A tunnel brightness control dynamic optimization method, system, terminal and medium

Abstract

The present invention discloses a tunnel brightness control dynamic optimization method, system, terminal and medium, and relates to the field of intelligent transportation technology. The main points of the technical solution are as follows: the present invention adopts a Kalman filtering method to perform state estimation on preprocessed multi-source state parameters, and can accurately obtain a vehicle operation estimation state that can characterize the overall situation of a target tunnel. The vehicle operation estimation state and an autoregressive distributed lag model (ADL model) are then combined to predict vehicle flow and vehicle speed, which can accurately analyze the overall change trend of a single data and accurately characterize the correlation characteristics between different data. At the same time, the target value of lighting brightness is solved by a brightness optimization function constructed by considering the coordination of vehicle flow and vehicle speed, and the accurate response to real-time changes in vehicle flow and vehicle speed can be achieved from a global perspective, thereby improving the reliability and timeliness of brightness adjustment.

Description

Technical Field

[0001] The present invention relates to the field of intelligent transportation technology, and more specifically, to a tunnel brightness control dynamic optimization method, system, terminal and medium. Background Art

[0002] In modern transportation systems, tunnels are key traffic nodes, and intelligent control of their lighting systems plays a vital role in improving driving safety and reducing energy consumption. Traditional tunnel lighting systems usually adopt fixed time and space control strategies, which not only wastes energy, but also affects the driver's visual comfort and driving safety.

[0003] To this end, the prior art records that the intelligent control of tunnel lighting is achieved by considering factors such as vehicle speed, vehicle flow, and brightness. For example, short-term predictions are made for data such as vehicle speed, vehicle flow, and brightness, and the predicted vehicle speed, vehicle flow, and brightness values ​​are input into a pre-built brightness compensation model, and tunnel brightness adjustment is achieved based on the brightness compensation results. However, since the brightness demand in the tunnel is affected by many factors, and factors such as vehicle speed and vehicle flow fluctuate greatly in a short period of time and are highly random, and are not easy to collect accurately, the accuracy and reliability of short-term predictions directly based on the collected single data are poor, and the response frequency of the lighting equipment will also be increased; in addition, the existing brightness compensation model generally achieves brightness compensation based on a single factor, such as adjusting the tunnel brightness in a positively correlated manner when the vehicle flow increases, ignoring the correlation between various factors, and unable to respond in detail to multi-factor working conditions such as real-time changes in vehicle flow and speed.

[0004] Therefore, how to study and design a tunnel brightness control dynamic optimization method, system, terminal and medium that can overcome the above-mentioned defects is a problem that we urgently need to solve. Summary of the invention

[0005] In order to address the deficiencies in the prior art, the purpose of the present invention is to provide a method, system, terminal and medium for dynamic optimization of tunnel brightness control. By considering the brightness optimization function constructed by the coordinated effect of vehicle flow and vehicle speed to solve the target value of lighting brightness, it is possible to accurately respond to real-time changes in vehicle flow and vehicle speed from a global perspective, thereby improving the reliability and timeliness of brightness adjustment.

[0006] The above technical objectives of the present invention are achieved through the following technical solutions:

[0007] In a first aspect, a tunnel brightness control dynamic optimization method is provided, comprising the following steps:

[0008] Collect multi-source state parameters in the target tunnel, including vehicle flow, vehicle speed, ambient light intensity and noise level;

[0009] Preprocessing the multi-source state parameters, and using the Kalman filter method to perform state estimation on the preprocessed multi-source state parameters to obtain the estimated vehicle operation state;

[0010] The estimated vehicle running state is input into the ADL model trained by considering time conditions and environmental conditions, and the predicted traffic flow and predicted vehicle speed are predicted;

[0011] The predicted traffic flow and predicted vehicle speed are input into the brightness optimization function constructed by considering the coordination of traffic flow and vehicle speed to obtain the target value of lighting brightness;

[0012] A corresponding real-time PWM signal is generated according to the lighting brightness target value, and brightness adjustment is achieved based on the real-time PWM signal.

[0013] Furthermore, the process of preprocessing the multi-source state parameters is specifically as follows:

[0014] Eliminate random errors and background noise in the multi-source state parameters by median filtering, mean filtering and / or wavelet transform to obtain a first parameter;

[0015] Eliminate the influence of different dimensions and magnitudes in the first parameter by Z-score standardization or Min-Max standardization to obtain the second parameter;

[0016] The sampling time deviation in the second parameter is time aligned by interpolation method to obtain the preprocessed multi-source state parameter.

[0017] Furthermore, the time condition is to divide the traffic flow into multiple traffic flow modes including morning peak, evening peak, day and night; the environmental condition is to consider the impact of weather conditions on traffic flow and the impact of ambient light intensity on lighting needs.

[0018] Furthermore, the brightness optimization function is a first function constructed with vehicle speed as the main variable and the increment of vehicle flow as the secondary variable, and the expression is:

[0019] ;

[0020] in, Indicates that the solution obtained by the first function is The target lighting brightness value at the moment; represents the main variable function in the first function; represents the subvariable function in the first function; express Predicted traffic flow at each moment; express Predicted vehicle speed at the time; represents the first benchmark traffic volume; represents the constant term in the first function; Represents the sample set for constructing the brightness optimization function, with size Matrix representation of ; Indicates the total number of samples in the sample set; It indicates the number of samples with traffic volume as the variable; It indicates the number of samples with vehicle speed as variable; Indicates vehicle speed , Traffic flow The illumination brightness of the corresponding sample; Indicates vehicle speed The traffic volume is The illumination brightness of the corresponding sample.

[0021] Furthermore, the brightness optimization function is a second function constructed with the vehicle flow as the main variable and the increment of the vehicle speed as the secondary variable, and the expression is:

[0022] ;

[0023] in, Indicates that the solution obtained by the second function is The target lighting brightness value at the moment; represents the secondary variable function in the second function; represents the main variable function in the second function; express Predicted traffic flow at each moment; express Predicted vehicle speed at the time; Indicates the first reference vehicle speed; represents the constant term in the second function; Represents the sample set for constructing the brightness optimization function, with size Matrix representation of ; Indicates the total number of samples in the sample set; It indicates the number of samples with traffic volume as the variable; It indicates the number of samples with vehicle speed as variable; Indicates vehicle speed , Traffic flow The illumination brightness of the corresponding sample; Indicates vehicle speed The traffic volume is The illumination brightness of the corresponding sample.

[0024] Furthermore, the brightness optimization function is a third function constructed with vehicle speed and vehicle flow as the co-dominant factors, and the expression is:

[0025] ;

[0026] in, Indicates that the solution obtained by the third function is The target lighting brightness value at the moment; It represents the main variable function when constructing the brightness optimization function with vehicle speed as the main variable and the increment of vehicle flow as the secondary variable; It represents the secondary variable function when constructing the brightness optimization function with vehicle speed as the main variable and the increment of vehicle flow as the secondary variable; It represents the secondary variable function when constructing the brightness optimization function with the traffic volume as the main variable and the increment of the vehicle speed as the secondary variable; It represents the main variable function when constructing the brightness optimization function with the traffic volume as the main variable and the speed increment as the secondary variable; express Predicted traffic flow at each moment; express Predicted vehicle speed at the time; Indicates the third reference vehicle speed; Indicates the third benchmark traffic volume; It represents the constant term when constructing the brightness optimization function with vehicle speed as the main variable and the increment of vehicle flow as the secondary variable; It represents the constant term when constructing the brightness optimization function with the traffic volume as the main variable and the speed increment as the secondary variable; Represents the sample set for constructing the brightness optimization function, with size Matrix representation of ; Indicates the total number of samples in the sample set; It indicates the number of samples with traffic volume as the variable; It indicates the number of samples with vehicle speed as variable; Indicates vehicle speed , Traffic flow The illumination brightness of the corresponding sample; Indicates vehicle speed The traffic volume is The illumination brightness of the corresponding sample.

[0027] Furthermore, the real-time PWM signal generation process is specifically as follows:

[0028] Establish a basic brightness and a basic duty cycle of the PWM signal required to control the lighting device to achieve the basic brightness;

[0029] The adjustment coefficient is determined by the ratio of the lighting brightness target value to the basic brightness;

[0030] The duty cycle of the real-time PWM signal is determined by the product of the basic duty cycle and the adjustment coefficient, and a corresponding real-time PWM signal is generated.

[0031] In a second aspect, a tunnel brightness control dynamic optimization system is provided, the system is used to implement a tunnel brightness control dynamic optimization method as described in any one of the first aspects, including:

[0032] A data acquisition module is used to collect multi-source state parameters in the target tunnel, including vehicle flow, vehicle speed, ambient light intensity and noise level;

[0033] The state estimation module is used to pre-process the multi-source state parameters and use the Kalman filter method to perform state estimation on the pre-processed multi-source state parameters to obtain the estimated vehicle operation state;

[0034] A state prediction module is used to input the estimated state of vehicle operation into the ADL model trained by considering time conditions and environmental conditions, and predict the predicted traffic flow and predicted vehicle speed;

[0035] A brightness solution module is used to input the predicted traffic flow and predicted vehicle speed into a brightness optimization function constructed by considering the coordination of traffic flow and vehicle speed to obtain a target lighting brightness value;

[0036] The adjustment optimization module is used to generate a corresponding real-time PWM signal according to the lighting brightness target value, and realize brightness adjustment based on the real-time PWM signal.

[0037] In a third aspect, a computer terminal is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, a method for dynamic optimization of tunnel brightness control as described in any one of the first aspects is implemented.

[0038] In a fourth aspect, a computer-readable medium is provided, on which a computer program is stored, and the computer program is executed by a processor to implement a method for dynamic optimization of tunnel brightness control as described in any one of the first aspects.

[0039] Compared with the prior art, the present invention has the following beneficial effects:

[0040] 1. A tunnel brightness control dynamic optimization method provided by the present invention uses a Kalman filtering method to perform state estimation on pre-processed multi-source state parameters, which can accurately obtain the vehicle operation estimation state that can characterize the overall situation of the target tunnel, and then combines the vehicle operation estimation state with the autoregressive distributed lag model (ADL model) to predict the traffic flow and speed, which can accurately analyze the overall change trend of a single data and accurately characterize the correlation characteristics between different data; at the same time, the target value of the lighting brightness is solved by constructing a brightness optimization function that considers the coordination of traffic flow and speed, which can achieve accurate response to real-time changes in traffic flow and speed from a global perspective, thereby improving the reliability and timeliness of brightness adjustment;

[0041] 2. When constructing the brightness optimization function, the present invention first performs linear regression analysis with one factor as the main variable based on historical sample data, and then performs nonlinear regression analysis on the error of the main variable with another factor as the secondary variable, so as to obtain a brightness optimization function that takes into account the coordinated effect of vehicle flow and vehicle speed, which can more accurately achieve brightness adjustment under different changing working conditions;

[0042] 3. When constructing the brightness optimization function, the present invention performs nonlinear regression analysis on the error of the main variable, with the optimization goal of minimizing the sum of the brightness errors between each sample data and the sample data corresponding to the secondary variable, and solves the secondary variable benchmark in each secondary variable function, so that the value range of the independent variable in the secondary variable function obtained by analysis is smaller, which is conducive to obtaining a more accurate and reliable secondary variable function;

[0043] 4. The present invention realizes precise dynamic control of the lighting system, significantly improving the flexibility and accuracy of the system response; it can continuously learn and adapt to the dynamic changes of traffic and environment, maintain the advancement and effectiveness of the system; and by maintaining a reasonable lighting level, it ensures the driver's clear vision, reduces visual fatigue, and effectively reduces the risk of traffic accidents. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] The drawings described herein are used to provide a further understanding of the embodiments of the present invention, constitute a part of this application, and do not constitute a limitation of the embodiments of the present invention. In the drawings:

[0045] Figure 1 is a flow chart of Embodiment 1 of the present invention;

[0046] Figure 2 It is a system block diagram in Example 2 of the present invention. DETAILED DESCRIPTION

[0047] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with embodiments and drawings. The exemplary embodiments of the present invention and their description are only used to explain the present invention and are not intended to limit the present invention.

[0048] Embodiment 1: A tunnel brightness control dynamic optimization method, such as Figure 1 As shown, the following steps are included:

[0049] S1: Collect multi-source state parameters in the target tunnel, including vehicle flow, vehicle speed, ambient light intensity and noise level;

[0050] S2: preprocessing the multi-source state parameters, and using the Kalman filter method to perform state estimation on the preprocessed multi-source state parameters to obtain the estimated vehicle operation state;

[0051] S3: inputting the estimated vehicle running state into the ADL model trained by considering time conditions and environmental conditions, and predicting the predicted traffic flow and predicted vehicle speed;

[0052] S4: inputting the predicted traffic flow and the predicted vehicle speed into a brightness optimization function constructed by considering the coordination of traffic flow and vehicle speed to obtain a target lighting brightness value;

[0053] S5: Generate a corresponding real-time PWM signal according to the target lighting brightness value, and implement brightness adjustment based on the real-time PWM signal. The PWM signal is a pulse width modulation signal.

[0054] In step S1, since the traffic volume and speed are factors that fluctuate greatly in the short term but show a stable trend in the long term, and the tunnel has a long distribution range, when a limited sensor or image acquisition terminal is used to collect the traffic volume and speed in the target tunnel, the collected traffic volume and speed can only represent the local situation and it is difficult to accurately represent the global situation.

[0055] To this end, the present invention performs subsequent processing on the collected data.

[0056] In step S2, the process of preprocessing the multi-source state parameters is specifically as follows: eliminating random errors and background noise in the multi-source state parameters by median filtering, mean filtering and / or wavelet transform to obtain the first parameter; eliminating the influence of different dimensions and magnitudes in the first parameter by Z-score standardization or Min-Max standardization to obtain the second parameter; and time-aligning the deviation of the sampling time in the second parameter by interpolation to obtain the preprocessed multi-source state parameter.

[0057] It should be noted that the present invention adopts the Kalman filtering method mainly to accurately estimate the state of multi-source state parameters, but it should not be used for data prediction at a subsequent time.

[0058] In step S3, since a vehicle operation estimation state is a state vector composed of multiple states, in order to ensure the overall prediction trend of a single factor and the correlation influence between various factors in the subsequent vehicle speed and traffic flow prediction process, the present invention adopts an autoregressive distributed lag model (ADL model) to predict vehicle flow and speed.

[0059] When the ADL model is established, the time condition considered is to divide the traffic flow into multiple traffic flow modes including morning peak hour, evening peak hour, daytime and nighttime. The environmental conditions considered are the impact of weather conditions on traffic flow and the impact of ambient light intensity on lighting needs.

[0060] In step S4, the brightness optimization function can be implemented based on standard sample data, and one sample data includes vehicle speed, vehicle flow, and the illumination brightness under the corresponding vehicle speed and vehicle flow. The present invention collects a large number of samples to form a sample set, first performs linear regression analysis with one factor as the main variable, and then performs nonlinear regression analysis on the error of the main variable with another factor as the secondary variable, so as to obtain a brightness optimization function that takes into account the coordination of vehicle flow and vehicle speed, and can more accurately achieve brightness adjustment under different changing working conditions.

[0061] Before constructing the brightness optimization function, it is necessary to determine the benchmark based on each sample data in the sample set. Specifically, when constructing the brightness optimization function, the error of the main variable is subjected to nonlinear regression analysis, with the optimization goal of minimizing the sum of the brightness errors between each sample data and the sample data corresponding to the secondary variable. The secondary variable benchmark in each secondary variable function is solved, so that the value range of the independent variable in the secondary variable function obtained by analysis is smaller, which is conducive to obtaining a more accurate and reliable secondary variable function.

[0062] As a first optional implementation, the brightness optimization function is a first function constructed with vehicle speed as the main variable and the increment of vehicle flow as the secondary variable, and the expression is:

[0063] ;

[0064] in, Indicates that the solution obtained by the first function is The target lighting brightness value at the moment; represents the main variable function in the first function; represents the subvariable function in the first function; express Predicted traffic flow at each moment; express Predicted vehicle speed at the time; represents the first benchmark traffic volume; represents the constant term in the first function; Represents the sample set for constructing the brightness optimization function, with size Matrix representation of ; Indicates the total number of samples in the sample set; It indicates the number of samples with traffic volume as the variable; It indicates the number of samples with vehicle speed as variable; Indicates vehicle speed , Traffic flow The illumination brightness of the corresponding sample; Indicates vehicle speed The traffic volume is The illumination brightness of the corresponding sample.

[0065] As a second optional implementation, the brightness optimization function is a second function constructed with the vehicle flow as the main variable and the increment of the vehicle speed as the secondary variable, and the expression is:

[0066] ;

[0067] in, Indicates that the solution obtained by the second function is The target lighting brightness value at the moment; represents the secondary variable function in the second function; represents the main variable function in the second function; express Predicted traffic flow at each moment; express Predicted vehicle speed at the time; Indicates the first reference vehicle speed; represents the constant term in the second function; Represents the sample set for constructing the brightness optimization function, with size Matrix representation of ; Indicates the total number of samples in the sample set; It indicates the number of samples with traffic volume as the variable; It indicates the number of samples with vehicle speed as variable; Indicates vehicle speed , Traffic flow The illumination brightness of the corresponding sample; Indicates vehicle speed The traffic volume is The illumination brightness of the corresponding sample.

[0068] The above two construction methods are both based on one factor as the dominant factor, which may easily lead to a sudden change in tunnel brightness in special situations such as emergency braking of the vehicle. Therefore, the present invention combines the above two construction methods to reconstruct the brightness optimization function.

[0069] As a third optional implementation, in the third construction method, different from the first and second construction methods, the selection of the reference vehicle speed or the reference vehicle flow is different. After simultaneously optimizing and solving the third reference vehicle speed and the third reference vehicle flow, they are distributed and constructed using the first and second construction methods, and finally the average is calculated.

[0070] For example, the brightness optimization function is a third function constructed with vehicle speed and vehicle flow as the co-dominant factors, and the expression is:

[0071] ;

[0072] in, Indicates that the solution obtained by the third function is The target lighting brightness value at the moment; It represents the main variable function when constructing the brightness optimization function with vehicle speed as the main variable and the increment of vehicle flow as the secondary variable; It represents the secondary variable function when constructing the brightness optimization function with vehicle speed as the main variable and the increment of vehicle flow as the secondary variable; It represents the secondary variable function when constructing the brightness optimization function with the traffic volume as the main variable and the increment of the vehicle speed as the secondary variable; It represents the main variable function when constructing the brightness optimization function with the traffic volume as the main variable and the speed increment as the secondary variable; express Predicted traffic flow at each moment; express Predicted vehicle speed at the time; Indicates the third reference vehicle speed; Indicates the third benchmark traffic volume; It represents the constant term when constructing the brightness optimization function with vehicle speed as the main variable and the increment of vehicle flow as the secondary variable; It represents the constant term when constructing the brightness optimization function with the traffic volume as the main variable and the speed increment as the secondary variable; Represents the sample set for constructing the brightness optimization function, with size Matrix representation of ; Indicates the total number of samples in the sample set; It indicates the number of samples with traffic volume as the variable; It indicates the number of samples with vehicle speed as variable; Indicates vehicle speed , Traffic flow The illumination brightness of the corresponding sample; Indicates vehicle speed The traffic volume is The illumination brightness of the corresponding sample.

[0073] In step S5, the real-time PWM signal generation process is specifically as follows: establish a basic brightness and a basic duty cycle of the PWM signal required to control the lighting device to reach the basic brightness; determine the adjustment coefficient by the ratio of the lighting brightness target value to the basic brightness; determine the duty cycle of the real-time PWM signal by the product of the basic duty cycle and the adjustment coefficient, and generate the corresponding real-time PWM signal.

[0074] Embodiment 2: A tunnel brightness control dynamic optimization system, the system is used to implement a tunnel brightness control dynamic optimization method as described in Embodiment 1, such as Figure 2 As shown, it includes a data acquisition module, a state estimation module, a state prediction module, a brightness solution module and an adjustment optimization module.

[0075] Among them, the data acquisition module is used to collect multi-source state parameters in the target tunnel, and the multi-source state parameters include traffic flow, vehicle speed, ambient light intensity and noise level; the state estimation module is used to preprocess the multi-source state parameters, and use the Kalman filtering method to estimate the state of the preprocessed multi-source state parameters to obtain the estimated vehicle operation state; the state prediction module is used to input the estimated vehicle operation state into the ADL model trained by considering time conditions and environmental conditions, and predict the predicted traffic flow and predicted speed; the brightness solution module is used to input the predicted traffic flow and predicted speed into the brightness optimization function constructed by considering the coordination of traffic flow and speed, and obtain the lighting brightness target value; the adjustment optimization module is used to generate the corresponding real-time PWM signal according to the lighting brightness target value, and realize brightness adjustment based on the real-time PWM signal.

[0076] The present invention also describes a computer terminal, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, a method for dynamic optimization of tunnel brightness control as described in Example 1 is implemented.

[0077] The present invention also describes a computer-readable medium on which a computer program is stored. The computer program is executed by a processor to implement a tunnel brightness control dynamic optimization method as described in Example 1.

[0078] Working principle: The present invention adopts the Kalman filtering method to perform state estimation on the pre-processed multi-source state parameters, and can accurately obtain the vehicle operation estimation state that can characterize the overall situation of the target tunnel, and then combine the vehicle operation estimation state and the autoregressive distributed lag model (ADL model) to predict the traffic flow and speed, which can not only accurately analyze the overall change trend of a single data, but also accurately characterize the correlation characteristics between different data; at the same time, the target value of the lighting brightness is solved by considering the brightness optimization function constructed by the coordination of traffic flow and speed, which can realize the accurate response of real-time changing traffic flow and speed from a global perspective, thereby improving the reliability and timeliness of brightness adjustment.

[0079] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0080] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0081] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0082] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0083] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A tunnel brightness control dynamic optimization method, characterized in that: The following steps are involved: Collect multi-source state parameters in the target tunnel, including vehicle flow, vehicle speed, ambient light intensity and noise level; Preprocessing the multi-source state parameters, and using the Kalman filter method to perform state estimation on the preprocessed multi-source state parameters to obtain the estimated vehicle operation state; The estimated vehicle running state is input into the ADL model trained by considering time conditions and environmental conditions, and the predicted traffic flow and predicted vehicle speed are predicted; The predicted traffic flow and predicted vehicle speed are input into the brightness optimization function constructed by considering the coordination of traffic flow and vehicle speed to obtain the target value of lighting brightness; Generate a corresponding real-time PWM signal according to the lighting brightness target value, and implement brightness adjustment based on the real-time PWM signal; Among them, when constructing the brightness optimization function, based on historical sample data, a linear regression analysis is first performed with one factor as the main variable, and then a nonlinear regression analysis is performed on the error of the main variable with another factor as the secondary variable, so as to obtain a brightness optimization function that takes into account the coordination of traffic flow and speed; The brightness optimization function is a first function constructed with vehicle speed as the main variable and the increment of vehicle flow as the secondary variable; Or, the brightness optimization function is a second function constructed with the vehicle flow rate as the main variable and the increment of the vehicle speed as the secondary variable; Alternatively, the brightness optimization function is a third function constructed with vehicle speed and vehicle flow as co-dominant factors.

2. A tunnel brightness control dynamic optimization method according to claim 1, characterized in that: The process of preprocessing the multi-source state parameters is specifically as follows: Eliminate random errors and background noise in the multi-source state parameters by median filtering, mean filtering and / or wavelet transform to obtain a first parameter; Eliminate the influence of different dimensions and magnitudes in the first parameter by Z-score standardization or Min-Max standardization to obtain the second parameter; The sampling time deviation in the second parameter is time aligned by interpolation method to obtain the preprocessed multi-source state parameter.

3. The tunnel brightness control dynamic optimization method according to claim 1 is characterized in that: The time condition is to divide the traffic flow into multiple traffic flow modes including morning peak, evening peak, day and night; the environmental condition is to consider the impact of weather conditions on traffic flow and the impact of ambient light intensity on lighting needs.

4. The tunnel brightness control dynamic optimization method according to claim 1 is characterized in that: The brightness optimization function is a first function constructed with vehicle speed as the main variable and the increment of vehicle flow as the secondary variable, and the expression is: ； in, Indicates that the solution obtained by the first function is The target lighting brightness value at the moment; represents the main variable function in the first function; represents the subvariable function in the first function; express Predicted traffic flow at each moment; express Predicted vehicle speed at the time; represents the first benchmark traffic volume; represents the constant term in the first function; Represents the sample set for constructing the brightness optimization function, with size Matrix representation of ; Indicates the total number of samples in the sample set; It indicates the number of samples with traffic volume as the variable; It indicates the number of samples with vehicle speed as variable; Indicates vehicle speed , Traffic flow The illumination brightness of the corresponding sample; Indicates vehicle speed The traffic volume is The illumination brightness of the corresponding sample.

5. The tunnel brightness control dynamic optimization method according to claim 1 is characterized in that: The brightness optimization function is a second function constructed with the vehicle flow as the main variable and the vehicle speed increment as the secondary variable, and the expression is: ； in, Indicates that the solution obtained by the second function is The target lighting brightness value at the moment; represents the secondary variable function in the second function; represents the main variable function in the second function; express Predicted traffic flow at each moment; express Predicted vehicle speed at the time; Indicates the first reference vehicle speed; represents the constant term in the second function; Represents the sample set for constructing the brightness optimization function, with size Matrix representation of ; Indicates the total number of samples in the sample set; It indicates the number of samples with traffic volume as the variable; It indicates the number of samples with vehicle speed as variable; Indicates vehicle speed , Traffic flow The illumination brightness of the corresponding sample; Indicates vehicle speed The traffic volume is The illumination brightness of the corresponding sample.

6. A tunnel brightness control dynamic optimization method according to claim 1, characterized in that: The brightness optimization function is a third function constructed with vehicle speed and vehicle flow as the co-dominant factors, and the expression is: ； in, Indicates that the solution obtained by the third function is The target lighting brightness value at the moment; It represents the main variable function when constructing the brightness optimization function with vehicle speed as the main variable and the increment of vehicle flow as the secondary variable; It represents the secondary variable function when constructing the brightness optimization function with vehicle speed as the main variable and the increment of vehicle flow as the secondary variable; It represents the secondary variable function when constructing the brightness optimization function with the traffic volume as the main variable and the increment of the vehicle speed as the secondary variable; It represents the main variable function when constructing the brightness optimization function with the traffic volume as the main variable and the speed increment as the secondary variable; express Predicted traffic flow at each moment; express Predicted vehicle speed at the time; Indicates the third reference vehicle speed; Indicates the third benchmark traffic volume; It represents the constant term when constructing the brightness optimization function with vehicle speed as the main variable and the increment of vehicle flow as the secondary variable; It represents the constant term when constructing the brightness optimization function with the traffic volume as the main variable and the speed increment as the secondary variable; Represents the sample set for constructing the brightness optimization function, with size Matrix representation of ; Indicates the total number of samples in the sample set; It indicates the number of samples with traffic volume as the variable; It indicates the number of samples with vehicle speed as variable; Indicates vehicle speed , Traffic flow The illumination brightness of the corresponding sample; Indicates vehicle speed The traffic volume is The illumination brightness of the corresponding sample.

7. The tunnel brightness control dynamic optimization method according to claim 1 is characterized in that: The generation process of the real-time PWM signal is specifically as follows: Establish a basic brightness and a basic duty cycle of the PWM signal required to control the lighting device to achieve the basic brightness; The adjustment coefficient is determined by the ratio of the lighting brightness target value to the basic brightness; The duty cycle of the real-time PWM signal is determined by the product of the basic duty cycle and the adjustment coefficient, and a corresponding real-time PWM signal is generated.

8. A tunnel brightness control dynamic optimization system, characterized in that: The system is used to implement a tunnel brightness control dynamic optimization method as described in any one of claims 1 to 7, comprising: A data acquisition module is used to collect multi-source state parameters in the target tunnel, including vehicle flow, vehicle speed, ambient light intensity and noise level; The state estimation module is used to pre-process the multi-source state parameters and use the Kalman filter method to perform state estimation on the pre-processed multi-source state parameters to obtain the estimated vehicle operation state; A state prediction module is used to input the estimated state of vehicle operation into the ADL model trained by considering time conditions and environmental conditions, and predict the predicted traffic flow and predicted vehicle speed; A brightness solution module is used to input the predicted traffic flow and predicted vehicle speed into a brightness optimization function constructed by considering the coordination of traffic flow and vehicle speed to obtain a target lighting brightness value; The adjustment optimization module is used to generate a corresponding real-time PWM signal according to the lighting brightness target value, and realize brightness adjustment based on the real-time PWM signal.

9. A computer terminal comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, a tunnel brightness control dynamic optimization method as described in any one of claims 1 to 7 is implemented.

10. A computer readable medium having a computer program stored thereon, characterized in that: The computer program is executed by a processor to implement a tunnel brightness control dynamic optimization method as described in any one of claims 1 to 7.

Images