Automotive glass adjusting method, device and equipment based on neural network and medium

Abstract

The invention discloses an automobile glass adjusting method, device and equipment based on a neural network and a medium, and relates to the technical field of vehicle thermal management control, and the method comprises the steps: obtaining vehicle driving data, inputting the vehicle driving data into a preset neural network model for processing, obtaining output data, obtaining adjusting parameters of vehicle window glass according to the output data, and adjusting the vehicle window glass according to the adjusting parameters. And adjusting the window glass according to the adjusting parameters. The vehicle window light transmission is intelligently adjusted through the neural network, heat management is accurately regulated and controlled, vehicle energy consumption is reduced, and the driving comfort is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle thermal management control, and in particular to a method, device, equipment and medium for adjusting automobile glass based on a neural network. Background Art

[0002] With the rapid advancement of new energy commercial vehicle technology, this type of vehicle is gradually dominating the market. Compared with traditional fuel vehicles, new energy commercial vehicles mainly rely on batteries and electric motors for power, which brings higher energy efficiency requirements and thermal management challenges. In particular, battery temperature management is crucial to vehicle performance and life. At the same time, maintaining the comfort of passengers in the car is also an important consideration, which requires that the interior of the vehicle must be maintained within a suitable temperature range. Against this background, the intelligent glass temperature control system came into being, aiming to use intelligent material technology to automatically adjust the light transmittance of the window to respond to environmental changes and maintain a comfortable light and temperature environment in the cabin.

[0003] The new energy commercial vehicles currently on the market generally adopt non-intelligent adjustment mechanisms. Traditional windows do not have the ability to automatically adjust light transmittance and cannot effectively respond to changes in light intensity, affecting the lighting and temperature management inside the vehicle. They also ignore driving safety. The adjustment of the front windshield may affect the driving vision due to being too dark, posing a safety hazard.

[0004] In some cases, due to the lack of precise environmental adaptability, traditional thermal management systems often rely too much on air conditioning systems, resulting in high energy consumption, and a single or fixed adjustment method cannot accurately match passengers' different needs for temperature and lighting, affecting the riding experience. The system's response to environmental changes is not flexible enough, especially under complex and changeable climate conditions, and the regulation effect is limited. In smart glass adjustment, the adjustment of the front windshield may affect the driver's field of vision due to excessive darkening, increasing the risk of accidents. Summary of the invention

[0005] The main purpose of this application is to provide a method, device, equipment and medium for adjusting automobile glass based on a neural network, aiming to solve the technical problem of how to intelligently adjust the light transmittance of the car window to control the temperature inside the car.

[0006] To achieve the above objectives, the present application proposes a method for adjusting automobile glass based on a neural network, the method comprising:

[0007] Obtain vehicle driving data;

[0008] Input the vehicle driving data into a preset neural network model for processing to obtain output data;

[0009] According to the output data, obtaining adjustment parameters of the vehicle window glass;

[0010] The vehicle window glass is adjusted according to the adjustment parameters.

[0011] Optionally, the preset neural network model includes at least an input layer, two hidden layers and an output layer, the input layer contains a first preset number of nodes, the hidden layer uses a ReLU activation function, and the output layer contains a second preset number of nodes and uses a Sigmoid activation function.

[0012] Optionally, before the vehicle driving data is processed by a preset neural network to obtain output data, the method includes:

[0013] Obtain vehicle driving sample data and establish an initial neural network model;

[0014] The initial neural network model is trained according to the vehicle driving sample data to obtain a preset neural network model.

[0015] Optionally, the training of the initial neural network model according to the vehicle driving sample data to obtain a preset neural network model includes:

[0016] Initializing model parameters of the initial neural network model;

[0017] Get input data;

[0018] Normalizing the input data to obtain processed input data;

[0019] Inputting the processed input data into the initial neural network model to obtain predicted output data;

[0020] According to the loss function calculation, the error value between the predicted output data and the actual data is obtained;

[0021] Get the learning rate;

[0022] The model parameters are iteratively updated through an optimization algorithm according to the learning rate until a maximum number of iterations is reached or the error value calculated by the loss function converges to a preset threshold, thereby obtaining a preset neural network model.

[0023] Optionally, inputting the processed input data into the initial neural network model to obtain predicted output data includes:

[0024] The input data of the input layer is calculated by linear change to obtain the input data of the hidden layer;

[0025] The input data of the hidden layer is calculated by a nonlinear ReLU activation function to obtain the output data of the hidden layer;

[0026] The output data of the hidden layer is first subjected to linear change calculation and then to nonlinear ReLU activation function calculation until the output data of the last hidden layer is obtained;

[0027] The output data of the last hidden layer is used as the input data of the output layer, and is calculated according to the nonlinear Sigmoid activation function to obtain the predicted output data.

[0028] Optionally, after the initial neural network model is trained according to the vehicle driving sample data to obtain a preset neural network model, the method further comprises:

[0029] Evaluating the preset neural network model to obtain an evaluation result;

[0030] If the evaluation result does not meet the control requirement, the preset neural network model is retrained until the control requirement is met.

[0031] Optionally, adjusting the vehicle window glass according to the adjustment parameter includes:

[0032] The front windshield of the automobile is evenly divided into a first area, a second area, a third area and a fourth area;

[0033] According to the adjustment parameters, the glass transmittance adjustment voltage and the cab setting temperature are obtained;

[0034] The voltage is adjusted according to the glass transmittance and the set temperature of the cab, and the first area, the second area, the third area and the fourth area are adjusted accordingly to maintain the temperature inside the vehicle at a comfortable driving temperature.

[0035] In addition, to achieve the above-mentioned purpose, the present application also proposes a vehicle glass adjustment device based on a neural network, and the vehicle glass adjustment device based on a neural network includes:

[0036] An acquisition module, used for acquiring vehicle driving data;

[0037] A processing module, used to input the vehicle driving data into a preset neural network model for processing to obtain output data;

[0038] An acquisition module, used for obtaining adjustment parameters of the vehicle window glass according to the output data;

[0039] The adjustment module is used to adjust the vehicle window glass according to the adjustment parameters.

[0040] In addition, to achieve the above-mentioned purpose, the present application also proposes a medium, which is a computer-readable medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the neural network-based automobile glass adjustment method as described above are implemented.

[0041] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, it implements the steps of the automobile glass adjustment method based on neural network as described above.

[0042] The application obtains vehicle driving data, processes the vehicle driving data into a preset neural network model, obtains output data, obtains adjustment parameters of the window glass based on the output data, and adjusts the window glass based on the adjustment parameters. By using the neural network to intelligently adjust the light transmittance of the window and accurately control thermal management, the vehicle energy consumption is reduced and driving comfort is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the embodiments of the present application 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, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0044] Figure 1 This is a flow chart of the first embodiment of the neural network-based automobile glass adjustment method of the present application;

[0045] Figure 2 A schematic diagram of the front windshield segmentation of the first embodiment of the automobile glass adjustment method based on a neural network of the present application;

[0046] Figure 3 This is a flow chart of a second embodiment of the neural network-based automobile glass adjustment method of the present application;

[0047] Figure 4 This is a schematic diagram of the module structure of a vehicle glass adjustment device based on a neural network according to an embodiment of the present application;

[0048] Figure 5 Schematic diagram of the device structure of the hardware operating environment involved in the neural network-based automobile glass adjustment method in the embodiment of the present application.

[0049] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0050] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0051] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0052] The main solution of the embodiment of the present application is: obtaining vehicle driving data, inputting a preset neural network model for processing according to the vehicle driving data, obtaining output data, obtaining adjustment parameters of the vehicle window glass according to the output data, and adjusting the vehicle window glass according to the adjustment parameters.

[0053] Based on this, the embodiment of the present application provides a method for adjusting automobile glass based on a neural network, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the neural network-based automobile glass adjustment method of the present application.

[0054] In this embodiment, the automobile glass adjustment method based on neural network includes steps S10 to S40:

[0055] Step S10, obtaining vehicle driving data.

[0056] It should be noted that obtaining vehicle driving data is a basic and critical operation in the intelligent thermal management system of new energy commercial vehicles. Using multi-sensor fusion technology, the system integrates temperature sensors, humidity sensors, ambient temperature sensors, pressure sensors, etc., and realizes comprehensive perception of the thermal management system through data fusion and deep learning algorithms. This process involves the precise deployment of multiple sensors and real-time data collection, aiming to fully grasp the key indicators of the vehicle during operation, so as to provide accurate information support for subsequent intelligent analysis and dynamic adjustment. Acquiring vehicle status data includes data acquisition by multiple sensors, including temperature sensors, humidity sensors, ambient light sensors, and refrigerant pressure sensors. Through the temperature sensors installed in the cab, battery system, cooling system and the outside environment, the cab temperature, battery operating temperature, radiator temperature and outside environment temperature are monitored in real time. These data are essential for evaluating the vehicle heat load, adjusting the air conditioning system and ensuring battery safety. By arranging humidity sensors in the cab, the humidity level is monitored because humidity directly affects human comfort. By deploying ambient light sensors, although they are not directly involved in thermal management control in the thermal management system, they can provide light intensity information and indirectly assist the intelligent system in determining whether to enable or adjust lighting equipment, thereby indirectly affecting energy consumption.

[0057] Step S20, inputting the vehicle driving data into a preset neural network model for processing to obtain output data.

[0058] It should be noted that the neural network model includes but is not limited to the use of a multi-layer perceptron (MLP) neural network model. The preset neural network model includes at least an input layer, two hidden layers and an output layer. The input layer includes a first preset number of nodes, the hidden layer uses a ReLU activation function, and the output layer includes a second preset number of nodes, using a Sigmoid activation function. Specifically, the input layer is responsible for receiving data from multiple sensors, including the temperature in the cab, the temperature outside the car, the temperature difference between the inside and outside of the car, the light intensity, the humidity, and the time information, a total of six key parameters, that is, the first preset number of nodes in the input layer is 6. These parameters are normalized and converted into format data that is easy for the neural network to process. Both hidden layers use 64 neurons and a ReLU (Rectified Linear Unit) activation function. The ReLU activation function is widely used in deep learning models because it is simple and can effectively alleviate the problem of gradient disappearance. It makes the neuron output a positive value of the input value, or zero, which helps the model learn nonlinear features. The output layer uses a Sigmoid activation function, and outputs a second preset number of nodes corresponding to two key parameters: the smart glass transmittance adjustment voltage and the cab temperature setting parameter. The model uses the MLP neural network architecture to perform deep learning and feature extraction on the input data through a series of linear transformations and nonlinear activation functions, such as ReLU or Sigmoid functions. During the training process, the model uses a large amount of historical data to optimize the weights and bias parameters through the back propagation algorithm to minimize the error between the predicted output and the actual label. The mean square error (MSE) or cross-entropy loss (Cross-Entropy Loss) is often used as the loss function, and then the parameters are iteratively updated to minimize the error and obtain the final neural network model. The output result is obtained by integrating the multi-sensor data inside and outside the vehicle, including key parameters such as the temperature and humidity in the cab and the ambient temperature outside the vehicle. After preprocessing, these data are used as the input of the neural network model, and then after passing through the neural network model, the output result is obtained.

[0059] Step S30, obtaining adjustment parameters of the vehicle window glass according to the output data.

[0060] It should be understood that the adjustment parameters required for the window glass can be accurately calculated based on the output data collected from the sensor and processed by the neural network algorithm. These parameters mainly include the glass transmittance adjustment voltage and the target temperature setting value of the cab, which together guide the change of the light transmittance of the window glass and the temperature adjustment of the air conditioning system in the car, thereby ensuring the comfort and energy efficiency of the interior environment. The glass transmittance adjustment voltage is used as a direct control signal to drive the smart material in the window to change its optical properties. This change is dynamic and can be automatically adjusted according to the external light intensity. When the external sunlight is strong, the glass transmittance decreases to reduce the heat intake. On the contrary, the light transmittance is appropriately increased to ensure sufficient natural light. Such an adjustment mechanism effectively suppresses the drastic fluctuations in the temperature inside the car, reduces the load on the air conditioning system, and improves energy efficiency. The cab temperature setting parameter provides a target temperature reference for the intelligent thermal management system. According to the difference between this set value and the actual detected cab temperature, the air conditioning system is instructed to perform corresponding heating or cooling operations to ensure that the cab is maintained within a predetermined comfortable temperature range. In addition, the system can also predict and adjust in advance based on time factors (such as morning and evening, seasonal changes) and actual driving environments (such as urban congestion, high-speed driving, etc.) to cope with upcoming environmental changes, further improving the forward-looking and intelligent level of regulation. Through real-time monitoring and flexible response, the intelligent thermal management system ensures that no matter how the external environment changes, the car can always maintain an energy-saving, environmentally friendly and comfortable riding space, demonstrating the technological progress and innovative advantages of new energy commercial vehicles in improving user experience.

[0061] Step S40, adjusting the vehicle window glass according to the adjustment parameters.

[0062] It should be noted that the front windshield of the automobile is evenly divided into a first area, a second area, a third area and a fourth area. Specifically, Figure 2 The front windshield segmentation diagram shown in the figure divides the front windshield into four evenly spaced areas, 0 to d 1 , d 1 ~d 2 , d 2 ~d 3 , d 3 ~d 4 . According to the adjustment parameters, the glass transmittance adjustment voltage and the cab setting temperature are obtained. According to the glass transmittance adjustment voltage and the cab setting temperature, the first area, the second area, the third area and the fourth area are adjusted accordingly to maintain the temperature inside the car at a comfortable driving temperature. Specifically, according to the results obtained after inputting the preset neural network model, the two adjustment parameters of the intelligent glass transmittance adjustment voltage and the cab temperature setting parameter are analyzed and obtained. Then, according to the intelligent glass transmittance adjustment voltage and the cab temperature setting parameter, combined with the current sunlight intensity and the current weather conditions, the 0~d1 , d 1 ~d 2 , d 2 ~d 3 , d 3 ~d 4 The four areas make a comprehensive assessment of the light transmittance of the window glass and the temperature of the cockpit air-conditioning system, and then adjust them to keep the vehicle's cab in a comfortable driving environment.

[0063] This embodiment provides a method for adjusting automobile glass based on a neural network, which obtains vehicle driving data, processes the vehicle driving data according to a preset neural network model, obtains output data, obtains adjustment parameters of the window glass according to the output data, and adjusts the window glass according to the adjustment parameters. By using a neural network to intelligently adjust the light transmittance of the window and accurately control thermal management, the vehicle energy consumption is reduced and driving comfort is improved.

[0064] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above-mentioned embodiment 1 can refer to the above introduction, and will not be repeated later. Figure 3 The neural network-based automobile glass adjustment method step S20 also includes steps S201 to S202:

[0065] Step S201, obtaining vehicle driving sample data and establishing an initial neural network model.

[0066] It should be noted that in order to achieve precise control of the intelligent glass temperature adjustment technology in the intelligent thermal management system, it is necessary to first obtain rich vehicle driving sample data. These data cover a wide range of driving environments, including different time periods (morning, noon, evening and night), different seasons (spring, summer, autumn and winter), various weather conditions (sunny, rainy, cloudy, etc.) and diverse road conditions such as cities, suburbs and highways. The sample data specifically includes information such as the temperature inside and outside the car, light intensity, cabin humidity and vehicle operating status, which are collected and recorded in real time through the on-board sensor module. Based on these comprehensive sample data, the initial neural network model is established next. The model design needs to consider the reasonable configuration of the input layer, hidden layer and output layer of the neural network. The input layer is designed with 6 nodes, corresponding to the 6 key environmental parameters collected, to ensure that the model can receive all relevant input information. The hidden layer adopts a two-layer structure, each layer is configured with 64 neurons, and uses the ReLU activation function, which can effectively handle nonlinear relationships and improve the model's adaptability to complex environments. Two nodes are designed in the output layer. The output value includes the information of two parameters: the smart glass transmittance adjustment voltage and the cab temperature setting parameter. The Sigmoid activation function is used to ensure that the output value is within a reasonable range.

[0067] The initial neural network model is improved and updated through machine learning methods to intelligently manage the glass of new energy commercial vehicles, ensuring that the vehicle thermal management system can operate efficiently under various working conditions while improving energy efficiency and ride comfort.

[0068] Step S202, training the initial neural network model according to the vehicle driving sample data to obtain a preset neural network model.

[0069] It should be understood that to train the initial thermal management deep learning model, first initialize the model parameters, obtain input data, and then normalize the input data to obtain processed input data, and input the processed input data into the initial neural network model to obtain predicted output data, and then calculate according to the loss function to obtain the error value between the predicted output data and the actual data, obtain the learning rate, and finally iteratively update the model parameters through the optimization algorithm according to the learning rate until the maximum number of iterations is reached or the error value calculated by the loss function converges to the preset threshold, and the preset neural network model is obtained. Specifically, first, collect vehicle status data covering multiple dimensions such as temperature, humidity, ambient light, time, etc. inside and outside the cab, clean and normalize them, eliminate noise and outliers, and form a high-quality training data set. The specific normalization is according to the formula:

[0070]

[0071] Normalize the input data to between 0 and 1 to facilitate neural network processing.

[0072] The data set is divided into training set, validation set and test set in a certain proportion, generally with a ratio of 70%, 15%, and 15%, to ensure that the training, tuning and generalization ability evaluation of the model are scientific and reasonable. Then, these data sets are used to train the initial model. The model adopts a multi-layer perceptron structure, including a carefully designed input layer, two hidden layers and an output layer. During the training process, the model predicts the output through forward propagation calculation, and the input data of the input layer is calculated through linear change to obtain the input data of the hidden layer. Specifically, the input data of the first hidden layer is obtained by the following formula:

[0073] Z( 1 )=W( 1 )x+b( 1 )

[0074] Where Z (1) is the input value of the first hidden layer, W (1) is the weight matrix of the first hidden layer, which indicates the connection strength between the input layer and the hidden layer. x is the input data of the input layer, and b (1)It is a bias vector used to adjust the activation value of the hidden layer. The superscript represents the data of the hidden layer. Each hidden layer has a different weight matrix and bias vector.

[0075] The input data of the hidden layer is calculated through the nonlinear ReLU activation function to obtain the output data of the first hidden layer. Specifically, it is obtained by the following formula:

[0076] A (1 )=ReLU(z (1) )

[0077] Among them, A (1) The output data of the first hidden layer. This means that for the input data, the output of the ReLU function is a larger value between 0 and 1. If the input data is greater than 0, the output is 1; if the input data is less than or equal to 0, the output is 0. According to the above two formulas, the output data of the hidden layer is first calculated by linear change and then by nonlinear ReLU activation function until the output data Z of the last hidden layer is obtained. (2) and A (2) , the output data of the last hidden layer is used as the input data of the output layer, and is calculated according to the nonlinear Sigmoid activation function. Thus, the predicted output data is obtained. Specifically, it is obtained according to the following formula:

[0078] Z( 3 )=W( 3 )A( 2 )+b( 3 )

[0079] Y=Sigmoid(Z (3) )

[0080] Among them, Z (3) is the input value of the output layer, W (3) is the weight matrix of the output layer, which represents the connection strength between the output layer and the second hidden layer. (2) is the input data of the second hidden layer, b (3) is the bias vector, and Y is the output value of the output layer.

[0081] In this embodiment, the error value between the predicted result and the actual result is obtained by using the mean square error MSE as the loss function, specifically:

[0082]

[0083] Among them, Y i It is real data. is the predicted data, and m is the number of samples. Subsequently, the stochastic gradient descent optimization strategy is adopted to obtain the learning rate a and gradually adjust the model parameters until the loss function converges or reaches the predetermined number of iterations. This process is repeated to gradually approach the global optimal solution. During the entire training phase, it is also necessary to pay close attention to the overfitting problem of the model and use regularization, dropout and other techniques to alleviate it when appropriate. The model hyperparameters, such as learning rate and number of hidden layer nodes, are continuously adjusted through cross-validation and other means to optimize the model performance. After obtaining the preset neural network model, the preset neural network model is evaluated to obtain the evaluation result. If the evaluation result does not meet the thermal management control requirements, the preset neural network model is retrained until it meets the thermal management control requirements; if the evaluation result meets the thermal management control requirements, the preset neural network model is used as the final neural network model, and the vehicle driving data is analyzed.

[0084] This embodiment obtains vehicle driving sample data and establishes an initial neural network model. The initial neural network model is trained according to the vehicle driving sample data to obtain a preset neural network model. By establishing the neural network model, corresponding changes in glass control can be made in real time according to environmental changes through training and optimization.

[0085] This application also provides a vehicle glass adjustment device based on a neural network, please refer to Figure 4 , the device comprises:

[0086] An acquisition module 10 is used to acquire vehicle driving data;

[0087] The processing module 20 is used to process the vehicle driving data input into a preset neural network model to obtain output data;

[0088] An acquisition module 10 is used to obtain adjustment parameters of the vehicle window glass according to the output data;

[0089] The adjustment module 30 is used to adjust the vehicle window glass according to the adjustment parameters.

[0090] The automobile glass adjustment device based on a neural network provided by the present application adopts the automobile glass adjustment method based on a neural network in the above-mentioned embodiment, and can solve the technical problem of how to intelligently adjust the light transmittance of the car window to control the temperature inside the car. Compared with the prior art, the beneficial effects of the automobile glass adjustment device based on a neural network provided by the present application are the same as the beneficial effects of the automobile glass adjustment method based on a neural network provided by the above-mentioned embodiment, and the other technical features of the automobile glass adjustment device based on a neural network are the same as the features disclosed in the above-mentioned embodiment method, which will not be repeated here.

[0091] In one embodiment, the processing module 20 is further used to obtain vehicle driving sample data and establish an initial neural network model; the initial neural network model is trained according to the vehicle driving sample data to obtain a preset neural network model.

[0092] In one embodiment, the processing module 20 is also used to initialize the model parameters of the initial neural network model; obtain input data; normalize the input data to obtain processed input data; input the processed input data into the initial neural network model to obtain predicted output data; calculate according to the loss function to obtain the error value between the predicted output data and the actual data; obtain the learning rate; iteratively update the model parameters through the optimization algorithm according to the learning rate until the maximum number of iterations is reached or the error value calculated by the loss function converges to a preset threshold, thereby obtaining a preset neural network model.

[0093] In one embodiment, the processing module 20 is further used to perform linear change calculation on the input data of the input layer to obtain the input data of the hidden layer; perform nonlinear ReLU activation function calculation on the input data of the hidden layer to obtain the output data of the hidden layer; perform linear change calculation on the output data of the hidden layer and then perform nonlinear ReLU activation function calculation on the output data of the hidden layer until the output data of the last hidden layer is obtained; and use the output data of the last hidden layer as the input data of the output layer, perform calculation according to the nonlinear Sigmoid activation function, and obtain predicted output data.

[0094] In one embodiment, the processing module 20 is further used to evaluate the preset neural network model to obtain an evaluation result; if the evaluation result does not meet the control requirement, the preset neural network model is retrained until the control requirement is met.

[0095] In one embodiment, the adjustment module 30 is also used to evenly divide the front windshield of the automobile into a first area, a second area, a third area and a fourth area; obtain the glass transmittance adjustment voltage and the cab set temperature according to the adjustment parameters; and adjust the first area, the second area, the third area and the fourth area accordingly according to the glass transmittance adjustment voltage and the cab set temperature to maintain the temperature inside the vehicle at a comfortable driving temperature.

[0096] The present application provides a neural network-based automobile glass adjustment device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the neural network-based automobile glass adjustment method in the above-mentioned embodiment one.

[0097] Reference below Figure 5, which shows a schematic diagram of the structure of a vehicle glass adjustment device based on a neural network suitable for implementing the embodiment of the present application. The vehicle glass adjustment device based on a neural network in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle terminals (such as vehicle navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 5 The neural network-based automobile glass adjustment device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0098] like Figure 5 As shown, the automobile glass adjustment device based on the neural network may include a processing device 1001 (such as a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM: Read Only Memory) 1002 or the program loaded from the storage device 1003 to the random access memory (RAM: Random Access Memory) 1004. In the RAM 1004, various programs and data required for the operation of the automobile glass adjustment device based on the neural network are also stored. The processing device 1001, the ROM 1002 and the RAM 1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems may be connected to the I / O interface 1006: input devices 1007 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 1003 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 1009. The communication device 1009 may allow the neural network-based automobile glass adjustment device to communicate wirelessly or wired with other devices to exchange data. Although the figure shows a neural network-based automobile glass adjustment device with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems may be implemented or have instead.

[0099] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0100] The automobile glass adjustment device based on a neural network provided by the present application adopts the automobile glass adjustment method based on a neural network in the above-mentioned embodiment, which can solve the technical problem of how to intelligently adjust the light transmittance of the car window to control the temperature inside the car. Compared with the prior art, the beneficial effects of the automobile glass adjustment device based on a neural network provided by the present application are the same as the beneficial effects of the automobile glass adjustment method based on a neural network provided by the above-mentioned embodiment, and the other technical features of the automobile glass adjustment device based on a neural network are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0101] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0102] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0103] The present application provides a computer-readable medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the neural network-based automobile glass adjustment method in the above-mentioned embodiment.

[0104] The computer-readable medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above.

[0105] The computer-readable medium may be included in the automobile glass adjustment device based on a neural network; or may exist independently without being assembled into the automobile glass adjustment device based on a neural network.

[0106] The computer-readable medium carries one or more programs, and when the one or more programs are executed by the neural network-based automobile glass adjustment device, the neural network-based automobile glass adjustment device can write computer program codes for performing the operations of the present application in one or more programming languages ​​or a combination thereof, and the programming languages ​​include object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, through the Internet using an Internet service provider).

[0107] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0108] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0109] The readable medium provided by the present application is a computer-readable medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned neural network-based automobile glass adjustment method, and can solve the technical problem of how to intelligently adjust the light transmittance of the car window to control the temperature inside the car. Compared with the prior art, the beneficial effects of the computer-readable medium provided by the present application are the same as the beneficial effects of the neural network-based automobile glass adjustment method provided by the above-mentioned embodiment, and will not be repeated here.

[0110] The present application also provides a computer program product, including a computer program, which implements the steps of the above-mentioned neural network-based automobile glass adjustment method when executed by a processor.

[0111] The computer program product provided by the present application can solve the technical problem of how to intelligently adjust the light transmittance of the car window to control the temperature inside the car. Compared with the prior art, the beneficial effects of the computer program product provided by the present application are the same as the beneficial effects of the automobile glass adjustment method based on the neural network provided in the above embodiment, which will not be repeated here.

[0112] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A method for adjusting automobile glass based on neural network, characterized in that: The method comprises: Obtain vehicle driving data; Input the vehicle driving data into a preset neural network model for processing to obtain output data; According to the output data, obtaining adjustment parameters of the vehicle window glass; The vehicle window glass is adjusted according to the adjustment parameters.

2. The method according to claim 1, characterized in that The preset neural network model includes at least an input layer, two hidden layers and an output layer, the input layer contains a first preset number of nodes, the hidden layer uses a ReLU activation function, and the output layer contains a second preset number of nodes and uses a Sigmoid activation function.

3. The method according to claim 2, characterized in that Before the vehicle driving data is processed by a preset neural network to obtain output data, the method includes: Obtain vehicle driving sample data and establish an initial neural network model; The initial neural network model is trained according to the vehicle driving sample data to obtain a preset neural network model.

4. The method according to claim 3, characterized in that The initial neural network model is trained according to the vehicle driving sample data to obtain a preset neural network model, including: Initializing model parameters of the initial neural network model; Get input data; Normalizing the input data to obtain processed input data; Inputting the processed input data into the initial neural network model to obtain predicted output data; According to the loss function calculation, the error value between the predicted output data and the actual data is obtained; Get the learning rate; The model parameters are iteratively updated through an optimization algorithm according to the learning rate until a maximum number of iterations is reached or the error value calculated by the loss function converges to a preset threshold, thereby obtaining a preset neural network model.

5. The method according to claim 3, characterized in that The step of inputting the processed input data into the initial neural network model to obtain predicted output data comprises: The input data of the input layer is calculated by linear change to obtain the input data of the hidden layer; The input data of the hidden layer is calculated by a nonlinear ReLU activation function to obtain the output data of the hidden layer; The output data of the hidden layer is first subjected to linear change calculation and then to nonlinear ReLU activation function calculation until the output data of the last hidden layer is obtained; The output data of the last hidden layer is used as the input data of the output layer, and is calculated according to the nonlinear Sigmoid activation function to obtain the predicted output data.

6. The method according to claim 3, characterized in that After the initial neural network model is trained according to the vehicle driving sample data to obtain a preset neural network model, the method includes: Evaluating the preset neural network model to obtain an evaluation result; If the evaluation result does not meet the control requirement, the preset neural network model is retrained until the control requirement is met.

7. The method according to claim 1, characterized in that The adjusting the vehicle window glass according to the adjustment parameter comprises: The front windshield of the automobile is evenly divided into a first area, a second area, a third area and a fourth area; According to the adjustment parameters, the glass transmittance adjustment voltage and the cab setting temperature are obtained; The voltage is adjusted according to the glass transmittance and the set temperature of the cab, and the first area, the second area, the third area and the fourth area are adjusted accordingly to maintain the temperature inside the vehicle at a comfortable driving temperature.

8. A vehicle glass adjustment device based on a neural network, characterized in that: The device comprises: An acquisition module, used for acquiring vehicle driving data; A processing module, used to input the vehicle driving data into a preset neural network model for processing to obtain output data; An acquisition module, used for obtaining adjustment parameters of the vehicle window glass according to the output data; The adjustment module is used to adjust the vehicle window glass according to the adjustment parameters.

9. A vehicle glass adjustment device based on a neural network, characterized in that: The device includes: a memory, a processor, and a neural network-based automobile glass adjustment program stored in the memory and executable on the processor, wherein the neural network-based automobile glass adjustment program is configured to implement the steps of the neural network-based automobile glass adjustment method as described in any one of claims 1 to 7.

10. A medium, characterized in that The medium stores a neural network-based automobile glass adjustment program, which, when executed by a processor, implements the steps of the neural network-based automobile glass adjustment method as described in any one of claims 1 to 7.

Images