Self-adaptive control system and method for LED driving power supply

Abstract

The invention provides a self-adaptive control system and method of an LED driving power supply, relates to the field of intelligent control, and adopts a data analysis technology based on artificial intelligence to carry out time sequence correlation characteristic analysis of a driving chip real-time temperature and a port voltage real-time offset value. Therefore, the reference current value is intelligently obtained based on the local and global interaction response relation between the real-time temperature time sequence correlation characteristic and the port voltage real-time offset value time sequence correlation characteristic. Therefore, the working state and the environment change of the chip can be more accurately captured, so that the reference current is adjusted in time to adjust the output voltage, the accurate adjustment of the output voltage of the power supply is realized, and the intelligent degree of the control of the LED driving power supply is improved.

Description

Technical Field

[0001] The present application relates to the field of intelligent control, and more specifically, to an adaptive control system and method for an LED driving power supply. Background Art

[0002] LED (light emitting diode) lighting has become an important part of modern lighting technology due to its advantages such as high efficiency, energy saving, long life and environmental protection. The normal operation of LED requires a stable power supply, and the LED driver power supply is the key component to provide this stable power supply. A good LED driver power supply can not only ensure the normal operation of LED lamps, but also extend the service life of lamps and reduce maintenance costs.

[0003] Chinese patent CN116403517A proposes a power adaptive control method for LED display system, which determines the voltage level by monitoring the port voltage of LED driver chip and comparing it with the preset standard value. Once the voltage deviation is found, the corresponding reference current is generated and fed back to the power management system through the FB port, thereby adjusting the output voltage to ensure that the port voltage of the LED driver chip is maintained at an ideal level.

[0004] In the above patent, the magnitude and direction of the reference current are determined based on the current value of the current counter and are implemented through a reference current selection circuit. However, the method of relying on the value of the current counter to adjust based on the relative high and low conditions of the port voltage may cause the system to react slowly when faced with rapidly changing environmental conditions or sudden changes in system status. For example, in the case of a sudden change in drive temperature or power supply fluctuations, simple counter logic may not be able to quickly identify and make appropriate adjustments, thereby affecting the performance and life of the LED driver chip. In addition, this method based on fixed logic ignores the nonlinear relationship and complex interactions between the voltage and temperature of the chip, and lacks the adaptive and generalization capabilities to cope with control in different environments, resulting in the inability to make optimal adjustments in some cases.

[0005] Therefore, an optimized adaptive control scheme for LED driving power supply is needed. Summary of the invention

[0006] In order to solve the above technical problems, the present application is proposed. The embodiment of the present application provides an adaptive control system and method for an LED driving power supply, which adopts artificial intelligence-based data analysis technology to analyze the timing correlation characteristics of the real-time temperature of the driving chip and the real-time offset value of the port voltage, so as to intelligently obtain the reference current value based on the local-global interactive response relationship between the real-time temperature timing correlation characteristics and the port voltage real-time offset value timing correlation characteristics. In this way, the working state and environmental changes of the chip can be captured more accurately, so as to adjust the reference current in time to adjust the output voltage, thereby realizing precise adjustment of the power supply output voltage, which is conducive to improving the intelligence level of the LED driving power supply control.

[0007] According to one aspect of the present application, an adaptive control system for an LED driving power supply is provided, comprising:

[0008] A port voltage information acquisition module, used to acquire the port voltage information of the LED driver chip, wherein the port voltage information is a time queue of the port voltage;

[0009] An adjustment signal generating module, used for generating a reference current value based on a preset port voltage standard value and the port voltage information;

[0010] A port voltage information adjustment module, used to transmit the reference current value to the FB port of the power management system, so as to adjust the output voltage of the power management system and adjust the port voltage of the LED driver chip;

[0011] Wherein, the adjustment signal generating module includes:

[0012] A temperature real-time data acquisition unit, used to obtain a time queue of the real-time temperature of the LED driver chip;

[0013] A port voltage real-time offset value calculation unit, used for calculating a time queue of a port voltage real-time offset value based on the preset port voltage standard value and the port voltage time queue;

[0014] A temperature-port voltage timing association unit, used for inputting the time queue of the real-time temperature and the time queue of the real-time offset value of the port voltage into a sequence encoder respectively to obtain a temperature timing association feature vector and a port voltage offset timing association feature vector;

[0015] A temperature-port voltage interactive response unit, used for inputting the temperature timing-related characteristic vector and the port voltage offset timing-related characteristic vector into a characteristic local-global interactive response module based on characteristic decoupling to obtain a temperature drift-voltage offset local-global interactive response matrix;

[0016] The reference current value generating unit is used to obtain the reference current value based on the temperature drift-voltage offset local-global interaction response matrix.

[0017] According to another aspect of the present application, there is provided an adaptive control method for an LED driving power supply, comprising:

[0018] Acquire port voltage information of the LED driver chip, where the port voltage information is a time queue of the port voltage;

[0019] Generate a reference current value based on a preset port voltage standard value and the port voltage information;

[0020] Transmitting the reference current value to the FB port of the power management system to adjust the output voltage of the power management system and adjust the port voltage of the LED driver chip;

[0021] The step of generating a reference current value based on a preset port voltage standard value and the port voltage information includes:

[0022] A time queue for obtaining the real-time temperature of the LED driver chip;

[0023] Calculate the time queue of the port voltage real-time offset value based on the preset port voltage standard value and the time queue of the port voltage;

[0024] Inputting the time queue of the real-time temperature and the time queue of the real-time offset value of the port voltage into a sequence encoder respectively to obtain a temperature timing correlation feature vector and a port voltage offset timing correlation feature vector;

[0025] Inputting the temperature timing correlation feature vector and the port voltage offset timing correlation feature vector into a feature local-global interactive response module based on feature decoupling to obtain a temperature drift-voltage offset local-global interactive response matrix;

[0026] The reference current value is obtained based on the temperature drift-voltage offset local-global interaction response matrix.

[0027] Compared with the prior art, the adaptive control system and method of the LED driving power supply provided by the present application adopts data analysis technology based on artificial intelligence to analyze the timing correlation characteristics of the real-time temperature of the driving chip and the real-time offset value of the port voltage, so as to intelligently obtain the reference current value based on the local and global interactive response relationship between the real-time temperature timing correlation characteristics and the port voltage real-time offset value timing correlation characteristics. In this way, the working state and environmental changes of the chip can be captured more accurately, so as to adjust the reference current in time to adjust the output voltage, realize the precise adjustment of the power supply output voltage, and help to improve the intelligence level of the LED driving power supply control. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. In the drawings:

[0029] Figure 1 4 is a system block diagram of an adaptive control system of an LED driving power supply according to an embodiment of the present application.

[0030] Figure 2 The block diagram is a regulation signal generation module in the adaptive control system of the LED driving power supply according to the embodiment of the present application.

[0031] Figure 3 Schematic diagram of data flow of a regulating signal generating module in an adaptive control system of an LED driving power supply according to an embodiment of the present application.

[0032] Figure 4 4 is a block diagram of a temperature-port voltage interactive response unit in an adaptive control system of an LED driving power supply according to an embodiment of the present application.

[0033] Figure 5 The block diagram is a subunit for calculating the temperature-port voltage offset characteristic interaction energy factor in the adaptive control system of the LED driving power supply according to the embodiment of the present application.

[0034] Figure 6 Flow chart of an adaptive control method of an LED driving power supply according to an embodiment of the present application. DETAILED DESCRIPTION

[0035] Below, the exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application, and it should be understood that the present application is not limited to the exemplary embodiments described here.

[0036] LED lighting has become an important part of modern lighting technology due to its high energy efficiency, long life and environmental protection characteristics. As the key to its stable power supply, LED driver power supply is crucial to ensure the normal operation and extend the service life of LED lamps. Chinese patent CN116403517A proposes an adaptive control method for LED display system power supply, which adjusts the output voltage by monitoring the port voltage of the LED driver chip and comparing it with the preset value to ensure voltage stability. However, this method depends on the value of the current counter, which easily leads to insufficient response when the environment changes rapidly or the system state suddenly changes, affecting the performance and life of the LED driver chip. In addition, this method fails to fully consider the nonlinear relationship between voltage and temperature, lacks adaptive and generalization capabilities, and may not be able to achieve optimal regulation under specific conditions.

[0037] Based on this, the present application proposes an optimized adaptive control system for LED driving power supply. Figure 1 FIG. 1 is a system block diagram of an adaptive control system of an LED driving power supply according to an embodiment of the present application. Figure 1 As shown, the adaptive control system 100 of the LED driving power supply according to the embodiment of the present application includes: a port voltage information acquisition module 110, used to obtain the port voltage information of the LED driving chip, and the port voltage information is a time queue of the port voltage; an adjustment signal generation module 120, used to generate a reference current value based on a preset port voltage standard value and the port voltage information; a port voltage information adjustment module 130, used to transmit the reference current value to the FB port of the power management system, so as to adjust the output voltage of the power management system and adjust the port voltage of the LED driving chip.

[0038] It should be understood that in the adaptive control system provided in the present application, the port voltage time series information of the LED driver chip is first obtained in the port voltage information acquisition module. By continuously acquiring the port voltage data, the system can monitor the working state of the LED driver chip in real time, and the acquired port voltage data is the basis for subsequent analysis and adjustment. Then, in the adjustment signal generation module, a reference current value is generated based on the preset port voltage standard value and the port voltage information. This module is the core of the adaptive control system. It needs to generate an adjustment signal according to real-time data and preset standards to ensure that the port voltage of the LED driver chip remains in the optimal state. Finally, the generated reference current value is transmitted to the FB port of the power management system in the port voltage information adjustment module. Through feedback adjustment, the output voltage of the power management system can be adjusted, thereby keeping the port voltage of the LED driver chip at an ideal level. Specifically, when the acquired port voltage is lower than the port voltage standard value, the feedback reference current is controlled to flow out of the FB port of the power management system to increase the output voltage of the power management system; when the acquired port voltages are not lower than the port voltage standard value and are higher than the port voltage standard value, the feedback reference current is controlled to flow into the FB port of the power management system to reduce the output voltage of the power management system. The port voltage information adjustment module is the executive part of the adaptive control system. It directly acts on the power management system to achieve real-time adjustment of the output voltage of the power management system, ensuring that the system can quickly adapt to environmental changes and power fluctuations.

[0039] Accordingly, in the adjustment signal generation module, the technical concept of the present application is to analyze the timing correlation characteristics of the real-time temperature of the driver chip and the real-time offset value of the port voltage through data analysis and processing technology based on artificial intelligence, so as to intelligently obtain the reference current value based on the local and global interactive response relationship between the real-time temperature timing correlation characteristics and the port voltage real-time offset value timing correlation characteristics. In this way, the working state and environmental changes of the chip can be captured more accurately, so as to adjust the reference current in time to adjust the output voltage, avoid the problems caused by the traditional current counter control method, and fully understand the interaction between temperature and voltage, so as to achieve accurate adjustment of the power supply output voltage, so as to improve the adaptability and generalization ability of the adaptive control system, and improve the intelligence of the LED drive power supply control.

[0040] Figure 2 The block diagram is a regulation signal generation module in the adaptive control system of the LED driving power supply according to the embodiment of the present application. Figure 3 FIG. 1 is a schematic diagram of data flow of a regulating signal generating module in an adaptive control system of an LED driving power supply according to an embodiment of the present application. Figure 2 and Figure 3As shown, the adjustment signal generating module 120 includes: a temperature real-time data acquisition unit 121, which is used to obtain the time queue of the real-time temperature of the LED driver chip; a port voltage real-time offset value calculation unit 122, which is used to calculate the time queue of the port voltage real-time offset value based on the preset port voltage standard value and the time queue of the port voltage; a temperature port voltage timing association unit 123, which is used to input the time queue of the real-time temperature and the time queue of the port voltage real-time offset value into a sequence encoder respectively to obtain a temperature timing association feature vector and a port voltage offset timing association feature vector; a temperature-port voltage interactive response unit 124, which is used to input the temperature timing association feature vector and the port voltage offset timing association feature vector into a feature local-global interactive response module based on feature decoupling to obtain a temperature drift-voltage offset local-global interactive response matrix; a reference current value generating unit 125, which is used to obtain the reference current value based on the temperature drift-voltage offset local-global interactive response matrix.

[0041] In the embodiment of the present application, the temperature real-time data acquisition unit 121 is used to obtain the time queue of the real-time temperature of the LED driver chip. It should be understood that due to the thermal drift phenomenon of the LED driver chip, the voltage of the LED driver chip will change with the change of temperature. By introducing real-time temperature data, the system can more accurately understand the actual working conditions of the LED driver chip, and comprehensively consider the control strategy of environmental factors such as temperature, so as to achieve more efficient and stable adaptive control.

[0042] In the embodiment of the present application, the port voltage real-time offset value calculation unit 122 is used to calculate the time queue of the port voltage real-time offset value based on the preset port voltage standard value and the time queue of the port voltage. It should be understood that in order to reflect the gap between the actual port voltage of the LED driver chip and the preset standard value, so as to more accurately generate the reference current value, it is necessary to calculate the time queue of the port voltage real-time offset value based on the preset port voltage standard value and the time queue of the port voltage in the technical solution of the present application.

[0043] In an embodiment of the present application, the temperature-port voltage timing association unit 123 is used to input the time queue of the real-time temperature and the time queue of the port voltage real-time offset value into a sequence encoder respectively to obtain a temperature timing association feature vector and a port voltage offset timing association feature vector. Specifically, in an embodiment of the present application, the temperature-port voltage timing association unit is used to: input the time queue of the real-time temperature and the time queue of the port voltage real-time offset value into a sequence encoder based on a backward LSTM model respectively to obtain the temperature timing association feature vector and the port voltage offset timing association feature vector. It should be understood that there are different correlation dependencies between the port voltage and temperature at different times in the time queue of the port voltage real-time offset value and the time queue of the real-time temperature, and the information at the current time point may be affected by future data. The backward LSTM can capture the complex dependencies in the time series data through the back-propagation mechanism, and by considering the impact of future time points on the current time point, more accurate timing association features can be extracted. Based on this, in the technical solution of the present application, the time queue of the real-time temperature and the time queue of the real-time offset value of the port voltage are respectively input into the sequence encoder based on the backward LSTM model to capture and characterize the dependency relationship between the port voltage and temperature in different time spans, and obtain the temperature time series correlation feature vector and the port voltage offset time series correlation feature vector. This is very effective for predicting future trends or identifying patterns in time series.

[0044] In the embodiment of the present application, the temperature-port voltage interactive response unit 124 is used to input the temperature timing correlation feature vector and the port voltage offset timing correlation feature vector into the feature local-global interactive response module based on feature decoupling to obtain the temperature drift-voltage offset local-global interactive response matrix. Accordingly, considering that the temperature timing correlation feature vector captures the trend and pattern of temperature changes over time, it provides a detailed view of temperature changes for the system; the port voltage offset timing correlation feature vector represents the change of the port voltage of the LED driver chip over time. And there is a mutual correlation relationship between the two in the local timing and global range, that is, the increase in temperature may cause the resistance of the semiconductor device to change, thereby affecting the voltage in the circuit; the change in port voltage will affect the power consumption of the chip, and the increase in power consumption will cause more heat to be generated, thereby affecting the temperature. In order to deeply understand and carefully analyze the correlation response relationship between the two, in the technical solution of the present application, the temperature timing correlation feature vector and the port voltage offset timing correlation feature vector are locally-globally interactively responded to by the feature local-global interactive response module based on feature decoupling to obtain the temperature drift-voltage offset local-global interactive response matrix. It is worth mentioning that the feature local-global interactive response module based on feature decoupling is used to deeply mine and integrate information in feature vectors through feature decoupling, multi-scale feature interaction and interactive metric learning. This module can finely analyze feature data, extract key information, and promote effective fusion between different features to achieve a comprehensive understanding and utilization of data, thereby more accurately capturing and responding to the complex dynamics in the LED driver, thereby optimizing the control strategy and improving system performance.

[0045] In detail, first, the port voltage offset timing correlation feature vector is feature decoupled to decompose the port voltage timing feature into multiple independent sub-features containing local time segments to obtain a sequence of port voltage offset local timing correlation feature vectors, so as to better understand and analyze the timing feature information of each local time period. Next, the temperature timing correlation feature vector is nonlinearly transformed to capture these more complex relationships and patterns to obtain the temperature timing correlation feature vector after nonlinear transformation. Furthermore, the correlation matrix between each port voltage offset local timing correlation feature vector and the temperature timing correlation feature vector after nonlinear transformation is calculated to obtain a sequence of temperature-port voltage offset interactive correlation matrices. That is, the correlation matrix can quantify and understand the relationship between temperature and port voltage features, so as to better capture the dynamic changes and interactions in the system, so as to more accurately identify and analyze the complex relationship between various variables in the system. After that, the characteristic interaction energy factor of each correlation matrix is ​​calculated. In particular, the characteristic interaction energy factor is calculated based on the mean, variance and kurtosis value of the correlation interaction matrix. In this way, the interaction strength between features can be more deeply understood, and the degree of such interaction can be quantified through these statistics, so as to highlight the most significant interaction features. Then, the characteristic interaction energy factor of each interaction matrix is ​​normalized based on the Sigmoid function to map the values ​​in any range to the interval [0,1], and converted into the form of weights to ensure that the model can more effectively focus on the importance of different feature interactions, so that the model can consider the interaction between each feature in a more balanced way. Finally, the sequence of normalized factors is used as the weight sequence to weight and calculate the sequence of the interaction correlation matrix to obtain the temperature drift-voltage offset local-global interaction response matrix. In this way, it can be ensured that when analyzing and processing temperature drift (temperature drift) and voltage offset, the energy factor of each feature interaction can be reasonably considered, and the contribution to the overall calculation result can be appropriately adjusted.

[0046] Specifically, Figure 4 FIG. 1 is a block diagram of a temperature-port voltage interactive response unit in an adaptive control system of an LED driving power supply according to an embodiment of the present application. Figure 4As shown, the temperature-port voltage interactive response unit 124 includes: a port voltage offset timing correlation feature decoupling subunit 1241, which is used to perform feature decoupling on the port voltage offset timing correlation feature vector to obtain a sequence of port voltage offset local timing correlation feature vectors; a temperature timing nonlinear transformation subunit 1242, which is used to perform nonlinear transformation on the temperature timing correlation feature vector to obtain a temperature timing correlation feature vector after nonlinear transformation; a temperature-port voltage local timing correlation subunit 1243, which is used to calculate the correlation matrix between the temperature timing correlation feature vector after nonlinear transformation and each port voltage offset local timing correlation feature vector in the sequence of the port voltage offset local timing correlation feature vector to obtain a sequence of temperature-port voltage offset interactive correlation matrices; a temperature-port voltage offset feature interaction energy factor calculation subunit 1244. 244, used to calculate the characteristic interaction energy factor of each temperature-port voltage offset interaction correlation matrix in the sequence of the temperature-port voltage offset interaction correlation matrix to obtain a sequence of temperature-port voltage offset characteristic interaction energy factors; a temperature-port voltage offset characteristic interaction energy factor normalization processing subunit 1245, used to input the sequence of the temperature-port voltage offset characteristic interaction energy factors into a Sigmoid function to obtain a sequence of normalized temperature-port voltage offset characteristic interaction energy factors; a temperature drift-voltage offset local-global interaction response matrix generation subunit 1246, used to use the sequence of normalized temperature-port voltage offset characteristic interaction energy factors as a sequence of weights, calculate the position-weighted sum of the sequence of the temperature-port voltage offset interaction correlation matrix to obtain the temperature drift-voltage offset local-global interaction response matrix.

[0047] More specifically, in an embodiment of the present application, the temperature time series nonlinear transformation subunit is used to: after multiplying the temperature time series associated feature vector with the temperature transformation matrix, add the obtained temperature time series associated weight vector and temperature bias vector by position to obtain the temperature time series associated feature vector after the nonlinear transformation.

[0048] More specifically, Figure 5 FIG. 1 is a block diagram of a temperature-port voltage offset characteristic interaction energy factor calculation subunit in an adaptive control system of an LED driving power supply according to an embodiment of the present application. Figure 5As shown, the temperature-port voltage offset characteristic interaction energy factor calculation subunit 1244 includes: a temperature-port voltage offset interactive correlation kurtosis value calculation secondary subunit 12441, which is used to calculate the kurtosis value of each temperature-port voltage offset interactive correlation matrix in the sequence of the temperature-port voltage offset interactive correlation matrix to obtain a sequence of temperature-port voltage offset interactive correlation kurtosis values; a temperature-port voltage offset interactive energy factor calculation secondary subunit 12442, which is used to calculate the characteristic interaction energy factor of each temperature-port voltage offset interactive correlation matrix based on each temperature-port voltage offset interactive correlation kurtosis value in the sequence of the temperature-port voltage offset interactive correlation kurtosis value to obtain the sequence of the temperature-port voltage offset characteristic interaction energy factors.

[0049] More specifically, in an embodiment of the present application, the temperature-port voltage offset interactive correlation kurtosis value calculation secondary subunit is used to: respectively calculate the mean and variance of the temperature-port voltage offset interactive correlation matrix to obtain the temperature-port voltage offset interactive correlation mean and the temperature-port voltage offset interactive correlation variance; calculate the positional difference between the temperature-port voltage offset interactive correlation matrix and the temperature-port voltage offset interactive correlation mean to obtain a temperature-port voltage offset interactive correlation difference matrix; calculate the fourth power of each eigenvalue in the temperature-port voltage offset interactive correlation difference matrix to obtain a temperature-port voltage offset interactive correlation modulation difference matrix; calculate the expected value of the temperature-port voltage offset interactive correlation modulation difference matrix to obtain a temperature-port voltage offset interactive correlation expected value; divide the temperature-port voltage offset interactive correlation expected value by the square of the temperature-port voltage offset interactive correlation variance to obtain the temperature-port voltage offset interactive correlation kurtosis value.

[0050] More specifically, in an embodiment of the present application, the temperature-port voltage offset interaction energy factor calculation secondary subunit is used to: calculate the sum of the temperature-port voltage offset interaction correlation variance and the hyperparameter to obtain a temperature-port voltage offset interaction correlation first energy factor; calculate the square of the difference between the temperature-port voltage offset interaction correlation kurtosis value and the temperature-port voltage offset interaction correlation mean to obtain a temperature-port voltage offset interaction correlation difference value; add the value obtained by multiplying the temperature-port voltage offset interaction correlation variance by a constant two and the value obtained by multiplying the hyperparameter by a constant two to the temperature-port voltage offset interaction correlation difference value to obtain a temperature-port voltage offset interaction correlation second energy factor; divide the temperature-port voltage offset interaction correlation first energy factor by the temperature-port voltage offset interaction correlation second energy factor to obtain the temperature-port voltage offset characteristic interaction energy factor corresponding to the temperature-port voltage offset interaction correlation matrix.

[0051] In the embodiment of the present application, specifically, the temperature-port voltage interactive response unit is used to: input the temperature timing correlation feature vector and the port voltage offset timing correlation feature vector into a feature local-global interactive response module based on feature decoupling, and process them with the following local-global interactive response formula to obtain the temperature drift-voltage offset local-global interactive response matrix; wherein the local-global interactive response formula is:

[0052] Decouple(f2)={f 21 , f 22 , ..., f 2i , ..., f 2n}

[0053] f 1t =Wf1+b

[0054]

[0055] E norm，12i =sigmoid(E 12i )

[0056] M=Σ i M 12i ⊙E norm，12i

[0057] Wherein, f2 is the port voltage offset timing correlation characteristic vector, Decouple(·) is the characteristic decoupling operation, and f 21 , f 22 , ..., f 2i , ..., f 2n are the first, second, ..., i-th, ..., n-th local timing associated feature vectors of the port voltage offset in the sequence of the local timing associated feature vectors of the port voltage offset, n is the number of feature vectors in the sequence of the local timing associated feature vectors of the port voltage offset, f1 is the temperature timing associated feature vector, W and b are the temperature transformation matrix and the temperature offset vector, respectively, f 1t is the temperature time series correlation feature vector after the nonlinear transformation, f 1t T Yes 1t The transposed vector of Represents vector multiplication, M 12i is the temperature-port voltage offset interaction correlation matrix between the local timing correlation feature vector of the i-th port voltage offset and the temperature timing correlation feature vector after the nonlinear transformation, M 12i (t) is M 12i The eigenvalues ​​at each position in 12i It is M 12iThe mean of the matrix, E(·) is the expected value of the matrix, σ 12i 2 It is M 12i The variance of 12i M 12i The kurtosis value, λ is a hyperparameter, E 12i It is M 12i The corresponding temperature-port voltage offset characteristic interaction energy factor, sigmoid(·) is the sigmoid function, E norm，12i It is M 12i The corresponding normalized temperature-port voltage offset characteristic interaction energy factor, ⊙ is the position point multiplication, and M is the temperature drift-voltage offset local-global interaction response matrix.

[0058] In the embodiment of the present application, the reference current value generating unit 125 is used to obtain the reference current value based on the temperature drift-voltage offset local-global interactive response matrix. Specifically, in the embodiment of the present application, the reference current value generating unit is used to: input the temperature drift-voltage offset local-global interactive response matrix into the reference current generator based on the decoder to obtain the decoded value of the reference current. That is, the temperature drift-voltage offset local-global interactive response matrix obtained by the local-global interactive response of the temperature timing association feature vector and the port voltage offset timing association feature vector is decoded to intelligently obtain the reference current value. In this way, the working state and environmental changes of the chip can be captured more accurately, so as to adjust the reference current in time to adjust the output voltage, avoid the problems caused by the traditional current counter control method, and fully understand the interaction between temperature and voltage, and realize the precise adjustment of the power supply output voltage, so as to improve the adaptability and generalization ability of the adaptive control system, and improve the intelligence of the LED drive power supply control.

[0059] In a preferred example, since the temperature timing association feature vector and the port voltage offset timing association feature vector respectively represent the bidirectional short-range-long-range timing association features of the real-time temperature and the port voltage real-time offset values, when they are input into a feature local-global interactive response module based on feature decoupling, the temperature drift-voltage offset local-global interactive response matrix will also have a timing feature interactive response aggregation offset caused by the inconsistency of the timing decoupling local-global interactive response under the difference in source timing feature distribution, thereby expecting to improve the timing feature interactive response aggregation comprehensibility of the temperature drift-voltage offset local-global interactive response matrix, thereby improving the accuracy of the decoded value of the reference current obtained by the temperature drift-voltage offset local-global interactive response matrix input into the decoder-based reference current generator.

[0060] Therefore, when the temperature drift-voltage offset local-global interaction response matrix is ​​input into the decoder-based reference current generator, the present application optimizes the temperature drift-voltage offset local-global interaction response matrix, including the steps of: expanding the temperature drift-voltage offset local-global interaction response matrix into a temperature drift-voltage offset local-global interaction response vector; subtracting the 0 norm of the temperature drift-voltage offset local-global interaction response vector from the length of the temperature drift-voltage offset local-global interaction response vector to obtain an isolated representation value of the temperature drift-voltage offset local-global interaction response; calculating the logarithm of the sum of the square of the temperature drift-voltage offset local-global interaction response isolated representation value and the temperature drift-voltage offset local-global interaction response isolated representation value with base 2 to obtain the temperature drift-voltage offset local-global interaction response information order value; calculating the temperature drift-voltage offset local-global interaction response information order value with each eigenvalue of the temperature drift-voltage offset local-global interaction response vector as the base. The difference between the isolated representation value and one is an exponential power function, and is point-multiplied with the temperature drift-voltage offset local-global interactive response information order value to obtain the temperature drift-voltage offset local-global interactive response pilot vector; the temperature drift-voltage offset local-global interactive response vector is point-multiplied with the difference between the isolated representation value of the temperature drift-voltage offset local-global interactive response and one, and then point-multiplied with the reciprocal of the isolated representation value of the temperature drift-voltage offset local-global interactive response to obtain the temperature drift-voltage offset local-global interactive response field constraint vector; an exponential function is calculated with the natural constant as the base, and each eigenvalue of the temperature drift-voltage offset local-global interactive response field constraint vector is an exponential function to obtain the temperature drift-voltage offset local-global interactive response field bias vector; the temperature drift-voltage offset local-global interactive response pilot vector is point-added with the temperature drift-voltage offset local-global interactive response field bias vector to obtain the optimized temperature drift-voltage offset local-global interactive response vector.

[0061] The optimization process of the temperature drift-voltage offset local-global interaction response vector is expressed as:

[0062]

[0063] n=L-||V||0

[0064] Wherein, V represents the temperature drift-voltage offset local-global interaction response vector, L represents the length of the temperature drift-voltage offset local-global interaction response vector, ||·||0 represents the zero norm of the vector, n represents the isolated representation value of the temperature drift-voltage offset local-global interaction response, ⊙ represents the position point multiplication, log represents the logarithm with base 2, represents point-by-point addition, exp represents the natural exponential function, V ⊙(n-1) is a power function calculated with each eigenvalue of the temperature drift-voltage offset local-global interaction response vector as the base, the difference between the isolated representation value of the temperature drift-voltage offset local-global interaction response and one as the exponent, and V′ represents the optimized temperature drift-voltage offset local-global interaction response vector.

[0065] Therefore, the high-dimensional feature manifold of the temperature drift-voltage offset local-global interaction response matrix is ​​represented by the eigenvalues ​​of the feature set as the vector field of the aggregation dimension, and the superposition value of the vector field of the temperature drift-voltage offset local-global interaction response vector after the temperature drift-voltage offset local-global interaction response matrix is ​​expanded at the isolated zero position is used as the order information, the local position of the eigenvalue of its feature set is fixed, and a bias for the reversibility of the characteristic regression distribution field of the temperature drift-voltage offset local-global interaction response vector is added as a reward to achieve the mapping target tracking of the regression distribution of the temperature drift-voltage offset local-global interaction response vector for the eigenvalue position, so that the feature set of the temperature drift-voltage offset local-global interaction response matrix perceives the mapping migration to the aggregate distribution, thereby improving the accuracy of the decoded value of the reference current obtained by inputting it into the decoder-based reference current generator by improving the aggregate comprehensibility of the timing feature interaction response of the temperature drift-voltage offset local-global interaction response matrix. In this way, the working status and environmental changes of the chip can be captured more accurately, so as to adjust the reference current in time to adjust the output voltage, avoiding the problems caused by the traditional current counter control method, and being able to fully understand the interaction between temperature and voltage, and achieve precise adjustment of the power supply output voltage, so as to improve the adaptability and generalization ability of the adaptive control system, and improve the intelligence of the LED drive power supply control.

[0066] In summary, the adaptive control system 100 of the LED driving power supply based on the embodiment of the present application is explained, which uses artificial intelligence-based data analysis technology to analyze the timing correlation characteristics of the real-time temperature of the driving chip and the real-time offset value of the port voltage, so as to intelligently obtain the reference current value based on the local and global interactive response relationship between the real-time temperature timing correlation characteristics and the port voltage real-time offset value timing correlation characteristics. In this way, the working state and environmental changes of the chip can be captured more accurately, so as to adjust the reference current in time to adjust the output voltage, realize the precise adjustment of the power supply output voltage, and help to improve the intelligence of the LED driving power supply control.

[0067] As described above, the adaptive control system 100 of the LED driving power supply according to the embodiment of the present application can be implemented in various terminal devices, such as a server for adaptive control of the LED driving power supply. In one example, the adaptive control system 100 of the LED driving power supply according to the embodiment of the present application can be integrated into the terminal device as a software module and / or a hardware module. For example, the adaptive control system 100 of the LED driving power supply can be a software module in the operating system of the terminal device, or can be an application developed for the terminal device; of course, the adaptive control system 100 of the LED driving power supply can also be one of the many hardware modules of the terminal device.

[0068] Alternatively, in another example, the adaptive control system 100 of the LED driving power supply and the terminal device may also be separate devices, and the adaptive control system 100 of the LED driving power supply may be connected to the terminal device via a wired and / or wireless network and transmit interactive information in accordance with an agreed data format.

[0069] Figure 6 FIG. 1 is a flow chart of an adaptive control method for an LED driving power supply according to an embodiment of the present application. Figure 6 As shown, in the adaptive control method of the LED driving power supply, it includes: S110, obtaining the port voltage information of the LED driving chip, the port voltage information is the time queue of the port voltage; S120, generating a reference current value based on a preset port voltage standard value and the port voltage information; S130, transmitting the reference current value to the FB port of the power management system to adjust the output voltage of the power management system and adjust the port voltage of the LED driving chip; wherein, in step S120, it includes: obtaining the time queue of the real-time temperature of the LED driving chip; calculating the time queue of the real-time offset value of the port voltage based on the preset port voltage standard value and the time queue of the port voltage; inputting the time queue of the real-time temperature and the time queue of the real-time offset value of the port voltage into a sequence encoder respectively to obtain a temperature timing correlation feature vector and a port voltage offset timing correlation feature vector; inputting the temperature timing correlation feature vector and the port voltage offset timing correlation feature vector into a feature local-global interactive response module based on feature decoupling to obtain a temperature drift-voltage offset local-global interactive response matrix; and obtaining the reference current value based on the temperature drift-voltage offset local-global interactive response matrix.

[0070] Here, those skilled in the art can understand that the specific operations of each step in the above-mentioned adaptive control method of LED driving power supply have been described in the above reference. Figures 1 to 5The adaptive control system of the LED driving power supply has been described in detail, and therefore, its repeated description will be omitted.

[0071] In summary, the adaptive control method of the LED driving power supply based on the embodiment of the present application is explained, which uses artificial intelligence-based data analysis technology to analyze the timing correlation characteristics of the real-time temperature of the driving chip and the real-time offset value of the port voltage, so as to intelligently obtain the reference current value based on the local and global interactive response relationship between the real-time temperature timing correlation characteristics and the port voltage real-time offset value timing correlation characteristics. In this way, the working state and environmental changes of the chip can be captured more accurately, so as to adjust the reference current in time to adjust the output voltage, realize the precise adjustment of the power supply output voltage, and help to improve the intelligence of the LED driving power supply control.

[0072] In the several embodiments provided in this application, it should be understood that the disclosed methods and systems can be implemented in other ways. For example, the system embodiments described above are only schematic, for example, the division of the modules is only a logical function division, and there may be other division methods in actual implementation.

[0073] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0074] In addition, each functional module in each embodiment of the present application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above integrated unit can be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0075] It is obvious to those skilled in the art that the present application is not limited to the details of the above exemplary embodiments, and that the present application can be implemented in other specific forms without departing from the spirit or essential features of the present application.

Claims

1. An adaptive control system for an LED driving power supply, characterized in that: include: A port voltage information acquisition module, used to acquire the port voltage information of the LED driver chip, wherein the port voltage information is a time queue of the port voltage; An adjustment signal generating module, used for generating a reference current value based on a preset port voltage standard value and the port voltage information; A port voltage information adjustment module, used to transmit the reference current value to the FB port of the power management system, so as to adjust the output voltage of the power management system and adjust the port voltage of the LED driver chip; Wherein, the adjustment signal generating module includes: A temperature real-time data acquisition unit, used to obtain a time queue of the real-time temperature of the LED driver chip; A port voltage real-time offset value calculation unit, used for calculating a time queue of a port voltage real-time offset value based on the preset port voltage standard value and the port voltage time queue; A temperature-port voltage timing association unit, used for inputting the time queue of the real-time temperature and the time queue of the real-time offset value of the port voltage into a sequence encoder respectively to obtain a temperature timing association feature vector and a port voltage offset timing association feature vector; A temperature-port voltage interactive response unit, used for inputting the temperature timing-related characteristic vector and the port voltage offset timing-related characteristic vector into a characteristic local-global interactive response module based on characteristic decoupling to obtain a temperature drift-voltage offset local-global interactive response matrix; The reference current value generating unit is used to obtain the reference current value based on the temperature drift-voltage offset local-global interaction response matrix.

2. The adaptive control system of LED driving power supply according to claim 1, characterized in that: The temperature-port-voltage timing association unit is used to input the time queue of the real-time temperature and the time queue of the port voltage real-time offset value into a sequence encoder based on a backward LSTM model to obtain the temperature timing association feature vector and the port voltage offset timing association feature vector.

3. The adaptive control system of the LED driving power supply according to claim 2, characterized in that: The temperature-port voltage interactive response unit comprises: A port voltage offset timing correlation feature decoupling subunit, used for performing feature decoupling on the port voltage offset timing correlation feature vector to obtain a sequence of port voltage offset local timing correlation feature vectors; A temperature time series nonlinear transformation subunit, used for performing a nonlinear transformation on the temperature time series associated characteristic vector to obtain a temperature time series associated characteristic vector after nonlinear transformation; The temperature-port voltage local timing correlation subunit is used to calculate the correlation matrix between the temperature timing correlation feature vector after the nonlinear transformation and each port voltage offset local timing correlation feature vector in the sequence of the port voltage offset local timing correlation feature vector to obtain a sequence of temperature-port voltage offset interactive correlation matrices; A temperature-port voltage offset characteristic interaction energy factor calculation subunit, used to calculate the characteristic interaction energy factor of each temperature-port voltage offset interaction correlation matrix in the sequence of temperature-port voltage offset interaction correlation matrices to obtain a sequence of temperature-port voltage offset characteristic interaction energy factors; A temperature-port voltage offset characteristic interaction energy factor normalization processing subunit, used for inputting the sequence of the temperature-port voltage offset characteristic interaction energy factors into a Sigmoid function to obtain a sequence of normalized temperature-port voltage offset characteristic interaction energy factors; The temperature drift-voltage offset local-global interaction response matrix generation subunit is used to calculate the position-weighted sum of the sequence of the temperature-port voltage offset interaction correlation matrix using the sequence of the normalized temperature-port voltage offset characteristic interaction energy factors as the sequence of weights to obtain the temperature drift-voltage offset local-global interaction response matrix.

4. The adaptive control system of the LED driving power supply according to claim 3, characterized in that: The temperature time series nonlinear transformation subunit is used to: after multiplying the temperature time series associated feature vector with the temperature transformation matrix, add the obtained temperature time series associated weight vector and temperature bias vector according to the position to obtain the temperature time series associated feature vector after the nonlinear transformation.

5. The adaptive control system of the LED driving power supply according to claim 4, characterized in that: The temperature-port voltage local timing association subunit is used to: vector-multiply the transposed vector of the temperature timing association feature vector after the nonlinear transformation and each port voltage offset local timing association feature vector in the sequence of the port voltage offset local timing association feature vector to obtain the sequence of the temperature-port voltage offset interactive correlation matrix.

6. The adaptive control system of the LED driving power supply according to claim 5, characterized in that: The temperature-port voltage offset characteristic interaction energy factor calculation subunit includes: A temperature-port voltage offset cross-correlation kurtosis value calculation secondary subunit is used to calculate the kurtosis value of each temperature-port voltage offset cross-correlation matrix in the sequence of temperature-port voltage offset cross-correlation matrices to obtain a sequence of temperature-port voltage offset cross-correlation kurtosis values; The temperature-port voltage offset interaction energy factor calculation secondary subunit is used to calculate the characteristic interaction energy factor of each temperature-port voltage offset interaction correlation matrix based on each temperature-port voltage offset interaction correlation kurtosis value in the sequence of the temperature-port voltage offset interaction correlation kurtosis value to obtain the sequence of the temperature-port voltage offset characteristic interaction energy factors.

7. The adaptive control system of LED driving power supply according to claim 6, characterized in that: The temperature-port voltage offset interactive correlation kurtosis value calculation secondary subunit is used for: Respectively calculating the mean and variance of the temperature-port voltage offset interaction correlation matrix to obtain the temperature-port voltage offset interaction correlation mean and the temperature-port voltage offset interaction correlation variance; Calculating the positional difference between the temperature-port voltage offset interaction correlation matrix and the temperature-port voltage offset interaction correlation mean to obtain a temperature-port voltage offset interaction correlation difference matrix; Calculating the fourth power of each eigenvalue in the temperature-port voltage offset cross-correlation difference matrix to obtain a temperature-port voltage offset cross-correlation modulation difference matrix; Calculating the expected value of the temperature-port voltage offset cross-correlation modulation difference matrix to obtain the temperature-port voltage offset cross-correlation expected value; The temperature-port voltage offset cross-correlation expected value is divided by the square of the temperature-port voltage offset cross-correlation variance to obtain the temperature-port voltage offset cross-correlation kurtosis value.

8. The adaptive control system of LED driving power supply according to claim 7, characterized in that: The temperature-port voltage offset interaction energy factor calculation secondary subunit is used for: Calculating the sum of the temperature-port voltage offset interaction variance and the hyperparameter to obtain a temperature-port voltage offset interaction first energy factor; Calculating the square of the difference between the temperature-port voltage offset cross-correlation kurtosis value and the temperature-port voltage offset cross-correlation mean value to obtain a temperature-port voltage offset cross-correlation difference value; The temperature-port voltage offset cross-correlation variance is multiplied by a constant of two, the hyperparameter is multiplied by a constant of two, and the temperature-port voltage offset cross-correlation difference value is added to obtain a temperature-port voltage offset cross-correlation second energy factor; The temperature-port voltage offset interaction first energy factor is divided by the temperature-port voltage offset interaction second energy factor to obtain the temperature-port voltage offset characteristic interaction energy factor corresponding to the temperature-port voltage offset interaction matrix.

9. The adaptive control system of LED driving power supply according to claim 8, characterized in that: The reference current value generating unit is used to: input the temperature drift-voltage offset local-global interaction response matrix into a decoder-based reference current generator to obtain a decoded value of the reference current.

10. An adaptive control method for an LED driving power supply, characterized in that: include: Acquire port voltage information of the LED driver chip, where the port voltage information is a time queue of the port voltage; Generate a reference current value based on a preset port voltage standard value and the port voltage information; Transmitting the reference current value to the FB port of the power management system to adjust the output voltage of the power management system and adjust the port voltage of the LED driver chip; The step of generating a reference current value based on a preset port voltage standard value and the port voltage information includes: A time queue for obtaining the real-time temperature of the LED driver chip; Calculate the time queue of the port voltage real-time offset value based on the preset port voltage standard value and the time queue of the port voltage; Inputting the time queue of the real-time temperature and the time queue of the real-time offset value of the port voltage into a sequence encoder respectively to obtain a temperature timing correlation feature vector and a port voltage offset timing correlation feature vector; Inputting the temperature timing correlation feature vector and the port voltage offset timing correlation feature vector into a feature local-global interactive response module based on feature decoupling to obtain a temperature drift-voltage offset local-global interactive response matrix; The reference current value is obtained based on the temperature drift-voltage offset local-global interaction response matrix.

Images