Tunnel intelligent lighting system based on self-luminous paint

Abstract

The invention belongs to the technical field of tunnel lighting, and provides a tunnel intelligent lighting system based on self-luminous paint, which comprises an LED lamp fixed in a tunnel, the self-luminous paint, an environment monitoring module and a control terminal, the self-luminous paint is coated on the inner wall of the entrance of the tunnel, the environment monitoring module is fixed at the entrance of the tunnel, and the control terminal is connected with the LED lamp. And the control terminal is used for detecting the illumination intensity outside the tunnel, the meteorological data, the speed of the vehicle and the brightness of the self-luminous coating, is in communication connection with the environment detection module and the LED lamp, and adjusts the brightness of the LED lamp according to the meteorological data, the speed of the vehicle and the brightness of the self-luminous coating. The self-luminous coating and active LED lighting can be cooperatively controlled, the problems that a traditional system is poor in visual adaptation, high in energy consumption and low in reliability are solved, the LED light supplementing amount is dynamically adjusted according to environment illumination, meteorological conditions, the vehicle speed and the actual brightness of the coating, active and passive light source complementation and accurate dimming are achieved, and the black and white hole effect is effectively relieved.

Description

Technical Field

[0001] This invention belongs to the field of tunnel lighting technology and provides a tunnel intelligent lighting system based on self-luminous coating. Background Technology

[0002] With the continuous improvement of transportation infrastructure, tunnels are increasingly widely used in highway and railway transportation networks, becoming a key node for ensuring smooth cross-regional traffic. Tunnel lighting, as a core component of tunnel operation, directly affects driver safety and overall tunnel operational efficiency. It not only needs to provide a stable and visible lighting environment inside the tunnel but also needs to alleviate visual adaptation problems caused by the drastic difference in light intensity between the inside and outside of the tunnel at tunnel entrances and exits. However, current tunnel lighting scenarios present significant challenges: on the one hand, the "black hole effect" (the brightness inside the tunnel is much lower than outside when a vehicle enters, causing a sudden dimming of the driver's vision) and the "white hole effect" (the brightness inside the tunnel is much higher than outside when a vehicle exits, causing a sudden brightening of the driver's vision) frequently occur at tunnel entrances and exits, severely interfering with drivers' visual judgment and increasing the risk of traffic accidents; on the other hand, most tunnel lighting systems still adopt fixed or segmented lighting modes, maintaining a constant brightness output throughout the entire operating period. They cannot dynamically adjust brightness according to real-time changes in light intensity inside and outside the tunnel, weather fluctuations (such as sunny, cloudy, and rainy days), which may affect safety due to insufficient brightness and cause significant energy waste, increasing tunnel operation and maintenance costs.

[0003] To address the aforementioned safety and energy-saving issues in tunnel lighting, the industry and academia have developed several technical solutions to seek breakthroughs. The first type of solution focuses on optimizing active lighting systems through intelligent control algorithms. Its core logic involves using sensors to collect environmental (light intensity, weather) and traffic (vehicle flow, speed) information, combined with advanced algorithms to dynamically adjust the brightness of traditional active lighting fixtures such as LEDs within the tunnel. For example, the solution based on digital twin technology disclosed in Chinese patent CN116761309B simulates vehicle trajectories by constructing a three-dimensional tunnel model. Based on time, weather, and traffic flow, it formulates coarse-adjustment strategies and dynamic fine-tuning strategies for various scenarios such as "cloudy days," "sunny days," and "late night," combining brightness control of "basic lights" and "enhanced lights," and optimizing the solution based on energy consumption statistics and driver feedback. The second type of solution emphasizes alleviating brightness issues at entrances and exits through physical structures. The first type of solution is a tunnel light reduction module designed in Chinese patent CN119653556A. This module uses photovoltaic glass with gradually varying light transmittance to build a shading canopy, which not only achieves a smooth transition between light inside and outside the tunnel to reduce the black hole effect, but also uses solar energy to power the tunnel lighting. At the same time, the internal light environment detector and intelligent dimming module adjust the brightness and color temperature of the variable color temperature (CCT) lamps. The second type of solution takes a macro-level energy management approach, such as the energy management platform built in patent CN115293633A. This platform collects energy consumption data from multiple systems such as tunnel lighting, ventilation, and drainage through an energy consumption monitoring system. The data is then processed by visualization analysis and machine learning models to generate optimization reports, and then the operating strategies of each system are adjusted to achieve overall energy saving.

[0004] Although the aforementioned existing technical solutions have achieved certain results in improving the safety and energy efficiency of tunnel lighting, none of them have broken through the core limitations of traditional active lighting control. The above solutions still rely on actively generated lighting systems (such as LED lights and variable color temperature lights) as the only lighting output carrier. Their technical logic always revolves around "adjusting the brightness of active light sources". This not only makes it difficult to reduce the consumption of electricity (it requires continuous power supply to active lights), but also causes the lighting system to lose its lighting ability under special conditions such as circuit failure and power outage, resulting in darkness in the tunnel and posing a serious threat to the safety of stranded vehicles and personnel. The overall reliability and risk resistance of the system are significantly insufficient. Summary of the Invention

[0005] To address the aforementioned technical problems, this invention provides a tunnel intelligent lighting system based on self-luminous coating. This system can coordinate the control of self-luminous coating and active LED lighting, solving the problems of poor visual adaptation, high energy consumption, and low reliability of traditional systems. Furthermore, it dynamically adjusts the amount of LED supplementary light according to ambient light, weather conditions, vehicle speed, and the actual brightness of the coating, achieving complementarity between active and passive light sources and precise dimming, effectively mitigating the black hole effect.

[0006] The technical solution of the present invention includes LED lights fixed in a tunnel, and further includes: Self-illuminating paint is applied to the inner walls of the tunnel entrances and exits.

[0007] The environmental monitoring module is fixed at the tunnel entrance and exit to detect the light intensity outside the tunnel, meteorological data, vehicle speed, and the brightness of the self-illuminating coating.

[0008] The control terminal is connected to the environmental monitoring module and the LED lights. The control terminal calculates the light intensity required for a vehicle to enter or exit the tunnel based on meteorological data and vehicle speed, and then adjusts the brightness of the LED lights according to the brightness of the self-luminous coating.

[0009] Furthermore, the self-luminous coating is an energy-storing self-luminous coating, and the energy-storing self-luminous coating is an aluminate long afterglow luminescent material.

[0010] Furthermore, the environmental monitoring module includes: The external lighting detection unit is fixed outside the tunnel and is used to detect the lighting intensity outside the tunnel.

[0011] The meteorological information detection unit is fixed outside the tunnel and is used to detect meteorological data outside the tunnel.

[0012] The vehicle information detection unit is fixed at the tunnel entrance and exit to detect the speed of vehicles entering and exiting the tunnel.

[0013] The self-luminescent coating detection unit includes an illuminance sensor fixed to the inner wall of the tunnel, which is used to detect the brightness of the self-luminescent coating.

[0014] The external lighting detection unit, meteorological information detection unit, vehicle information detection unit, and self-luminous coating detection unit are all connected to the control terminal.

[0015] Furthermore, the meteorological information detection unit is also connected to the regional meteorological service center to obtain real-time weather phenomena and forecast and early warning information measured by the meteorological service center.

[0016] Furthermore, the self-luminous coating detection unit also includes a micro-damage sensing network, which comprises several miniature fiber Bragg grating sensors distributed within the self-luminous coating. These miniature fiber Bragg grating sensors are used to detect whether the self-luminous coating has cracks and thickness variations.

[0017] Furthermore, the control terminal includes a management module, which includes: The module fault management module is used to diagnose whether the external lighting detection unit, meteorological information detection unit, and vehicle information detection unit are malfunctioning.

[0018] The self-illuminating coating management module is used to diagnose whether the self-illuminating coating needs to be repaired by staff.

[0019] Furthermore, the diagnostic steps of the module fault management module are as follows: Establish a multi-source data correlation prediction model to generate normal expected range values ​​for external lighting parameters, meteorological parameters, and vehicle information parameters based on historical parameters.

[0020] The real-time monitored parameters of external lighting, meteorological parameters, and vehicle information are compared with their corresponding normal expected range values.

[0021] If the value is within the expected normal range, it is considered normal; if the actual measured value exceeds the expected normal range, then proceed.

[0022] For transient interference filtering, check whether the abnormal reading time is within the time threshold and exhibits a spike pulse pattern. If so, it is determined to be transient interference and is not recorded.

[0023] Continuous verification is performed. If the abnormal reading time exceeds a preset time threshold, it is initially determined to be a potential fault.

[0024] If other independent data with the same error as the abnormal data are retrieved for comparison, and the error exceeds 10% of the error of the other independent data, the detection unit corresponding to the abnormal data is considered to be faulty.

[0025] Furthermore, the diagnostic method for the self-illuminating coating management module is as follows: Establish a three-dimensional digital twin of the self-luminous coating structure.

[0026] It receives damage data from the micro-damage sensor network and multi-dimensional environmental data from the environmental monitoring module, including light intensity, meteorological data, vehicle speed, and brightness of the self-luminous coating.

[0027] The acquired damage data is presented at the corresponding location in the three-dimensional structural digital twin, including crack morphology features and stress distribution cloud maps around them.

[0028] The modification judgment is made, including threshold judgment and prediction judgment. If either the threshold judgment or the prediction judgment needs to be repaired, then it is determined that repair is required.

[0029] The threshold determination is as follows: the crack morphology and surrounding stress distribution are compared with the safety threshold. If it is higher than the safety threshold, it is determined that repair is required; otherwise, monitoring continues.

[0030] The prediction and judgment are as follows: Based on multidimensional environmental data and historical energy storage data of self-luminous coatings, combined with crack morphology characteristics and surrounding stress distribution, predict whether the development of self-luminous materials will affect lighting safety within 24 hours. If so, it is determined that repair is required; otherwise, continuous monitoring is carried out.

[0031] Furthermore, the management module generates a health status report based on the judgment results of the module fault management module and the self-illuminating coating management module, and the control terminal makes decisions based on the health status report.

[0032] Furthermore, the multi-source data correlation expectation model is established as follows: several historical data are used to construct a mathematical model reflecting the correlation between the light intensity outside the tunnel, meteorological data, vehicle speed and the brightness required at the tunnel entrance through statistical learning methods; the historical data includes meteorological data, vehicle speed and light intensity data and the brightness required for vehicles to enter and exit the tunnel.

[0033] The technical solution provided by this invention has the following advantages compared with the prior art: In use, the self-luminous coating applied to the inner wall of the tunnel entrance first provides basic lighting for the tunnel entrance. An environmental monitoring module fixed at the tunnel entrance simultaneously collects real-time data on external light intensity, meteorological data, vehicle speed, and the brightness of the self-luminous coating, transmitting this data to a control terminal with which it is connected. Upon receiving this data, the control terminal analyzes the required lighting intensity for the tunnel entrance based on the collected meteorological data, vehicle speed, and the brightness of the self-luminous coating. It then sends control commands to the LED lights inside the tunnel, which are also with the same communication connection, dynamically adjusting the brightness of the LED lights. This allows the basic lighting from the self-luminous coating and the supplementary lighting from the LED lights to work synergistically to meet the lighting needs of the tunnel entrance, ensuring driving safety and optimizing lighting energy consumption. Compared to existing technologies, this invention coordinates the control of the self-luminous coating and active LED lighting, solving the problems of poor visual adaptation, high energy consumption, and low reliability in traditional systems. Furthermore, it dynamically adjusts the amount of LED supplementary light based on ambient light, meteorological conditions, vehicle speed, and the actual brightness of the coating, achieving complementary active and passive light sources and precise dimming, effectively mitigating the black hole effect.

[0034] Other advantages, objectives and features of the present invention will become apparent in part from the following description, and in part from those skilled in the art through study and practice of the invention. Attached Figure Description

[0035] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the 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.

[0036] Figure 1 This is a schematic diagram of the layout structure of an embodiment of the present invention.

[0037] Figure 2 This is an overall workflow diagram of an embodiment of the present invention.

[0038] Figure label: 1. Cave external illumination detection unit; 2. Meteorological information detection unit; 3. Vehicle information detection unit; 4. Self-luminous coating detection unit; 5. Self-luminous coating; 6. LED lamps; 7. Illuminance sensor. Detailed Implementation

[0039] The following detailed description of a specific embodiment of the present invention is provided in conjunction with the accompanying drawings. However, it should be understood that the scope of protection of the present invention is not limited to the specific embodiment.

[0040] In the description of this invention, it should be understood that the terms "center," "longitudinal," "lateral," "length," "width," "thickness," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," "axial," "radial," and "circumferential" indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing the technical solution of this invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this invention.

[0041] In the description of the embodiments of the present invention, unless otherwise stated, "a plurality of" means two or more.

[0042] like Figure 1 and Figure 2 As shown, the present invention provides a tunnel intelligent lighting system based on self-luminous coating 5, comprising LED lamps 6 fixed in the tunnel, and further including: Self-luminescent coating 5 is applied to the inner walls of the tunnel entrance and exit.

[0043] An environmental monitoring module is fixed at the tunnel entrance and exit to detect the light intensity outside the tunnel, meteorological data, vehicle speed, and the brightness of the self-luminous coating 5.

[0044] The control terminal is connected to the environmental monitoring module and the LED lamps 6. The control terminal calculates the light intensity required for the vehicle to enter or exit the tunnel based on meteorological data and vehicle speed, and then adjusts the brightness of the LED lamps 6 according to the brightness of the self-luminous coating 5.

[0045] This invention realizes a tunnel intelligent lighting system that integrates active and passive light sources and possesses environmental perception and intelligent control capabilities. The system provides continuous illumination by coating the inner walls of the tunnel entrances and exits with a self-luminous coating 5, serving as a basic passive light source. Simultaneously, an environmental monitoring module collects multi-dimensional information in real time, including external light intensity, weather conditions, vehicle driving status, and the luminous performance of the self-luminous coating 5. The control terminal comprehensively analyzes this data and dynamically adjusts the output brightness of the LED lamps 6 to achieve precise supplemental lighting. This architecture not only improves the energy efficiency and safety of the tunnel lighting system but also enhances its robustness in complex environments and under equipment malfunctions.

[0046] Among them, self-luminous coating 5 refers to a type of functional coating material that can continuously emit visible light after absorbing external light energy without the need for an external power supply. This coating absorbs and stores light energy during the day or when there is light in the tunnel, and releases soft and uniform visible light at night or when the light is weak, forming a stable background lighting, which helps to alleviate the perception of sudden changes in brightness when drivers enter the tunnel.

[0047] The environmental monitoring module is a set of multifunctional sensing units deployed in the tunnel entrance and exit areas to acquire key environmental parameters affecting lighting requirements in real time. This module includes, but is not limited to: a light sensor (such as a silicon photodiode illuminance meter) for detecting the intensity of natural light outside the tunnel, installed in an unobstructed location outside the tunnel entrance, with a sampling frequency of no less than 1Hz and a measurement range covering 0–200,000 lux; a meteorological information detection unit 2 for collecting information such as temperature, humidity, precipitation, wind speed, and visibility, which can integrate temperature and humidity sensors, rain gauges, ultrasonic anemometers, and forward-scattering visibility meters; a vehicle information detection unit 3 for monitoring vehicle entry / exit speeds, which can achieve non-contact speed measurement via millimeter-wave radar or Doppler radar, or combine with a high-definition video camera and computer vision algorithms to identify vehicle speed and type; and an illuminance sensor 7 for detecting the current luminous intensity of the self-luminous coating 5, placed near the coating surface and periodically calibrated to ensure measurement accuracy. All of the above sensors have digital communication interfaces (such as RS485, LoRa, or Ethernet), allowing data to be uploaded to the control terminal via wired or wireless means.

[0048] The control terminal is an embedded control system with data processing and logical decision-making capabilities. It typically consists of an industrial-grade central processing unit (CPU), storage unit, communication module, and power management module, and is deployed in a local control box or regional monitoring center within the tunnel. This terminal establishes bidirectional connections with various sensor units in the environmental monitoring module via standard communication protocols (such as Modbus TCP / IP, MQTT, etc.) and receives their real-time monitoring data. Simultaneously, the control terminal establishes a control link (such as DALI, 0–10V analog signal, or PWM dimming interface) with the dimmable LED lights 6 within the tunnel, enabling the issuance of precise brightness adjustment commands. The control terminal has a pre-set multi-parameter fusion algorithm and lighting strategy rule base. Based on received meteorological data (such as reduced visibility due to cloudy or rainy / foggy weather), vehicle speed (high-speed vehicles require a longer adaptation distance), and the actual luminous intensity of the self-luminous coating 5, it calculates the target total illuminance value that meets visual adaptation requirements. It then deducts the contribution from the self-luminous coating 5, with the remaining brightness difference being supplemented only by the LED lights 6, thus achieving on-demand lighting.

[0049] The components described above are organically synergistic: the self-luminous coating 5 acts as a passive light source, storing energy during the day and releasing light at night to provide basic lighting for the tunnel, reducing reliance on active lighting; the environmental monitoring module, as the system's "sensory system," continuously senses changes in the external environment and material conditions, providing data support for intelligent decision-making; the control terminal, as the "brain," fuses and analyzes multi-source information to generate the optimal dimming strategy; and the LED luminaire 6, as the actuator, responds to control commands to adjust light output. Together, these four components form a closed-loop feedback control system, achieving full-process automation from environmental perception to lighting response.

[0050] This invention realizes a tunnel intelligent lighting system based on self-luminous coating 5. By combining self-luminous coating 5 with LED active lighting, the system can automatically adjust the supplementary light intensity under different lighting conditions, achieving a smooth transition in brightness between the inside and outside of the tunnel. This fundamentally reduces the "black hole effect" and "white hole effect," improving driving safety and comfort. By sensing the brightness output of the self-luminous coating 5 in real time, energy waste caused by repeated lighting is avoided, significantly reducing the workload and overall energy consumption of the LED lamps 6. Dynamic control based on vehicle speed and meteorological data further optimizes the adaptability and precision of the lighting strategy. In extreme situations such as power grid failure or lamp damage, the self-luminous coating 5 can continue to emit light, providing minimum safety guidance lighting, improving the system's fault tolerance and operational reliability. Therefore, this system effectively solves the technical problems of poor visual adaptation, high energy consumption, and weak emergency response capabilities in traditional tunnel lighting, achieving multiple technical effects such as energy saving, improved safety, and enhanced system resilience.

[0051] In the embodiments provided by this invention, the self-luminous coating 5 is an energy-storing self-luminous coating 5, which is an aluminate long-afterglow luminescent material. Aluminate long-afterglow luminescent materials are a class of functional inorganic luminescent materials based on alkaline earth metal aluminates and doped with rare earth ions (such as Eu²⁺, Dy³⁺, etc.). Their crystal structure contains numerous defect sites, which can form electron trap energy levels of varying depths, endowing the material with excellent energy storage capacity and an afterglow luminescence time of 8 to 12 hours or more.

[0052] The self-luminescent coating 5 can be made of energy-storing long-afterglow luminescent material, which has high initial brightness, long afterglow time (up to 8 hours or more), and good environmental stability. The coating is applied evenly to the concrete or metal inner wall surface of the tunnel entrance and transition sections by spraying, rolling, or scraping. The coverage area can be set according to the requirements of the visual adaptation zone length in the "Specifications for Ventilation and Lighting Design of Highway Tunnels", which is usually within 50-150 meters of the entrance section.

[0053] This type of material can be prepared into powder form using conventional processes and uniformly dispersed in organic or inorganic binders to form a composite coating that can be sprayed, rolled, or scraped. In actual construction, this coating can be layered and embedded into the inner walls of concrete or steel structures at tunnel entrances and transition sections. The coating thickness can be controlled between 0.5mm and 3mm according to the design illuminance requirements, with a coating weight of approximately 1.2kg / m² to 2.5kg / m². To ensure consistent optical performance, it is recommended to clean, sand, and prime the substrate before application to avoid impurities affecting luminous efficiency.

[0054] Aluminate long-afterglow materials exhibit wavelength selectivity for the excitation light source, primarily responding within the blue-violet light region between 300nm and 450nm, which perfectly matches the blue light component emitted by LED luminaire 6. Therefore, during daily tunnel operation, LED luminaire 6 not only provides direct illumination for vehicles but also acts as a "charging source" for the self-luminous coating 5, achieving a closed-loop energy utilization between active and passive light sources. At night or during periods of low traffic volume, the control system can gradually dim or even shut down some LED luminaire 6, relying on the stored energy in the self-luminous coating 5 to provide safe guidance lighting, thereby significantly extending the energy-saving operating cycle.

[0055] It is worth noting that this material is chemically stable, has strong resistance to ultraviolet aging, and is not prone to powdering or flaking. It can serve for a long time in harsh environments such as humidity, large temperature differences, and corrosion from vehicle exhaust. Experimental data shows that in accelerated aging tests in simulated tunnel environments, after 5,000 hours of continuous irradiation and thermal cycling, its initial luminous intensity retention rate is still higher than 85%, meeting the basic requirements for the durability of lighting facilities in the "Specifications for Ventilation and Lighting Design of Highway Tunnels".

[0056] This invention employs aluminate long-afterglow luminescent material as the functional core of the self-luminescent coating 5, solving the technical problems of short luminescence duration and rapid brightness decline of traditional self-luminescent materials. This allows the coating to maintain observable brightness for a long time without external power supply. Furthermore, because it can efficiently absorb LED light source energy and release energy again, it forms a closed-loop system for coordinated active and passive lighting, thereby significantly reducing the overall energy consumption of the tunnel lighting system. At the same time, the uniform, soft, and glare-free background light generated by this material helps to smoothly transition the difference in lighting inside and outside the tunnel, improving the driver's visual adaptation ability and enhancing driving safety and comfort.

[0057] In the embodiments provided by the present invention, the environmental monitoring module includes: The external lighting detection unit 1 is fixed outside the tunnel and is used to detect the lighting intensity outside the tunnel.

[0058] Meteorological information detection unit 2 is fixed outside the tunnel and is used to detect meteorological data outside the tunnel.

[0059] Vehicle information detection unit 3 is fixed at the tunnel entrance and exit to detect the speed of vehicles entering and exiting the tunnel.

[0060] The self-luminescent coating detection unit 4 includes an illuminance sensor 7 fixed to the inner wall of the tunnel, which is used to detect the brightness of the self-luminescent coating 5.

[0061] The external lighting detection unit 1, meteorological information detection unit 2, vehicle information detection unit 3, and self-luminous coating detection unit 4 are all connected to the control terminal.

[0062] In the proposed technical solution, the environmental monitoring module, as the core component of the entire system's perception layer, undertakes the crucial task of collecting multi-source heterogeneous environmental information. This module consists of four functionally defined and rationally arranged detection units, which independently but collaboratively collect data on external illumination, meteorological conditions, traffic dynamics, and the state of self-luminous materials. All data is then uniformly transmitted to the control terminal for fusion processing and decision analysis. This multi-dimensional, distributed information acquisition architecture significantly enhances the system's ability to identify complex operating conditions, enabling lighting control to not only be real-time but also forward-looking and adaptable.

[0063] The external lighting detection unit 1 is located outside the tunnel, typically installed above or to the side of the tunnel entrance in an unobstructed area, to continuously monitor the light intensity in the natural environment. This unit employs a high-sensitivity silicon photodiode type light sensor with a spectral response range covering the visible light band (400–700 nm), a measurement range of 0–200,000 lx, and a resolution of no less than 1 lx. The sensor is equipped with a dustproof and waterproof housing (IP67 or higher) and features an automatic cleaning device (such as an ultrasonic transducer or miniature wiper) to ensure measurement accuracy during long-term outdoor operation. The unit's function is to capture trends in light intensity caused by sunrise and sunset, cloud cover, and changes in weather, providing a basis for the system to proactively adjust lighting. For example, during the slow decrease in light intensity at dusk, the system can gradually increase the brightness of the LED lights 6 according to a preset curve, preventing the driver from suddenly entering a low-light environment.

[0064] Meteorological information detection unit 2 is also deployed outside the tunnel to acquire key meteorological parameters affecting visual perception and driving safety, including but not limited to ambient temperature, relative humidity, precipitation status, wind speed and direction, and visibility. This unit integrates various specialized sensors: a temperature and humidity sensor using a capacitive probe with an accuracy of ±0.5°C / ±3%RH; a rain gauge with a tipping bucket structure and a resolution of 0.1mm; and a visibility meter using the forward scattering principle to measure the meteorological optical range (MOR), typically with a range of 10m–50km, suitable for identifying low-visibility scenarios such as fog, haze, and snow. All sensors are connected to a local data acquisition unit via RS-485 or LoRa wireless communication protocols, and then uploaded to the control terminal via wired or wireless networks. The function of this unit is to identify the risk of visual attenuation under severe weather conditions, thereby triggering enhanced lighting strategies. For example, when the detected MOR is below 500 meters, the system automatically increases the target brightness value to ensure the driver's ability to recognize the road outline ahead.

[0065] Vehicle information detection unit 3 is positioned high on the top or side wall of the tunnel entrance / exit to detect vehicle speed information in real time as they enter or exit. This unit can be a composite perception system consisting of millimeter-wave radar and a high-definition video camera: the millimeter-wave radar operates at 77GHz, possesses multi-target tracking capabilities, a speed range of 0–200km / h, and an accuracy of ±1km / h, and can operate stably in adverse weather conditions such as rain, snow, fog, and haze; the camera uses machine vision algorithms to achieve vehicle type recognition, lane positioning, and trajectory prediction, assisting the radar in speed verification and traffic flow statistics. The data from both systems are fused through edge computing to output a single, highly reliable speed parameter. The significance of this unit lies in achieving "on-demand lighting"—that is, predicting the time a vehicle will take to cross a transition zone based on its approach speed, and then dynamically adjusting the rate of brightness change to match the brightness gradient with the vehicle's movement rhythm, reducing visual impact.

[0066] The self-luminescent coating detection unit 4 is installed on the inner wall of the tunnel, directly facing the surface of the coated self-luminescent coating 5, for real-time monitoring of its actual luminous brightness. This unit mainly includes one or more illuminance sensors 7, which can be silicon photodiode sensors with filters. Their spectral response characteristics are highly matched to the human visual function V(λ), ensuring that the measurement results reflect the true visual brightness. The sensor installation position should avoid areas of direct LED light interference, typically embedded below the coating layer or on a side support, at a distance of 0.3–0.5 m from the coating surface, with a sampling frequency of not less than 1 Hz. The sensor output signal is transmitted to the control terminal after analog-to-digital conversion to quantify the basic illuminance level provided by the current self-luminescent coating 5. The introduction of this unit overcomes the limitation of traditional systems that rely solely on theoretical models to estimate afterglow brightness, achieving closed-loop feedback control of passive light source output. For example, if the measured brightness of a section of coating is lower than expected due to aging or contamination, the system will automatically increase the LED supplemental lighting to maintain the total lighting requirements.

[0067] Although the aforementioned detection units are physically independent, they form a logically integrated whole. External illumination detection unit 1 and meteorological information detection unit 2 jointly characterize the external environmental background, vehicle information detection unit 3 reflects traffic dynamics, and self-luminous coating detection unit 4 provides feedback on the internal material status of the system. These four units establish a bidirectional connection with the control terminal via a standardized communication interface (such as Modbus TCP / IP or MQTT protocol), supporting real-time data upload and remote configuration updates. After receiving all the raw data, the control terminal combines a preset rule base with a data fusion algorithm to comprehensively determine the required lighting intensity, deducting the contribution from the self-luminous coating 5, and ultimately generating precise LED dimming instructions. This collaborative working mechanism based on multi-source sensing enables the system to maintain optimal lighting conditions under different time, weather, and traffic combinations.

[0068] This invention achieves comprehensive perception and accurate modeling of the lighting environment at tunnel entrances and exits. By integrating multi-dimensional data acquisition capabilities for external illumination, weather conditions, vehicle speed, and the actual brightness of the self-luminous coating 5, it solves the technical problem that a single sensor cannot fully reflect complex operating environments, improving the system's response accuracy under unsteady conditions such as rain, fog, and sudden changes in light intensity between morning and evening. Simultaneously, by directly measuring the output brightness of the self-luminous coating 5 through the illuminance sensor 7, errors caused by theoretical estimations are avoided, enabling refined and dynamic supplementary lighting control. The rational layout and complementary functions of each detection unit ensure the authenticity and representativeness of the data acquisition, comprehensively improving the intelligence level, safety, and energy efficiency of the tunnel intelligent lighting system.

[0069] In the embodiments provided by the present invention, the meteorological information detection unit 2 is also connected to the regional meteorological service center to obtain real-time weather phenomena and forecast and early warning information measured by the meteorological service center.

[0070] This invention achieves wide-area perception and forward-looking control of the external meteorological environment of tunnels. The meteorological information detection unit 2 includes field sensors installed outside the tunnel entrances and exits for directly collecting parameters such as temperature, humidity, precipitation, and visibility. It also includes a functional module that establishes a data connection with the regional meteorological service center via a communication interface. This module can access meteorological data services provided by authoritative institutions such as provincial or municipal meteorological bureaus and traffic meteorological observation networks via standard APIs (Application Programming Interfaces). It can acquire real-time information covering a wide area of ​​meteorological optical visibility, cloud distribution, wind speed and direction, precipitation intensity, lightning activity, and the changing trends of weather phenomena in the next few hours, including the tunnel area and its upstream road sections. The acquired information includes, but is not limited to, the presence of weather phenomena affecting visibility such as fog, sandstorms, heavy rain, and snow, as well as short-term nowcasts and severe weather warnings issued by meteorological departments (such as yellow fog warnings and red rainstorm warnings). This data is imported into the control terminal via an encrypted transmission protocol and undergoes spatiotemporal alignment and fusion processing with data collected by local sensors.

[0071] The regional meteorological service center refers to a specialized meteorological monitoring and forecasting institution operated by the government's meteorological authorities. Its network of radar, satellite remote sensing, and automatic weather stations boasts high spatiotemporal resolution and wide coverage, ensuring the legal authority and high reliability of the data it provides. Meteorological information detection unit 2 connects to this center via wired or wireless communication links (such as fiber optic, 4G / 5G, NB-IoT), supporting various common data formats (such as JSON, XML) and communication protocols (such as HTTP, MQTT) to ensure the stability and compatibility of data exchange. In actual deployment, the system can be configured to receive data in either a timed polling mode or an event-triggered mode. It can also set a focus radius based on geographical location (e.g., within a 50-kilometer radius of the tunnel) to prioritize meteorological dynamics that may affect tunnel operation safety.

[0072] The acquired forecast and early warning information plays a crucial role in the control strategy. For example, if continuous heavy rainfall accompanied by low visibility is detected 30 kilometers upstream, the control terminal can activate a pre-adjustment mechanism before vehicles enter the tunnel, increasing the basic brightness level of the LED lights 6 at the tunnel entrance and exit sections and extending the light intensity gradient distribution in the visual adaptation transition zone. Similarly, upon receiving an orange fog warning, the system can automatically switch to "low visibility emergency lighting mode," enhancing the active supplementary lighting intensity in the self-illuminating coating 5 area on the side walls and simultaneously adjusting the color temperature of the lights to a warm white range (approximately 3000K–4000K) that is more conducive to penetrating fog, thereby improving the driver's visual clarity. Furthermore, this mechanism can be linked with other traffic management systems to push meteorological risk information to variable message signs or in-vehicle navigation systems, forming a multi-dimensional safety assurance system.

[0073] This invention represents a leap from relying solely on local sensors to fusing multi-source meteorological information from both local and regional sources. By incorporating real-time weather phenomena and forecast / warning information from regional meteorological service centers, it compensates for the limitations of on-site sensors in terms of spatial coverage and temporal predictability. It also overcomes the technical shortcomings of traditional systems that cannot respond in advance to severe weather conditions over long distances. Therefore, it significantly improves the foresight and proactiveness of lighting control, enhances driving safety and system robustness under special weather conditions, and provides a data foundation and technical support for cross-regional traffic collaborative management.

[0074] In the embodiments provided by the present invention, the self-luminous coating detection unit 4 further includes a micro-damage sensing network, which includes a plurality of miniature fiber optic grating sensors distributed inside the self-luminous coating 5. The miniature fiber optic grating sensors are used to detect whether the self-luminous coating 5 has cracks and thickness changes.

[0075] These miniature fiber Bragg grating sensors are uniformly distributed within the 5 layers of self-luminous coating, forming a spatially covering monitoring array. Each miniature fiber Bragg grating sensor has a corresponding physical location identifier and can reflect the strain and temperature status of its area in real time through changes in wavelength signals. By analyzing the drift of the reflection spectrum, the system can determine whether there is crack initiation or propagation behavior in the self-luminous coating 5, or whether the coating thickness is unevenly reduced due to wear or peeling.

[0076] By deeply integrating highly sensitive distributed fiber optic sensing technology with functional self-emissive coatings, non-destructive and continuous monitoring of the internal mechanical and structural states of materials has been achieved. Among these technologies, the miniature fiber optic grating sensor is an optical sensing element based on the Bragg grating principle. Its core is a grating structure formed by periodically modulating the refractive index within the fiber core. When stress or temperature changes in the external environment, the grating period and effective refractive index change accordingly, causing a shift in the reflected light of a specific wavelength (i.e., wavelength drift). By accurately measuring this wavelength change, the strain or temperature change at the sensor's location can be deduced.

[0077] Miniature fiber Bragg grating sensors, typically with diameters between 80 and 125 micrometers, are characterized by their small size, flexibility, strong resistance to electromagnetic interference, and corrosion resistance. They are suitable for embedding into five layers of self-luminous coating (1-3 mm thick) without affecting their optical performance or construction process. In actual deployment, sensor density can be increased in critical areas susceptible to vibration and wind pressure, such as the tunnel entrance and sidewalls, based on the structural characteristics and traffic load distribution. For example, 3 to 5 sensor points can be set per square meter to ensure monitoring resolution in key areas. The sensors are connected to an external data acquisition module via fine leads, employing wavelength division multiplexing (WDM) technology for multi-point synchronous reading, avoiding signal crosstalk.

[0078] These miniature fiber Bragg grating sensors can not only detect localized tensile or compressive deformation, but also identify the initiation location and propagation direction of cracks through strain field reconstruction algorithms. For example, when a microcrack appears in a certain area, uneven stress release occurs on both sides of the crack, causing abrupt changes in the strain gradient between adjacent sensors. By comparing the wavelength response differences between adjacent measuring points and combining them with a preset criterion model, the system can locate the crack and assess its severity. Simultaneously, since changes in coating thickness also cause interfacial stress redistribution, resulting in a recognizable strain response on the sensors, this sensor network can also be used to indirectly monitor the wear or peeling trend of the coating.

[0079] Furthermore, the micro-damage sensing network works in conjunction with the illuminance sensors 7 arranged on the coating surface to provide dual data dimensions: "intrinsic structural state" and "external luminescence performance." The former reflects the physical integrity of the material, while the latter characterizes its functional output level. The fusion of these two dimensions allows for a more comprehensive assessment of the overall health of the self-luminous coating 5. For example, even if the current luminescence brightness is within the normal range, if the sensing data shows that microcracks are continuing to propagate, potential failure risks can be predicted in advance, enabling a shift from "post-failure repair" to "pre-failure prediction."

[0080] This invention enables early detection and dynamic tracking of microscopic damage in self-luminous coating 5. By distributing miniature fiber Bragg grating sensors within the coating, it can capture stress anomalies and structural evolution processes within the material in real time, solving the technical challenge of traditional detection methods failing to identify hidden damage. Due to the use of a wavelength-coded optical sensing mechanism, the system boasts advantages such as high precision, anti-interference capabilities, and long-distance transmission, making it suitable for tunnel conditions in complex electromagnetic environments. Furthermore, the spatial distribution characteristics of the sensor network allow for differentiated monitoring of damage states in different areas, providing a reliable data foundation for subsequent digital twin modeling, lifetime prediction, and precise repair. In summary, this embodiment significantly improves the maintainability, operational stability, and long-term reliability of the self-luminous coating 5 system, ensuring the safe and efficient operation of the tunnel intelligent lighting system throughout its entire lifecycle.

[0081] In the embodiments provided by the present invention, the control terminal includes a management module, the management module comprising: The module fault management module is used to diagnose whether the external lighting detection unit 1, meteorological information detection unit 2, and vehicle information detection unit 3 are faulty.

[0082] The self-luminescent coating management module is used to diagnose whether self-luminescent coating 5 requires repair by staff.

[0083] By integrating a management module with dual diagnostic functions into the control terminal, online monitoring and intelligent judgment of the health status of the environmental monitoring subsystem and the self-luminous coating 5 are achieved. The module fault management module continuously evaluates the working status of multiple external environment sensing units, distinguishing between transient interference and actual equipment failure in complex and changing field environments, preventing system malfunctions caused by fluctuations in individual sensor data. The self-luminous coating management module relies on microscopic mechanical response data provided by an embedded micro-damage sensing network, combined with macroscopic luminescent performance feedback, to comprehensively determine whether the coating has structural damage exceeding its self-healing capabilities, thus deciding whether to initiate manual intervention repair procedures. These two sub-modules together constitute the system's "self-checkup" mechanism, enabling the lighting control system to not only perceive the external environment but also manage the health of its own key components.

[0084] The module fault management module is an intelligent diagnostic unit based on multi-source data correlation analysis. Its core lies in establishing a physical and logical relationship model between various environmental parameters. For example, under clear daytime conditions, the light intensity outside the tunnel should be at a high level, the meteorological optical visibility should be good, and there should be no precipitation records. However, at night or in rainy or foggy weather, the light intensity decreases significantly, humidity increases, and visibility decreases. This module generates a joint expected range database containing tunnel light parameters, meteorological parameters, and traffic behavior characteristics through training on historical operating data. In real-time operation, it compares the data uploaded by each detection unit with the normal range under its corresponding operating conditions. When a parameter deviates from expectations, the system does not immediately identify it as a fault. Instead, it initiates a phased verification process: First, it performs transient interference filtering to check whether the abnormal reading manifests as a short-term spike pulse (such as that caused by lightning induction or electromagnetic interference). If the duration is less than a preset time threshold (e.g., 3 seconds), it is considered a temporary disturbance and ignored. If the abnormal state continues to exceed this threshold, it enters the continuous verification phase and is marked as a potential fault point. Subsequently, it retrieves other independent information sources for cross-verification, such as using large-scale meteorological observation data obtained through the API interface provided by the regional meteorological service center, or using millimeter-wave radar and video camera fusion to determine the accuracy of vehicle speed. If there is a systematic deviation of more than 10% between multiple independent data sources and the abnormal sensor readings, the detection unit is finally confirmed to have a functional fault. This process can be applied to any one or more of the following: external illumination detection unit 1, meteorological information detection unit 2, and vehicle information detection unit 3.

[0085] The self-luminescent coating management module is a functional unit specifically designed to assess the service status of self-luminescent materials. Its operation relies on dual inputs from a micro-damage sensing network and illuminance sensors 7. Miniature fiber optic grating sensors, serving as high-precision strain-sensitive elements, are pre-embedded within the five layers of the self-luminescent coating, with 3 to 5 sensors per square meter forming a distributed sensing array. These sensors can capture minute deformation signals within the material in real time, thereby retrieving the crack initiation location, propagation direction, and length, and using a temperature compensation algorithm to eliminate misjudgments caused by thermal expansion and contraction. Simultaneously, illuminance sensors 7, positioned near the coating surface, periodically collect its luminous intensity values ​​to reflect the material's current light output capability. After receiving these two types of data, the self-luminescent coating management module maps them to a pre-constructed three-dimensional digital twin, dynamically reconstructing the actual physical state of the coating in virtual space. Based on this, the module executes two types of judgment logic: first, threshold judgment, which compares the measured crack size and surrounding stress distribution cloud map with a preset safety threshold; if the limit is exceeded, a repair suggestion is triggered; second, prediction judgment, which predicts the crack propagation trend and luminous efficiency decay rate in the next 24 hours based on material aging models, environmental temperature and humidity cyclic loads, and historical energy storage-luminescence cycle data. If the prediction results indicate that the minimum illuminance standard required for the tunnel's visual transition will be affected, then manual intervention for repair is also deemed necessary. This module can also combine regional rainfall forecast information to assess the risk of water vapor infiltration and provide early warnings of potential coating peeling or interface debonding problems.

[0086] The management module is deployed within the control terminal, employing an industrial-grade embedded processor to run diagnostic algorithms and supporting remote upgrades and log export. The module outputs diagnostic results in a structured report, covering the health score, fault type identifier, confidence level, recommended handling measures, and timeliness alerts for each detection unit. This report serves two purposes: firstly, it allows the control terminal to reference different data sources during decision-making, dynamically adjusting their weighting coefficients—for example, automatically reducing the weight of a light sensor to zero upon confirmation of its failure, relying more on meteorological service center data and historical pattern extrapolation; secondly, it can be uploaded to the tunnel central management system via wired or wireless communication links, pushing early warning information to maintenance personnel's mobile terminals for predictive maintenance. Furthermore, when the system detects that a localized area of ​​the self-illuminating coating 5 requires repair, it can activate a micro-repair agent directional release mechanism to automatically inject sealant or active repair fluid during off-peak hours, slowing damage progression and only notifying manual repair in cases of severe failure.

[0087] This invention realizes a tunnel intelligent lighting system with autonomous health diagnosis capabilities. By introducing a module fault management module, the system can automatically identify and isolate failed environmental detection units without relying on manual inspections, preventing erroneous data from contaminating control decisions. This ensures that basic lighting adjustment functions can still be maintained even when some sensors fail, improving the system's robustness and availability. With the configuration of a self-illuminating coating management module, the system can accurately grasp the microscopic damage evolution process of functional materials, avoiding passive lighting insufficiency caused by coating performance degradation, and ensuring the long-term stability of the coordinated operation of active and passive light sources. The synergistic effect of these two modules enables the entire lighting system not only to respond to changes in the external environment but also to sense the status of internal components, achieving a technological leap from "passive response" to "active health management." This design effectively solves the safety hazards caused by sensor false alarms and the difficulty in detecting latent material damage, reduces operation and maintenance costs, and extends the system's lifespan. It is particularly suitable for unattended or high-reliability long tunnel applications.

[0088] In the embodiments provided by this invention, the diagnostic steps of the module fault management module are as follows: Establish a multi-source data correlation prediction model to generate normal expected range values ​​for external lighting parameters, meteorological parameters, and vehicle information parameters based on historical parameters.

[0089] The real-time monitored parameters of external lighting, meteorological parameters, and vehicle information are compared with their corresponding normal expected range values.

[0090] If the value is within the expected normal range, it is considered normal; if the actual measured value exceeds the expected normal range, then proceed.

[0091] For transient interference filtering, check whether the abnormal reading time is within the time threshold and exhibits a spike pulse pattern. If so, it is determined to be transient interference and is not recorded.

[0092] Continuous verification is performed. If the abnormal reading time exceeds a preset time threshold, it is initially determined to be a potential fault.

[0093] If other independent data with the same error as the abnormal data are retrieved for comparison, and the error exceeds 10% of the error of the other independent data, the detection unit corresponding to the abnormal data is considered to be faulty.

[0094] The "establishment of a multi-source data correlation prediction model" refers to constructing a mathematical model based on historical operational data accumulated over a long period. This model utilizes statistical learning methods combining data clustering and pattern recognition to reflect the inherent correlation between external light intensity, meteorological conditions (such as temperature, humidity, precipitation probability, and meteorological optical visibility), and vehicle traffic characteristics (such as average vehicle speed and traffic flow). For example, under clear daytime conditions, light intensity is high (usually greater than 3000 lux), temperature is within a reasonable daytime range (e.g., 15℃~35℃), and vehicle speed is stable (close to the speed limit). However, at night or during heavy rain, light intensity approaches zero, visibility decreases, and vehicle speed generally slows down. Through data clustering and pattern recognition of these typical scenarios, the system can generate expected ranges of multi-dimensional parameter combinations for different time periods and weather types, serving as a benchmark for subsequent real-time comparisons. The model supports periodic updates and can dynamically adjust the expected parameter boundaries according to seasonal changes and holiday traffic patterns to ensure its adaptability and accuracy. The historical data must meet the following conditions: 1) The data coverage includes at least 12 complete calendar months (including traffic periods during the four seasons and statutory holidays) to match the impact of seasonal changes and holiday traffic patterns on the parameters; 2) The data collection frequency is once every 5 minutes, and extreme abnormal data exceeding 3 times the standard deviation (such as abnormal parameters under rare weather conditions such as typhoons and severe snow disasters) must be excluded; 3) The data content includes meteorological data (temperature, humidity, precipitation probability, meteorological optical range), vehicle speed, external light intensity, and "brightness required for vehicles to enter and exit the tunnel" data determined based on the brightness limits of the tunnel entrance section and transition section in the "Specifications for Ventilation and Lighting Design of Highway Tunnels" and the driver's visual adaptation needs.

[0095] "Comparing the real-time detected external lighting parameters, meteorological parameters, and vehicle information parameters with their corresponding expected normal range values" refers to the control terminal immediately calling the aforementioned expected model after receiving the latest data uploaded by the environmental monitoring module to verify each parameter one by one. The comparison process includes not only checking whether the values ​​fall within the preset range but also verifying the logical consistency between parameters. For example, when the lighting intensity is extremely low but the average vehicle speed remains high, the system will mark this combination as an abnormal state, triggering further diagnosis. This step, as the first line of defense in the entire fault identification process, can quickly screen out operational situations that significantly deviate from the normal state.

[0096] The judgment logic distinguishes between normal fluctuations and potential anomalies. When all parameters are within the expected range, the system determines that each detection unit is operating normally; once any parameter is found to exceed its corresponding historical normal range, the anomaly handling process is initiated. This design avoids simply and crudely treating any deviation from the limit as a fault, preserving a reasonable margin of error.

[0097] "Transient interference filtering" aims to eliminate brief signal spikes caused by lightning, high beams, electromagnetic pulses, etc. The system performs waveform analysis on the time series of abnormal readings to determine if they exhibit a pulse pattern with an extremely short duration (e.g., less than 3 seconds), a sudden increase in amplitude followed by a rapid decrease. If this characteristic is met, and the data before and after the spikes return to normal, it is considered transient interference, not recorded, and subsequent diagnostic procedures are not initiated. This mechanism effectively prevents false alarms caused by occasional events, ensuring system stability.

[0098] "Continuous verification" makes a preliminary judgment on persistent anomalies. If a parameter deviates from the expected range for more than a preset time threshold (e.g., 5 to 10 seconds), the system no longer considers it a temporary disturbance, but rather preliminarily determines that the detection unit may have a potential malfunction. This time threshold can be flexibly set according to the importance and response characteristics of different parameters. For example, the illumination parameter can be set to 5 seconds, while the meteorological parameter, which changes more slowly, can be set to more than 10 seconds.

[0099] "Comparing with other independent data that are identical to the abnormal data" is a crucial step in fault confirmation. "Other independent data" refers to information sources from different physical principles or deployment locations that reflect the same environmental variables. For example, when the external lighting detection unit 1 reports a sudden drop in lighting, the system can retrieve the brightness information from the high-definition video camera in the vehicle information detection unit 3 as an independent source for comparison; if the camera image shows the sky is still bright, it indicates that the lighting sensor may have failed. Similarly, when the meteorological information detection unit 2 reports heavy fog, the system can access real-time weather phenomenon API data provided by the regional meteorological service center for verification. Only when there is a consistency deviation among multiple independent sources, and the difference between the data under test and other sources exceeds 10%, is the detection unit ultimately deemed to have failed. This quantified error standard enhances the objectivity and feasibility of the judgment, avoiding subjective assumptions.

[0100] The above steps proceed sequentially, forming a closed-loop fault diagnosis chain: first, a baseline of normal behavior is established through historical modeling; then, anomalies are identified through real-time comparison; next, transient interference is filtered out through time characteristics; and finally, the actual fault is confirmed through multi-source cross-verification. The entire process is automatically executed by the management module within the control terminal, achieving continuous monitoring of sensor health status and fault isolation without manual intervention.

[0101] This invention achieves high-precision fault diagnosis for various detection units in an environmental monitoring module. By introducing a multi-source correlation prediction model based on historical data, the system can understand the coordinated change patterns among different environmental parameters, thus more accurately identifying anomalies. Due to the implementation of a transient interference filtering mechanism, the system can effectively avoid the risk of misjudgment caused by occasional noise. Furthermore, by employing a combination of continuous verification and multi-source cross-validation, the system can make robust decisions under uncertain environments, significantly reducing false alarm and false negative rates. Therefore, this solution solves the technical problems of traditional diagnostic methods being susceptible to transient interference and lacking multi-source verification methods, achieving the technical effects of improving system reliability, ensuring lighting control accuracy, and enhancing operation and maintenance efficiency.

[0102] In the embodiments provided by this invention, the diagnostic method of the self-illuminating coating management module is as follows: A three-dimensional digital twin of the self-luminous coating 5 was created.

[0103] It receives damage data from the micro-damage sensor network and multi-dimensional environmental data from the environmental monitoring module, including light intensity, meteorological data, vehicle speed, and the brightness of the self-luminous coating.

[0104] The acquired damage data is presented at the corresponding location in the three-dimensional structural digital twin, including crack morphology features and stress distribution cloud maps around them.

[0105] The modification judgment is made, including threshold judgment and prediction judgment. If either the threshold judgment or the prediction judgment needs to be repaired, then it is determined that repair is required.

[0106] The threshold determination is as follows: the crack morphology and surrounding stress distribution are compared with the safety threshold. If it is higher than the safety threshold, it is determined that repair is required; otherwise, monitoring continues.

[0107] The prediction and judgment are as follows: Based on multidimensional environmental data and historical energy storage data of self-luminous coating 5, combined with crack morphology characteristics and surrounding stress distribution, it is predicted whether the development of self-luminous material will affect lighting safety within 24 hours. If so, it is determined that repair is required; otherwise, continuous monitoring is carried out.

[0108] This invention constructs a three-dimensional digital twin of the self-luminous coating 5 and integrates real-time damage data and multi-dimensional environmental parameters to achieve visualized monitoring and intelligent repair decision-making of the coating's microscopic state, thereby improving the reliability and safety of the system under complex operating conditions.

[0109] The creation of a three-dimensional digital twin of the self-luminous coating 5 involves constructing a virtual three-dimensional model in the control terminal that perfectly matches the geometry of the actual coated area. This model includes not only the spatial distribution information of the self-luminous coating 5 (such as length, width, thickness, curvature, etc.), but also material property parameters (such as elastic modulus, coefficient of thermal expansion, light conversion efficiency, etc.) and a preset safety threshold database. This digital twin can be rendered using an industrial-grade graphics engine and supports different color-coding of different areas' health levels on the human-machine interface; for example, green indicates normal, yellow indicates a warning, and red indicates immediate repair. This digital twin is applicable to modeling coating structures for various tunnel cross-sections (such as circular, horseshoe, and rectangular) and different construction techniques, and can also be extended to other transportation infrastructure scenarios with functional coatings.

[0110] The micro-damage sensing network, which receives damage data in real time, consists of multiple miniature fiber optic grating sensors embedded within five layers of the self-emissive coating. These sensors are distributed throughout the coating area at a predetermined grid density, with 3 to 5 sensing nodes per square meter, for continuously acquiring physical signals such as strain, temperature, and displacement. The FBG sensors demodulate local stress changes by analyzing variations in reflected wavelengths, thereby identifying the initiation location and propagation direction of micron-sized cracks. The sensing network also includes a wireless communication module, which can upload raw data to a control terminal via LoRa or NB-IoT protocols, ensuring basic data transmission functionality even without external power. Furthermore, alternative solutions mentioned in the disclosure include using piezoelectric thin-film sensors or carbon nanotube conductive composite materials as damage sensing elements, both of which can achieve highly sensitive responses to changes in the internal structure of the coating.

[0111] The environmental monitoring module detects multi-dimensional environmental data including light intensity, meteorological data, vehicle speed, and the brightness of the self-luminous coating 5, covering key external factors affecting coating performance degradation. Light intensity data is provided by a silicon photodiode sensor in the external illumination detection unit 1, with a measurement range of 0–200,000 lx and a sampling frequency of at least 1 Hz. Meteorological data includes ambient temperature and humidity, precipitation probability, wind speed, and MOR (meteorological optical range), some from locally deployed sensors and some obtained via API access to the regional meteorological service center. Vehicle speed information is extracted jointly by millimeter-wave radar and a video camera, with a sampling accuracy better than ±2 km / h. The brightness of the self-luminous coating 5 is measured in real-time by an illuminance sensor 7 fixed to the inner wall, in cd / m². These multi-source heterogeneous data are then input into the digital twin system after timestamp alignment, forming a complete environmental stimulus input sequence.

[0112] The system displays the acquired damage data on the corresponding locations within a 3D structural digital twin. Based on the spatial coordinates of each FBG sensor, the system precisely maps the monitored crack morphology characteristics, such as length, width, depth, and orientation angle, into the virtual model. It then uses finite element analysis algorithms to calculate and generate a stress distribution cloud map around the crack. This cloud map dynamically displays high-stress concentration areas, assisting managers in visually identifying hazardous areas. For example, when a transverse penetrating microcrack appears and the maximum principal stress around it exceeds 1.5 MPa, the system automatically marks it as a high-risk area and triggers a pop-up alarm. This function is applicable to mechanical simulation analysis under various complex boundary conditions and can be combined with machine learning models to continuously optimize the stress inversion algorithm, improving prediction accuracy.

[0113] The core decision-making logic of this invention involves modification judgment, including threshold judgment and predictive judgment. Threshold judgment is a rule-based static criterion that compares the currently measured crack size with a preset safety threshold. If the value exceeds the limit (e.g., crack length > 0.5 mm or peak stress > 2 MPa), repair is directly determined. This safety threshold can be configured differently according to different material systems (e.g., aluminate-based, silicate-based) and construction environments (high temperature and humidity, freeze-thaw cycles) to ensure the adaptability of the judgment standard.

[0114] Predictive assessment is a model-based dynamic extrapolation process. It integrates historical energy storage data (i.e., the coating's ability to absorb and release light energy over the past 24 hours), current environmental loads (such as rainfall frequency and temperature fluctuations), crack propagation rate models, and material fatigue characteristics. Using time-series prediction algorithms (such as LSTM neural networks or the Prophet model), it estimates whether cracks will propagate to a critical size or cause a decrease in luminous efficiency exceeding 30% within the next 24 hours. If the prediction indicates a safety hazard, the repair process is initiated even if the current threshold has not been reached. This predictive function is applicable to long-term operational optimization in different climate regions, facilitating a shift from "post-failure maintenance" to "pre-failure intervention."

[0115] The aforementioned technical features are tightly coupled through data and control flows: the micro-damage sensing network provides raw sensing data, the environmental monitoring module supplements external disturbance information, and the 3D digital twin serves as a unified data integration platform and visualization carrier. Threshold judgment and predictive judgment together constitute a dual-channel decision-making mechanism, complementing each other and avoiding the risk of misjudgment caused by a single judgment mode. For example, in rainy or snowy weather, even if the current crack has not exceeded the limit, if the predictive model identifies that the low-temperature frost heave effect will continue to aggravate crack propagation, the predictive judgment result will be adopted first to issue a repair instruction; while in the case of a sudden impact load causing instantaneous exceedance of limits but with a stable environment, execution may be temporarily suspended, pending further observation.

[0116] This invention achieves intelligent lifecycle management of the health status of self-luminous coatings. By establishing a three-dimensional structural digital twin and updating it synchronously with real-time damage data, it overcomes the technical bottleneck of traditional methods' inability to visualize internal defects. The introduction of a dual mechanism combining threshold judgment and predictive judgment balances current safety and future risks, preventing conservative or aggressive maintenance strategies. Furthermore, the integration of multi-dimensional environmental data and historical energy storage records during the decision-making process makes repair recommendations more scientifically grounded and forward-looking. Ultimately, this achieves the technical effects of improving the reliability of tunnel lighting systems, extending the service life of functional materials, reducing operation and maintenance costs, and ensuring traffic safety. This method can be applied not only to highway tunnels but also to enclosed space lighting scenarios requiring passive light guidance, such as subway platforms and underground passages.

[0117] In the embodiments provided by the present invention, the management module generates a health status report based on the judgment results of the module fault management module and the self-illuminating coating management module, and the control terminal makes decisions based on the health status report.

[0118] This invention achieves comprehensive perception and intelligent response to the system's operational status. The management module, as the core execution unit of the entire system's health management function, integrates dual diagnostic outputs from the module fault management module and the self-luminous coating management module. The module fault management module is responsible for real-time diagnosis of the working status of each sensor unit in the environmental monitoring module (such as the external illumination detection unit 1, meteorological information detection unit 2, and vehicle information detection unit 3), identifying whether there are hardware faults or signal anomalies. The self-luminous coating management module focuses on evaluating the physical integrity and optical performance degradation trend of the self-luminous coating 5 itself, determining whether there are microcrack propagation, coating peeling, or decreased energy storage efficiency requiring manual intervention. The two types of diagnostic results are not isolated but are uniformly integrated into the management module, and after formatting, generate a structured "System Health Status Report."

[0119] The health status report includes, but is not limited to, the following: online / offline status of each detection unit, fault marking information, data reliability score, current health level of the self-luminous coating 5, coordinates of local damage locations, recommended repair time window, and potential risk warning level. The report is uploaded to the control terminal via a communication interface in standardized data frame format, serving as the core basis for the latter to select operating modes and adjust control strategies. For example, when the module fault management module determines that a certain external lighting detection unit 1 has failed, the health status report will mark the device as abnormal and suggest reducing its data weight or even setting it to zero. After receiving this information, the control terminal will automatically reduce the input weight of this channel during subsequent multi-source data fusion to avoid erroneous data affecting the overall judgment. As another example, when the self-luminous coating management module predicts through a digital twin that a crack on a section of wall will expand to a critical size within the next 12 hours, potentially causing a decrease in local luminous brightness of more than 30%, the health status report will generate proactive repair suggestions. Based on this, the control terminal can appropriately increase the supplementary lighting intensity of nearby LED lights 6 in the short term to compensate for the expected brightness loss in advance, thereby ensuring the continuity and safety of the visual transition.

[0120] Furthermore, the health status report can be integrated with the tunnel's central control system via an API interface, supporting remote monitoring, operation and maintenance scheduling, and historical data analysis. In extreme cases, such as simultaneous failure of multiple sensors or large-area paint aging, the control terminal can switch to a preset degraded operation mode or emergency backup mode based on the report content, prioritizing the minimum safe lighting requirements. This closed-loop mechanism, from status perception and fault diagnosis to decision response, significantly enhances the system's autonomous adaptability and engineering practicality.

[0121] This invention achieves closed-loop information flow management from decentralized diagnosis to centralized decision-making. Because the management module integrates the judgment results from the module fault management module and the self-illuminating coating management module and generates a unified health status report, it solves the problems of isolated diagnostic information and delayed response in traditional systems. Therefore, the control terminal can make accurate and timely control decisions based on global status awareness, effectively responding to various complex working conditions such as sensor failures, actuator anomalies, and material performance degradation. This continuously ensures the lighting safety and visual adaptability of tunnel entrances and exits under various operating conditions, improving the system's reliability, intelligence level, and maintainability.

[0122] It should be noted that any parts not disclosed or specifically described in this invention are existing technology or conventional configurations, and their specific structures and working principles will not be elaborated further. In this document, 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 limitations, 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 that element.

[0123] Although embodiments of the present invention have been disclosed above, they are not limited to the applications listed in the specification and embodiments. It can be applied to various fields suitable for the present invention. Other modifications can be readily implemented by those skilled in the art. Therefore, without departing from the general concept defined by the claims and their equivalents, the present invention is not limited to the specific details and examples shown and described herein.

Claims

1. A tunnel intelligent lighting system based on self-luminous coating, comprising LED lights fixed inside the tunnel, characterized in that, Also includes: Self-illuminating paint is applied to the inner walls of the tunnel entrances and exits; The environmental monitoring module is fixed at the entrance and exit of the tunnel to detect the light intensity, meteorological data, vehicle speed, and brightness of the self-luminous coating outside the tunnel. The control terminal is connected to the environmental monitoring module and the LED lights respectively. The control terminal calculates the light intensity required for the vehicle to enter or exit the tunnel based on meteorological data and vehicle speed, and then adjusts the brightness of the LED lights according to the brightness of the self-luminous coating.

2. The tunnel intelligent lighting system based on self-luminous coating as described in claim 1, characterized in that, The self-luminescent coating is an energy-storing self-luminescent coating, and the energy-storing self-luminescent coating is an aluminate long afterglow luminescent material.

3. The tunnel intelligent lighting system based on self-luminous coating as described in claim 1, characterized in that, The environmental monitoring module includes: The external lighting detection unit is fixed outside the tunnel and is used to detect the lighting intensity outside the tunnel. The meteorological information detection unit is fixed outside the tunnel and is used to detect meteorological data outside the tunnel; The vehicle information detection unit is fixed at the tunnel entrance and exit to detect the speed of vehicles entering and exiting the tunnel; The self-luminescent coating detection unit includes an illuminance sensor fixed to the inner wall of the tunnel, which is used to detect the brightness of the self-luminescent coating; The external lighting detection unit, meteorological information detection unit, vehicle information detection unit, and self-luminous coating detection unit are all connected to the control terminal.

4. The tunnel intelligent lighting system based on self-luminous coating as described in claim 3, characterized in that, The meteorological information detection unit is also connected to the regional meteorological service center to obtain real-time weather phenomena and forecast and early warning information measured by the meteorological service center.

5. A tunnel intelligent lighting system based on self-luminous coating as described in claim 3, characterized in that, The self-luminescent coating detection unit also includes a micro-damage sensing network, which comprises several miniature fiber optic grating sensors distributed within the self-luminescent coating. These miniature fiber optic grating sensors are used to detect whether the self-luminescent coating has cracks and thickness variations.

6. The tunnel intelligent lighting system based on self-luminous coating as described in claim 5, characterized in that, The control terminal includes a management module, which includes: The module fault management module is used to diagnose whether the external lighting detection unit, meteorological information detection unit, and vehicle information detection unit are faulty. The self-illuminating coating management module is used to diagnose whether the self-illuminating coating needs to be repaired by staff.

7. A tunnel intelligent lighting system based on self-luminous coating as described in claim 6, characterized in that, The diagnostic steps of the module fault management module are as follows: Establish a multi-source data correlation prediction model, and generate normal expected range values ​​for external lighting parameters, meteorological parameters, and vehicle information parameters based on historical parameters; The real-time detected external lighting parameters, meteorological parameters, and vehicle information parameters are compared with their corresponding normal expected range values. If the value is within the expected normal range, it is considered normal. If the actual measured value exceeds the expected normal range, then proceed as follows: Transient interference filtering: Check whether the abnormal reading time is within the time threshold and presents as a spike pulse. If so, it is determined to be transient interference and is not recorded. Continuous verification is performed. If the abnormal reading time exceeds a preset time threshold, it is initially determined to be a potential fault. If other independent data with the same error as the abnormal data are retrieved for comparison, and the error exceeds 10% of the error of the other independent data, the detection unit corresponding to the abnormal data is considered to be faulty.

8. A tunnel intelligent lighting system based on self-luminous coating as described in claim 7, characterized in that, The diagnostic method for the self-illuminating coating management module is as follows: Establish a three-dimensional digital twin of the self-luminous coating structure; It receives damage data from the micro-damage sensor network and multi-dimensional environmental data from the environmental monitoring module, including light intensity, meteorological data, vehicle speed, and brightness of the self-luminous coating. The acquired damage data is presented at the corresponding location in the three-dimensional structural digital twin, including crack morphology features and stress distribution cloud map around them; The modification judgment is made, including threshold judgment and prediction judgment. If either the threshold judgment or the prediction judgment needs to be repaired, then it is determined that repair is needed. The threshold judgment is as follows: compare the crack morphology and surrounding stress distribution with the safety threshold. If it is higher than the safety threshold, it is determined that repair is required; otherwise, monitoring continues. The prediction and judgment are as follows: Based on multidimensional environmental data and historical energy storage data of self-luminous coatings, combined with crack morphology characteristics and surrounding stress distribution, predict whether the development of self-luminous materials will affect lighting safety within 24 hours. If so, it is determined that repair is required; otherwise, continuous monitoring is carried out.

9. A tunnel intelligent lighting system based on self-luminous coating as described in claim 8, characterized in that, The management module generates a health status report based on the judgment results of the module fault management module and the self-illuminating coating management module, and the control terminal makes decisions based on the health status report.

10. A tunnel intelligent lighting system based on self-luminous coating as described in claim 7, characterized in that, The multi-source data correlation expectation model is established by constructing a mathematical model reflecting the correlation between several historical data, including light intensity outside the cave, meteorological data, vehicle speed, and the required brightness at the cave entrance, through statistical learning methods. The historical data includes meteorological data, vehicle speed, and data on light intensity and the brightness required for vehicles to enter and exit the tunnel.

Images