An AI-based lighting control method

Abstract

This invention relates to the field of intelligent lighting control technology and discloses a lighting control method based on artificial intelligence. A predefined driving current is applied to the warm white and cool white channels of a dual-color LED, and the color temperature is measured to establish an accurate linear mapping. The start and end times of sunshine, upper and lower limits of color temperature, sampling interval, moving average window, and total driving current are reasonably set and verified. A sampling time sequence is generated during the effective sunshine period, and a dynamic color temperature target is calculated according to the diurnal rhythm. A mixing function is defined based on the color temperature-current model and the target curve. The current distribution ratio is accurately solved using mathematical methods, and the current is smoothed using a moving average. A final current command is output at each sampling time, and the system automatically shuts off power at the end of the day and restarts the next day.

Description

Technical Field

[0001] This invention relates to the field of intelligent lighting control technology, specifically to a lighting control method based on artificial intelligence. Background Technology

[0002] In modern buildings and interior environments, lighting systems not only fulfill basic illumination functions but also increasingly require consideration of energy conservation, efficiency, and human health. Traditional lighting control relies primarily on fixed-time switching or manual adjustment, with color temperature and brightness parameters often set based on experience, lacking intelligent responses to circadian rhythms and individual needs. When preset time periods become disconnected from actual usage scenarios, it often leads to a mismatch between the lighting environment and human physiological rhythms, affecting comfort and work efficiency. Furthermore, using a single color temperature or single-channel control makes it difficult to achieve more natural and healthier spectral adjustment.

[0003] In existing technologies, many smart lighting solutions employ predefined schedules or simple ambient light sensors for automatic switching, such as automatically switching to high-brightness mode during commuting hours and switching to low-brightness lighting during idle periods. While these methods save energy to some extent, they lack fine-grained control over dynamic color temperature changes and cannot adjust in real time to match the human body's circadian rhythm. Some systems simply drive warm white and cool white lamps in parallel, changing the color temperature through a fixed ratio or manual switching, but without precise calibration and mathematical modeling for different channels, resulting in significant deviations between the color temperature output and expectations. In the field of dual-color LED mixing, the industry commonly uses empirical formulas or fixed dimming tables in vehicle DALI protocols for color temperature allocation. These solutions struggle to ensure smooth and synchronized changes in color temperature and brightness in complex scenarios and cannot be optimized online based on real-time environments or user needs. Furthermore, most existing color temperature calibrations only perform linear fitting for a single channel, ignoring the potential non-ideal characteristics between LED drive current and color temperature. Improving color temperature accuracy requires multi-point measurements and piecewise fitting, which increases cost and engineering workload in practical deployments. In recent years, "human-centric lighting" technology has received widespread attention, utilizing circadian rhythm sine curves to simulate the time-varying color temperature of natural light and its application in smart homes and commercial lighting. However, most commercial systems rely on preset curves and remote app control, lacking autonomous calculation and real-time adjustment capabilities. They still require manual design of time periods and spectral mappings, lacking intelligent responses to specific environmental changes. Furthermore, these systems begin closed-loop control upon startup, resulting in high operational complexity and stringent hardware performance requirements, making them unsuitable for resource-constrained embedded platforms. Regarding filtering and smoothing, existing control systems typically employ simple low-pass filters or fixed-parameter PID algorithms for brightness adjustment to reduce flicker and abrupt changes. However, because model parameters are often empirical values ​​and insufficient sample size is not adequately considered during system startup and at the end-point boundaries, sluggish filtering response or initial flicker often occurs, impacting user experience. Simultaneously, the output after multi-channel mixing often ignores the effectiveness of real-time judgment results. If a calculation anomaly occurs, the system requires manual intervention or directly reuses the previous state, failing to adaptively degrade to a usable state.

[0004] Therefore, this case aims to propose an artificial intelligence-based lighting control method. Through a series of intelligent algorithms such as system modeling, parameter verification, target color temperature generation, proportional allocation, and dynamic output, the lighting equipment can automatically adjust the output color temperature according to the circadian rhythm, environment, and usage needs, thereby improving the intelligence level of lighting and human comfort. Summary of the Invention

[0005] This invention provides an artificial intelligence-based lighting control method, which helps to solve the problems mentioned in the background art.

[0006] This invention provides the following technical solution: a lighting control method based on artificial intelligence, comprising:

[0007] S1. Apply a predefined driving current to the warm white channel and cool white channel of the dual-color LED respectively, and establish a linear calibration model between the color temperature of each channel and the driving current based on the measured output color temperature.

[0008] S2. Define and verify system parameters, including the start time of sunshine, the end time of sunshine, the upper and lower limits of the target color temperature, the sampling time interval, the length of the moving average filter window, and the total drive current of the dual-color channels. Also, verify the rationality of the effective sunshine duration and determine the number of sampling times.

[0009] S3. Generate a sampling time sequence based on the effective sunshine duration and sampling interval;

[0010] S4. Based on the sampling time, according to the preset day-night variation pattern, calculate the target color temperature curve for each time moment to obtain the dynamic color temperature target sequence of the lighting output throughout the entire cycle.

[0011] S5. Based on the color temperature-current model of the dual-color channel and the target color temperature curve, define the mixing function and solve the distribution ratio of the current of the dual-color channel through mathematical methods.

[0012] S6. Allocate the obtained current values ​​for each channel and smooth the current data using a moving average method.

[0013] S7. At each sampling moment, output the final determined warm white and cool white channel drive current values ​​to the lighting driver;

[0014] S8. Automatically cut off the lighting power supply after the end of the daily lighting cycle, and restart it the next day according to the established procedure.

[0015] Optionally, the step of applying a predefined driving current to the warm white channel and cool white channel of the dual-color LED, and establishing a linear calibration model between the color temperature of each channel and the driving current based on the measured output color temperature, specifically includes:

[0016] Two different sets of driving currents were applied to the warm white LED channel and the cool white LED channel, respectively:

[0017] Warm white channel current: I w1 I w2 Corresponding color temperature for measurement: T w1 T w2 Among them, I w1 I is the first calibration point drive current for the warm white channel; w2 The second calibration point drive current for the warm white channel; T w1 For the warm white channel at current I w1 The color temperature measured below; Tw2 For the warm white channel at current I w2 The color temperature measured below;

[0018] Cold white channel current: I c1 I c2 Corresponding color temperature for measurement: T c1 T c2 Among them, I c1 I is the first calibration point drive current for the cold white channel; c2 T is the second calibration point drive current for the cold white channel; c1 For the cold white channel at current I c1 The color temperature measured below; T c2 For the cold white channel at current I c2 The color temperature measured below;

[0019] Calculate the current gain α caused by the color temperature change in the warm white channel. w Linear bias term b of warm white channel color temperature and current w : Calculate the color temperature change corresponding to a unit current change in the warm white channel, reflecting the sensitivity of the driving current adjustment to color temperature; b w =T w1 -α w I w1 ;

[0020] Calculate the current gain α caused by the color temperature change in the cool white channel. c The linear bias term b between the color temperature and current of the cool white channel c : b c =T c1 -α c I c1 ;

[0021] Construct arbitrary warm white channel current I respectively w The output color temperature function T w (I w ) and arbitrary cold white channel current I c The output color temperature function T c (I c ):

[0022] T w (I w )=α w I w +b w T c (i c )=α c I c +b c .

[0023] Optionally, the definition and verification of system parameters, the rationality check of the effective sunshine duration, and the determination of the number of sampling times specifically include:

[0024] Preset by the designer: the start time of sunlight t rise The time when sunlight ends (t) set Target color temperature lower limit T min Target color temperature upper limit T max The sampling time interval Δt, the moving average filter window length M, and the total drive current I fixedly allocated to the two-color channels. tot ;

[0025] Calculate the effective duration of sunshine D = t set -t rise If D≤0, an invalid sunshine duration will be displayed; please reset it.

[0026] Calculate the number of sampling times within a day

[0027] Optionally, generating a sampling time sequence based on the effective sunshine duration and sampling interval specifically includes:

[0028] For each sampling point n = {0, 1, ..., N-1}, calculate t[n] = t rise +nΔt; where n is the sampling sequence number; t[n] is the nth sampling time;

[0029] If t[N-1]>t set Then let t[N-1] = t set .

[0030] Optionally, the step of calculating the target color temperature curve for each moment based on the sampling time and according to a preset day-night variation pattern to obtain the dynamic color temperature target sequence of the lighting output throughout the entire cycle specifically includes:

[0031] Calculate the normalized day / night phase at time n.

[0032] Obtain the target output color temperature T at time n. tgt [n]:

[0033] T tgt [n] = T min +(T max -T min )sin(φ[n]).

[0034] Optionally, the step of defining a mixing function based on the color temperature-current model of the dual-color channels and the target color temperature curve, and solving the current distribution ratio of the dual-color channels using mathematical methods, specifically includes:

[0035] Let the proportion of the warm white channel current be r, then the warm white channel current I w =r·I tot Cold white channel current I c =(1-r)·I tot ;

[0036] Constructing the color temperature function for light mixing: Among them, T mix (r) represents the mixed warm and cool color temperature output.

[0037] Expand and organize Ar 2 +Br+C=0; where A=I tot (α w +α c ) represents the coefficient of the quadratic term; B = b w -b c -2α c I tot The coefficient of the linear term; C = α c I tot +b c -T tgt [n] is a constant term;

[0038] Obtain the discriminant Δ = B 2 -4AC;

[0039] If Δ≥0, we get Where r1 and r2 are the two roots of the quadratic equation, representing the possible solutions for the current ratio of the warm white channel;

[0040] Select the first root that satisfies 0≤r≤1 in turn. If both roots exist, then take r1.

[0041] If Δ < 0 or neither root is in [0,1], it degenerates into a linear approximation:

[0042] in, Color temperature under full current only for the warm white channel; r[n] represents the color temperature of the cool white channel under full current only; r[n] represents the current ratio of the warm white channel at the nth sampling point.

[0043] like Let r[n] = 0.5;

[0044] Boundary cutoff:

[0045] Optionally, the process of allocating the obtained current values ​​for each channel and smoothing the current data using a moving average method specifically includes:

[0046] Original current distribution: I w [n]=r[n]Itot I c [n]=(1-r[n])I tot Among them, I w [n] represents the warm white channel current at time n; I c [n] represents the cold white channel current at time n;

[0047] Obtain the number of valid samples K participating in the averaging at time n. n =min(M,n+1);

[0048] Calculate the smoothed current of the warm white channel at time n.

[0049] Calculate the smoothed current of the cold white channel at time n.

[0050] Optionally, at each sampling time, outputting the finally determined warm white and cool white channel drive current values ​​to the lighting driver specifically includes:

[0051] Write at each sampling time t[n] To the LED driver;

[0052] If the write operation fails, log the error and retain the previous valid value.

[0053] Optionally, the automatic disconnection of the lighting power supply at the end of the daily lighting cycle and the restarting according to a predetermined procedure the following day specifically includes:

[0054] If the last sampling point t[N-1]≥t set If , then writing (0,0) will turn off the power to the lamp;

[0055] The system enters low-power sleep mode until the next day. rise Automatically return to step S3 and start again.

[0056] The present invention has the following beneficial effects:

[0057] 1. A precise linear model between the driving current and output color temperature was systematically established for each channel of a dual-color LED. By applying different currents to the warm white and cool white channels and measuring the output color temperature, the physical parameters were accurately quantified. Unlike traditional lighting control methods that often rely on empirical values ​​or simple lookup tables, this method provides a highly reproducible mathematical foundation for subsequent light mixing algorithms. This improves the predictability and accuracy of lighting color temperature adjustment, avoiding problems such as color temperature drift and output instability. It also solves the problem of inaccurate adjustment caused by LED batch differences and temperature drift, laying a solid foundation for system adaptability and large-scale deployment.

[0058] 2. By integrating the definition, boundary verification, and anomaly warning of system parameters into the overall algorithm process, the parameter compliance and operational safety of the lighting control system are ensured. Compared with the traditional approach of manual parameter adjustment by maintenance or design personnel and the lack of automatic verification mechanisms, this invention improves the system's intelligent self-checking capabilities and configuration fault tolerance by automatically calculating the effective sunshine duration and the number of sampling points, and providing real-time feedback on parameter setting anomalies (such as time overlap or unreasonable ranges). This ensures the logical validity and boundary compliance of all subsequent adjustment and output processes, effectively preventing potential hazards such as lighting anomalies, excessive energy consumption, or decreased comfort caused by parameter errors.

[0059] 3. An automated sampling time sequence generation mechanism is introduced, ensuring that each sampling point for lighting adjustment is precisely aligned with the actual solar eclipse rhythm. Unlike existing lighting systems that adjust only at a few fixed time points or manually configure sampling points, this solution automatically allocates sampling time points throughout the day based on preset parameters and automatically corrects boundary points (such as the end of the day), effectively avoiding abrupt color temperature transitions and erroneous adjustments during invalid time periods. This improves the continuity of lighting adjustment and user experience, enabling the lighting system to seamlessly integrate with the human biological clock and natural light cycles, resulting in a more comfortable and healthy light environment.

[0060] 4. Based on the day-night cycle and target color temperature range, the target color temperature curve for each sampling moment is dynamically generated, enabling the lighting system to continuously change over time. Unlike traditional solutions that only support segmented color temperature settings or simple day-night switching, this method, based on scientific human-centered lighting theory, accurately calculates the optimal color temperature for every moment of the day, improving human comfort and circadian rhythm synchronization. It not only meets the needs of natural light simulation and energy saving in different application scenarios, but also automatically optimizes lighting output based on the human body's biological response to the light environment, enhancing the health and intelligence of the lighting system.

[0061] 5. By utilizing the physical modeling of dual-color LED channels, the driving current distribution ratio of the two channels can be accurately deduced at any target color temperature, and the algorithm can adapt to extreme or abnormal scenarios for fault tolerance. Unlike traditional dimming methods that use simple table lookups or manual interpolation, this method ensures that the output color temperature falls precisely within the target range at every moment through rigorous mathematical modeling and root discrimination filtering. This improves the accuracy, response speed, and physical consistency of color temperature adjustment, avoids common phenomena such as channel drive mismatch, brightness loss, and color temperature drift, and enhances the scalability and adaptability of the lighting system in multiple scenarios.

[0062] 6. By introducing a moving average algorithm into the dual-color channel current distribution, a smooth transition of lighting color temperature output is innovatively achieved. Compared with previous lighting control systems that are prone to flickering and abrupt changes during channel switching or rapid response, this method effectively eliminates jitter and noise during adjustment through smoothing processing, improving visual comfort and lighting quality. It reduces the negative impact of current abrupt changes on LED lifespan and user experience, making the lighting system more suitable for demanding environments (such as medical, educational, and office settings), while also facilitating subsequent expansion into more complex dynamic lighting scenarios.

[0063] 7. Through automated communication with the driver, the calculated smoothed current value is periodically output to the actual hardware, with a closed-loop mechanism for automatically recording and handling output anomalies. Unlike traditional solutions where output failure can easily lead to a system-wide blackout or unresponsiveness, this method automatically retains the previous valid value and logs it when hardware communication fails, effectively improving system robustness and reliability. It reduces the risk of service interruption due to single points of failure, ensuring long-term, stable, and high-quality system operation, and facilitating later maintenance and fault tracing.

[0064] 8. This invention achieves automatic closed-loop and energy-saving management of the lighting system. Unlike existing solutions that require manual power-off or separate timer operation, this invention automatically shuts off power and enters low-power sleep mode after the daily lighting tasks are completed, then automatically restarts the next day, all without manual intervention. This reduces system energy consumption and maintenance costs, improves equipment lifespan and operational safety, and is particularly suitable for locations requiring long-term continuous operation and high energy efficiency. Attached Figure Description

[0065] Figure 1 This is a schematic diagram of the process of the present invention. Detailed Implementation

[0066] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0067] An example of an artificial intelligence-based lighting control method includes:

[0068] S1. Apply a predefined driving current to the warm white channel and cool white channel of the dual-color LED respectively, and establish a linear calibration model between the color temperature of each channel and the driving current based on the measured output color temperature.

[0069] S2. Define and verify system parameters, including the start time of sunshine, the end time of sunshine, the upper and lower limits of the target color temperature, the sampling time interval, the length of the moving average filter window, and the total drive current of the dual-color channels. Also, verify the rationality of the effective sunshine duration and determine the number of sampling times.

[0070] S3. Generate a sampling time sequence based on the effective sunshine duration and sampling interval;

[0071] S4. Based on the sampling time, according to the preset day-night variation pattern, calculate the target color temperature curve for each time moment to obtain the dynamic color temperature target sequence of the lighting output throughout the entire cycle.

[0072] S5. Based on the color temperature-current model of the dual-color channel and the target color temperature curve, define the mixing function and solve the distribution ratio of the current of the dual-color channel through mathematical methods.

[0073] S6. Allocate the obtained current values ​​for each channel and smooth the current data using a moving average method.

[0074] S7. At each sampling moment, output the final determined warm white and cool white channel drive current values ​​to the lighting driver;

[0075] S8. Automatically cut off the lighting power supply after the end of the daily lighting cycle, and restart it the next day according to the established procedure.

[0076] First, by applying predefined driving currents to the warm white and cool white channels of a dual-color LED and measuring the output color temperature, an accurate color temperature-current model is established, solving the problem of inaccurate color temperature adjustment. Second, by rationally setting and verifying system operating parameters (such as the start and end times of sunlight, upper and lower limits of color temperature, and sampling intervals), lighting anomalies or energy waste caused by improper parameter settings are effectively prevented. Then, the generation of the sampling time sequence and the calculation of the target color temperature curve ensure the continuity and scientific nature of color temperature adjustment, enabling it to conform to the diurnal rhythm and achieve comfortable human-centered lighting. Furthermore, by accurately solving the mixing ratio and using the sliding average of the channel current, the problems of sudden changes in lighting output and flickering are overcome, improving lighting quality. Finally, the system's timed output and automatic power-off restart mechanism ensure stable system operation and energy saving. Overall, this method not only improves the intelligence of the lighting system but also enhances energy efficiency, user comfort, and system stability, making it highly suitable for offices, medical facilities, educational institutions, and other places with extremely high lighting requirements.

[0077] The process involves applying predefined driving currents to the warm white and cool white channels of the dual-color LED, and establishing a linear calibration model between the color temperature of each channel and the driving current based on the measured output color temperature. Specifically, this includes:

[0078] Obtain the color temperature-current relationship for warm white and cool white channels to ensure accurate subsequent light distribution;

[0079] Two different sets of driving currents were applied to the warm white LED channel and the cool white LED channel, respectively:

[0080] Warm white channel current: I w1 This serves as the data starting point for establishing the color temperature-current relationship in the warm white channel; I w2 , with I w1 Pairing is used to obtain the linear gain of the warm white channel; corresponding measured color temperature: T w1 T w2 Among them, I w1 I is the first calibration point drive current for the warm white channel; w2 The second calibration point drive current for the warm white channel; T w1 For the warm white channel at current I w1 The color temperature measured below; T w2 For the warm white channel at current I w2 The color temperature measured below;

[0081] Cold white channel current: I c1 I c2 Corresponding color temperature for measurement: T c1 T c2 Among them, I c1 I is the first calibration point drive current for the cold white channel; c2 The driving current at the second calibration point of the cool white channel; respectively serving as the boundary data points for the color temperature-current relationship of the cool white channel; T c1 For the cold white channel at current I c1 The color temperature measured below; T c2 For the cold white channel at current I c2 The color temperature measured below;

[0082] T w1 T w2 T c1 T c2 The output color temperature of the LED channel under different currents was measured for calibration purposes.

[0083] Calculate the current gain α caused by the color temperature change in the warm white channel. w Linear bias term b of warm white channel color temperature and current w : Calculate the color temperature change corresponding to a unit current change in the warm white channel, reflecting the sensitivity of the driving current adjustment to color temperature; b w =T w1 -α w I w1 Determine the zero-point offset for the linear relationship between the color temperature of the warm white channel and the current to ensure that the function can accurately describe all intervals;

[0084] Calculate the current gain α caused by the color temperature change in the cool white channel. c The linear bias term b between the color temperature and current of the cool white channel c : b c =T c1 -α c I c1 This allows the color temperature adjustment capability of the cool white channel to be reflected with a precise mathematical relationship.

[0085] Construct arbitrary warm white channel current I respectively w The output color temperature function T w (I w ) and arbitrary cold white channel current I c The output color temperature function T c (I c ):

[0086] T w (I w )=α w I w +b w According to the input warm white current I w Real-time calculation of actual color temperature provides accurate parameters for subsequent light mixing; T c (I c )=α c I c +b c Corresponding to the cool white channel, this ensures that the color temperature of both channels is linearly controllable with the current.

[0087] By performing detailed linear calibration of the LED dual-color channels, problems such as inaccurate color temperature adjustment and output drift caused by LED characteristic fluctuations or batch differences in traditional lighting systems are solved. This allows the control system to dynamically allocate current based on the actual physical characteristics of each LED channel, thereby achieving more precise color temperature control. Specifically, only by accurately understanding the response characteristics of the warm white and cool white channels can the appropriate current allocation to each channel at each moment be precisely deduced during the light mixing process, ultimately ensuring that the output color temperature always meets the target requirements. This not only improves the controllability of the light mixing effect but also provides an important guarantee for the consistency and stability of lighting equipment in large-scale venues. At the same time, this calibration mechanism also greatly simplifies the complexity of subsequent system maintenance and upgrades, helping to enhance product competitiveness.

[0088] The definition and verification of system parameters, the rationality check of the effective sunshine duration, and the determination of the number of sampling times specifically include:

[0089] Clearly define control parameters and ensure the legality of runtime segments;

[0090] Preset by the designer: the start time of sunlight t rise The time when sunlight ends (t) set Define the effective time range for daily lighting color temperature changes to provide boundaries and target lower limit T for subsequent dynamic color temperature adjustment. min Target color temperature upper limit T max Define the adjustment range of the lighting color temperature to ensure that the output color temperature conforms to human circadian rhythms while avoiding exceeding the limits; specify the sampling time interval Δt to determine the system refresh and adjustment frequency, balancing response speed and system power consumption; define the moving average filter window length M to set the number of samples for smoothing, effectively reducing output flicker; and fix the total drive current I allocated to the dual-color channels. tot As a global upper limit constraint on lighting intensity, it provides a basis for the light distribution ratio;

[0091] Calculate the effective duration of sunshine D = t set -t rise If D≤0, an invalid sunshine duration will be displayed; please reset. Calculate the duration of daily dynamic lighting color temperature changes; if invalid, prevent the system from malfunctioning.

[0092] Calculate the number of sampling times within a day Specify the number of times for dynamic adjustment within a day to facilitate subsequent array initialization and indexing.

[0093] By centrally managing and automatically verifying key parameters of the lighting system, the system effectively solves the problems of cumbersome configuration, error-proneness, and difficulty in detecting anomalies in traditional lighting systems. Before system deployment and operation, the rationality of key parameters is verified to prevent lighting failures, excessive energy consumption, or decreased comfort caused by parameter conflicts or extreme settings. For example, the system can detect conflicts in setting the start and end times of sunlight or color temperature range violations in advance, prompting users to make corrections and ensuring logical consistency in subsequent control processes. For large-scale, intelligent lighting scenarios, this mechanism improves the system's usability, maintainability, and security, making lighting solutions more aligned with human rhythms and actual needs, and providing a solid guarantee for automated, unattended operation.

[0094] The process of generating a sampling time sequence based on the effective sunshine duration and sampling interval specifically includes:

[0095] Generate all dimming sampling moments to ensure continuous and smooth dynamic color temperature;

[0096] For each sampling point n = {0, 1, ..., N-1}, calculate t[n] = t rise +nΔt; where n is the sampling sequence number; t[n] is the nth sampling time; forming a specific timestamp for each sampling point to ensure that the dimming and color adjustment are aligned with the natural day-night rhythm;

[0097] If t[N-1]>tset Then let t[N-1] = t set To avoid the last sampling time exceeding the sunlight range, and to prevent color temperature from changing during invalid periods.

[0098] By generating automated sampling time sequences, the system solves problems such as discontinuous lighting, rhythmic fragmentation, and complex manual maintenance caused by manually setting sampling time nodes. This allows lighting adjustment sampling points to intelligently cover the entire effective lighting range, accurately aligning with diurnal variations and the human biological clock, effectively ensuring natural, smooth, and real-time color temperature adjustments. It also automatically prevents the last sampling point from exceeding the time interval within the effective range, eliminating abnormal lighting actions and improving system robustness. This mechanism enhances the dynamic response capability and user experience of intelligent lighting, making color temperature changes smoother and more natural, and providing a solid time reference for subsequent target color temperature calculations and light mixing control.

[0099] Based on the sampling time and according to a preset day-night variation pattern, the target color temperature curve for each moment is calculated to obtain the dynamic color temperature target sequence of the lighting output throughout the entire cycle, specifically including:

[0100] Determine the optimal target color temperature for each sampling moment to achieve scientific human-centered lighting;

[0101] Calculate the normalized day / night phase at time n. By mapping the sampling points within a day to the interval [0,π], a periodic description of the color temperature change between day and night can be achieved;

[0102] Obtain the target output color temperature T at time n. tgt [n]:

[0103] T tgt [n] = T min +(T max -T min sin(φ[n]); calculates the physiological health color temperature curve value for each sampling point, so that the lighting is both in line with natural changes and scientifically reasonable.

[0104] By calculating the target color temperature in real time for each sampling moment based on circadian rhythms and preset curves, this system solves the problems of abrupt color temperature changes and difficulty in meeting human physiological needs in traditional lighting systems. It enables the lighting color temperature to continuously and gradually respond to changes in natural light or user health needs, scientifically simulating the natural light environment and helping to improve the physiological comfort and health of indoor occupants. Furthermore, the dynamic generation of the target color temperature facilitates subsequent algorithms for precise light mixing and dynamic drive current distribution, fundamentally improving the human-centered design, scene adaptability, and market competitiveness of intelligent lighting systems. This control concept based on dynamic target curves is the technological foundation of modern healthy lighting and smart building lighting control.

[0105] Based on the color temperature-current model of the dual-color channels and the target color temperature curve, a mixing function is defined, and the distribution ratio of the dual-color channel current is solved mathematically, specifically including:

[0106] Calculate the two-color mixing ratio to ensure that the output color temperature is strictly consistent with the target color temperature;

[0107] Let r be the proportion of the warm white channel current, which directly determines the dual-color light distribution at each moment and is the core parameter for color temperature adjustment; then the warm white channel current I... w =r·I tot Cold white channel current I c =(1-r)·I tot The actual operating current of the channel is calculated in real time based on the allocation ratio, which directly affects the LED output color temperature.

[0108] Constructing the color temperature function for light mixing: Among them, T mix (r) represents the output color temperature of the warm and cool color mixing; it expresses the total output color temperature of the system after two-color mixing, allowing for precise calculation of the allocation ratio;

[0109] Expand and organize Ar 2 +Br+C=0 transforms the problem of color temperature mixing into a mathematical root-finding problem, which can be rigorously solved using algebraic methods; where A=I tot (α w +α c ) represents the coefficient of the quadratic term; B = b w -b c -2α c I tot The coefficient of the linear term; C = α c I tot +b c -T tgt [n] represents constant terms; each term reflects the sensitivity and bias of the dual-color channel color temperature adjustment, providing the necessary conditions for solving r.

[0110] Obtain the discriminant Δ = B 2 -4AC; Determine the existence and distribution of solutions to the equations to ensure that the results of light mixing adjustment have physical meaning;

[0111] If Δ≥0, we get Where r1 and r2 are the two roots of the quadratic equation, representing the possible solutions for the current ratio of the warm white channel;

[0112] Select the first root that satisfies 0≤r≤1 in turn. If both roots exist, then take r1.

[0113] Screen out the legal light distribution ratio and avoid negative or excessive channel current;

[0114] If Δ < 0 or neither root is in [0,1], it degenerates into a linear approximation:

[0115] in, Color temperature under full current only for the warm white channel; r[n] represents the color temperature of the cool white channel under full current only; r[n] represents the current ratio of the warm white channel at the nth sampling point.

[0116] Even when the quadratic method has no solution or the values ​​are extreme, the system color temperature can still be continuously adjusted.

[0117] like Let r[n] = 0.5; in extreme cases, ensure color balance and prevent the denominator from being zero;

[0118] Boundary cutoff: Ensure that the light distribution ratio is physically effective and that the current distribution never exceeds the limits.

[0119] Through rigorous mathematical modeling and precise calculation of the mixing ratio, this method solves the problems of large adjustment errors, blind light distribution, and poor system stability in existing dual-color LED mixing methods. Based on the known target color temperature and the calibration model of each channel, the optimal current distribution at each moment is derived, improving the accuracy and physical consistency of lighting color temperature control. It also features fault-tolerant mechanisms such as automatic boundary verification, outlier detection, and switching to linear approximation to ensure that the lighting output always operates within the physically and safety-allowed range, avoiding color temperature deviation or channel damage. This mechanism also facilitates future algorithm expansion and multi-channel system applications, enhancing system adaptability, robustness, and scalability, providing technical support for high-end intelligent lighting control.

[0120] The process of allocating the obtained current values ​​for each channel and smoothing the current data using a moving average method specifically includes:

[0121] To prevent sudden changes in output color temperature caused by abrupt changes in the ratio, and to improve lighting comfort;

[0122] Original current distribution: I w [n]=r[n]I tot I c [n]=(1-r[n]I tot Among them, I w [n] represents the warm white channel current at time n; I c [n] represents the current of the cold white channel at time n; the actual driving current of the dual-color channels is allocated to ensure the overall brightness stability of the system;

[0123] Obtain the number of valid samples K participating in the averaging at time n. n =min(M,n+1); Dynamically determine the sliding window length to ensure no sampling is lost during system startup;

[0124] Calculate the smoothed current of the warm white channel at time n.

[0125] Calculate the smoothed current of the cold white channel at time n.

[0126] Smooth raw current data, eliminate flicker and abrupt changes, and optimize human eye perception and system reliability.

[0127] By processing the channel current distribution at each moment using the moving average method, the visual discomfort problems such as output abrupt changes and flickering during dynamic adjustment in traditional lighting systems are solved. The moving average algorithm can effectively reduce short-term changes caused by sampling, calculation, or driving errors, making the lighting output smoother, more natural, continuous, and comfortable, thus optimizing the human visual experience. In addition, this method also helps extend the lifespan of LED devices, avoids component stress and failure caused by excessive current fluctuations, and improves the long-term reliability of the system. The smoothing process also facilitates the integration of more complex human-centered lighting strategies, supporting the lighting needs of diverse smart scenarios.

[0128] At each sampling moment, the final determined drive current values ​​for the warm white and cool white channels are output to the lighting driver, specifically including:

[0129] The calculated smooth current command is written into the drive system in sequence to form high-quality lighting;

[0130] Write at each sampling time t[n] To the LED driver; directly drive the LED channel to achieve automated color temperature conversion and ensure synchronization between lighting output and calculation;

[0131] If writing fails, record the error log and maintain the previous valid value; when the system encounters communication failure or hardware error, record the log and maintain the previous valid command to prevent sudden blackouts or misoperations.

[0132] By employing high-frequency timed output and an anomaly adaptive mechanism, the system mitigates the risks of global blackouts and uncontrolled lighting in traditional lighting systems when communication anomalies or driver failures occur. It not only achieves real-time synchronization between drive current commands and lighting hardware, ensuring a high degree of consistency between theoretical color temperature and actual output, but also enhances system robustness and automatic maintenance capabilities through anomaly recording and fault-tolerance mechanisms. In the event of unexpected situations such as write failures, the system automatically retains the previous valid output value, preventing adverse user experiences or equipment damage caused by sudden output changes. This mechanism improves the engineering practicality and post-maintenance controllability of intelligent lighting systems, making them suitable for long-term, stable operation in critical locations.

[0133] The automatic disconnection of lighting power at the end of each daily lighting cycle, followed by restarting according to a predetermined procedure the next day, specifically includes:

[0134] The system is closed-loop, ensuring energy efficiency and long-term stability.

[0135] If the last sampling point t[N-1]≥t set If (0,0) is written, the lamp will be powered off; it will automatically enter energy-saving mode to reduce energy consumption and LED lifespan loss.

[0136] The system enters low-power sleep mode until the next day. rise It automatically returns to step S3 to restart; enabling continuous operation of the lighting rhythm without human intervention, facilitating long-term deployment.

[0137] By implementing daily periodic automatic power-offs and automatic wake-ups the following day, this system solves the problems of high energy consumption, manual operation requirements, and the tendency to forget to turn off power in traditional systems. It ensures the system automatically enters a low-power sleep mode during non-lighting periods, reducing standby power consumption and overall operating costs. Simultaneously, the scheduled wake-up the following day and automatic resumption of lighting control processes enables unattended, continuous automatic operation, greatly facilitating efficient management in long-term deployment scenarios such as smart buildings, factories, and campuses. This closed-loop mechanism not only saves energy and reduces consumption but also protects the lifespan of equipment components, improving the overall reliability and intelligence level of the lighting system, aligning with the development trends of green buildings and smart cities.

[0138] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0139] 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 technical principles 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 lighting control method based on artificial intelligence, characterized in that, include: S1. Apply a predefined driving current to the warm white channel and cool white channel of the dual-color LED respectively, and establish a linear calibration model between the color temperature of each channel and the driving current based on the measured output color temperature. The process involves applying predefined driving currents to the warm white and cool white channels of the dual-color LED, and establishing a linear calibration model between the color temperature of each channel and the driving current based on the measured output color temperature. Specifically, this includes: Towards warm white Channel and cold white Two different drive currents are applied to the channel: Warm white channel current: , Corresponding color temperature for measurement: , ;in, This is the first calibration point drive current for the warm white channel; This is the second calibration point drive current for the warm white channel; For the warm white channel in current The color temperature measured below; For the warm white channel in current The color temperature measured below; Cold white channel current: , Corresponding color temperature for measurement: , ;in, This is the first calibration point drive current for the cold white channel; This is the second calibration point drive current for the cold white channel; For the cold white channel in current The color temperature measured below; For the cold white channel in current The color temperature measured below; Calculate the current gain caused by the color temperature change in the warm white channel. Linear bias term of color temperature and current in warm white channel : The color temperature change corresponding to a unit current change in the warm white channel is calculated, reflecting the sensitivity of the driving current adjustment to the color temperature. ; Calculate the current gain caused by the color temperature change in the cool white channel. Linear bias term of color temperature and current in cool white channel : , ; Construct arbitrary warm white channel currents respectively Output color temperature function and arbitrary cold white channel current Output color temperature function : ， ； S2. Define and verify system parameters, including the start time of sunshine, the end time of sunshine, the upper and lower limits of the target color temperature, the sampling time interval, the length of the moving average filter window and the total drive current of the dual-color channels, and perform a reasonableness check on the effective duration of sunshine and determine the number of sampling times. The definition and verification of system parameters, the rationality check of the effective sunshine duration, and the determination of the number of sampling times specifically include: Preset by the designer: the start time of sunlight End of sunshine Target color temperature lower limit Target color temperature upper limit Sampling time interval Length of moving average filter window and the total drive current fixedly allocated to the dual-color channels ; Calculate the effective duration of sunshine ;like If the setting is incorrect, an invalid sunshine duration will be displayed; please reset it. Calculate the number of sampling times within a day ; S3. Generate a sampling time sequence based on the effective sunshine duration and sampling interval; The process of generating a sampling time sequence based on the effective sunshine duration and sampling interval specifically includes: For each sampling point calculate ;in, The sampling sequence number; For the first Each sampling time; like Then let ; S4. Based on the sampling time, according to the preset day-night variation pattern, calculate the target color temperature curve for each time moment to obtain the dynamic color temperature target sequence of the lighting output throughout the entire cycle. Based on the sampling time and according to a preset day-night variation pattern, the target color temperature curve for each moment is calculated to obtain the dynamic color temperature target sequence of the lighting output throughout the entire cycle, specifically including: Calculate the first Normalized day / night phase at any given moment ; Get the The target output color temperature at any given moment : ； S5. Based on the color temperature-current model of the dual-color channel and the target color temperature curve, define the mixing function and solve the distribution ratio of the current of the dual-color channel through mathematical methods. Based on the color temperature-current model of the dual-color channels and the target color temperature curve, a mixing function is defined, and the distribution ratio of the dual-color channel current is solved mathematically, specifically including: Let the current ratio of the warm white channel be... Then the warm white channel current Cold white channel current ; Constructing the color temperature function for light mixing: ;in, The output color temperature is a mixture of warm and cool tones; Expanded and organized ;in, The coefficient of the quadratic term; The coefficient of the linear term; For constant terms; Obtain the discriminant ; like ,have to , ;in, , The two roots of the quadratic equation represent the solutions for the proportion of current in the warm white channel. Select the first one that satisfies the condition in turn If both roots exist, then take the root. ; like Or neither of them is present. Internally, it degenerates into a linear approximation: , , ;in, Color temperature under full current only for the warm white channel; Color temperature under full current only for the cool white channel; For the first The proportion of warm white channel current at the sampling point; like Then let ; Boundary cutoff: ; S6. Allocate the obtained current values ​​for each channel and smooth the current data using a moving average method. S7. At each sampling moment, output the final determined warm white and cool white channel drive current values ​​to the lighting driver; S8. Automatically cut off the lighting power supply after the end of the daily lighting cycle, and restart it the next day according to the established procedure.

2. The lighting control method based on artificial intelligence according to claim 1, characterized in that, The process of allocating the obtained current values ​​for each channel and smoothing the current data using a moving average method specifically includes: Original current distribution: , ;in, For the first Constant warm white channel current; For the first The current in the cold white channel is constant. Get the The number of effective samples participating in the average at each time point ; Calculate the first Current after smoothing the warm white channel at all times ; Calculate the first Current after smoothing the cold white channel at all times .

3. The lighting control method based on artificial intelligence according to claim 2, characterized in that, At each sampling moment, the final determined drive current values ​​for the warm white and cool white channels are output to the lighting driver, specifically including: At each sampling time Write to drive; If the write operation fails, log the error and retain the previous valid value.

4. The lighting control method based on artificial intelligence according to claim 3, characterized in that, The automatic disconnection of lighting power at the end of each daily lighting cycle, followed by restarting according to a predetermined procedure the next day, specifically includes: If the last sampling point Then write Turn off the power to the lights; The system enters low-power sleep mode until the next day. Automatically return to step S3 and start again.

Images