A whitening light adaptive adjustment control method based on user skin condition

Abstract

The present invention relates to a whitening light adaptive adjustment control method based on the user's skin state, and belongs to the technical field of optical instruments. The method includes the following steps: initially setting control parameters: selecting light control parameters according to the collected skin state parameters; determining dimming parameters: selecting input pulses and duty cycles according to the initially set light intensity according to the temperature rise combination relationship table; measuring state values: when operating with the determined dimming parameters, detecting the luminous flux and calculating the luminous efficiency, inputting the luminous efficiency into the constructed junction temperature prediction model, and predicting the junction temperature value; correcting dimming parameters: setting the junction temperature threshold according to the constructed variable temperature spectrum, and reselecting the input pulse and duty cycle combination when the predicted junction temperature value is greater than the junction temperature threshold; the present invention provides a dimming parameter combination through the temperature rise combination relationship table, realizes the refined control of light output, and dynamically and adaptively adjusts the dimming parameters by monitoring the changes in junction temperature during operation, thereby improving the stability of the output spectrum.

Description

Technical Field

[0001] The present invention belongs to the technical field of optical instruments, and in particular relates to a whitening illumination adaptive adjustment control method based on a user's skin condition. Background Art

[0002] LED has shown great application value in the medical field due to its excellent characteristics. In the phototherapy research of cardiovascular diseases, red light LED has a good effect. Phototherapy has gradually been widely used in clinical medicine such as skin diseases due to its many advantages such as few adverse reactions, no drug resistance, no trauma, and no pollution.

[0003] In the study of LED phototherapy, it is often necessary to conduct irradiation experiments with different light intensities in order to study the lighting parameters for the best treatment effect. At the same time, due to the different penetration depths of different wavelengths in the skin, it is necessary to select light waves of different wavelengths. However, the current LED skin phototherapy devices have selectable wavelengths and few adjustable intensity options. There is a one-size-fits-all light output that cannot match the user's skin condition well, and there are few adjustable parameters, resulting in average phototherapy effects or over-treatment. At the same time, there is a lack of dynamic feedback mechanism during the phototherapy process, and it cannot adaptively adjust to cope with changes in the state of the instrument during operation, resulting in a deviation between the actual light output and the set value.

[0004] Therefore, there is an urgent need to provide a whitening light adaptive adjustment control method based on the user's skin condition, which can achieve matching light output by setting a fine combination of dimming parameters; at the same time, dynamically adjust the light parameters according to the feedback results during the phototherapy process to ensure the consistency of output control, ensure the phototherapy effect, and improve the comfort and safety of the phototherapy process. Summary of the invention

[0005] In order to solve the above-mentioned problems existing in the prior art, the present invention provides a whitening light adaptive adjustment control method based on the user's skin condition, provides a dimming parameter combination through the temperature rise combination relationship table, realizes the refined control of the light output, and dynamically and adaptively adjusts the dimming parameters by monitoring the changes in junction temperature during operation, thereby improving the output spectrum stability.

[0006] The purpose of the present invention can be achieved through the following technical solutions:

[0007] The present disclosure provides a whitening light adaptive adjustment control method based on the user's skin condition, comprising the following steps:

[0008] Initial setting of control parameters: According to the collected skin condition parameters, select the light control parameters, including wavelength, duration and light intensity;

[0009] Determine dimming parameters: select input pulse and duty cycle according to the temperature rise combination relationship table based on the initially set light intensity;

[0010] Predicted state value: When operating with the determined dimming parameters, the luminous flux is detected and the luminous efficiency is calculated. The luminous efficiency is input into the constructed LED junction temperature prediction model to predict the LED junction temperature value;

[0011] Correct dimming parameters: Set the junction temperature threshold according to the constructed variable temperature spectrum. When the predicted LED junction temperature value is greater than the junction temperature threshold, reselect the input pulse and duty cycle combination.

[0012] The temperature rise combination relationship table includes parameter combinations of the "light intensity-input pulse-duty cycle" mode; the variable temperature spectrum includes LED spectrum curves of different junction temperatures under the condition of the same input pulse.

[0013] Furthermore, the construction of the temperature rise combination relationship table includes the following steps:

[0014] According to the input pulse range of the LED, set the step value, and measure the light intensity corresponding to different duty cycles under each input pulse in turn;

[0015] Change the input pulse, repeat the above steps, record the data and draw the relationship curve, and establish the relationship model between the duty cycle and the light intensity under each input pulse;

[0016] According to the input pulse range of LED, select the average input pulse of LED, set the step value, establish the combination of LED input pulse and PWM signal duty cycle under different average pulses, detect the temperature rise of LED under different duty cycle and input pulse combinations and draw curves;

[0017] Specifically, a curve is drawn according to the temperature rise of the LED under different combinations of duty cycles and input pulses, with time as the horizontal axis and temperature as the vertical axis, to draw a temperature rise curve of the combination of the LED input pulse and the PWM signal duty cycle.

[0018] Furthermore, the construction of the temperature rise combination relationship table further includes the steps of:

[0019] According to the LED temperature rise curve under different duty cycle and input pulse combinations, the combination of PWM dimming duty cycle and input pulse with minimum temperature rise is screened out;

[0020] According to the selected minimum temperature rise combination of duty cycle and pulse, corresponding to the size of the input pulse, the light intensity is matched according to the relationship model between duty cycle and light intensity under the input pulse, and a temperature rise combination relationship table of the "light intensity-input pulse-duty cycle" mode is constructed.

[0021] Furthermore, the correction of the dimming parameters comprises the following steps:

[0022] Construct variable temperature spectrum: Test the LED spectrum under the same constant current and different junction temperature conditions. According to the input pulse in the temperature rise combination relationship table, obtain the LED spectrum under different junction temperatures under the same input pulse condition and establish the variable temperature spectrum.

[0023] Set the junction temperature threshold: according to the light control wavelength requirements and deviation, and based on the temperature spectrum, set the junction temperature threshold for triggering regulation;

[0024] Select dimming parameters: When the predicted LED junction temperature value is greater than the junction temperature threshold, return to step "Determine dimming parameters" and reselect dimming parameters. Select a new combination of input pulses and duty cycle based on the strategy of lowest power consumption with constant light intensity.

[0025] Furthermore, before the step of initially setting the control parameters, the following steps are also included:

[0026] Collect skin data: Use a high-precision skin analyzer to collect the user's skin physiological parameter measurement indicators and build a complete skin condition parameter.

[0027] Furthermore, the skin physiological parameter measurement indicators include skin chromaticity, transepidermal water loss, stratum corneum water content, sebum content, skin surface pH value, melanin index and erythema index.

[0028] Furthermore, after the step of determining the dimming parameters, the step of:

[0029] Control drive operation: Input the selected input pulse and duty cycle into the drive circuit to complete the dimming of the target light wave, where the drive circuit adopts a switch-type constant current source architecture, including:

[0030] The power circuit of the BUCK step-down topology controls the switching frequency and duty cycle of the MOSFET in the power circuit through PWM dimming; the pulse is sampled through the feedback circuit and the output is stabilized. After analog-to-digital conversion, the microcontroller unit calculates the actual pulse value. When a change in the pulse is detected, the PWM dimming circuit is adjusted through the MCU to change the switching duty cycle and the output voltage, thereby changing the output pulse.

[0031] Furthermore, after the control driving operation step, the step of:

[0032] Physiological data feedback: By setting up sensors to monitor changes in the skin's response to light, including skin temperature, erythema index and moisture content, the light intensity is adjusted in time according to the preset safety threshold and an alarm is issued.

[0033] Furthermore, the construction of the LED junction temperature prediction model includes the following steps:

[0034] Establish a data set: place the LED to be tested on a constant temperature heat sink, set the initial temperature, maintain it for a period of time, and collect temperature values; select a driving pulse to light up the LED, measure the luminous flux and calculate the luminous efficiency;

[0035] Change the temperature of the constant temperature heat sink, repeat the above steps, calculate the luminous efficiency of the LED to be tested corresponding to different junction temperatures, and construct a data set of luminous efficiency-LED junction temperature;

[0036] Build the model: determine the number of neurons in the hidden layer, determine the range through empirical formulas, and then conduct experiments one by one to find the optimal value;

[0037] Model training: With light efficiency as input and junction temperature as output, the data under fixed driving pulses are allocated as training set, validation set, and test set in a ratio of 70%, 15%, and 15%;

[0038] Select the Levenberg-Marquardt algorithm, set the learning rate to 0.1, determine the target accuracy and the maximum number of iterations, and conduct training; complete the model training when the number of iterations of the training process and the mean square error reach the minimum value;

[0039] Junction temperature prediction: The luminous efficiency of the LED during normal operation is imported into the LED junction temperature prediction model to obtain the LED junction temperature value.

[0040] Furthermore, the empirical formula is:

[0041] ;

[0042] In the formula, h , m , n are the number of neurons in the hidden layer, input layer, and output layer, respectively. a is a constant ranging from 1 to 10.

[0043] The beneficial effects of the present invention are:

[0044] The present invention provides illumination control parameters based on user skin parameters, obtains dimming parameter combinations based on illumination control parameters according to the temperature rise combination relationship table, wherein the temperature rise combination relationship table provides a large number of dimming parameter combinations for dimming control, improves the refined control of dimming, realizes targeted illumination output, and avoids ineffective or excessive treatment that may be caused by one-size-fits-all illumination output. At the same time, by monitoring the feedback of the user's skin state and the change of LED junction temperature during operation, the dimming parameters are dynamically adjusted to ensure the wavelength and illumination consistency of the light wave during operation, thereby improving the comfort and safety of phototherapy.

[0045] The temperature rise combination relationship table created by the present invention is based on the selected LED light source. By setting the step value, the matching of light intensity-input pulse-duty cycle is tested, and dimming parameter selection is provided for different lighting requirements, thereby improving the accuracy and personalization of dimming. Secondly, based on the temperature rise curve of the LED, the best duty cycle and pulse temperature rise combination is further screened out, and the means of controlling the junction temperature is introduced from the root, thereby reducing the spectral deviation caused by the temperature rise problem. At the same time, during the operation, the junction temperature is predicted, and the dimming parameters are changed based on the set threshold value, thereby further ensuring the stability of the spectrum during phototherapy. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to facilitate understanding by those skilled in the art, the present invention is further described below with reference to the accompanying drawings.

[0047] Figure 1 A schematic diagram of the steps of a whitening light adaptive adjustment control method based on the user's skin condition provided by an embodiment of the present invention;

[0048] Figure 2 A schematic diagram of steps for establishing a temperature rise combination relationship table provided in an embodiment of the present invention;

[0049] Figure 3 A schematic diagram of the structure of a driving circuit provided by an embodiment of the present invention;

[0050] Figure 4 A schematic diagram of steps for constructing an LED junction temperature prediction model provided by an embodiment of the present invention;

[0051] Figure 5 A schematic diagram of steps for correcting dimming parameters provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0052] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the specific implementation methods, structures, features and effects of the present invention are described in detail below in conjunction with the accompanying drawings and preferred embodiments.

[0053] As an incoherent monochromatic light, LED light can achieve the same biostimulation effect as laser light at the same wavelength and other conditions. The penetration depth of LED light at different wavelengths in the skin is also different. The red light with a long wavelength of 630nm to 700nm can be used to treat deeper skin tissues, while the blue light with a wavelength of 400nm to 470nm is generally used for epidermal treatment. The monochromatic light with a wavelength of 660nm can act on deeper skin layers and can penetrate into and act on the skin fibroblasts in the dermis.

[0054] Therefore, the present application selects a combination of multi-band light sources, selects the most suitable wavelength based on the user's skin parameters, and realizes personalized and refined control of light output through pulse width modulation (PWM) and analog parallel hybrid dimming, and performs adaptive adjustment based on operating status values ​​and physiological data feedback, thereby providing users with the best light therapy effect.

[0055] This embodiment provides a whitening light adaptive adjustment control method based on the user's skin condition. Figure 1 As shown, the following steps are included:

[0056] S1. Collect skin data: Use a high-precision skin analyzer to collect the user's skin physiological parameter measurement indicators and build a complete skin condition parameter;

[0057] It should be noted that the collection process steps are as follows:

[0058] The test was carried out under constant temperature and humidity conditions, with a temperature of (22±1)℃ and a humidity of (41.5±0.5)%. The test subjects entered the test environment 30 minutes in advance and waited quietly for the test. The test site was exposed 10 minutes before the measurement. Each parameter was measured three times in a row and the average value was taken to reduce the measurement error.

[0059] The test areas of the subjects were marked, and a high-precision skin analyzer was used to measure indicators including skin color, transepidermal water loss, stratum corneum water content, sebum content, skin surface pH value, melanin index, and erythema index.

[0060] S2. Initial setting of control parameters: According to the collected skin condition parameters, select the light control parameters, including wavelength, duration and light intensity.

[0061] It is understandable that the depth of skin that light waves can penetrate is related to the wavelength of the light waves. The longer the wavelength of the light wave, that is, the lower the frequency, the deeper it can penetrate the skin. Light energy of different wavelengths can activate cell activity, promote blood circulation, accelerate metabolism, produce important biological effects on the body and skin, and achieve therapeutic and repair effects. The corresponding band, duration and light intensity are selected according to the effects of different wavelengths on the skin through the collected skin parameters.

[0062] Specifically, clarify the effect you want to achieve through light therapy, such as increasing collagen, reducing inflammation or reducing pigmentation; select the appropriate light wavelength according to the skin problem. For example, blue light (415nm) is often used to treat acne, red light (630nm-660nm) is used to reduce fine lines and wrinkles, and near-infrared light (850nm) is used for deep tissue repair; set the duration of light treatment for each treatment according to the target effect and skin tolerance. Usually, the treatment time ranges from a few minutes to tens of minutes; set the intensity of light (usually in mW / cm²) to avoid skin damage caused by excessive intensity through real-time feedback of skin status.

[0063] S3. Determine dimming parameters: Select input pulse and duty cycle according to the temperature rise combination relationship table based on the initial light intensity, where the temperature rise combination relationship table is obtained through test modeling, such as Figure 2 As shown, the following steps are included:

[0064] S31, setting the step value according to the input pulse range of the LED, and measuring the light intensity corresponding to different duty cycles under each input pulse in turn;

[0065] It should be noted that the increase of input pulse will increase the temperature rise of LED, thus reducing the LED light efficiency and causing the attenuation of light. Therefore, the LED driving pulse should be reasonably selected. Under the premise of meeting the light intensity, it is necessary to choose a small pulse as much as possible to reduce the temperature rise. By testing the irradiance under different pulse driving, when the driving pulse increases and the irradiance begins to decrease, the pulse value at this time is used as the reference value for determining the upper limit of the input range.

[0066] S32, changing the input pulse, repeating the above steps, recording the data and drawing a relationship curve, and establishing a relationship model between the duty cycle and the light intensity under each input pulse;

[0067] S33, according to the input pulse range of the LED, select the average input pulse of the LED, set the step value, establish the combination of the LED input pulse and the PWM signal duty cycle under different average pulses, detect the LED temperature rise under different duty cycle and input pulse combinations and draw a curve;

[0068] Specifically, a curve is drawn according to the temperature rise of the LED under different combinations of duty cycles and input pulses, with time as the horizontal axis and temperature as the vertical axis, to draw a temperature rise curve of the combination of the LED input pulse and the PWM signal duty cycle.

[0069] S34, according to the LED temperature rise curves under different duty cycle and input pulse combinations, screen out the PWM dimming duty cycle and input pulse minimum temperature rise combination;

[0070] S35. Based on the selected minimum temperature rise combination of duty cycle and pulse, corresponding to the size of the input pulse, the light intensity is matched according to the relationship model between duty cycle and light intensity under the input pulse, and a temperature rise combination relationship table of the "light intensity-input pulse-duty cycle" mode is constructed.

[0071] It is understandable that by setting the step value in the above manner, a large number of dimming parameter combinations are obtained to meet the refined selection of light intensity and wavelength, and then by screening the input pulse and duty cycle combination that meets the light intensity, the LED temperature rise condition is added to the LED PWM and analog parallel hybrid dimming in the initial state, thereby promoting the reduction of temperature rise and meeting the refined dimming. In this embodiment, hybrid dimming is used to achieve the regulation of light.

[0072] S4, control driving operation: input the selected input pulse and duty cycle into the driving circuit to complete the dimming of the target light wave, wherein the driving circuit adopts a switch-type constant current source architecture, such as Figure 3 As shown, including:

[0073] The power circuit of the BUCK step-down topology controls the switching frequency and duty cycle of the MOSFET in the power circuit through PWM dimming. At the same time, the pulse is sampled through the feedback circuit to stabilize the output. After analog-to-digital conversion, the microcontrol unit (MCU) calculates the actual pulse value. When a change in the pulse is detected, the PWM dimming circuit is adjusted through the MCU, thereby changing the switching duty cycle and adjusting the output voltage, thereby changing the output pulse.

[0074] It should be noted that the circuit of the dimming process generally includes a control circuit and a drive circuit. The two parts of the circuit communicate through an asynchronous serial port to isolate the high-power drive circuit from the low-power control circuit, which is convenient for controlling the selection of light wavelength and light energy and realizing free combination of parameters.

[0075] S5. Physiological data feedback: By setting up sensors to monitor changes in the skin's response to light, including skin temperature, erythema index and moisture content, the light intensity is adjusted in time according to the preset safety threshold and an alarm is issued.

[0076] It is understandable that in order to ensure the best whitening effect during phototherapy and avoid possible damage caused by excessive exposure, the skin's response is continuously monitored through built-in sensors, such as using infrared temperature sensors or thermocouples to measure temperature changes on the skin surface, using optical sensors or cameras combined with image processing technology to measure the degree of skin erythema, and using capacitive or impedance moisture sensors to measure the moisture content of the skin; by setting safety thresholds, including temperature thresholds, erythema index thresholds, and moisture content thresholds, safety measures are triggered, such as stopping light exposure and sounding alarms to remind users to perform skin care.

[0077] S6. Predicting state value: When operating with the determined dimming parameters, detect the luminous flux and calculate the luminous efficiency, input the luminous efficiency into the constructed LED junction temperature prediction model, and predict the LED junction temperature value. The construction of the LED junction temperature prediction model is as follows: Figure 4 As shown, the following steps are included:

[0078] S61, establishing a data set: placing the LED to be tested on a constant temperature heat sink, setting an initial temperature, and maintaining it for a period of time to ensure sufficient heat exchange between the LED and the constant temperature heat sink;

[0079] Select a driving pulse to light up the LED, measure the luminous flux and calculate the luminous efficiency; change the temperature of the constant temperature heat sink, repeat the above steps, calculate the luminous efficiency of the LED to be tested corresponding to different junction temperatures, and construct a data set of luminous efficiency-LED junction temperature.

[0080] It is understandable that the size of the temperature interval is adjusted according to the amount of data required, and the BP neural network LED junction temperature prediction model is constructed using the junction temperature and luminous efficiency data obtained from the experiment.

[0081] S62. Build the model: Determine the number of neurons in the hidden layer. If the number of neurons in the hidden layer is too small, the accuracy of each training will be too low, and multiple trainings will be required; if the number is too large, overfitting may occur. Currently, there is no method to accurately calculate the number of neurons in the hidden layer. We can only determine the approximate range through empirical formulas, and then conduct experiments one by one to find the best value. The empirical formula is:

[0082] ;

[0083] In the formula, h , m , n are the number of neurons in the hidden layer, input layer, and output layer, respectively. a is a constant ranging from 1 to 10.

[0084] It can be understood that the BP neural network is a multi-layer feedforward network trained according to the error back propagation algorithm. It can approximate any function with arbitrary accuracy without the need for complex mathematical models and is suitable for data prediction.

[0085] S63, model training: with light efficiency as input and junction temperature as output, the data under fixed driving pulses are allocated into training set, validation set and test set in the ratio of 70%, 15% and 15% respectively;

[0086] Select the Levenberg-Marquardt algorithm, which provides a faster convergence speed;

[0087] Set the learning rate to 0.1, determine the target accuracy and maximum number of iterations, and perform training.

[0088] The Levenberg-Marquardt algorithm (LM algorithm for short) is a numerical optimization method for nonlinear least squares problems, especially suitable for fitting data or solving nonlinear parameter estimation problems. By iteratively optimizing parameters, the predicted value of the nonlinear function is made as close as possible to the actual observed value. It combines the advantages of the steepest descent method and the Gauss-Newton method and can effectively handle various types of nonlinear minimization problems.

[0089] When the number of iterations of the training process and the mean square error reach the minimum value, the target accuracy is met and the convergence speed is fast, and the model training is completed.

[0090] In this embodiment, according to the functional relationship between luminous efficiency and junction temperature, which changes from the original linear relationship to an approximate exponential relationship when a certain temperature is reached, an LED junction temperature prediction method based on luminous efficiency and BP neural network is proposed. The BP neural network can approximate the characteristic of any function with arbitrary precision, measure the luminous efficiency and junction temperature data, fit the functional relationship between the two, and construct a junction temperature prediction model, thereby providing accurate data for monitoring the spectral shift affected by junction temperature changes.

[0091] S64, junction temperature prediction: import the luminous efficiency of the LED during normal operation into the LED junction temperature prediction model to obtain the LED junction temperature value.

[0092] It is understandable that by constructing an LED junction temperature prediction model, the characteristics of any function can be approximated with arbitrary precision. A large amount of light efficiency and junction temperature data can be collected through experiments to establish a junction temperature prediction model, which can achieve accurate prediction of LED junction temperature, provide a basis for LED dimming parameters, and make effective decisions.

[0093] S7, modify dimming parameters: set the junction temperature threshold according to the constructed variable temperature spectrum. When the predicted LED junction temperature value is greater than the junction temperature threshold, reselect the input pulse and duty cycle combination, such as Figure 5 As shown, the following steps are included:

[0094] S71. Construct a variable temperature spectrum: Test the LED spectrum under the same constant current and different junction temperatures. According to the input pulse in the temperature rise combination relationship table, obtain the LED spectrum at different junction temperatures under the same input pulse condition to establish a variable temperature spectrum.

[0095] As a semiconductor material, the carrier concentration of LED has a great influence on the photoelectric characteristics of LED to a certain extent. In addition, the carrier concentration of semiconductor materials is not only related to its own materials and doping, but also the temperature of the material has a significant impact on the carrier concentration. Through testing, it is found that with the increase of temperature, the output spectrum curve continues to move downward, that is, the overall intensity of the light wave decreases with the increase of temperature, and the peak wavelength is red-shifted. In addition, in the band near the peak wavelength, as the temperature increases, the light wave energy spectrum in the short-wave direction of the peak wavelength increases, while the long-wave direction decreases.

[0096] Therefore, in this embodiment, by constructing the variable temperature spectrum of the LED, the data of the spectrum peak movement is obtained to provide a basis for setting the junction temperature threshold, so as to timely adjust the problems of the semiconductor band contraction, spectrum red shift, center wavelength change and half-width reduction caused by the increase of junction temperature. The above method provides support for ensuring the stability of the phototherapy spectrum.

[0097] S72, setting the junction temperature threshold: according to the light control wavelength requirement and the deviation, and based on the variable temperature spectrum, setting the junction temperature threshold for triggering regulation.

[0098] It should be noted that in the actual application process, the equipment is usually equipped with a cooling system. Therefore, even if the trigger mechanism for controlling parameter adjustment is set by the junction temperature threshold in this embodiment, it will not cause frequent changes in the control parameters. In the specific application process, it is necessary to combine the equipped cooling system, the electrical parameters of the light source and the variable temperature spectrum to test and obtain the optimal junction temperature threshold, so as to ensure the stability of the spectrum and control the spectral red shift caused by the junction temperature change within an acceptable deviation range without affecting the stability of the system.

[0099] S73, select dimming parameters: when the predicted LED junction temperature value is greater than the junction temperature threshold, return to step S3, reselect the dimming parameters, and select a new input pulse and duty cycle combination based on the strategy of keeping the light intensity constant and the power consumption lowest.

[0100] It is understandable that, under the premise of keeping the light intensity constant, the combination of input pulse and duty cycle is selected so that the pulse is as close to the efficient working range of the LED as possible. For example, a combination of low pulse and high duty cycle is selected. By optimizing the dimming parameter combination, the temperature rise of the LED is effectively reduced and the stability of the light wavelength is guaranteed. By adjusting the parameters, the wavelength and illumination consistency of the light wave are maintained, so as to customize the phototherapy plan in accordance with the skin physiological parameters collected in the early stage, and ensure the scientificity and safety of the phototherapy.

[0101] The present invention provides illumination control parameters based on user skin parameters, obtains dimming parameter combinations based on illumination control parameters according to the temperature rise combination relationship table, wherein the temperature rise combination relationship table provides a large number of dimming parameter combinations for dimming control, improves the refined control of dimming, realizes targeted illumination output, and avoids ineffective or excessive treatment that may be caused by one-size-fits-all illumination output. At the same time, by monitoring the feedback of the user's skin state and the change of LED junction temperature during operation, the dimming parameters are dynamically adjusted to ensure the wavelength and illumination consistency of the light wave during operation, thereby improving the comfort and safety of phototherapy.

[0102] The temperature rise combination relationship table created by the present invention is based on the selected LED light source. By setting the step value, the matching of light intensity-input pulse-duty cycle is tested, and dimming parameter selection is provided for different lighting requirements, thereby improving the accuracy and personalization of dimming. Secondly, based on the temperature rise curve of the LED, the best duty cycle and pulse temperature rise combination is further screened out, and the means of controlling the junction temperature is introduced from the root, thereby reducing the spectral deviation caused by the temperature rise problem. At the same time, during the operation, the junction temperature is predicted, and the dimming parameters are changed based on the set threshold value, thereby further ensuring the stability of the spectrum during phototherapy.

[0103] The above description is only a preferred embodiment of the present invention and does not limit the present invention in any form. Although the present invention has been disclosed as a preferred embodiment as above, it is not used to limit the present invention. Any technical personnel in this field can make some changes or modify the technical contents disclosed above into equivalent embodiments without departing from the scope of the technical solution of the present invention. However, any brief modifications, equivalent changes and modifications made to the above embodiments based on the technical essence of the present invention without departing from the content of the technical solution of the present invention are still within the scope of the technical solution of the present invention.

Claims

1. A whitening light adaptive adjustment control method based on the user's skin condition, characterized by: The following steps are involved: Initial setting of control parameters: According to the collected skin condition parameters, select the light control parameters, including wavelength, duration and light intensity; Determine dimming parameters: select input pulse and duty cycle according to the temperature rise combination relationship table based on the initially set light intensity; Predicted state value: When operating with the determined dimming parameters, the luminous flux is detected and the luminous efficiency is calculated. The luminous efficiency is input into the constructed LED junction temperature prediction model to predict the LED junction temperature value; Correct dimming parameters: Set the junction temperature threshold according to the constructed variable temperature spectrum. When the predicted LED junction temperature value is greater than the junction temperature threshold, reselect the input pulse and duty cycle combination. The temperature rise combination relationship table includes the parameter combination of the "light intensity-input pulse-duty cycle" mode; the variable temperature spectrum includes the LED spectrum curves of different junction temperatures under the condition of the same input pulse; The construction of the temperature rise combination relationship table includes the following steps: According to the input pulse range of the LED, set the step value, and measure the light intensity corresponding to different duty cycles under each input pulse in turn; Change the input pulse, repeat the above steps, record the data and draw the relationship curve, and establish the relationship model between the duty cycle and the light intensity under each input pulse; According to the input pulse range of LED, select the average input pulse of LED, set the step value, establish the combination of LED input pulse and PWM signal duty cycle under different average pulses, detect the temperature rise of LED under different duty cycle and input pulse combinations and draw curves; Specifically, a curve is drawn according to the temperature rise of the LED under different duty cycles and input pulse combinations, with time as the horizontal axis and temperature as the vertical axis, to draw a temperature rise curve of the combination of the LED input pulse and the PWM signal duty cycle; The construction of the temperature rise combination relationship table also includes the steps of: According to the LED temperature rise curve under different duty cycle and input pulse combinations, the combination of PWM dimming duty cycle and input pulse with minimum temperature rise is screened out; According to the selected minimum temperature rise combination of duty cycle and pulse, corresponding to the size of the input pulse, the light intensity is matched according to the relationship model between duty cycle and light intensity under the input pulse, and the temperature rise combination relationship table of the "light intensity-input pulse-duty cycle" mode is constructed; The method of correcting the dimming parameters comprises the following steps: Construct variable temperature spectrum: Test the LED spectrum under the same constant current and different junction temperature conditions. According to the input pulse in the temperature rise combination relationship table, obtain the LED spectrum under different junction temperatures under the same input pulse condition and establish the variable temperature spectrum. Set the junction temperature threshold: according to the light control wavelength requirements and deviation, and based on the temperature spectrum, set the junction temperature threshold for triggering regulation; Select dimming parameters: When the predicted LED junction temperature value is greater than the junction temperature threshold, return to step "determine dimming parameters" and reselect dimming parameters. Select a new combination of input pulses and duty cycle based on the strategy of lowest power consumption when the light intensity remains unchanged. The construction of the LED junction temperature prediction model includes the following steps: Establish a data set: place the LED to be tested on a constant temperature heat sink, set the initial temperature, maintain it for a period of time, and collect temperature values; select a driving pulse to light up the LED, measure the luminous flux and calculate the luminous efficiency; Change the temperature of the constant temperature heat sink, repeat the above steps, calculate the luminous efficiency of the LED to be tested corresponding to different junction temperatures, and construct a data set of luminous efficiency-LED junction temperature; Build the model: determine the number of neurons in the hidden layer, determine the range through empirical formulas, and then conduct experiments one by one to find the optimal value; Model training: With light efficiency as input and junction temperature as output, the data under fixed driving pulses are allocated as training set, validation set, and test set in a ratio of 70%, 15%, and 15%; Select the Levenberg-Marquardt algorithm, set the learning rate to 0.1, determine the target accuracy and the maximum number of iterations, and conduct training; complete the model training when the number of iterations of the training process and the mean square error reach the minimum value; Junction temperature prediction: The luminous efficiency of the LED during normal operation is imported into the LED junction temperature prediction model to obtain the LED junction temperature value.

2. The method for adaptively adjusting and controlling whitening illumination based on the user's skin condition according to claim 1, characterized in that: Before the step of initially setting the control parameters, the following steps are also included: Collect skin data: Use a high-precision skin analyzer to collect the user's skin physiological parameter measurement indicators and build a complete skin condition parameter.

3. The method for adaptively adjusting and controlling whitening illumination based on the user's skin condition according to claim 2, characterized in that: The skin physiological parameter measurement indicators include skin chromaticity, transepidermal water loss, stratum corneum water content, sebum content, skin surface pH value, melanin index and erythema index.

4. The method for adaptively adjusting and controlling whitening illumination based on the user's skin condition according to claim 1, characterized in that: After the step of determining the dimming parameters, the following steps are also included: Control drive operation: Input the selected input pulse and duty cycle into the drive circuit to complete the dimming of the target light wave, where the drive circuit adopts a switch-type constant current source architecture, including: The power circuit of the BUCK step-down topology controls the switching frequency and duty cycle of the MOSFET in the power circuit through PWM dimming; the pulse is sampled through the feedback circuit and the output is stabilized. After analog-to-digital conversion, the microcontroller unit calculates the actual pulse value. When a change in the pulse is detected, the PWM dimming circuit is adjusted through the MCU to change the switching duty cycle and the output voltage, thereby changing the output pulse.

5. The method for adaptively adjusting and controlling whitening illumination based on the user's skin condition according to claim 4, characterized in that: After the control driving operation step, the step further includes: Physiological data feedback: By setting up sensors to monitor changes in the skin's response to light, including skin temperature, erythema index and moisture content, the light intensity is adjusted in time according to the preset safety threshold and an alarm is issued.

6. The method for adaptively adjusting and controlling whitening illumination based on the user's skin condition according to claim 1, characterized in that: The empirical formula is: ； In the formula, h , m , n are the number of neurons in the hidden layer, input layer, and output layer, respectively. is a constant ranging from 1 to 10.

Images