High-power LED lamp bead self-adaptive dimming method and system based on intelligent driving

Abstract

The invention discloses a high-power LED lamp bead self-adaptive dimming method and system based on intelligent driving, and belongs to the technical field of illumination control, and the method comprises the steps: collecting a mode switching threshold value and factor data influencing the mode switching threshold value, and constructing a historical data set and a prediction model; periodically collecting and constructing a real-time data set; calculating according to the real-time data set to obtain a current state value; inputting the real-time data set into the prediction model to obtain a current switching threshold value; switching the current dimming mode according to the size relationship between the current state value and the current mode switching threshold value; and generating a corresponding control signal according to the current dimming mode, and sending the control signal to an LED driving circuit, thereby controlling an LED lamp bead. The mode switching threshold is predicted by adopting the neural network model, and the dimming mode is switched according to the size relationship between the current state value and the current mode switching threshold, so that the adaptive dimming of the high-power LED lamp bead can be realized, the dimming range and precision are improved, and the brightness is adaptively adjusted according to the environmental change.

Description

Technical Field

[0001] The present invention relates to the field of lighting control technology, and in particular to a high-power LED lamp bead adaptive dimming method and system based on intelligent drive. Background Art

[0002] With the continuous development of LED technology, high-power LED lamp beads have been widely used in the lighting field. However, traditional LED dimming methods often have problems such as limited dimming range, low dimming accuracy, and inability to adaptively adjust brightness according to environmental changes. These problems not only affect the lighting effect of LED lamps, but may also lead to energy waste and reduced user experience.

[0003] At present, most traditional LED dimming methods use fixed-frequency PWM (pulse width modulation) dimming or analog dimming. PWM dimming adjusts the brightness of the LED by changing the duty cycle of the LED drive signal, but fixed-frequency PWM dimming may produce obvious flickering during the dimming process, affecting the user experience. Analog dimming adjusts the brightness by changing the voltage or current of the LED drive circuit, but the dimming accuracy is relatively low and it is difficult to achieve fine brightness adjustment.

[0004] Traditional LED dimming methods often fail to adjust adaptively to environmental changes, which may result in under- or over-lighting, which not only wastes energy but may also cause discomfort to the user's eyes. Summary of the invention

[0005] To solve the above problems, the present invention provides a method and system for adaptive dimming of high-power LED lamp beads based on intelligent drive, which adopts a neural network model to predict the mode switching threshold, and switches the dimming mode according to the relationship between the current state value and the current mode switching threshold. It can realize adaptive dimming of high-power LED lamp beads, improve the dimming range and accuracy, and adaptively adjust the brightness according to environmental changes.

[0006] The above objectives can be achieved through the following solutions:

[0007] A method for adaptive dimming of high-power LED lamp beads based on intelligent drive, the method comprising: collecting mode switching thresholds and factor data affecting the mode switching thresholds to construct a historical data set; constructing and training a prediction model for predicting the mode switching thresholds based on the historical data set; periodically collecting ambient light intensity data, LED lamp bead operating temperature data, and user-set brightness requirement data to construct a real-time data set; calculating a current state value based on the real-time data set; inputting the real-time data set into the prediction model, and outputting a current switching threshold; switching the current dimming mode based on the relationship between the current state value and the current mode switching threshold; generating a corresponding control signal based on the current dimming mode and sending it to an LED drive circuit, thereby controlling the LED lamp beads; wherein the dimming modes include a high-frequency PWM dimming mode, a low-frequency PWM dimming mode, an analog dimming mode, and a mixed mode of low-frequency PWM dimming and analog dimming.

[0008] Optionally, the prediction model constructed and trained according to the historical data set to predict the mode switching value includes: establishing a neural network model including an input layer, at least one hidden layer and an output layer; setting three neurons in the input layer to receive ambient light intensity, LED lamp bead operating temperature and user-set brightness requirements as input features; setting three neurons in the output layer to output a first threshold, a second threshold and a third threshold respectively; setting an activation function, and constructing a prediction function for each neuron in the output layer according to the activation function; using the historical data set to train the neural network model to generate a stable prediction model; wherein the first threshold is less than the second threshold, and the second threshold is less than the third threshold.

[0009] Optionally, the current state value calculated according to the real-time data set includes: calculating the change rate of ambient light intensity data, LED lamp bead operating temperature data, and user-set brightness requirement data; determining whether the change rate is greater than a fourth threshold; if so, calculating the current state value according to the real-time data set; if not, maintaining the current dimming mode.

[0010] Optionally, the calculating of the current state value according to the real-time data set includes: normalizing the ambient light intensity data, the operating temperature data of the LED lamp beads, and the brightness requirement data set by the user; setting a first weight for the ambient light intensity, a second weight for the operating temperature of the LED lamp beads, and a third weight for the brightness requirement set by the user; calculating the current state value according to the first weight, the second weight, the third weight, and the normalized data, and for the current state value ,have ,

[0011] In the formula, is the first weight, is the second weight, is the third weight, is the normalized ambient light intensity data, This is the normalized working temperature data of the LED lamp beads. This is the brightness requirement data set by the user after normalization.

[0012] Optionally, the step of inputting the real-time data set into the prediction model and outputting the current switching threshold comprises: normalizing the ambient light intensity data, the operating temperature data of the LED lamp beads, and the brightness requirement data set by the user; inputting the normalized data into the prediction model to obtain the current first threshold, the current second threshold, and the current third threshold. ,have ,

[0013] In the formula, is the activation function, is the transpose of the weight vector corresponding to the current first threshold, is the bias of the current first threshold, and for the current second threshold ,have ,

[0014] In the formula, is the transpose of the weight vector corresponding to the current second threshold, is the offset corresponding to the current second threshold, and for the current third threshold ,have ,

[0015] In the formula, is the transpose of the weight vector corresponding to the current third threshold, is the offset corresponding to the current third threshold; wherein the current switching threshold includes the current first threshold, the current second threshold and the current third threshold.

[0016] Optionally, switching the current dimming mode according to the size relationship between the current state value and the current mode switching threshold includes: determining whether the current state value is greater than the current first threshold; if not, switching to the analog dimming mode; if yes, determining whether the current state value is greater than the current second threshold; if no, switching to the low-frequency PWM dimming mode; if yes, determining whether the current state value is greater than the current third threshold; if no, switching to the mixed mode of low-frequency PWM dimming plus analog dimming; if yes, switching to the high-frequency PWM dimming mode.

[0017] Optionally, the switching of the mixed mode of the low-frequency PWM dimming plus the analog dimming comprises: calculating the proportion of the analog dimming according to the current state value, the current second threshold value and the current third threshold value, and for the proportion of the analog dimming ,have ;

[0018] The mixed mode of low-frequency PWM dimming plus analog dimming is switched according to the ratio of the analog dimming.

[0019] Optionally, switching the current dimming mode according to the relationship between the current state value and the current mode switching threshold also includes: adding the real-time data set, the current state value and the current mode switching threshold to the historical data set to obtain a new historical data set; training the prediction model according to the new historical data set to optimize the transpose of the weight vector corresponding to the first threshold, the bias of the first threshold, the transpose of the weight vector corresponding to the second threshold, the bias of the second threshold, the transpose of the weight vector corresponding to the third threshold, and the bias of the third threshold.

[0020] Optionally, generating a corresponding control signal according to the current dimming mode and sending it to the LED drive circuit includes: determining whether the category of the current dimming mode is PWM wave dimming; if so, generating a duty cycle value according to the current state value; generating a PWM waveform control signal according to the duty cycle value, and sending it to the LED drive circuit; if not, generating a voltage and current control signal according to the current state value, and sending it to the LED drive circuit; wherein, if the current dimming mode is a mixed mode of low-frequency PWM dimming plus analog dimming, the PWM waveform control signal and the voltage and current control signal are generated simultaneously and sent to the LED drive circuit.

[0021] Based on the same inventive concept, the present invention also provides a high-power LED lamp bead adaptive dimming system based on intelligent drive, the system comprising: a historical data set construction module, used to collect mode switching thresholds and factor data affecting the mode switching thresholds to construct a historical data set; a prediction model construction module, used to construct and train a prediction model for predicting the mode switching threshold based on the historical data set; a real-time data set collection module, used to periodically collect ambient light intensity data, LED lamp bead operating temperature data and user-set brightness requirement data to construct a real-time data set; a state value calculation module, used to calculate the current state value based on the real-time data set; a switching threshold calculation module, used to input the real-time data set into the prediction model, and output the current switching threshold; a dimming mode switching module, used to switch the current dimming mode according to the size relationship between the current state value and the current mode switching threshold; the dimming mode switching module is also used to generate a corresponding control signal according to the current dimming mode and send it to the LED drive circuit; the LED drive circuit is used to control the LED lamp bead according to the corresponding control signal.

[0022] Compared with the prior art, the present invention has the following advantages:

[0023] 1. The present invention can intelligently switch the dimming mode and realize adaptive dimming by collecting data such as ambient light intensity, LED lamp bead operating temperature and user-set brightness requirements in real time, combined with the mode switching threshold predicted by the neural network model;

[0024] 2. The present invention covers a variety of dimming modes including high-frequency PWM dimming mode, low-frequency PWM dimming mode, analog dimming mode, and a mixed mode of low-frequency PWM dimming plus analog dimming. The appropriate dimming mode can be selected according to actual needs, thereby improving the dimming range and accuracy;

[0025] 3. The present invention dynamically adjusts the switching threshold of the dimming mode according to the environment, the operating temperature of the LED lamp beads, and the brightness requirements set by the user. It can adjust the brightness according to actual needs, avoid unnecessary energy consumption, contribute to energy conservation and environmental protection, and provide a more comfortable and energy-saving lighting experience.

[0026] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures pointed out in the description, claims and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0028] Figure 1 It is a flow chart of a method for adaptive dimming of high-power LED lamp beads based on intelligent driving according to an embodiment of the present invention.

[0029] Figure 2 It is an execution flow chart of a high-power LED lamp bead adaptive dimming method based on intelligent driving according to an embodiment of the present invention.

[0030] Figure 3 The present invention is a schematic diagram of a high-power LED lamp bead adaptive dimming system based on intelligent driving according to an embodiment of the present invention. DETAILED DESCRIPTION

[0031] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0032] Reference Figure 1 An embodiment of the present invention proposes an adaptive dimming method for high-power LED lamp beads based on intelligent driving, which adopts a neural network model to predict the mode switching threshold, and switches the dimming mode according to the relationship between the current state value and the current mode switching threshold. It can realize adaptive dimming of high-power LED lamp beads, improve the dimming range and accuracy, and adaptively adjust the brightness according to environmental changes.

[0033] The method of this embodiment specifically includes:

[0034] Collect data on mode switching thresholds and factors affecting the mode switching thresholds, and construct a historical data set;

[0035] For example, it is assumed that within a certain time period, different ambient light intensities (such as sunny days, cloudy days, nights, etc.), different operating temperatures of LED lamp beads (such as low temperature, normal temperature, high temperature, etc.) and mode switching thresholds under various brightness requirements set by users are recorded; for example, on a sunny day and when the operating temperature of the LED lamp beads is normal, the user's brightness requirement suddenly increases from low to high brightness. At this time, the recorded mode switching threshold can be a specific brightness value or brightness change rate; these data and the corresponding mode switching thresholds are organized into a table or database form to constitute a historical data set.

[0036] Constructing and training a prediction model for predicting a mode switching threshold based on the historical data set;

[0037] Exemplarily, a neural network model is constructed based on historical data sets using a neural network algorithm in machine learning; the input layer of the model receives three characteristic values: ambient light intensity, LED lamp operating temperature, and user-set brightness requirements, and the output layer outputs the predicted mode switching threshold; through training, the model can learn the complex relationship between these characteristic values ​​and the mode switching threshold; after the training is completed, the model can predict the corresponding mode switching threshold based on the new input data.

[0038] Periodically collect ambient light intensity data, LED lamp working temperature data, and user-set brightness requirement data to build a real-time data set;

[0039] For example, at regular intervals (such as every second or every few minutes), sensors collect the current ambient light intensity, the operating temperature of LED lamp beads, and the brightness requirement data set by the user through a remote control or smart device; these data constitute a real-time data set for subsequent calculations and predictions.

[0040] Calculate the current state value according to the real-time data set;

[0041] Inputting the real-time data set into the prediction model, and outputting a current switching threshold;

[0042] Switching the current dimming mode according to a magnitude relationship between the current state value and the current mode switching threshold;

[0043] Generate corresponding control signals according to the current dimming mode and send them to the LED driving circuit to control the LED lamp beads;

[0044] The dimming modes include a high-frequency PWM dimming mode, a low-frequency PWM dimming mode, an analog dimming mode, and a mixed mode of low-frequency PWM dimming and analog dimming.

[0045] Optionally, the prediction model for predicting the mode switching value constructed and trained according to the historical data set includes:

[0046] Establishing a neural network model including an input layer, at least one hidden layer and an output layer;

[0047] Exemplarily, a neural network model is established including an input layer, at least one hidden layer and an output layer; this model will be used to receive input features (i.e., ambient light intensity, operating temperature of LED lamp beads, and brightness requirements set by users) and output a predicted mode switching threshold.

[0048] Three neurons are set in the input layer to receive the ambient light intensity, the working temperature of the LED lamp beads and the brightness requirement set by the user as input features respectively;

[0049] Exemplarily, three neurons are set in the input layer, and each neuron corresponds to an input feature; in this way, when the system collects ambient light intensity, LED lamp bead operating temperature and user-set brightness requirement data, these data can be passed to the neural network model as input features.

[0050] Three neurons are set in the output layer, respectively used to output a first threshold, a second threshold and a third threshold;

[0051] Exemplarily, three neurons are set in the output layer, which are used to output the first threshold, the second threshold and the third threshold respectively; these three thresholds will be used to switch the dimming mode according to the current state value in the future; it should be noted that the first threshold is smaller than the second threshold, and the second threshold is smaller than the third threshold, so as to ensure that the switching logic of the dimming mode is reasonable.

[0052] Setting an activation function and constructing a prediction function for each neuron in the output layer according to the activation function;

[0053] Exemplarily, in order to enable the neural network model to handle nonlinear problems, an activation function is set in the output layer; the choice of the activation function can be determined according to the specific problem and data characteristics; then, the prediction function of each neuron in the output layer is constructed according to the activation function, and these functions will be used to calculate the predicted mode switching threshold.

[0054] Using the historical data set to train the neural network model to generate a stable prediction model;

[0055] The first threshold is smaller than the second threshold, and the second threshold is smaller than the third threshold.

[0056] Exemplarily, the collected historical data set (i.e., the mode switching threshold and the data of factors affecting the mode switching threshold in the past period of time) is used to train the neural network model; by continuously iterating and adjusting the model parameters, a stable prediction model can be obtained, which can accurately predict the mode switching threshold based on the input features.

[0057] For example, suppose there is a historical data set that contains the ambient light intensity, LED lamp operating temperature, user-set brightness requirement data, and corresponding mode switching thresholds at different time periods every day in the past week; these data can be used to train a neural network model; during the training process, the model will learn the complex relationship between these input features and the mode switching threshold, and learn how to predict future mode switching thresholds based on new input data.

[0058] Alternatively, if Figure 2 As shown, the current state value calculated according to the real-time data set includes:

[0059] Calculate the change rate of ambient light intensity data, LED lamp working temperature data and user-set brightness requirement data;

[0060] Specifically, the system first collects data on ambient light intensity, LED lamp operating temperature, and user-set brightness requirements in real time. These data are the basis for the system to determine whether the dimming mode needs to be adjusted. Next, the rate of change of these data is calculated. The rate of change can reflect the fluctuation of the data in a short period of time. For example, the ambient light intensity may change rapidly due to weather changes, while the brightness requirements set by the user may change slowly due to user activities or preferences.

[0061] Determining whether the change rate is greater than a fourth threshold;

[0062] Specifically, a fourth threshold is set to determine whether the data change is significant; this threshold can be adjusted according to actual conditions to ensure that the system can sensitively respond to environmental changes while avoiding too frequent dimming mode switching.

[0063] If yes, calculating the current state value according to the real-time data set;

[0064] If not, maintain the current dimming mode.

[0065] Specifically, if any of the change rates of the ambient light intensity, the operating temperature of the LED lamp beads, or the brightness requirement data set by the user is greater than the fourth threshold, it is considered that the current environment or user demand has changed significantly, and it is necessary to calculate the current state value and consider switching the dimming mode; if the change rates of all data are less than or equal to the fourth threshold, the system believes that the current environment is relatively stable and user demand has not changed significantly, so the current dimming mode is maintained unchanged; if the data change rate is greater than the fourth threshold, the current state value is calculated based on the real-time data set; this state value can be a value that combines the ambient light intensity, the operating temperature of the LED lamp beads and the brightness requirement set by the user, which is used to reflect the current overall state; the calculated current state value is compared with the current switching threshold output by the previously trained prediction model; based on the comparison result, it is decided whether the dimming mode needs to be switched, and a corresponding control signal is generated and sent to the LED drive circuit.

[0066] For example, assume that at a certain point in time, it is detected that the ambient light intensity suddenly dims, and the rate of change is much greater than the fourth threshold; at the same time, the operating temperature of the LED lamp beads rises slightly, but the rate of change is still within the threshold range; the brightness requirement set by the user has not changed; in this case, it is considered that the significant change in the ambient light intensity is the main one, so the current state value is calculated and compared with the switching threshold output by the prediction model; if the current state value is lower than a certain threshold (such as the first threshold), it can switch to a brighter dimming mode to adapt to the change in ambient light; if the current state value is still within the threshold range, the current dimming mode will be maintained unchanged; by introducing the judgment logic of the rate of change, it can respond to environmental changes more intelligently and avoid unnecessary dimming mode switching, thereby providing a more comfortable and energy-saving lighting experience.

[0067] Optionally, calculating the current state value according to the real-time data set includes:

[0068] Normalize the ambient light intensity data, LED lamp bead operating temperature data, and user-set brightness requirement data;

[0069] Specifically, first, the ambient light intensity, the operating temperature of the LED lamp beads and the brightness requirement data set by the user are collected in real time; these data are usually expressed in different units and ranges, for example, the ambient light intensity can be expressed in lux (lx), the operating temperature of the LED lamp beads can be expressed in degrees Celsius (°C), and the brightness requirement set by the user can be expressed in percentage or specific brightness value; in order to enable these data to be compared and calculated on the same scale, they are normalized; normalization is a process of scaling data to a specific range (usually 0 to 1); for example, for ambient light intensity data, the system can scale it to a range of 0 (complete darkness) to 1 (maximum light intensity); similarly, the operating temperature of the LED lamp beads and the brightness requirement data set by the user are also scaled to the corresponding range.

[0070] Set the first weight of the ambient light intensity, the second weight of the LED lamp bead operating temperature, and the third weight of the brightness requirement set by the user;

[0071] Specifically, the first weight of the ambient light intensity is set ( )、The second weight of the working temperature of the LED lamp bead ( ) and the third weight of the brightness requirement set by the user ( ); these weights reflect the degree of influence of each factor on the current state value; for example, if the ambient light intensity is considered to be the most important factor, then If the brightness requirement set by the user is considered secondary, then a higher value may be assigned. Assign a lower value.

[0072] The current state value is calculated based on the first weight, the second weight, the third weight and the normalized data. ,have ,

[0073] In the formula, is the first weight, is the second weight, is the third weight, is the normalized ambient light intensity data, This is the normalized working temperature data of the LED lamp beads. This is the brightness requirement data set by the user after normalization.

[0074] Specifically, based on the normalized data and the set weights, the system calculates the current state value.

[0075] For example, assume that the real-time data collected by the system is as follows: the ambient light intensity is 500 lux (normalized to 0.5), the operating temperature of the LED lamp is 40 degrees Celsius (normalized to 0.6, assuming the temperature range is 0 to 100 degrees Celsius), and the brightness requirement set by the user is 70% (normalized to 0.7); at the same time, the weights are set as follows: = 0.5 (the importance of ambient light intensity is medium), =0.3 (the importance of the working temperature of the LED lamp bead is relatively low), =0.2 (the brightness requirement set by the user is the least important); Based on these data and weights, the system can calculate the current state value =0.5x0.5+0.3x0.6+0.2x0.7=0.25+0.18+0.14=0.57; this current state value It reflects the current overall state, and this value can be compared with the switching threshold output by the prediction model to decide whether the dimming mode needs to be switched.

[0076] Optionally, inputting the real-time data set into the prediction model and outputting a current switching threshold comprises:

[0077] Normalize the ambient light intensity data, LED lamp bead operating temperature data, and user-set brightness requirement data;

[0078] Specifically, the ambient light intensity, the operating temperature of the LED lamp beads and the brightness requirement data set by the user are collected in real time, and these data are normalized so that they can be compared and calculated on the same scale.

[0079] The normalized data is input into the prediction model to obtain the current first threshold, the current second threshold and the current third threshold. ,have ,

[0080] In the formula, is the activation function, is the transpose of the weight vector corresponding to the current first threshold, is the bias of the current first threshold,

[0081] For the current second threshold ,have ,

[0082] In the formula, is the transpose of the weight vector corresponding to the current second threshold, is the offset corresponding to the current second threshold,

[0083] For the current third threshold ,have ,

[0084] In the formula, is the transpose of the weight vector corresponding to the current third threshold, is the offset corresponding to the current third threshold;

[0085] The current switching threshold includes the current first threshold, the current second threshold and the current third threshold.

[0086] For example, the normalized data As input features, it is input into the trained neural network prediction model; the prediction model contains three output neurons, corresponding to the current first threshold ( ), the current second threshold ( ) and the current third threshold ( ); For each output neuron, the model uses the transpose of the corresponding weight vector ( , , ) and bias ( , , ) to calculate the output value; the calculation process uses the activation function (For example, it can be a sigmoid function, ReLU function, etc.), converting the linear combination of input features into a nonlinear output; after the prediction model is calculated, the current first threshold is output ( ), the current second threshold ( ) and the current third threshold ( ).

[0087] Alternatively, if Figure 2 As shown, switching the current dimming mode according to the magnitude relationship between the current state value and the current mode switching threshold value includes:

[0088] Determine whether the current state value is greater than the current first threshold; if not, switch to the analog dimming mode;

[0089] Specifically, the current state value Compare with four thresholds to determine which dimming mode should be switched to; if < , it is believed that for fine brightness control, such as reading lights, artistic lighting, etc., analog dimming can provide smooth brightness transition and stable lighting effect, so switch to analog dimming mode, analog dimming adjusts the brightness by changing the current of the LED.

[0090] If yes, determine whether the current state value is greater than the current second threshold; if no, switch to the low-frequency PWM dimming mode;

[0091] Specifically, if < < , it is considered that the current environment is moderate or the user needs medium brightness, so it switches to low-frequency PWM (pulse width modulation) dimming mode; low-frequency PWM dimming adjusts the brightness by changing the switching duty cycle of the LED, which is suitable for scenes that are not very sensitive to brightness changes.

[0092] If yes, determining whether the current state value is greater than the current third threshold value; if no, switching to the mixed mode of low-frequency PWM dimming plus analog dimming;

[0093] Specifically, if < < , it is considered that the current environment is brighter or the user needs a higher brightness, but it has not yet reached the level that requires high-frequency PWM dimming, so it switches to a mixed mode of low-frequency PWM dimming plus analog dimming; this mode combines the advantages of the first two dimming methods and can improve dimming efficiency and accuracy to a certain extent.

[0094] If yes, the high frequency PWM dimming mode is switched.

[0095] Specifically, if < , it is considered that the current environment is very bright or the user requires very high brightness, so it switches to high-frequency PWM dimming mode; high-frequency PWM dimming reduces the flicker visible to the human eye by increasing the switching frequency, and is suitable for scenes that require high brightness and are sensitive to flicker.

[0096] For example, assuming that the current state value is 0.6, and the thresholds obtained by the system through training are =0.5, =0.7, =0.9; first compare and ,Discover =0.6> =0.5, so the condition of switching to analog dimming mode is not met; then compare and ,Discover =0.6< =0.7, so the condition for switching to low-frequency PWM dimming mode is met; No more than , so there is no need to consider switching to mixed mode or high-frequency PWM dimming mode; therefore, it finally switches to low-frequency PWM dimming mode; this process is automatic and the user does not need manual intervention; in this way, the intelligent LED lighting system can automatically adjust the dimming mode according to real-time environmental conditions and user needs to provide the best lighting effect and user experience.

[0097] Optionally, the hybrid mode of switching low-frequency PWM dimming plus analog dimming includes:

[0098] The analog dimming ratio is calculated according to the current state value, the current second threshold value and the current third threshold value. ,have

[0099] ;

[0100] Specifically, according to the given formula, the ratio of analog dimming can be calculated, and the current state value With two thresholds and Connected by calculation Relative to and The position of the analog dimming function determines the proportion of analog dimming in the mixed mode.

[0101] For example, assuming that the current state value The second threshold is 0.75. is 0.7, the third threshold is 0.8; substituting these values ​​into the formula, we get =(0.75-0.7) / (0.8-0.7)x100%=50%; this means that in mixed mode, analog dimming should account for 50% of the proportion, while low-frequency PWM dimming accounts for the remaining 50%.

[0102] The mixed mode of low-frequency PWM dimming plus analog dimming is switched according to the ratio of the analog dimming.

[0103] For example, once the analog dimming ratio is calculated , the system can switch the hybrid dimming mode according to this ratio; this usually involves adjusting the parameters of the LED driver circuit so that a low-frequency PWM signal and an analog dimming signal are output simultaneously; in actual implementation, a digital-to-analog converter (DAC) may be used to generate the analog dimming signal, and a PWM controller may be used to generate the low-frequency PWM signal; then, these two signals may be combined to produce the desired hybrid dimming effect.

[0104] Optionally, switching the current dimming mode according to the magnitude relationship between the current state value and the current mode switching threshold further includes:

[0105] Adding the real-time data set, the current state value and the current mode switching threshold to the historical data set to obtain a new historical data set;

[0106] Specifically, the data such as ambient light intensity, LED lamp working temperature and user-set brightness requirements are collected in real time to form a real-time data set; the current state value is calculated based on the real-time data set and the prediction model. , the current state value With the three preset thresholds (the first threshold , the second threshold , the third threshold ) and switch to the corresponding dimming mode (such as analog dimming, low-frequency PWM dimming, hybrid dimming or high-frequency PWM dimming) according to the comparison result; after completing the dimming mode switching, the real-time data set and the current state value are and the current mode switching threshold (i.e. , , ) is added to the historical data set; thus, the historical data set includes real-time data, state values ​​and switching thresholds at multiple time points, as well as the corresponding dimming mode switching results.

[0107] The prediction model is trained according to the new historical data set to optimize the transpose of the weight vector corresponding to the first threshold, the bias of the first threshold, the transpose of the weight vector corresponding to the second threshold, the bias of the second threshold, the transpose of the weight vector corresponding to the third threshold, and the bias of the third threshold.

[0108] Specifically, the prediction model is retrained using a new historical data set. During the training process, the parameters in the prediction model can be adjusted, such as the transpose of the weight vector corresponding to the first threshold, the bias of the first threshold, the transpose of the weight vector corresponding to the second threshold, the bias of the second threshold, the transpose of the weight vector corresponding to the third threshold, the bias of the third threshold, etc.; the adjustment of these parameters is intended to make the prediction model more accurately reflect changes in the actual environment and user needs, so as to more accurately calculate the current state value and make more reasonable dimming mode switching decisions.

[0109] For example, assume that at a certain time point t, the collected real-time data set is {ambient light intensity: 500lx, LED operating temperature: 40°C, user brightness requirement: 70%}; according to the prediction model, calculate the current state value is 0.65; Compared with the threshold, it is found Falling on the second threshold (assumed to be 0.6) and the third threshold (assuming it is 0.7), so switch to mixed dimming mode; the real-time data set and state value and the second threshold for judging and the third threshold Add historical data sets; at a subsequent point in time, retrain the prediction model using the new historical data sets and adjust the model parameters to optimize performance; in this way, the smart LED lighting system can continuously learn and adapt to environmental changes and changes in user needs, thereby providing more accurate and efficient dimming services.

[0110] Optionally, generating a corresponding control signal according to the current dimming mode and sending the control signal to the LED driving circuit includes:

[0111] Determine whether the current dimming mode is PWM dimming;

[0112] If yes, generating a duty cycle value according to the current state value;

[0113] Generate a PWM waveform control signal according to the duty cycle value and send it to the LED drive circuit;

[0114] For example, assuming that the current dimming mode is PWM wave dimming, the current state value has been calculated based on the real-time data set and the prediction model. , determine the current dimming mode type is PWM wave dimming; according to the current state value , calculate a duty cycle value; this duty cycle value determines the proportion of time the LED lamp bead is lit in a PWM cycle; when the duty cycle value is large, the LED lamp bead is lit for a longer time in each cycle, so the average brightness is higher; conversely, when the duty cycle value is small, the LED lamp bead is lit for a shorter time in each cycle, and the average brightness is lower; for example, if is 0.5, the duty cycle value can be 50%, which means that the LED lamp bead is lit for half of the time in each cycle, so that the average brightness of the LED will be half of the maximum brightness; a PWM waveform control signal is generated according to the duty cycle value. This signal is a periodic high and low level signal, and the length of the high level time is determined by the duty cycle value; the generated PWM waveform control signal is sent to the LED drive circuit, and the drive circuit controls the lighting and extinguishing of the LED lamp bead according to this signal, thereby achieving a dimming effect.

[0115] If not, a voltage and current control signal is generated according to the current state value and sent to the LED driving circuit;

[0116] For example, assuming that the current dimming mode is analog dimming, the current state value has also been calculated. ; Determine whether the current dimming mode is analog dimming, according to the current state value , calculate a voltage or current control value V / I; this value determines the voltage across the LED lamp bead or the current flowing through it, thereby controlling the brightness of the LED; generate a voltage and current control signal based on the voltage / current control value V / I; this signal can be an analog voltage signal or a digital signal (converted into analog voltage by DAC), which is used to control the output voltage or current of the LED drive circuit; send the generated voltage and current control signal to the LED drive circuit, and the drive circuit adjusts the voltage or current of the LED lamp bead according to this signal, thereby achieving a dimming effect.

[0117] If the current dimming mode is a mixed mode of low-frequency PWM dimming and analog dimming, the PWM waveform control signal and the voltage and current control signal are generated simultaneously and sent to the LED driving circuit.

[0118] For example, assuming that the current dimming mode is a mixed mode of low-frequency PWM dimming and analog dimming, the current state value has also been calculated. ; Determine whether the current dimming mode is a mixed mode; Based on the current state value , respectively calculate a duty cycle value and a voltage / current control value V / I, which together determine the LED brightness in the hybrid dimming mode; generate a PWM waveform control signal according to the duty cycle value, and generate a voltage / current control signal according to the voltage / current control value V / I; send these two control signals to the LED drive circuit at the same time, the drive circuit can include two independent control channels, one for receiving the PWM waveform control signal, and the other for receiving the voltage and current control signal; these two signals work together to achieve a hybrid effect of low-frequency PWM dimming and analog dimming.

[0119] Based on the same inventive concept, Figure 3 As shown, the present invention also provides a high-power LED lamp bead adaptive dimming system based on intelligent drive, the system comprising:

[0120] A historical data set construction module is used to collect data on mode switching thresholds and factors affecting the mode switching thresholds to construct a historical data set;

[0121] A prediction model building module, used to build and train a prediction model for predicting a mode switching threshold based on the historical data set;

[0122] The real-time data set acquisition module is used to periodically collect ambient light intensity data, LED lamp bead operating temperature data, and user-set brightness requirement data to build a real-time data set;

[0123] A state value calculation module, used to calculate the current state value according to the real-time data set;

[0124] A switching threshold calculation module, used to input the real-time data set into the prediction model and output a current switching threshold;

[0125] A dimming mode switching module, used to switch the current dimming mode according to the magnitude relationship between the current state value and the current mode switching threshold; the dimming mode switching module is also used to generate a corresponding control signal according to the current dimming mode and send it to the LED driving circuit;

[0126] The LED driving circuit is used to control the LED lamp beads according to the corresponding control signal.

[0127] It should be noted that the electrical connection between the above-mentioned units does not necessarily mean the connection between the lines. The indirect connection method can be applied to the embodiments of the present invention as long as the purpose of the present invention is achieved. The above is only an exemplary embodiment of the present invention and cannot be used to limit the scope of the present invention.

[0128] That is, any equivalent changes and modifications made according to the teachings of the present invention are still within the scope of the present invention. After considering the disclosure of the specification and the truth of practice, those skilled in the art will easily think of other embodiments of the present invention. This application is intended to cover any variation, use or adaptive change of the present invention, which follows the general principles of the present invention and includes common knowledge or customary technical means in the art that are not described in the present invention.

Claims

1. A high-power LED lamp bead adaptive dimming method based on intelligent drive, characterized in that: The method comprises: Collect data on mode switching thresholds and factors affecting the mode switching thresholds, and construct a historical data set; Constructing and training a prediction model for predicting a mode switching threshold based on the historical data set; Periodically collect ambient light intensity data, LED lamp working temperature data, and user-set brightness requirement data to build a real-time data set; Calculate the current state value according to the real-time data set; Input the real-time data set into the prediction model, and output the current mode switching threshold; Switching the current dimming mode according to a magnitude relationship between the current state value and the current mode switching threshold; Generate corresponding control signals according to the current dimming mode and send them to the LED driving circuit to control the LED lamp beads; The dimming modes include a high-frequency PWM dimming mode, a low-frequency PWM dimming mode, an analog dimming mode, and a mixed mode of low-frequency PWM dimming and analog dimming.

2. According to claim 1, a high-power LED lamp bead adaptive dimming method based on intelligent drive is characterized in that: The prediction model for predicting the mode switching value constructed and trained according to the historical data set includes: Establishing a neural network model including an input layer, at least one hidden layer and an output layer; Three neurons are set in the input layer to receive the ambient light intensity, the working temperature of the LED lamp beads and the brightness requirement set by the user as input features respectively; Three neurons are set in the output layer, respectively used to output a first threshold, a second threshold and a third threshold; Setting an activation function and constructing a prediction function for each neuron in the output layer according to the activation function; Using the historical data set to train the neural network model to generate a stable prediction model; The first threshold is smaller than the second threshold, and the second threshold is smaller than the third threshold.

3. According to the method of high-power LED lamp bead adaptive dimming based on intelligent drive according to claim 1, it is characterized in that: The calculating the current state value according to the real-time data set comprises: Calculate the change rate of ambient light intensity data, LED lamp working temperature data and user-set brightness requirement data; Determining whether the change rate is greater than a fourth threshold; If yes, calculating the current state value according to the real-time data set; If not, maintain the current dimming mode.

4. According to claim 3, a high-power LED lamp bead adaptive dimming method based on intelligent drive is characterized in that: Calculating the current state value according to the real-time data set includes: Normalize the ambient light intensity data, LED lamp bead operating temperature data, and user-set brightness requirement data; Set the first weight of the ambient light intensity, the second weight of the LED lamp bead operating temperature, and the third weight of the brightness requirement set by the user; The current state value is calculated based on the first weight, the second weight, the third weight and the normalized data. ,have , where is the first weight, is the second weight, is the third weight, is the normalized ambient light intensity data, This is the normalized working temperature data of the LED lamp beads. This is the brightness requirement data set by the user after normalization.

5. According to the method of high-power LED lamp bead adaptive dimming based on intelligent drive according to claim 1, it is characterized in that: The step of inputting the real-time data set into the prediction model and outputting the current switching threshold comprises: Normalize the ambient light intensity data, LED lamp bead operating temperature data, and user-set brightness requirement data; The normalized data is input into the prediction model to obtain the current first threshold, the current second threshold and the current third threshold. ,have , where is the activation function, is the transpose of the weight vector corresponding to the current first threshold, is the bias of the current first threshold, For the current second threshold ,have , In the formula, is the transpose of the weight vector corresponding to the current second threshold, is the offset corresponding to the current second threshold, For the current third threshold ,have , where is the transpose of the weight vector corresponding to the current third threshold, is the offset corresponding to the current third threshold; The current switching threshold includes the current first threshold, the current second threshold and the current third threshold.

6. The method for adaptive dimming of high-power LED lamp beads based on intelligent driving according to claim 5, characterized in that: The method further comprises: Determine whether the current state value is greater than the current first threshold; if not, switch to the analog dimming mode; If yes, determine whether the current state value is greater than the current second threshold; if no, switch to the low-frequency PWM dimming mode; If yes, determining whether the current state value is greater than the current third threshold value; if no, switching to the mixed mode of low-frequency PWM dimming plus analog dimming; If yes, the high frequency PWM dimming mode is switched.

7. The method for adaptive dimming of high-power LED lamp beads based on intelligent driving according to claim 6, characterized in that: The switching of the mixed mode of low-frequency PWM dimming plus analog dimming includes: The analog dimming ratio is calculated according to the current state value, the current second threshold value and the current third threshold value. ,have ; Switching the mixed mode of low-frequency PWM dimming plus analog dimming according to the ratio of the analog dimming.

8. The method for adaptive dimming of high-power LED lamp beads based on intelligent driving according to claim 5, characterized in that: The switching the current dimming mode according to the magnitude relationship between the current state value and the current mode switching threshold further comprises: Adding the real-time data set, the current state value and the current mode switching threshold to the historical data set to obtain a new historical data set; The prediction model is trained according to the new historical data set to optimize the transpose of the weight vector corresponding to the first threshold, the bias of the first threshold, the transpose of the weight vector corresponding to the second threshold, the bias of the second threshold, the transpose of the weight vector corresponding to the third threshold, and the bias of the third threshold.

9. The method for adaptive dimming of high-power LED lamp beads based on intelligent driving according to claim 1, characterized in that: The generating a corresponding control signal according to the current dimming mode and sending the control signal to the LED driving circuit comprises: Determine whether the current dimming mode is PWM dimming; If yes, generating a duty cycle value according to the current state value; Generate a PWM waveform control signal according to the duty cycle value and send it to the LED drive circuit; If not, a voltage and current control signal is generated according to the current state value and sent to the LED driving circuit; If the current dimming mode is a mixed mode of low-frequency PWM dimming and analog dimming, the PWM waveform control signal and the voltage and current control signal are generated simultaneously and sent to the LED driving circuit.

10. A high-power LED lamp bead adaptive dimming system based on intelligent drive, characterized in that: The system comprises: A historical data set construction module is used to collect data on mode switching thresholds and factors affecting the mode switching thresholds to construct a historical data set; A prediction model building module, used to build and train a prediction model for predicting a mode switching threshold based on the historical data set; The real-time data set acquisition module is used to periodically collect ambient light intensity data, LED lamp bead operating temperature data, and user-set brightness requirement data to build a real-time data set; A state value calculation module, used to calculate the current state value according to the real-time data set; A switching threshold calculation module, used to input the real-time data set into the prediction model and output a current mode switching threshold; A dimming mode switching module, used to switch the current dimming mode according to the magnitude relationship between the current state value and the current mode switching threshold; the dimming mode switching module is also used to generate a corresponding control signal according to the current dimming mode and send it to the LED driving circuit; The LED driving circuit is used to control the LED lamp beads according to the corresponding control signal.

Images