LED multi-light color regulation method and system based on multi-objective evolutionary algorithm

Abstract

The application provides an LED multi-light color regulation method and system based on a multi-target evolution algorithm, which firstly acquires the spectrum and electric power data of each single-color LED, and pre-processes the data by combining a cubic spline interpolation method and a fitting function; then each light color index such as a color coordinate, a color rendering index, a color temperature, an SDCM value and power consumption is optimized by designing an evaluation function; the core of the algorithm is to use a multi-target genetic algorithm to iteratively optimize the population through individual evaluation, survival of the fittest, genetic and mutation operations until the optimal PWM combination meeting all the light color index requirements is found. Specifically, the method has the advantages of strong flexibility, good expansibility and the like, can adapt to different LED channel configurations, and provides a light color regulation scheme with strong pertinence, and is particularly suitable for factory adjustment of a phosphor-free multi-primary color LED lamp, and provides an efficient and automated solution for light color optimization.

Description

Technical Field

[0001] This invention belongs to the field of intelligent control technology, and specifically relates to an LED multi-color control method and system based on a multi-objective evolutionary algorithm. Background Technology

[0002] With the rapid development of LED (Light Emitting Diode) technology, LED light sources, with their advantages of high efficiency, energy saving, and long lifespan, have gradually become the mainstream light source in the lighting field. Multi-color LED luminaires have attracted much attention in recent years due to their ability to adjust multiple light colors and achieve personalized lighting solutions. Especially in demanding scenarios such as display technology, plant lighting, and medical lighting, higher requirements are placed on the precision of light color control. However, due to the complex spectral combinations of multi-color LED luminaires, there are mutual constraints between power consumption, color rendering index, color temperature, and other light color indicators under different light colors. How to achieve efficient and precise control of multi-color LED luminaires has become a current research challenge and focus.

[0003] Existing methods for controlling LED light color typically employ linear adjustment schemes based on empirical formulas, or manually adjust the PWM (Pulse Width Modulation) values ​​of each primary color to achieve the desired light color output. However, these methods are complex and time-consuming, and struggle to simultaneously meet all light color requirements while optimizing power consumption. Furthermore, due to the lack of systematic approach in manual adjustments, the control results are often imprecise, failing to meet the stringent light color requirements of certain specialized applications.

[0004] To address the aforementioned issues, some studies have introduced intelligent optimization methods such as genetic algorithms and multi-objective optimization algorithms to solve nonlinear, multi-objective problems in the color modulation of multi-color LEDs. These algorithms can optimize power consumption and color rendering performance while meeting color performance requirements, thus improving the efficiency and accuracy of color modulation. However, existing intelligent algorithms still have many shortcomings in practical applications. For example, some algorithms converge slowly in complex scenarios and are prone to getting trapped in local optima; some algorithms have simple evaluation functions that cannot balance the optimization of multiple color performance indicators; and some algorithms lack flexibility and are difficult to adapt to multi-color LED luminaires with different configurations.

[0005] Therefore, designing an effective scheme for optimizing the color temperature control of multi-primary-color LED luminaires, particularly by introducing a multi-objective evolutionary algorithm to comprehensively optimize multiple objectives such as color coordinates, color rendering index, color temperature, and power consumption, has become a key problem urgently needing to be solved in the current technical field. Against this backdrop, this invention proposes an LED multi-color temperature control optimization method based on a multi-objective evolutionary algorithm, aiming to provide an efficient, automated color temperature optimization solution adaptable to different application scenarios. Summary of the Invention

[0006] Based on this, the present invention provides a method and system for LED multi-color control based on a multi-objective evolutionary algorithm, which aims to solve the problems of low efficiency, poor accuracy, and difficulty in simultaneously taking into account multiple color indicators in the prior art.

[0007] A first aspect of this invention provides a method for LED multicolor modulation based on a multi-objective evolutionary algorithm, the method comprising:

[0008] The spectral data and power data of the LED lamps under different PWM values ​​are collected, and the spectral data are smoothed by cubic spline interpolation, and the power data is processed by a preset fitting function.

[0009] Calculate the colorimetric index corresponding to each PWM combination. The colorimetric index includes at least color coordinates, color rendering index, color temperature, SDCM value and power consumption. The color rendering index includes color rendering index Ra and color rendering index R9.

[0010] An initial population is randomly generated, where each individual represents a PWM combination. The population evolves using a multi-objective evolutionary algorithm, which optimizes the population step by step through selection, crossover, and mutation operations in the genetic algorithm. Specifically, in the selection operation, a roulette wheel selection strategy is used to select target individuals to enter the next generation; in the crossover operation, a single-point crossover method is used to cross the PWM combinations of two parent individuals to generate new offspring individuals; in the mutation operation, a dynamic mutation rate adjustment mechanism is used to introduce random perturbations to increase the diversity of the population.

[0011] When all light and color indicators meet the preset requirements, a target PWM combination is output, which is used to control the LED lamps.

[0012] This invention provides a method for LED multi-color modulation based on a multi-objective evolutionary algorithm. The method first acquires the spectral and electrical power data of each monochromatic LED, and preprocesses the data using cubic spline interpolation and a fitting function. Then, by designing an evaluation function, it optimizes various color parameters such as chromaticity coordinates, color rendering index, color temperature, SDCM value, and power consumption. The core of the algorithm lies in using a multi-objective genetic algorithm to iteratively optimize the population through individual evaluation, survival of the fittest, genetic and mutation operations until the optimal PWM combination that meets all color parameter requirements is found. Specifically, this method has advantages such as high flexibility and good scalability, can adapt to different LED channel configurations, and provides targeted color modulation schemes. It is particularly suitable for the factory adjustment of phosphorless multi-color LED lamps, providing an efficient and automated solution for color optimization.

[0013] Furthermore, the calculation formula for the cubic spline interpolation method is as follows:

[0014]

[0015] in, It is the input value of the PWM combination. This is the corresponding spectral output. , , , The first Interpolation coefficients for each sampling point For the first The PWM value of each sampling point.

[0016] Furthermore, the multi-objective evolutionary algorithm is a combination of genetic algorithm and non-dominated sorting algorithm. By performing multi-objective optimization on the initial population, the optimal balance point between light color index and power consumption is gradually screened out.

[0017] Furthermore, the evaluation function of the multi-objective evolutionary algorithm takes into account color coordinates, color rendering index, color temperature, SDCM value and power consumption. The evaluation function performs a comprehensive calculation on each index through weighting coefficients.

[0018] Furthermore, in the design of the evaluation function, a weighted multi-objective fitness function was adopted. Specifically, the calculation formula of the weighted multi-objective fitness function is as follows:

[0019]

[0020] in, Indicates the fitness of color coordinates. The colorimetric index Ra and colorimetric index R9 represent the fitness of the individual. Indicates the suitability of color temperature. Indicates the fitness of electrical power consumption. Indicates the fitness of the SDCM value. , , , , These are the weighting coefficients for each indicator.

[0021] Furthermore, the color rendering index Ra and color rendering index R9 are calculated based on the CIE colorimetric standard, and a dynamic weight adjustment method is used to correct the color rendering index score of each evolutionary individual in real time, so as to improve the color reproduction of the final generated PWM combination in practical applications.

[0022] Furthermore, the calculation formula for the dynamic mutation rate adjustment mechanism is as follows:

[0023]

[0024] in, This indicates the genetic algorithm in the th... The probability of performing a mutation operation. For the current generation, To adjust the constant of the rate, This is the convergence point of the algorithm.

[0025] A second aspect of this invention provides an LED multi-color modulation system based on a multi-objective evolutionary algorithm, used to implement the LED multi-color modulation method based on a multi-objective evolutionary algorithm described in the first aspect, the system comprising:

[0026] The acquisition module is used to acquire spectral data and electrical power data of LED lamps under different PWM values, and to smooth the spectral data using cubic spline interpolation and to process the electrical power data using a preset fitting function.

[0027] The calculation module is used to calculate the light color index corresponding to each PWM combination. The light color index includes at least color coordinates, color rendering index, color temperature, SDCM value and power consumption. The color rendering index includes color rendering index Ra and color rendering index R9.

[0028] The optimization module is used to randomly generate the initial population, where each individual represents a PWM combination. The population evolves through a multi-objective evolutionary algorithm, which optimizes the population step by step through selection, crossover, and mutation operations in the genetic algorithm. Specifically, in the selection operation, a roulette wheel selection strategy is used to select target individuals to enter the next generation; in the crossover operation, a single-point crossover method is used to cross the PWM combinations of two parent individuals to generate new offspring individuals; in the mutation operation, a dynamic mutation rate adjustment mechanism is used to introduce random perturbations to increase the diversity of the population.

[0029] The output module is used to output a target PWM combination when all light and color indicators meet the preset requirements. The target PWM combination is used to control the LED lamps.

[0030] A third aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the LED multicolor modulation method based on a multi-objective evolutionary algorithm provided in the first aspect.

[0031] A fourth aspect of the present invention provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the LED multi-color modulation method based on a multi-objective evolutionary algorithm provided in the first aspect.

[0032] The beneficial effects of the LED multicolor modulation method based on a multi-objective evolutionary algorithm provided by this invention are as follows:

[0033] 1. By introducing a multi-objective evolutionary algorithm, the problem of light color control in multi-primary-color LED lamps is effectively solved. It can simultaneously optimize multiple light color indicators such as color coordinates, color rendering index, color temperature, and power consumption, achieving highly precise light color control. Compared to traditional manual control methods, this invention significantly improves control efficiency through intelligent optimization algorithms, reduces human intervention, and yields more accurate and stable optimization results.

[0034] 2. Cubic spline interpolation was used to smooth the spectral data, enabling a continuous transition between different PWM values ​​and reducing data dispersion errors, thereby improving the accuracy of the spectral data. This data processing method has higher fitting accuracy than traditional linear interpolation methods and is particularly suitable for multi-primary-color LED lighting scenarios with nonlinear spectral changes.

[0035] 3. By introducing a dynamic mutation rate adjustment mechanism, the genetic algorithm avoids the tendency to get trapped in local optima. In the early stages of optimization, increasing the mutation rate enhances population diversity and thus strengthens global search capabilities; in the later stages, decreasing the mutation rate accelerates convergence, ensuring the algorithm quickly finds the global optimum. This dynamic mutation rate strategy significantly improves the efficiency and stability of the optimization algorithm.

[0036] 4. The multi-objective fitness function design is flexible and can dynamically adjust the weight coefficients according to different application requirements, achieving adaptive optimization for different scenarios. For example, in indoor lighting, this invention can prioritize optimizing the color rendering index and power consumption; in display screen lighting, it can focus on optimizing the color coordinates and color rendering index. This flexible optimization strategy makes this invention applicable to a variety of application scenarios, possessing strong practicality and promotional value.

[0037] 5. By employing genetic, crossover, and mutation operations to perform multi-generational population evolution, the optimal PWM combination can be automatically generated, avoiding the tedious manual adjustment process for different light colors in traditional methods and greatly improving control efficiency. Furthermore, by preserving the best individuals from each generation, the global optimality of the final output PWM combination in terms of light color indicators is guaranteed, enabling this method to achieve excellent light color performance in various application scenarios. Attached Figure Description

[0038] Figure 1 This is a flowchart illustrating the implementation of an LED multi-color modulation method based on a multi-objective evolutionary algorithm, as provided in Embodiment 1 of the present invention.

[0039] Figure 2This is a structural block diagram of an LED multi-color control system based on a multi-objective evolutionary algorithm provided in Embodiment 4 of the present invention;

[0040] Figure 3 This is a structural block diagram of an electronic device provided in Embodiment 5 of the present invention. Detailed Implementation

[0041] To facilitate understanding of the present invention, a more complete description will be given below with reference to the accompanying drawings. Several embodiments of the invention are illustrated in the drawings. However, the invention can be implemented in many different forms and is not limited to the embodiments described herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete.

[0042] It should be noted that when a component is said to be "fixed to" another component, it can be directly on the other component or there may be an intervening component. When a component is said to be "connected to" another component, it can be directly connected to the other component or there may be an intervening component. The terms "vertical," "horizontal," "left," "right," and similar expressions used in this document are for illustrative purposes only.

[0043] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used herein in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0044] Example 1

[0045] According to an embodiment of the present invention, an embodiment of an LED multi-color control method based on a multi-objective evolutionary algorithm is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0046] This invention provides a method for LED multi-color modulation based on a multi-objective evolutionary algorithm, which can be used in electronic devices, such as computers. Please refer to... Figure 1 , Figure 1 The flowchart of the implementation of an LED multi-color modulation method based on a multi-objective evolutionary algorithm provided in Embodiment 1 of the present invention is shown, specifically including steps S01 to S04.

[0047] Step S01: Collect spectral data and power data of LED lamps under different PWM values, and smooth the spectral data using cubic spline interpolation, and process the power data using a preset fitting function.

[0048] First, the system collects the spectrum of multi-primary-color LED lamps, acquiring spectral data for each primary-color LED under different PWM combinations. To improve the accuracy of data processing, this invention employs a cubic spline interpolation algorithm when processing the spectral data. The advantage of this algorithm is that it enables a smooth transition of spectral data between discrete PWM combinations, thereby effectively reducing errors caused by the nonlinearity of LED spectral variations. The calculation formula for the cubic spline interpolation method is as follows:

[0049]

[0050] in, It is the input value of the PWM combination. This is the corresponding spectral output. , , , The first Interpolation coefficients for each sampling point For the first The PWM values ​​at each sampling point. This interpolation method can generate continuous spectral data under different PWM values, providing more accurate input for subsequent optimization algorithms.

[0051] Step S02: Calculate the color index corresponding to each PWM combination. The color index includes at least color coordinates, color rendering index, color temperature, SDCM value and power consumption. The color rendering index includes color rendering index Ra and color rendering index R9.

[0052] In this embodiment of the invention, by collecting spectral data and electrical power data, and combining the calculation method in the CIE standard colorimetric system, the colorimetric index corresponding to each PWM combination is calculated. The formula for calculating the color rendering index Ra is as follows:

[0053]

[0054] Here, ΔE represents the color difference value, which is calculated by the difference between the LED spectrum and the standard light source spectrum. R9, as the color rendering index of high-saturation red, is an important parameter in certain special applications (such as medical lighting and plant lighting). Unlike existing technologies, this invention uses both R9 and Ra as optimization targets for the color rendering index, ensuring that the light color control results not only perform well in conventional applications but are also suitable for special lighting needs.

[0055] Step S03: Randomly generate an initial population, where each individual represents a PWM combination, and perform population evolution through a multi-objective evolutionary algorithm.

[0056] The population evolution process is as follows: First, an initial population is generated, with each individual representing a PWM combination. The population is then gradually optimized through selection, crossover, and mutation operations in the genetic algorithm. In the selection operation, a roulette wheel selection strategy is used to select individuals with higher fitness for the next generation. In the crossover operation, a single-point crossover method is used to crossover the PWM combinations of two parent individuals to generate new offspring individuals. In the mutation operation, a dynamic mutation rate adjustment mechanism is used to appropriately introduce random perturbations to increase population diversity.

[0057] It should be noted that the multi-objective evolutionary algorithm is a combination of genetic algorithm and non-dominated sorting algorithm. By performing multi-objective optimization on the initial population, it gradually selects the optimal balance point between light and color indicators and power consumption, ensuring that the final output PWM combination performs well in all light and color indicators. Specifically, the evaluation function of the multi-objective evolutionary algorithm considers color coordinates, color rendering index, color temperature, SDCM value, and power consumption. The evaluation function comprehensively calculates each indicator through weighting coefficients. The weighting coefficients are adjusted according to specific application requirements to achieve light and color control optimization in different scenarios. The calculation formula of this weighted multi-objective fitness function is as follows:

[0058]

[0059] in, Indicates the fitness of color coordinates. The colorimetric index Ra and colorimetric index R9 represent the fitness of the individual. Indicates the suitability of color temperature. Indicates the fitness of electrical power consumption. Indicates the fitness of the SDCM value. , , , , These are the weighting coefficients for each indicator. Understandably, by dynamically adjusting these weighting coefficients, one or more light and color indicators can be prioritized for optimization based on actual application needs. For example, in medical lighting, the focus might be on optimizing the color rendering index, while in general lighting, the focus might be on minimizing power consumption.

[0060] In this embodiment of the invention, to avoid the algorithm getting trapped in local optima, the mutation rate is dynamically adjusted based on the fitness distribution of each generation of the population. In the early stages of evolution, the mutation rate is increased to enhance population diversity; in the later stages of evolution, the mutation rate is decreased to accelerate convergence. The calculation formula for this dynamic mutation rate adjustment mechanism is as follows:

[0061]

[0062] in, This indicates the genetic algorithm in the th... The probability of performing a mutation operation. For the current generation, To adjust the constant of the rate, This represents the convergence point of the algorithm. This mechanism helps the algorithm avoid premature convergence in the early stages of exploration, while simultaneously accelerating the search for the global optimum in later stages.

[0063] Step S04: When all light and color indicators meet the preset requirements, output the target PWM combination, which is used to control the LED lamps.

[0064] In summary, the LED multi-color control method based on a multi-objective evolutionary algorithm in the above embodiments of the present invention first acquires the spectral and electrical power data of each monochromatic LED, and preprocesses the data using cubic spline interpolation and a fitting function. Then, by designing an evaluation function, it optimizes various color indicators such as chromaticity coordinates, color rendering index, color temperature, SDCM value, and power consumption. The core of the algorithm lies in using a multi-objective genetic algorithm to iteratively optimize the population through individual evaluation, survival of the fittest, genetic and mutation operations until the optimal PWM combination that meets all color indicator requirements is found. Specifically, this method has advantages such as high flexibility and good scalability, can adapt to different LED channel configurations, and provides targeted color control schemes. It is particularly suitable for the factory adjustment of phosphorless multi-color LED lamps, providing an efficient and automated solution for color optimization.

[0065] Example 2

[0066] Embodiment 2 of this invention illustrates how to optimize the light color control of multi-primary-color LED lamps using a multi-objective evolutionary algorithm. In this embodiment, for a phosphorless multi-primary-color LED lamp, the goal is to adjust the PWM value at different color temperature levels (e.g., 5000K, 4000K, 3000K, and 2000K) to meet specific light color index requirements, including optimization of color coordinates, SDCM, color rendering index Ra, color rendering index R9, and power consumption. The entire process runs on a pre-designed machine with a built-in control system and an interface with a host computer for easy data acquisition and transmission. In this embodiment, the algorithm is written in Python, and all data processing and optimization processes are completed within this language environment.

[0067] First, the device collects spectral and power data of the LED lights at different PWM values. To ensure data accuracy, the measured PWM values ​​cover a certain range of variation; for example, the PWM value for red LEDs ranges from 50 to 200, with a step size of 20. After acquiring the spectral data corresponding to these PWM values, it is saved to a data file for later use. In addition, power consumption data at different PWM values ​​is also recorded simultaneously with the spectral measurements; this data is used to fit a power model.

[0068] Next, the system performs fitting and interpolation processing on the acquired spectral and electrical power data. Since spectral data is typically discrete, to obtain accurate spectral output at any PWM value, this embodiment employs cubic spline interpolation to preprocess the data, ensuring that all PWM values ​​between 50 and 200 can be interpolated to obtain the corresponding spectrum. Simultaneously, the electrical power data is processed using a fitting function to establish a four-channel power estimation model. This model uses the PWM values ​​of the four RGBA channels as independent variables to output an estimated electrical power value. This processing step ensures that subsequent algorithms can quickly query spectral and electrical power data during multi-objective optimization without requiring remeasurement.

[0069] After data preprocessing, the main process of the multi-objective evolutionary algorithm is initiated. The core task of this algorithm is to achieve comprehensive optimization of color coordinates, SDCM values, color rendering index Ra, color rendering index R9, and power consumption through iterative optimization using a genetic algorithm. This embodiment of the invention treats the optimization problem as a multi-input, multi-output problem; the inputs are the PWM values ​​of four channels: red, green, blue, and yellow light, and the outputs are color coordinates, SDCM values, color rendering index Ra, and color rendering index R9. To ensure comprehensive optimization, the multi-objective evolutionary algorithm of this embodiment sets multiple objective functions and scores each objective using a fitness function.

[0070] Specifically, each colorimetric index has an independent evaluation function. For example, the color coordinate evaluation function determines fitness by calculating the Euclidean distance between the LED color and the target color coordinate under the current PWM combination. The SDCM value evaluation function uses a set threshold to ensure that the highest score is given when the SDCM value is less than the set value. The color rendering index Ra and color rendering index R9 evaluation functions are based on set numerical requirements (e.g., both color rendering index Ra and color rendering index R9 are greater than 90). As long as this requirement is met, the fitness score is the highest. For the power consumption evaluation function, the system sets a target power range. As long as the power under the PWM combination falls within this range, it is considered to meet the requirements and obtains the corresponding score. By weighting and summing the outputs of all evaluation functions, this embodiment of the invention ensures that each colorimetric index is fully considered during the optimization process.

[0071] Furthermore, the system begins a multi-generational evolutionary iteration process. First, a set of random PWM combinations is generated as the initial population. Each PWM combination represents the spectral output of an LED. The spectral data for these combinations is found using cubic spline interpolation, and their corresponding colorimetric indices are calculated. Then, the system evaluates the fitness of these individuals. Individuals with high evaluation values ​​are retained, while those with lower fitness are gradually eliminated. Next, the system performs genetic and mutation operations on the retained superior individuals. Genetic operations generate new PWM combinations by cross-referencing the characteristics of different PWM combinations, while mutation operations increase population diversity by randomly changing certain PWM values. This process continues iteratively until the optimal individuals in the population converge to a stable optimal solution, meaning all colorimetric indices meet the predetermined requirements.

[0072] In this embodiment of the invention, the iterative process of the multi-objective evolutionary algorithm also employs a dynamic mutation rate adjustment mechanism. In the early stages of evolution, the mutation rate is increased to enhance population diversity and avoid early entrapment in local optima. In the later stages of evolution, as the population fitness increases, the mutation rate gradually decreases to accelerate the algorithm's convergence speed. Furthermore, this embodiment of the invention records the individual with the highest fitness in each generation as a reference to prevent the loss of optimal solutions due to subsequent mutations. This mechanism effectively improves the algorithm's global search capability while ensuring the reliability of the optimal solution.

[0073] After the iteration process is completed, the system outputs the final optimal PWM combination. The corresponding colorimetric parameters of this combination meet the requirements at multiple color temperature levels. For example, at 5000K, 4000K, 3000K, and 2000K, the color coordinates of the LED luminaire meet the target color coordinate requirements, the SDCM value is less than 1, and both the color rendering index Ra and color rendering index R9 are greater than 90. Power consumption is also controlled within a reasonable range. Through the method of this invention, the optimized PWM combination ensures that the colorimetric performance of multi-primary-color LED luminaires at different color temperatures not only meets design requirements but also possesses high energy efficiency.

[0074] It should be noted that the embodiments of this invention demonstrate the flexibility and scalability of the optimization method. Although the embodiments of this invention are aimed at four-channel (red, green, blue, yellow) LED lamps, the algorithm can be easily modified to control LED lamps with more channels. Furthermore, since the multi-objective evolutionary algorithm can adaptively adjust according to different optimization objectives, this method is also applicable in other future application scenarios, such as plant lighting and display backlighting, where there are specific requirements for color rendering index, power consumption, or other light color indicators. By adjusting the weight coefficients in the fitness function, the system can quickly adapt to different optimization objectives, improving the versatility of this invention.

[0075] This invention demonstrates the advantages of applying a multi-objective evolutionary algorithm to the color modulation of multi-primary-color LED lamps in improving color modulation accuracy, optimizing energy efficiency, and achieving automated modulation. The method of this invention not only effectively simplifies the LED color modulation process but also significantly improves modulation efficiency and color performance, possessing broad application potential.

[0076] Example 3

[0077] Embodiment 3 of this invention also focuses on factory adjustment of phosphorless multi-color LED luminaires, but employs a different algorithm optimization strategy, aiming to achieve greater flexibility and adaptability in the multi-objective optimization process. The goal of this embodiment is to ensure that the light color indicators (including color coordinates, color rendering index Ra, color rendering index R9, and power consumption) of the LED luminaires meet stringent standards at various color temperature levels (such as 5000K, 4000K, 3000K, and 2000K).

[0078] Specifically, the system first collects spectral and power data of the LED lights under various PWM combinations to ensure the accuracy and representativeness of the data. Compared to the first embodiment, this embodiment places greater emphasis on the breadth of the data acquisition range, including not only the PWM values ​​of red, green, blue, and yellow light, but also comprehensive spectral measurements at each color temperature level. This means that the machine repeatedly measures the spectrum and power under different color temperature conditions to ensure the reliability and accuracy of the light and color data.

[0079] In the data processing stage, this embodiment of the invention also employs cubic spline interpolation. However, during the processing of interpolated data, the focus is on the characteristics of each LED spectrum, using different interpolation parameters for targeted processing. By analyzing the characteristics of each spectrum and the nonlinear changes in PWM output, a more refined interpolation strategy is formulated to improve the accuracy of subsequent calculations. Specifically, LEDs of different colors may exhibit different spectral fluctuations under the same PWM value. Therefore, this embodiment of the invention uses color-specific parameters when processing the spectral data of red, green, blue, and yellow light, which can better adapt to the light-emitting characteristics of LEDs.

[0080] In the implementation of the multi-objective optimization algorithm, this embodiment of the invention constructs an improved multi-objective fitness function. This function not only includes the calculation of color coordinates, color rendering index Ra, color rendering index R9, and power consumption, but also introduces a new index: user-customized light color preference settings. Users can set the priority of different light colors according to specific application requirements. This flexible optimization method has high adaptability in market applications.

[0081] Specifically, when establishing the fitness function, this embodiment of the invention considers user feedback and market demand, allowing users to set certain light color targets before the algorithm runs. For example, in indoor lighting applications, users may pay more attention to the color rendering index and color temperature, while in display screen applications, users may prioritize color coordinates and power consumption. Therefore, the fitness function can dynamically adjust the weights according to user input in different application scenarios, ensuring optimal control effects under different needs.

[0082] This invention employs a non-dominated sorting genetic algorithm (NSGA-II) for multi-objective optimization. Compared to the genetic algorithm in the first embodiment, the NSGA-II algorithm in this invention can handle multiple objectives simultaneously and ensures population diversity during evolution, preventing individuals from prematurely converging to local optima. In the initial population generation stage, a larger random range is used to ensure coverage of more PWM combinations. Individuals with high fitness are selected through evaluation of the initial population, and crossover and mutation operations are then performed on these individuals.

[0083] In the crossover operation, this embodiment of the invention employs a multi-point crossover method, randomly selecting multiple crossover points for feature mixing to generate new individuals. Compared to single-point crossover, this method produces more diverse individuals, enhancing the genetic diversity of the population. In the mutation operation, this embodiment of the invention uses a combination of random mutation and purposeful mutation. For individuals with high fitness, a small-scale random mutation is used to maintain their superior traits; for individuals with low fitness, a larger-scale mutation is introduced to increase their chances of exploring new solutions.

[0084] In each iteration, the fitness evaluation in this embodiment of the invention is more flexible. In addition to evaluating fixed target values, a dynamic fitness correction mechanism is introduced. By providing real-time feedback on changes in current light and color indices, the fitness function can adjust the weights of each target in a timely manner to quickly adapt to changes in the light and color requirements of the current environment. This dynamic correction mechanism ensures that the algorithm can maintain its optimization performance even when faced with changes that may occur in practical applications.

[0085] The iterative process of this invention continues until a preset number of iterations is reached or the population fitness stabilizes. Finally, the optimal individual in each generation is selected to determine the final output of the PWM combination. This PWM combination should ensure that the LED luminaire's color performance meets predetermined standards at color temperatures of 5000K, 4000K, 3000K, and 2000K. Specifically, in terms of color rendering index (CRI), both CRI Ra and CRI R9 are greater than 90; in terms of color coordinates, SDCM is less than a set threshold; and in terms of power consumption, it is controlled within a reasonable range.

[0086] It should be noted that the embodiments of this invention demonstrate the flexibility and scalability of the light and color control algorithm. In these embodiments, the user-customizable light and color preference settings not only improve the ability to meet personalized control needs but also enhance market competitiveness. The ability to adjust and optimize objectives based on user feedback and actual needs ensures that this invention can achieve optimal light and color performance in different application scenarios.

[0087] This invention, through the adoption of a series of innovative technologies such as an improved multi-objective fitness function, a non-dominated sorting genetic algorithm, and a dynamic fitness correction mechanism, effectively enhances the efficiency and accuracy of color temperature control in phosphorless multi-color LED lamps. Through flexible algorithm design, this invention not only ensures that the color temperature indicators of LED lamps meet the expected requirements at different color temperatures, but also adapts to constantly changing market demands and personalized user requirements, demonstrating promising application prospects.

[0088] Example 4

[0089] Please see Figure 2 , Figure 2 This is a structural block diagram of an LED multi-color control system based on a multi-objective evolutionary algorithm, provided in Embodiment 4 of the present invention. This LED multi-color control system 200 based on the multi-objective evolutionary algorithm is used to implement the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the apparatus described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0090] Specifically, the LED multi-color control system 200 based on a multi-objective evolutionary algorithm includes: a data acquisition module 21, a calculation module 22, an optimization module 23, and an output module 24, wherein:

[0091] The acquisition module 21 is used to acquire spectral data and electrical power data of the LED lamp under different PWM values, and to smooth the spectral data using cubic spline interpolation. A preset fitting function is used to process the electrical power data. The calculation formula for the cubic spline interpolation is as follows:

[0092]

[0093] in, It is the input value of the PWM combination. This is the corresponding spectral output. , , , The first Interpolation coefficients for each sampling point For the first The PWM value at each sampling point;

[0094] Calculation module 22 is used to calculate the light color index corresponding to each PWM combination. The light color index includes at least color coordinates, color rendering index, color temperature, SDCM value and power consumption. The color rendering index includes color rendering index Ra and color rendering index R9.

[0095] Optimization module 23 is used to randomly generate an initial population, where each individual represents a PWM combination. The population evolves using a multi-objective evolutionary algorithm, which optimizes the population step-by-step through selection, crossover, and mutation operations in a genetic algorithm. Specifically, in the selection operation, a roulette wheel selection strategy is used to select target individuals for the next generation; in the crossover operation, a single-point crossover method is used to cross the PWM combinations of two parent individuals to generate new offspring individuals; in the mutation operation, a dynamic mutation rate adjustment mechanism is used to introduce random perturbations to increase population diversity. The multi-objective evolutionary algorithm is a combination of a genetic algorithm and a non-dominated sorting algorithm. By performing multi-objective optimization on the initial population, the optimal balance between light color index and power consumption is gradually selected to ensure that the final output PWM combination performs well in all light color indexes. The evaluation function of the multi-objective evolutionary algorithm considers color coordinates, color rendering index, color temperature, SDCM value, and power consumption. The evaluation function comprehensively calculates each index using weighting coefficients. The weighting coefficients are adjusted according to specific application requirements to achieve optimized light color control in different scenarios. A weighted multi-objective fitness function is used in the design of the evaluation function. Specifically, the calculation formula of the weighted multi-objective fitness function is as follows:

[0096]

[0097] in, Indicates the fitness of color coordinates. The colorimetric index Ra and colorimetric index R9 represent the fitness of the individual. Indicates the suitability of color temperature. Indicates the fitness of electrical power consumption. Indicates the fitness of the SDCM value. , , , , The weighting coefficients for each indicator, the color rendering index Ra and color rendering index R9 are calculated based on the CIE colorimetric standard, and a dynamic weighting adjustment method is used to correct the color rendering index score of each evolutionary individual in real time, so as to improve the color reproduction of the final generated PWM combination in practical applications. The calculation formula of the dynamic mutation rate adjustment mechanism is as follows:

[0098]

[0099] in, This indicates the genetic algorithm in the th... The probability of performing a mutation operation. For the current generation, To adjust the constant of the rate, This is the convergence point of the algorithm;

[0100] The output module 24 is used to output a target PWM combination when all light and color indicators meet the preset requirements. The target PWM combination is used to control the LED lamps.

[0101] Example 5

[0102] In another aspect, the present invention also proposes an electronic device, please refer to [link to relevant documentation]. Figure 3 The image shows an electronic device according to Embodiment 5 of the present invention, including a memory 20, a processor 10, and a computer program 30 stored in the memory and executable on the processor. When the processor 10 executes the computer program 30, it implements the LED multi-color control method based on the multi-objective evolutionary algorithm as described above.

[0103] In some embodiments, the processor 10 may be a central processing unit (CPU), controller, microcontroller, microprocessor or other data processing chip, used to run program code stored in memory 20 or process data, such as executing access restriction programs.

[0104] The memory 20 includes at least one type of readable storage medium, such as flash memory, hard disk, multimedia card, card-type memory (e.g., SD or DX memory), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 20 can be an internal storage unit of an electronic device, such as the hard disk of the electronic device. In other embodiments, the memory 20 can also be an external storage device of the electronic device, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc. Furthermore, the memory 20 can include both internal and external storage units of the electronic device. The memory 20 can be used not only to store application software and various types of data of the electronic device, but also to temporarily store data that has been output or will be output.

[0105] It should be pointed out that, Figure 3 The structure shown does not constitute a limitation on the electronic device. In other embodiments, the electronic device may include fewer or more components than shown, or combine certain components, or have different component arrangements.

[0106] This invention also proposes a computer-readable storage medium storing a computer program that, when executed by a processor, implements the LED multicolor modulation method based on a multi-objective evolutionary algorithm as described above.

[0107] Those skilled in the art will understand that the logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as a ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can mean any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0108] More specific examples of computer-readable media (a non-exhaustive list) include: electrical connections (electronic devices) having one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which the program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0109] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0110] In the description of this specification, references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0111] The above embodiments merely illustrate several implementation methods of the present invention, and their descriptions are relatively specific and detailed, but they should not be construed as limiting the scope of the present invention. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these all fall within the protection scope of the present invention. Therefore, the protection scope of this patent should be determined by the appended claims.

Claims

1. A method for controlling multiple colors of LEDs based on a multi-objective evolutionary algorithm, characterized in that, The method includes: Collect spectral and electrical power data of LED lights under different PWM values; The spectral data were smoothed using cubic spline interpolation. The power data is then processed through a fitting function to establish a four-channel power estimation model. The power estimation model uses the PWM values ​​of the four RGBA channels as independent variables to output the power. An initial population is randomly generated, where each individual represents a PWM combination. The population is then evolved using a multi-objective evolutionary algorithm, specifically through selection, crossover, and mutation operations within the genetic algorithm to progressively optimize the population. In the selection process, a roulette wheel selection strategy is adopted to select target individuals for the next generation. Each PWM combination represents an LED spectral output. The spectral data corresponding to each PWM combination is found by cubic spline interpolation, and the colorimetric index corresponding to each PWM combination is calculated. The fitness of individuals corresponding to each PWM combination is evaluated. Individuals with high evaluation values ​​are retained, while individuals with low fitness are gradually eliminated. The colorimetric index includes at least color coordinates, color rendering index, color temperature, SDCM value, and power consumption. The color rendering index includes color rendering index Ra and color rendering index R9. In the crossover operation, the single-point crossover method is used to crossover the PWM combination of two parent individuals to generate a new child individual, that is, to generate a new PWM combination by crossing the characteristics of different PWM combinations. In the mutation operation, a dynamic mutation rate adjustment mechanism is used to introduce random perturbations, i.e., by randomly changing certain PWM values, to increase the diversity of the population. By providing real-time feedback on changes in current light and color indicators, the fitness function can adjust the weights of each objective in a timely manner. When all color and light indicators meet the preset requirements, a target PWM combination is output. This target PWM combination is used to control the LED lighting fixture. Each color and light indicator corresponds to an independent evaluation function. The color coordinate evaluation function determines the fitness by calculating the Euclidean distance between the LED color and the target color coordinate under the current PWM combination. The SDCM value evaluation function uses a set threshold to ensure that the highest score is given when the SDCM value is less than the set value. The color rendering index Ra and color rendering index R9 evaluation functions are based on set numerical requirements. As long as this requirement is met, the fitness score is the highest. For the power consumption evaluation function, a target power range is set. As long as the power under the PWM combination falls within this range, it is considered to meet the requirements and obtains the corresponding score. The outputs of all evaluation functions are weighted and combined. The calculation formula for the cubic spline interpolation method is as follows: in, It is the input value of the PWM combination. This is the corresponding spectral output. , , , The first Interpolation coefficients for each sampling point For the first The PWM value at each sampling point; The evaluation function of the multi-objective evolutionary algorithm takes into account color coordinates, color rendering index, color temperature, SDCM value and power consumption. The evaluation function performs a comprehensive calculation on each index through weighting coefficients. The color rendering index Ra and color rendering index R9 are calculated based on the CIE colorimetric standard and a dynamic weight adjustment method is used to correct the color rendering index score of each evolutionary individual in real time, so as to improve the color reproduction of the final generated PWM combination in practical applications.

2. The LED multi-color modulation method based on multi-objective evolutionary algorithm according to claim 1, characterized in that, The multi-objective evolutionary algorithm is a combination of genetic algorithm and non-dominated sorting algorithm. By performing multi-objective optimization on the initial population, it gradually selects the optimal balance point between light color index and power consumption.

3. The LED multi-color modulation method based on a multi-objective evolutionary algorithm according to claim 2, characterized in that, In the design of the evaluation function, a weighted multi-objective fitness function was adopted. Specifically, the calculation formula of the weighted multi-objective fitness function is as follows: in, Indicates the fitness of color coordinates. The colorimetric index Ra and colorimetric index R9 represent the fitness of the individual. Indicates the suitability of color temperature. Indicates the fitness of electrical power consumption. Indicates the fitness of the SDCM value. , , , , These are the weighting coefficients for each indicator.

4. The LED multi-color modulation method based on a multi-objective evolutionary algorithm according to claim 1, characterized in that, The calculation formula for the dynamic mutation rate adjustment mechanism is as follows: in, This indicates the genetic algorithm in the th... The probability of performing a mutation operation. For the current generation, To adjust the constant of the rate, This is the convergence point of the algorithm.

5. An LED multi-color control system based on a multi-objective evolutionary algorithm, characterized in that, The system is used to implement the LED multicolor modulation method based on a multi-objective evolutionary algorithm as described in any one of claims 1-4, the system comprising: The acquisition module is used to acquire spectral data and electrical power data of LED lamps under different PWM values, and to smooth the spectral data using cubic spline interpolation. The electrical power data is processed by a fitting function to establish a four-channel power estimation model. The power estimation model is based on the PWM values ​​of the four RGBA channels as independent variables and outputs the electrical power. The calculation module is used to calculate the light color index corresponding to each PWM combination. The light color index includes at least color coordinates, color rendering index, color temperature, SDCM value and power consumption. The color rendering index includes color rendering index Ra and color rendering index R9. The optimization module randomly generates the initial population, where each individual represents a PWM combination. The population evolves using a multi-objective evolutionary algorithm, employing selection, crossover, and mutation operations within a genetic algorithm to progressively optimize the population. Specifically, in the selection operation, a roulette wheel selection strategy is used to select target individuals for the next generation. Each PWM combination represents an LED spectral output. Cubic spline interpolation is used to find the spectral data corresponding to each PWM combination, and the corresponding colorimetric index is calculated. The fitness of individuals corresponding to each PWM combination is evaluated; individuals with high fitness are retained, while those with low fitness are gradually eliminated. In the crossover operation, a single-point crossover method is used to crossover the PWM combinations of two parent individuals to generate new offspring individuals; that is, new PWM combinations are generated by crossover based on the characteristics of different PWM combinations. In the mutation operation, a dynamic mutation rate adjustment mechanism is used to introduce random perturbations, i.e., by randomly changing certain PWM values, to increase the diversity of the population. The output module provides real-time feedback on changes in current color and light indicators. The fitness function adjusts the weights of each objective in a timely manner. When all color and light indicators meet preset requirements, a target PWM combination is output. This target PWM combination is used to control LED lights. Each color and light indicator corresponds to an independent evaluation function. The color coordinate evaluation function determines the fitness by calculating the Euclidean distance between the LED color and the target color coordinates under the current PWM combination. The SDCM value evaluation function uses a set threshold to ensure that the highest score is given when the SDCM value is less than the set value. The color rendering index Ra and color rendering index R9 evaluation functions are based on set numerical requirements; as long as these requirements are met, the fitness score is the highest. For the power consumption evaluation function, a target power range is set. As long as the power under the PWM combination falls within this range, it is considered to meet the requirements and receives the corresponding score. By weighting and summing the outputs of all evaluation functions, it is ensured that each color and light indicator is fully considered during the optimization process.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by the processor, the program implements the LED multi-color control method based on the multi-objective evolutionary algorithm as described in any one of claims 1-4.

7. An electronic device, characterized in that, It includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the LED multicolor modulation method based on a multi-objective evolutionary algorithm as described in any one of claims 1-4.

Images