A ship cabin intelligent lighting system and a lighting brightness adjusting method thereof

Abstract

The present application relates to the technical field of ship cabin intelligent lighting, and particularly relates to a ship cabin intelligent lighting system and a lighting brightness adjusting method thereof, the system comprising a data acquisition module, a data cleaning and estimation module, an illumination calculation module, a fuzzy neural network control module, an adjustable light LED lighting execution module, a human rhythm coordination module, and a fault self-diagnosis and redundancy switching module. The present application improves the accuracy of cabin brightness real value estimation and the system anti-interference ability in complex sea conditions, solves the problem of fixed light source illumination distribution change when the ship is rocking, ensures that each work plane in the cabin always obtains stable and suitable illumination, reduces visual discomfort caused by ship movement, responds faster, has smaller overshoot, and can balance energy saving and comfort targets, helps to adjust the biological clock of the crew, relieve sailing fatigue, improve the psychological and physiological health of long-term sea operation, avoids ship lighting failure, and is convenient for expansion and maintenance.

Description

Technical Field

[0001] This invention relates to the field of intelligent lighting technology for ship cabins, specifically to an intelligent lighting system for ship cabins and a method for adjusting the lighting brightness thereon. Background Technology

[0002] Shipboard lighting systems are an important component in ensuring the work and living conditions of crew members and the safe operation of the ship. Unlike land-based building environments, ships experience continuous rolling and pitching motions due to wind and waves during navigation, causing dynamic changes in the effective illuminance on the horizontal and vertical planes inside the cabins. This directly affects the visual comfort, work efficiency, and circadian rhythms of the crew.

[0003] Existing ship cabin lighting systems mainly suffer from the following technical defects: (1) Lack of motion compensation mechanism. Traditional ship lighting systems usually use constant illuminance output and do not consider the impact of ship motion attitude on effective illuminance. When the ship rolls or pitches significantly, the actual amount of light received on horizontal surfaces such as tabletops and passageways decreases significantly, and the existing system cannot make dynamic compensation, resulting in a sharp deterioration in cabin lighting quality under bad sea conditions.

[0004] (2) Poor sensor data quality. The ship's environment is subject to strong interference factors such as vibration and turbulence. Data collected by a single sensor often contains outliers and noise, which can lead to system malfunctions if used directly for control. Existing systems lack effective data cleaning and multi-source fusion mechanisms for the special environment of ships, making it difficult to obtain accurate and reliable true values ​​of cabin brightness.

[0005] (3) Low level of intelligence. Existing systems mostly use manual adjustment or simple timing control, lacking adaptive learning capabilities based on fuzzy neural networks, and are unable to make comprehensive decisions based on the presence of personnel, environmental changes, and ship attitude. The control strategy is simplistic and cannot achieve refined and personalized lighting adjustment.

[0006] (4) Ignoring the needs of human circadian rhythms. People who work in enclosed cabins for long periods of time are prone to circadian rhythm disorders, resulting in sleep disturbances, decreased attention, and other problems. Existing lighting systems do not have the function of automatically adjusting color temperature according to time to coordinate with the human biological clock, thus failing to give full play to the positive regulatory role of lighting on human physiological rhythms.

[0007] (5) Insufficient reliability. The electrical environment of ships is complex, and factors such as high humidity, salt spray corrosion, and voltage fluctuations can easily lead to electronic equipment failures. The existing lighting system lacks module-level fault self-diagnosis and redundancy switching capabilities. Once the controller fails, the entire lighting system will be paralyzed, seriously affecting the normal operation of the ship and the safety of the crew.

[0008] No solutions have yet been proposed for the relevant technical issues. Summary of the Invention

[0009] To address the problems in related technologies, this invention proposes an intelligent lighting system for ship cabins and its brightness adjustment method to overcome the aforementioned technical issues in existing technologies. The purpose of this invention is to improve the accuracy of estimating the true brightness value of cabins under complex sea conditions and the system's anti-interference capability, solve the problem of changes in the illuminance distribution of fixed light sources when the ship is rolling, ensure that each working surface in the cabin always receives stable and suitable illuminance, reduce visual discomfort caused by ship movement, respond faster, have less overshoot, and can balance energy saving and comfort goals. It helps to regulate the crew's biological clock, alleviate sailing fatigue, improve the psychological and physiological health of long-term sea operations, avoid the failure of shipwide lighting, and facilitate expansion and maintenance.

[0010] To achieve the above objectives, the present invention provides the following technical solution: an intelligent lighting system for ship cabins, comprising: The data acquisition module is used to collect ambient brightness data, point light source parameters and illumination intensity information in the ship's cabin in real time. The data acquisition module includes a ship motion attitude sensor interface for receiving ship roll and pitch angle data. The data cleaning and estimation module, connected to the data acquisition module, is used to clean the acquired data using an adaptive weighted fusion algorithm and estimate the true value of the cabin brightness based on the fusion of multiple sensor data. The data cleaning and estimation module is also used to filter the ship's motion attitude data. The illuminance calculation module, connected to the data cleaning and estimation module, is used to calculate the illumination brightness values ​​of the horizontal and vertical surfaces inside the cabin based on the cleaned data and according to the inverse square law of distance and the cosine law. The illuminance calculation module is also used to dynamically correct the effective illuminance of the horizontal and vertical surfaces according to the ship's roll and pitch angles, and use the calculation results as input parameters for subsequent modules. The fuzzy neural network control module has its input layer connected to the illuminance calculation module and the data cleaning and estimation module, respectively. It is used to receive the illumination brightness values ​​of the horizontal and vertical planes, as well as the filtered ship roll and pitch angle data as feedforward control signals. The fuzzy neural network control module outputs specific illumination brightness adjustment values ​​through internal fuzzification processing, fuzzy rule reasoning, and defuzzification operations. A dimmable LED lighting execution module is connected to the fuzzy neural network control module and is used to automatically adjust the lighting brightness of the ship's cabins according to the adjustment value output by the fuzzy neural network control module. The human circadian rhythm coordination module is connected to the fuzzy neural network control module. It is used to obtain current time information and calculate the phase of the human circadian rhythm, generate color temperature adjustment instructions, and then send the color temperature adjustment instructions and the brightness adjustment values ​​output by the fuzzy neural network control module to the dimmable LED lighting execution module. The fault self-diagnosis and redundancy switching module is connected to the data acquisition module, data cleaning and estimation module, illuminance calculation module, fuzzy neural network control module and dimmable LED lighting execution module, respectively. It is used to monitor the operating status of each module in real time and perform backup channel switching when an abnormality is detected.

[0011] Preferably, the data acquisition module further includes an illuminance sensor, a color temperature sensor, a millimeter-wave radar human presence sensor, and a multi-point illuminance detection unit.

[0012] Preferably, the data cleaning and estimation module integrates a Kalman filter, which is used to predict and smooth the ship's roll and pitch angle data in real time, and to remove outlier data caused by the ship's instantaneous turbulence.

[0013] Preferably, the illuminance calculation module is internally equipped with a three-dimensional spatial grid division unit, which is used to divide the cabin into multiple lighting control sub-regions, calculate the illuminance values ​​of the horizontal and vertical planes of each sub-region, and output the independent adjustment parameters of each sub-region.

[0014] Preferably, the fault self-diagnosis and redundancy switching module includes a main controller fault monitoring unit, a communication link disconnection detection unit, a power supply anomaly monitoring unit, and a backup analog lighting control circuit.

[0015] Preferably, the dimmable LED lighting execution module includes warm and cool white LED beads and RGB ambient lighting beads.

[0016] To achieve the above objectives, the present invention also provides the following technical solution: A method for adjusting lighting brightness includes the following steps: Step S1: Collect ambient brightness data, point light source parameters, and illumination intensity information in the ship's cabin in real time through the data acquisition module, and connect to the ship's motion attitude sensor to obtain the ship's current roll and pitch angle data; Step S2: The data cleaning and estimation module receives the data collected in step S1, uses an adaptive weighted fusion algorithm to perform consistency verification and outlier removal on the multi-sensor data, and uses the built-in Kalman filter to perform real-time prediction and smoothing filtering on the ship's roll and pitch angle data, removing outlier data caused by the ship's instantaneous turbulence, and simultaneously estimates the true value of cabin brightness based on the fusion of multiple sensor data. Step S3: The illuminance calculation module receives the data processed in step S2, and calculates the basic lighting brightness values ​​of the horizontal and vertical planes inside the cabin according to the inverse square law of distance and the cosine law. Then, based on the filtered ship roll and pitch angle data, it dynamically corrects the effective illuminance of the horizontal and vertical planes. The cabin is divided into multiple lighting control sub-regions through the internal three-dimensional spatial grid division unit, and the lighting brightness value of each sub-region is calculated and the independent adjustment parameters of each sub-region are output. Step S4: The input layer of the fuzzy neural network control module simultaneously receives the horizontal and vertical illumination brightness values ​​output in step S3, as well as the ship's roll angle data, pitch angle data, roll angle change rate, and pitch angle change rate after filtering in step S2, as feedforward control signals; the fuzzy neural network control module sequentially performs fuzzification processing, fuzzy rule reasoning, and defuzzification operations, and outputs specific illumination brightness adjustment values; Step S5: The human-cause circadian rhythm coordination module obtains the current time information, calculates the phase of the human diurnal rhythm, generates a color temperature adjustment command, and merges the color temperature adjustment command with the brightness adjustment value output in step S4. The fusion rule is: the brightness adjustment value prioritizes meeting the target illumination requirements of the cabin, and the color temperature adjustment is independently adjusted according to the current rhythm phase based on the brightness adjustment value. The two are merged into the final light and color parameters through a lookup table mapping. Step S6: The dimmable LED lighting execution module receives the adjustment signal fused in step S5 and automatically adjusts the brightness and color temperature of the warm and cool white LED beads and RGB ambient lighting beads in the ship's cabin to achieve lighting output; Step S7: The fault self-diagnosis and redundancy switching module monitors the operating status of the data acquisition module, data cleaning and estimation module, illuminance calculation module, fuzzy neural network control module, and dimmable LED lighting execution module in real time. When a single module malfunction is detected, the backup channel is automatically switched and the backup analog lighting control loop is enabled. When multiple modules malfunction are detected simultaneously, the degradation strategy is executed according to the preset priority order: the dimmable LED lighting execution module is kept operating with the locally saved default values ​​first, and then the backup analog lighting control loop is enabled.

[0017] Preferably, in step S2, the Kalman filter's processing of the ship's roll and pitch angle data specifically includes: state prediction, covariance prediction, Kalman gain calculation, state update, and covariance update, to achieve real-time optimal estimation of dynamic attitude data.

[0018] Preferably, in step S4, the fuzzy rule base of the fuzzy neural network control module is pre-established based on the cabin occupant comfort illuminance range, energy-saving optimization target, and the attenuation characteristics of effective illuminance on the ship's motion attitude. The input variables include horizontal illuminance deviation, vertical illuminance deviation, roll angle change rate, and pitch angle change rate.

[0019] Preferably, in step S7, when the main controller fault monitoring unit detects that the fuzzy neural network control module has failed, it automatically switches to the backup analog lighting control loop, and the output of the illuminance calculation module directly drives the dimmable LED lighting execution module through the analog PID circuit.

[0020] Compared with the prior art, the beneficial effects of the present invention are: This invention relates to an intelligent lighting system for ship cabins and its lighting brightness adjustment method. By setting up a data acquisition module that integrates multiple sensors and ship motion attitude sensor interfaces, and combining an adaptive weighted fusion algorithm with a Kalman filter, it can effectively eliminate outlier data generated by instantaneous ship turbulence, and perform real-time prediction and smoothing filtering of roll and pitch angles, significantly improving the accuracy of cabin brightness estimation and the system's anti-interference capability under complex sea conditions. This invention relates to an intelligent lighting system for ship cabins and its lighting brightness adjustment method. By setting up an illuminance calculation module based on the inverse square law of distance and the cosine law, and using filtered ship roll and pitch angle data, the effective illuminance on the horizontal and vertical planes is dynamically corrected. This solves the problem of illuminance distribution changes of fixed light sources when the ship is rolling, ensuring that each working plane in the cabin always obtains stable and suitable illuminance, and reducing visual discomfort caused by ship movement. This invention relates to an intelligent lighting system for ship cabins and its lighting brightness adjustment method. By setting up a three-dimensional spatial grid division unit, the cabin is divided into multiple independent control sub-regions, which can calculate the lighting brightness value and output independent adjustment parameters respectively. The fuzzy neural network control module not only receives the current illuminance deviation, but also uses the ship's attitude angle and its rate of change as feedforward signals to achieve predictive adjustment. Compared with traditional feedback control, it has a faster response, smaller overshoot, and can take into account both energy saving and comfort goals. This invention relates to an intelligent lighting system for ship cabins and its lighting brightness adjustment method. By setting up a human-cause rhythm coordination module to calculate the phase of the human body's diurnal rhythm based on the current time, it automatically generates a color temperature adjustment command and integrates it with the brightness adjustment value. Under the premise of meeting the target illuminance, the color temperature is dynamically adjusted, which helps to regulate the crew's biological clock, alleviate sailing fatigue, and improve the psychological and physiological health of long-term maritime operations. This invention relates to an intelligent lighting system for ship cabins and its lighting brightness adjustment method. By setting up a fault self-diagnosis and redundancy switching module, it monitors the operating status of the data acquisition module, data cleaning and estimation module, illuminance calculation module, fuzzy neural network control module, and dimmable LED lighting execution module in real time. It also incorporates main controller fault monitoring, communication circuit failure detection, power abnormality monitoring, and backup simulated lighting control loop. Once an abnormality is detected, it can automatically switch to the backup channel or execute a degradation strategy to avoid the failure of the entire ship's lighting. It is especially suitable for scenarios such as ocean voyages where timely maintenance is not possible. This invention relates to an intelligent lighting system for ship cabins and its lighting brightness adjustment method. By setting a fuzzy rule library in the fuzzy neural network control module, it simultaneously considers the illuminance range for personnel comfort, energy-saving optimization objectives, and the attenuation characteristics of effective illuminance due to ship motion. Under the premise of ensuring visual needs, it minimizes the illuminance output in unnecessary areas and achieves precise dimming through a dimmable LED execution module. Compared with traditional constant brightness lighting, it can significantly reduce ship power consumption. Detailed Implementation

[0021] The technical solutions in the embodiments of the present invention will be clearly and completely described below. Example

[0022] This invention proposes a technical solution for an intelligent lighting system for ship cabins and a method for adjusting the lighting brightness: An intelligent lighting system for ship cabins includes: The data acquisition module is used to collect real-time ambient brightness data, point light source parameters, and illumination intensity information inside the ship's cabins. The data acquisition module includes a ship motion attitude sensor interface for receiving ship roll and pitch angle data. Specifically, the data acquisition module is responsible for collecting real-time ambient brightness data, point light source parameters (such as light source position and luminous intensity), and illumination intensity information inside the ship's cabins. In particular, the data acquisition module includes a ship motion attitude sensor interface, which can receive ship roll and pitch angle data to provide raw input for subsequent motion compensation. Through the combination of multiple types of sensors, a comprehensive perception of the cabin lighting environment and ship motion status can be achieved. The data cleaning and estimation module, connected to the data acquisition module, is used to clean the acquired data using an adaptive weighted fusion algorithm and estimate the true value of cabin brightness based on the fusion of data from multiple sensors. The module also filters the ship's motion and attitude data. Specifically, the data cleaning and estimation module preprocesses the raw acquired data, uses an adaptive weighted fusion algorithm to assign weights to each data source according to the confidence level of different sensors, removes outliers, and estimates the true value of cabin brightness through multi-sensor data fusion. Simultaneously, the module filters the ship's motion and attitude data to eliminate measurement noise caused by vibration and turbulence, providing clean and reliable input data for subsequent calculations. The illuminance calculation module, connected to the data cleaning and estimation module, calculates the illumination brightness values ​​of the horizontal and vertical surfaces inside the cabin based on the cleaned data, according to the inverse square law and the cosine law. The illuminance calculation module also dynamically corrects the effective illuminance of the horizontal and vertical surfaces based on the ship's roll and pitch angles, and uses the calculation results as input parameters for subsequent modules. Specifically, based on the cleaned data, the illuminance calculation module calculates the illumination brightness values ​​of the horizontal and vertical surfaces inside the cabin according to two fundamental laws in lighting engineering—the inverse square law (illuminance is inversely proportional to the square of the distance) and the cosine law (illuminance is directly proportional to the cosine of the incident angle). The illuminance calculation module also dynamically corrects the effective illuminance of the horizontal and vertical surfaces based on the ship's roll and pitch angles, because when the ship rolls, the orientation of the originally horizontal working surface relative to the light source changes, resulting in a change in the actual received luminous flux. The illuminance calculation module uses the corrected calculation results as input parameters for the subsequent fuzzy neural network control module. The fuzzy neural network control module has its input layer connected to both the illuminance calculation module and the data cleaning and estimation module. It receives horizontal and vertical illumination values, as well as filtered ship roll and pitch angle data as feedforward control signals. Through internal fuzzification, fuzzy rule reasoning, and defuzzification operations, the fuzzy neural network control module outputs specific illumination adjustment values. Specifically, its input layer simultaneously receives horizontal and vertical illumination values ​​from the illuminance calculation module, and filtered ship roll and pitch angle data from the data cleaning and estimation module—the latter serving as feedforward control signals to enable pre-compensation at the onset of attitude changes. Internally, the fuzzy neural network control module sequentially performs fuzzification (converting precise input values ​​into fuzzy membership degrees), fuzzy rule reasoning (performing logical reasoning based on a preset expert rule base), and defuzzification (converting fuzzy conclusions back into precise control values), ultimately outputting specific illumination adjustment values. The introduction of the fuzzy neural network enables the system to adaptively learn and optimize rule parameters based on actual control effects. The dimmable LED lighting execution module is connected to the fuzzy neural network control module and is used to automatically adjust the lighting brightness of the ship's cabin according to the adjustment value output by the fuzzy neural network control module. Specifically, the dimmable LED lighting execution module receives the adjustment value output by the fuzzy neural network control module and automatically adjusts the lighting brightness of the ship's cabin through PWM (pulse width modulation) or other dimming methods to achieve closed-loop control from decision-making to execution. The human-cause rhythm coordination module, connected to the fuzzy neural network control module, is used to acquire current time information and calculate the phase of the human circadian rhythm, generate color temperature adjustment instructions, and then fuse the color temperature adjustment instructions with the brightness adjustment values ​​output by the fuzzy neural network control module before sending them to the dimmable LED lighting execution module. Specifically, the human-cause rhythm coordination module acquires current time information, calculates the phase of the human circadian rhythm (i.e., the stage of the human biological clock, such as morning, noon, night, etc.), and generates color temperature adjustment instructions accordingly. High color temperature (cool white light) helps to keep people awake, while low color temperature (warm yellow light) helps to relax and promote melatonin secretion. The human-cause rhythm coordination module fuses the color temperature adjustment instructions with the brightness adjustment values ​​output by the fuzzy neural network control module before sending them to the dimmable LED lighting execution module, realizing the coordinated adjustment of brightness and color temperature to help the cabin personnel maintain a normal circadian rhythm. The fault self-diagnosis and redundancy switching module is connected to the data acquisition module, data cleaning and estimation module, illuminance calculation module, fuzzy neural network control module, and dimmable LED lighting execution module, respectively. It is used to monitor the operating status of each module in real time and perform backup channel switching when an anomaly is detected. Specifically, the operating status includes whether the signal is normal, whether the communication is interrupted, and whether the power supply is stable. When any module anomaly is detected, the backup channel switching is automatically executed, and the redundant circuit or degradation strategy is activated to ensure that the lighting system can still maintain basic functions under fault conditions, avoid the paralysis of the entire system, and significantly improve the reliability of the system in the complex marine electrical environment.

[0023] Furthermore, the data acquisition module also includes an illuminance sensor, a color temperature sensor, a millimeter-wave radar human presence sensor, and a multi-point illuminance detection unit.

[0024] In this embodiment, the illuminance sensor measures the ambient illuminance, the color temperature sensor measures the color temperature of the light source, the millimeter-wave radar human presence sensor detects whether there are people in the cabin and their locations, and the multi-point illuminance detection unit deploys multiple illuminance detection points at different locations in the cabin. The illuminance sensor, color temperature sensor, millimeter-wave radar human presence sensor, and multi-point illuminance detection unit can more comprehensively perceive the cabin environment and provide richer data support for refined control.

[0025] Furthermore, the data cleaning and estimation module integrates a Kalman filter, which is used to predict and smooth the ship's roll and pitch angle data in real time, and to remove outlier data caused by the ship's instantaneous turbulence.

[0026] In this embodiment, the Kalman filter is used to perform real-time prediction and smoothing filtering of the ship's roll and pitch angle data. It can effectively eliminate outlier data (i.e., abnormal measurements that deviate significantly from the true values) caused by the ship's instantaneous turbulence. The recursive nature of the Kalman filter makes it very suitable for real-time processing of dynamic attitude data, achieving an optimal balance between prediction and correction.

[0027] Furthermore, the illuminance calculation module is equipped with a three-dimensional spatial mesh division unit, which is used to divide the cabin into multiple lighting control sub-regions, calculate the lighting brightness values ​​of the horizontal and vertical planes of each sub-region, and output the independent adjustment parameters of each sub-region.

[0028] In this embodiment, spatially differentiated lighting control is achieved—for example, high illuminance is maintained in areas where people are present, while illuminance is reduced in unoccupied areas to save energy.

[0029] Furthermore, the fault self-diagnosis and redundancy switching module includes a main controller fault monitoring unit, a communication link break detection unit, a power supply anomaly monitoring unit, and a backup analog lighting control circuit.

[0030] In this embodiment, the main controller fault monitoring unit detects whether the fuzzy neural network controller has crashed or has abnormal output, the communication link disconnection detection unit checks whether the communication lines between modules are interrupted, the power supply abnormality monitoring unit monitors whether the power supply voltage is within the normal range, and the backup analog lighting control circuit is an independent analog circuit backup scheme that does not rely on the digital controller. The main controller fault monitoring unit, the communication link disconnection detection unit, the power supply abnormality monitoring unit, and the backup analog lighting control circuit work together to achieve comprehensive coverage of various faults.

[0031] Furthermore, the dimmable LED lighting execution module includes warm and cool white LED beads and RGB ambient lighting beads.

[0032] In this embodiment, the color temperature of the cool and warm white LED beads is adjusted by mixing the ratio of cool white and warm white LEDs. The RGB ambient lighting beads are red, green and blue LEDs used to create a specific atmosphere or provide indicator lighting. The cool and warm white LED beads mainly meet the brightness and color temperature requirements of daily lighting, while the RGB ambient lighting beads provide additional color adjustment capabilities, enriching the adaptability of lighting scenarios.

[0033] To achieve the above objectives, the present invention also provides the following technical solution: A method for adjusting lighting brightness includes the following steps: Step S1: The data acquisition module collects real-time data on ambient brightness, point light source parameters, and illumination intensity inside the ship's cabin, and connects to the ship's motion attitude sensor to obtain the ship's current roll and pitch angle data; specifically, this lays the foundation for all subsequent processing, and the quality and completeness of the collected data directly affect the system's control effect; Step S2: The data cleaning and estimation module receives the data collected in step S1, uses an adaptive weighted fusion algorithm to perform consistency verification and outlier removal on the multi-sensor data, and uses a built-in Kalman filter to perform real-time prediction and smoothing filtering on the ship's roll and pitch angle data, eliminating outlier data caused by the ship's instantaneous turbulence. At the same time, it estimates the true value of the cabin brightness based on the fusion of multiple sensor data; specifically, the true value is more accurate and reliable than the measurement value of any single sensor. Step S3: The illuminance calculation module receives the data processed in step S2 and calculates the basic lighting brightness values ​​of the horizontal and vertical planes inside the cabin according to the inverse square law of distance and the cosine law. Then, based on the filtered ship roll and pitch angle data, it dynamically corrects the effective illuminance of the horizontal and vertical planes. The cabin is divided into multiple lighting control sub-regions through the internal three-dimensional spatial grid division unit, and the lighting brightness value of each sub-region is calculated and the independent adjustment parameters of each sub-region are output. Specifically, the corrected illuminance value reflects the actual lighting level felt by personnel in a swaying environment. Step S4: The input layer of the fuzzy neural network control module simultaneously receives the horizontal and vertical illumination brightness values ​​output in step S3, as well as the ship's roll angle data, pitch angle data, roll angle change rate, and pitch angle change rate after filtering in step S2, as feedforward control signals. The fuzzy neural network control module sequentially performs fuzzification processing, fuzzy rule reasoning, and defuzzification operations, outputting specific illumination brightness adjustment values. Specifically, the change rate is used as a feedforward control signal, enabling the system to predict attitude change trends. The fuzzification processing converts the input quantity into a fuzzy set, the fuzzy rule reasoning performs reasoning based on the "if-then" rule base, and the defuzzification operation outputs precise brightness adjustment values. Step S5: The human-cause circadian rhythm coordination module acquires the current time information, calculates the human circadian rhythm phase, generates a color temperature adjustment command, and merges the color temperature adjustment command with the brightness adjustment value output in step S4. The fusion rule is: the brightness adjustment value prioritizes meeting the cabin's target illuminance requirements, and the color temperature adjustment is independently adjusted according to the current circadian rhythm phase based on the determined brightness adjustment value. The two are merged into the final light and color parameters through a lookup table mapping. Specifically, the cabin's target illuminance requirements are to ensure basic lighting functions, and independent adjustment means increasing the color temperature during the day and decreasing the color temperature at night. Step S6: The dimmable LED lighting execution module receives the adjustment signal fused in step S5 and automatically adjusts the brightness and color temperature of the warm and cool white LED beads and RGB ambient lighting beads in the ship's cabin to achieve lighting output; specifically, the dimmable LED lighting execution module has fast response and high-precision adjustment capabilities and can follow the changes in control commands in real time. Step S7: The fault self-diagnosis and redundancy switching module monitors the operating status of the data acquisition module, data cleaning and estimation module, illuminance calculation module, fuzzy neural network control module, and dimmable LED lighting execution module in real time. When a single module malfunction is detected, the backup channel is automatically switched and the backup analog lighting control loop is activated. When multiple modules malfunction are detected simultaneously, a degradation strategy is executed according to a preset priority order: the dimmable LED lighting execution module is kept operating at its locally saved default values ​​first, and then the backup analog lighting control loop is activated. Specifically, this ensures that the system is degraded under fault conditions, rather than completely failed.

[0034] Furthermore, in step S2, the Kalman filter's processing of the ship's roll and pitch angle data specifically includes: state prediction, covariance prediction, Kalman gain calculation, state update, and covariance update, thereby achieving real-time optimal estimation of dynamic attitude data.

[0035] In this embodiment, state prediction is to predict the state at the current time based on the optimal estimate of the previous time step, covariance prediction is to predict the uncertainty of the estimate, Kalman gain calculation is to weigh the reliability of the predicted value and the observed value, state update is to correct the predicted value with the current observed value to obtain a new optimal estimate, and covariance update is to update the uncertainty of the estimate. These five steps are executed in a loop to achieve real-time optimal estimation of dynamic attitude data, which smooths out noise and maintains the speed of tracking.

[0036] Furthermore, in step S4, the fuzzy rule base of the fuzzy neural network control module is pre-established based on the cabin occupant comfort illuminance range, energy-saving optimization target, and the attenuation characteristics of effective illuminance on the ship's motion attitude. The input variables include horizontal illuminance deviation, vertical illuminance deviation, roll angle change rate, and pitch angle change rate.

[0037] In this embodiment, the comfort illuminance range is the recommended horizontal illuminance value of 300-500 lx. The energy-saving optimization goal is to reduce energy consumption as much as possible while meeting the illuminance requirements. The attenuation characteristic means that the larger the roll angle, the more severe the attenuation of the effective illuminance on the horizontal plane, and the greater the compensation output is required.

[0038] Furthermore, in step S7, when the main controller fault monitoring unit detects that the fuzzy neural network control module has failed, it automatically switches to the backup analog lighting control loop, and the output of the illuminance calculation module directly drives the dimmable LED lighting execution module through the analog PID circuit.

[0039] In this embodiment, the failure conditions are output lockout, no response, or exceeding a reasonable range, ensuring that the lighting system can still function normally even if the smart controller fails completely.

[0040] The core of this invention lies in using roll / pitch angles as feedforward control signals to add dynamic correction functions based on ship attitude, thereby enhancing reliability.

[0041] Application Scenario: The research vessel "Exploration" is currently on a mission in the North Pacific. The outdoor weather is severe, with wind and waves causing the ship to roll continuously by ±15° and pitch by ±8°. Inside the cabin, six researchers are conducting sample analysis in the experimental area, while two others are working in shifts in the rest area.

[0042] Data Acquisition: The illuminance sensor measured the current average illuminance in the cabin to be 180 lx (below the comfort threshold). The color temperature sensor measured the current color temperature to be 6500K (cool white light, from the existing lighting). The millimeter-wave radar detected 6 people in the experimental area and 2 people in the rest area. The ship's motion attitude sensor interface acquired the roll angle +12°, pitch angle -5°, and rate of change in real time.

[0043] Data cleaning and estimation: An adaptive weighted fusion algorithm compares data from three illumination sensors and removes an abnormally low value caused by human obstruction. A Kalman filter predicts and smooths the roll angle data, filtering out outliers caused by high-frequency ship vibrations (such as instantaneous ±2° jumps), and outputs a stable roll angle of +11.8° and pitch angle of -4.9°.

[0044] Illuminance Calculation and Dynamic Correction: The three-dimensional spatial mesh divides the cabin into an experimental area (Area A) and a rest area (Area B). Based on the inverse square law of distance and the cosine law, the basic illuminance requirement for the horizontal plane in the experimental area is 400 lx. Due to a 12° roll, the effective illuminance on the horizontal plane decreases by approximately 11%, and the system dynamically corrects the target illuminance to 445 lx. The illuminance on the vertical plane decreases by approximately 4% due to a -5° pitch, and the corrected target is 320 lx. The target illuminance for the rest area is set at 150 lx (night mode).

[0045] Fuzzy Neural Network Control (Real-time Feedforward + Feedback) Input variables: Horizontal illuminance deviation: Experimental area current 180 lx → target 445 lx, deviation -265 lx.

[0046] Vertical plane illuminance deviation: Current 120 lx → Target 320 lx, deviation -200 lx.

[0047] Roll rate of change: +0.5° / s (the ship continues to tilt to port).

[0048] Pitch angle change rate: -0.3° / s.

[0049] Feedforward function: When the system detects an increasing trend in the roll angle, it increases the output in advance to prevent the illuminance from decreasing further.

[0050] Fuzzy inference output: The PWM duty cycle in the experimental area increased from 40% to 82%, while the duty cycle in the rest area remained at 15%.

[0051] Dimmable LED execution: Cool and warm white LED beads are mixed and output at a color temperature of 2700K, and RGB ambient light beads are slightly adjusted to a light amber color to create a comfortable nighttime atmosphere. The illuminance in the experimental area is increased to 438 lx (close to the target of 445 lx), with a color temperature of 2700K, and the visual comfort of people is significantly improved.

[0052] Fault self-diagnosis and redundancy switching: The fault self-diagnosis module monitors the communication and power status of each module in real time. If the system is running normally and there is no switching action, if the fuzzy neural network controller unexpectedly locks up, the main controller fault monitoring unit will detect the abnormality within 2 control cycles (100ms) and automatically switch to the backup analog PID lighting control loop to maintain the illuminance of the experimental area at no less than 300 lx to ensure basic working requirements.

[0053] The application results are summarized in Table 1 below: Table 1 Summary of Application Results This implementation case was simulated using real ship rolling motion data and typical scientific research operation scenarios. All control logic (feedforward compensation, Kalman filtering, fuzzy neural network, human factor rhythm, redundancy switching) has been implemented in the system and tested in practice, verifying its high reliability and intelligence level in complex ship environments.

[0054] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A ship cabin intelligent lighting system, characterized in that, include: The data acquisition module is used to collect ambient brightness data, point light source parameters and illumination intensity information in the ship's cabin in real time. The data acquisition module includes a ship motion attitude sensor interface for receiving ship roll and pitch angle data. The data cleaning and estimation module, connected to the data acquisition module, is used to clean the acquired data using an adaptive weighted fusion algorithm and estimate the true value of the cabin brightness based on the fusion of multiple sensor data. The data cleaning and estimation module is also used to filter the ship's motion attitude data. The illuminance calculation module, connected to the data cleaning and estimation module, is used to calculate the illumination brightness values ​​of the horizontal and vertical surfaces inside the cabin based on the cleaned data and according to the inverse square law of distance and the cosine law. The illuminance calculation module is also used to dynamically correct the effective illuminance of the horizontal and vertical surfaces according to the ship's roll and pitch angles, and use the calculation results as input parameters for subsequent modules. The fuzzy neural network control module has its input layer connected to the illuminance calculation module and the data cleaning and estimation module, respectively. It is used to receive the illumination brightness values ​​of the horizontal and vertical planes, as well as the filtered ship roll and pitch angle data as feedforward control signals. The fuzzy neural network control module outputs specific illumination brightness adjustment values ​​through internal fuzzification processing, fuzzy rule reasoning, and defuzzification operations. A dimmable LED lighting execution module is connected to the fuzzy neural network control module and is used to automatically adjust the lighting brightness of the ship's cabins according to the adjustment value output by the fuzzy neural network control module. The human circadian rhythm coordination module is connected to the fuzzy neural network control module. It is used to obtain current time information and calculate the phase of the human circadian rhythm, generate color temperature adjustment instructions, and then send the color temperature adjustment instructions and the brightness adjustment values ​​output by the fuzzy neural network control module to the dimmable LED lighting execution module. The fault self-diagnosis and redundancy switching module is connected to the data acquisition module, data cleaning and estimation module, illuminance calculation module, fuzzy neural network control module and dimmable LED lighting execution module, respectively. It is used to monitor the operating status of each module in real time and perform backup channel switching when an abnormality is detected.

2. The intelligent lighting system for ship cabins according to claim 1, characterized in that: The data acquisition module also includes an illuminance sensor, a color temperature sensor, a millimeter-wave radar human presence sensor, and a multi-point illuminance detection unit.

3. The intelligent lighting system for ship cabins according to claim 1, characterized in that: The data cleaning and estimation module integrates a Kalman filter, which is used to predict and smooth the ship's roll and pitch angle data in real time, and to remove outlier data caused by the ship's instantaneous turbulence.

4. A shipboard cabin intelligent lighting system according to claim 1, characterized in that: The illuminance calculation module is equipped with a three-dimensional spatial grid division unit, which is used to divide the cabin into multiple lighting control sub-regions, calculate the lighting brightness values ​​of the horizontal and vertical planes of each sub-region, and output the independent adjustment parameters of each sub-region.

5. A shipboard cabin intelligent lighting system according to claim 1, characterized in that: The fault self-diagnosis and redundancy switching module includes a main controller fault monitoring unit, a communication link circuit breaker detection unit, a power supply anomaly monitoring unit, and a backup analog lighting control circuit.

6. A shipboard cabin intelligent lighting system as defined in claim 1, wherein: The dimmable LED lighting execution module includes warm and cool white LED beads and RGB ambient lighting beads.

7. A method of adjusting the brightness of illumination based on the system of any one of claims 1 to 6, characterized in that, Includes the following steps: Step S1: Collect ambient brightness data, point light source parameters, and illumination intensity information in the ship's cabin in real time through the data acquisition module, and connect to the ship's motion attitude sensor to obtain the ship's current roll and pitch angle data; Step S2: The data cleaning and estimation module receives the data collected in step S1, uses an adaptive weighted fusion algorithm to perform consistency verification and outlier removal on the multi-sensor data, and uses the built-in Kalman filter to perform real-time prediction and smoothing filtering on the ship's roll and pitch angle data, removing outlier data caused by the ship's instantaneous turbulence, and simultaneously estimates the true value of cabin brightness based on the fusion of multiple sensor data. Step S3: The illuminance calculation module receives the data processed in step S2, and calculates the basic lighting brightness values ​​of the horizontal and vertical planes inside the cabin according to the inverse square law of distance and the cosine law. Then, based on the filtered ship roll and pitch angle data, it dynamically corrects the effective illuminance of the horizontal and vertical planes. The cabin is divided into multiple lighting control sub-regions through the internal three-dimensional spatial grid division unit, and the lighting brightness value of each sub-region is calculated and the independent adjustment parameters of each sub-region are output. Step S4: The input layer of the fuzzy neural network control module simultaneously receives the horizontal and vertical illumination brightness values ​​output in step S3, as well as the ship's roll angle data, pitch angle data, roll angle change rate, and pitch angle change rate after filtering in step S2, as feedforward control signals; the fuzzy neural network control module sequentially performs fuzzification processing, fuzzy rule reasoning, and defuzzification operations, and outputs specific illumination brightness adjustment values; Step S5: The human-cause circadian rhythm coordination module obtains the current time information, calculates the phase of the human diurnal rhythm, generates a color temperature adjustment command, and merges the color temperature adjustment command with the brightness adjustment value output in step S4. The fusion rule is: the brightness adjustment value prioritizes meeting the target illumination requirements of the cabin, and the color temperature adjustment is independently adjusted according to the current rhythm phase based on the brightness adjustment value. The two are merged into the final light and color parameters through a lookup table mapping. Step S6: The dimmable LED lighting execution module receives the adjustment signal fused in step S5 and automatically adjusts the brightness and color temperature of the warm and cool white LED beads and RGB ambient lighting beads in the ship's cabin to achieve lighting output; Step S7: The fault self-diagnosis and redundancy switching module monitors the operating status of the data acquisition module, data cleaning and estimation module, illuminance calculation module, fuzzy neural network control module, and dimmable LED lighting execution module in real time. When a single module malfunction is detected, the backup channel is automatically switched and the backup analog lighting control loop is enabled. When multiple modules malfunction are detected simultaneously, the degradation strategy is executed according to the preset priority order: the dimmable LED lighting execution module is kept operating with the locally saved default values ​​first, and then the backup analog lighting control loop is enabled.

8. A method of adjusting the brightness of illumination according to claim 7, characterized in that: In step S2, the Kalman filter's processing of the ship's roll and pitch angle data specifically includes: state prediction, covariance prediction, Kalman gain calculation, state update, and covariance update, thereby achieving real-time optimal estimation of dynamic attitude data.

9. The method of claim 7, wherein: In step S4, the fuzzy rule base of the fuzzy neural network control module is pre-established based on the illuminance range of cabin personnel comfort, energy-saving optimization target and the attenuation characteristics of effective illuminance on the ship's motion attitude. The input variables include horizontal illuminance deviation, vertical illuminance deviation, roll angle change rate and pitch angle change rate.

10. The method of claim 7, wherein: In step S7, when the main controller fault monitoring unit detects that the fuzzy neural network control module has failed, it automatically switches to the backup analog lighting control loop, and the output of the illuminance calculation module directly drives the dimmable LED lighting execution module through the analog PID circuit.