Control method of intelligent lighting control equipment

Abstract

The invention provides a control method of intelligent lighting control equipment, and belongs to the technical field of intelligent control, and the equipment for realizing the control method comprises a background monitoring host, a loop controller, an intelligent lamp, an intelligent dual-technology human body sensor, an intelligent illumination sensor and communication equipment. According to the control method, the intelligent control system is arranged in the background monitoring host and runs in the background monitoring host, and algorithm control and data processing of the lighting system are achieved. Through a sensor linkage algorithm, real-time adjustment of lighting parameters is achieved, user experience is improved, potential faults are found in advance, non-planned downtime is shortened, maintenance cost is reduced, lighting strategies are adjusted according to actual requirements, energy consumption cost is reduced, multi-protocol interfaces are supported, integration with systems such as security and protection and production management is facilitated, and application scenes are expanded.

Description

Technical Field

[0001] This invention relates to the field of intelligent lighting control, and more particularly to a control method for an intelligent lighting control device. Specifically, it is a lighting control device based on multi-sensor fusion and intelligent algorithms, suitable for intelligent lighting management in areas such as turbine rooms, boilers, booster stations, electrostatic precipitators, desulfurization facilities, transformer enclosures, and plant roads. Background Technology

[0002] With the popularization of LED lighting technology, the controllability of lamps has been significantly enhanced. However, existing intelligent lighting control equipment has the following problems: 1. Single control method: relying on manual or simple timetable control, unable to dynamically adjust according to environmental changes; 2. Delayed fault response: lacking real-time monitoring and early warning mechanisms, resulting in low efficiency in fault detection and handling; 3. Coarse energy management: failing to achieve refined dimming based on actual needs, resulting in energy waste; 4. Poor system compatibility: difficult to integrate with third-party systems (such as security and production management), limiting intelligent application scenarios.

[0003] Currently, lighting in many factory areas is controlled individually or manually, making it impossible to achieve overall control of the entire factory area. This application, based on the Beihai Power Plant Phase II (2×660MW) expansion project of Guangxi Investment Group Beihai Power Generation Co., Ltd., designs a control method for intelligent lighting control equipment. Summary of the Invention The purpose of this invention is to provide a control method for intelligent lighting control equipment, which solves the technical problems of existing equipment having a single control method, slow fault response, crude energy consumption management, and poor system compatibility.

[0004] To achieve the above objectives, the technical solution adopted by the present invention is as follows: A control method for an intelligent lighting control device, wherein the device implementing the control method includes a background monitoring host, a loop controller, intelligent lamps, an intelligent dual-technology human body sensor and an intelligent illuminance sensor, and a communication device. The background monitoring host is wirelessly and / or wiredly connected to several loop controllers through the communication device. The loop controllers are wirelessly and / or wiredly connected to several intelligent lamps in corresponding areas. The intelligent dual-technology human body sensor and the intelligent illuminance sensor are set in the area where the intelligent lamps are set and are connected to the loop controllers. The background monitoring host is configured in a central control room for centralized control and management. The loop controllers are connected to the intelligent lamps and the background monitoring host to execute control commands. The control method involves setting up an intelligent control system within the background monitoring host, which runs on the background monitoring host to realize algorithmic control and data processing of the lighting system.

[0005] Furthermore, the communication equipment includes a 5G smart edge control box and a fiber optic transceiver, supporting wireless 5G and LoRa converged communication. The communication equipment supports several protocol interfaces, including but not limited to Modbus, BACnet, and OPCUA, enabling seamless integration with third-party systems.

[0006] Furthermore, the intelligent control system embeds an intelligent control algorithm module, which is used to automatically dim the intelligent lights based on the time schedule and sensor linkage, predict and adaptively repair intelligent light faults, and optimize the energy consumption and dynamically save energy of the intelligent lights.

[0007] Furthermore, the intelligent control algorithm module includes a time-based dimming submodule, a sensor linkage submodule, a fault prediction submodule, and an energy consumption optimization submodule. The time-based dimming submodule is used to automatically adjust the brightness of the lamps according to the user's preset time schedule and latitude and longitude calculations. The sensor linkage submodule is used to receive data from human body sensors and illuminance sensors in real time, dynamically adjust lighting parameters, and achieve full power range adjustment from 0 to 100%. The fault prediction submodule is used to predict single lamp / circuit faults by analyzing historical fault data and real-time operating status, and trigger an alarm mechanism. The energy consumption optimization submodule is used to optimize lighting strategies and reduce energy consumption costs based on regional power demand and light intensity.

[0008] Furthermore, the collective process for calculating latitude and longitude is as follows: Obtain the current time, real-time illuminance, and local latitude and longitude. Based on the latitude, longitude, and date, obtain the precise sunrise and sunset times for the day using astronomical algorithms or APIs. Based on the calculated sunrise and sunset times, dynamically divide the time into three key periods: sunrise transition period ([sunrise-30 minutes, sunrise+30 minutes]), daytime core period ([sunrise+30 minutes, sunset-30 minutes]), and sunset transition period ([sunset-30 minutes, sunset+30 minutes]). Brightness decisions are made according to the following priority, from highest to lowest: Priority 1: Light Sensing Priority, i.e., daytime and transition periods. Rule: During the core daytime period and sunrise / sunset transition period, as long as the real-time illuminance is <50 lux, regardless of the schedule setting, the system will force an output of 100% brightness, which is the cloudy / insufficient light mode. Priority 2: Schedule strategy, i.e. nighttime. Rule: During nighttime hours, since natural light is very weak or has disappeared, the system sets the brightness entirely according to the preset schedule strategy, without referring to the light sensor value. Priority 3: Smooth transition, which is a transition period with sufficient light. Rule: During the sunrise / sunset transition period, if the real-time illuminance is ≥50 lux, the system will not trigger light-sensing priority, but will instead perform a linear smooth transition between the two brightness values ​​set in the schedule to avoid sudden changes in light.

[0009] Furthermore, the sensor linkage submodule's sensor linkage control process involves: receiving data from the human body sensor and illuminance sensor in real time, dynamically adjusting lighting parameters, and achieving energy-saving effects by turning on lights when people are present and turning them off when they leave. First, initialization and data acquisition: at the beginning of each control cycle, the system reads the current time, real-time illumination value, radar signal, and calculates sunrise and sunset. The current time is used for subsequent comparison with the schedule strategy. The real-time illumination value is obtained from the light sensor and is used for light priority judgment. The radar signal is used to determine whether there is human activity in the target area. The sunrise and sunset calculation is used by the system to calculate the sunrise and sunset times of the day based on the date and preset geographical location, thereby dynamically defining the start and end points of day and night. Then, a three-level priority judgment is performed. The first priority is the light priority judgment. First, check whether the real-time light value is higher than the preset threshold. If it is higher than the threshold, it means that the ambient light is bright enough. Then, immediately adjust the light to the dimmest or turn it off directly, disable the radar sensor to save energy, and directly end the current control cycle without executing subsequent logic. This level has the highest priority, ensuring that energy is never wasted by turning on the lights when there is sufficient light during the day. The second priority is the human presence detection. This entry condition only occurs when the light priority judgment fails (i.e., insufficient ambient light). This logic activates the radar, which begins monitoring human activity within the area. The radar continuously scans; if a person is detected, the lights immediately turn on and an idle timer is reset to zero. If no person is detected, the system checks if the idle timer has exceeded a preset duration. If not, the lights remain in their current state, and detection continues. If the timer has expired, it's assumed the person has left, and the lights are dimmed or turned off. This achieves the key to high efficiency, energy saving, and improved user experience: lights turn on when someone is present and turn off when they leave. The third priority is the integration of the schedule strategy. This strategy does not run independently, but integrates and modifies the output of the first two logics. It compares the current time with the calculated sunrise and sunset times to distinguish between daytime and nighttime periods. During the daytime, even if the presence of a human body is detected and the lights are turned on, the brightness will be adjusted with reference to the daytime mode brightness configuration. During the nighttime, when the lights are turned on, the brightness configuration of the nighttime mode will be referenced. While meeting the needs of human body sensing, the brightness of the lights is made to better match the natural light intensity and scene requirements of different times, making the lighting strategy more refined and humanized.

[0010] Furthermore, the time-overlay calculation process of the time-adjusting submodule is as follows: It reads and sets system parameters: light threshold (light_threshold), radar timeout (radar_timeout), and day / night brightness configuration; initializes the hardware; starts the light sensor, radar sensor, and light controller; initializes global variables: timer = None, radar_signal = False, last_detection = 0; starts the main control loop; obtains the current system time; reads the current ambient light value (light_value) from the light sensor; reads the current human detection signal from the radar sensor; when radar_signal is True, someone is present; when it is False, no one is present; checks if light_value is greater than the predefined light threshold; if so, the environment is bright enough; calls set_light_state or sets it to the minimum brightness; cancels the existing timer; checks if radar_signal detects a person; if so, calls the reset_timer() function, which cancels the old timer and starts a new timer with a duration of radar_timeout seconds; and records last_detection. =time.time() marks the light status as needing to be turned on, and continues execution. If no one is present, it waits, and the timer continues counting down. Based on the current time, it determines the current time period, i.e., day / night / transition period. Based on the obtained light on / off requirements and time period information, it determines the final brightness. Depending on whether it is day or night, it reads the target brightness when someone is present from the corresponding brightness configuration and calls set_light_state. If no one is present and the timer has not expired, it maintains the current light state, and the brightness is not changed in this loop. If no one is present and the timer expires, it executes the timeout_callback() function to handle the timer start. When the timer expires, this function is automatically called. Inside the function, it checks if not radar_signal: to confirm that no one is present, and then calls set_light_stat to dim or turn off the light.

[0011] Furthermore, the specific process of fault prediction performed by the fault prediction submodule is as follows: Real-time parameter monitoring collects the following seven types of raw data from lighting equipment: online status, whether the equipment can communicate, input and output voltage, current and power, power factor, dimming value, and illuminance value. Data cleaning processes invalid data caused by communication packet loss, outlier filtering removes extreme values ​​from sensor false alarms, and normalization processes standardize parameters such as voltage and current to facilitate comparison. The preprocessed data is analyzed to extract key features for diagnostic purposes: trend analysis (observing current and power trends), harmonic detection (analyzing power factor to assess power quality), waveform analysis (checking for voltage and current waveform distortion), and spatial mapping (correlation between dimming values ​​and actual illuminance values). The diagnostic decision-making process begins, with the diagnostic engine prioritizing judgments from simple to complex and from explicit to implicit: Basic status check: Determines if the device's online status is False. If yes, immediately diagnoses an offline fault (device cannot communicate), and the process ends. If no, the device is online, proceeding to the next diagnostic step. Power supply fault diagnosis: Determines if the input voltage is normal but the output voltage is abnormal. If yes, diagnoses a driver power supply fault (input normal but output abnormal), and the process ends. If no, the power supply output is normal, and proceeding to the next diagnostic step. Aluminum substrate fault diagnosis: Determines if both input and output voltages are normal, but the current parameter is abnormal. If yes, diagnoses an LED aluminum substrate fault (input and output normal but current abnormal), and the process ends. If no... The current is also normal, proceeding to the next diagnostic step: Light source fault diagnosis. Voltage, current, and dimming values ​​are all normal, but is the illuminance value measured by the sensor abnormally low? If so, a light source fault is identified (electrical parameters are normal, but illuminance is abnormal), and the process ends. If not, all basic electrical and optical parameters are normal, and AI model-assisted diagnosis is used. When all previous rules cannot provide a clear diagnosis, the AI ​​model is activated. The pre-processed and feature-extracted complete data is input into the trained AI prediction model. Does the model's predicted value exceed a preset fault threshold? If so, an unknown fault type is identified. The diagnostic clues provided by the model help discover potential, complex, or newly emerging fault modes. If not, the current equipment status is determined to be healthy.

[0012] Furthermore, the specific process of dynamically adjusting the lighting is as follows: The system invokes a sensor network to acquire current environmental data. Input data includes: `sensor_data['natural_light']`, which is the natural light illuminance value measured by the illuminance sensor from the window; `sensor_data['artificial_light']`, which is the illuminance value generated by the current luminaire itself measured by the illuminance sensor, or a value calculated from the current brightness of the luminaire given its known efficiency; `time_of_day`, which is the current time used to calculate the color temperature; and `weather`, which is the current weather condition, such as sunny or rainy, obtained from a weather API. The system then evaluates the current total illuminance using a weighted calculation: `total_illumination = natural_light * 0.7 + artificial_light * 0.3`. The weights simulate the subjective perception of natural and artificial light by the human eye. Adaptive dimming decision: Compare the calculated total illuminance with the target value and make a dimming decision to determine if it is insufficient. If total_illumination < TARGET_ILLUMINANCE, if so, call the function adjust_brightness(up = True, ratio = 1.2). This function sends an instruction to the lighting driver system to increase the brightness to 1.2 times the current level. If not, enter the next judgment to determine if it is too bright. elif total_illumination > TARGET_ILLUMINANCE, if so, call adjust_brightness(up = False, ratio = 0.8) to instruct the lamp to reduce the brightness to 0.8 times the current level. If not, the total illuminance is already within the target range, and the brightness is not adjusted in this loop; Color temperature coordinated adjustment: While adjusting the brightness, synchronously optimize the color of the light to make it more in line with the natural rhythm, and calculate the optimal color temperature. Call optimal_cct = calculate_optimal_cct(time_of_day, weather). The function matches the preset color temperature curve according to time_of_day, uses a high color temperature in the morning to boost spirits and a low color temperature in the evening to promote relaxation, and makes fine adjustments according to weather. Call set_cct(optimal_cct) to send the calculated optimal color temperature value to the intelligent lamp that supports color temperature adjustment.

[0013] Due to the adoption of the above technical solutions, the present invention has the following beneficial effects: Through the sensor linkage algorithm, the present invention realizes real-time adjustment of lighting parameters, improves the user experience, discovers potential faults in advance, reduces unplanned downtime, reduces maintenance costs, adjusts the lighting strategy according to actual needs, reduces energy consumption costs, supports multiple protocol interfaces, facilitates integration with systems such as security and production management, and expands application scenarios. Brief Description of the Drawings

[0014] Figure 1 It is a block diagram of the principle of the water intelligent lighting control device of the present invention. Detailed Embodiments

[0015] To make the purpose, technical solutions and advantages of the present invention clearer and more understandable, the following gives preferred embodiments by referring to the attached drawings and further elaborates on the present invention. However, it should be noted that many details listed in the specification are only for enabling the reader to have a thorough understanding of one or more aspects of the present invention, and these aspects of the present invention can be realized even without these specific details.

[0016] Such as Figure 1As shown, a control method for an intelligent lighting control device is disclosed. The device implementing the control method includes a background monitoring host, a loop controller, intelligent lamps, an intelligent dual-technology human body sensor and an intelligent illuminance sensor, and a communication device. The background monitoring host is wirelessly and / or wiredly connected to several loop controllers via the communication device. The loop controllers are wirelessly and / or wiredly connected to several intelligent lamps in corresponding areas. The intelligent dual-technology human body sensor and the intelligent illuminance sensor are set in the area where the intelligent lamps are set and are connected to the loop controllers. The background monitoring host is configured in the central control room for centralized control and management. The loop controllers are connected to the intelligent lamps and the background monitoring host to execute control commands.

[0017] Background monitoring host: Configured in the central control room, running intelligent control system software, supporting remote / centralized control; Intelligent control system software: Embedded with intelligent control algorithm module to realize data acquisition, processing and command issuance; Loop controller: Connects smart lighting fixtures to the back-end monitoring host and executes dimming and switching commands; Smart lighting fixtures: support dimming and color changing functions, and are distributed in various lighting areas; Sensor group: including intelligent dual-technology human body sensor (detects human movement and light intensity) and intelligent illuminance sensor (detects ambient light); Communication equipment: 5G smart edge control box, fiber optic transceiver, supporting wireless 5G and LoRa converged communication.

[0018] Intelligent control algorithm module: Schedule-based dimming algorithm: Based on the user's preset schedule and latitude and longitude, it automatically adjusts the brightness of the lamps to adapt to the light needs at different times of the day; Key points of core algorithm implementation Latitude and longitude time calculation: Use the datetime module to calculate local sunrise and sunset times (example uses Beijing time 6:00-18:00). In practical projects, precise time can be obtained by connecting to astronomical APIs (such as Sunrise-Sunset.org). Triple priority control logic Table 1 shows examples of timetable strategies. Dynamic adjustment of light sensing threshold Rainy / overcast day detection: Automatically turn on lights when daytime illuminance is <50 lux. Sunrise / Sunset Transition: A 30-minute buffer period enables a smooth brightness transition. Table 2 shows the verification test results. Sensor linkage algorithm: Receives data from human body sensor and illuminance sensor in real time, dynamically adjusts lighting parameters, and achieves energy-saving effect of lights turning on when people are present and turning off when people leave. Intelligent lighting system control logic architecture Key points of core algorithm implementation 1. Triple priority control logic 2. Implementation of the time superposition algorithm 3. Microwave Radar Technical Parameters Operating frequency: 5.8GHz (strong penetration, suitable for 10-12 meter detection) Sensitivity: 0.6mW power consumption, capable of detecting minute respiratory movements in a stationary human body. Anti-interference: Employs FMCW (Frequency Modulated Continuous Wave) technology to resist multipath reflection. Interface: Supports UART / I²C protocol for direct communication with the MCU. Table 3 shows the test results for microwave radar technology verification. Fault prediction algorithm: By analyzing historical fault data and real-time operating status, it predicts single lamp / circuit faults and triggers an alarm mechanism; Key technological innovations 1. Six-dimensional parameter fusion diagnosis: Online status + Input voltage → Offline fault Input voltage + Output voltage → Drive power supply failure Input / output voltage + current → Aluminum substrate failure Electrical parameters + illuminance → Light source failure Power factor + harmonic analysis → Power quality fault Table 4 shows the typical fault scenario handling process. Energy consumption optimization algorithm: Optimize lighting strategies based on regional electricity demand and light intensity to reduce energy costs.

[0019] Central monitoring and independent zone operation: Stopping the central monitoring does not affect the operation of zone equipment; Multi-protocol interface: Supports protocols such as Modbus, BACnet, and OPC UA, enabling seamless integration with third-party systems; Manual bypass function: In case of system failure, it can be manually controlled locally to ensure basic lighting needs.

[0020] Dynamic dimming: Real-time adjustment of lighting parameters through sensor-linked algorithms enhances user experience; Fault prediction: Early detection of potential faults reduces unplanned downtime and lowers maintenance costs; Energy optimization: Adjustment of lighting strategies based on actual needs reduces energy consumption costs; System compatibility: Support for multiple protocol interfaces facilitates integration with security, production management, and other systems, expanding application scenarios.

[0021] Example 1: Lighting Control in Turbine Room Area System deployment: Install smart lights, circuit controllers, human body sensors and illuminance sensors in the turbine room area; realize communication between sensor data and the background monitoring host through fiber optic transceivers and 5G smart edge control boxes.

[0022] Algorithm configuration: Configure a timetable dimming algorithm to set the lighting schedule for weekdays and holidays; configure a sensor linkage algorithm to set a human body detection trigger threshold (e.g., activate human body detection when the light intensity is <50 lux); configure a fault prediction algorithm to set a fault warning threshold (e.g., detect abnormal lamp current 3 times consecutively).

[0023] Operational results: The system automatically adjusts the brightness of the lights according to the schedule, reducing the power to 30% during the day and restoring it to 100% at night; when human movement is detected, the brightness of the lights in the local area is increased to 100%, and then restored to 30% within 30 seconds after the person leaves; when a light malfunction is predicted, the system automatically triggers an alarm mechanism to notify maintenance personnel for handling.

[0024] Example 2: Factory Area Road Lighting Control System deployment: Install smart streetlights, single-lamp controllers, and illuminance sensors on factory roads; use LoRa wireless communication modules to enable communication between sensor data and the back-end monitoring host.

[0025] Algorithm configuration: Configure a time-based dimming algorithm to automatically turn lights on and off at sunrise / sunset times; configure a sensor-linked algorithm to set illuminance trigger thresholds (e.g., start streetlights when ambient light is <20 lux); configure an energy consumption optimization algorithm to dynamically adjust streetlight brightness based on traffic flow data.

[0026] Operational results: The system automatically switches the lights on and off according to sunrise / sunset times to avoid human error; when insufficient ambient light is detected, the streetlights are automatically turned on and adjusted to 50% brightness; based on traffic flow data, the streetlight brightness is reduced to 30% during low-traffic periods at night and restored to 100% during high-traffic periods.

[0027] By integrating multi-sensor data and intelligent algorithms, dynamic dimming, fault prediction, energy consumption optimization, and system linkage of lighting systems are achieved. The equipment includes a back-end monitoring host, intelligent control system software, loop controllers, intelligent luminaires, sensor groups, and communication equipment; the algorithm module is embedded in the software, supporting time-based dimming, sensor linkage, fault prediction, and energy consumption optimization. This invention solves the problems of existing equipment's single control method, delayed fault response, crude energy management, and poor system compatibility, and is suitable for intelligent lighting management in areas such as turbine rooms, boiler rooms, and factory roads.

[0028] Matters not covered in this invention are common knowledge.

[0029] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A control method for an intelligent lighting control device, characterized in that: The device for implementing the control method includes a background monitoring host, a loop controller, smart lamps, a smart dual-technology human body sensor and a smart illuminance sensor, and a communication device. The background monitoring host is wirelessly and / or wiredly connected to several loop controllers through the communication device. The loop controllers are wirelessly and / or wiredly connected to several smart lamps in corresponding areas. The smart dual-technology human body sensor and the smart illuminance sensor are set in the area where the smart lamps are set and are connected to the loop controllers. The background monitoring host is configured in the central control room for centralized control and management. The loop controllers are connected to the smart lamps and the background monitoring host to execute control commands. The control method involves setting up an intelligent control system within the background monitoring host, which runs on the background monitoring host to realize algorithmic control and data processing of the lighting system.

2. The intelligent lighting control device according to claim 1, characterized in that: The communication equipment includes a 5G smart edge control box and a fiber optic transceiver, supporting wireless 5G and LoRa converged communication. The communication equipment supports several protocol interfaces, including but not limited to Modbus, BACnet, and OPCUA, enabling seamless integration with third-party systems.

3. The intelligent lighting control device according to claim 2, characterized in that: The intelligent control system embeds an intelligent control algorithm module, which is used to automatically dim the intelligent lights based on the time schedule and sensor linkage, predict and adaptively repair intelligent light faults, and optimize the energy consumption and dynamically save energy of the intelligent lights.

4. The intelligent lighting control device according to claim 3, characterized in that: The intelligent control algorithm module includes a time-based dimming submodule, a sensor linkage submodule, a fault prediction submodule, and an energy consumption optimization submodule. The time-based dimming submodule automatically adjusts the brightness of the lamps according to the user's preset time schedule and latitude and longitude calculations. The sensor linkage submodule receives data from human body sensors and illuminance sensors in real time and dynamically adjusts lighting parameters to achieve full power range adjustment from 0 to 100%. The fault prediction submodule predicts single lamp / circuit faults by analyzing historical fault data and real-time operating status and triggers an alarm mechanism. The energy consumption optimization submodule optimizes lighting strategies and reduces energy costs based on regional power demand and light intensity.

5. The intelligent lighting control device according to claim 3, characterized in that: The overall process for calculating latitude and longitude is as follows: Obtain the current time, real-time illuminance, and local latitude and longitude. Based on the latitude, longitude, and date, obtain the precise sunrise and sunset times for the day using astronomical algorithms or APIs. Based on the calculated sunrise and sunset times, dynamically divide the time into three key periods: sunrise transition period ([sunrise-30 minutes, sunrise+30 minutes]), daytime core period ([sunrise+30 minutes, sunset-30 minutes]), and sunset transition period ([sunset-30 minutes, sunset+30 minutes]). Brightness decisions are made according to the following priority, from highest to lowest: Priority 1: Light Sensing Priority, i.e., daytime and transition periods. Rule: During the core daytime period and sunrise / sunset transition period, as long as the real-time illuminance is <50 lux, regardless of the schedule setting, the system will force an output of 100% brightness, which is the cloudy / insufficient light mode. Priority 2: Schedule strategy, i.e. nighttime. Rule: During nighttime hours, since natural light is very weak or absent, the system sets the brightness entirely based on the preset schedule strategy, without referring to the light sensor value. Priority 3: Smooth transition, which is a transition period with sufficient light. Rule: During the sunrise / sunset transition period, if the real-time illuminance is ≥50 lux, the system will not trigger light priority, but will instead perform a linear smooth transition between the two brightness values ​​set in the schedule to avoid sudden changes in light.

6. The intelligent lighting control device according to claim 4, characterized in that: The sensor linkage submodule's sensor linkage control process involves: receiving data from the human body sensor and illuminance sensor in real time, dynamically adjusting lighting parameters to achieve energy-saving effects such as lights turning on when people are present and turning off when they leave. First, initialization and data acquisition: at the beginning of each control cycle, the system reads the current time, real-time illumination value, radar signal, and calculates sunrise and sunset. The current time is used for subsequent comparison with the schedule strategy. The real-time illumination value is obtained from the light sensor and is used for light priority judgment. The radar signal is used to determine whether there is human activity in the target area. The sunrise and sunset calculation is used by the system to calculate the sunrise and sunset times of the day based on the date and preset geographical location, thereby dynamically defining the start and end points of day and night. Then, a three-level priority judgment is performed. The first priority is the light priority judgment. First, check whether the real-time light value is higher than the preset threshold. If it is higher than the threshold, it means that the ambient light is bright enough. Then, immediately adjust the light to the dimmest or turn it off directly, disable the radar sensor to save energy, and directly end the current control cycle without executing subsequent logic. This level has the highest priority, ensuring that energy is never wasted by turning on the lights when there is sufficient light during the day. The second priority is the human presence detection. This entry condition only occurs when the light priority judgment fails (i.e., insufficient ambient light). This logic activates the radar, which begins monitoring human activity within the area. The radar continuously scans; if a person is detected, the lights immediately turn on and an idle timer is reset to zero. If no person is detected, the system checks if the idle timer has exceeded a preset duration. If not, the lights remain in their current state, and detection continues. If the timer has expired, it's assumed the person has left, and the lights are dimmed or turned off. This achieves the key to high efficiency, energy saving, and improved user experience: lights turn on when someone is present and turn off when they leave. The third priority is the integration of the schedule strategy. This strategy does not run independently, but integrates and modifies the output of the first two logics. It compares the current time with the calculated sunrise and sunset times to distinguish between daytime and nighttime periods. During the daytime, even if the presence of a human body is detected and the lights are turned on, the brightness will be adjusted with reference to the daytime mode brightness configuration. During the nighttime, when the lights are turned on, the brightness configuration of the nighttime mode will be referenced. While meeting the needs of human body sensing, the brightness of the lights is made to better match the natural light intensity and scene requirements of different times, making the lighting strategy more refined and humanized.

7. The intelligent lighting control device according to claim 4, characterized in that: The time-overlay calculation process of the time-adjusting module is as follows: It reads and sets system parameters: light threshold (light_threshold), radar timeout (radar_timeout), and day / night brightness configuration; initializes the hardware; starts the light sensor, radar sensor, and light controller; initializes global variables: timer = None, radar_signal = False, last_detection = 0; starts the main control loop; obtains the current system time; reads the current ambient light value (light_value) from the light sensor; reads the current human detection signal from the radar sensor (radar_signal is True if someone is present, False if no one is present); checks if light_value is greater than the predefined light threshold; if so, the environment is bright enough; calls set_light_state or sets it to the minimum brightness; cancels the existing timer; checks if radar_signal detects a person; if so, calls the reset_timer() function, which cancels the old timer and starts a new timer with a duration of radar_timeout seconds; and records last_detection = ... `time.time()` marks the light status as needing to be turned on and continues execution. If no one is present, it waits while the timer continues counting down. Based on the current time, it determines the current time period (day / night / transition period). Based on the obtained light on / off requirements and time period information, it determines the final brightness. Depending on whether it is day or night, it reads the target brightness for when someone is present from the corresponding brightness configuration and calls `set_light_state`. If no one is present and the timer has not expired, it maintains the current light state and does not change the brightness in this loop. If no one is present and the timer has expired, it executes the `timeout_callback()` function to handle the timer start. When the timer expires, this function is automatically called. Inside the function, it checks `if not radar_signal:` to confirm that no one is present, and then calls `set_light_stat` to dim or turn off the light.

8. The intelligent lighting control device according to claim 4, characterized in that: The specific process of fault prediction by the fault prediction submodule is as follows: Real-time parameter monitoring collects the following seven types of raw data from lighting equipment: online status, whether the equipment can communicate, input and output voltage, current and power, power factor, dimming value, and illuminance value. Data cleaning processes invalid data caused by communication packet loss, outlier filtering removes extreme values ​​from sensor false alarms, and normalization processes standardize parameters such as voltage and current to facilitate comparison. The preprocessed data is analyzed to extract key features for diagnostic purposes: trend analysis (observing current and power trends), harmonic detection (analyzing power factor to assess power quality), waveform analysis (checking for voltage and current waveform distortion), and spatial mapping (correlation between dimming values ​​and actual illuminance values). The diagnostic decision-making process begins, with the diagnostic engine prioritizing judgments from simple to complex and from explicit to implicit: Basic status check: Determines if the device's online status is False. If yes, immediately diagnoses an offline fault (device cannot communicate), and the process ends. If no, the device is online, proceeding to the next diagnostic step. Power supply fault diagnosis: Determines if the input voltage is normal but the output voltage is abnormal. If yes, diagnoses a driver power supply fault (input normal but output abnormal), and the process ends. If no, the power supply output is normal, proceeding to the next diagnostic step. Aluminum substrate fault diagnosis: Determines if both input and output voltages are normal, but the current parameter is abnormal. If yes, diagnoses an LED aluminum substrate fault. If input and output are normal but current is abnormal, the process ends. If not, and current is also normal, proceed to the next diagnostic step: Light source fault diagnosis. Voltage, current, and dimming values ​​are all normal, but is the illuminance value measured by the sensor abnormally low? If so, a light source fault is identified (electrical parameters are normal, but illuminance is abnormal), and the process ends. If not, and all basic electrical and optical parameters are normal, AI model-assisted diagnosis is used. When all previous rules cannot clearly determine the fault, the AI ​​model is activated. The pre-processed and feature-extracted complete data is input into the trained AI prediction model. Does the model's predicted value exceed a preset fault threshold? If so, an unknown fault type is identified. The diagnostic clues provided by the model help discover potential, complex, or newly emerging fault modes. If not, the current equipment status is determined to be healthy.

9. The control method for an intelligent lighting control device according to claim 4, characterized in that: The specific process of dynamically adjusting the lighting is as follows: The system invokes a sensor network to acquire current environmental data. Input data includes: `sensor_data['natural_light']`, which is the natural light illuminance value measured by the illuminance sensor from the window; `sensor_data['artificial_light']`, which is the illuminance value generated by the current luminaire itself measured by the illuminance sensor, or a value calculated from the current brightness of the luminaire given its known efficiency; `time_of_day`, which is the current time used to calculate the color temperature; and `weather`, which is the current weather condition, such as sunny or rainy, obtained from a weather API. The system then evaluates the current total illuminance using a weighted calculation: `total_illumination = natural_light * 0.7 + artificial_light * 0.3`. The weights simulate the subjective perception of natural and artificial light by the human eye. The adaptive dimming decision compares the calculated total illuminance with the target value and makes a dimming decision, determining whether it is insufficient: if total_illumination < TARGET_ILLUMINANCE, if so, the function adjust_brightness(up=True, ratio=1.2) is called. This function sends an instruction to the luminaire driver system to increase the brightness to 1.2 times the current level. If not, proceed to the next judgment to determine whether it is too bright: elif total_illumination > TARGET_ILLUMINANCE. If so, adjust_brightness(up=False, ratio=0.8) is called, instructing the luminaire to reduce the brightness to 0.8 times the current level. If not, the total illuminance is already within the target range, and the brightness is not adjusted in this loop. Color temperature adjustment works by simultaneously optimizing the color of the light while adjusting the brightness, making it more in line with natural rhythms. The optimal color temperature is calculated by calling `optimal_cct = calculate_optimal_cct(time_of_day, weather)`. The function matches the preset color temperature curve based on `time_of_day`, using a high color temperature in the morning to invigorate the spirit and a low color temperature in the evening to promote relaxation. Fine-tuning is performed based on `weather`. The function then calls `set_cct(optimal_cct)` to send the calculated optimal color temperature value to smart lights that support color temperature adjustment.

Images