Heat dissipation monitoring method and system of organic electroluminescence display panel

Abstract

The invention relates to the technical field of heat dissipation of display panels, and discloses a heat dissipation monitoring method and system for an organic electroluminescence display panel, and the method comprises the steps: presetting a plurality of monitoring points and a standard monitoring time length, obtaining the real-time temperature data and real-time temperature change characteristics of each monitoring point in the standard monitoring time length, generating a first heat dissipation coefficient; constructing an influence prediction model, obtaining predicted performance influence characteristics, generating a second heat dissipation coefficient according to the predicted performance influence characteristics, generating a comprehensive heat dissipation coefficient in combination with the second heat dissipation coefficient, judging whether an optimization instruction of a preset heat dissipation strategy is generated or not, and if yes, determining an optimized heat dissipation strategy and performing analogue simulation to obtain a simulation application evaluation value; whether the optimized heat dissipation strategy is optimized again or not is judged, the application effect of the heat dissipation strategy is accurately evaluated, and the influence on the performance and the service life of the display panel is reduced.

Description

Technical Field

[0001] The present application relates to the technical field of heat dissipation of display panels, and particularly to a method and system for monitoring heat dissipation of an organic light-emitting diode display panel. Background Art

[0002] The organic light-emitting diode display panel is a new type of display technology. The organic light-emitting diode display panel has characteristics such as high contrast, bright colors, and fast response speed, making the display effect more excellent. At the same time, the characteristics of being thin, light, and flexible also bring more innovation space. However, a large amount of heat is generated when the display panel works, and heat dissipation of the display panel is required. If the heat dissipation efficiency is low or the heat dissipation uniformity is poor, it will affect the light-emitting efficiency and service life of the panel. Therefore, there is an urgent need for a method and system for monitoring heat dissipation of an organic light-emitting diode display panel to accurately evaluate the application effect of the heat dissipation strategy and reduce the impact on the performance and service life of the display panel. Summary of the Invention

[0003] To solve the above technical problems, the present application provides a method and system for monitoring heat dissipation of an organic light-emitting diode display panel. By calculating the first heat dissipation coefficient and the second heat dissipation coefficient of each monitoring point and generating a comprehensive heat dissipation coefficient, it is determined whether to correct the preset heat dissipation strategy. If so, an optimized heat dissipation strategy is obtained and simulated, and a simulation application evaluation value is obtained, so as to timely discover and adjust the deficiencies of the preset heat dissipation strategy, improve the heat dissipation efficiency, and reduce the impact on the performance and service life of the display panel.

[0004] In some embodiments of the present application, a method for monitoring heat dissipation of an organic light-emitting diode display panel is provided, including: Pre-setting a number of monitoring points and a standard monitoring duration, obtaining the real-time temperature data and real-time temperature change characteristics of each monitoring point within the standard monitoring duration, and generating a first heat dissipation coefficient according to the real-time temperature data and the real-time temperature change characteristics; Determining the historical performance influence characteristics corresponding to each monitoring point according to the historical monitoring log, constructing an influence prediction model, and generating predicted performance influence characteristics according to the real-time temperature data and the influence prediction model; Generating a second heat dissipation coefficient according to the predicted performance influence characteristics, generating a comprehensive heat dissipation coefficient according to the first heat dissipation coefficient and the second heat dissipation coefficient, and determining whether to generate an optimization instruction for the preset heat dissipation strategy. If so, determining the optimized heat dissipation strategy; Performing simulation on the optimized heat dissipation strategy, generating a simulation application evaluation value of the optimized heat dissipation strategy according to the simulation result, and determining whether to further optimize the optimized heat dissipation strategy according to the simulation application evaluation value. If not, issuing an optimization instruction.

[0005] In some embodiments of the present application, the standard monitoring duration includes: Preset several heat dissipation evaluation indicators, and determine the comprehensive heat dissipation evaluation indicator according to the several heat dissipation evaluation indicators; Collect the historical heat dissipation evaluation value of the comprehensive heat dissipation evaluation indicator and the historical temperature data at each monitoring point under different monitoring devices based on the historical monitoring time nodes in the historical monitoring log; Construct several historical temperature change curves at the corresponding monitoring points according to the historical temperature data at each monitoring point under different monitoring devices, compare them with the historical real-time temperature change curves at the corresponding monitoring points, and generate the adaptability of each monitoring device to the corresponding historical ambient parameters according to the comparison results; Set the historical temperature change curve corresponding to the monitoring device with the maximum adaptability as the historical characteristic temperature change curve of the corresponding monitoring point; Construct a device-environment adaptation mapping table according to the adaptability of the monitoring devices and historical ambient parameters in several historical monitoring logs; Construct a historical heat dissipation evaluation value change curve according to the historical heat dissipation evaluation value of the comprehensive heat dissipation evaluation indicator in each historical monitoring log; Conduct curve correlation analysis on the historical characteristic temperature change curve of each monitoring point and the historical heat dissipation evaluation value of the comprehensive heat dissipation evaluation indicator in the same historical monitoring log to obtain the curve correlation degree; Mark the historical monitoring nodes with a curve correlation degree greater than the preset correlation degree threshold and the historical monitoring nodes with a curve correlation degree less than the preset correlation degree threshold in the historical characteristic temperature change curve of each monitoring point, and set the historical time duration between the marked historical monitoring nodes as the pending standard time duration; Perform mean processing on the pending standard time durations of the same monitoring point in different historical monitoring logs, and set the mean-processed pending standard time duration as the standard monitoring time duration of the corresponding monitoring point.

[0006] In some embodiments of the present application, generating the first heat dissipation coefficient of the organic electroluminescent display panel according to the real-time temperature data and temperature change characteristics includes: Obtain the real-time ambient parameters, compare and analyze the real-time ambient parameters with the historical ambient parameters in the device-environment adaptation mapping table, and obtain the consistency between the real-time ambient parameters and the historical ambient parameters according to the analysis results; Set the monitoring device corresponding to the historical ambient parameter with the maximum consistency as the real-time monitoring device of the current organic electroluminescent display panel; Set the inspection duration according to the standard monitoring duration of each monitoring point, and set the data acquisition nodes of the corresponding monitoring points according to the standard monitoring duration and the preset time interval; Based on the real-time monitoring device and data acquisition nodes, obtain the real-time temperature data of the corresponding monitoring points, map it to the inspection duration of the corresponding monitoring points, and generate a real-time temperature data change curve; Analyze the real-time temperature data change curve to obtain the real-time temperature change characteristics of the corresponding monitoring points. The real-time temperature change characteristics include the real-time temperature change trend, the real-time temperature change rate, and the real-time temperature change magnitude; Perform curve extrapolation based on the real-time temperature data change curve and the real-time temperature change characteristics to obtain the predicted temperature data change curve within the standard monitoring duration of the corresponding monitoring points; Obtain the predicted temperature data and predicted temperature change characteristics of several data acquisition nodes of the corresponding monitoring points according to the predicted temperature data change curve. The predicted temperature change characteristics include the predicted temperature change trend, the predicted temperature change rate, and the predicted temperature change magnitude; Construct a reference library of standard temperature data change curves for each monitoring point. The reference library of standard temperature data change curves includes several standard temperature data change curves; Intercept several standard temperature data change curves according to the inspection duration of each monitoring point to obtain several first standard temperature data change curve segments and corresponding first standard temperature change characteristics; Compare the real-time temperature data change curve with several first standard temperature data change curve segments to obtain a similarity coefficient; Select the first standard temperature data change curve segment with the largest similarity coefficient, perform a first difference analysis with the real-time temperature data change curve, and perform a second difference analysis on the corresponding second standard temperature data change curve segment of the selected first standard temperature data change curve segment and the predicted temperature data change curve. Generate a first heat dissipation coefficient according to the first difference analysis result and the second difference analysis result; Among them, the first difference analysis result includes the real-time temperature data difference and the real-time temperature change characteristic difference at each data acquisition node in the inspection duration; The second difference analysis result includes the predicted temperature data difference and the predicted temperature change characteristic difference at each data acquisition node remaining in the corresponding standard monitoring duration.

[0007] In some embodiments of the present application, determine the historical performance influence characteristics corresponding to the historical temperature data according to the historical monitoring log, and construct an influence prediction model, including: Preset the preset performance factors of the organic electroluminescent display panel in advance; Based on the data acquisition nodes in the standard monitoring duration of each monitoring point in the historical monitoring log, obtain the historical temperature data and the historical performance-related data of each preset performance factor; Compare the historical performance-related data with the corresponding standard performance-related data to obtain the historical performance evaluation values of each preset performance factor at each data collection node; Obtain the historical temperature data difference between adjacent data collection nodes in the standard monitoring duration of each monitoring point and the historical performance evaluation value difference of each preset performance factor, and construct a historical temperature data difference sequence and several historical performance evaluation value difference sequences; Compare and analyze the historical temperature data difference sequence with the historical performance evaluation value difference sequences of each preset performance factor respectively to obtain several sequence correlations; Set the preset performance factor with a sequence correlation greater than the preset sequence correlation threshold as the historical performance impact factor corresponding to the monitoring point; Set each historical performance evaluation value difference in the historical performance evaluation value difference sequence corresponding to the historical performance impact factor as the historical performance impact magnitude of the historical temperature data difference of the corresponding data collection node of the monitoring point; Set the historical performance impact factor and several historical performance impact magnitudes as the historical performance impact characteristics of the corresponding monitoring point; Use several historical temperature data differences in the historical temperature data difference sequence of each monitoring point as training input data, and use the historical performance impact factor in the historical performance impact characteristics of the corresponding monitoring point and the corresponding several historical performance evaluation value differences in the historical performance evaluation value difference sequence as training output data; Perform neural network training based on the training input data and the training output data to obtain an impact prediction model for the corresponding monitoring point.

[0008] In some embodiments of the present application, generating a second heat dissipation coefficient according to the predicted performance impact characteristics includes: Obtain the real-time performance-related data at each data collection node of the performance impact factor of each monitoring point during the inspection duration, and generate the real-time performance evaluation value of the performance impact factor at the corresponding data collection node according to the real-time performance-related data; Generate a real-time performance evaluation value change curve of the corresponding performance impact factor according to the real-time performance evaluation values of each performance impact factor at each data collection node during the inspection duration, and obtain real-time evaluation change characteristics; Wherein, the real-time evaluation change characteristics include a real-time evaluation change trend, a real-time evaluation change rate, and a real-time evaluation change magnitude; Generate a predicted temperature data difference at the corresponding remaining data collection node according to the predicted temperature data at the remaining adjacent data collection nodes of each monitoring point in the standard monitoring duration, and construct a predicted temperature data difference sequence; Sequentially input the predicted temperature data differences in the predicted temperature data difference sequence of each monitoring point into the corresponding influence prediction model to obtain the prediction performance influence characteristics at the remaining data acquisition nodes; The prediction performance influence characteristics include prediction performance influence factors and several prediction performance evaluation value differences of the prediction performance influence factors. A prediction performance evaluation value difference sequence is constructed based on the several prediction performance evaluation value differences; Generate the predicted performance evaluation value of the corresponding performance influence factor at the remaining data acquisition nodes during the standard monitoring duration based on the real-time performance evaluation value of the corresponding performance influence factor at the last data acquisition node during the inspection duration and the prediction performance evaluation value difference sequence; Generate a predicted performance evaluation value change curve of the corresponding performance influence factor based on the predicted performance evaluation values of each performance influence factor at the remaining data acquisition nodes during the standard monitoring duration, and obtain the prediction evaluation change characteristics. The prediction evaluation change characteristics include prediction evaluation change trend, prediction evaluation change rate, and prediction evaluation change magnitude; Compare the real-time performance evaluation value change curve with several first standard performance evaluation value change curve segments in the standard performance evaluation value change curve reference library of the corresponding performance influence factor of the corresponding monitoring point to obtain a similarity coefficient; Among them, the standard performance evaluation value change curve reference library includes several standard performance evaluation value change curves. Based on the inspection duration, the several standard performance evaluation value change curves are divided into first standard performance evaluation value change curve segments and second standard performance evaluation value change curve segments; Select the first standard performance evaluation value change curve segment with the largest similarity coefficient, and perform a third difference analysis with the real-time performance evaluation value change curve. Perform a fourth difference analysis on the second standard performance evaluation value change curve segment corresponding to the selected first standard performance evaluation value change curve segment and the predicted performance evaluation value change curve. Generate a second heat dissipation coefficient according to the results of the third difference analysis and the fourth difference analysis; Among them, the results of the third difference analysis include the real-time performance evaluation value differences of each performance influence factor at each data acquisition node during the inspection duration and the real-time evaluation change characteristic differences; The results of the fourth difference analysis include the predicted performance evaluation value differences of each performance influence factor at each remaining data acquisition node during the standard monitoring duration and the prediction evaluation change characteristic differences.

[0009] In some embodiments of the present application, generating a comprehensive heat dissipation coefficient according to the first heat dissipation coefficient and the second heat dissipation coefficient includes: The calculation formula of the first heat dissipation coefficient is: ; Wherein, H1 is the first heat dissipation coefficient, a1 is the first heat dissipation conversion coefficient, a2 is the second heat dissipation conversion coefficient, f1 is the weight coefficient of the temperature data difference, f2 is the weight coefficient of the temperature change characteristic difference, n1 is the total number of data acquisition nodes in the inspection duration, n2 is the remaining number of data acquisition nodes in the standard monitoring duration corresponding to the monitoring point, is the real-time temperature data difference at the i1-th data acquisition node in the inspection duration, is the predicted temperature data difference at the i2-th data acquisition node remaining in the standard monitoring duration, is the real-time temperature change characteristic difference at the i1-th data acquisition node in the inspection duration, is the predicted temperature change characteristic difference at the i2-th data acquisition node remaining in the standard monitoring duration; The calculation formula of the second heat dissipation coefficient is: ; Wherein, H2 is the second heat dissipation coefficient, a3 is the third heat dissipation conversion coefficient, a4 is the fourth heat dissipation conversion coefficient, h1 is the weight coefficient of the performance evaluation value difference, h2 is the weight coefficient of the evaluation change characteristic difference, m is the total number of performance impact factors of the current monitoring point, is the real-time performance evaluation value difference of the s-th performance impact factor at the i1-th data acquisition node in the inspection duration, is the predicted performance evaluation value difference of the s-th performance impact factor at the i2-th data acquisition node remaining in the standard monitoring duration, ds is the weight coefficient of the s-th performance impact factor, is the real-time evaluation change characteristic difference of the s-th performance impact factor at the i1-th data acquisition node in the inspection duration, is the predicted evaluation change characteristic difference of the s-th performance impact factor at the i2-th data acquisition node remaining in the standard monitoring duration; The calculation formula of the comprehensive heat dissipation coefficient is: k2; Wherein, H0 is the comprehensive heat dissipation coefficient, k1 is the weight coefficient of the first heat dissipation coefficient, k2 is the weight coefficient of the second heat dissipation coefficient.

[0010] In some embodiments of the present application, it is determined whether to generate an optimization instruction for the preset heat dissipation strategy. If so, determining the optimized heat dissipation strategy includes: Presetting the comprehensive heat dissipation coefficient threshold for each monitoring point; If the comprehensive heat dissipation coefficient of each monitoring point is greater than the corresponding comprehensive heat dissipation coefficient threshold, it is determined not to generate an optimization instruction for the preset heat dissipation strategy; If the comprehensive heat dissipation coefficient of a monitoring point is less than the corresponding comprehensive heat dissipation coefficient threshold, an optimization instruction for generating a preset heat dissipation strategy is determined. The optimization instruction includes the temperature value to be optimized of the monitoring point to be optimized and a preset optimization strategy for the temperature value to be optimized; Optimize the preset heat dissipation strategy according to the preset optimization strategy of each monitoring point to be optimized to obtain an optimized heat dissipation strategy.

[0011] In some embodiments of the present application, a simulation is performed on the optimized heat dissipation strategy, and a simulation application evaluation value of the optimized heat dissipation strategy is generated according to the simulation results, including: Generate a simulation model of the monitoring point to be optimized according to the position information of the monitoring point to be optimized and the surrounding environment information, in combination with the real-time temperature data at the last data acquisition node of the inspection duration; Perform heat dissipation control on the simulation model according to the optimized heat dissipation strategy to obtain the simulation temperature data at the remaining data acquisition nodes of the standard monitoring duration of each monitoring point to be optimized and the simulation heat dissipation duration when the corresponding temperature value to be optimized is reached; Set a corresponding compensation coefficient according to the simulation heat dissipation duration; Preset a preset temperature data threshold for each remaining data acquisition node of each monitoring point to be optimized after the optimized heat dissipation strategy; Compare the simulation temperature data of each monitoring point to be optimized with the corresponding preset temperature data threshold to obtain a simulation temperature data difference; Generate a simulation application evaluation value of the optimized heat dissipation strategy according to the simulation temperature data differences of multiple monitoring points to be optimized and the corresponding compensation coefficients; The calculation formula of the simulation application evaluation value is: ; Where P is the simulation application evaluation value, is the simulation application conversion coefficient, z is the total number of monitoring points to be optimized, is the simulation temperature data difference at the i2-th data acquisition node remaining in the standard monitoring duration of the v-th monitoring point to be optimized, is the compensation coefficient of the v-th monitoring point to be optimized, and Uv is the weight coefficient of the v-th monitoring point to be optimized.

[0012] In some embodiments of the present application, it is determined whether to further optimize the optimized heat dissipation strategy according to the simulation application evaluation value, including: Preset a simulation application evaluation value threshold; If the simulation application evaluation value is greater than the simulation application evaluation value threshold, do not further optimize the optimized heat dissipation strategy, and issue an optimization instruction; If the simulation application evaluation value is not greater than the simulation application evaluation value threshold, further optimize the optimized heat dissipation strategy.

[0013] In some embodiments of the present application, there is also provided a heat dissipation monitoring system for an organic electroluminescent display panel: An acquisition module, configured to preset a plurality of monitoring points and a standard monitoring duration, acquire real-time temperature data and real-time temperature change characteristics of each monitoring point within the standard monitoring duration, and generate a first heat dissipation coefficient according to the real-time temperature data and the real-time temperature change characteristics; A construction module, configured to determine historical performance influence characteristics corresponding to each monitoring point according to historical monitoring logs, construct an influence prediction model, and generate predicted performance influence characteristics according to the real-time temperature data and the influence prediction model; A judgment module, configured to generate a second heat dissipation coefficient according to the predicted performance influence characteristics, generate a comprehensive heat dissipation coefficient according to the first heat dissipation coefficient and the second heat dissipation coefficient, and judge whether to generate an optimization instruction for a preset heat dissipation strategy. If so, determine an optimized heat dissipation strategy; An optimization module, configured to perform simulation on the optimized heat dissipation strategy, generate a simulation application evaluation value of the optimized heat dissipation strategy according to the simulation result, and judge whether to further optimize the optimized heat dissipation strategy according to the simulation application evaluation value. If not, issue an optimization instruction.

[0014] A heat dissipation monitoring method and system for an organic electroluminescent display panel according to an embodiment of the present application, compared with the prior art, has the beneficial effects that: By calculating the first heat dissipation coefficient and the second heat dissipation coefficient of each monitoring point, generating a comprehensive heat dissipation coefficient, judging whether to correct the preset heat dissipation strategy, if so, obtaining an optimized heat dissipation strategy and performing simulation, obtaining a simulation application evaluation value, timely discovering and adjusting the deficiencies of the preset heat dissipation strategy, improving the heat dissipation efficiency, and reducing the impact on the performance and lifespan of the display panel. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 is a schematic flowchart of a heat dissipation monitoring method for an organic electroluminescent display panel according to an embodiment of the present application; Figure 2 is a schematic diagram of a heat dissipation monitoring system for an organic electroluminescent display panel according to an embodiment of the present application. DETAILED DESCRIPTION

[0016] The following will further describe in detail the specific embodiments of the present application with reference to the drawings and embodiments. The following embodiments are used to illustrate the present application, but are not used to limit the scope of the present application.

[0017] In the description of the present application, it should be understood that the orientation or positional relationship indicated by terms such as "center", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc. is based on the orientation or positional relationship shown in the drawings. It is only for the convenience of describing the present application and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as a limitation to the present application.

[0018] The terms "first" and "second" are only used for descriptive purposes and should not be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, features defined with "first" and "second" may explicitly or implicitly include one or more of such features. In the description of the present application, unless otherwise specified, the meaning of "a plurality" is two or more.

[0019] In the description of the present application, it should be noted that unless otherwise clearly specified and limited, the terms "install", "connect", and "couple" should be understood in a broad sense. For example, it may be a fixed connection, a detachable connection, or an integral connection; it may be a mechanical connection or an electrical connection; it may be directly connected or indirectly connected through an intermediate medium, and it may be the communication inside two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present application can be understood according to specific circumstances.

[0020] As Figure 1 shown, a heat dissipation monitoring method for an organic electroluminescent display panel according to an embodiment of the present application includes: Step S101: Preset a number of monitoring points and a standard monitoring duration in advance, obtain the real-time temperature data and real-time temperature change characteristics of each monitoring point within the standard monitoring duration, and generate a first heat dissipation coefficient according to the real-time temperature data and the real-time temperature change characteristics; Step S102: Determine the historical performance influence characteristics corresponding to each monitoring point according to the historical monitoring logs, construct an influence prediction model, and generate predicted performance influence characteristics according to the real-time temperature data and the influence prediction model; Step S103: Generate a second heat dissipation coefficient according to the predicted performance influence characteristics, generate a comprehensive heat dissipation coefficient according to the first heat dissipation coefficient and the second heat dissipation coefficient, and determine whether to generate an optimization instruction for a preset heat dissipation strategy. If so, determine an optimized heat dissipation strategy; Step S104: Perform a simulation for the optimized heat dissipation strategy, generate a simulation application evaluation value for the optimized heat dissipation strategy according to the simulation results, and determine whether to further optimize the optimized heat dissipation strategy according to the simulation application evaluation value. If not, issue an optimization instruction.

[0021] In this embodiment, the preset heat dissipation strategy refers to a heat dissipation strategy set in advance, and the optimized heat dissipation strategy is adjusted according to the preset heat dissipation strategy within the time after the inspection duration in the standard monitoring duration for each monitoring point.

[0022] In some embodiments of the present application, the standard monitoring duration includes: Set a number of heat dissipation evaluation indicators in advance, and determine the comprehensive heat dissipation evaluation indicator according to the number of heat dissipation evaluation indicators; Collect the historical heat dissipation evaluation value of the comprehensive heat dissipation evaluation indicator and the historical temperature data at each monitoring point under different monitoring devices based on the historical monitoring time nodes in the historical monitoring log; Construct a number of historical temperature change curves at the corresponding monitoring points according to the historical temperature data at each monitoring point under different monitoring devices, and compare them with the historical real-time temperature change curves at the corresponding monitoring points. Generate the adaptability of each monitoring device to the corresponding historical ambient parameters according to the comparison results; Set the historical temperature change curve corresponding to the monitoring device with the maximum adaptability as the historical characteristic temperature change curve of the corresponding monitoring point; Construct a device-environment adaptation mapping table according to the adaptability of the monitoring devices and historical ambient parameters in a number of historical monitoring logs; Construct a historical heat dissipation evaluation value change curve according to the historical heat dissipation evaluation value of the comprehensive heat dissipation evaluation indicator in each historical monitoring log; Perform curve correlation analysis on the historical characteristic temperature change curve of each monitoring point and the historical heat dissipation evaluation value of the comprehensive heat dissipation evaluation indicator in the same historical monitoring log to obtain the curve correlation degree; Mark the historical monitoring nodes with a curve correlation degree greater than the preset correlation degree threshold and the historical monitoring nodes with a curve correlation degree less than the preset correlation degree threshold in the historical characteristic temperature change curve of each monitoring point, and set the historical duration between the marked historical monitoring nodes as the to-be-determined standard duration; Perform mean processing on the to-be-determined standard durations of the same monitoring point in different historical monitoring logs, and set the to-be-determined standard duration after mean processing as the standard monitoring duration of the corresponding monitoring point.

[0023] In this embodiment, the heat dissipation evaluation indicators include multiple evaluation indicators such as heat dissipation efficiency, heat dissipation uniformity, heat dissipation reliability, and heat dissipation cost. The comprehensive heat dissipation evaluation indicator refers to the calculation based on a number of heat dissipation evaluation indicators and corresponding weight coefficients.

[0024] In this embodiment, the historical heat dissipation evaluation value of the comprehensive heat dissipation evaluation indicator is obtained according to a preset heat dissipation evaluation model trained in advance. The monitoring devices include but are not limited to temperature sensors, resistance measurement devices, fluorescent thermometric agents, drive current or voltage monitoring, etc.

[0025] In this embodiment, adaptability refers to the degree to which the monitoring device is affected by the surrounding environmental factors. The smaller the degree of influence, the greater the corresponding adaptability, that is, the higher the accuracy of the temperature data obtained by the corresponding monitoring device, and vice versa. By constructing a device-environment adaptation mapping table, the selection accuracy and monitoring accuracy of subsequent monitoring devices are improved, laying the foundation for the subsequent determination of the standard monitoring time for each monitoring point and the calculation of the first heat dissipation coefficient.

[0026] In this embodiment, curve correlation analysis refers to evaluating whether two curves have a nonlinear correlation. If so, the curve correlation degree is calculated. The preset correlation degree threshold refers to the minimum curve correlation degree for the existence of a nonlinear correlation. The curve correlation degree is used to screen out the standard time length to be determined, which is convenient for subsequent temperature data monitoring and data processing of the monitoring points.

[0027] In this embodiment, by constructing a device-environment adaptation mapping table and a standard monitoring time for each monitoring point, a foundation is laid for subsequent temperature data monitoring of each monitoring point, the accuracy of selecting the monitoring device for each monitoring point and the accuracy of monitoring the temperature data are improved, a foundation is laid for the subsequent calculation of the first heat dissipation coefficient, the accuracy of heat dissipation monitoring and the accurate evaluation of the heat dissipation effect are improved, and the impact on the luminous performance and life of the organic electroluminescent display panel is reduced.

[0028] In some embodiments of the present application, generating a first heat dissipation coefficient of an organic electroluminescent display panel according to real-time temperature data and temperature change characteristics includes: Acquire real-time ambient environment parameters, compare and analyze the real-time ambient environment parameters with historical ambient environment parameters in the device-environment adaptation mapping table, and obtain consistency between the real-time ambient environment parameters and the historical ambient environment parameters according to the analysis results; The monitoring device corresponding to the historical ambient environment parameter with the greatest consistency is set as the real-time monitoring device of the current organic electroluminescent display panel; Set the inspection time according to the standard monitoring time of each monitoring point, and set the data collection node of the corresponding monitoring point according to the standard monitoring time and the preset time interval; Based on the real-time monitoring device and the data acquisition node, the real-time temperature data of the corresponding monitoring point is obtained, and mapped to the inspection time of the corresponding monitoring point to generate a real-time temperature data change curve; Analyze the real-time temperature data change curve to obtain the real-time temperature change characteristics of the corresponding monitoring point, wherein the real-time temperature change characteristics include the real-time temperature change trend, the real-time temperature change rate and the real-time temperature change value; Perform curve extrapolation based on the real-time temperature data change curve and the real-time temperature change characteristics to obtain the predicted temperature data change curve within the standard monitoring duration of the corresponding monitoring point; Obtain the predicted temperature data and the predicted temperature change characteristics of several data acquisition nodes of the corresponding monitoring point according to the predicted temperature data change curve, and the predicted temperature change characteristics include the predicted temperature change trend, the predicted temperature change rate, and the predicted temperature change magnitude; Construct a reference library of standard temperature data change curves for each monitoring point, and the reference library of standard temperature data change curves includes several standard temperature data change curves; Intercept several standard temperature data change curves according to the inspection duration of each monitoring point to obtain several first standard temperature data change curve segments and the corresponding first standard temperature change characteristics; Compare the real-time temperature data change curve with several first standard temperature data change curve segments to obtain a similarity coefficient; Select the first standard temperature data change curve segment with the largest similarity coefficient, and perform a first difference analysis with the real-time temperature data change curve. Perform a second difference analysis on the corresponding second standard temperature data change curve segment of the selected first standard temperature data change curve segment and the predicted temperature data change curve, and generate a first heat dissipation coefficient according to the first difference analysis result and the second difference analysis result; Among them, the first difference analysis result includes the real-time temperature data difference and the real-time temperature change characteristic difference at each data acquisition node during the inspection duration; The second difference analysis result includes the predicted temperature data difference and the predicted temperature change characteristic difference at each data acquisition node remaining in the corresponding standard monitoring duration.

[0029] In some embodiments of the present application, determine the historical performance influence characteristics corresponding to the historical temperature data according to the historical monitoring log, and construct an influence prediction model, including: Preset the preset performance factors of the organic electroluminescent display panel in advance; Obtain the historical temperature data and the historical performance-related data of each preset performance factor based on the data acquisition nodes in the standard monitoring duration of each monitoring point in the historical monitoring log; Compare the historical performance-related data with the corresponding standard performance-related data to obtain the historical performance evaluation value of each preset performance factor at each data acquisition node; Obtain the historical temperature data difference between adjacent data acquisition nodes in the standard monitoring duration of each monitoring point and the historical performance evaluation value difference of each preset performance factor, and construct a historical temperature data difference sequence and several historical performance evaluation value difference sequences; The historical temperature data difference sequence is respectively compared and analyzed with the historical performance evaluation value difference sequences of each preset performance factor to obtain a number of sequence correlations; The preset performance factors with sequence correlations greater than the preset sequence correlation threshold are set as the historical performance impact factors corresponding to the monitoring points; Each historical performance evaluation value difference in the historical performance evaluation value difference sequence corresponding to the historical performance impact factor is set as the historical performance impact value of the historical temperature data difference of the corresponding data acquisition node of the corresponding monitoring point; The historical performance impact factors and a number of historical performance impact values are set as the historical performance impact characteristics of the corresponding monitoring points; A number of historical temperature data differences in the historical temperature data difference sequence of each monitoring point are used as training input data, and the historical performance impact factors in the historical performance impact characteristics of the corresponding monitoring point and the corresponding number of historical performance evaluation value differences in the historical performance evaluation value difference sequence are used as training output data; Based on the training input data and the training output data, neural network training is performed to obtain an impact prediction model corresponding to the monitoring point.

[0030] In this embodiment, the preset performance factors include luminous efficiency, contrast ratio of the display panel, brightness, brightness uniformity, color performance, response time, lifespan, panel power consumption, etc.

[0031] In this embodiment, the sequence correlation means that the historical temperature data difference in the historical temperature data difference sequence has a correlation or dependence relationship with the corresponding historical performance evaluation value difference in each historical performance evaluation value difference sequence, and the correlation or dependence relationship means that the historical performance evaluation value difference changes with the change of the historical temperature data difference.

[0032] In this embodiment, by determining the performance impact characteristics of each monitoring point, constructing a corresponding impact prediction model, and predicting the performance impact characteristics of the remaining data acquisition nodes of the standard monitoring duration, the performance impact degree of the preset heat dissipation strategy on the display panel in the future period is evaluated, laying a foundation for subsequent calculation of the comprehensive heat dissipation coefficient and optimization of the preset heat dissipation strategy.

[0033] In some embodiments of the present application, generating a second heat dissipation coefficient according to the predicted performance impact characteristics includes: Obtain the real-time performance-related data of the performance impact factor of each monitoring point at each data acquisition node during the inspection duration, and generate the real-time performance evaluation value of the performance impact factor at the corresponding data acquisition node according to the real-time performance-related data; Generate a real-time performance evaluation value change curve for the corresponding performance impact factor based on the real-time performance evaluation values of each performance impact factor at each data collection node during the inspection duration, and obtain the real-time evaluation change characteristics; Among them, the real-time evaluation change characteristics include the real-time evaluation change trend, the real-time evaluation change rate, and the real-time evaluation change magnitude; Generate the predicted temperature data difference for the corresponding remaining data collection nodes based on the predicted temperature data at the adjacent data collection nodes remaining in the standard monitoring duration for each monitoring point, and construct a predicted temperature data difference sequence; Input the predicted temperature data differences in the predicted temperature data difference sequence of each monitoring point into the corresponding impact prediction model in turn to obtain the predicted performance impact characteristics at the remaining data collection nodes; The predicted performance impact characteristics include the predicted performance impact factor and several predicted performance evaluation value differences of the predicted performance impact factor. Construct a predicted performance evaluation value difference sequence based on the several predicted performance evaluation value differences; Generate the predicted performance evaluation value of the corresponding performance impact factor at the remaining data collection nodes in the standard monitoring duration based on the real-time performance evaluation value of the performance impact factor of each monitoring point at the last data collection node during the inspection duration and the predicted performance evaluation value difference sequence; Generate a predicted performance evaluation value change curve for the corresponding performance impact factor based on the predicted performance evaluation values of each performance impact factor at the remaining data collection nodes in the standard monitoring duration, and obtain the predicted evaluation change characteristics. The predicted evaluation change characteristics include the predicted evaluation change trend, the predicted evaluation change rate, and the predicted evaluation change magnitude; Compare the real-time performance evaluation value change curve with several first standard performance evaluation value change curve segments in the standard performance evaluation value change curve reference library of the corresponding performance impact factor of the corresponding monitoring point to obtain a similarity coefficient; Among them, the standard performance evaluation value change curve reference library includes several standard performance evaluation value change curves. Based on the inspection duration, the several standard performance evaluation value change curves are divided into first standard performance evaluation value change curve segments and second standard performance evaluation value change curve segments; Select the first standard performance evaluation value change curve segment with the largest similarity coefficient, and perform a third difference analysis with the real-time performance evaluation value change curve. Perform a fourth difference analysis on the second standard performance evaluation value change curve segment corresponding to the selected first standard performance evaluation value change curve segment and the predicted performance evaluation value change curve. Generate a second heat dissipation coefficient according to the results of the third difference analysis and the fourth difference analysis; Among them, the third difference analysis result includes the difference in real-time performance evaluation values of each performance impact factor at each data collection node in the inspection duration and the difference in real-time evaluation change characteristics; The fourth difference analysis result includes the difference in predicted performance evaluation values of each performance impact factor at each data collection node remaining in the standard monitoring duration and the difference in predicted evaluation change characteristics.

[0034] In this embodiment, the standard performance evaluation value change curve reference library refers to the performance evaluation value change curve of the performance impact factor during the normal heat dissipation process at the corresponding monitoring point.

[0035] In this embodiment, the data collection nodes remaining in the standard monitoring duration refer to all data collection nodes except those within the inspection duration.

[0036] In this embodiment, by calculating the difference in real-time performance evaluation values, the difference in real-time evaluation change characteristics, the difference in predicted performance evaluation values, and the difference in predicted evaluation change characteristics for each monitoring point, a second heat dissipation coefficient is obtained, accurately evaluating and predicting the influence degree of the preset heat dissipation strategy on the performance impact factor of each monitoring point, and further improving the accuracy of evaluating the heat dissipation effect of the preset heat dissipation strategy.

[0037] In some embodiments of the present application, generating a comprehensive heat dissipation coefficient according to the first heat dissipation coefficient and the second heat dissipation coefficient includes: The calculation formula of the first heat dissipation coefficient is: ; Among them, H1 is the first heat dissipation coefficient, a1 is the first heat dissipation conversion coefficient, a2 is the second heat dissipation conversion coefficient, f1 is the weight coefficient of the temperature data difference, f2 is the weight coefficient of the temperature change characteristic difference, n1 is the total number of data collection nodes in the inspection duration, n2 is the number of remaining data collection nodes in the standard monitoring duration corresponding to the monitoring point, is the difference in real-time temperature data at the i1-th data collection node in the inspection duration, is the difference in predicted temperature data at the i2-th data collection node remaining in the standard monitoring duration, is the difference in real-time temperature change characteristics at the i1-th data collection node in the inspection duration, is the difference in predicted temperature change characteristics at the i2-th data collection node remaining in the standard monitoring duration; The calculation formula of the second heat dissipation coefficient is: ; Wherein, H2 is the second heat dissipation coefficient, a3 is the third heat dissipation conversion coefficient, a4 is the fourth heat dissipation conversion coefficient, h1 is the weight coefficient of the performance evaluation value difference, h2 is the weight coefficient of the evaluation change characteristic difference, and m is the total number of performance impact factors at the current monitoring point. is the real-time performance evaluation value difference of the s-th performance impact factor at the i1-th data acquisition node during the inspection duration. is the predicted performance evaluation value difference of the s-th performance impact factor at the i2-th data acquisition node remaining in the standard monitoring duration, and ds is the weight coefficient of the s-th performance impact factor. is the real-time evaluation change characteristic difference of the s-th performance impact factor at the i1-th data acquisition node during the inspection duration. is the predicted evaluation change characteristic difference of the s-th performance impact factor at the i2-th data acquisition node remaining in the standard monitoring duration. The calculation formula of the comprehensive heat dissipation coefficient is: k2; Wherein, H0 is the comprehensive heat dissipation coefficient, k1 is the weight coefficient of the first heat dissipation coefficient, and k2 is the weight coefficient of the second heat dissipation coefficient.

[0038] In this embodiment, c1 + c2 + c3, 、 respectively refer to the real-time temperature change trend difference, real-time temperature change rate difference, and real-time temperature change amount difference at the i1-th data acquisition node during the inspection duration. The calculation formula of is not described in detail.

[0039] In this embodiment, the first heat dissipation conversion coefficient, the second heat dissipation conversion coefficient, the third heat dissipation conversion coefficient, and the fourth heat dissipation conversion coefficient respectively refer to the values obtained by converting the temperature data difference, the temperature change characteristic difference, the performance evaluation value difference, and the evaluation change characteristic difference to the same dimension as the heat dissipation coefficient. When the temperature data difference is smaller and the temperature change characteristic difference is smaller, the corresponding first heat dissipation coefficient is larger. When the performance evaluation value difference of each performance impact factor is smaller and the evaluation change characteristic difference is smaller, the corresponding second heat dissipation coefficient is larger.

[0040] In this embodiment, when the first heat dissipation coefficient and the second heat dissipation coefficient are larger, the comprehensive heat dissipation coefficient is larger, which indicates that the heat dissipation efficiency of the preset heat dissipation strategy is higher and the influence on the performance of the organic electroluminescent display panel is smaller. By calculating the comprehensive heat dissipation coefficient, the temperature change situation of each monitoring point and the influence on the preset performance factor can be accurately evaluated, and the preset heat dissipation strategy can be discovered and adjusted in time to improve the heat dissipation efficiency and ensure the maximization of the performance and lifespan of the organic electroluminescent display panel.

[0041] In some embodiments of the present application, it is determined whether to generate an optimization instruction for the preset heat dissipation strategy. If so, the optimized heat dissipation strategy is determined, including: Pre-set the comprehensive heat dissipation coefficient threshold for each monitoring point; If the comprehensive heat dissipation coefficient of each monitoring point is greater than the corresponding comprehensive heat dissipation coefficient threshold, it is determined not to generate an optimization instruction for the preset heat dissipation strategy; If the comprehensive heat dissipation coefficient of a monitoring point is less than the corresponding comprehensive heat dissipation coefficient threshold, it is determined to generate an optimization instruction for the preset heat dissipation strategy. The optimization instruction includes the to-be-optimized temperature value of the to-be-optimized monitoring point and the preset optimization strategy for the to-be-optimized temperature value; Optimize the preset heat dissipation strategy according to the preset optimization strategy of each to-be-optimized monitoring point to obtain the optimized heat dissipation strategy.

[0042] In this embodiment, the preset optimization strategy is set according to the historical optimization log of the heat dissipation strategy at each monitoring point.

[0043] In this embodiment, by calculating the comprehensive heat dissipation coefficient of each monitoring point, the heat dissipation effect of the preset heat dissipation strategy on each monitoring point is evaluated to avoid uneven heat dissipation. If the heat dissipation effect is poor, the preset heat dissipation strategy is adjusted in time to minimize the impact on the performance and lifespan of the display panel.

[0044] In some embodiments of the present application, a simulation is performed on the optimized heat dissipation strategy, and a simulation application evaluation value of the optimized heat dissipation strategy is generated according to the simulation result, including: Generate a simulation model of the to-be-optimized monitoring point according to the position information of the to-be-optimized monitoring point and the surrounding environment information, in combination with the real-time temperature data at the last data acquisition node of the inspection duration; Perform heat dissipation control on the simulation model according to the optimized heat dissipation strategy to obtain the simulation temperature data at the remaining data acquisition nodes of the standard monitoring duration of each to-be-optimized monitoring point and the simulation heat dissipation duration when the corresponding to-be-optimized temperature value is reached; Set the corresponding compensation coefficient according to the simulation heat dissipation duration; Pre-set the preset temperature data threshold for each remaining data acquisition node of each to-be-optimized monitoring point after the optimized heat dissipation strategy; Compare the simulated temperature data of each monitoring point to be optimized with the corresponding preset temperature data threshold to obtain the difference in simulated temperature data; Generate a simulated application evaluation value for the optimized heat dissipation strategy based on the difference in simulated temperature data of multiple monitoring points to be optimized and the corresponding compensation coefficients; The calculation formula for the simulated application evaluation value is: ; where P is the simulated application evaluation value, is the simulated application conversion coefficient, z is the total number of monitoring points to be optimized, is the difference in simulated temperature data of the v-th monitoring point to be optimized at the i2-th data acquisition node remaining in the standard monitoring duration, is the compensation coefficient of the v-th monitoring point to be optimized, and Uv is the weight coefficient of the v-th monitoring point to be optimized.

[0045] In this embodiment, the compensation coefficient is set according to the duration difference between the simulated heat dissipation duration and the heat dissipation duration threshold. When the duration difference is negative and smaller, the corresponding compensation coefficient is smaller, and vice versa. The value range of the compensation coefficient is (0.85, 1.25).

[0046] In this embodiment, the simulated application conversion coefficient refers to converting the difference in simulated temperature data into a value with the same dimension as the simulated application evaluation value. When the difference in simulated temperature data is smaller and the compensation coefficient is smaller, the corresponding simulated application evaluation value is larger, and vice versa.

[0047] In this embodiment, by calculating the simulated application evaluation value, the application effect of the optimized heat dissipation strategy is accurately evaluated, and the heat dissipation strategy is discovered and adjusted in a timely manner to maximize the heat dissipation efficiency of the organic electroluminescent panel and ensure the maximization of its performance and lifespan.

[0048] In some embodiments of the present application, it is determined whether to re-optimize the optimized heat dissipation strategy according to the simulated application evaluation value, including: Preset a simulated application evaluation value threshold in advance; If the simulated application evaluation value is greater than the simulated application evaluation value threshold, do not re-optimize the optimized heat dissipation strategy and issue an optimization instruction; If the simulated application evaluation value is not greater than the simulated application evaluation value threshold, re-optimize the optimized heat dissipation strategy.

[0049] In some embodiments of the present application, as Figure 2 shown, it further includes a heat dissipation monitoring system for an organic electroluminescent display panel: An acquisition module, configured to preset a plurality of monitoring points and a standard monitoring duration in advance, acquire real-time temperature data and real-time temperature change characteristics of each monitoring point within the standard monitoring duration, and generate a first heat dissipation coefficient according to the real-time temperature data and the real-time temperature change characteristics; A construction module, configured to determine historical performance impact characteristics corresponding to each monitoring point according to historical monitoring logs, construct an impact prediction model, and generate predicted performance impact characteristics according to the real-time temperature data and the impact prediction model; A judgment module, configured to generate a second heat dissipation coefficient according to the predicted performance impact characteristics, generate a comprehensive heat dissipation coefficient according to the first heat dissipation coefficient and the second heat dissipation coefficient, and judge whether to generate an optimization instruction for a preset heat dissipation strategy. If so, determine an optimized heat dissipation strategy; An optimization module, configured to perform simulation on the optimized heat dissipation strategy, generate a simulation application evaluation value of the optimized heat dissipation strategy according to the simulation result, judge whether to further optimize the optimized heat dissipation strategy according to the simulation application evaluation value. If not, issue an optimization instruction.

[0050] The above are only the preferred embodiments of the present application. It should be noted that for those of ordinary skill in the art, without departing from the technical principle of the present application, several improvements and replacements can be made, and these improvements and replacements should also be regarded as the protection scope of the present application.

Claims

1. A heat dissipation monitoring method for an organic electroluminescent display panel, characterized in that, Including: Presetting a number of monitoring points and a standard monitoring duration, obtaining real-time temperature data and real-time temperature change characteristics of each monitoring point within the standard monitoring duration, and generating a first heat dissipation coefficient based on the real-time temperature data and the real-time temperature change characteristics; Determining historical performance impact characteristics corresponding to each monitoring point according to historical monitoring logs, constructing an impact prediction model, and generating predicted performance impact characteristics based on the real-time temperature data and the impact prediction model; Generating a second heat dissipation coefficient based on the predicted performance impact characteristics, generating a comprehensive heat dissipation coefficient based on the first heat dissipation coefficient and the second heat dissipation coefficient, and determining whether to generate an optimization instruction for a preset heat dissipation strategy. If so, determining an optimized heat dissipation strategy; Performing a simulation on the optimized heat dissipation strategy, generating a simulation application evaluation value of the optimized heat dissipation strategy based on the simulation results, and determining whether to further optimize the optimized heat dissipation strategy based on the simulation application evaluation value. If not, issuing an optimization instruction.

2. The heat dissipation monitoring method of the organic electroluminescent display panel according to claim 1, wherein, The standard monitoring duration includes: Presetting a number of heat dissipation evaluation indicators, and determining a comprehensive heat dissipation evaluation indicator according to the number of heat dissipation evaluation indicators; Collecting historical heat dissipation evaluation values of the comprehensive heat dissipation evaluation indicator and historical temperature data at each monitoring point under different monitoring devices based on historical monitoring time nodes in the historical monitoring logs; Constructing a number of historical temperature change curves at the corresponding monitoring points according to the historical temperature data at each monitoring point under different monitoring devices, comparing them with the historical real-time temperature change curves at the corresponding monitoring points, and generating the adaptability of each monitoring device to the corresponding historical ambient parameters based on the comparison results; Setting the historical temperature change curve corresponding to the monitoring device with the maximum adaptability as the historical characteristic temperature change curve of the corresponding monitoring point; Constructing a device-environment adaptation mapping table according to the adaptability of the monitoring devices and historical ambient parameters in a number of historical monitoring logs; Constructing a historical heat dissipation evaluation value change curve according to the historical heat dissipation evaluation values of the comprehensive heat dissipation evaluation indicator in each historical monitoring log; Performing curve correlation analysis on the historical characteristic temperature change curves of each monitoring point and the historical heat dissipation evaluation values of the comprehensive heat dissipation evaluation indicator in the same historical monitoring log to obtain the curve correlation degree; Marking the historical monitoring nodes with a curve correlation degree greater than a preset correlation degree threshold and the historical monitoring nodes with a curve correlation degree less than the preset correlation degree threshold in the historical characteristic temperature change curves of each monitoring point, and setting the historical duration between the marked historical monitoring nodes as the to-be-determined standard duration; Performing an average processing on the to-be-determined standard durations of the same monitoring point in different historical monitoring logs, and setting the to-be-determined standard duration after the average processing as the standard monitoring duration of the corresponding monitoring point.

3. The heat dissipation monitoring method of the organic electroluminescent display panel according to claim 2, wherein Generating a first heat dissipation coefficient of the organic electroluminescent display panel based on the real-time temperature data and the temperature change characteristics, including: Obtaining real-time ambient parameters, comparing and analyzing the real-time ambient parameters with the historical ambient parameters in the device-environment adaptation mapping table, and obtaining the consistency between the real-time ambient parameters and the historical ambient parameters based on the analysis results; Set the monitoring device corresponding to the historical ambient parameters with the greatest consistency as the real-time monitoring device for the current organic electroluminescent display panel; Set the inspection duration according to the standard monitoring duration of each monitoring point, and set the data acquisition nodes corresponding to each monitoring point according to the standard monitoring duration and the preset time interval; Obtain the real-time temperature data of the corresponding monitoring point based on the real-time monitoring device and the data acquisition node, and map it to the inspection duration of the corresponding monitoring point to generate a real-time temperature data change curve; Analyze the real-time temperature data change curve to obtain the real-time temperature change characteristics of the corresponding monitoring point, where the real-time temperature change characteristics include the real-time temperature change trend, the real-time temperature change rate, and the real-time temperature change magnitude; Perform curve extrapolation based on the real-time temperature data change curve and the real-time temperature change characteristics to obtain the predicted temperature data change curve within the standard monitoring duration of the corresponding monitoring point; Obtain the predicted temperature data and the predicted temperature change characteristics of several data acquisition nodes corresponding to the corresponding monitoring point according to the predicted temperature data change curve, where the predicted temperature change characteristics include the predicted temperature change trend, the predicted temperature change rate, and the predicted temperature change magnitude; Construct a reference library of standard temperature data change curves for each monitoring point, where the reference library of standard temperature data change curves includes several standard temperature data change curves; Intercept several standard temperature data change curves according to the inspection duration of each monitoring point to obtain several first standard temperature data change curve segments and the corresponding first standard temperature change characteristics; Compare the real-time temperature data change curve with several first standard temperature data change curve segments to obtain a similarity coefficient; Select the first standard temperature data change curve segment with the largest similarity coefficient, and perform a first difference analysis with the real-time temperature data change curve. Perform a second difference analysis on the second standard temperature data change curve segment corresponding to the selected first standard temperature data change curve segment and the predicted temperature data change curve, and generate a first heat dissipation coefficient according to the first difference analysis result and the second difference analysis result; Among them, the first difference analysis result includes the real-time temperature data difference and the real-time temperature change characteristic difference at each data acquisition node in the inspection duration; The second difference analysis result includes the predicted temperature data difference and the predicted temperature change characteristic difference at each data acquisition node remaining in the corresponding standard monitoring duration.

4. The heat dissipation monitoring method of the organic electroluminescent display panel according to claim 3, characterized in that Determine the historical performance impact characteristics corresponding to the historical temperature data according to the historical monitoring log, and construct an impact prediction model, including: Preset the preset performance factors of the organic electroluminescent display panel in advance; Obtain the historical temperature data and the historical performance-related data of each preset performance factor based on the data acquisition nodes with the standard monitoring duration of each monitoring point in the historical monitoring log; Compare the historical performance-related data with the corresponding standard performance-related data to obtain the historical performance evaluation value of each preset performance factor at each data acquisition node; Obtain the historical temperature data differences of adjacent data acquisition nodes with the standard monitoring duration for each monitoring point and the historical performance evaluation value differences of each preset performance factor, and construct a historical temperature data difference sequence and several historical performance evaluation value difference sequences; Compare and analyze the historical temperature data difference sequence with the historical performance evaluation value difference sequences of each preset performance factor respectively to obtain several sequence correlations; Set the preset performance factors with sequence correlations greater than the preset sequence correlation threshold as the historical performance impact factors for the corresponding monitoring points; Set each historical performance evaluation value difference in the historical performance evaluation value difference sequence corresponding to the historical performance impact factor as the historical performance impact magnitude of the historical temperature data difference of the corresponding data acquisition node of the corresponding monitoring point; Set the historical performance impact factors and several historical performance impact magnitudes as the historical performance impact characteristics of the corresponding monitoring points; Take several historical temperature data differences in the historical temperature data difference sequence of each monitoring point as training input data, and take the historical performance impact factors in the historical performance impact characteristics of the corresponding monitoring point and the corresponding several historical performance evaluation value differences in the historical performance evaluation value difference sequence as training output data; Perform neural network training based on the training input data and the training output data to obtain an impact prediction model for the corresponding monitoring point.

5. The heat dissipation monitoring method of the organic electroluminescent display panel according to claim 4, characterized in that Generate a second heat dissipation coefficient according to the predicted performance impact characteristics, including: Obtain the real-time performance-related data of each performance impact factor at each data acquisition node during the inspection duration, and generate the real-time performance evaluation value of the performance impact factor at the corresponding data acquisition node according to the real-time performance-related data; Generate a real-time performance evaluation value change curve of the corresponding performance impact factor according to the real-time performance evaluation values of each performance impact factor at each data acquisition node during the inspection duration, and obtain the real-time evaluation change characteristics; Among them, the real-time evaluation change characteristics include the real-time evaluation change trend, the real-time evaluation change rate, and the real-time evaluation change magnitude; Generate the predicted temperature data differences at the corresponding remaining data acquisition nodes according to the predicted temperature data at the adjacent data acquisition nodes remaining in the standard monitoring duration for each monitoring point, and construct a predicted temperature data difference sequence; Sequentially input the predicted temperature data differences in the predicted temperature data difference sequence of each monitoring point into the corresponding impact prediction model to obtain the predicted performance impact characteristics at the remaining data acquisition nodes; The predicted performance impact characteristics include the predicted performance impact factors and several predicted performance evaluation value differences of the predicted performance impact factors, and construct a predicted performance evaluation value difference sequence according to the several predicted performance evaluation value differences; Generate the predicted performance evaluation value of the corresponding performance impact factor at the remaining data acquisition nodes in the standard monitoring duration according to the real-time performance evaluation value of the performance impact factor at the last data acquisition node during the inspection duration of each monitoring point and the predicted performance evaluation value difference sequence; Generate a predicted performance evaluation value change curve for each performance impact factor based on the predicted performance evaluation values at the remaining data collection nodes during the standard monitoring duration, and obtain the predicted evaluation change characteristics, where the predicted evaluation change characteristics include the predicted evaluation change trend, the predicted evaluation change rate, and the predicted evaluation change magnitude; Compare the real-time performance evaluation value change curve with several first standard performance evaluation value change curve segments in the standard performance evaluation value change curve reference library of the corresponding performance impact factor at the corresponding monitoring point to obtain a similarity coefficient; Among them, the standard performance evaluation value change curve reference library includes several standard performance evaluation value change curves, and based on the inspection duration, the several standard performance evaluation value change curves are divided into a first standard performance evaluation value change curve segment and a second standard performance evaluation value change curve segment; Select the first standard performance evaluation value change curve segment with the largest similarity coefficient, and perform a third difference analysis with the real-time performance evaluation value change curve. Perform a fourth difference analysis on the corresponding second standard performance evaluation value change curve segment of the selected first standard performance evaluation value change curve segment and the predicted performance evaluation value change curve, and generate a second heat dissipation coefficient according to the results of the third difference analysis and the fourth difference analysis; Among them, the results of the third difference analysis include the real-time performance evaluation value difference of each performance impact factor at each data collection node during the inspection duration and the real-time evaluation change characteristic difference; The results of the fourth difference analysis include the predicted performance evaluation value difference of each performance impact factor at each data collection node remaining in the standard monitoring duration and the predicted evaluation change characteristic difference.

6. The heat dissipation monitoring method of the organic electroluminescent display panel according to claim 5, characterized in that Generate a comprehensive heat dissipation coefficient based on the first heat dissipation coefficient and the second heat dissipation coefficient, including: The calculation formula for the first heat dissipation coefficient is: ； Wherein, H1 is the first heat dissipation coefficient, a1 is the first heat dissipation conversion coefficient, a2 is the second heat dissipation conversion coefficient, f1 is the weight coefficient of the temperature data difference, f2 is the weight coefficient of the temperature change characteristic difference, n1 is the total number of data acquisition nodes in the inspection duration, and n2 is the total number of remaining data acquisition nodes in the standard monitoring duration corresponding to the monitoring point. is the real-time temperature data difference at the i1-th data acquisition node in the inspection duration. is the predicted temperature data difference at the i2-th data acquisition node remaining in the standard monitoring duration. is the real-time temperature change characteristic difference at the i1-th data acquisition node in the inspection duration. is the predicted temperature change characteristic difference at the i2-th data acquisition node remaining in the standard monitoring duration. The calculation formula for the second heat dissipation coefficient is: ； Among them, H2 is the second heat dissipation coefficient, a3 is the third heat dissipation conversion coefficient, a4 is the fourth heat dissipation conversion coefficient, h1 is the weight coefficient of the difference in performance evaluation values, h2 is the weight coefficient of the difference in evaluation change characteristics, and m is the total number of performance impact factors at the current monitoring point. is the real-time performance evaluation value difference of the s-th performance impact factor at the i1-th data acquisition node during the inspection duration. is the predicted performance evaluation value difference of the s-th performance impact factor at the i2-th data acquisition node remaining in the standard monitoring duration, and ds is the weight coefficient of the s-th performance impact factor. is the real-time evaluation change characteristic difference of the s-th performance impact factor at the i1-th data acquisition node during the inspection duration. is the predicted evaluation change characteristic difference of the s-th performance impact factor at the i2-th data acquisition node remaining in the standard monitoring duration. The calculation formula for the comprehensive heat dissipation coefficient is: k2； Among them, H0 is the comprehensive heat dissipation coefficient, k1 is the weight coefficient of the first heat dissipation coefficient, and k2 is the weight coefficient of the second heat dissipation coefficient.

7. The heat dissipation monitoring method of the organic electroluminescent display panel according to claim 6, characterized in that, Judge whether to generate an optimization instruction for the preset heat dissipation strategy. If so, determine the optimized heat dissipation strategy, including: Preset a comprehensive heat dissipation coefficient threshold for each monitoring point in advance; If the comprehensive heat dissipation coefficient of each monitoring point is greater than the corresponding comprehensive heat dissipation coefficient threshold, then judge not to generate an optimization instruction for the preset heat dissipation strategy; If there is a monitoring point whose comprehensive heat dissipation coefficient is less than the corresponding comprehensive heat dissipation coefficient threshold, then judge to generate an optimization instruction for the preset heat dissipation strategy. The optimization instruction includes the temperature value to be optimized at the monitoring point to be optimized and the preset optimization strategy for the temperature value to be optimized; Optimize the preset heat dissipation strategy according to the preset optimization strategy of each monitoring point to be optimized to obtain an optimized heat dissipation strategy.

8. The heat dissipation monitoring method of the organic electroluminescent display panel according to claim 7, characterized in that, Perform a simulation for the optimized heat dissipation strategy, and generate a simulation application evaluation value for the optimized heat dissipation strategy according to the simulation results, including: Generate a simulation model for the monitoring point to be optimized according to the position information and surrounding environment information of the monitoring point to be optimized, combined with the real-time temperature data at the last data collection node during the inspection duration; The heat dissipation control of the simulation model is carried out according to the optimized heat dissipation strategy, and the simulation temperature data at the remaining data acquisition nodes of the standard monitoring duration of each monitoring point to be optimized and the simulation heat dissipation duration when the corresponding temperature value to be optimized is reached are obtained; Set the corresponding compensation coefficient according to the simulation heat dissipation duration; Preset the preset temperature data threshold at each remaining data acquisition node of each monitoring point to be optimized after the optimized heat dissipation strategy; Compare the simulation temperature data of each monitoring point to be optimized with the corresponding preset temperature data threshold to obtain the simulation temperature data difference; Generate the simulation application evaluation value of the optimized heat dissipation strategy according to the simulation temperature data differences of multiple monitoring points to be optimized and the corresponding compensation coefficients; The calculation formula of the simulation application evaluation value is: ； Among them, P is the evaluation value of the simulation application, is the conversion coefficient of the simulation application, z is the total number of monitoring points to be optimized, is the difference in simulation temperature data at the data acquisition node for the remaining i2 of the standard monitoring duration at the v-th monitoring point to be optimized, is the compensation coefficient of the v-th monitoring point to be optimized, and Uv is the weight coefficient of the v-th monitoring point to be optimized.

9. The heat dissipation monitoring method of the organic electroluminescent display panel according to claim 8, wherein Judge whether to optimize the optimized heat dissipation strategy again according to the simulation application evaluation value, including: Preset the simulation application evaluation value threshold; If the simulation application evaluation value is greater than the simulation application evaluation value threshold, do not optimize the optimized heat dissipation strategy again, and issue an optimization instruction; If the simulation application evaluation value is not greater than the simulation application evaluation value threshold, optimize the optimized heat dissipation strategy again.

10. A heat dissipation monitoring system for an organic electroluminescent display panel, characterized in that, Including: An acquisition module, configured to preset a plurality of monitoring points and a standard monitoring duration, acquire the real-time temperature data and the real-time temperature change characteristics of each monitoring point within the standard monitoring duration, and generate a first heat dissipation coefficient according to the real-time temperature data and the real-time temperature change characteristics; A construction module, configured to determine the historical performance influence characteristics corresponding to each monitoring point according to the historical monitoring log, construct an influence prediction model, and generate predicted performance influence characteristics according to the real-time temperature data and the influence prediction model; A judgment module, configured to generate a second heat dissipation coefficient according to the predicted performance influence characteristics, generate a comprehensive heat dissipation coefficient according to the first heat dissipation coefficient and the second heat dissipation coefficient, and judge whether to generate an optimization instruction for the preset heat dissipation strategy. If so, determine the optimized heat dissipation strategy; An optimization module, configured to perform simulation on the optimized heat dissipation strategy, generate the simulation application evaluation value of the optimized heat dissipation strategy according to the simulation result, judge whether to optimize the optimized heat dissipation strategy again according to the simulation application evaluation value, and if not, issue an optimization instruction.

Images