A Tunnel Lighting Control Method and System Based on Illumination Environment Analysis

Abstract

This invention discloses a tunnel dimming control method and system based on illumination environment analysis. The method includes: acquiring real-time illumination intensity data and environmental correlation parameters at multiple locations in a tunnel area; predicting the light environment characteristics of the tunnel area within a preset future time period based on the real-time illumination intensity data and the environmental correlation parameters; matching corresponding dynamic control parameters according to the light environment prediction characteristics and determining a brightness adjustment strategy for each lighting zone based on the spatial layout of the tunnel area; generating brightness control instructions for lighting devices in each lighting zone according to the brightness adjustment strategy, and sending the brightness control instructions to the lighting devices. Therefore, this invention enables a technological improvement in tunnel lighting from static sensing to active predictive control, effectively eliminating the "black hole effect" at tunnel entrances and significantly optimizing the energy efficiency and driving safety of the tunnel lighting system.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a tunnel dimming control method and system based on illumination environment analysis. Background Technology

[0002] With the accelerated construction of smart highways, intelligent management of tunnel lighting systems has become a crucial link in ensuring tunnel driving safety and energy conservation and emission reduction. The "black hole effect" caused by drastic changes in light intensity at tunnel entrances, and the on-demand adjustment of lighting inside tunnels, have always been core issues of concern in the field of traffic engineering. However, existing tunnel lighting monitoring technologies typically rely on real-time sensing or preset schedule control. The lack of technical support for acquiring multi-location illumination data and environmental parameters within the tunnel to predict future light environment characteristics prevents the system from dynamically determining brightness adjustment strategies for lighting zones based on predicted light environment characteristics and spatial layout. This hinders the technological improvement of tunnel lighting from static sensing to active predictive control. Consequently, the system's response to changes in the external environment exhibits significant lag, and it is difficult to balance energy efficiency and driving safety under different weather conditions or traffic flows, limiting the level of refined management of tunnel lighting systems in complex climates and operating environments. Therefore, existing technologies have shortcomings that urgently need to be addressed. Summary of the Invention

[0003] The technical problem to be solved by the present invention is to provide a tunnel dimming control method and system based on illumination environment analysis, which can realize the technical improvement of tunnel lighting from static sensing to active predictive control, effectively eliminate the "black hole effect" at the tunnel entrance, and significantly optimize the energy efficiency and driving safety of the tunnel lighting system.

[0004] To address the aforementioned technical problems, the first aspect of this invention discloses a tunnel dimming control method based on illumination environment analysis, the method comprising: Acquire real-time illumination intensity data and environmental parameters at multiple locations within the tunnel area; Based on the real-time illumination intensity data and the environmental correlation parameters, predict the light environment characteristics of the tunnel area in the future preset time period; Based on the predicted characteristics of the light environment, the corresponding dynamic control parameters are matched, and the brightness adjustment strategy of each lighting zone is determined in combination with the spatial layout of the tunnel area. According to the brightness adjustment strategy, a brightness control command is generated for the lighting devices in each lighting zone, and the brightness control command is sent to the lighting devices.

[0005] As an optional implementation, in the first aspect of the invention, the location is the entrance section location, transition section location, or exit section location of the tunnel area.

[0006] As an optional implementation, in the first aspect of the invention, the environmental correlation parameters include at least one of time parameters, weather parameters, and traffic flow change parameters.

[0007] As an optional implementation, in the first aspect of the present invention, predicting the light environment characteristics of the tunnel area within a future preset time period based on the real-time illumination intensity data and the environmental correlation parameters includes: The external environmental impact factors of the tunnel area are quantitatively characterized based on the environmental correlation parameters. Extract the light intensity gradient features of the real-time light intensity data on the spatial axis, and extract the corresponding light intensity fluctuation components based on the historical evolution features of the real-time light intensity data; The light intensity gradient features, the light intensity fluctuation components, and the quantified external environmental influencing factors are used to construct a multi-dimensional feature vector to generate a spatiotemporal feature matrix of the light environment. The light environment spatiotemporal feature matrix is ​​input into a preset time series prediction model. The time series prediction model is used to extract features and perform nonlinear mapping on the brightness evolution trend and color temperature shift law in the future preset time period to obtain the light environment prediction features.

[0008] As an optional implementation, in the first aspect of the present invention, the time series prediction model is trained through the following steps: Historical illumination intensity data and historical environmental correlation parameters of the tunnel area during the historical operation cycle are obtained, and the historical illumination intensity data and historical environmental correlation parameters are preprocessed by denoising and normalization to construct the original time series training set. The original time series training set is sampled based on a preset sliding window length to extract the historical light intensity evolution features and environmental disturbance components corresponding to each sampling moment, and to construct a sample pair consisting of a multi-dimensional feature vector and the corresponding future light intensity ground value. Construct a deep learning network containing recurrent neural network layers or attention mechanism layers, and use the deep learning network to perform feature mapping on the sample pairs in order to capture the long-term and short-term dependencies and nonlinear evolution laws of light environment data on the time axis. Define a target loss function for the prediction bias of the light environment, and use the backpropagation algorithm and a preset optimizer to iteratively optimize the model weights of the deep learning network until the target loss function reaches a preset convergence threshold. The optimized model is evaluated on a comprehensive basis in terms of prediction accuracy and response latency using reserved test samples. After the evaluation is passed, the model is solidified to generate the time series prediction model.

[0009] As an optional implementation, in the first aspect of the invention, the step of matching corresponding dynamic control parameters based on the predicted light environment features and determining the brightness adjustment strategy for each lighting zone in conjunction with the spatial layout of the tunnel area includes: Based on the predicted characteristics of the light environment, a target dimming curve and brightness fluctuation tolerance corresponding to the expected brightness evolution trend are matched from the preset control index matrix as dynamic control parameters. The lighting topology of the tunnel area is obtained, and the functional positioning of each lighting zone in the tunnel area is identified based on the lighting topology to determine the brightness response weight of each lighting zone. By combining the dynamic control parameters and the brightness response weight, the brightness adjustment reference value for each lighting zone is calculated; Based on the brightness adjustment reference value, a preset visual transition model is used to generate the brightness gradient distribution between each adjacent lighting zone, so as to determine the brightness adjustment strategy for each lighting zone.

[0010] As an optional implementation, in the first aspect of the present invention, generating a brightness control command for the lighting devices in each of the lighting zones according to the brightness adjustment strategy, and sending the brightness control command to the lighting devices, includes: The brightness adjustment strategy of each lighting zone is analyzed, and the corresponding brightness target value and preset brightness smooth switching slope are extracted. According to the hardware communication protocol of the lighting equipment in each lighting zone, the target brightness value and the brightness smooth switching slope are mapped to the corresponding pulse width modulation duty cycle signal or analog voltage adjustment parameter. Based on the current real-time current feedback of the lighting zone and the preset equipment life protection model, the pulse width modulation duty cycle signal is threshold-limited and its electrical characteristics are corrected to generate the brightness control command that meets the hardware driving requirements. According to the spatial topology order of the tunnel area, each brightness control command is encapsulated with a corresponding device physical address and a synchronous execution timestamp, and then mapped to the communication scheduling queue for execution.

[0011] As an optional implementation, in the first aspect of the present invention, the method further includes: During the instruction encapsulation stage, the cyclic redundancy check code (CRC-16) of the brightness control instruction is calculated synchronously and appended to the end of the instruction message to construct a complete transmission frame. The transmission frames carrying the same timestamp are sent synchronously through the redundant dual links (main link and backup link) of the tunnel backbone network, and the dual link data are compared in real time at the distributed control node side. The receiving end performs a self-check on the legality of the incoming command message. If it detects a CRC check failure or a discontinuous message sequence number, it immediately triggers a retransmission mechanism and sends a link abnormality alarm to the central controller. A logic redundancy determination based on majority voting mechanism is introduced. When multiple sets of control commands arrive within a preset synchronization window, the execution logic can only be activated if more than half of the message contents are completely identical. Before the final hardware is driven, instruction readback verification is performed. That is, the lighting driver feeds back the brightness parameters to the control node for pre-execution. Only after the parameters are verified to be correct can the hardware drive signal be officially generated.

[0012] A second aspect of this invention discloses a tunnel dimming control system based on illumination environment analysis, the system comprising: The acquisition module is used to acquire real-time light intensity data and environmental parameters at multiple locations in the tunnel area; The prediction module is used to predict the light environment characteristics of the tunnel area within a future preset time period based on the real-time light intensity data and the environmental correlation parameters. The determination module is used to match the corresponding dynamic control parameters based on the predicted characteristics of the light environment, and to determine the brightness adjustment strategy of each lighting zone in combination with the spatial layout of the tunnel area. The control module is used to generate brightness control instructions for the lighting devices in each lighting zone according to the brightness adjustment strategy, and send the brightness control instructions to the lighting devices.

[0013] As an optional implementation, in a second aspect of the invention, the location is the entrance section location, transition section location, or exit section location of the tunnel area.

[0014] As an optional implementation, in a second aspect of the invention, the environmental correlation parameters include at least one of time parameters, weather parameters, and traffic flow change parameters.

[0015] As an optional implementation, in a second aspect of the invention, the specific method by which the prediction module predicts the light environment prediction characteristics of the tunnel area within a future preset time period based on the real-time illumination intensity data and the environmental correlation parameters includes: The external environmental impact factors of the tunnel area are quantitatively characterized based on the environmental correlation parameters. Extract the light intensity gradient features of the real-time light intensity data on the spatial axis, and extract the corresponding light intensity fluctuation components based on the historical evolution features of the real-time light intensity data; The light intensity gradient features, the light intensity fluctuation components, and the quantified external environmental influencing factors are used to construct a multi-dimensional feature vector to generate a spatiotemporal feature matrix of the light environment. The light environment spatiotemporal feature matrix is ​​input into a preset time series prediction model. The time series prediction model is used to extract features and perform nonlinear mapping on the brightness evolution trend and color temperature shift law in the future preset time period to obtain the light environment prediction features.

[0016] As an optional implementation, in a second aspect of the invention, the time series prediction model is trained through the following steps: Historical illumination intensity data and historical environmental correlation parameters of the tunnel area during the historical operation cycle are obtained, and the historical illumination intensity data and historical environmental correlation parameters are preprocessed by denoising and normalization to construct the original time series training set. The original time series training set is sampled based on a preset sliding window length to extract the historical light intensity evolution features and environmental disturbance components corresponding to each sampling moment, and to construct a sample pair consisting of a multi-dimensional feature vector and the corresponding future light intensity ground value. Construct a deep learning network containing recurrent neural network layers or attention mechanism layers, and use the deep learning network to perform feature mapping on the sample pairs in order to capture the long-term and short-term dependencies and nonlinear evolution laws of light environment data on the time axis. Define a target loss function for the prediction bias of the light environment, and use the backpropagation algorithm and a preset optimizer to iteratively optimize the model weights of the deep learning network until the target loss function reaches a preset convergence threshold. The optimized model is evaluated on a comprehensive basis in terms of prediction accuracy and response latency using reserved test samples. After the evaluation is passed, the model is solidified to generate the time series prediction model.

[0017] As an optional implementation, in a second aspect of the invention, the determining module matches corresponding dynamic control parameters based on the predicted light environment features and determines the specific method of the brightness adjustment strategy for each lighting zone in conjunction with the spatial layout of the tunnel area, including: Based on the predicted characteristics of the light environment, a target dimming curve and brightness fluctuation tolerance corresponding to the expected brightness evolution trend are matched from the preset control index matrix as dynamic control parameters. The lighting topology of the tunnel area is obtained, and the functional positioning of each lighting zone in the tunnel area is identified based on the lighting topology to determine the brightness response weight of each lighting zone. By combining the dynamic control parameters and the brightness response weight, the brightness adjustment reference value for each lighting zone is calculated; Based on the brightness adjustment reference value, a preset visual transition model is used to generate the brightness gradient distribution between each adjacent lighting zone, so as to determine the brightness adjustment strategy for each lighting zone.

[0018] As an optional implementation, in a second aspect of the invention, the specific method by which the control module generates a brightness control command for the lighting devices in each lighting zone according to the brightness adjustment strategy, and sends the brightness control command to the lighting devices, includes: The brightness adjustment strategy of each lighting zone is analyzed, and the corresponding brightness target value and preset brightness smooth switching slope are extracted. According to the hardware communication protocol of the lighting equipment in each lighting zone, the target brightness value and the brightness smooth switching slope are mapped to the corresponding pulse width modulation duty cycle signal or analog voltage adjustment parameter. Based on the current real-time current feedback of the lighting zone and the preset equipment life protection model, the pulse width modulation duty cycle signal is threshold-limited and its electrical characteristics are corrected to generate the brightness control command that meets the hardware driving requirements. According to the spatial topology order of the tunnel area, each brightness control command is encapsulated with a corresponding device physical address and a synchronous execution timestamp, and then mapped to the communication scheduling queue for execution.

[0019] As an optional implementation, in a second aspect of the invention, the system is further configured to perform the following steps: During the instruction encapsulation stage, the cyclic redundancy check code (CRC-16) of the brightness control instruction is calculated synchronously and appended to the end of the instruction message to construct a complete transmission frame. The transmission frames carrying the same timestamp are sent synchronously through the redundant dual links (main link and backup link) of the tunnel backbone network, and the dual link data are compared in real time at the distributed control node side. The receiving end performs a self-check on the legality of the incoming command message. If it detects a CRC check failure or a discontinuous message sequence number, it immediately triggers a retransmission mechanism and sends a link abnormality alarm to the central controller. A logic redundancy determination based on majority voting mechanism is introduced. When multiple sets of control commands arrive within a preset synchronization window, the execution logic can only be activated if more than half of the message contents are completely identical. Before the final hardware is driven, instruction readback verification is performed. That is, the lighting driver feeds back the brightness parameters to the control node for pre-execution. Only after the parameters are verified to be correct can the hardware drive signal be officially generated.

[0020] A third aspect of this invention discloses another tunnel dimming control system based on illumination environment analysis, the system comprising: Memory containing executable program code; A processor coupled to the memory; The processor calls the executable program code stored in the memory to execute some or all of the steps in the tunnel dimming control method based on illumination environment analysis disclosed in the first aspect of the present invention.

[0021] The fourth aspect of the present invention discloses a computer storage medium storing computer instructions, which, when invoked, are used to execute some or all of the steps in the tunnel dimming control method based on illumination environment analysis disclosed in the first aspect of the present invention.

[0022] Compared with the prior art, the embodiments of the present invention have the following beneficial effects: This invention predicts future light environment characteristics by acquiring multi-location illumination data and environmental parameters of the tunnel, and determines the brightness adjustment strategy for each lighting zone based on the predicted light environment characteristics and spatial layout. It then issues brightness control commands for the lighting zones, thereby achieving a technological improvement in tunnel lighting from static sensing to active predictive control. This effectively eliminates the "black hole effect" at the tunnel entrance and significantly optimizes the energy efficiency and driving safety of the tunnel lighting system. Attached Figure Description

[0023] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0024] Figure 1 This is a flowchart illustrating a tunnel dimming control method based on illumination environment analysis disclosed in an embodiment of the present invention.

[0025] Figure 2 This is a schematic diagram of a tunnel dimming control system based on illumination environment analysis disclosed in an embodiment of the present invention.

[0026] Figure 3 This is a schematic diagram of another tunnel dimming control system based on illumination environment analysis disclosed in an embodiment of the present invention.

[0027] Figure 4 This is a schematic diagram of the user interface of a tunnel lighting system disclosed in an embodiment of the present invention.

[0028] Figure 5 This is a graph showing the energy consumption analysis results of a tunnel lighting control system disclosed in an embodiment of the present invention.

[0029] Figure 6This is a schematic diagram of power consumption data after the tunnel lighting control system disclosed in this embodiment of the invention is applied to a tunnel area. Detailed Implementation

[0030] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0031] The terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this invention are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, apparatus, product, or device that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or devices.

[0032] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of the invention. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0033] This invention discloses a tunnel dimming control method and system based on illumination environment analysis. By acquiring illumination data and environmental parameters from multiple locations within the tunnel, it predicts future illumination environment characteristics. Based on the predicted illumination environment characteristics and spatial layout, it determines the brightness adjustment strategy for each lighting zone and issues brightness control commands to these zones. This enables a technological improvement in tunnel lighting, moving from static sensing to active predictive control, effectively eliminating the "black hole effect" at tunnel entrances, and significantly optimizing the energy efficiency and driving safety of the tunnel lighting system. Detailed explanations follow.

[0034] Example 1 Please see Figure 1 , Figure 1 This is a flowchart illustrating a tunnel dimming control method based on illumination environment analysis disclosed in an embodiment of the present invention. Figure 1The described tunnel dimming control method based on illumination environment analysis can be applied to data processing systems / data processing equipment / data processing servers (wherein, the server includes a local processing server or a cloud processing server). For example... Figure 1 As shown, the tunnel dimming control method based on illumination environment analysis may include the following operations: 101. Obtain real-time illumination intensity data and environmental parameters at multiple locations within the tunnel area.

[0035] Optionally, this location can be the entrance section, transition section, or exit section of the tunnel area.

[0036] Optionally, environmental parameters may include at least one of time parameters, weather parameters, and traffic flow change parameters.

[0037] Optionally, the real-time illumination intensity data can be a lux value collected by a high-precision silicon photodiode, an illuminance sensor, or a visual imaging sensor with high dynamic range (HDR), and the present invention does not limit it.

[0038] Optionally, the environmental parameters may be the tunnel entrance brightness (L20), real-time traffic flow, average vehicle speed, vehicle type ratio, weather conditions (sunny, rainy, snowy, foggy) or air visibility, and this invention does not limit them.

[0039] 102. Based on real-time light intensity data and environmental parameters, predict the light environment characteristics of the tunnel area within a preset time period in the future. Optionally, the predictive feature can be the average light intensity of each segment inside the hole, the predicted value of the glare index, the color rendering index shift, or the risk assessment index of the black hole effect within the next 5-15 minutes. This invention does not limit the specific features.

[0040] 103. Match the corresponding dynamic control parameters according to the predicted characteristics of the light environment, and determine the brightness adjustment strategy for each lighting zone in combination with the spatial layout of the tunnel area. 104. Based on the brightness adjustment strategy, generate brightness control instructions for the lighting equipment in each lighting zone, and send the brightness control instructions to the lighting equipment.

[0041] As can be seen, the above-mentioned embodiments of the invention predict future light environment characteristics by acquiring multi-location illumination data and environmental parameters of the tunnel, and determine the brightness adjustment strategy of each lighting zone based on the predicted light environment characteristics and spatial layout, and issue brightness control instructions for the lighting zones, thereby realizing the technical improvement of tunnel lighting from static sensing to active predictive control, effectively eliminating the "black hole effect" at the tunnel entrance, and significantly optimizing the energy efficiency and driving safety of the tunnel lighting system.

[0042] As an optional embodiment, the step above, predicting the light environment characteristics of the tunnel area within a preset time period based on real-time illumination intensity data and environmental correlation parameters, includes: The external environmental impact factors of the tunnel area are quantitatively characterized based on environmental correlation parameters. Extract the light intensity gradient features of real-time light intensity data on the spatial axis, and extract the corresponding light intensity fluctuation components based on the historical evolution features of real-time light intensity data; The light intensity gradient features, light intensity fluctuation components, and quantified external environmental influencing factors are used to construct a multi-dimensional feature vector to generate a spatiotemporal feature matrix of the light environment. The spatiotemporal feature matrix of the light environment is input into a preset time series prediction model. The time series prediction model is used to extract features and perform nonlinear mapping on the brightness evolution trend and color temperature shift law in the preset future time period to obtain the light environment prediction features.

[0043] Optionally, the external environmental influencing factor can be expressed as the cloud cover ratio coefficient, ground reflectivity model parameters, light transmittance of the shading canopy at the opening, or vegetation shadow shading frequency; this invention does not limit this.

[0044] Optionally, the light intensity gradient feature can be the slope of the first derivative based on the mileage marker, the light intensity contrast between the tunnel entrance and the tunnel interior, or the illuminance uniformity vector between adjacent lamps; this invention does not impose any limitations on this feature.

[0045] As can be seen, through the above optional embodiments, by quantifying environmental influencing factors and extracting light intensity gradient and fluctuation components to construct a spatiotemporal feature matrix, and then using a time series prediction model to extract the brightness evolution trend and color temperature shift law, a high-precision nonlinear mapping of the dynamic changes of the light environment in complex tunnel environments is achieved, providing more forward-looking data prediction support for refined on-demand lighting.

[0046] As an optional embodiment, the time series prediction model in the above steps is trained through the following steps: Historical illumination intensity data and historical environmental parameters of the tunnel area during the historical operation cycle are obtained, and the historical illumination intensity data and historical environmental parameters are preprocessed by denoising and normalization to construct the original time series training set. The original time series training set is sampled based on a preset sliding window length to extract the historical light intensity evolution features and environmental disturbance components corresponding to each sampling time, and to construct a sample pair consisting of a multi-dimensional feature vector and the corresponding future light intensity ground value. Construct a deep learning network containing recurrent neural network layers or attention mechanism layers, and use the deep learning network to perform feature mapping on sample pairs in order to capture the long-term and short-term dependencies and nonlinear evolution laws of light environment data on the time axis. Define a target loss function for the prediction bias of the light environment, and use the backpropagation algorithm and a preset optimizer to iteratively optimize the model weights of the deep learning network until the target loss function reaches the preset convergence threshold. The optimized model is evaluated on a comprehensive basis in terms of prediction accuracy and response latency using reserved test samples. After the evaluation is passed, the model is solidified to generate a time series prediction model.

[0047] Optionally, the denoising and normalization preprocessing can be Kalman filtering, wavelet transform denoising, max-min normalization, or mean-variance standardization; this invention does not limit the specific processing method.

[0048] Optionally, the deep learning network can be a gated recurrent unit (GRU), a bidirectional long short-term memory network (Bi-LSTM), a multi-head attention network, or a temporal convolutional network (TCN), and this invention does not limit it.

[0049] Optionally, the target loss function can be mean squared error (MSE), mean absolute error (MAE), or Huber loss function, and this invention does not limit it.

[0050] Optionally, the optimizer can be Adam, Nadam, stochastic gradient descent (SGD), or AdaGrad optimizer; this invention does not limit the optimization.

[0051] As can be seen, by sampling and denoising historical data and constructing a deep learning network with an attention mechanism, the long-term and short-term dependencies of light environment data on the time axis can be captured, which can significantly improve the robustness of the prediction model to non-stationary environmental disturbances such as sudden weather changes. Furthermore, closed-loop iterative optimization ensures the prediction accuracy and millisecond-level response speed of the model in actual operation.

[0052] As an optional embodiment, the above steps, including matching corresponding dynamic control parameters based on the predicted characteristics of the light environment and determining the brightness adjustment strategy for each lighting zone in conjunction with the spatial layout of the tunnel area, include: Based on the predicted characteristics of the light environment, the target dimming curve and brightness fluctuation tolerance corresponding to the expected brightness evolution trend are matched from the preset control index matrix and used as dynamic control parameters. The lighting topology of the tunnel area is obtained, and the functional location of each lighting zone in the tunnel area is identified based on the lighting topology to determine the brightness response weight of each lighting zone. By combining dynamic control parameters and brightness response weights, the brightness adjustment benchmark value for each lighting zone is calculated; Based on the brightness adjustment benchmark value, a preset visual transition model is used to generate the brightness gradient distribution between adjacent lighting zones in order to determine the brightness adjustment strategy for each lighting zone.

[0053] Optionally, this function can be positioned as an inlet section, a transition section (TR1 / TR2), an intermediate section, an exit section, or an emergency stop strip; the present invention does not limit this.

[0054] Optionally, the visual transition model can be a brightness distribution model based on the Adrian adaptation model or a visual adaptation curve model conforming to CIE standards; this invention does not impose any limitations.

[0055] As can be seen, through the above optional embodiments, the response weight is determined by matching the dimming curve according to the predicted features and combining the functional positioning of the lighting topology, and the brightness gradient distribution is generated by using the visual transition model to determine the adjustment strategy. This achieves a smooth transition and functional adaptation of the brightness of the lighting zones, which greatly improves the visual comfort during driving while conforming to the visual adaptation characteristics of the human eye.

[0056] As an optional embodiment, the step described above, generating brightness control instructions for the lighting devices in each lighting zone according to the brightness adjustment strategy, and sending the brightness control instructions to the lighting devices, includes: Analyze the brightness adjustment strategy of each lighting zone, and extract the corresponding brightness target value and the preset brightness smooth switching slope; Based on the hardware communication protocol of the lighting equipment in each lighting zone, the target brightness value and the brightness smooth switching slope are mapped to the corresponding pulse width modulation duty cycle signal or analog voltage adjustment parameter. By combining the current real-time current feedback of the lighting zone and the preset equipment life protection model, the pulse width modulation duty cycle signal is threshold-limited and its electrical characteristics are corrected to generate brightness control commands that meet the hardware driving requirements. According to the spatial topology order of the tunnel area, each brightness control command is encapsulated with the corresponding device physical address and synchronous execution timestamp, and then mapped to the communication scheduling queue for execution.

[0057] Optionally, the hardware communication protocol can be DALI, DMX512, 0-10V analog control protocol, ZigBee wireless communication protocol, or PLC protocol based on carrier communication; this invention does not limit the specific protocol.

[0058] Optionally, the carrier frequency of the pulse width modulation (PWM) duty cycle signal can be set between 200Hz and 20kHz, and this invention does not limit it.

[0059] Optionally, the device life protection model can be a derating curve model based on LED junction temperature estimation, an attenuation compensation model based on cumulative operating time, or a stable power control algorithm based on grid voltage fluctuations; the present invention does not limit the specific model.

[0060] As can be seen, through the above optional embodiments, the adjustment strategy is parsed and mapped to a pulse width modulation signal, and threshold limiting is performed by combining real-time current feedback and life protection model. This achieves a safe conversion of brightness commands from the logic layer to the physical driving layer. By encapsulating the address and timestamp through spatial topology order, the high synchronization and electrical operation stability of the lighting equipment in the distributed control scenario are ensured.

[0061] As an optional embodiment, the method further includes the following steps: During the instruction encapsulation stage, the cyclic redundancy check code (CRC-16) of the brightness control instruction is calculated synchronously and appended to the end of the instruction message to construct a complete transmission frame. The redundant dual links (primary link and backup link) of the tunnel backbone network are used to synchronously send transmission frames with the same timestamp, and the dual link data is compared in real time at the distributed control node. The receiving end performs a self-check on the legality of the incoming command message. If it detects a CRC check failure or a discontinuous message sequence number, it immediately triggers a retransmission mechanism and sends a link abnormality alarm to the central controller. A logic redundancy determination based on majority voting mechanism is introduced. When multiple sets of control commands arrive within a preset synchronization window, the execution logic can only be activated if more than half of the message contents are completely identical. Before the final hardware is driven, instruction readback verification is performed. That is, the lighting driver feeds back the brightness parameters to the control node for pre-execution. Only after the parameters are verified to be correct can the hardware drive signal be officially generated.

[0062] Optionally, the redundant dual links can be industrial Ethernet based on a dual-ring network architecture, dual RS-485 buses, or physically isolated primary and backup 5G dedicated network slices; this invention does not limit the scope of the invention.

[0063] Optionally, the duration of the synchronization window can be set from 10ms to 100ms, and this invention does not impose any limitation.

[0064] Optionally, the hardware drive signal can be a power-amplified MOSFET drive level, an IGBT trigger pulse, or a solid-state relay control logic signal; this invention does not impose any limitations.

[0065] As can be seen, through the above optional embodiments, by introducing CRC-16 check, redundant dual-link transmission and majority voting logic, and in conjunction with the readback check mechanism of pre-executed instructions, a full-link redundant defense system from instruction encapsulation to hardware driver is constructed, which significantly reduces the risk of malfunction caused by communication link failure or electromagnetic interference and ensures the deterministic operation of the tunnel safety assurance system.

[0066] In one specific implementation scheme, the above technical solution is achieved through a smart dimming server and its supporting system. This smart dimming server has built-in field-level dimming software, serving as the core control unit of the tunnel lighting system.

[0067] The specific implementation process is as follows: First, this intelligent dimming server acquires real-time light intensity data (such as external tunnel brightness and internal tunnel ambient brightness) and related environmental parameters (such as traffic flow and speed) from multiple locations within the tunnel area via its configured one RS232 serial port (3-wire) and five RS485 serial ports. Furthermore, utilizing its built-in 10 / 100 / 1000M adaptive Ethernet card, the server can also connect to various monitoring terminals within the tunnel via industrial Ethernet.

[0068] Secondly, the server utilizes the computing power provided by its quad-core processor and 8GB of memory to run the prediction algorithm in the on-site dimming software. This algorithm combines historical environmental data stored on the server's 500GB hard drive to analyze the real-time light intensity data and related environmental parameters, predicting the light environment characteristics of the tunnel area within a preset future time period.

[0069] Subsequently, the server matches the corresponding dynamic control parameters based on the predicted characteristics of the lighting environment, and determines the brightness adjustment strategy for each lighting zone in conjunction with the spatial layout of the tunnel area. During this process, managers can monitor the brightness distribution and strategy execution of each zone in real time through the server's built-in 8-inch capacitive touch LCD display (with a resolution of 1024*768 and a wide viewing angle of 178° horizontally and 170° vertically).

[0070] Finally, based on the brightness adjustment strategy, the server generates brightness control commands for the lighting devices in each lighting zone and sends these commands to the corresponding lighting devices (such as LED dimming power supplies) for execution via an RS485 interface or an Ethernet interface. Because this intelligent dimming server has good environmental adaptability and can operate stably in environments ranging from 0℃ to 50℃, it ensures that the tunnel lighting system can perform uninterrupted real-time intelligent dimming according to changes in the external environment. A user interface for this tunnel lighting system can be found in [reference needed]. Figure 4Its visualization interface can display the specific automatically adjusted lighting strategy and analyze the energy consumption of the tunnel control system, including the tunnel lighting system. The results can be found in [reference needed]. Figure 5 Therefore, it can achieve excellent energy-saving effects.

[0071] Furthermore, after applying this tunnel lighting control system to a specific tunnel area, its power consumption data can be found in [reference needed]. Figure 6 Before the system went online, from January to May 2025, the tunnel's overall energy consumption increased by nearly 20% compared to the same period in 2024. During the trial operation of the system in mid-May 2025, relying on automatic lighting control based on "brightness + traffic flow," the tunnel's energy consumption in May 2025 was on par with the same period in 2024, a significant improvement compared to the "20% year-on-year increase" trend from January to April 2025. In June 2025, energy consumption decreased by 30% year-on-year, demonstrating significant energy-saving effects, and the energy consumption curve was smooth without significant fluctuations. During July and August 2025, with increased sunny weather, energy savings were around 18%. From September to October 2025, energy consumption decreased by more than 30% year-on-year, and the energy consumption data remained stable, ensuring both energy-saving effects and compliance with safety requirements.

[0072] Example 2 Please see Figure 2 , Figure 2 This is a schematic diagram of a tunnel dimming control system based on illumination environment analysis, as disclosed in an embodiment of the present invention. Figure 2 The described tunnel dimming control system based on illumination environment analysis can be applied to data processing systems / data processing equipment / data processing servers (wherein, the server includes a local processing server or a cloud processing server). For example... Figure 2 As shown, the tunnel dimming control system based on illumination environment analysis may include: The acquisition module 201 is used to acquire real-time light intensity data and environmental parameters at multiple locations in the tunnel area.

[0073] The prediction module 202 is used to predict the light environment characteristics of the tunnel area in a future preset time period based on real-time light intensity data and environmental related parameters. The determination module 203 is used to match the corresponding dynamic control parameters based on the predicted characteristics of the light environment, and to determine the brightness adjustment strategy for each lighting zone in combination with the spatial layout of the tunnel area. The control module 204 is used to generate brightness control instructions for the lighting devices in each lighting zone according to the brightness adjustment strategy, and send the brightness control instructions to the lighting devices.

[0074] As can be seen, the above-mentioned embodiments of the invention predict future light environment characteristics by acquiring multi-location illumination data and environmental parameters of the tunnel, and determine the brightness adjustment strategy of each lighting zone based on the predicted light environment characteristics and spatial layout, and issue brightness control instructions for the lighting zones, thereby realizing the technical improvement of tunnel lighting from static sensing to active predictive control, effectively eliminating the "black hole effect" at the tunnel entrance, and significantly optimizing the energy efficiency and driving safety of the tunnel lighting system.

[0075] As an optional embodiment, the location is the entrance section, transition section, or exit section of the tunnel area.

[0076] As can be seen, the above optional embodiments limit the type of sensor data acquisition location so that real-time light intensity data can comprehensively characterize the lighting characteristics of the tunnel, and help realize the technical improvement of tunnel lighting from static sensing to active predictive control.

[0077] As an optional embodiment, the environmental parameters include at least one of time parameters, weather parameters, and traffic flow change parameters.

[0078] As can be seen, the above optional embodiments define the data details of environmental correlation parameters to comprehensively characterize the multi-location environmental characteristics of the tunnel, and assist in realizing the technical improvement of tunnel lighting from static sensing to active predictive control.

[0079] As an optional embodiment, the prediction module predicts the specific methods by which it predicts the light environment characteristics of the tunnel area within a preset time period based on real-time illumination intensity data and environmental correlation parameters, including: The external environmental impact factors of the tunnel area are quantitatively characterized based on environmental correlation parameters. Extract the light intensity gradient features of real-time light intensity data on the spatial axis, and extract the corresponding light intensity fluctuation components based on the historical evolution features of real-time light intensity data; The light intensity gradient features, light intensity fluctuation components, and quantified external environmental influencing factors are used to construct a multi-dimensional feature vector to generate a spatiotemporal feature matrix of the light environment. The spatiotemporal feature matrix of the light environment is input into a preset time series prediction model. The time series prediction model is used to extract features and perform nonlinear mapping on the brightness evolution trend and color temperature shift law in the preset future time period to obtain the light environment prediction features.

[0080] As can be seen, through the above optional embodiments, by quantifying environmental influencing factors and extracting light intensity gradient and fluctuation components to construct a spatiotemporal feature matrix, and then using a time series prediction model to extract the brightness evolution trend and color temperature shift law, a high-precision nonlinear mapping of the dynamic changes of the light environment in complex tunnel environments is achieved, providing more forward-looking data prediction support for refined on-demand lighting.

[0081] As an optional implementation, the time series prediction model is trained through the following steps: Historical illumination intensity data and historical environmental parameters of the tunnel area during the historical operation cycle are obtained, and the historical illumination intensity data and historical environmental parameters are preprocessed by denoising and normalization to construct the original time series training set. The original time series training set is sampled based on a preset sliding window length to extract the historical light intensity evolution features and environmental disturbance components corresponding to each sampling time, and to construct a sample pair consisting of a multi-dimensional feature vector and the corresponding future light intensity ground value. Construct a deep learning network containing recurrent neural network layers or attention mechanism layers, and use the deep learning network to perform feature mapping on sample pairs in order to capture the long-term and short-term dependencies and nonlinear evolution laws of light environment data on the time axis. Define a target loss function for the prediction bias of the light environment, and use the backpropagation algorithm and a preset optimizer to iteratively optimize the model weights of the deep learning network until the target loss function reaches the preset convergence threshold. The optimized model is evaluated on a comprehensive basis in terms of prediction accuracy and response latency using reserved test samples. After the evaluation is passed, the model is solidified to generate a time series prediction model.

[0082] As can be seen, by sampling and denoising historical data and constructing a deep learning network with an attention mechanism, the long-term and short-term dependencies of light environment data on the time axis can be captured, which can significantly improve the robustness of the prediction model to non-stationary environmental disturbances such as sudden weather changes. Furthermore, closed-loop iterative optimization ensures the prediction accuracy and millisecond-level response speed of the model in actual operation.

[0083] As an optional embodiment, the determining module matches corresponding dynamic control parameters based on the predicted characteristics of the light environment, and determines the specific method of brightness adjustment strategy for each lighting zone in combination with the spatial layout of the tunnel area, including: Based on the predicted characteristics of the light environment, the target dimming curve and brightness fluctuation tolerance corresponding to the expected brightness evolution trend are matched from the preset control index matrix and used as dynamic control parameters. The lighting topology of the tunnel area is obtained, and the functional location of each lighting zone in the tunnel area is identified based on the lighting topology to determine the brightness response weight of each lighting zone. By combining dynamic control parameters and brightness response weights, the brightness adjustment benchmark value for each lighting zone is calculated; Based on the brightness adjustment benchmark value, a preset visual transition model is used to generate the brightness gradient distribution between adjacent lighting zones in order to determine the brightness adjustment strategy for each lighting zone.

[0084] As can be seen, through the above optional embodiments, the response weight is determined by matching the dimming curve according to the predicted features and combining the functional positioning of the lighting topology, and the brightness gradient distribution is generated by using the visual transition model to determine the adjustment strategy. This achieves a smooth transition and functional adaptation of the brightness of the lighting zones, which greatly improves the visual comfort during driving while conforming to the visual adaptation characteristics of the human eye.

[0085] As an optional embodiment, the control module generates brightness control commands for the lighting devices in each lighting zone according to the brightness adjustment strategy, and sends the brightness control commands to the lighting devices in the following specific ways: Analyze the brightness adjustment strategy of each lighting zone, and extract the corresponding brightness target value and the preset brightness smooth switching slope; Based on the hardware communication protocol of the lighting equipment in each lighting zone, the target brightness value and the brightness smooth switching slope are mapped to the corresponding pulse width modulation duty cycle signal or analog voltage adjustment parameter. By combining the current real-time current feedback of the lighting zone and the preset equipment life protection model, the pulse width modulation duty cycle signal is threshold-limited and its electrical characteristics are corrected to generate brightness control commands that meet the hardware driving requirements. According to the spatial topology order of the tunnel area, each brightness control command is encapsulated with the corresponding device physical address and synchronous execution timestamp, and then mapped to the communication scheduling queue for execution.

[0086] As can be seen, through the above optional embodiments, the adjustment strategy is parsed and mapped to a pulse width modulation signal, and threshold limiting is performed by combining real-time current feedback and life protection model. This achieves a safe conversion of brightness commands from the logic layer to the physical driving layer. By encapsulating the address and timestamp through spatial topology order, the high synchronization and electrical operation stability of the lighting equipment in the distributed control scenario are ensured.

[0087] As an optional embodiment, the system is also used to perform the following steps: During the instruction encapsulation stage, the cyclic redundancy check code (CRC-16) of the brightness control instruction is calculated synchronously and appended to the end of the instruction message to construct a complete transmission frame. The redundant dual links (primary link and backup link) of the tunnel backbone network are used to synchronously send transmission frames with the same timestamp, and the dual link data is compared in real time at the distributed control node. The receiving end performs a self-check on the legality of the incoming command message. If it detects a CRC check failure or a discontinuous message sequence number, it immediately triggers a retransmission mechanism and sends a link abnormality alarm to the central controller. A logic redundancy determination based on majority voting mechanism is introduced. When multiple sets of control commands arrive within a preset synchronization window, the execution logic can only be activated if more than half of the message contents are completely identical. Before the final hardware is driven, instruction readback verification is performed. That is, the lighting driver feeds back the brightness parameters to the control node for pre-execution. Only after the parameters are verified to be correct can the hardware drive signal be officially generated.

[0088] As can be seen, through the above optional embodiments, by introducing CRC-16 check, redundant dual-link transmission and majority voting logic, and in conjunction with the readback check mechanism of pre-executed instructions, a full-link redundant defense system from instruction encapsulation to hardware driver is constructed, which significantly reduces the risk of malfunction caused by communication link failure or electromagnetic interference and ensures the deterministic operation of the tunnel safety assurance system.

[0089] Example 3 Please see Figure 3 , Figure 3 This is another tunnel dimming control system based on illumination environment analysis disclosed in the embodiments of the present invention. Figure 3 The described tunnel dimming control system based on illumination environment analysis is applied in a data processing system / data processing equipment / data processing server (wherein, the server includes a local processing server or a cloud processing server). For example... Figure 3 As shown, the tunnel dimming control system based on illumination environment analysis may include: Memory 301 storing executable program code; Processor 302 coupled to memory 301; The processor 302 calls the executable program code stored in the memory 301 to execute the steps of the tunnel dimming control method based on illumination environment analysis described in Embodiment 1.

[0090] Example 4 This invention discloses a computer read storage medium that stores a computer program for electronic data interchange, wherein the computer program causes a computer to execute the steps of the tunnel dimming control method based on illumination environment analysis described in Embodiment 1.

[0091] Example 5 This invention discloses a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to perform the steps of the tunnel dimming control method based on illumination environment analysis described in Embodiment 1.

[0092] The foregoing has described specific embodiments of this specification; other embodiments are within the scope of the appended claims. In some cases, the actions or steps described in the claims may be performed in a different order than those shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily have to follow the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0093] The systems, devices, modules, or units described in the above embodiments can be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, a computer can be, for example, a personal computer, laptop computer, cellular phone, camera phone, smartphone, personal digital assistant, media player, navigation device, email device, game console, tablet computer, wearable device, or any combination of these devices.

[0094] For ease of description, the above devices are described in terms of function, divided into various units. Of course, in implementing this specification, the functions of each unit can be implemented in one or more software and / or hardware components.

[0095] Those skilled in the art will understand that the embodiments of this specification can be provided as methods, systems, or computer program products. Therefore, the embodiments of this specification can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the embodiments of this specification can take 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 code.

[0096] This specification is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this specification. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create a machine for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0097] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0098] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0099] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0100] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0101] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0102] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0103] This specification can be described in the general context of computer-executable instructions that are executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform a specific task or implement a specific abstract data type. This specification can also be practiced in distributed computing environments, where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0104] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to interchangeably. Each embodiment focuses on describing the differences from other embodiments. In particular, the system embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments.

[0105] Finally, it should be noted that the tunnel dimming control method and system based on illumination environment analysis disclosed in the embodiments of the present invention are merely preferred embodiments of the present invention and are only used to illustrate the technical solutions of the present invention, not to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A tunnel dimming control method based on illumination environment analysis, characterized in that, The method includes: Acquire real-time illumination intensity data and environmental parameters at multiple locations within the tunnel area; Based on the real-time illumination intensity data and the environmental correlation parameters, predict the light environment characteristics of the tunnel area in the future preset time period; Based on the predicted characteristics of the light environment, the corresponding dynamic control parameters are matched, and the brightness adjustment strategy of each lighting zone is determined in combination with the spatial layout of the tunnel area. According to the brightness adjustment strategy, a brightness control command is generated for the lighting devices in each lighting zone, and the brightness control command is sent to the lighting devices.

2. The tunnel dimming control method based on illumination environment analysis according to claim 1, characterized in that, The location refers to the entrance section, transition section, or exit section of the tunnel area.

3. The tunnel dimming control method based on illumination environment analysis according to claim 1, characterized in that, The environmental parameters include at least one of time parameters, weather parameters, and traffic flow change parameters.

4. The tunnel dimming control method based on illumination environment analysis according to claim 1, characterized in that, The step of predicting the light environment characteristics of the tunnel area within a future preset time period based on the real-time illumination intensity data and the environmental correlation parameters includes: The external environmental impact factors of the tunnel area are quantitatively characterized based on the environmental correlation parameters. Extract the light intensity gradient features of the real-time light intensity data on the spatial axis, and extract the corresponding light intensity fluctuation components based on the historical evolution features of the real-time light intensity data; The light intensity gradient features, the light intensity fluctuation components, and the quantified external environmental influencing factors are used to construct a multi-dimensional feature vector to generate a spatiotemporal feature matrix of the light environment. The light environment spatiotemporal feature matrix is ​​input into a preset time series prediction model. The time series prediction model is used to extract features and perform nonlinear mapping on the brightness evolution trend and color temperature shift law in the future preset time period to obtain the light environment prediction features.

5. The tunnel dimming control method based on illumination environment analysis according to claim 4, characterized in that, The time series prediction model is trained through the following steps: Historical illumination intensity data and historical environmental correlation parameters of the tunnel area during the historical operation cycle are obtained, and the historical illumination intensity data and historical environmental correlation parameters are preprocessed by denoising and normalization to construct the original time series training set. The original time series training set is sampled based on a preset sliding window length to extract the historical light intensity evolution features and environmental disturbance components corresponding to each sampling moment, and to construct a sample pair consisting of a multi-dimensional feature vector and the corresponding future light intensity ground value. Construct a deep learning network containing recurrent neural network layers or attention mechanism layers, and use the deep learning network to perform feature mapping on the sample pairs in order to capture the long-term and short-term dependencies and nonlinear evolution laws of light environment data on the time axis. Define a target loss function for the prediction bias of the light environment, and use the backpropagation algorithm and a preset optimizer to iteratively optimize the model weights of the deep learning network until the target loss function reaches a preset convergence threshold. The optimized model is evaluated on a comprehensive basis in terms of prediction accuracy and response latency using reserved test samples. After the evaluation is passed, the model is solidified to generate the time series prediction model.

6. The tunnel dimming control method based on illumination environment analysis according to claim 1, characterized in that, The step of matching corresponding dynamic control parameters based on the predicted light environment features and determining the brightness adjustment strategy for each lighting zone in conjunction with the spatial layout of the tunnel area includes: Based on the predicted characteristics of the light environment, a target dimming curve and brightness fluctuation tolerance corresponding to the expected brightness evolution trend are matched from the preset control index matrix as dynamic control parameters. The lighting topology of the tunnel area is obtained, and the functional positioning of each lighting zone in the tunnel area is identified based on the lighting topology to determine the brightness response weight of each lighting zone. By combining the dynamic control parameters and the brightness response weight, the brightness adjustment reference value for each lighting zone is calculated; Based on the brightness adjustment reference value, a preset visual transition model is used to generate the brightness gradient distribution between each adjacent lighting zone, so as to determine the brightness adjustment strategy for each lighting zone.

7. The tunnel dimming control method based on illumination environment analysis according to claim 1, characterized in that, The step of generating a brightness control command for the lighting devices in each lighting zone according to the brightness adjustment strategy, and sending the brightness control command to the lighting devices, includes: The brightness adjustment strategy of each lighting zone is analyzed, and the corresponding brightness target value and preset brightness smooth switching slope are extracted. According to the hardware communication protocol of the lighting equipment in each lighting zone, the target brightness value and the brightness smooth switching slope are mapped to the corresponding pulse width modulation duty cycle signal or analog voltage adjustment parameter. Based on the current real-time current feedback of the lighting zone and the preset equipment life protection model, the pulse width modulation duty cycle signal is threshold-limited and its electrical characteristics are corrected to generate the brightness control command that meets the hardware driving requirements. According to the spatial topology order of the tunnel area, each brightness control command is encapsulated with a corresponding device physical address and a synchronous execution timestamp, and then mapped to the communication scheduling queue for execution.

8. The tunnel dimming control method based on illumination environment analysis according to claim 7, characterized in that, The method further includes: During the instruction encapsulation stage, the cyclic redundancy check code (CRC-16) of the brightness control instruction is calculated synchronously and appended to the end of the instruction message to construct a complete transmission frame. The transmission frames carrying the same timestamp are sent synchronously through the redundant dual links (main link and backup link) of the tunnel backbone network, and the dual link data are compared in real time at the distributed control node side. The receiving end performs a self-check on the legality of the incoming command message. If it detects a CRC check failure or a discontinuous message sequence number, it immediately triggers a retransmission mechanism and sends a link abnormality alarm to the central controller. A logic redundancy determination based on majority voting mechanism is introduced. When multiple sets of control commands arrive within a preset synchronization window, the execution logic can only be activated if more than half of the message contents are completely identical. Before the final hardware is driven, instruction readback verification is performed. That is, the lighting driver feeds back the brightness parameters to the control node for pre-execution. Only after the parameters are verified to be correct can the hardware drive signal be officially generated.

9. A tunnel dimming control system based on illumination environment analysis, characterized in that, The system includes: The acquisition module is used to acquire real-time light intensity data and environmental parameters at multiple locations in the tunnel area; The prediction module is used to predict the light environment characteristics of the tunnel area within a future preset time period based on the real-time light intensity data and the environmental correlation parameters. The determination module is used to match the corresponding dynamic control parameters based on the predicted characteristics of the light environment, and to determine the brightness adjustment strategy for each lighting zone in combination with the spatial layout of the tunnel area. The control module is configured to generate brightness control instructions for the lighting devices in each lighting zone according to the brightness adjustment strategy, and send the brightness control instructions to the lighting devices.

10. A tunnel dimming control system based on illumination environment analysis, characterized in that, The system includes: Memory containing executable program code; A processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the tunnel dimming control method based on illumination environment analysis as described in any one of claims 1-8.

Images