data into the network to dynamically adjust the interaction relationship, so that the application can accurately predict the life of the MiniLED module.

Description

Miniled module lifetime prediction method, device, and storage medium based on operational data Technical Field

[0001] This invention relates to the field of display technology, and more specifically, to a method, apparatus, and storage medium for predicting the lifetime of a Miniled module based on runtime data. Background Technology

[0002] In the field of display technology, MiniLED modules have been widely used in high-end display devices due to their superior characteristics such as high brightness, high contrast, and high resolution. However, the lifespan of MiniLED modules has always been a key factor restricting their large-scale adoption and long-term stable use. Accurately predicting the lifespan of MiniLED modules is of great value for planning maintenance strategies in advance, reducing operation and maintenance costs, and ensuring the reliable operation of display devices.

[0003] Currently, most existing lifespan prediction methods have limitations. Some methods rely solely on a single type of data, such as operating load data or ambient temperature data, neglecting the combined impact of other important factors on module lifespan, resulting in inaccurate predictions. Other methods, while considering multiple factors, fail to adequately account for the dynamic interactions between these factors, thus failing to accurately reflect the complex lifespan degradation mechanisms of modules during actual operation. Furthermore, most existing methods lack in-depth analysis and utilization of historical data, failing to dynamically adjust the prediction model based on the module's historical operating conditions, making it difficult to adapt to changes in module lifespan under different operating stages and environmental conditions. Summary of the Invention

[0004] In view of the aforementioned problems, and in conjunction with the first aspect of the present invention, embodiments of the present invention provide a method for predicting the lifetime of a minimized module based on runtime data, the method comprising:

[0005] Collect multi-source operational data and full-cycle historical lifespan correlation data of the Miniled module. The multi-source operational data includes operational load data, environmental impact data, performance feedback data, and component collaboration data. The full-cycle historical lifespan correlation data includes past multi-source operational records, lifespan end status records, stage performance degradation trajectories, and component interaction loss records.

[0006] Using the target lifetime influencing factor as the core node and the dynamic interaction relationship between factors as the flexible connection edge, a lifetime consumption interaction network of the Miniled module is constructed. The target lifetime influencing factor includes load effect factor, environmental correlation factor, performance degradation factor and component synergy factor.

[0007] Multi-source operational data is input into the lifetime consumption interaction network and dynamically coupled across dimensions with the stage performance degradation trajectory and component interaction loss records in the full-cycle historical lifetime correlation data to generate real-time historical interaction coupling results.

[0008] Based on the real-time historical interaction coupling results, the node response mode of the lifetime consumption interaction network is dynamically adapted according to the real-time changes in data to generate an adaptive lifetime consumption rate.

[0009] Based on the adaptive lifetime consumption rate and the current comprehensive performance status data of the Miniled module, the remaining lifetime prediction result of the Miniled module is generated. The actual operating data and actual lifetime status data generated by the Miniled module are then input back into the lifetime consumption interaction network to dynamically adjust the strength of the interaction relationship between core nodes and the transmission efficiency of flexible connection edges.

[0010] Furthermore, embodiments of the present invention also provide a Miniled module lifetime prediction device based on runtime data, characterized in that it includes:

[0011] A processor; a machine-readable storage medium for storing machine-executable instructions of the processor; wherein the processor is configured to execute the above-described runtime data-driven Miniled module lifetime prediction method by executing the machine-executable instructions.

[0012] In another aspect, embodiments of the present invention also provide a computer-readable storage medium, the computer-readable storage medium including machine-executable instructions, the machine-executable instructions being stored in the computer-readable storage medium, a processor of a computer device reading the machine-executable instructions from the computer-readable storage medium, the processor executing the machine-executable instructions, causing the computer device to execute the above-described method for predicting the lifetime of a minimized module based on runtime data.

[0013] Based on the above, by collecting multi-source operational data and full-cycle historical lifetime correlation data of MiniLED modules, covering information on operating load, environmental effects, performance feedback, component collaboration, and other aspects, as well as historical data such as past multi-source operational records, lifetime end-of-life status records, stage performance degradation trajectories, and component interaction loss records, a lifetime consumption interaction network is constructed with the target lifetime influencing factor as the core node. Considering the dynamic interaction relationships between factors, this method can realistically simulate the complex process of lifetime consumption caused by the mutual influence and combined effects of various factors during actual module operation, overcoming the deficiency of existing methods that ignore the dynamic interaction between factors. Cross-dimensional dynamic interaction coupling of multi-source operational data and full-cycle historical lifetime correlation data generates real-time historical interaction coupling results. Based on this, the node response mode of the lifetime consumption interaction network is dynamically adapted to generate an adaptive lifetime consumption rate. This allows for dynamic adjustment of the prediction model according to the real-time operation of the module, improving the accuracy and adaptability of the prediction. Finally, by combining the adaptive lifetime consumption rate and the module's current comprehensive performance status data, the remaining lifetime prediction result is generated. The subsequent actual operating data and actual lifetime status data are then fed back into the network to dynamically adjust the interaction strength and transmission efficiency, which can continuously optimize the prediction model and further improve the accuracy and reliability of the prediction. Attached Figure Description

[0014] Figure 1 is a schematic diagram of the execution flow of the Miniled module lifetime prediction method based on runtime data provided in an embodiment of the present invention.

[0015] Figure 2 is a schematic diagram of exemplary hardware and software components of the Miniled module lifetime prediction device based on runtime data provided in an embodiment of the present invention. Detailed Implementation

[0016] The present invention will now be described in detail with reference to the accompanying drawings. Figure 1 is a flowchart illustrating a method for predicting the lifetime of a Miniled module based on runtime data, according to an embodiment of the present invention. The method for predicting the lifetime of a Miniled module based on runtime data will now be described in detail.

[0017] Step S110: Collect multi-source operating data and full-cycle historical lifetime correlation data of the Miniled module. The multi-source operating data includes operating load data, environmental impact data, performance feedback data and component collaboration data. The full-cycle historical lifetime correlation data includes past multi-source operating records, lifetime end status records, stage performance degradation trajectory and component interaction loss records.

[0018] Taking a Miniled module from an electronic equipment manufacturer as an example, the company deploys various sensors and data acquisition devices in the module production and usage stages. Regarding operational load data, the system collects current, voltage, and power data in high-definition and standard display modes, such as current data in high-definition display mode, reflecting workload intensity. Environmental impact data includes temperature, humidity, air pressure, and electromagnetic interference intensity, such as environmental data under high-temperature and high-humidity testing conditions. Performance feedback data includes real-time monitoring data and attenuation data for performance parameters such as brightness, contrast, and color reproduction, such as periodically recorded brightness changes. Component collaboration data includes signal transmission delays and power distribution between chips, circuits, and optical components, such as the signal transmission time between the driver chip and the light-emitting chip.

[0019] The full-cycle historical lifespan data is extracted from the enterprise database. Past multi-source operation records include operation data from different batches and scenarios. Lifespan end status records include performance parameters, appearance, fault location, etc., such as brightness decay and local chip damage when a module reaches the end of its lifespan. Stage performance decay trajectory records the performance decay at different lifespan stages, such as recording brightness and contrast change curves in the early, middle, and late stages. Component interaction loss records record the changes in component interaction loss over time, such as the changes in signal transmission loss between the driver and the light-emitting chip.

[0020] Step S120: Using the target lifetime impact factor as the core node and the dynamic interaction relationship between factors as the flexible connection edge, construct the lifetime consumption interaction network of the Miniled module. The target lifetime impact factor includes load effect factor, environmental correlation factor, performance degradation factor and component synergy factor.

[0021] Step S121: Extract the load effect factor from the multi-source operation data. The load effect factor reflects the direct effect of various workloads on lifetime consumption during the operation of the Miniled module, covering the lifetime loss correlation characteristics corresponding to the load type and the loss accumulation characteristics corresponding to load changes.

[0022] In this embodiment, the load type is first analyzed. For example, the module's operating modes include normal display mode, high-definition display mode, and high-brightness display mode. Different modes have different load types, and their corresponding lifespan loss correlation characteristics are also different. For normal display mode, the load intensity is relatively low, and the lifespan loss rate is slow; for high-brightness display mode, the load intensity is high, and the lifespan loss rate is fast. Then, the load change situation is analyzed, such as the load duration and change frequency. When the load duration is long and the change frequency is high, the loss accumulation characteristic is more obvious. Through the analysis of the operating load data, a load effect factor is extracted. This load effect factor contains lifespan loss correlation characteristic data under different load types and loss accumulation characteristic data under load changes. For example, it is represented in the form of a vector, where each vector dimension corresponds to a load type or load change characteristic, and the value in the vector represents the degree of influence of the characteristic on lifespan loss.

[0023] Step S122: Extract environmental correlation factors from the environmental impact data of multi-source operation data. The environmental correlation factors reflect the indirect impact characteristics of the external environment in which the Miniled module is located on its lifespan consumption, covering the lifespan consumption triggering characteristics corresponding to environmental elements and the consumption aggravation characteristics corresponding to environmental changes.

[0024] In this embodiment, environmental factors include temperature, humidity, air pressure, and electromagnetic interference, etc., and different environmental factors correspond to different lifespan loss triggering characteristics. For example, high-temperature environments trigger increased thermal stress in the module, leading to accelerated chip aging; high-humidity environments trigger circuit corrosion in the module, affecting the module's performance and lifespan. Regarding the loss aggravation characteristics corresponding to environmental changes, for example, rapid temperature changes exacerbate the thermal expansion and contraction of the module, causing loosening of the connection between the chip and the circuit board, thereby aggravating lifespan loss. By analyzing the environmental impact data, environmental correlation factors are extracted. These environmental correlation factors include lifespan loss triggering characteristic data under different environmental factors and loss aggravation characteristic data under environmental changes. For example, they are represented in matrix form, where rows correspond to different environmental factors, columns correspond to different environmental changes, and the values ​​in the matrix represent the degree of influence of the environmental factor and environmental change on lifespan loss.

[0025] Step S123: Extract the performance degradation factor from the performance feedback data of multi-source operation data. The performance degradation factor reflects the correlation between performance output changes and lifetime consumption during the operation of the Miniled module, covering the lifetime loss mapping characteristics corresponding to performance parameter changes and the loss rate characteristics corresponding to performance stability.

[0026] In this embodiment, performance parameter changes include variations in brightness, contrast, and color fidelity, with different lifetime loss mapping characteristics corresponding to different performance parameter changes. For example, there is a certain mapping relationship between brightness decay and lifetime loss; the greater the brightness decay, the greater the lifetime loss. Regarding performance stability, fluctuations in performance output reflect the module's stability; modules with poor performance stability experience a faster lifetime loss rate. By analyzing performance feedback data, a performance decay factor is extracted. This factor includes lifetime loss mapping characteristic data under different performance parameter changes and loss rate characteristic data under performance stability, for example, represented in tensor form. Different dimensions of the tensor correspond to different performance parameters and performance stability conditions, and the values ​​in the tensor represent the degree of influence of the performance parameter change and performance stability condition on lifetime loss.

[0027] Step S124: Extract component coordination factors from the component coordination data of multi-source operation data. The component coordination factors reflect the synergistic effect of the interaction of various components within the Miniled module on the lifetime consumption, covering the loss correlation characteristics corresponding to the component matching accuracy and the loss accumulation characteristics corresponding to the component response synchronization.

[0028] In this embodiment, component matching accuracy includes signal transmission accuracy between the driver chip and the light-emitting chip, power distribution accuracy between circuit components, etc. Different matching accuracies correspond to different loss correlation characteristics. For example, with high matching accuracy, the loss between components is small, and the lifespan loss is also small; with low matching accuracy, the loss is large, and the lifespan loss is also large. Regarding component response synchronization, the better the response synchronization between components, the slower the loss accumulation and the smaller the lifespan loss; with poor response synchronization, the loss accumulation is fast, and the lifespan loss is large. By analyzing the component coordination data, a component coordination factor is extracted. This component coordination factor contains loss correlation characteristic data under different component matching accuracies and loss accumulation characteristic data under component response synchronization. For example, it can be represented in the form of a multi-dimensional array, where different dimensions of the array correspond to different component matching accuracies and component response synchronization conditions, and the values ​​in the array represent the degree of influence of the matching accuracy and synchronization condition on the lifespan loss.

[0029] Step S125: Extract historical load effect factor, historical environment correlation factor, historical performance degradation factor and historical component synergy factor from the past multi-source operation records of the full-cycle historical lifetime correlation data. Each type of historical factor corresponds to the historical operation record of the real-time target lifetime influence factor, which includes the loss correlation characteristics and change patterns in the historical operation process.

[0030] In this embodiment, the historical load factor corresponds to the historical operation record of the real-time load factor, containing load factor data under different historical periods and usage scenarios. For example, the changes in the load factor of a certain module at different time periods during past use, as well as the corresponding loss correlation characteristics and change patterns; the historical environment correlation factor corresponds to the historical operation record of the real-time environment correlation factor, containing environment correlation factor data under different historical periods and environmental conditions, as well as the corresponding loss correlation characteristics and change patterns; the historical performance degradation factor corresponds to the historical operation record of the real-time performance degradation factor, containing performance degradation factor data under different historical periods and life stages, as well as the corresponding loss correlation characteristics and change patterns; and the historical component coordination factor corresponds to the historical operation record of the real-time component coordination factor, containing component coordination factor data under different historical periods and usage stages, as well as the corresponding loss correlation characteristics and change patterns.

[0031] Step S126: Analyze the direct interaction between the load effect factor and the performance degradation factor, identify the mutual triggering path and influence transmission mode of the two during the lifetime consumption process, and construct a first flexible connection edge based on the direct interaction relationship and influence transmission mode. The first flexible connection edge includes the initial parameter of interaction strength and the parameter of influence transmission efficiency.

[0032] In this embodiment, through analysis of multi-source operational data and full-cycle historical lifespan correlation data, it was found that when the load factor increases, the performance degradation factor also increases. For example, an increase in power in the load factor leads to an increase in module temperature, thereby accelerating brightness degradation in the performance degradation factor. The mutual triggering paths between the two include changes in the load factor directly increasing energy loss within the module, thus affecting the performance degradation factor; changes in the performance degradation factor also feed back to the load factor, for example, performance degradation causes changes in module resistance, thereby affecting parameters such as current and voltage in the load factor. The transmission methods include energy transfer and signal transfer. For example, energy changes in the load factor affect the performance degradation factor through heat transfer, and signal changes in the performance degradation factor affect the load factor through circuit feedback.

[0033] Based on the aforementioned direct interaction relationship and influence transmission method, a first flexible connection edge is constructed. The initial parameter of interaction strength is determined according to the average influence between the load effect factor and the performance degradation factor in historical data. For example, the change in the performance degradation factor is statistically analyzed for each change in the load effect factor in historical data, thereby determining the initial parameter of interaction strength. The influence transmission efficiency parameter is determined according to the time required for the change in the load effect factor to be transmitted to the performance degradation factor and the accuracy of the transmission in historical data. For example, the change in the performance degradation factor after the change in the load effect factor in historical data and the accuracy of the change are statistically analyzed, thereby determining the influence transmission efficiency parameter.

[0034] Step S127: Analyze the indirect interaction between environmental correlation factors and performance degradation factors, identify the mediating path and loss amplification mechanism between the two in the lifetime consumption process, and construct a second flexible connection edge based on the indirect interaction relationship and loss amplification mechanism. The second flexible connection edge includes the initial parameter of interaction strength and the parameter of influence transmission efficiency.

[0035] In this embodiment, changes in the environmental correlation factor will affect the module's working environment, thereby affecting the performance degradation factor. For example, an increase in temperature in the environmental correlation factor will lead to an increase in the module's thermal stress, thereby accelerating the brightness decay in the performance degradation factor. The mediating path here is the module's working environment. At the same time, the synergistic effect of the environmental correlation factor and the load effect factor will amplify the loss. For example, in a high-temperature environment, the increase in the load effect factor will have a more significant impact on the performance degradation factor. This is the loss amplification mechanism.

[0036] Based on the aforementioned indirect interaction relationship and loss amplification mechanism, a second flexible connection edge is constructed. The initial parameter of the interaction strength is determined according to the average influence between the environmental correlation factor and the performance degradation factor in historical data. For example, it is calculated by the change in the performance degradation factor when the environmental correlation factor changes by a certain amount in historical data. The parameter of the influence transmission efficiency is determined according to the time required for the change in the environmental correlation factor to be transmitted to the performance degradation factor in historical data and the accuracy of the transmission. For example, it is calculated by the time it takes for the performance degradation factor to change after the environmental correlation factor changes in historical data, and the accuracy of the change.

[0037] Step S128: Analyze the synergistic interaction between the load effect factor and the environmental correlation factor, identify the joint action path and loss superposition effect of the two in the lifetime consumption process, and construct a third flexible connection edge based on the synergistic interaction relationship and loss superposition effect. The third flexible connection edge includes the initial parameter of interaction strength and the parameter of influence transmission efficiency.

[0038] In this embodiment, the impact on lifespan consumption is more pronounced when both the load factor and the environmental factor increase simultaneously. For example, the synergistic effect of high load and high temperature environment leads to a much faster lifespan consumption rate for the module than the effect of high load or high temperature environment alone. The combined effect path includes the energy change of the load factor and the environmental change of the environmental factor acting together on the internal structure of the module, resulting in increased losses. The loss superposition effect includes the superposition of energy losses and heat losses. For example, the combined effect of energy loss from the load factor and heat loss from the environmental factor causes a sharp increase in the module temperature, accelerating lifespan consumption.

[0039] Based on the aforementioned synergistic interaction relationship and loss superposition effect, a third flexible connection edge is constructed. The initial parameter of the interaction strength is determined according to the average synergistic influence between the load effect factor and the environmental correlation factor in historical data. For example, the degree of influence on lifetime consumption when both change simultaneously in historical data is statistically analyzed. The parameter affecting transmission efficiency is determined according to the transmission time and accuracy of the synergistic effect of the two in historical data. For example, how long does it take for the change in lifetime consumption to be reflected after the synergistic effect of the two in historical data is statistically analyzed, and the accuracy of the change is statistically analyzed.

[0040] Step S129: Analyze the cross-interaction relationship between component synergy factor and load effect factor, environmental correlation factor and performance degradation factor, identify the regulatory path and loss optimization / aggravation mechanism of component synergy factor in various interaction relationships, and construct the fourth flexible connection edge, the fifth flexible connection edge and the sixth flexible connection edge based on the cross-interaction relationship and regulation mechanism. Each flexible connection edge contains the initial parameter of interaction strength and the parameter affecting transmission efficiency.

[0041] Step S129: Analyze the cross-interaction relationship between component synergy factor and load effect factor, environmental correlation factor and performance degradation factor, identify the regulatory path and loss optimization / aggravation mechanism of component synergy factor in various interaction relationships, and construct the fourth flexible connection edge, the fifth flexible connection edge and the sixth flexible connection edge based on the cross-interaction relationship and regulation mechanism. Each flexible connection edge contains the initial parameter of interaction strength and the parameter affecting transmission efficiency.

[0042] Step S1291: Select component coordination factor change data, load effect factor change data, environmental correlation factor change data and performance degradation factor change data under different operating scenarios from multi-source operating data. Different operating scenarios reflect different combinations of load intensity, environmental conditions and component working modes.

[0043] In this embodiment, data from different operating scenarios are selected from multi-source operating data. For example, data on component synergy factors, load effect factors, environmental correlation factors, and performance degradation factors are selected under different scenarios such as low load, normal temperature, normal working mode; high load, high temperature, high brightness working mode; medium load, high humidity, energy saving working mode.

[0044] Step S1292: Perform synchronous analysis on the change data of the component synergy factor and the change data of the load effect factor for each group of components, and extract the synchronicity of the changes, numerical correlation characteristics and mutual triggering relationship between the two in the time dimension.

[0045] In this embodiment, each set of data is analyzed synchronously. For example, under high load, high temperature, and high brightness operating modes, the temporal synchronicity of the component coordination factor change data and the load effect factor change data is analyzed. It is found that when the power in the load effect factor increases, the signal transmission time in the component coordination factor also increases, and the changes of the two are synchronized in time. In terms of numerical correlation characteristics, there is a positive correlation between the increase in the power of the load effect factor and the increase in the signal transmission time of the component coordination factor. In terms of mutual triggering relationship, the increase in the power of the load effect factor triggers the increase in the signal transmission time of the component coordination factor, and the increase in the signal transmission time of the component coordination factor also feeds back to the load effect factor, causing further changes in power.

[0046] Step S1293: Combining the corresponding stage performance degradation trajectory and component interaction loss records in the full-cycle historical lifetime correlation data, analyze the impact of component synergy factor on the loss relationship between load action factor and performance degradation factor under different change synchronicity and numerical correlation characteristics.

[0047] In this embodiment, the impact of different change synchronicity and numerical correlation characteristics is analyzed by combining full-cycle historical lifetime correlation data. For example, when the change synchronicity is high and the numerical correlation characteristic is positively correlated, good coordination of component coordination factors can reduce the loss relationship between load effect factor and performance degradation factor. For example, high signal transmission accuracy in component coordination factors can reduce energy loss of load effect factor, thereby slowing down the change of performance degradation factor. However, when the change synchronicity is low and the numerical correlation characteristic is negatively correlated, the coordination deviation of component coordination factors will exacerbate the loss relationship between load effect factor and performance degradation factor. For example, large signal transmission delay in component coordination factors will lead to increased energy loss of load effect factor, thereby accelerating the change of performance degradation factor.

[0048] Step S1294: Identify the regulatory path of the component synergy factor in the interaction between the load factor and the performance degradation factor, including the positive regulation path of the component synergy factor reducing losses by optimizing load distribution, and the negative regulation path of the component synergy factor exacerbating losses due to synergy deviation.

[0049] In this embodiment, adjustment paths are identified. For example, a positive adjustment path, such as the component coordination factor, optimizes the power distribution between the driver chip and the light-emitting chip, enabling more rational utilization of the load factor's energy, thereby reducing losses and slowing down changes in the performance degradation factor. A negative adjustment path, such as the component coordination factor, causes an unreasonable power distribution between the driver chip and the light-emitting chip due to coordination deviation, leading to increased energy loss in the load factor and accelerating changes in the performance degradation factor.

[0050] Step S1295: Identify the loss optimization mechanism corresponding to the positive adjustment path, that is, under what state the component coordination factor can reduce the impact of the load factor on performance degradation.

[0051] In this embodiment, a loss optimization mechanism is identified. By analyzing historical and experimental data, it was found that when the signal transmission accuracy, power distribution, and response synchronization in the component coordination factor are high, the impact of the load factor on performance degradation can be reduced. For example, when the signal transmission time in the component coordination factor is within a certain range, the variance of power distribution is small, and the deviation of response synchronization is within a certain range, the energy loss of the load factor is small, and the change in the performance degradation factor is also small.

[0052] Step S1296: Identify the loss aggravation mechanism corresponding to the reverse adjustment path, that is, under what state the component coordination factor increases the degree of influence of the load action factor on performance degradation.

[0053] In this embodiment, when the signal transmission delay is large, the power distribution is uneven, or the response synchronization is poor in the component coordination factor, the impact of the load effect factor on performance degradation will increase. For example, when the signal transmission time in the component coordination factor exceeds a certain threshold, the variance of the power distribution is large, or the deviation of the response synchronization exceeds a certain threshold, the energy loss of the load effect factor will increase sharply, and the change of the performance degradation factor will also accelerate.

[0054] Step S1297: Based on the cross-interaction relationship between component coordination factor and load effect factor, positive adjustment path, reverse adjustment path, loss optimization mechanism and loss aggravation mechanism, define the interaction rules and parameter configuration logic of the fourth flexible connection edge.

[0055] In this embodiment, the interaction rules include how the interaction strength and impact on transmission efficiency of the fourth flexible connection edge change when the component coordination factor is in an optimized state, for example, a decrease in interaction strength leads to an increase in transmission efficiency; and how the interaction strength and impact on transmission efficiency of the fourth flexible connection edge change when the component coordination factor is in a deviated state, for example, an increase in interaction strength leads to a decrease in transmission efficiency. The parameter configuration logic includes dynamically adjusting the initial parameters of the interaction strength and the impact on transmission efficiency of the fourth flexible connection edge based on the state parameters of the component coordination factor, for example, when the signal transmission accuracy of the component coordination factor is high, the initial parameter of the interaction strength decreases, and the impact on transmission efficiency increases.

[0056] Step S1298: Set the initial parameters of the interaction strength and the parameters affecting the transmission efficiency of the fourth flexible connection edge. The initial parameters of the interaction strength are determined based on the average adjustment strength of the component coordination factor on the load effect factor in historical data, and the parameters affecting the transmission efficiency are determined based on the average transmission efficiency of the adjustment signal in historical data.

[0057] In this embodiment, the initial parameter of interaction strength is determined based on the average adjustment strength of the component synergy factor on the load effect factor in historical data. For example, the average adjustment strength of the component synergy factor on the load effect factor under different states in historical data is used as the initial parameter of interaction strength. The parameter affecting transmission efficiency is determined based on the average transmission efficiency of the adjustment signal in historical data. For example, the average transmission efficiency is calculated based on the time from the issuance of the adjustment signal of the component synergy factor to its effect on the load effect factor and the accuracy of the adjustment in historical data, and used as the parameter affecting transmission efficiency.

[0058] Step S1299: Using the same analysis method, perform synchronous analysis on the component synergy factor change data and the environmental correlation factor change data, and extract the synchronicity of change, numerical correlation characteristics and mutual triggering relationship between the two.

[0059] In this embodiment, the same analysis method as in step S1292 is used to synchronously analyze the component coordination factor change data and the environmental correlation factor change data. For example, under different environmental conditions, the time synchronization, numerical correlation characteristics, and mutual triggering relationships of the component coordination factor's signal transmission accuracy, power distribution, and other data with the environmental correlation factor's temperature, humidity, and other data are analyzed. It is found that when the temperature in the environmental correlation factor increases, the signal transmission time in the component coordination factor increases, and there is a negative numerical correlation between the two. The mutual triggering relationship is that the temperature change of the environmental correlation factor triggers the signal transmission time change of the component coordination factor, and the signal transmission time change of the component coordination factor also feeds back to the environmental correlation factor, causing further temperature changes.

[0060] Step S12910: Combining full-cycle historical lifetime correlation data, analyze the impact of component synergy factors on the loss relationship between environmental correlation factors and performance degradation factors, and identify the corresponding positive and negative adjustment paths.

[0061] In this embodiment, for example, in a high-temperature environment, good coordination of component coordination factors can reduce the loss relationship between environmental correlation factors and performance degradation factors. For example, high signal transmission accuracy of component coordination factors can reduce energy loss inside the module, thereby slowing down the change of performance degradation factors. This is a positive adjustment path. On the other hand, coordination deviation of component coordination factors will exacerbate the loss relationship between environmental correlation factors and performance degradation factors. For example, large signal transmission delay of component coordination factors will lead to increased energy loss inside the module, thereby accelerating the change of performance degradation factors. This is a negative adjustment path.

[0062] Step S12911: Identify the loss optimization mechanism of the forward adjustment path and the loss aggravation mechanism of the reverse adjustment path, and define the interaction rules and parameter configuration logic of the fifth flexible connection edge.

[0063] In this embodiment, loss optimization mechanisms, such as good coordination of component coordination factors, can optimize the heat dissipation of the module, thereby reducing the impact of environmental correlation factors' temperature on the performance degradation factor. Loss aggravation mechanisms, such as coordination deviation of component coordination factors, can lead to poor heat dissipation of the module, thereby aggravating the impact of environmental correlation factors' temperature on the performance degradation factor. Based on the above mechanisms, the interaction rules and parameter configuration logic of the fifth flexible connection edge are defined. For example, when the component coordination factor is in an optimized state, the interaction strength of the fifth flexible connection edge decreases, affecting the improvement of transmission efficiency; when the component coordination factor is in a deviated state, the interaction strength of the fifth flexible connection edge increases, affecting the reduction of transmission efficiency.

[0064] Step S12912: Set the initial parameters of the interaction strength and the parameters affecting the transmission efficiency of the fifth flexible connection edge. The parameter values ​​are determined based on the statistical analysis results of historical data.

[0065] In this embodiment, the parameter values ​​are based on the statistical analysis results of historical data. For example, the changes in the loss relationship between environmental correlation factors and performance degradation factors under different states of component synergy factors in historical data are statistically analyzed. The average interaction strength and average influence transmission efficiency are calculated and used as the initial parameters of interaction strength and influence transmission efficiency of the fifth flexible connection edge.

[0066] Step S12913: Perform synchronous analysis on the component synergy factor change data and the performance degradation factor change data, and extract the synchronicity of their changes, numerical correlation characteristics and mutual triggering relationship.

[0067] In this embodiment, the changes in component coordination factor and performance degradation factor are analyzed synchronously. For example, the analysis examines the time synchronization, numerical correlation, and mutual triggering relationship between data such as signal transmission accuracy and power distribution of the component coordination factor and data such as brightness and contrast of the performance degradation factor at different life stages. It is found that when the performance degradation factor increases, the signal transmission time of the component coordination factor also increases, and there is a positive numerical correlation between the two. The mutual triggering relationship is that changes in the performance degradation factor lead to changes in the internal structure of the module, thereby affecting the component coordination factor. Changes in the component coordination factor also feed back to the performance degradation factor, causing it to change further.

[0068] Step S12914: Combine the historical lifetime correlation data of the entire life cycle to analyze the impact of the component synergy factor on the loss law of the performance degradation factor itself, and identify the corresponding positive adjustment path and reverse adjustment path.

[0069] In this embodiment, for example, good coordination of component coordination factors can optimize the working state of the module, thereby slowing down the rate of performance degradation factor loss, which is a positive adjustment path; coordination deviation of component coordination factors will cause the working state of the module to deteriorate, thereby accelerating the rate of performance degradation factor loss, which is a negative adjustment path.

[0070] Step S12915: Identify the loss optimization mechanism of the forward adjustment path and the loss aggravation mechanism of the reverse adjustment path, and define the interaction rules and parameter configuration logic of the sixth flexible connection edge.

[0071] In this embodiment, loss optimization mechanisms for the forward adjustment path and loss aggravation mechanisms for the reverse adjustment path are identified. Loss optimization mechanisms, such as good coordination of component coordination factors, can reduce energy loss within the module, thereby mitigating the loss of the performance degradation factor. Loss aggravation mechanisms, such as coordination deviation of component coordination factors, increase energy loss within the module, thereby accelerating the loss of the performance degradation factor. Based on the above mechanisms, the interaction rules and parameter configuration logic of the sixth flexible connection edge are defined. For example, when the component coordination factor is in an optimized state, the interaction strength of the sixth flexible connection edge decreases, affecting the improvement of transmission efficiency; when the component coordination factor is in a deviated state, the interaction strength of the sixth flexible connection edge increases, affecting the reduction of transmission efficiency.

[0072] Step S12916: Set the initial parameters of the interaction strength and the parameters affecting the transmission efficiency of the sixth flexible connection edge. The parameter values ​​are determined based on the statistical analysis results of historical data.

[0073] In this embodiment, the parameter values ​​are based on the statistical analysis results of historical data. For example, the changes in the loss law of the performance degradation factor itself under different states of component coordination factors in the statistical historical data are used to calculate the average interaction strength and average influence transmission efficiency as the initial parameters of the interaction strength and influence transmission efficiency of the sixth flexible connection edge.

[0074] Step S12917: Verify the interaction rules and parameter configuration logic of the fourth, fifth, and sixth flexible connection edges respectively, so that the fourth, fifth, and sixth flexible connection edges reflect the cross-interaction relationship and adjustment mechanism between the component synergy factors and the corresponding core factors.

[0075] In this embodiment, by applying the constructed flexible connection edges to the simulation analysis of historical data, the interaction relationship and adjustment mechanism between the component synergy factor and the corresponding core factor are observed to see if they match the actual situation. For example, in the simulation analysis, when the component synergy factor is in an optimized state, whether the change in the interaction strength and the impact on transmission efficiency of the fourth flexible connection edge can correctly reflect the adjustment effect of the component synergy factor on the loss relationship between the load effect factor and the performance degradation factor; if the verification results do not match the actual situation, the interaction rules and parameter configuration logic are adjusted until the verification passes, ensuring that the fourth, fifth, and sixth flexible connection edges can accurately reflect the cross-interaction relationship and adjustment mechanism between the component synergy factor and the corresponding core factor.

[0076] Step S1210: The load effect factor, environmental correlation factor, performance degradation factor, component coordination factor and various historical factors are used as independent core nodes. The nodes are connected according to the interaction relationship of the first to sixth flexible connection edges to form the initial network structure.

[0077] In this embodiment, for example, the load factor node is connected to the performance degradation factor node via a first flexible connection edge, to the environment-related factor node via a third flexible connection edge, and to the component collaboration factor node via a fourth flexible connection edge; the environment-related factor node is connected to the performance degradation factor node via a second flexible connection edge, to the load factor node via a third flexible connection edge, and to the component collaboration factor node via a fifth flexible connection edge; the performance degradation factor node is connected to the load factor node via a first flexible connection edge, to the environment-related factor node via a second flexible connection edge, and to the component collaboration factor node via a sixth flexible connection edge; the component collaboration factor node is connected to the load factor node via a fourth flexible connection edge, to the environment-related factor node via a fifth flexible connection edge, and to the performance degradation factor node via a sixth flexible connection edge; various historical factor nodes are connected to their corresponding real-time factor nodes, for example, historical load factor nodes are connected to load factor nodes, historical environment-related factor nodes are connected to environment-related factor nodes, etc. Through the above connection methods, an initial lifetime consumption interaction network structure is formed.

[0078] Step S1211: Extract the correspondence between the stage performance degradation trajectory, component interaction loss record and target lifetime in the full-cycle historical lifetime correlation data, and generate the target interaction coupling node. The target interaction coupling node is used to integrate the synergistic effect logic of the target lifetime influencing factor on lifetime degradation and the historical data reference logic.

[0079] In this embodiment, through analysis of historical data, a close correspondence was found between the stage performance degradation trajectory and the load effect factor, environmental correlation factor, performance degradation factor, and component synergy factor in the target lifetime influencing factors. For example, during the mid-life stage of the module, changes in the load effect factor and environmental correlation factor will lead to changes in the slope of the stage performance degradation trajectory. The component interaction loss record also has a correspondence with the component synergy factor and performance degradation factor in the target lifetime influencing factors. For example, changes in signal transmission loss in the component interaction loss record are related to changes in the component synergy factor.

[0080] Based on the above correspondence, a target interaction coupling node is generated. This node integrates the synergistic effect logic of target lifetime influencing factors on lifetime decay and historical data reference logic. The synergistic effect logic includes how the interactions between target lifetime influencing factors jointly affect lifetime decay. For example, the synergistic effect of load factors and environmental factors can accelerate the change of performance decay factors, thereby affecting lifetime decay. The historical data reference logic includes referencing the stage performance decay trajectory and component interaction loss records in historical data to predict the lifetime decay of the current module. For example, when the change of the target lifetime influencing factors of the current module is similar to the change of a certain stage in history, the lifetime of the current module is predicted by referring to the performance decay trajectory and component interaction loss records of that stage.

[0081] Step S1212: Embed the target interactive coupling node into the initial network structure, and connect all core nodes and historical factor nodes by adding flexible connection edges. The added flexible connection edges include the initial parameters of interaction strength and the parameters affecting transmission efficiency.

[0082] In this embodiment, for example, the target interactive coupling node is placed at the center of the initial network structure, and connected to load factor nodes, environmental correlation factor nodes, performance degradation factor nodes, component collaboration factor nodes, and various historical factor nodes through newly added flexible connection edges. The initial parameters of the interaction strength and the influence transmission efficiency parameters of the newly added flexible connection edges are determined based on the correspondence and influence degree between the target interactive coupling node and each core node and historical factor node. For example, the initial parameter of the interaction strength between the target interactive coupling node and the load factor node is determined based on the influence degree of the load factor on the target interactive coupling node in historical data, and the influence transmission efficiency parameter is determined based on the efficiency of the signal transmission of the load factor to the target interactive coupling node in historical data.

[0083] Step S1213: Set the node activation rules and edge propagation rules for the lifetime consumption interaction network. The node activation rules define the conditions for core nodes to trigger responses based on input data and the calculation method for response intensity. The edge propagation rules define the attenuation logic and enhancement logic for flexible connection edges to transmit interactive signals.

[0084] Step S1214: Integrate all node activation rules and edge propagation rules to construct a lifetime consumption interaction network. The constructed lifetime consumption interaction network is used to reflect the full-dimensional dynamic interaction logic between the target lifetime influencing factors, historical factors, and target interactive coupling nodes, and realize cross-dimensional correlation and propagation between input data and historical data.

[0085] In this embodiment, for example, node activation rules and edge propagation rules are written into computer program code and embedded into the construction model of the lifetime consumption interaction network to ensure that each core node and flexible connection edge is activated and propagated according to the set rules. The constructed lifetime consumption interaction network can reflect the full-dimensional dynamic interaction logic between target lifetime influencing factors, historical factors, and target interactive coupling nodes. For example, when real-time operating data of the input module is received, the load effect factor node triggers a response based on the input data and transmits the interaction signal to the performance degradation factor node through the first flexible connection edge, and simultaneously transmits it to the environment-related factor node through the third flexible connection edge. The environment-related factor node also triggers a response based on the input data and transmits it to the performance degradation factor node through the second flexible connection edge. The component collaboration factor node triggers a response based on the input data and transmits it to the corresponding factor node through the fourth, fifth, and sixth flexible connection edges. Various historical factor nodes trigger responses based on the response intensity of the real-time factor nodes. The target interactive coupling node triggers a response based on the received various interaction signals, realizing cross-dimensional correlation and propagation between input data and historical data.

[0086] Step S130: Input multi-source operating data into the lifetime consumption interaction network, and perform cross-dimensional dynamic interaction coupling with the stage performance degradation trajectory and component interaction loss record in the full-cycle historical lifetime correlation data to generate real-time historical interaction coupling results.

[0087] Step S131: Analyze the core node association structure and flexible connection edge transmission logic of the lifetime consumption interaction network, and identify the interaction priority and signal transmission path between load factor nodes, environmental association factor nodes, performance degradation factor nodes, component collaboration factor nodes and target interaction coupling nodes.

[0088] The lifetime consumption interaction network of this enterprise module is analyzed. The core node association structure consists of load, environment, performance degradation, and component collaboration factor nodes connected to the target interaction coupling node, and historical factor nodes connected to their corresponding real-time nodes. In terms of interaction priority, load and environment factor nodes have high priority because they have a significant impact on lifetime consumption. The signal transmission path is as follows: load factor node signals are transmitted to the target interaction coupling node through the first, third, and fourth flexible connection edges; environment factor node signals are transmitted through the second, third, and fifth flexible connection edges; performance degradation factor node signals are transmitted through the first, second, and sixth flexible connection edges; and component collaboration factor node signals are transmitted through the fourth, fifth, and sixth flexible connection edges.

[0089] Step S132: Extract the real-time change trajectory of load effect factor, environmental correlation factor, performance degradation factor and component coordination factor from the multi-source operation data. Each real-time change trajectory contains factor state data and state change characteristics at continuous time nodes.

[0090] The load effect factor trajectory includes state data such as current, voltage, and power at different time points, as well as characteristics such as rate of change and fluctuation amplitude; the environmental correlation factor trajectory includes state data such as temperature, humidity, and air pressure, as well as characteristics such as frequency of change and rate of rise; the performance degradation factor trajectory includes state data such as brightness, contrast, and color reproduction, as well as characteristics such as attenuation rate and fluctuation range; the component coordination factor trajectory includes state data such as signal transmission time, power distribution accuracy, and response synchronization, as well as characteristics such as rate of change and deviation amplitude.

[0091] Step S133: Extract all stage performance degradation trajectories and corresponding component interaction loss records from the full-cycle historical lifetime correlation data. Each stage performance degradation trajectory is associated with the corresponding historical load effect factor change trajectory, historical environmental correlation factor change trajectory, historical performance degradation factor change trajectory, and historical component synergy factor change trajectory. Each component interaction loss record is associated with the corresponding historical component synergy factor change characteristics and historical performance degradation impact characteristics.

[0092] The phase performance degradation trajectory is like the mid-term trajectory. The associated historical load factor trajectory shows an increase in power, the historical environmental factor trajectory shows an increase in temperature, the historical performance degradation factor trajectory shows a decrease in brightness, and the historical component coordination factor trajectory shows an increase in signal transmission time. The component interaction loss record is like a certain record. The associated historical coordination factor change characteristic is an increase in signal transmission loss, and the historical performance degradation impact characteristic is an acceleration of brightness decay.

[0093] Step S134: Input the real-time change trajectory of the load factor into the lifetime consumption interaction network, and transmit it to the target interaction coupling node through the first flexible connection edge, the third flexible connection edge and the fourth flexible connection edge, triggering the target interaction coupling node to perform signal processing according to the activation rule and generate a real-time load interaction signal.

[0094] The real-time change trajectory of the load factor is input into the lifetime consumption interaction network. The load factor node determines whether to activate according to the activation rules. If the current exceeds the basic load threshold, it is activated, and the response intensity is calculated. The signal is transmitted to the target interaction coupling node through the first, third, and fourth flexible connection edges. The target interaction coupling node processes the signal according to the activation rules and generates a real-time load interaction signal containing the change characteristics of the load factor and its impact on lifetime consumption.

[0095] Step S135: Input the real-time change trajectory of environmental correlation factors into the lifetime consumption interaction network, and transmit it to the target interaction coupling node through the second, third and fifth flexible connection edges, triggering the target interaction coupling node to perform signal processing according to the activation rules and generate real-time environmental interaction signals.

[0096] The real-time change trajectory of environmental factors is input into the network. Environmentally related factor nodes are activated if the temperature exceeds the basic environmental tolerance range, and the response intensity is calculated. The signal is transmitted to the target interactive coupling node through the second, third, and fifth flexible connection edges. The target interactive coupling node processes the signal and generates a real-time environmental interaction signal containing the change characteristics and impact information of environmental factors.

[0097] Step S136: Input the real-time change trajectory of the performance degradation factor into the lifetime consumption interaction network, and transmit it to the target interaction coupling node through the first flexible connection edge, the second flexible connection edge and the sixth flexible connection edge, triggering the target interaction coupling node to perform signal processing according to the activation rule and generate a real-time performance interaction signal.

[0098] The real-time change trajectory of the performance degradation factor is input into the lifetime consumption interaction network. Performance degradation factor nodes are activated if their brightness exceeds the basic performance fluctuation range, and the response intensity is calculated. The signal is transmitted to the target interaction coupling node through the first, second, and sixth flexible connection edges. The target interaction coupling node processes the signal and generates a real-time performance interaction signal, containing the performance factor's change characteristics and impact information.

[0099] Step S137: Input the real-time change trajectory of the component coordination factor into the lifetime consumption interaction network, and transmit it to the target interaction coupling node through the fourth flexible connection edge, the fifth flexible connection edge and the sixth flexible connection edge, triggering the target interaction coupling node to perform signal processing according to the activation rule and generate a real-time coordination interaction signal.

[0100] The real-time change trajectory of the component coordination factor is input into the lifetime consumption interaction network. Component coordination factor nodes are activated if the signal transmission time exceeds the basic coordination accuracy range, and the response strength is calculated. The signal is transmitted to the target interaction coupling node through the fourth, fifth, and sixth flexible connection edges. The target interaction coupling node processes the signal and generates a real-time coordination interaction signal containing the change characteristics and impact information of the coordination factor.

[0101] Step S138: The target interactive coupling node receives real-time load interaction signals, real-time environment interaction signals, real-time performance interaction signals, and real-time collaborative interaction signals, integrates the signals according to the preset collaborative action logic, and generates real-time comprehensive interaction features. The real-time comprehensive interaction features include independent features and joint interaction features of various signals.

[0102] The target interactive coupling node receives four types of real-time interactive signals and integrates them according to the cooperative effect logic. Independent features include the rate of change of the load factor, the frequency of change of the environmental factor, the decay rate of the performance factor, and the deviation amplitude of the cooperative factor; joint features include the impact of the joint changes of the load and environmental factors on the performance factor, and the regulatory effect of the cooperative factor on the load and environmental factors. After integration, a real-time comprehensive interactive feature is generated, represented by a tensor, containing detailed information and interactive relationships of each type of signal.

[0103] Step S139: Traverse the historical comprehensive interaction features corresponding to the performance degradation trajectory of all stages. The historical comprehensive interaction features are generated by the change trajectories of various historical factors associated with the performance degradation trajectory of that stage through the target interaction coupling node, and include historical independent features and historical joint interaction features.

[0104] The historical comprehensive interaction characteristics of the performance degradation trajectory at all stages are traversed. For example, the historical comprehensive interaction characteristics of the mid-term trajectory are generated by the associated historical factor trajectories. Historical independent characteristics include the historical rate of change of the load factor and the historical frequency of change of the environmental factor. Historical joint characteristics include the impact of the historical joint changes of the load and environmental factors on the performance factor, and the moderating effect of the synergistic factors on the historical load and environmental factors.

[0105] Step S1310: Traverse all component interaction loss records and their corresponding historical collaborative interaction features. The historical collaborative interaction features are generated by the target interaction coupling node through the historical component collaborative factor change features and historical performance degradation impact features associated with the component interaction loss record.

[0106] Traverse all component interaction loss records to understand the historical collaborative interaction characteristics. For example, the historical collaborative interaction characteristics of a certain record are generated by the associated historical collaborative factor change characteristics (increased signal transmission loss) and historical performance degradation impact characteristics (accelerated brightness degradation), including the influence relationship between historical collaborative factors and historical performance degradation.

[0107] Step S1311: Perform correlation matching between real-time integrated interaction features and historical integrated interaction features, calculate the degree of fit of feature dimensions, and select the candidate stage performance degradation trajectory with the best degree of fit.

[0108] Real-time integrated interaction features are matched with historical integrated interaction features, and cosine similarity is used to calculate the similarity of each dimension. For example, if the load change rate of real-time features has high similarity with the load change rate of historical features, and the frequency of environmental changes has high similarity, the candidate stage performance degradation trajectory with the best fit, such as the mid-term trajectory, is selected.

[0109] Step S1312: Match the real-time collaborative interaction signal with each historical collaborative interaction feature, calculate the degree of fit of the collaborative action logic, and select the candidate component interaction loss record with the best degree of fit.

[0110] By matching real-time collaborative interaction signals with historical collaborative interaction features, the similarity of collaborative logic is analyzed. For example, the impact of the deviation amplitude of real-time collaborative factors on performance degradation is logically similar to that of the deviation amplitude of historical collaborative factors. Candidate component interaction loss records with the best fit are selected, such as a certain record.

[0111] Step S1313: Through the flexible connection edge propagation logic of the lifetime consumption interaction network, the performance degradation trajectory of the candidate stage and the interaction loss record of the candidate component are associated and integrated to ensure that the historical factor change patterns of the two are consistent.

[0112] By using the edge propagation logic of the lifetime consumption interaction network, the performance degradation trajectory of the candidate stage and the interaction loss record of the candidate component are correlated and integrated. For example, the time axis of the candidate trajectory and the record is adjusted to make the historical factor change pattern consistent over time; or the feature parameters are adjusted to make the numerical pattern consistent, ensuring that the historical factor change patterns of both are consistent.

[0113] Step S1314: Based on the integrated candidate stage performance decay trajectory and candidate component interaction loss record, and combined with the node response results of real-time comprehensive interaction features in the lifetime consumption interaction network, generate real-time historical interaction coupling results. The real-time historical interaction coupling results include the correlation mapping relationship between real-time data and historical data, interaction deviation features, and coupling adaptation parameters.

[0114] Step S13141: Extract the key decay nodes and the duration percentage of each decay stage in the integrated candidate stage performance decay trajectory. The key decay nodes represent important turning points in the performance decay of the candidate stage, and the duration percentage represents the time proportion of each decay stage in the entire life cycle.

[0115] The key decay nodes of the candidate stage performance decay trajectory are extracted and integrated, such as brightness decaying to 30% of the initial value and contrast decaying to 40% of the initial value, which are the turning points of performance decay; the duration accounts for 30% in the early stage, 50% in the middle stage, and 20% in the later stage.

[0116] Step S13142: Extract the key loss nodes and duration percentage of each loss stage from the integrated candidate component interaction loss record. Key loss nodes reflect the important turning points of component interaction loss in the candidate component interaction loss record, and duration percentage reflects the time proportion of each loss stage in the entire life cycle.

[0117] The key loss nodes of the candidate component interaction loss records are extracted and integrated. For example, when the signal transmission loss reaches 20% of the initial value and the power distribution loss reaches 30% of the initial value, it is the turning point of component interaction loss. The duration accounts for 25% in the early stage, 55% in the middle stage and 20% in the later stage.

[0118] Step S13143: Associate the key feature points in the real-time integrated interactive features with the key decay nodes of the candidate stage performance decay trajectory, establish a one-to-one correspondence between real-time feature points and historical decay nodes, and form the core association mapping relationship between real-time data and historical data.

[0119] By associating key feature points of real-time integrated interactive features (such as the rate of change of load factors and the frequency of change of environmental factors) with key decay nodes of candidate trajectories (such as brightness decay nodes), a one-to-one correspondence is established to form a core association mapping relationship, and the historical node positions and feature attributes corresponding to real-time feature points are clarified.

[0120] Step S13144: Associate the key feature points in the real-time collaborative interaction signal with the key loss nodes in the candidate component interaction loss record, establish a one-to-one correspondence between real-time collaborative feature points and historical loss nodes, and supplement the association mapping relationship between real-time data and historical data.

[0121] By associating key feature points of real-time collaborative interaction signals (such as the deviation amplitude of the collaborative factor) with key loss nodes of candidate records (such as signal transmission loss nodes), a one-to-one correspondence is established, and the association mapping relationship is supplemented to make the mapping relationship more complete.

[0122] Step S13145: Based on the core association mapping relationship and the supplementary association mapping relationship, generate a complete association mapping relationship between real-time data and historical data. The association mapping relationship clarifies the historical node position and feature attributes corresponding to each real-time feature point.

[0123] Based on the core and supplementary mapping relationships, a complete association mapping relationship is generated and stored in a table, clearly defining the historical node position (time or numerical position) and feature attributes (feature values ​​such as brightness, contrast, and signal transmission loss) corresponding to each real-time feature point.

[0124] Step S13146: Calculate the difference values ​​of the real-time integrated interaction features and the historical integrated interaction features corresponding to the candidate stage performance decay trajectory in each dimension to form the interaction deviation features. The interaction deviation features include the magnitude, direction and trend of the difference values ​​in each dimension.

[0125] Calculate the difference between real-time and historical integrated interaction characteristics. For example, for the load factor's rate of change dimension, the real-time value is x, the historical value is y, and the difference is xy; for the environmental factor's frequency of change dimension, the real-time value is c, the historical value is d, and the difference is cd. This forms the interaction deviation characteristic, including the magnitude, direction (positive or negative), and trend of the difference (e.g., change over time).

[0126] Step S13147: Calculate the difference values ​​of the historical collaborative interaction features corresponding to the real-time collaborative interaction signal and the interaction loss record of the candidate component in each dimension, and supplement them into the interaction deviation features.

[0127] Calculate the difference between real-time collaborative interaction signals and historical collaborative interaction features. For example, in the dimension of deviation magnitude of the collaborative factor, the real-time value is e, the historical value is f, and the difference value is ef; in the dimension of response synchronization deviation, the real-time value is g, the historical value is h, and the difference value is gh. Add the difference values ​​to the interaction deviation features to ensure feature completeness.

[0128] Step S13148: Analyze the distribution pattern and causes of interaction deviation characteristics. The distribution pattern reflects the degree of concentration of deviation in each dimension, and the causes are determined based on the differences in operating scenarios, parameter settings, and environmental conditions between real-time data and historical data.

[0129] Analyze the distribution patterns of interaction deviation characteristics, statistically analyze the frequency and concentration areas of differences in each dimension, and determine the degree of concentration of deviations. The causes are based on differences in operating scenarios between real-time and historical data (e.g., real-time is high-definition display, historical is normal display), differences in parameter settings (e.g., real-time drive parameters are different from historical ones), and differences in environmental conditions (e.g., real-time is high temperature and high humidity, historical is normal temperature and humidity).

[0130] Step S13149: Based on the correlation mapping relationship and interaction deviation characteristics, calculate the coupling adaptation parameters, which include the adaptation coefficient between real-time data and historical data, the deviation correction coefficient, and the signal conditioning coefficient. The adaptation coefficient is determined based on the degree of fit between real-time features and historical features; the higher the degree of fit, the larger the adaptation coefficient. The deviation correction coefficient is determined based on the strength and distribution pattern of the interaction deviation characteristics; the larger the deviation, the greater the adjustment range of the deviation correction coefficient. The signal conditioning coefficient is determined based on the node response results and edge propagation efficiency in the lifetime consumption interaction network and is used to optimize the coupling effect between real-time signals and historical signals.

[0131] The fit coefficient is calculated based on the degree of fit between real-time and historical features. For example, if the fit is 0.8, the fit coefficient is 0.8. The deviation correction coefficient is calculated based on the strength and distribution of the interaction deviation features. For example, if the deviation strength is 0.5 and the distribution is concentrated, the correction coefficient is adjusted by 0.5. The signal conditioning coefficient is calculated based on the network node response and edge propagation efficiency. For example, if the node response strength is high and the edge propagation efficiency is high, the signal conditioning coefficient is 1.2. By calculating these parameters, the coupling effect between real-time and historical data is optimized.

[0132] Step S131410: Integrate the association mapping relationship, interaction deviation features and coupling adaptation parameters to generate a real-time historical interaction coupling result containing complete association mapping relationship, comprehensive interaction deviation features and precise coupling adaptation parameters.

[0133] Step S140: Based on the real-time historical interaction coupling results, dynamically adapt the node response mode of the lifetime consumption interaction network according to the real-time changes of data, and generate an adaptive lifetime consumption rate.

[0134] Step S141: Continuously acquire the latest state data and state change information of the target lifespan influencing factors according to the preset acquisition interval, and capture the state change characteristics of the target lifespan influencing factors in real time to form a dynamic feedback feature set.

[0135] In this embodiment, the latest state data and state change information of the target lifetime influencing factors are continuously acquired at preset acquisition intervals (e.g., at regular intervals). For example, the latest current, voltage, power, and other state data of the load effect factor, as well as the change information of these data (e.g., rate of change, fluctuation amplitude, etc.), are acquired from the module's real-time monitoring system; the latest temperature, humidity, air pressure, and other state data of the environmental factors, as well as the change information, are acquired; the latest brightness, contrast, color reproduction, and other state data of the performance degradation factor, as well as the change information, are acquired; and the latest signal transmission time, power allocation accuracy, response synchronization, and other state data of the component coordination factor, as well as the change information, are acquired. The state change characteristics of these target lifetime influencing factors are captured in real time, such as an increase in the rate of change of the load effect factor, an increase in the frequency of change of the environmental factors, an increase in the degradation rate of the performance degradation factor, and an increase in the deviation amplitude of the component coordination factor. These characteristics are then formed into a dynamic feedback feature set, which includes the latest state change characteristics of various factors.

[0136] Step S142: Analyze the candidate stage performance degradation trajectory and candidate component interaction loss record in the real-time historical interaction coupling results, and extract the corresponding historical lifetime consumption rate change curve and historical component interaction loss rate curve.

[0137] In this embodiment, the real-time historical interaction coupling results are analyzed. From the candidate stage performance degradation trajectory, the corresponding historical lifetime consumption rate change curve is extracted, reflecting the module's lifetime consumption rate changes at different historical stages. For example, the initial lifetime consumption rate is slow, gradually accelerating in the middle stage, and further accelerating in the later stage. From the candidate component interaction loss records, the corresponding historical component interaction loss rate curve is extracted, reflecting the changes in the interaction loss rate of the module's internal components at different historical stages. For example, the initial component interaction loss rate is slow, the loss rate accelerates in the middle stage with changes in load and environment, and the loss rate further changes in the later stage due to performance degradation.

[0138] Step S143: After normalizing the independent feedback characteristics of each factor in the dynamic feedback feature set with the associated consumption rate of the corresponding stage in the historical rate curve, compare them to identify load rate difference characteristics, environmental rate difference characteristics, performance rate difference characteristics and collaborative rate difference characteristics.

[0139] In this embodiment, for example, the independent feedback characteristics of each factor in the dynamic feedback feature set (such as the rate of change of the load effect factor, the frequency of change of the environmental correlation factor, the decay rate of the performance decay factor, and the deviation amplitude of the component coordination factor) and the corresponding stage of the historical rate curve (such as the historical lifetime consumption rate and the historical component interaction loss rate) are converted to the same dimensions and range (such as [0, 1]). Then, the normalized independent feedback characteristics are compared with the normalized associated consumption rates, and the differences between them are calculated. For example, the normalized independent feedback characteristic of the load effect factor is x, and the normalized historical lifetime consumption rate is y, with a difference of xy, thus identifying the load rate difference characteristic; similarly, the environmental rate difference characteristic, performance rate difference characteristic, and coordination rate difference characteristic are identified. The above rate difference characteristics contain the difference information between the dynamic feedback characteristics and the historical rate curve. For example, if the load rate difference characteristic is positive, it indicates that the change of the real-time load effect factor has a greater impact on the lifetime consumption rate than in the historical case.

[0140] Step S144: Input the normalized rate difference features into the lifetime consumption interaction network, and analyze the comprehensive impact of various difference features on the overall lifetime consumption rate through the target interaction coupling node.

[0141] For example, step S1441: extract the priority weight of the impact of the target lifetime influencing factors on lifetime consumption from the target interactive coupling nodes of the lifetime consumption interaction network. The priority weight is determined based on the statistical analysis results of the full-cycle historical lifetime correlation data, reflecting the relative importance of various factors in the lifetime consumption process.

[0142] In this embodiment, statistical analysis of historical lifetime correlation data throughout the entire lifecycle is used to determine the priority weights of various target lifetime influencing factors on lifetime depletion. For example, in the statistical historical data, the proportion of lifetime depletion changes caused by changes in load factors, environmental factors, performance degradation factors, and component synergy factors is used to determine the priority weights. For example, the weight of the load factor is 0.3, the weight of the environmental factor is 0.3, the weight of the performance degradation factor is 0.2, and the weight of the component synergy factor is 0.2, reflecting the relative importance of each factor in the lifetime depletion process.

[0143] Step S1442: Determine the intensity level, duration level, and scope of influence level for each type of rate difference feature. The intensity level is determined based on the comparison between the numerical value of the difference feature and a preset difference intensity threshold. The larger the difference value, the higher the intensity level. The duration level is determined based on the comparison between the duration of the difference feature and a preset difference duration threshold. The longer the duration, the higher the duration level. The scope of influence level is determined based on the degree to which the difference feature affects other core factors. The more core factors affected, the higher the scope of influence level.

[0144] In this embodiment, regarding the intensity level, a preset difference intensity threshold is a certain numerical range. For example, the preset difference intensity threshold for load rate difference features is [0, 0.2, 0.4, 0.6]. The magnitude of the difference feature is compared with these thresholds to classify the intensity level. For example, a difference value between 0 and 0.2 is level 1, between 0.2 and 0.4 is level 2, and so on. The larger the difference value, the higher the intensity level. Regarding the duration level, a preset difference duration threshold is a certain time range. For example, the preset difference duration threshold for load rate difference features is [0, 10, 20, 30] (unit: hours). The duration of the difference feature is compared with these thresholds to classify the duration level. For example, a duration between 0 and 10 hours is level 1, between 10 and 20 hours is level 2, and so on. The longer the duration, the higher the duration level. Regarding the level of impact, it is classified according to the degree of influence of the difference characteristics on other core factors. For example, if the load rate difference characteristics affect three core factors, namely environmental factors, performance degradation factors, and component synergy factors, the level of impact is 3. If only one core factor is affected, the level of impact is 1. The more core factors affected, the higher the level of impact.

[0145] Step S1443: Based on the impact priority weight, intensity level, duration level, and impact range level, establish a comprehensive impact degree calculation logic. According to the comprehensive impact degree calculation logic, calculate the individual impact degree scores of load rate difference characteristics, environmental rate difference characteristics, performance rate difference characteristics, and collaborative rate difference characteristics respectively. The comprehensive impact degree calculation logic includes the quantitative score and weight allocation ratio corresponding to each level.

[0146] For example, the quantitative scores corresponding to each level are as follows: Intensity Level 1 corresponds to 1 point, Level 2 to 2 points, Level 3 to 3 points, and Level 4 to 4 points; Duration Level 1 corresponds to 1 point, Level 2 to 2 points, Level 3 to 3 points, and Level 4 to 4 points; Impact Scope Level 1 corresponds to 1 point, Level 2 to 2 points, Level 3 to 3 points, and Level 4 to 4 points. The weighting ratio is: Impact Priority Weight 0.4, Intensity Level 0.2, Duration Level 0.2, and Impact Scope Level 0.2. The formula for calculating the comprehensive impact score is: Comprehensive Impact Score = Impact Priority Weight * 0.4 + Intensity Level * 0.2 + Duration Level * 0.2 + Impact Scope Level * 0.2. Following this calculation logic, the individual impact scores for load rate difference characteristics, environmental rate difference characteristics, performance rate difference characteristics, and collaborative rate difference characteristics are calculated separately.

[0147] Step S1444: Analyze the interaction between the normalized rate difference features and identify the synergistic enhancement effect or mutual cancellation effect between the normalized rate difference features. The synergistic enhancement effect refers to the presence of one type of normalized rate difference feature aggravating the influence of another type of normalized rate difference feature. The mutual cancellation effect refers to the presence of one type of normalized rate difference feature weakening the influence of another type of normalized rate difference feature.

[0148] For example, regarding load rate difference characteristics and environmental rate difference characteristics, when both are positive (the impact of real-time load factors is greater than historically) and environmental rate difference characteristics are positive (the impact of real-time environmental correlation factors is greater than historically), there is a synergistic enhancement effect between them. That is, the load effect exacerbates the environmental effect, or vice versa, resulting in a larger change in the overall lifetime attrition rate than the sum of the individual effects. Conversely, when the load rate difference characteristic is positive and the environmental rate difference characteristic is negative (the impact of real-time environmental correlation factors is smaller than historically), there may be a mutual cancellation effect. That is, the load effect is weakened by the environmental effect, or vice versa, resulting in a smaller change in the overall lifetime attrition rate than the sum of the individual effects. By analyzing the interactions between all rate difference characteristics, synergistic enhancement effects or mutual cancellation effects can be identified.

[0149] Step S1445: Based on the synergistic enhancement effect or mutual cancellation effect, correct the individual influence scores of the normalized rate difference characteristics to obtain the corrected individual influence scores. Increase the corresponding score when there is synergistic enhancement and decrease the corresponding score when there is mutual cancellation.

[0150] For example, when there is a synergistic enhancement effect between load rate difference characteristics and environmental rate difference characteristics, the score for the individual impact of load rate difference characteristics increases by a certain percentage (e.g., 10%), and the score for the individual impact of environmental rate difference characteristics also increases by a certain percentage (e.g., 10%). When there is a mutual cancellation effect, the score for the individual impact of the corresponding rate difference characteristics decreases by a certain percentage (e.g., 10%). Through the above corrections, the individual impact scores more accurately reflect the comprehensive impact of various rate difference characteristics on the overall lifespan consumption rate.

[0151] Step S1446: Sum the individual impact scores of the various normalized rate difference features to obtain the total comprehensive impact score of the various normalized rate difference features on the overall lifespan consumption rate.

[0152] Step S1447: Based on the total score of the comprehensive impact, classify the comprehensive impact level. Different comprehensive impact levels correspond to different adjustment ranges of node response mode and side transmission efficiency.

[0153] For example, a total score of 0-2 for the overall impact level corresponds to Level 1, 2-4 to Level 2, 4-6 to Level 3, 6-8 to Level 4, and 8-10 to Level 5. Different overall impact levels correspond to different adjustment ranges for node response patterns and side transmission efficiency. For instance, Level 1 corresponds to an adjustment range of 0.1 for both node response patterns and side transmission efficiency; Level 2 corresponds to 0.2 for both; Level 3 corresponds to 0.3 for both; and so on. Using this method, the adjustment range for the lifetime consumption interaction network is determined based on the magnitude of the overall impact level.

[0154] Step S145: Based on the overall impact level, dynamically adapt the node response mode and edge propagation efficiency of the lifetime consumption interaction network.

[0155] For example, a comprehensive impact level of 3 corresponds to a node response mode adjustment of 0.3 and an edge transmission efficiency adjustment of 0.3. Adjusting the node response mode, for example, by increasing the threshold of the activation trigger condition for load-affecting nodes, or by adjusting the parameters of the response intensity calculation method, can make the node response more sensitive or less sensitive. Adjusting the edge transmission efficiency, for example, by increasing the impact transmission efficiency parameter of the first flexible connection edge, or by adjusting the parameters of the attenuation logic and enhancement logic, can make the signal transmission of the flexible connection edge more efficient or less efficient. Through the above dynamic adaptation, the lifetime consumption interaction network can adapt to changes in real-time data, improving the accuracy of lifetime prediction.

[0156] Step S146: Based on the adjusted node response mode and edge transmission efficiency, recalculate the rate parameters of each stage in the historical lifetime consumption rate change curve and the historical component interaction loss rate curve to obtain the adjusted historical rate curve.

[0157] For example, regarding the historical lifetime attrition rate curve, the lifetime attrition rate for each stage is recalculated based on the adjusted node response mode, considering the impact of changes in node response on the lifetime attrition rate. Similarly, based on the adjusted edge transmission efficiency, the lifetime attrition rate for each stage is recalculated, considering the impact of changes in signal transmission at flexible connection edges on the lifetime attrition rate. Likewise, the historical component interaction loss rate curve is recalculated to obtain the adjusted historical rate curve. The adjusted historical rate curve can more accurately reflect the historical lifetime attrition and component interaction loss of the module under the current node response mode and edge transmission efficiency.

[0158] Step S147: Integrate the adjusted historical lifetime consumption rate curve with the historical component interaction loss rate curve to form a comprehensive historical consumption rate curve.

[0159] For example, by analyzing the correlation between historical lifetime attrition rates and historical component interaction loss rates, their synergistic relationship can be determined. Then, based on this synergistic relationship, the two curves are integrated into a single comprehensive historical attrition rate curve. This comprehensive historical attrition rate curve reflects both the overall lifetime attrition rate change of the module and the impact of changes in component interaction loss rates on lifetime attrition; for example, when the component interaction loss rate increases, the lifetime attrition rate also increases accordingly. Through this synergistic integration, the resulting comprehensive historical attrition rate curve is more comprehensive and accurate.

[0160] Step S148: Extract the initial segment rate features from the comprehensive historical consumption rate curve that correspond to the real-time historical interactive coupling results. Combine the latest change trend of the dynamic feedback feature set, and perform real-time adaptation and correction of the initial segment rate features through the collaborative logic of the target interactive coupling nodes to generate an adaptive lifetime consumption rate.

[0161] The initial segment rate characteristic corresponds to the current stage in the real-time historical interactive coupling results. For example, the historical initial segment rate characteristic corresponding to the current module's lifespan consumption stage includes the basic consumption rate, rate change coefficient, and rate fluctuation range for that stage. Combining the latest changing trends of the dynamic feedback feature set (such as an increase in the rate of change of the load effect factor and a faster frequency of change of environmental correlation factors), the initial segment rate characteristic is dynamically adapted and corrected through the collaborative action logic of the target interactive coupling nodes. The collaborative action logic considers the impact of the latest changes in various target lifespan influencing factors on the initial segment rate characteristic. For example, an increase in the rate of change of the load effect factor will lead to an increase in the basic consumption rate and rate change coefficient of the initial segment. Through the above real-time adaptation and correction, an adaptive lifespan consumption rate is generated. This adaptive lifespan consumption rate reflects the current lifespan consumption of the module and dynamically adjusts as real-time data changes.

[0162] Step S150: Based on the adaptive lifetime consumption rate and the current comprehensive performance status data of the Miniled module, generate the remaining lifetime prediction result of the Miniled module. Input the actual operating data and actual lifetime status data generated by the Miniled module in reverse into the lifetime consumption interaction network to dynamically adjust the strength of the interaction relationship between core nodes and the transmission efficiency of flexible connection edges.

[0163] Step S151: Collect the current comprehensive performance status data of the Miniled module. The comprehensive performance status data includes the current performance output parameters, performance output stability data, component collaborative work accuracy data, performance degradation start flag, and current runtime data. The current performance output parameters reflect the current core function output level of the module, the performance output stability data reflects the fluctuation of the module's current performance output, the component collaborative work accuracy data reflects the accuracy of the interaction between components inside the module, the performance degradation start flag is used to determine whether the module has entered a significant performance degradation stage, and the current runtime data reflects the cumulative time that the module has run.

[0164] In this embodiment, for example, current performance output parameters such as brightness, contrast, and color fidelity are collected using a module performance testing device. These parameters reflect the current core functional output level of the module. Performance output stability data, such as the fluctuation range of brightness and the fluctuation frequency of contrast, are collected by monitoring the performance output fluctuations of the module. The collaborative operation accuracy data of the components is collected by monitoring the interaction operation of the internal components of the module, such as the signal transmission time and power distribution error between the driver chip and the light-emitting chip. The performance degradation of the module is analyzed to determine the starting point of performance degradation. For example, when the brightness decays to a certain percentage of the initial value, it is marked as entering a significant performance degradation stage. Current running time data, such as the number of hours and days already run, is collected by recording the running time of the module.

[0165] Step S152: Analyze the adaptive lifetime consumption rate, extract the rate change trend, rate characteristics of each stage, rate peak range and rate decay cycle characteristics. The rate change trend reflects the overall direction of change of the adaptive lifetime consumption rate over time, and the rate characteristics of each stage reflect the core characteristics of the consumption rate in different lifetime stages.

[0166] In this embodiment, the rate change trend is extracted. For example, the adaptive lifespan consumption rate increases over time, indicating that the module's lifespan is being consumed faster and faster. Rate characteristics at each stage are extracted. For example, the rate characteristics of the initial stage are low basic consumption rate, small rate change coefficient, and narrow rate fluctuation range; the rate characteristics of the middle stage are medium basic consumption rate, increased rate change coefficient, and wider rate fluctuation range; and the rate characteristics of the later stage are high basic consumption rate, large rate change coefficient, and wide rate fluctuation range. Peak rate intervals are extracted. For example, a certain time period in the later stage is the peak rate interval, at which time the lifespan consumption rate reaches its maximum value. Rate decay cycle characteristics are extracted. For example, the rate decay cycle is a certain time interval, within which the lifespan consumption rate shows periodic changes.

[0167] Step S153: Compare the current comprehensive performance status data with the stage performance degradation trajectory in the full-cycle historical lifetime correlation data, and determine the current lifetime degradation stage of the Miniled module based on the current performance output parameters, performance output stability data and component collaborative work accuracy data.

[0168] In this embodiment, for example, the current performance output parameters (such as brightness and contrast) are compared with the corresponding parameters in the historical performance degradation trajectory; the current performance output stability data (such as brightness fluctuation amplitude) is compared with the stability data in the historical trajectory; and the current component collaborative working accuracy data (such as signal transmission time) is compared with the collaborative accuracy data in the historical trajectory. By comparing, the current lifespan degradation stage of the module is determined. For example, if the current performance output parameters and stability data are similar to the performance degradation trajectory in the historical mid-stage, and the component collaborative working accuracy data also matches the situation in the historical mid-stage, then it is determined that the module is currently in the mid-lifespan degradation stage.

[0169] Step S154: Based on the current lifetime decay stage, extract the corresponding stage rate parameter from the adaptive lifetime consumption rate. The stage rate parameter reflects the core characteristics of the current lifetime consumption rate, including the basic consumption rate, rate change coefficient and rate fluctuation range of the lifetime decay stage.

[0170] In this embodiment, based on the current lifetime decay stage, the corresponding stage rate parameters are extracted from the adaptive lifetime consumption rate. For example, if the current stage is the mid-life decay stage, the basic consumption rate, rate change coefficient, and rate fluctuation range for the mid-stage are extracted from the adaptive lifetime consumption rate. The basic consumption rate reflects the basic level of lifetime consumption rate in the mid-stage, the rate change coefficient reflects the rate of change of the lifetime consumption rate in the mid-stage, and the rate fluctuation range reflects the fluctuation of the lifetime consumption rate in the mid-stage.

[0171] Step S155: Analyze the performance degradation start marker in the current comprehensive performance status data, and combine it with the stage rate parameter and the current runtime data to determine the calculation start point of the remaining lifetime. The calculation start point is the lifetime consumption process position corresponding to the current time node.

[0172] In this embodiment, if the performance degradation start marker indicates that the module has entered a significant performance degradation stage (e.g., brightness decays to a certain percentage of its initial value), the starting point for calculating the remaining lifetime is determined by combining the stage rate parameter (e.g., the base consumption rate in the mid-stage) and the current runtime data (e.g., the number of hours already run). The calculation starting point is the lifetime consumption process position corresponding to the current time node. For example, if the current runtime is T and the total duration of the mid-stage is T_total, then the lifetime consumption process position corresponding to the calculation starting point is T / T_total, and the calculation of the remaining lifetime will begin from this position.

[0173] Step S156: Based on the stage rate parameters and rate change trend, predict the rate change in the subsequent stage of the current lifespan decay and generate the subsequent rate prediction sequence of the current stage. The subsequent rate prediction sequence of the current stage contains the predicted consumption rate for each time interval in the remaining time of the current stage.

[0174] In this embodiment, for example, the stage rate parameter for the intermediate stage is the base consumption rate v, the rate change coefficient k, the rate fluctuation range [v-Δv, v+Δv], and the rate change trend is upward. Assuming the remaining time for the current stage is t, and the time interval is Δt, then the subsequent rate prediction sequence for the current stage is: v1=v+k*Δt, v2=v1+k*Δt, ..., vn=v+k*n*Δt, where each vi needs to consider the influence of the rate fluctuation range, for example, vi within the range [vi-Δv, vi+Δv]. Through the above method, the subsequent rate prediction sequence for the current stage is generated, containing the predicted consumption rate for each time interval within the remaining time of the current stage.

[0175] Step S157: Based on the subsequent rate prediction sequence of the current stage and the remaining lifetime percentage of the current stage, calculate the remaining duration of the current lifetime decay stage.

[0176] In this embodiment, the remaining duration of the current stage is calculated based on the predicted rate sequence of the subsequent stages and the remaining lifetime percentage of the current stage. The remaining lifetime percentage of the current stage is (T_total-T) / T_total, where T_total is the total duration of the current lifetime decay stage, and T is the current running time. Assuming the average consumption rate of the predicted rate sequence of the subsequent stages is v_avg, the remaining duration of the current stage is (remaining lifetime percentage * total lifetime) / v_avg, or the remaining duration can be obtained by integrating the predicted rate sequence of the subsequent stages and calculating the total consumption rate within the remaining time. For example, if the total consumption rate of the predicted rate sequence of the subsequent stages is S=∫(v(t))dt (from the current time to the end time of the current stage), and the total lifetime consumption corresponding to the remaining lifetime percentage is L=remaining lifetime percentage * total lifetime, then the remaining duration is L / S.

[0177] Step S158: Extract the rate parameters of all subsequent stages after the current lifetime decay stage in the adaptive lifetime consumption rate, including the base consumption rate, rate change coefficient, rate fluctuation range and stage duration percentage for each subsequent stage.

[0178] In this embodiment, for example, if we are currently in the middle stage and the subsequent stage is the late stage, we extract the basic consumption rate, rate change coefficient, rate fluctuation range, and stage duration percentage of the late stage. The stage duration percentage is the proportion of the late stage in the total lifetime, for example, 30%.

[0179] Step S159: Calculate the expected duration of each subsequent stage based on the rate parameters and rate change trends of each subsequent stage.

[0180] In this embodiment, the expected duration is calculated based on the rate parameters and rate change trends of each subsequent stage. For example, the base consumption rate of the later stage is v_late, the rate change coefficient is k_late, the rate fluctuation range is [v_late-Δv_late, v_late+Δv_late], and the rate change trend is upward. Assuming the total lifetime consumption of the later stage is L_late = stage duration percentage * total lifetime, then the expected duration is L_late / v_avg_late, where v_avg_late is the average consumption rate of the later stage, calculated similarly to the intermediate stage, taking into account the influence of the rate change coefficient and fluctuation range.

[0181] Step S1510: Add the remaining duration of the current lifetime decay stage to the expected duration of all subsequent stages to obtain the total remaining lifetime of the Miniled module.

[0182] In this embodiment, for example, the remaining duration of the current stage is t_mid, the estimated duration of the subsequent stage (later stage) is t_late, and the total remaining lifetime is t_mid + t_late. If there are more subsequent stages, such as the final stage, their estimated durations also need to be added in to obtain the final total remaining lifetime.

[0183] Step S1511: Combining the performance output stability data, component collaborative work accuracy data, and total remaining lifetime in the current comprehensive performance status data, generate a remaining lifetime prediction result that includes the total remaining lifetime, the remaining lifetime of each stage, a stage decay characteristic description, and performance maintenance recommendations. The stage decay characteristic description reflects the consumption rate characteristics and performance change trends of each remaining lifetime stage, and the performance maintenance recommendations are generated based on the decay characteristics of each stage and historical data.

[0184] In this embodiment, the total remaining lifetime is t_mid + t_late; the remaining lifetime for each stage is t_mid (mid-term remaining lifetime) and t_late (late-term remaining lifetime); the stage decay characteristics are described as the consumption rate characteristics (base consumption rate, rate change coefficient, rate fluctuation range) and performance change trends (e.g., continued decay of brightness and contrast, and deterioration of performance output stability) in the mid-term stage, and the consumption rate characteristics and performance change trends (e.g., further acceleration of consumption rate and intensified performance decay) in the late-term stage; performance maintenance recommendations are generated based on the decay characteristics of each stage and historical data references. For example, in the mid-term stage, it is recommended to optimize load and environmental conditions and reduce component interaction losses; in the late-term stage, it is recommended to strengthen performance monitoring and prepare for module replacement, etc. Through the above methods, the generated remaining lifetime prediction results contain detailed lifetime information and maintenance recommendations.

[0185] Step S1512: Input the actual operating data and actual lifetime status data generated by the Miniled module into the lifetime consumption interaction network in reverse order, and dynamically adjust the strength of the interaction relationship between core nodes and the transmission efficiency of flexible connection edges.

[0186] Step S15121: Establish a subsequent data acquisition and tracking mechanism. This mechanism starts when the remaining lifetime prediction result is generated and continuously collects the actual operating data and actual lifetime status data generated by the Miniled module until the Miniled module reaches the end of its lifetime. The subsequent actual operating data includes the trajectory of subsequent load effect factors, the trajectory of subsequent environmental correlation factors, the trajectory of subsequent performance degradation factors, and the trajectory of subsequent component coordination factors. Each trajectory contains the actual status data and status change characteristics of continuous time nodes. The subsequent actual lifetime status data includes subsequent performance degradation records, subsequent component interaction loss records, and final lifetime end status records. The subsequent performance degradation records reflect the actual changes in performance parameters during the subsequent operation of the module. The subsequent component interaction loss records reflect the actual loss of component interactions during the subsequent operation of the module. The final lifetime end status records reflect the core status data when the module reaches the end of its lifetime.

[0187] In this embodiment, starting from the generation of the remaining lifetime prediction result, the data acquisition device is activated to continuously collect subsequent actual operating data and actual lifetime status data of the module. The actual operating data includes the trajectory of subsequent load-related factors (such as changes in current, voltage, and power), the trajectory of subsequent environmental factors (such as changes in temperature, humidity, and air pressure), the trajectory of subsequent performance degradation factors (such as changes in brightness, contrast, and color fidelity), and the trajectory of subsequent component coordination factors (such as changes in signal transmission time, power allocation accuracy, and response synchronization). Each trajectory contains actual status data and status change characteristics at consecutive time points. The actual lifetime status data includes subsequent performance degradation records (such as changes in performance parameters at different times), subsequent component interaction loss records (such as component interaction loss at different times), and final lifetime end-of-life status records (such as performance parameters, appearance condition, and fault location at the end of lifetime).

[0188] Step S15122: Input the subsequent load effect factor change trajectory, subsequent environmental correlation factor change trajectory, subsequent performance degradation factor change trajectory, and subsequent component synergy factor change trajectory into the lifetime consumption interaction network in reverse, corresponding to the load effect factor node, environmental correlation factor node, performance degradation factor node, and component synergy factor node, respectively.

[0189] In this embodiment, for example, the subsequent load effect factor change trajectory is input into the load effect factor node, the subsequent environmental correlation factor change trajectory is input into the environmental correlation factor node, the subsequent performance degradation factor change trajectory is input into the performance degradation factor node, and the subsequent component coordination factor change trajectory is input into the component coordination factor node. Through the above reverse input, the lifetime consumption interaction network can receive the module's subsequent actual operating data.

[0190] Step S15123: Input the subsequent performance degradation record and the subsequent component interaction loss record into the target interaction coupling node of the lifetime consumption interaction network in reverse order, in order to compare the deviation between the prediction result and the actual situation.

[0191] In this embodiment, for example, subsequent performance degradation records and subsequent component interaction loss records are input into the target interaction coupling node. The target interaction coupling node compares the above actual data with the previous prediction results and calculates the deviation between the prediction results and the actual situation. For example, the deviation between the actual brightness degradation recorded in the performance degradation record and the predicted brightness degradation, and the deviation between the actual loss recorded in the component interaction loss record and the predicted loss.

[0192] Step S15124: Through the target interaction coupling node, integrate the change trajectory of subsequent target lifetime influencing factors and subsequent performance degradation records, and subsequent component interaction loss records to generate subsequent comprehensive interaction features and subsequent collaborative interaction features.

[0193] In this embodiment, the change trajectories of subsequent target lifetime influencing factors (load, environment, performance, and collaboration) and subsequent performance degradation records and subsequent component interaction loss records are integrated to generate subsequent comprehensive interaction features and subsequent collaborative interaction features. The subsequent comprehensive interaction features include the change characteristics of subsequent target lifetime influencing factors and their comprehensive impact on performance degradation; the subsequent collaborative interaction features include the change characteristics of subsequent component collaboration factors and their collaborative impact on performance degradation.

[0194] Step S15125: Extract the corresponding prediction integrated interaction features and prediction collaborative interaction features from the remaining lifetime prediction results, compare the subsequent integrated interaction features with the prediction integrated interaction features, and identify the interaction deviation between the two.

[0195] In this embodiment, the subsequent integrated interaction features are compared with the predicted integrated interaction features, and the differences between them are calculated to identify interaction bias. Interaction bias includes the differences between the actual data and the predicted data in the interaction relationships of various factors. For example, the impact of changes in the load factor on performance degradation may differ from the predicted impact, leading to interaction bias.

[0196] Step S15126: Compare the subsequent collaborative interaction features with the predicted collaborative interaction features to identify the collaborative deviation between the two.

[0197] In this embodiment, the coordination bias includes the difference between the actual data and the predicted data in the interaction relationship of the component coordination factors. For example, the coordination effect of the subsequent changes in the component coordination factors on performance degradation is different from the predicted effect, resulting in coordination bias.

[0198] Step S15127: Based on interaction bias and coordination bias, calculate the bias impact value of the interaction relationship between each core node in the lifetime consumption interaction network. The bias impact value reflects the degree of difference between the current interaction relationship strength and the actual interaction situation.

[0199] In this embodiment, for example, the magnitude of the interaction deviation is ΔI, the magnitude of the coordination deviation is ΔC, and the deviation impact value is ΔI+ΔC, or it can be calculated according to their weights, such as deviation impact value = w1*ΔI+w2*ΔC, where w1 and w2 are weights. The deviation impact value reflects the degree of difference between the strength of the interaction relationship between each core node in the current lifetime consumption interaction network and the actual interaction situation. The larger the deviation impact value, the greater the degree of difference.

[0200] Step S15128: Based on the deviation impact value, dynamically adjust the interaction strength between the load effect factor node and the performance degradation factor node, the interaction strength between the environmental correlation factor node and the performance degradation factor node, the interaction strength between the load effect factor node and the environmental correlation factor node, and the interaction strength between the component coordination factor node and other core factor nodes. The larger the deviation impact value, the greater the adjustment range.

[0201] In this embodiment, for example, the deviation impact value is Δ, and the adjustment range is k*Δ, where k is the adjustment coefficient. For the interaction strength between the load effect factor node and the performance degradation factor node, the initial parameter of the interaction strength is increased or decreased according to the deviation impact value. Similarly, the interaction strength between the environmental correlation factor node and the performance degradation factor node, the load effect factor node and the environmental correlation factor node, and the component coordination factor node and other core factor nodes are adjusted. The larger the deviation impact value, the larger the adjustment range, to ensure that the interaction strength reflects the actual interaction situation.

[0202] Step S15129: Synchronously calculate the conduction efficiency deviation value of each flexible connection edge in the lifetime consumption interaction network. The conduction efficiency deviation value reflects the degree of difference between the current conduction efficiency and the actual data transmission requirements.

[0203] In this embodiment, the conduction efficiency deviation value of each flexible connection edge is calculated simultaneously. The conduction efficiency deviation value is calculated based on the difference between the actual data transmission efficiency and the current conduction efficiency of the flexible connection edge. For example, if the actual data transmission efficiency is η_actual and the current conduction efficiency is η_current, the conduction efficiency deviation value is η_actual - η_current. The conduction efficiency deviation value reflects the degree of difference between the current conduction efficiency of the flexible connection edge and the actual data transmission requirements; the larger the deviation value, the greater the degree of difference.

[0204] Step S151210: Based on the conduction efficiency deviation value, dynamically adjust the conduction efficiency parameters of the first to sixth flexible connection edges and the newly added flexible connection edges, including adjusting the attenuation coefficient, enhancement threshold and signal transmission delay parameters of the adjustment edges. The larger the conduction efficiency deviation value, the greater the adjustment range.

[0205] In this embodiment, the conduction efficiency parameters of each flexible connection edge are dynamically adjusted based on the conduction efficiency deviation value. For example, if the conduction efficiency deviation value is Δη, the adjustment range is m*Δη, where m is the adjustment coefficient. For the first flexible connection edge, the attenuation coefficient, enhancement threshold, and signal transmission delay parameter are adjusted according to the conduction efficiency deviation value; similarly, the conduction efficiency parameters of the second to sixth flexible connection edges and the newly added flexible connection edges are adjusted. The larger the conduction efficiency deviation value, the larger the adjustment range, to ensure that the conduction efficiency of the flexible connection edges can meet the actual data transmission requirements.

[0206] Step S151211: Adjust the internal collaborative logic and weight allocation ratio of the target interactive coupling node so that the target interactive coupling node can accurately integrate subsequent actual data and optimize the signal processing method.

[0207] In this embodiment, based on the characteristics of subsequent actual data and the interaction and coordination deviations, the coordination logic of the target interactive coupling node is adjusted. For example, the integration method of various signals is optimized to more accurately reflect the interaction relationships of subsequent actual data; the weight allocation ratio is adjusted, for example, increasing the weight of load effect factor signals and decreasing the weight of environmental correlation factor signals to adapt to changes in subsequent actual data. Through the above adjustments, the target interactive coupling node can accurately integrate subsequent actual data, optimize signal processing methods, and improve the accuracy of lifetime prediction.

[0208] Step S151212: Using sample data from the full-cycle historical lifetime correlation data that did not participate in the initial network construction, verify the transmission accuracy and prediction precision of the adjusted lifetime consumption interaction network.

[0209] In this embodiment, sample data that did not participate in the initial network construction is selected from the full-cycle historical lifetime correlation data. This sample data is then input into the adjusted lifetime consumption interaction network for lifetime prediction. The prediction results are then compared with the actual lifetime of the sample data to calculate the transmission accuracy (e.g., signal transmission accuracy) and prediction precision (e.g., the error between predicted and actual lifetime). If the verification results meet the requirements (e.g., prediction precision is within a certain range), it indicates that the adjusted lifetime consumption interaction network can accurately reflect the module's lifetime consumption pattern; if the verification results do not meet the requirements, the network parameters need to be further adjusted until verification is successful.

[0210] Step S151213: Based on the verification results, the interaction strength between core nodes and the transmission efficiency of flexible connection edges are fine-tuned a second time so that the adjusted lifetime consumption interaction network reflects the actual lifetime consumption law of the Miniled module.

[0211] In this embodiment, if the verification results show that the prediction accuracy has room for improvement, or the transmission accuracy is insufficient, the problem is analyzed based on the verification results, and secondary fine-tuning is performed on the interaction strength between core nodes and the transmission efficiency of flexible connection edges. For example, if the error between the predicted lifetime and the actual lifetime mainly comes from the influence of the load factor, then the interaction strength between the load factor node and other core nodes, as well as the transmission efficiency parameters of the relevant flexible connection edges, are further adjusted. Through the above secondary fine-tuning, the adjusted lifetime consumption interaction network can more accurately reflect the actual lifetime consumption pattern of the module.

[0212] Based on the same inventive concept, please refer to FIG2, which shows a schematic block diagram of the structure of a running data-driven Miniled module lifetime prediction device 100 for performing the above-described running data-driven Miniled module lifetime prediction method provided in an embodiment of this application. The running data-driven Miniled module lifetime prediction device 100 may include a communication unit 110, a machine-readable storage medium 120, and a processor 130.

[0213] In this embodiment, both the machine-readable storage medium 120 and the processor 130 are located in the runtime data-driven Miniled module lifetime prediction device 100 and are separately configured. Alternatively, the machine-readable storage medium 120 can also be integrated into the processor 130 and can communicate and interact with external systems through the communication unit 110. The machine-readable storage medium 120 stores machine-executable instructions for implementing the scheme of this application, and the processor 130 executes the machine-executable instructions stored in the machine-readable storage medium 120 to implement the runtime data-driven Miniled module lifetime prediction method provided in the aforementioned method embodiments.

[0214] It should be noted that, in order to simplify the description of the present invention and thus help to understand one or more embodiments of the invention, multiple features may sometimes be grouped into one embodiment, drawing or description thereof in the foregoing description of the embodiments of the present invention.

Claims

1. A method for predicting the lifetime of a minimized module based on runtime data, characterized in that, The method includes: collecting multi-source operational data and full-cycle historical lifetime correlation data of the Miniled module. The multi-source operational data includes operational load data, environmental impact data, performance feedback data, and component collaboration data. The full-cycle historical lifetime correlation data includes past multi-source operational records, lifetime end-of-life status records, stage performance degradation trajectories, and component interaction loss records. A lifetime consumption interaction network for the Miniled module is constructed, using the target lifetime influencing factor as the core node and the dynamic interaction relationship between factors as flexible connecting edges. The target lifetime influencing factor includes load impact factors, environmental correlation factors, performance degradation factors, and component collaboration factors. The multi-source operational data is then input into the lifetime... The lifespan consumption interaction network is dynamically coupled across dimensions with the stage performance degradation trajectory and component interaction loss records in the full-cycle historical lifespan correlation data to generate real-time historical interaction coupling results. Based on the real-time historical interaction coupling results, the node response mode of the lifespan consumption interaction network is dynamically adapted according to real-time data changes to generate an adaptive lifespan consumption rate. Based on the adaptive lifespan consumption rate and the current comprehensive performance status data of the Miniled module, the remaining lifespan prediction result of the Miniled module is generated. The actual operating data and actual lifespan status data generated by the Miniled module are then fed back into the lifespan consumption interaction network to dynamically adjust the interaction strength between core nodes. The transmission efficiency of the degree and flexible connection edges; the construction of the lifetime consumption interaction network of the Miniled module with the target lifetime influencing factor as the core node and the dynamic interaction relationship between the factors as the flexible connection edge, includes: extracting load effect factors from the operating load data of multi-source operating data. The load effect factors reflect the direct effect characteristics of various workloads on lifetime consumption during the operation of the Miniled module, covering the lifetime loss correlation characteristics corresponding to the load type and the loss accumulation characteristics corresponding to load changes; extracting environmental correlation factors from the environmental effect data of multi-source operating data. The environmental correlation factors reflect the indirect influence characteristics of the external environment in which the Miniled module is located on lifetime consumption. It covers the lifetime loss triggering characteristics corresponding to environmental factors and the loss aggravation characteristics corresponding to environmental changes; it extracts the performance degradation factor from the performance feedback data of multi-source operation data. The performance degradation factor reflects the correlation characteristics between performance output changes and lifetime consumption during the operation of the Miniled module, covering the lifetime loss mapping characteristics corresponding to performance parameter changes and the loss rate characteristics corresponding to performance stability; it extracts the component coordination factor from the component coordination data of multi-source operation data. The component coordination factor reflects the synergistic effect of the interaction of various components within the Miniled module on lifetime consumption, covering the loss correlation characteristics corresponding to component matching accuracy and the loss accumulation characteristics corresponding to component response synchronization.Historical load factors, historical environmental factors, historical performance degradation factors, and historical component synergy factors are extracted from multi-source operational records of full-cycle historical lifetime correlation data. Each historical factor corresponds to a historical operational record of the real-time target lifetime influencing factor, containing loss correlation characteristics and change patterns during historical operation. The direct interaction relationship between load factors and performance degradation factors is analyzed to identify their mutual triggering paths and influence transmission methods during lifetime consumption. Based on this direct interaction relationship and influence transmission method, a first flexible connection edge is constructed, containing initial parameters for interaction strength and influence transmission efficiency parameters. The relationship between environmental factors and performance degradation factors is analyzed. The study analyzes the indirect interaction between attenuation factors, identifies the mediating action path and loss amplification mechanism between them during the lifetime attenuation process, and constructs a second flexible connection edge based on this indirect interaction and loss amplification mechanism. The second flexible connection edge includes initial parameters for interaction strength and parameters for influence transfer efficiency. It also analyzes the synergistic interaction between load factors and environmental factors, identifies their joint action path and loss superposition effect during the lifetime attenuation process, and constructs a third flexible connection edge based on this synergistic interaction and loss superposition effect. The third flexible connection edge includes initial parameters for interaction strength and parameters for influence transfer efficiency. Finally, it analyzes the relationship between component synergistic factors and load factors, environmental factors, and performance factors. The cross-interaction relationships between attenuation factors are investigated to identify the regulatory paths and loss optimization / aggravation mechanisms of component synergy factors in various interaction relationships. Based on these cross-interaction relationships and regulatory mechanisms, a fourth, fifth, and sixth flexible connection edge are constructed, each containing initial parameters for interaction strength and parameters for influence transmission efficiency. Load factors, environmental factors, performance attenuation factors, component synergy factors, and various historical factors are used as independent core nodes, connected according to the interaction relationships of the first to sixth flexible connection edges to form an initial network structure. Stage performance attenuation trajectories and component interaction loss records are extracted from the full-cycle historical lifetime correlation data. The correspondence of target lifetime influencing factors is established, generating target interactive coupling nodes. These nodes integrate the synergistic effect logic of target lifetime influencing factors on lifetime decay and the historical data reference logic. These nodes are embedded into the initial network structure, and all core nodes and historical factor nodes are connected by newly added flexible connection edges. These flexible connection edges contain initial parameters for interaction strength and parameters for influence transmission efficiency. Node activation rules and edge propagation rules for the lifetime consumption interaction network are defined. Node activation rules define the conditions for core nodes to trigger responses based on input data and the method for calculating response strength. Edge propagation rules define the attenuation and enhancement logic for the interaction signals transmitted by flexible connection edges.By integrating all node activation rules and edge propagation rules, a lifetime consumption interaction network is constructed. This network reflects the full-dimensional dynamic interaction logic between target lifetime influencing factors, historical factors, and target interactive coupling nodes, enabling cross-dimensional correlation and propagation between input data and historical data.

2. The method for predicting the lifetime of a minimized module based on runtime data as described in claim 1, characterized in that, The process involves inputting multi-source operational data into a lifetime consumption interaction network and dynamically coupling it across dimensions with stage performance degradation trajectories and component interaction loss records in the full-cycle historical lifetime correlation data to generate real-time historical interaction coupling results. This includes: analyzing the core node association structure and flexible connection edge transmission logic of the lifetime consumption interaction network; identifying the interaction priority and signal transmission path between load factor nodes, environmental correlation factor nodes, performance degradation factor nodes, component synergy factor nodes, and target interaction coupling nodes; and extracting the real-time change trajectories of load factor, environmental correlation factor, performance degradation factor, and component synergy factor from the multi-source operational data. Each real-time change trajectory contains... The system collects continuous time-point factor state data and state change characteristics; extracts all stage performance degradation trajectories and corresponding component interaction loss records from the full-cycle historical lifetime correlation data. Each stage performance degradation trajectory is associated with the corresponding historical load factor change trajectory, historical environmental correlation factor change trajectory, historical performance degradation factor change trajectory, and historical component synergy factor change trajectory. Each component interaction loss record is associated with the corresponding historical component synergy factor change characteristics and historical performance degradation impact characteristics. The real-time change trajectory of the load factor is input into the lifetime consumption interaction network and transmitted to the target interaction coupling node through the first, third, and fourth flexible connection edges, triggering the target interaction coupling node to proceed according to the activation rules. The system performs signal processing to generate real-time load interaction signals. It inputs the real-time change trajectory of environmental factors into the lifetime consumption interaction network, transmitting it to the target interaction coupling node via the second, third, and fifth flexible connection edges. This triggers the target interaction coupling node to perform signal processing according to the activation rules, generating real-time environmental interaction signals. Similarly, it inputs the real-time change trajectory of performance degradation factors into the lifetime consumption interaction network, transmitting it to the target interaction coupling node via the first, second, and sixth flexible connection edges. This triggers the target interaction coupling node to perform signal processing according to the activation rules, generating real-time performance interaction signals. Finally, it inputs the real-time change trajectory of component coordination factors into the lifetime consumption interaction network, transmitting it via the fourth, fifth, and sixth flexible connection edges. The flexible connection edge and the sixth flexible connection edge are transmitted to the target interactive coupling node, triggering the target interactive coupling node to perform signal processing according to the activation rules and generate real-time collaborative interaction signals. The target interactive coupling node receives real-time load interaction signals, real-time environment interaction signals, real-time performance interaction signals, and real-time collaborative interaction signals, and integrates the signals according to the preset collaborative action logic to generate real-time comprehensive interaction features. The real-time comprehensive interaction features include independent features and joint interaction features of various signals. The historical comprehensive interaction features corresponding to the performance decay trajectory of all stages are traversed. The historical comprehensive interaction features are generated by the target interactive coupling node through the change trajectories of various historical factors associated with the performance decay trajectory of that stage, and include historical independent features and historical joint interaction features.The process iterates through all component interaction loss records, identifying historical collaborative interaction features. These features are generated from the historical component collaborative factor change features and historical performance degradation impact features associated with the component interaction loss record, through the target interaction coupling node. Real-time integrated interaction features are matched with each historical integrated interaction feature to calculate the degree of fit in feature dimensions, selecting the candidate stage performance degradation trajectory with the best fit. Real-time collaborative interaction signals are matched with each historical collaborative interaction feature to calculate the degree of fit in collaborative logic, selecting the candidate component interaction loss record with the best fit. Through the flexible connection edge propagation logic of the lifetime consumption interaction network, the candidate stage performance degradation trajectory and candidate component interaction loss records are integrated to ensure consistency in the historical factor change patterns of both. Based on the integrated candidate stage performance degradation trajectory and candidate component interaction loss records, combined with the node response results of the real-time integrated interaction features in the lifetime consumption interaction network, a real-time historical interaction coupling result is generated. This result includes the correlation mapping between real-time and historical data, interaction deviation features, and coupling adaptation parameters.

3. The method for predicting the lifetime of a minimized module based on runtime data as described in claim 1, characterized in that, The process of generating an adaptive lifetime consumption rate based on real-time historical interaction coupling results and dynamically adapting the node response mode of the lifetime consumption interaction network according to real-time data changes includes: continuously acquiring the latest state data and state change information of the target lifetime influencing factors at preset acquisition intervals, and capturing the state change characteristics of the target lifetime influencing factors in real time to form a dynamic feedback feature set; analyzing the candidate stage performance decay trajectory and candidate component interaction loss records in the real-time historical interaction coupling results, and extracting the corresponding historical lifetime consumption rate change curves and historical component interaction loss rate curves; comparing the normalized independent feedback features of each factor in the dynamic feedback feature set with the associated consumption rates of the corresponding stages in the historical rate curves to identify load rate difference features, environmental rate difference features, performance rate difference features, and collaborative rate difference features; and inputting the normalized rate difference features into the lifetime consumption rate... The lifetime consumption interaction network analyzes the comprehensive impact of various differential characteristics on the overall lifetime consumption rate through target interaction coupling nodes. Based on the comprehensive impact, the node response mode and edge transmission efficiency of the lifetime consumption interaction network are dynamically adapted. Based on the adjusted node response mode and edge transmission efficiency, the rate parameters of each stage in the historical lifetime consumption rate change curve and the historical component interaction loss rate curve are recalculated to obtain the adjusted historical rate curve. The adjusted historical lifetime consumption rate change curve and the historical component interaction loss rate curve are collaboratively integrated to form a comprehensive historical consumption rate curve. The initial segment rate features corresponding to the real-time historical interaction coupling results are extracted from the comprehensive historical consumption rate curve. Combined with the latest change trend of the dynamic feedback feature set, the initial segment rate features are adapted and corrected in real time through the collaborative action logic of the target interaction coupling nodes to generate an adaptive lifetime consumption rate.

4. The method for predicting the lifetime of a minimized module based on runtime data as described in claim 1, characterized in that, The process of generating a remaining lifetime prediction result for the Miniled module based on the adaptive lifetime consumption rate and the current comprehensive performance status data of the Miniled module includes: collecting the current comprehensive performance status data of the Miniled module, which includes current performance output parameters, performance output stability data, component collaborative work accuracy data, performance degradation start marker, and current runtime data. The current performance output parameters reflect the module's current core function output level; the performance output stability data reflects the fluctuation of the module's current performance output; the component collaborative work accuracy data reflects the accuracy of the interaction between components within the module; and the performance degradation start marker is used to determine the module's remaining lifetime prediction result. Whether the module has entered a significant performance degradation phase is determined by the current runtime data, which reflects the cumulative running time of the module. The adaptive lifetime consumption rate is analyzed to extract the rate change trend, rate characteristics at each stage, rate peak intervals, and rate degradation cycle characteristics. The rate change trend reflects the overall direction of the adaptive lifetime consumption rate over time, and the rate characteristics at each stage reflect the core characteristics of the consumption rate at different lifetime stages. The current comprehensive performance status data is compared with the stage performance degradation trajectory in the full-cycle historical lifetime correlation data. Based on the current performance output parameters, performance output stability data, and component collaborative work accuracy data, the current lifetime degradation stage of the Miniled module is determined. During the current lifetime decay phase, the corresponding phase rate parameters are extracted from the adaptive lifetime consumption rate. These parameters reflect the core characteristics of the current lifetime consumption rate, including the base consumption rate, rate change coefficient, and rate fluctuation range. The performance decay initiation marker in the current comprehensive performance status data is analyzed, and combined with the phase rate parameters and current runtime data, the starting point for calculating the remaining lifetime is determined. This starting point is the lifetime consumption process position corresponding to the current time node. Based on the phase rate parameters and rate change trends, the subsequent rate changes in the current lifetime decay phase are predicted, generating a subsequent rate prediction sequence for the current phase. This subsequent rate prediction sequence includes the current lifetime decay data. The predicted consumption rate for each time interval within the remaining time of the previous stage; based on the predicted rate sequence of the subsequent stages and the remaining lifetime ratio of the current stage, the remaining duration of the current lifetime decay stage is calculated; the rate parameters of all subsequent stages after the current lifetime decay stage are extracted from the adaptive lifetime consumption rate, including the base consumption rate, rate change coefficient, rate fluctuation range, and stage duration ratio of each subsequent stage; the expected duration of each subsequent stage is calculated according to the rate parameters and rate change trend of each subsequent stage; the remaining duration of the current lifetime decay stage is accumulated with the expected duration of all subsequent stages to obtain the total remaining lifetime of the Miniled module;By combining performance output stability data, component collaborative work accuracy data, and total remaining lifetime from the current comprehensive performance status data, a remaining lifetime prediction result is generated, including the total remaining lifetime, the remaining lifetime of each stage, stage decay characteristic descriptions, and performance maintenance recommendations. The stage decay characteristic descriptions reflect the consumption rate characteristics and performance change trends of each remaining lifetime stage, and the performance maintenance recommendations are generated based on the decay characteristics of each stage and historical data.

5. The method for predicting the lifetime of a minimized module based on runtime data as described in claim 1, characterized in that, The process of inputting the subsequent actual operating data and actual lifetime status data generated by the Miniled module into the lifetime consumption interaction network to dynamically adjust the strength of the interaction relationship between core nodes and the transmission efficiency of flexible connection edges includes: establishing a subsequent data acquisition and tracking mechanism, which starts when the remaining lifetime prediction result is generated, and continuously collects the subsequent actual operating data and actual lifetime status data generated by the Miniled module until the Miniled module reaches the end of its lifetime; the subsequent actual operating data includes the trajectory of subsequent load factor changes, the trajectory of subsequent environmental correlation factor changes, the trajectory of subsequent performance degradation factor changes, and the trajectory of subsequent component coordination factor changes, with each trajectory containing the actual operating data of consecutive time nodes. The actual lifetime state data and state change characteristics are generated subsequently. Subsequent actual lifetime state data includes subsequent performance degradation records, subsequent component interaction loss records, and final lifetime end-of-life state records. Subsequent performance degradation records reflect the actual changes in performance parameters during the module's subsequent operation; subsequent component interaction loss records reflect the actual losses in component interactions during the module's subsequent operation; and the final lifetime end-of-life state record reflects the core state data when the module reaches the end of its lifetime. The subsequent load factor change trajectory, subsequent environmental correlation factor change trajectory, subsequent performance degradation factor change trajectory, and subsequent component collaboration factor change trajectory are input inversely into the lifetime consumption interaction network, corresponding to load factor nodes, environmental correlation factor nodes, performance degradation factor nodes, and components, respectively. The system uses a collaborative factor node; it inputs subsequent performance degradation records and subsequent component interaction loss records into the target interaction coupling node of the lifetime consumption interaction network to compare the deviation between the prediction results and the actual situation; through the target interaction coupling node, it integrates the change trajectory of subsequent target lifetime influencing factors and subsequent performance degradation records and subsequent component interaction loss records to generate subsequent comprehensive interaction features and subsequent collaborative interaction features; it extracts the corresponding predicted comprehensive interaction features and predicted collaborative interaction features from the remaining lifetime prediction results, compares the subsequent comprehensive interaction features with the predicted comprehensive interaction features to identify the interaction deviation between the two; it compares the subsequent collaborative interaction features with the predicted collaborative interaction features to identify the collaborative deviation between the two; based on the interaction deviation and collaborative deviation, it calculates... The deviation impact value of the interaction relationship between each core node in the lifetime consumption interaction network is calculated. The deviation impact value reflects the degree of difference between the current interaction relationship strength and the actual interaction situation. Based on the deviation impact value, the interaction relationship strength between load factor node and performance degradation factor node, environmental correlation factor node and performance degradation factor node, load factor node and environmental correlation factor node, and component collaboration factor node and other core factor node are dynamically adjusted. The larger the deviation impact value, the larger the adjustment range. The transmission efficiency deviation value of each flexible connection edge in the lifetime consumption interaction network is calculated simultaneously. The transmission efficiency deviation value reflects the degree of difference between the current transmission efficiency and the actual data transmission requirements.Based on the conduction efficiency deviation, the conduction efficiency parameters of the first to sixth flexible connecting edges and newly added flexible connecting edges are dynamically adjusted, including adjusting the edge attenuation coefficient, enhancement threshold, and signal transmission delay parameters. The larger the conduction efficiency deviation, the greater the adjustment magnitude. The internal collaborative logic and weight allocation ratio of the target interactive coupling nodes are adjusted to enable the target interactive coupling nodes to accurately integrate subsequent actual data and optimize signal processing. The conduction accuracy and prediction precision of the adjusted lifetime consumption interactive network are verified using sample data from the full-cycle historical lifetime correlation data that did not participate in the initial network construction. Based on the verification results, the interaction strength between core nodes and the conduction efficiency of flexible connecting edges are fine-tuned a second time to ensure that the adjusted lifetime consumption interactive network reflects the actual lifetime consumption pattern of the Miniled module.

6. The method for predicting the lifetime of a minimized module based on runtime data as described in claim 1, characterized in that, The analysis examines the cross-interaction relationships between component synergy factors and load action factors, environmental correlation factors, and performance degradation factors. It identifies the regulatory paths and loss optimization / aggravation mechanisms of component synergy factors within these interactions. Based on these cross-interaction relationships and regulatory mechanisms, it constructs a fourth, fifth, and sixth flexible connection edge. This includes: selecting component synergy factor variation data, load action factor variation data, environmental correlation factor variation data, and performance degradation factor variation data from multi-source operational data under different operational scenarios. Different operational scenarios reflect different combinations of load intensity, environmental conditions, and component operating modes. Simultaneous analysis is performed on each group of component synergy factor variation data and load action factor variation data to extract their temporal dimensions. This study examines the synchronicity, numerical correlation, and mutual triggering relationships of changes in load factors. It combines the corresponding stage performance degradation trajectories and component interaction loss records from the full-cycle historical lifetime correlation data to analyze the impact of component synergy factors on the loss relationship between load factors and performance degradation factors under different synchronicity and numerical correlation characteristics. The study identifies the regulatory paths of component synergy factors in the interaction process between load factors and performance degradation factors, including the positive regulation path where component synergy factors reduce losses by optimizing load allocation, and the negative regulation path where component synergy factors exacerbate losses due to synergy deviations. It also identifies the loss optimization mechanisms corresponding to the positive regulation path, i.e., the state in which component synergy factors can reduce the impact of load factors on performance degradation; and identifies the negative regulation path. This study investigates the loss aggravation mechanism corresponding to the adjustment path, specifically, the state in which the component synergy factor increases the impact of the load effect factor on performance degradation. Based on the cross-interaction relationship between the component synergy factor and the load effect factor, positive adjustment paths, negative adjustment paths, loss optimization mechanisms, and loss aggravation mechanisms, the interaction rules and parameter configuration logic of the fourth flexible connection edge are defined. Initial parameters for the interaction strength and the influence transmission efficiency of the fourth flexible connection edge are set. The initial interaction strength parameter is determined based on the average adjustment strength of the component synergy factor on the load effect factor in historical data, and the influence transmission efficiency parameter is determined based on the average transmission efficiency of the adjustment signal in historical data. Using the same analysis method, the study further analyzes the changes in component synergy factor data and environmental correlation factor data. Synchronous analysis is performed to extract the synchronicity of changes, numerical correlation characteristics, and mutual triggering relationships between the two factors. Combined with historical lifetime correlation data, the impact of component synergy factors on the loss relationship between environmental correlation factors and performance degradation factors is analyzed, identifying corresponding positive and negative adjustment paths. The loss optimization mechanism of the positive adjustment path and the loss aggravation mechanism of the negative adjustment path are identified, and the interaction rules and parameter configuration logic of the fifth flexible connection edge are defined. Initial parameters for the interaction strength and influence transmission efficiency of the fifth flexible connection edge are set, with parameter values ​​determined based on statistical analysis results of historical data. Synchronous analysis is performed on the component synergy factor change data and the performance degradation factor change data to extract their synchronicity of changes, numerical correlation characteristics, and mutual triggering relationships.By combining historical lifetime correlation data, this study analyzes the impact of component synergy factors on the inherent loss patterns of performance degradation factors, identifying corresponding positive and negative adjustment paths. It also identifies the loss optimization mechanism of the positive adjustment path and the loss aggravation mechanism of the negative adjustment path, defining the interaction rules and parameter configuration logic for the sixth flexible connection edge. Initial parameters for the interaction strength and influence transmission efficiency of the sixth flexible connection edge are set, with parameter values ​​determined based on statistical analysis of historical data. The interaction rules and parameter configuration logic for the fourth, fifth, and sixth flexible connection edges are then verified to ensure that these edges reflect the cross-interaction relationship and adjustment mechanism between component synergy factors and their corresponding core factors.

7. The method for predicting the lifetime of a minimized module based on runtime data as described in claim 2, characterized in that, The process involves generating real-time historical interaction coupling results based on the integrated candidate stage performance degradation trajectory and candidate component interaction loss records, combined with the node response results in the lifetime consumption interaction network using real-time comprehensive interaction features. This includes: extracting key degradation nodes and the duration percentage of each degradation stage from the integrated candidate stage performance degradation trajectory; the key degradation nodes represent important turning points in performance degradation within the candidate stage performance degradation trajectory, and the duration percentage represents the proportion of time for each degradation stage within the entire lifetime; and extracting key loss nodes and the duration percentage of each loss stage from the integrated candidate component interaction loss records; the key loss nodes represent important turning points in component interaction loss within the candidate component interaction loss records, and the duration percentage... This approach reflects the time proportion of each loss stage within the entire lifecycle; it associates key feature points in the real-time integrated interaction characteristics with key decay nodes in the performance decay trajectory of candidate stages, establishing a one-to-one correspondence between real-time feature points and historical decay nodes, forming a core correlation mapping relationship between real-time and historical data; it also associates key feature points in the real-time collaborative interaction signals with key loss nodes in the interaction loss records of candidate components, establishing a one-to-one correspondence between real-time collaborative feature points and historical loss nodes, supplementing the correlation mapping relationship between real-time and historical data; based on the core correlation mapping relationship and the supplementary correlation mapping relationship, it generates a complete correlation mapping relationship between real-time and historical data, with the correlation mapping relationship clearly defining each real-time feature point. The corresponding historical node positions and characteristic attributes are analyzed; the differences between the real-time integrated interaction characteristics and the historical integrated interaction characteristics corresponding to the candidate stage performance degradation trajectory are calculated in each dimension to form interaction deviation characteristics, which include the magnitude, direction, and trend of the differences in each dimension; the differences between the real-time collaborative interaction signals and the historical collaborative interaction characteristics corresponding to the candidate component interaction loss records are calculated in each dimension and added to the interaction deviation characteristics; the distribution pattern and causes of the interaction deviation characteristics are analyzed, the distribution pattern reflects the concentration of deviations in each dimension, and the causes are determined based on the differences in operating scenarios, parameter settings, and environmental conditions between real-time data and historical data; based on the correlation mapping relationship and interaction deviation characteristics, the coupling is calculated. The adaptation parameters, including the adaptation coefficient between real-time and historical data, the deviation correction coefficient, and the signal conditioning coefficient, are used to optimize the coupling effect between real-time and historical signals. The adaptation coefficient is determined based on the degree of fit between real-time and historical features; the higher the fit, the larger the adaptation coefficient. The deviation correction coefficient is determined based on the strength and distribution of the interaction deviation features; the larger the deviation, the greater the adjustment range of the deviation correction coefficient. The signal conditioning coefficient is determined based on the node response results and edge propagation efficiency in the lifetime consumption interaction network and is used to optimize the coupling effect between real-time and historical signals. The correlation mapping relationship, interaction deviation features, and coupling adaptation parameters are integrated to generate a real-time historical interaction coupling result that includes a complete correlation mapping relationship, comprehensive interaction deviation features, and precise coupling adaptation parameters.

8. A Miniled module lifetime prediction device based on runtime data, characterized in that, include: processor; A machine-readable storage medium for storing machine-executable instructions of the processor; wherein the processor is configured to perform the runtime data-driven Miniled module lifetime prediction method of any one of claims 1 to 7 by executing the machine-executable instructions.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes machine-executable instructions, the processor reads the machine-executable instructions from the computer-readable storage medium, and the processor executes the machine-executable instructions to cause the computer device to perform the runtime data-driven Miniled module lifetime prediction method as described in any one of claims 1 to 7.

Images