Light source driving module and vehicle lamp comprising same

Abstract

The invention discloses a light source driving module and a vehicle lamp comprising the same, and relates to the technical field of light source driving. The light source driving module comprises a target analysis unit which is used for monitoring a current speed value of a vehicle, a current state parameter set of a vehicle lamp and a current environment state parameter set in a set area, and inputting the current speed value, the current state parameter set and the current environment state parameter set into a pre-trained target analysis model to analyze a target state parameter set of the vehicle lamp in the set area; the current analysis unit is used for analyzing a target state parameter set of the vehicle lamp in a set area; the pre-training target analysis model is introduced, real-time collection and data fusion of the current vehicle speed, the vehicle lamp state and the regional environment parameters are achieved, the brightness, the color temperature and the light beam angle target state of the vehicle lamp can be dynamically generated, and therefore the target state of the vehicle lamp, the color temperature and the light beam angle can be dynamically generated. And the driving module can automatically adjust a driving current set according to real-time data, so that actual lighting requirements can be accurately matched under various road and environment working conditions.

Description

Technical Field

[0001] The present invention relates to the technical field of light source driving, and in particular to a light source driving module and a vehicle lamp containing the same. Background Art

[0002] In recent years, with the rapid development of the automobile industry and the increasing requirements for energy conservation and emission reduction, LED headlights, as the core components of automobile lighting systems, have received widespread attention. LED headlights have the advantages of small size, fast response speed, high energy efficiency, and long service life. They have gradually replaced traditional halogen lamps and xenon lamps and become an important configuration of modern automobiles. However, the performance of LED headlights not only depends on the LED device itself, but also the design and control strategy of its driver module have a key impact on the overall lighting effect and energy consumption performance.

[0003] Traditional headlight driving technology usually adopts a fixed current driving mode to drive the LED according to pre-set working parameters. It fails to fully consider the real-time changing environmental conditions, vehicle speed, and the working status of the headlight itself during driving. Due to the influence of road environment, weather changes and vehicle dynamic factors, the headlights may have problems such as insufficient brightness, unstable color temperature or misaligned beam angle during actual use, which directly affects the driver's visual safety and driving experience. In addition, the fixed driving mode also has certain limitations in energy efficiency, which can easily lead to energy waste, accelerate LED aging, and shorten service life.

[0004] Therefore, how to achieve dynamic control of the headlight driving current and perform intelligent analysis and adjustment based on real-time collection of vehicle status and environmental parameters has become an important issue that needs to be urgently solved in the current LED headlight driving technology. By introducing advanced target analysis models and adaptive control strategies, it is possible to not only optimize the brightness, color temperature and beam angle of the headlights, but also achieve energy saving and consumption reduction under different driving conditions, further improving the safety and economy of the automotive lighting system. This provides a new technological breakthrough for the development of future automotive intelligent and high-efficiency lighting systems.

[0005] The prior art, such as the light source driving device and the light source driving method disclosed in the invention patent application with the announcement number: CN106658886A, turns off each light-emitting unit in turn in each unit time period, wherein when one of the light-emitting units is turned off, the remaining light-emitting units are turned on to maintain the total brightness of the light-emitting units at a preset brightness. By using the light source driving device and the light source driving method of the present invention, the total brightness of the light-emitting units can be maintained at a preset brightness, so that the purpose of effectively saving power can be achieved without affecting the light quality.

[0006] Based on the above solution, it is found that the limitations of the existing technology include at least the following problems. First, the existing headlight driving system is usually designed based on fixed working modes and environmental conditions, and lacks the flexibility to adjust the light source output by real-time input of vehicle speed, headlight status and environmental parameters, which easily leads to the difficulty of accurately adapting the brightness, color temperature and beam angle of the headlight under different road conditions, and it is often difficult to fully optimize the lighting effect and energy efficiency. For example, in a complex driving environment, such as high-speed driving or low-speed driving, the brightness and color temperature of the headlight may not be dynamically optimized in time, resulting in a situation that affects the driver's field of vision and wastes energy. Secondly, in traditional technology, the operating parameters of the headlight are usually fixed in the design stage, and a mature system solution is derived, which lacks a response mechanism for real-time data feedback and environmental changes. This method not only fails to effectively adapt to the diverse needs of road and speed changes, but may also cause additional energy waste due to improper light source matching, affecting the life of the headlight under long-term driving, and further affecting the overall vehicle energy efficiency and driving experience. Summary of the invention

[0007] In view of the deficiencies of the prior art, the present invention provides a light source driving module and a vehicle lamp containing the same, which solves the problem in the prior art of lacking real-time dynamic adjustment of vehicle lamp brightness, color temperature and beam angle.

[0008] To achieve the above objectives, the present invention is implemented through the following technical solutions: a light source driving module, comprising: a target analysis unit, used to monitor the current speed value of the vehicle, the current state parameter set of the headlights, and the current environmental state parameter set in a set area, and input them into a pre-trained target analysis model for data analysis to obtain a target state parameter set of the headlights in the set area, the current state parameter set includes the current headlight brightness value, the current headlight color temperature value, and the current headlight beam angle value, the current environmental state parameter set includes the current environmental brightness value, the current environmental temperature value, and the current environmental humidity value, the target state parameter set includes the headlight target brightness value, the headlight target color temperature value, and the headlight target beam angle value; a current analysis unit, used to analyze the driving current set of the headlight based on the target state parameter set of the headlight in the set area, the driving current set includes the brightness driving current value, the color temperature driving current value, and the beam angle driving current value; a driving unit, used to send a light source driving instruction to the headlight based on the headlight driving current set.

[0009] Furthermore, the target analysis model is specifically a deep neural network model, which is composed of an input layer, several hidden layers, and an output layer, wherein: the input layer is used to receive the current speed value of the vehicle, the current state parameter set of the headlights, and the current environmental state parameter set in the set area, and perform preprocessing; the hidden layer is used to perform feature analysis on the preprocessed current speed value of the vehicle, the current state parameter set of the headlights, and the current environmental state parameter set in the set area; the output layer is used to convert the feature analysis results of the hidden layer into the target state parameter set of the headlights in the set area.

[0010] Furthermore, the specific steps for analyzing the brightness driving current value of the headlights are as follows: obtain the headlight brightness reference current value, the vehicle speed parameter value, and the ambient brightness parameter value; obtain the brightness current response index, and combine the vehicle current speed value, the vehicle speed parameter value, the headlight brightness reference current value, the current headlight brightness value, the headlight target brightness value within the set area, the current ambient brightness value within the set area of ​​the headlight, and the ambient brightness parameter value for comprehensive analysis to obtain the brightness driving current value of the headlight.

[0011] Furthermore, the specific steps for obtaining the brightness current response index are as follows: several measurement currents are passed through the light source, and the brightness value of the light source under each measurement current is recorded respectively; the brightness value of the light source under each measurement current is logarithmically linearized; after logarithmic linearization, data fitting analysis is performed on the brightness value of the light source under each measurement current to obtain the brightness current response index.

[0012] Furthermore, the specific formula for calculating the brightness driving current value of the headlight is as follows: ;in, is the driving current value of the headlight brightness, is the reference current value of the headlight brightness, is the target brightness value of the headlight in the set area, is the current brightness value of the headlight, is the current speed of the vehicle, is the vehicle speed parameter, is the vehicle speed brightness influence coefficient stored in the database, is the brightness current response index stored in the database, is the ambient brightness parameter value, The current ambient brightness value within the set area of ​​the headlight. It is the environmental brightness influence coefficient stored in the database.

[0013] Furthermore, the specific steps of analyzing the color temperature driving current value of the headlight are as follows: obtaining the headlight color temperature reference current value, the color temperature adjustment amplitude value, and the environmental parameter set, wherein the environmental parameter set includes the ambient temperature parameter value and the ambient humidity parameter value; reading the vehicle current speed value and the vehicle speed parameter value, and combining the headlight color temperature reference current value, the current headlight color temperature value, the headlight target color temperature value within the set area, the color temperature adjustment amplitude value, the current ambient temperature value within the set area of ​​the headlight, the current ambient humidity value, and the environmental parameter set for comprehensive analysis to obtain the color temperature driving current value of the headlight.

[0014] Furthermore, the specific formula for calculating the color temperature driving current value of the headlight is as follows: ;in, is the color temperature driving current value of the headlight, is the reference current value of the headlight color temperature, is the target color temperature value of the headlight in the set area. is the current color temperature value of the headlight, is the color temperature influence coefficient stored in the database, is the ambient temperature parameter value, The current ambient temperature value in the setting area of ​​the headlight. is the ambient humidity parameter value, The current ambient humidity value in the setting area of ​​the headlight. is the temperature and humidity combined influence coefficient stored in the database, is the vehicle speed parameter, is the current speed of the vehicle, It is the vehicle speed color temperature influence coefficient stored in the database.

[0015] Furthermore, the specific steps of analyzing the light beam angle driving current value of the headlight are as follows: obtain the light beam angle reference current value of the headlight; read the current speed value of the vehicle and the vehicle speed parameter value, and perform a comprehensive analysis based on the light color temperature reference current value, the current light beam angle value of the headlight, and the target light beam angle value of the headlight in the set area to obtain the light beam angle driving current value of the headlight.

[0016] Furthermore, the specific formula for calculating the beam angle driving current value of the headlight is as follows: ;in, is the driving current value of the light beam angle of the car lamp, is the reference current value of the headlight beam angle, is the target beam angle value of the headlight in the set area. is the current light beam angle value of the headlight, is the beam angle attenuation coefficient stored in the database, is the beam angle adjustment coefficient stored in the database, is the current speed of the vehicle, is the vehicle speed parameter, is the vehicle speed beam angle attenuation coefficient stored in the database, It is the vehicle speed beam angle adjustment coefficient stored in the database.

[0017] A headlight, comprising: a data acquisition module, used to acquire a current vehicle speed value, a current state parameter set of the headlight, and a current environmental state parameter set in a set area; a light source driving module, used to analyze a headlight driving current set based on the current vehicle speed value, the current state parameter set of the headlight, and the current environmental state parameter set in the set area, and send a light source driving instruction to the headlight; and an execution module, used to receive the light source driving instruction and execute a light source driving operation on the headlight.

[0018] The present invention has the following beneficial effects: (1) The light source driver module, by introducing a pre-trained target analysis model, realizes real-time collection and data fusion of the vehicle's current speed, headlight status and regional environmental parameters, so that the target states of the headlight brightness, color temperature and beam angle can be dynamically generated. As a result, the driver module can automatically adjust the driving current set according to real-time data, thereby accurately matching the actual lighting needs under various road and environmental conditions, effectively improving the lighting effect and energy utilization efficiency, and avoiding the blind spots and resource waste caused by fixed parameter design.

[0019] (2) The light source driver module adopts multi-dimensional parameter calibration and database storage of influence coefficients, and establishes targeted calculation logic for the driving current of brightness, color temperature and beam angle, fully considering the comprehensive influence of LED nonlinear response, ambient brightness, temperature and humidity, and vehicle speed. Through experimental calibration and data fitting, the brightness current response index, color temperature adjustment amplitude, beam angle attenuation and adjustment coefficient are obtained, so that the driver module can finely control each optical parameter, effectively overcoming the problem of fixed parameters and inability to respond to environmental changes in real time in the existing technology, thereby reducing energy waste and extending the life of the LED.

[0020] (3) The light source driving module forms an intelligent light source driving system through three modules: target analysis unit, current analysis unit and driving unit. It can not only generate the target state parameters of the headlights based on real-time data, but also extract and fuse the data features through multi-level, deep neural networks, thereby achieving precise control of the brightness, color temperature and beam angle of the headlights. Compared with traditional technologies, this solution can flexibly adapt to complex roads and environmental changes, ensure balanced and stable operation of lighting, and greatly improve energy utilization and reduce system power consumption, providing stronger technical support for the overall energy efficiency and driving experience of the vehicle.

[0021] Of course, any product implementing the present invention does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 This is a structural block diagram of a light source driving module of the present invention.

[0023] Figure 2 The present invention is a flowchart of the specific steps for analyzing the brightness driving current value of a vehicle lamp in a light source driving module.

[0024] Figure 3 The figure is a structural block diagram of a vehicle lamp according to the present invention. DETAILED DESCRIPTION

[0025] See also Figure 1 The embodiment of the present invention provides a technical solution: a light source driving module, comprising: a target analysis unit, used to monitor the current speed value of the vehicle, the current state parameter set of the headlights, and the current environment state parameter set in a set area, and input them into a pre-trained target analysis model for data analysis to obtain a target state parameter set of the headlights in the set area, the current state parameter set includes the current headlight brightness value, the current headlight color temperature value, and the current headlight beam angle value, the current environment state parameter set includes the current environment brightness value, the current environment temperature value, and the current environment humidity value, the target state parameter set includes the headlight target brightness value, the headlight target color temperature value, and the headlight target beam angle value; a current analysis unit, used to analyze the headlight driving current set based on the headlight target state parameter set in the set area, the driving current set includes the brightness driving current value, the color temperature driving current value, and the beam angle driving current value; a driving unit, used to send a light source driving instruction to the headlight based on the headlight driving current set.

[0026] Specifically, the target analysis model is a deep neural network model, which consists of an input layer, several hidden layers, and an output layer, where: The input layer is used to receive the current speed value of the vehicle, the current state parameter set of the headlights, the current state parameter set of the environment in the set area, and perform preprocessing. Its function is to receive external data and pass it to the next layer of the neural network. It is the interface between the model and external information. Each node in the input layer corresponds to a feature, such as vehicle speed, current headlight brightness, color temperature and beam angle, temperature and humidity in the environment, etc. The data in the input layer will be passed to the hidden layer through weights and biases for subsequent calculations and learning. The main purpose of the input layer is to convert the original external data into a form that can be used for model processing.

[0027] The hidden layer is used to perform feature analysis on the pre-processed current vehicle speed value, the current state parameter set of the headlights, and the current environmental state parameter set in the set area. Its function is to learn complex patterns and features from the input data and map them to the next layer. The hidden layer contains multiple neurons, each of which is connected to the nodes of the previous layer, and generates output by applying an activation function (such as ReLU) after weighted summation. The output of each layer is a further abstraction and feature extraction of the input data. Through multiple hidden layers, the model can capture nonlinear relationships in the data, learn higher-order features, and thus improve the model's predictive ability. The hidden layer is the core part of the neural network, which determines the performance and complexity of the network.

[0028] The output layer is used to convert the feature analysis results of the hidden layer into the target state parameter set of the headlights in the set area. Its function is to convert the features extracted by the hidden layer into the final prediction results. It maps the output of the hidden layer to the target output space through a linear combination of weights and biases. For example, in the headlight control scenario, the output layer will predict the target headlight brightness, color temperature and beam angle. Each node in the output layer corresponds to a target parameter, and the final prediction value is the value of each target parameter given by the model. The main task of the output layer is to output a reasonable result based on the learning process of the model to meet specific application requirements.

[0029] In this embodiment, the input layer includes 7 nodes (corresponding to the current state parameters of the vehicle and the environment).

[0030] There are three hidden layers, including: Hidden layer 1 consists of 128 neurons activated by ReLU.

[0031] Hidden layer 2 consists of 64 neurons activated by ReLU.

[0032] Hidden layer 3 consists of 32 neurons activated by ReLU.

[0033] The output layer consists of three nodes (target brightness, target color temperature, target beam angle), which predict the value through a linear activation function.

[0034] Among them, the pre-training steps of the target analysis model are as follows: Collect and prepare data. The data should include input features (vehicle and environment status) and target parameters (target headlight status). The data needs to be labeled and representative. Each sample should contain the vehicle status, environment status, and the corresponding headlight target value.

[0035] Input characteristics (vehicle and environment state parameters): Vehicle speed (unit: km / h or m / s); Current headlight brightness (unit: lumens); Current headlight color temperature (unit: Kelvin); Current headlight beam angle (unit: degree); Current ambient brightness (unit: lux); Current ambient temperature (unit: °C); Current ambient humidity (unit: %); Target parameters (target state of the lights): Target brightness; Target color temperature; Target beam angle; The target value of each data sample (target brightness, target color temperature, and target beam angle) is determined based on environmental factors and vehicle status. These target values ​​can be obtained through simulation or actual testing, and data is generated through a variety of different vehicles and environmental conditions, making the training set rich in diversity.

[0036] Preprocess the collected data (a key step to ensure that the input data can be effectively processed by the neural network during training) Data preprocessing: Standardization: Each input feature (such as vehicle speed, current headlight brightness, ambient temperature, etc.) is standardized, that is, its value is converted into a zero-mean unit variance form; Missing value processing: If the data set has missing values, it is usually filled (such as using the mean, median, or mode) or deleting samples with missing data.

[0037] Data segmentation: Divide the dataset into training set, validation set and test set: Training set: used to train the neural network (usually 70% of the dataset).

[0038] Validation set: used for model tuning to help select optimal hyperparameters (usually 15%).

[0039] Test set: used for final evaluation of the model (usually 15%).

[0040] The mean squared error (MSE) is used as the loss function to measure the gap between the model output and the true target.

[0041] At the beginning of training, the weights and biases of all neural networks are randomly initialized. Xavier initialization or He initialization can be used to ensure that the weights are properly initialized to avoid gradient explosion or gradient disappearance problems.

[0042] For each training sample, the network calculates the target headlight state through forward propagation: The input data is passed through the input layer to the first hidden layer.

[0043] The hidden layer computes the output by taking a weighted sum and applying an activation function (ReLU).

[0044] The data passes through multiple hidden layers in sequence and finally generates the predicted value of the target headlight state through the output layer.

[0045] The loss function calculates the gap between the model's prediction and the actual target. The goal of the model is to minimize this loss value to improve the prediction accuracy.

[0046] The gradient of each weight is calculated through the back-propagation algorithm, and the weight is updated according to the gradient value. Common optimization methods include stochastic gradient descent (SGD) and Adam optimizer (an adaptive learning rate optimization method that can automatically adjust the learning rate of each parameter to accelerate convergence and avoid local minima).

[0047] The training process includes multiple epochs, that is, traversing the entire training dataset multiple times. Each iteration updates the weights and gradually reduces the value of the loss function. After each epoch is completed, the loss value on the validation set is calculated to verify whether the model is overfitting during the training process.

[0048] To avoid overfitting, early stopping is used: the training process is stopped when the loss on the validation set stops decreasing.

[0049] The validation set is used to adjust hyperparameters (such as learning rate, number of hidden layer neurons, etc.). If the loss on the validation set begins to increase, it may indicate overfitting and you need to stop training or adjust the model structure.

[0050] After training is complete, use the test set to evaluate the generalization ability of the model. Calculate the loss on the test set to evaluate the model's predictive ability on unseen data.

[0051] Hyperparameter tuning: Tune hyperparameters (such as learning rate, batch size, number of hidden layers, etc.) using methods such as grid search or random search to find the optimal configuration.

[0052] Regularization: Overfitting can be reduced through techniques such as L2 regularization or dropout.

[0053] In this implementation scheme, by inputting multi-source data such as vehicle speed, headlight status and environmental parameters into the deep neural network model, and after standardization, missing value processing, data set division and multiple iterative training, the potential rules in the data can be fully mined and the target brightness, color temperature and beam angle of the headlights can be predicted, thereby realizing intelligent control of the headlights. This method adopts multiple hidden layers in model design, which can capture complex nonlinear relationships, and through the activation function (such as ReLU) and the mean square error (MSE) loss function, the training process has good generalization ability for various input features. In addition, the validation set and the test set are used for hyperparameter tuning and final performance evaluation, combined with the early stopping method and regularization technology, which can effectively reduce the risk of overfitting and improve the robustness of the model. Overall, this set of training and verification processes can not only ensure the accurate prediction of the target parameters of the headlights in a multi-dimensional environment, but also flexibly adapt to different road conditions, providing efficient, stable and scalable intelligent control means for vehicle lighting.

[0054] Specifically, Figure 2 As shown, the specific steps for analyzing the brightness driving current value of the headlight are as follows: obtain the headlight brightness reference current value, the vehicle speed parameter value, and the ambient brightness parameter value; obtain the brightness current response index, and combine the vehicle current speed value, the vehicle speed parameter value, the headlight brightness reference current value, the current headlight brightness value, the headlight target brightness value within the set area, the current ambient brightness value within the set area of ​​the headlight, and the ambient brightness parameter value for comprehensive analysis to obtain the brightness driving current value of the headlight.

[0055] The reference current value for the brightness of the headlights can be found in the LED manufacturer's specification sheet, which shows the typical driving current of the LED under standard working conditions. An intermediate value (such as 1.5A) can be selected as the reference current for the system in a normal, balanced state.

[0056] The vehicle speed parameter value can select a typical reference speed (for example, 50km / h) based on common road speed limits and driving habits.

[0057] The specific steps of obtaining the brightness current response index are as follows: several measurement currents are passed through the light source, and the brightness value of the light source under each measurement current is recorded respectively; the brightness value of the light source under each measurement current is logarithmically linearized; after logarithmic linearization, the brightness value of the light source under each measurement current is subjected to data fitting analysis to obtain the brightness current response index. The specific implementation example is as follows: Before starting formal measurement, give the LED a small or medium current (such as 0.8A) and let it work for a period of time (such as 5 to 10 minutes) to allow the LED to reach a thermally stable state.

[0058] This can reduce brightness fluctuations caused by changes in LED junction temperature.

[0059] Set a series of current points (for example, from 0.5A to 2.5A, measure every 0.1A or 0.2A, the specific step is determined by the experimental accuracy requirements).

[0060] For each current value, record the corresponding brightness.

[0061] If you use an integrating sphere or spectrometer, you can directly read the luminous flux (lm) or light intensity.

[0062] If you use a lux meter, you need to convert or calibrate the measured illuminance value into brightness value; or use the relative size of the illuminance value instead of brightness (as long as consistency is maintained during subsequent fitting).

[0063] After each current change, wait for several seconds to tens of seconds to allow the LED to become thermally stable before measuring again to reduce transient thermal effects.

[0064] To improve data reliability, multiple measurements can be made on the same current point, the average value is taken and the standard deviation or error range is recorded.

[0065] Collect enough measurement points (at least 8 to 12 or more in this embodiment) to make subsequent data fitting more accurate.

[0066] The brightness value of the light source under each measurement current is logarithmically linearized, and a linear regression method is used for fitting analysis to obtain the slope value and intercept value.

[0067] By looking at the residuals or calculating R 2 value to assess the goodness of fit.

[0068] If the deviation is too large, check whether the experimental error, temperature effect or data distribution is reasonable.

[0069] The specific formula for calculating the brightness driving current value of the headlight is as follows: ;in, is the driving current value of the headlight brightness, is the reference current value of the headlight brightness, is the target brightness value of the headlight in the set area, is the current brightness value of the headlight, is the current speed of the vehicle, is the vehicle speed parameter, is the vehicle speed brightness influence coefficient stored in the database, is the brightness current response index stored in the database, is the ambient brightness parameter value, The current ambient brightness value within the set area of ​​the headlight. It is the environmental brightness influence coefficient stored in the database.

[0070] It needs to be explained that the vehicle speed brightness influence coefficient stored in the database , Ambient brightness influence coefficient The specific steps to obtain are: when the vehicle is traveling at different speeds, select common models and test environments (such as day and night, different vehicle speeds and ambient brightness) respectively, and measure the brightness changes of the headlights on the spot. Through this test, the changes in the brightness of the light source at different vehicle speeds can be recorded, and the specific impact of the vehicle speed on the brightness can be calculated based on these data. The ambient brightness influence coefficient is to test the brightness output of the headlights under different ambient lighting conditions (such as day, night, dim, etc.) to obtain the correction factor of the ambient brightness on the headlight brightness. These data will be stored in the database, so that in actual driving, according to the real-time collected vehicle speed and ambient brightness values, the headlight drive current can be dynamically adjusted to ensure the best lighting effect.

[0071] The specific implementation example of calculating the brightness driving current value of the headlight is as follows, and the following data is available: The reference current value for car light brightness is approximately: 1.572A.

[0072] The target brightness value of the headlights in the set area is approximately: 780.234.

[0073] The current brightness value of the headlight is approximately: 620.456.

[0074] The vehicle's current speed is approximately: 50.125.

[0075] The vehicle speed parameter value is approximately: 80.789.

[0076] The vehicle speed brightness influence coefficient stored in the database is approximately: 0.785.

[0077] The brightness current response index stored in the database is approximately: 1.23.

[0078] The ambient brightness parameter value is approximately: 950.345.

[0079] The current ambient brightness value within the setting area of ​​the headlight is approximately: 420.756.

[0080] The ambient brightness influence coefficient stored in the database is approximately: 0.328.

[0081] Substituting the above data into the specific formula for calculating the brightness driving current value of the headlight, we get: The brightness driving current value of the headlight = 1.572×(780.234 / 620.456) 1 / （1.23×0.785×（80.789 / 50.125））×exp(0.328×((950.345-420.756) / 950.345))≈2.186A.

[0082] In this implementation, by introducing a comprehensive analysis method of reference current, vehicle speed parameter value, ambient brightness parameter value and brightness current response index in the design and implementation, the brightness of the headlights can be accurately adjusted under different driving speeds and lighting conditions, significantly improving the intelligence and adaptability of vehicle lighting. Specifically, the brightness current response index is first obtained through experimental measurement and logarithmic linear fitting, and then combined with database parameters such as vehicle speed brightness influence coefficient and ambient brightness influence coefficient, the brightness driving current value of the headlights can be dynamically calculated. This not only allows the headlights to maintain ideal brightness when driving at high or low speeds, but also can automatically compensate for the light source according to changes in daytime, nighttime or dim environments. Output avoids the waste of resources and insufficient lighting caused by fixed parameter design. At the same time, in the process of measurement and data fitting, the differences in measurement methods such as LED thermal stability, illuminance meter or integrating sphere, as well as the heat dissipation and optical characteristics of the vehicle at different speeds are fully considered, making the solution more practical and robust. For the overall energy efficiency and driving safety of the vehicle, this method of optimizing the brightness of the headlights through real-time collection and dynamic adjustment can not only significantly extend the life of the LED and reduce energy consumption, but also maintain a stable lighting level under various complex road and weather conditions, thereby improving the clarity of the driver's field of vision and reaction time, which is of great significance to reducing traffic accidents and improving driving experience.

[0083] Specifically, the specific steps for analyzing the color temperature driving current value of the headlight are as follows: obtain the headlight color temperature reference current value, the color temperature adjustment amplitude value, and the environmental parameter set, the environmental parameter set including the ambient temperature parameter value and the ambient humidity parameter value; read the vehicle current speed value and the vehicle speed parameter value, and combine the headlight color temperature reference current value, the current headlight color temperature value, the headlight target color temperature value within the set area, the color temperature adjustment amplitude value, the current ambient temperature value within the set area of ​​the headlight, the current ambient humidity value, and the environmental parameter set for comprehensive analysis to obtain the color temperature driving current value of the headlight.

[0084] Among them, the color temperature reference current value of the headlight is the reference current of the LED under the default or standard color temperature conditions (such as the working state recommended by the LED manufacturer). It represents the driving current required for the LED to achieve the ideal spectral output under the "normal" color temperature.

[0085] The color temperature adjustment amplitude value indicates the maximum increment or variation range of the current allowed during the color temperature adjustment process, that is, the amount of current that the LED is allowed to increase or decrease within a safe range to achieve the target color temperature. The acquisition steps are: By gradually changing the driving current, the range of LED color temperature changes is recorded until the LED enters saturation or exceeds the safe operating area.

[0086] Analyze the data to find the maximum current increment that the LED can safely adjust while meeting the spectrum adjustment requirements.

[0087] Combined with the thermal characteristics and life requirements of the LED, determine an amplitude value that can meet the color temperature adjustment requirements without causing excessive heat load on the LED. This amplitude value can be used as the upper limit during system design (for example, 0.8A or other appropriate values).

[0088] The ambient temperature parameter value refers to a reference temperature selected as the ideal or standard ambient temperature in the experiment or design of LED color temperature adjustment. For example, the LED spectrum data measured under a certain standard temperature condition indoors or outdoors (such as 25°C, i.e. 298K) can be used as a reference.

[0089] The ambient humidity parameter value refers to the humidity reference used by the LED color temperature adjustment system under standard conditions (such as standard indoor humidity). It is used to compare with the current ambient humidity and correct the impact of humidity changes on the LED color temperature output.

[0090] The specific formula for calculating the color temperature driving current value of the headlight is as follows: ;in, is the color temperature driving current value of the headlight, is the reference current value of the headlight color temperature, is the target color temperature value of the headlight in the set area. is the current color temperature value of the headlight, is the color temperature influence coefficient stored in the database, is the ambient temperature parameter value, The current ambient temperature value in the setting area of ​​the headlight. is the ambient humidity parameter value, The current ambient humidity value in the setting area of ​​the headlight. is the temperature and humidity combined influence coefficient stored in the database, is the vehicle speed parameter, is the current speed of the vehicle, It is the vehicle speed color temperature influence coefficient stored in the database.

[0091] It needs to be explained that the color temperature influence coefficient stored in the database The specific steps for obtaining the color temperature are as follows: in laboratory or field tests, by adjusting the color temperature output of the headlights and recording the color temperature change data under different target color temperatures, current color temperatures and multiple sets of contrast environments (such as standard temperature, humidity or typical driving speed), these data are then subjected to regression or machine learning analysis to extract the key parameters of the color temperature response that changes with different environments and headlight states, and these parameters are solidified as color temperature influence coefficients in the database for real-time calculation of the color temperature drive current of the headlights.

[0092] Temperature and humidity combined influence coefficient stored in the database , Vehicle speed and color temperature influence coefficient The specific acquisition steps are as follows: in multi-condition tests, the color temperature changes of the headlights and the corresponding current and environmental feedback data are collected under different temperature, humidity and vehicle speed conditions, and regression or model fitting methods are used to quantify the coupled effects of temperature and humidity on color temperature and the dynamic effects of vehicle speed on color temperature. Finally, the fitted temperature and humidity joint influence coefficient and vehicle speed color temperature influence coefficient are stored in the database to provide real-time reference for the color temperature adjustment formula.

[0093] In this implementation scheme, through laboratory and field tests, regression and machine learning methods are used to extract the color temperature influence coefficient, temperature and humidity combined influence coefficient and vehicle speed color temperature influence coefficient from a large amount of LED color temperature adjustment data, and these key parameters are solidified into the database, providing a reliable basis for real-time calculation of the color temperature driving current of the headlights. This method can achieve precise adjustment of the LED driving current based on the difference between the target color temperature and the current color temperature, while comprehensively considering the dynamic influence of ambient temperature, humidity and vehicle speed, to ensure that the headlights can output the expected color temperature under various working conditions, thereby effectively avoiding the problem of insufficient or excessive adjustment caused by fixed parameter design. This scheme fully considers the thermal characteristics and working life of LEDs, optimizes energy utilization, reduces energy waste, and greatly improves the adaptability and safety of headlights under complex roads and environmental changes through a real-time feedback mechanism, providing solid technical support for intelligent driving and energy conservation and environmental protection.

[0094] Specifically, the specific steps for analyzing the light beam angle driving current value of the headlight are as follows: obtain the light beam angle reference current value of the headlight; read the current speed value of the vehicle and the vehicle speed parameter value, and perform a comprehensive analysis based on the light color temperature reference current value, the current light beam angle value of the headlight, and the target light beam angle value of the headlight in the set area to obtain the light beam angle driving current value of the headlight.

[0095] The reference current value of the headlight beam angle is the reference current of the LED working at the default or standard beam angle (such as the working state recommended by the LED manufacturer). It represents the driving current required for the LED to achieve the ideal spectral output at the "normal" beam angle.

[0096] The specific formula for calculating the beam angle driving current value of the headlight is as follows: ;in, is the driving current value of the light beam angle of the car lamp, is the reference current value of the headlight beam angle, is the target beam angle value of the headlight in the set area. is the current light beam angle value of the headlight, is the beam angle attenuation coefficient stored in the database, is the beam angle adjustment coefficient stored in the database, is the current speed of the vehicle, is the vehicle speed parameter, is the vehicle speed beam angle attenuation coefficient stored in the database, It is the vehicle speed beam angle adjustment coefficient stored in the database.

[0097] Among them, the sigmoid function is: sigmoid (x) = 1 / (1 + e -x ).

[0098] It should be explained that the beam angle attenuation coefficient stored in the database , beam angle adjustment coefficient The specific steps for obtaining are as follows: in an experimental environment, by changing the light beam angle of the car headlights and recording its optical output, energy consumption and lighting effect at different target angles and current angles, and measuring the temperature and power of the LED chip and other information, after obtaining multiple sets of data, the angle deviation and the corresponding current response are fitted using regression or machine learning methods, and then the light beam angle attenuation coefficient and adjustment coefficient are extracted, and these parameters are solidified into the database for real-time call of the formula.

[0099] The vehicle speed beam angle attenuation coefficient stored in the database , Vehicle speed beam angle adjustment coefficient The specific acquisition steps are as follows: Similarly, perform a dynamic adjustment test on the headlight beam angle under different vehicle speed conditions, record the deviation between the target angle and the current angle, and the corresponding power, temperature, lighting quality and other data, and combine the vehicle speed information to find out the influence of vehicle speed changes on beam angle attenuation and adjustment through regression or modeling analysis, and store the fitted vehicle speed beam angle attenuation coefficient and adjustment coefficient in the database for real-time control.

[0100] In this implementation scheme, by dynamically adjusting the light beam angle of the headlight in an experimental environment, the optical output, energy consumption, LED chip temperature and power data at different target angles and current angles are systematically recorded, and regression or machine learning methods are used to fit the angle deviation and the corresponding current response, so as to extract the light beam angle attenuation coefficient and the adjustment coefficient and store them in a database; at the same time, under different vehicle speed conditions, by testing the deviation between the target angle and the actual angle and the relevant power consumption and lighting quality data, modeling is used to analyze the influence of vehicle speed on the light beam angle adjustment, and the vehicle speed light beam angle attenuation coefficient and the adjustment coefficient are determined and stored. By calling these database parameters in real time, the system can combine the current angle of the headlight, the target angle and the vehicle speed to accurately calculate the required light beam angle driving current, so as to realize intelligent control of the headlight under different driving conditions, thereby ensuring that the lighting effect is always in the optimal state, reducing energy waste, extending the service life of the LED, and significantly improving the safety and energy efficiency of the entire headlight system.

[0101] See also Figure 3 A headlight comprises: a data acquisition module for acquiring a current speed value of a vehicle, a current state parameter set of the headlight, and a current environment state parameter set in a set area; a light source driving module for analyzing a headlight driving current set based on the current speed value of the vehicle, the current state parameter set of the headlight, and the current environment state parameter set in the set area, and sending a light source driving instruction to the headlight; and an execution module for receiving the light source driving instruction and executing a light source driving operation on the headlight.

[0102] In summary, this application has at least the following effects: By introducing a pre-trained target analysis model, real-time collection and data fusion of the vehicle's current speed, headlight status and regional environmental parameters are achieved, so that the target states of headlight brightness, color temperature and beam angle can be dynamically generated. As a result, the drive module can automatically adjust the drive current set according to real-time data, thereby accurately matching actual lighting needs under various road and environmental conditions, effectively improving lighting effects and energy utilization efficiency, and avoiding blind spots and resource waste caused by fixed parameter design.

[0103] Multi-dimensional parameter calibration and database storage of influencing coefficients are adopted, and targeted calculation logic is established for the driving current of brightness, color temperature and beam angle respectively, fully considering the comprehensive influence of LED nonlinear response, ambient brightness, temperature and humidity and vehicle speed. Through experimental calibration and data fitting, the brightness current response index, color temperature adjustment amplitude, beam angle attenuation and adjustment coefficient are obtained, so that the driving module can finely control each optical parameter, effectively overcoming the problem of fixed parameters and inability to respond to environmental changes in real time in the existing technology, thereby reducing energy waste and extending the life of LED.

[0104] An intelligent light source driving system is formed through the three modules of target analysis unit, current analysis unit and driving unit. It can not only generate the target state parameters of the headlights based on real-time data, but also extract and fuse the data features through multi-level and deep neural networks, so as to achieve precise control of the brightness, color temperature and beam angle of the headlights. Compared with traditional technologies, this solution can flexibly adapt to complex roads and environmental changes, ensure balanced and stable operation of lighting, and greatly improve energy utilization and reduce system power consumption, providing stronger technical support for the overall energy efficiency and driving experience of the vehicle.

[0105] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0106] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A light source driving module, characterized in that: include: A target analysis unit is used to monitor the current speed value of the vehicle, the current state parameter set of the headlights, and the current environment state parameter set in a set area, and input them into a pre-trained target analysis model for data analysis to obtain a target state parameter set of the headlights in the set area, wherein the current state parameter set includes a current headlight brightness value, a current headlight color temperature value, and a current headlight beam angle value, the current environment state parameter set includes a current environment brightness value, a current environment temperature value, and a current environment humidity value, and the target state parameter set includes a headlight target brightness value, a headlight target color temperature value, and a headlight target beam angle value; A current analysis unit, used to analyze a driving current set of the headlight based on a target state parameter set of the headlight in a set area, wherein the driving current set includes a brightness driving current value, a color temperature driving current value, and a beam angle driving current value; The driving unit is used to send a light source driving instruction to the vehicle lamp based on the vehicle lamp driving current set.

2. The light source driving module according to claim 1, characterized in that: The target analysis model is specifically a deep neural network model, which consists of an input layer, several hidden layers, and an output layer, wherein: The input layer is used to receive the current speed value of the vehicle, the current state parameter set of the headlights, and the current state parameter set of the environment in the set area, and perform preprocessing; The hidden layer is used to perform feature analysis on the preprocessed current speed value of the vehicle, the current state parameter set of the headlights, and the current state parameter set of the environment in the set area; The output layer is used to convert the feature analysis results of the hidden layer into a target state parameter set of the headlights in a set area.

3. The light source driving module according to claim 1, characterized in that: The specific steps to analyze the brightness driving current value of the car lights are as follows: Obtain the reference current value of the headlight brightness, the vehicle speed parameter value, and the ambient brightness parameter value; The brightness current response index is obtained, and a comprehensive analysis is performed based on the current vehicle speed value, the vehicle speed parameter value, the headlight brightness reference current value, the current headlight brightness value, the headlight target brightness value within the set area, the current ambient brightness value within the set area of ​​the headlight, and the ambient brightness parameter value to obtain the headlight brightness driving current value.

4. The light source driving module according to claim 3, characterized in that: The specific steps to obtain the brightness current response index are as follows: Pass several measuring currents into the light source, and record the brightness value of the light source under each measuring current; Perform logarithmic linearization on the brightness value of the light source under each measurement current; After logarithmic linearization, data fitting analysis is performed on the brightness value of the light source at each measurement current to obtain the brightness current response index.

5. The light source driving module according to claim 3, characterized in that: The specific formula for calculating the brightness driving current value of the headlight is as follows: ; in, is the driving current value of the headlight brightness, is the reference current value of the headlight brightness, is the target brightness value of the headlight in the set area, is the current brightness value of the headlight, , They are the current speed value of the vehicle and the parameter value of the vehicle speed. , They are the vehicle speed brightness influence coefficient and brightness current response index stored in the database. is the ambient brightness parameter value, The current ambient brightness value within the set area of ​​the headlight. It is the environmental brightness influence coefficient stored in the database.

6. The light source driving module according to claim 3, characterized in that: The specific steps to analyze the color temperature driving current value of the car light are as follows: Obtaining a vehicle lamp color temperature reference current value, a color temperature adjustment amplitude value, and an environmental parameter set, wherein the environmental parameter set includes an environmental temperature parameter value and an environmental humidity parameter value; The current speed value of the vehicle and the vehicle speed parameter value are read, and a comprehensive analysis is performed based on the light color temperature reference current value, the current light color temperature value, the light target color temperature value within the set area, the color temperature adjustment amplitude value, the current ambient temperature value within the set area of ​​the light, the current ambient humidity value, and the environmental parameter set to obtain the light color temperature driving current value.

7. The light source driving module according to claim 6, characterized in that: The specific formula for calculating the color temperature driving current value of the headlight is as follows: ; in, is the color temperature driving current value of the headlight, is the reference current value of the headlight color temperature, is the target color temperature value of the headlight in the set area. is the current color temperature value of the headlight, is the color temperature influence coefficient stored in the database, is the ambient temperature parameter value, The current ambient temperature value in the setting area of ​​the headlight. is the ambient humidity parameter value, The current ambient humidity value in the setting area of ​​the headlight. is the temperature and humidity combined influence coefficient stored in the database, , They are the vehicle speed parameter value and the vehicle current speed value. It is the vehicle speed color temperature influence coefficient stored in the database.

8. The light source driving module according to claim 3, characterized in that: The specific steps to analyze the beam angle driving current value of the headlight are as follows: Get the reference current value of the light beam angle of the vehicle headlight; The current speed value of the vehicle and the vehicle speed parameter value are read, and a comprehensive analysis is performed in combination with the reference current value of the color temperature of the lamp, the current light beam angle value of the lamp, and the target light beam angle value of the lamp in the set area to obtain the light beam angle driving current value of the lamp.

9. The light source driving module according to claim 8, characterized in that: The specific formula for calculating the beam angle driving current value of the headlight is as follows: ; in, is the driving current value of the light beam angle of the car lamp, is the reference current value of the headlight beam angle, is the target beam angle value of the headlight in the set area. is the current light beam angle value of the headlight, , They are the beam angle attenuation coefficient and beam angle adjustment coefficient stored in the database, , They are the current speed value of the vehicle and the parameter value of the vehicle speed. , They are the vehicle speed beam angle attenuation coefficient and the vehicle speed beam angle adjustment coefficient stored in the database respectively.

10. A vehicle lamp, using the light source driving module according to any one of claims 1 to 9, characterized in that: include: A data acquisition module is used to obtain the current speed value of the vehicle, the current state parameter set of the headlights, and the current state parameter set of the environment in the set area; A light source driving module, used to analyze the light source driving current set based on the current speed value of the vehicle, the current state parameter set of the light, and the current environmental state parameter set in the set area, and send a light source driving instruction to the light; The execution module is used to receive the light source driving instruction and execute the light source driving operation on the vehicle lamp.

Images