Intelligent light coordination control system and method based on artificial intelligence

Abstract

The application proposes an intelligent light coordination control system and method based on artificial intelligence, which comprises the following steps: acquiring lamp operation state, environment lighting state and engineering parameters, and generating a basic executable constraint interval; utilizing an adjacency list and coupling weight to cooperatively trim the basic constraint set to generate a system-level cooperative constraint set; within the range limited by the system-level cooperative constraint set, combining the current state and neighborhood trend value, and determining the target control value through constrained least square calculation; and based on the first-order inertia model discretization logic, calculating the actual control value and issuing it for execution. Through dynamic constraint construction and cooperative optimization, the application effectively solves the adjustment conflict problem under multi-lamp coupling, realizes smooth transition and regional uniformity of light control, and improves lighting comfort and energy saving effect.

Description

Technical Field

[0001] This invention belongs to the field of intelligent lighting control, and particularly relates to an intelligent lighting collaborative control system and method based on artificial intelligence. Background Technology

[0002] With the increasing demand for intelligent building and refined energy management, smart lighting control systems have evolved from manual and timed control to automatic control based on sensors and rules, further incorporating data-driven intelligent decision-making to improve energy efficiency and user experience. In practical applications involving multiple lighting fixtures and areas, such as office buildings, commercial complexes, hospitals, and transportation hubs, the engineering challenge of lighting control often lies not in calculating a specific set of lighting parameters, but in ensuring that the calculated control is truly executable under current operating conditions and maintains overall consistency when multiple fixtures are operating simultaneously. Existing technologies generally use single-lamp or group strategies to directly output control quantities such as brightness and color temperature, easily ignoring the spatial coupling and superposition effects between fixtures. This leads to a deviation between local optimization and overall experience, manifesting as uneven regional illuminance, visual discomfort, or excessively rapid brightness changes. Furthermore, with the introduction of intelligent algorithms, the direct output of control quantities may result in abrupt changes in control values, mismatch with engineering boundaries or equipment capabilities, and increased difficulty in debugging and maintenance during actual operation. More importantly, existing multi-light coordination mechanisms mostly remain at the level of linkage or centralized scheduling, lacking a directly calculable, transferable, and applicable "system executable boundary" expression that can be used for subsequent decision-making and execution. This makes it difficult to stably implement control strategies at the engineering level, even if they are reasonable at the algorithmic level. Therefore, a control mechanism for multi-light coordination is still needed to incorporate engineering boundaries, spatial coupling, and operational continuity into a unified computational framework, ensuring that the control process is executable and consistent from the outset. Summary of the Invention

[0003] This invention discloses an intelligent lighting collaborative control system and method based on artificial intelligence to solve the problems mentioned in the background art.

[0004] To achieve the above objectives, the first aspect of the present invention provides a smart lighting collaborative control method based on artificial intelligence, the method comprising:

[0005] Obtain the current operating status of each lamp, the ambient lighting status of the corresponding area, and the preset lighting engineering parameters;

[0006] Based on the current operating state, the ambient lighting state, and the lighting engineering parameters, a basic executable constraint interval is generated for each lamp, and all the basic executable constraint intervals constitute a basic executable constraint set.

[0007] Obtain a preset adjacency list, which records the set of adjacent lamps and the corresponding coupling weights for each lamp;

[0008] Using the set of adjacent lamps, the coupling weights, and the set of basic executable constraints, the basic executable constraint interval of each lamp is collaboratively pruned to generate a system-level collaborative constraint interval for each lamp. All the system-level collaborative constraint intervals constitute a system-level collaborative constraint set.

[0009] Within the system-level collaborative constraint range of each lamp, the target control value of each lamp is determined by constrained least squares calculation, combining the current operating state and neighborhood trend value, to form a lighting control scheme.

[0010] Based on the first-order inertial model discretization logic, the actual control value of each lamp is calculated using the target control value, the current operating state, and the preset execution coefficient, and then sent to the corresponding lamp driver interface for adjustment.

[0011] Furthermore, the specific steps for generating the basic executable constraint interval for each lamp include:

[0012] Map the ambient lighting state to a control scale consistent with the current operating state;

[0013] The mapped ambient lighting state and the current operating state are weighted and combined according to a preset ratio to obtain a combined mapping value;

[0014] Read the minimum allowable adjustment boundary, the maximum allowable adjustment boundary, and the allowable offset range per single cycle from the lighting engineering parameters;

[0015] Centered on the combined mapping value, and in conjunction with the minimum allowable adjustment boundary, the maximum allowable adjustment boundary, and the single-cycle allowable offset range, the lower and upper boundaries of the basic executable constraint interval are determined.

[0016] Furthermore, the lighting engineering parameters also include scene mode parameters, which are used to adjust the relative weight ratio of the current operating state deviation term and the neighborhood trend value deviation term in the constrained least squares calculation.

[0017] Furthermore, the specific steps for collaboratively pruning the basic executable constraint interval of each lamp using the set of adjacent lamps, the coupling weights, and the set of basic executable constraints include:

[0018] Read the allowable offset range for a single cycle from the lighting engineering parameters;

[0019] Iterate through the set of adjacent lamps for each lamp, and for each adjacent lamp, calculate the interval expansion amplitude by multiplying the coupling weight by the single-cycle allowable offset range;

[0020] Using the aforementioned range expansion, the basic executable constraint range of the adjacent lamps is symmetrically expanded to obtain a compatible range;

[0021] Perform interval intersection operation between the basic executable constraint interval of the lamp itself and the compatible intervals corresponding to all the adjacent lamps;

[0022] The maximum value of all lower boundaries in the intersection operation result of the interval is taken as the new lower boundary, and the minimum value of all upper boundaries is taken as the new upper boundary, thus obtaining the system-level collaborative constraint interval.

[0023] Furthermore, the adjacency list is stored in the controller configuration file or the host computer configuration table, and the adjacency list is configured according to the grid division of the lighting area, the definition of the workstation area, or the connection relationship of the corridor direction.

[0024] Furthermore, the calculation steps for the neighborhood trend value include:

[0025] Read the center point of the system-level collaborative constraint interval for each adjacent lamp in the adjacent lamp set, where the center point is the average of the lower and upper boundaries of the system-level collaborative constraint interval;

[0026] The neighborhood trend value is obtained by using the coupling weight to calculate the weighted average of the center point.

[0027] Furthermore, the specific steps for determining the target control value for each lamp through constrained least squares calculation include:

[0028] Construct a cost function, which includes a weighted sum of a first deviation square and a second deviation square, wherein the first deviation square is the square of the difference between the candidate control value and the current operating state, and the second deviation square is the square of the difference between the candidate control value and the neighborhood trend value.

[0029] The constraint condition is set such that the candidate control value must be within the system-level collaborative constraint interval;

[0030] Find the extreme points of the cost function under unconstrained conditions;

[0031] Determine whether the extreme point is located within the system-level collaborative constraint interval. If the extreme point is located within the system-level collaborative constraint interval, then the extreme point is determined as the target control value. If the extreme point is less than the lower boundary of the system-level collaborative constraint interval, then the lower boundary is determined as the target control value. If the extreme point is greater than the upper boundary of the system-level collaborative constraint interval, then the upper boundary is determined as the target control value.

[0032] Furthermore, the specific steps for calculating the actual control value of each lamp based on the first-order inertial model discretization logic include:

[0033] Calculate the difference between the target control value and the current operating state;

[0034] Multiply the difference by the execution coefficient to obtain the adjustment increment;

[0035] The current operating state is added to the adjustment increment to obtain the actual control value;

[0036] The actual control value is written into the lighting driver interface, and the current operating status of the next cycle is updated to the actual control value.

[0037] Furthermore, the ambient lighting status is acquired by an ambient lighting acquisition device located within the lighting area, the ambient lighting acquisition device including an illuminance sensor or a color temperature sensor.

[0038] A second aspect of the invention provides an artificial intelligence-based intelligent lighting coordination control system, the system comprising:

[0039] The data acquisition module is used to obtain the current operating status of each lamp, the ambient lighting status of the corresponding area, and the preset lighting engineering parameters;

[0040] The basic constraint generation module is used to generate the basic executable constraint range for each lamp based on the current operating state, the ambient lighting state, and the lighting engineering parameters, and to form a basic executable constraint set.

[0041] The collaborative constraint construction module is used to obtain a preset adjacency list, and use the set of adjacent lamps and coupling weights in the adjacency list to collaboratively prune the basic executable constraint set to generate a system-level collaborative constraint set.

[0042] The control scheme generation module is used to determine the target control value of each lamp by constrained least squares calculation within the limited range of the system-level collaborative constraint set, combined with the current operating state and neighborhood trend value, to form a lighting control scheme.

[0043] The execution adjustment module is used to calculate the actual control value of each lamp based on the first-order inertial model discretization logic, using the target control value, the current operating state, and the preset execution coefficient, and then send it to the corresponding lamp driver interface for adjustment.

[0044] The beneficial technical effects of the present invention are at least as follows:

[0045] To address the aforementioned issues, this invention provides an AI-based intelligent lighting collaborative control system and method. The system first transforms the lighting control problem into a computable set of constraint intervals. Then, it introduces spatially correlated collaborative pruning to obtain a set of collaborative constraint intervals for simultaneous operation of multiple lights. Furthermore, within this collaborative constraint range, it generates a target control scheme by combining the current operating state and neighborhood trends. Finally, it applies the control scheme stably to the lighting state of the lights through a convergent execution process. This mechanism explicitly solidifies the constraints originally scattered across engineering specifications, equipment capabilities, and operational continuity requirements into transitible constraint objects. It transforms the spatial coupling relationships between lights into collaborative processing rules for constraint intervals, thus ensuring that the control scheme naturally falls within the system's allowable range and reflects regional consistency and continuity. Simultaneously, it limits intelligent decision-making to determining control values ​​within the collaborative constraint range, enabling it to leverage data-driven advantages to generate schemes more suited to the scenario's needs without exceeding the engineering execution boundaries. Through this overall structure, this invention achieves adaptive lighting adjustment for complex scenarios while ensuring multi-light coordination and stable operation, reducing engineering debugging difficulty and improving the long-term stability and maintainability of the system. Attached Figure Description

[0046] The present invention will be further described with reference to the accompanying drawings, but the embodiments in the drawings do not constitute any limitation on the present invention. For those skilled in the art, other drawings can be obtained based on the following drawings without creative effort.

[0047] Figure 1 This is a flowchart of the intelligent lighting collaborative control method based on artificial intelligence according to the present invention.

[0048] Figure 2 This is a framework diagram of the intelligent lighting collaborative control system based on artificial intelligence of the present invention. Detailed Implementation

[0049] Embodiments of the present invention are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and should not be construed as limiting the present invention.

[0050] In one or more embodiments, such as Figure 1 As shown, a smart lighting collaborative control method based on artificial intelligence is disclosed, the method comprising the following:

[0051] S100: Obtain the current operating status of each lamp, the ambient lighting status of the corresponding area, and the preset lighting engineering parameters. Based on the current operating status, the ambient lighting status, and the lighting engineering parameters, generate the basic executable constraint interval for each lamp to form a basic executable constraint set.

[0052] It should be noted that within the current operating cycle of the intelligent lighting system, the system first needs to establish a set of basic executable constraints that govern subsequent collaborative control and intelligent decision-making. The core of this step lies in unifying the constraints scattered across device states, environmental backgrounds, and engineering specifications into directly usable control boundaries. Current lighting control often relies on threshold judgments from single sensors or fixed schedules, lacking comprehensive consideration of multi-lamp coupling relationships and dynamic environmental changes, resulting in rigid adjustment processes, high energy consumption, and insufficient comfort. This invention constructs a basic constraint model encompassing individual lamp states, environmental backgrounds, and engineering parameters, providing a precise feasible domain for subsequent collaborative optimization.

[0053] In this embodiment of the invention, step S100, which involves obtaining the current operating state of each lamp, the ambient lighting state of the corresponding area, and preset lighting engineering parameters, and generating the basic executable constraint range for each lamp, further includes: the system obtaining the current operating state of each lamp from its control interface, which reflects the current light emission control level of the lamp and is stored in a standardized representation form within the control system; simultaneously, the system obtaining the ambient lighting state from an ambient lighting acquisition device located within the lighting area, which is used to characterize the overall lighting background formed by natural light or other light sources in the current space, and mapping the ambient lighting state to a control scale consistent with the lamp's operating state; in addition, the system calls the lighting engineering parameter set configured during the deployment phase, which includes the minimum allowable adjustment boundary, the maximum allowable adjustment boundary, and the single-cycle allowable offset range.

[0054] Specifically, by collecting real-time operating data of the luminaires and environmental sensing data, and combining this with pre-set engineering specifications, the safe adjustment range of a single lamp at the current moment is calculated. This not only considers the physical limits of the luminaire itself, but also incorporates ambient light compensation requirements and engineering constraints to prevent visual abrupt changes; a basic executable constraint range is constructed for each luminaire. This constraint range is calculated by comprehensively considering the current operating state of the luminaire, the ambient lighting state, and engineering parameters, and is used to limit the control range that the luminaire is allowed to enter within the current operating cycle. The calculation method is as follows:

[0055] ;

[0056] in, Indicates the first The basic executable constraint range formed by each lamp within the current operating cycle; Indicates the first The current operating status of the lamp, which is provided directly by the lamp control interface; This indicates the ambient lighting status corresponding to the area where the luminaire is located, which is acquired and scaled by the ambient lighting acquisition device. Indicates to and The deterministic processing of combined mapping is achieved by weighting the two according to a preset ratio and mapping them to a control scale. and These represent the minimum and maximum allowable adjustment boundaries pre-configured in the engineering parameters, respectively. This indicates the maximum allowable offset range within a single operating cycle, used to constrain the magnitude of change in the control interval.

[0057] Furthermore, regarding input data, the first step is to collect operational status data of the luminaires. This data originates from the feedback interface of the luminaire driver or the host computer monitoring database, including brightness percentage, color temperature value, on / off status, and equipment health. Secondly, ambient lighting data needs to be collected. This data comes from illuminance sensors, color temperature sensors, or camera image analysis results deployed in key areas, primarily including work surface illuminance, ambient color temperature, and natural light contribution rate. Finally, lighting engineering parameters need to be collected. This information comes from lighting calculation sheets or on-site commissioning records during the design phase and needs to be read through configuration files or databases. Examples include minimum / maximum brightness limits for human eye comfort, maximum step size limits for single adjustments to prevent flicker, and energy-saving constraints for specific scenarios.

[0058] Furthermore, in this embodiment, within a smart lighting system for an office area, the control value corresponding to the operating state of a certain lamp in the current cycle is at a medium level, while the ambient lighting data collection results indicate that the area is in a relatively bright state due to natural light. When performing combined mapping, the system will, according to a preset ratio, ensure that the ambient lighting state has a significant impact on the mapping result, thereby... The calculation results are shifted towards lower artificial lighting requirements. Based on this, and combined with the allowable adjustment boundaries and single-cycle offset range set in the engineering parameters, the final basic executable constraint range obtained by the system will be concentrated in a lower control range, which satisfies the current lighting requirements while avoiding unnecessary energy consumption and abrupt changes.

[0059] Through the above processing, the system generates a clear and continuous basic executable constraint range for each lamp. The constraint ranges corresponding to all lamps together constitute the basic executable constraint set. This constraint set is used to fully describe the control space allowed by the system within the current operating cycle and serves as the direct input for subsequent multi-lamp collaborative constraint construction and artificial intelligence decision-making processes.

[0060] S200: Obtain a preset adjacency list, and use the set of adjacent lamps and coupling weights in the adjacency list to collaboratively prune the basic executable constraint interval of each lamp to generate a system-level collaborative constraint interval for each lamp. All the system-level collaborative constraint intervals constitute a system-level collaborative constraint set.

[0061] It should be noted that the goal of step S200 is to further converge the basic constraints of a single lamp into system-level constraints for multi-lamp collaboration by utilizing the constructed adjacency relationships. This process ensures that adjacent lamps maintain spatial continuity and consistency during adjustment by coupling weights and interval expansion intersection operations, avoiding the "zebra stripe" effect or sudden changes in local brightness, thereby improving the overall lighting quality. The spatial association information used for collaborative processing comes from the configuration file during the deployment phase or the area configuration table issued by the host computer, and is usually stored in the form of an adjacency list, that is, giving each lamp an adjacent set. This represents a set of luminaires that have significant overlap or coupling effects with the given luminaire in terms of lighting coverage. For open office areas, adjacency is typically defined by grid or workstation area; for corridor scenarios, adjacency is connected in series along the direction to ensure vertical continuity; for enclosed spaces such as meeting rooms, adjacency covers luminaires within the same room to ensure overall consistency. In addition to the adjacency table, the configuration file also includes the coupling weight for each pair of adjacent luminaires. This weight is used to reflect the strength of coupling. In engineering, it can be obtained by looking up a table of the overlap ratio between the installation spacing and the lighting coverage, or it can be calibrated and written after adjusting the uniformity of the area during the commissioning stage.

[0062] In this embodiment of the invention, step S200, which involves obtaining a preset adjacency list and using the adjacent lamp sets and coupling weights in the adjacency list to collaboratively prune the basic executable constraint set, further includes: the system reading the preset adjacency list, which records the adjacent lamp sets and corresponding coupling weights for each lamp; traversing the adjacent lamp sets for each lamp, and for each adjacent lamp, calculating the interval expansion range by multiplying the coupling weight by the single-cycle allowable offset range; using this interval expansion range, symmetrically expanding the basic executable constraint intervals of the adjacent lamps to obtain a compatible interval; and finally, performing an interval intersection operation between the basic executable constraint interval of the lamp itself and the compatible intervals corresponding to all adjacent lamps to obtain a system-level collaborative constraint interval.

[0063] The collaborative processing employs the classic "constraint propagation" concept: transforming the executable intervals of adjacent lamps into compatibility constraints on the interval of the current lamp, and then achieving pruning through interval intersection. Interval intersection and interval expansion originate from interval and set operations in mathematics, belonging to deterministic computable operations; among them, "interval expansion" corresponds to a special case of Minkowski addition on interval sets of one-dimensional sets, used to express "allowing relative changes within a certain margin." To ensure that the collaborative margin remains consistent with the engineering constraints of the previous step, this step transforms the constraints formed in the previous step... The single-cycle allowable offset range used at that time Directly introduce collaborative computing and couple it with weights Combining the adjacent constraints yields the expansion range. This combination relationship derives from the mathematical form of scaling: under the same control scale, the allowable offset range is linearly scaled using a scaling factor, thereby solidifying the engineering intuition that "the stronger the coupling, the tighter the cooperative constraint" into a computable quantity, calculated as follows:

[0064] ;

[0065] in, Indicates lighting fixtures In relation to adjacent light fixtures The range of expansion used during coordination is derived from the combination of configuration weights and parameters from the previous step; The coupling weights obtained from the deployment phase configuration or debugging calibration are stored in the controller configuration file or the host computer configuration table. For the lighting fixtures in the previous engineering parameter set The corresponding allowable offset range for a single cycle has been calculated in the previous step. This approach is adopted at times. All the above quantities are under the same control scale, and the product still corresponds to the "expansion range" under the same scale, which is used for subsequent interval expansion operations.

[0066] In obtaining Then, the system connects adjacent lights. Basic executable constraint range Expanding to a "compatibility range", the engineering implementation method is to read The lower and upper boundaries, extending the lower boundary downwards. The upper boundary extends upwards. Thus obtain The system then... Its own basic executable constraint range Intersections are established with the compatible intervals provided by all adjacent luminaires. The engineering implementation of the intersection is to take the maximum value of the lower boundaries of all participating intervals as the new lower boundary, and take the minimum value of the upper boundaries of all intervals as the new upper boundary, thereby forming a system-level collaborative constraint interval. The calculation is as follows:

[0067] ;

[0068] in, Indicates lighting fixtures The system-level collaborative constraint interval is the target result of this step; and Lighting fixtures With adjacent light fixtures Based on the executable constraint range obtained in the previous step; For lighting fixtures The set of adjacent lights is derived from the deployment configuration; Indicates the interval by The interval operations that perform symmetrical expansion are specifically implemented by adding or subtracting from the interval endpoints; This represents the interval intersection operation, specifically implemented by taking the maximum / minimum values ​​at the endpoints. All the above operations are performed under the same control scale; interval expansion and intersection operations do not change the scale type, therefore the generated... and input range Maintaining a consistent scale expression allows it to be directly used as the boundary input for generating the next control scheme.

[0069] Furthermore, in this embodiment, a set of specific calculation examples are given, assuming that the lighting fixtures in an open office area... The basic executable constraint interval obtained in the previous step is: Its adjacent set Includes two lamps and And the adjacent lamp intervals output in the previous step are respectively , The deployment configuration provides coupling weights. , Meanwhile, the lighting fixtures in the previous engineering parameters The single-cycle allowable offset range is First, we obtain from the first equation. , Based on this, expand the adjacent intervals: , Next, perform interval intersection: first... and Intersection , and then with The intersection yields the final result This result directly demonstrates the effect of collaborative clipping: while maintaining the luminaire... While constraining its own basic executable range, the system also considers the executable range and coupling strength of adjacent luminaires within the same space. This tightens the system-level collaborative constraint range at the high end and raises it at the low end, providing a consistent collaborative boundary for selecting specific control values ​​within this range. The final output is a system-level collaborative constraint set, obtained by repeating the above calculation for each luminaire in the system. A set of.

[0070] S300: Within the constraints of the system-level collaborative constraint set, and combining the current operating status and neighborhood trend values, the target control value of each lamp is determined by constrained least squares calculation to form a lighting control scheme.

[0071] It should be noted that the objective of step S300 is to [do something] in each [item]. Select a target control value and put all the lights This step involves assembling a lighting control scheme. Since the lighting scenario is sensitive to both "continuous stability" and "regional consistency," this step categorizes these two engineering requirements into two types of calculable deviation terms: one is the target value relative to the current operating state. One type of deviation is the deviation of the target value relative to the trend of the neighborhood; then the requirement of "must be within the cooperative constraint interval" is written as a constraint condition, thereby transforming the scheme generation into a one-dimensional, deterministic solution of a constrained least squares problem.

[0072] In this embodiment of the invention, step S300, within the defined scope of the system-level collaborative constraint set, and combining the current operating state and neighborhood trend values, further includes determining the target control value for each lamp through constrained least squares calculation:

[0073] First, calculate the neighborhood trend value. Read the center point of the system-level collaborative constraint interval for each adjacent lamp in the adjacent lamp set, and calculate a weighted average of these center points using coupling weights to obtain the neighborhood trend value; the neighborhood trend is represented by a scalar. express. The construction is derived from the weighted mean in statistics: a weighted average of representative values ​​from adjacent lights, with the weights given by the deployment configuration. Here, adjacent lights are selected. The representative value is its co-constraint interval. The center point of the interval is the natural representative value in the geometric sense of the interval, and the controller can be directly calculated from the interval endpoints. Combining the "interval center point" with the "weighted mean" yields the neighborhood trend, calculated as follows:

[0074] ;

[0075] in, For lighting fixtures The neighborhood trend value; The adjacency set configured for the deployment phase comes from the controller configuration file or the region configuration table issued by the host computer; The coupling weights obtained from configuration or debugging during the deployment phase come from the same configuration source. For adjacent light fixtures The system-level collaborative constraint interval is derived from the output of the previous step; and These are the lower and upper endpoints of the interval, respectively, which the controller reads directly from the interval data structure. Both sides of the equation are scalars on the control scale; the weighted average does not change the dimensional properties, therefore... With interval endpoints, Being within the same dimensional system, they can directly participate in subsequent deviation calculations.

[0076] Secondly, a cost function is constructed and the target control value is solved. Scenario mode parameters are set to adjust the relative weight ratio of the current operating state deviation term and the neighborhood trend value deviation term. A cost function containing the sum of squared deviations is constructed, and the constraint condition that the candidate control value must be within the system-level collaborative constraint interval is set.

[0077] In obtaining After that, the target control value Determined through constrained least squares. This method originates from least squares and convex optimization in mathematics: it measures the degree of "closeness to the target" using the squared deviation and searches for the point that minimizes the cost within the feasible region. The cost here consists of two parts, corresponding to "closeness to the current operating state" and "closeness to the target state." "and the trend of being close to the neighborhood" The relative weights between the two parts are given by the deployment configuration or scenario mode parameters. Adjustment; feasible region by The above engineering concept can be expressed in optimized form as follows:

[0078] ;

[0079] in, For lighting fixtures Target control value; Candidate control values; This refers to the system-level collaborative constraint interval output in the previous step; For lighting fixtures The current operating status is provided by the lighting control interface and updated and maintained within the controller; Calculated from the previous formula; Parameters for the scenario are configured from the controller configuration file or issued by the host computer policy. Both squared deviations in this formula are composed of the squares of the "control scale difference". Since the cost is a proportionality coefficient, the two terms can be directly added and have the same dimensions. This optimization problem has a definite solution path in the one-dimensional case: for the cost function within the parentheses... By taking the derivative and setting it to zero, we can obtain the unconstrained extreme points. ; then Limit to interval You can get it inside. The engineering implementation involves a weighted calculation followed by comparison and trimming of the interval endpoints.

[0080] An example with a set of parameters is provided to demonstrate the complete calculation process from the previous step's interval to the control value in this step. Assume a lighting fixture... The system-level collaborative constraint interval is The current operating status of the lighting fixture is Its adjacency set contains two adjacent light fixtures. and ,and , The coupling weight is configured as follows , First, calculate the center points of adjacent intervals: , Substituting into the weighted mean formula yields the neighborhood trend:

[0081] .

[0082] Get scene parameters Calculate the unconstrained extreme points:

[0083] .

[0084] because lie in Internally, after cutting, it becomes After repeating the above process of "neighborhood trend calculation - constrained least squares solution - interval pruning" for each lamp in the system, the control scheme is obtained. Each of the schemes All fall in the corresponding The design also takes into account both the current state and the trends in the surrounding area in terms of numerical values, thereby creating more coherent area lighting in open office areas, a smoother vertical transition in corridor scenes, and more consistent indoor lighting in meeting room scenes.

[0085] S400: Based on the first-order inertial model discretization logic, it calculates the actual control value of each lamp using the target control value, the current operating state, and the preset execution coefficients, and sends it to the corresponding lamp driver interface for adjustment.

[0086] It should be noted that the goal of step S400 is to smoothly implement the calculated target control values ​​onto the physical devices. This process introduces a first-order inertial element to prevent abrupt changes in control commands from causing flickering in the lights or impacting the power grid, thus achieving a soft and natural lighting transition effect. In the previous step, the system has already generated target control values ​​for each light fixture. The target value is within the system-level collaborative constraint range. The stable control results are determined internally. This step implements these target control values ​​into the actual adjustment process of the physical lighting fixtures, so that the lighting state of the fixtures changes gradually according to the control scheme, and maintains overall coordination and consistency when multiple fixtures are executed in parallel. The basic idea used in the execution phase comes from the first-order inertial element model in classical control theory. This model is widely used to describe the process of "system state converging towards target state under finite rate constraints". Its continuous form can be expressed as a first-order linear differential equation. By discretizing this continuous model using the Euler approximation under discrete control cycles, a simple and stable recursive execution relationship can be obtained, which is used to update the operating state of the lighting fixtures between adjacent control cycles.

[0087] Specifically, lighting fixtures The running state before entering the current execution cycle is as follows: The target control value generated in the previous stage is During the deployment phase, the system configures an execution coefficient for the lighting fixture. This is used to characterize the allowable adjustment ratio within a single execution cycle. Based on the state update relationship after discretization of the first-order inertial model, the actual execution control value of the current cycle can be determined. It is represented as a linear interpolation between the current state and the target state, and its calculation is as follows:

[0088] ;

[0089] The above relation is directly derived from the first-order system. Discrete approximation under a fixed sampling period, where This corresponds to the discrete gain, which is determined by both the system time constant and the sampling period. In the formula... This indicates that the power supply will be issued to the lighting fixtures within the current execution cycle. The actual control value, which will be written to the lamp driver interface through the lamp control network; Indicates lighting fixtures The running status before execution is fed back in real time by the lighting control interface and saved in the controller; This represents the target control value, derived from the lighting control scheme output in the previous stage; The execution coefficient is derived from the configuration file or the scenario parameter table issued by the host computer during the deployment phase. Because... , and All are under the same control scale. The difference within the parentheses and the scaling will not introduce scale inconsistency issues. The linear superposition result can be directly used as a control command.

[0090] The logical effect of this execution relationship can be clearly demonstrated by substituting parameters. Taking a light fixture in an office area as an example, let's assume the light fixture's operating state before entering the execution cycle is... The target control value generated in the previous stage is The execution coefficient given in the deployment configuration is Substituting these values ​​into the above formula, we obtain... The results indicate that during the current execution cycle, the actual control value of the luminaire only underwent relatively minor changes and did not jump to the target value all at once. Upon completion of the execution, the operating status of the luminaire will be updated to the new value. In the next execution cycle, the same relation is substituted to calculate the new one. Thus, it gradually approaches the target over multiple cycles. .when and As the difference between them continues to narrow, the above recursive relationship naturally converges, eventually allowing the lighting fixtures to operate stably near the target control value.

[0091] In multi-lighting collaborative scenarios, the system performs the above calculations in parallel for all lights and then returns the results to each light. Simultaneous distribution is achieved through network control. This is due to the generation in the previous stage. Neighborhood consistency and spatial continuity have already been demonstrated within the system-level cooperative constraint interval. The first-order inertial execution in this step will not disrupt this cooperative structure, but rather smoothly map it to the physical execution level. In the corridor scenario, this recursive execution will create a continuous brightness transition in the spatial direction; in the conference room scenario, multiple light fixtures... Proximity, the above relationship will affect the performance of each lamp. Synchronous convergence; in open office areas, different areas Different values ​​can be configured according to comfort requirements to match the adjustment speed with the perceptual characteristics of people. In this way, this step transforms the control scheme into an executable, debuggable, and clearly convergent collaborative lighting adjustment process, realizing the complete implementation from abstract control decisions to actual changes in the luminous state of the lamps.

[0092] In one or more embodiments, such as Figure 2 As shown, an intelligent lighting collaborative control system based on artificial intelligence is disclosed, the system comprising:

[0093] The data acquisition module is used to obtain the current operating status of each lamp, the ambient lighting status of the corresponding area, and the preset lighting engineering parameters;

[0094] The basic constraint generation module is used to generate the basic executable constraint range for each lamp based on the current operating state, the ambient lighting state, and the lighting engineering parameters, and to form a basic executable constraint set.

[0095] The collaborative constraint construction module is used to obtain a preset adjacency list, and use the set of adjacent lamps and coupling weights in the adjacency list to collaboratively prune the basic executable constraint set to generate a system-level collaborative constraint set.

[0096] The control scheme generation module is used to determine the target control value of each lamp by constrained least squares calculation within the limited range of the system-level collaborative constraint set, combined with the current operating state and neighborhood trend value, to form a lighting control scheme.

[0097] The execution adjustment module is used to calculate the actual control value of each lamp based on the first-order inertial model discretization logic, using the target control value, the current operating state, and the preset execution coefficient, and then send it to the corresponding lamp driver interface for adjustment.

[0098] It is worth noting that the specific workflow of the AI-based intelligent lighting collaborative control system provided in this embodiment is the same as that of the AI-based intelligent lighting collaborative control method described in the above embodiments, and will not be repeated here.

[0099] This invention also provides an artificial intelligence-based intelligent lighting coordination control device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements the steps described in the above-described embodiments of the artificial intelligence-based intelligent lighting coordination control method, for example... Figure 1 The steps S1 to S4 described above; or, when the processor executes the computer program, it implements the functions of each module in the above system embodiments.

[0100] For example, the computer program may be divided into one or more modules, which are stored in the memory and executed by the processor to complete the present invention. The one or more modules may be a series of computer program instruction segments capable of performing specific functions, which describe the execution process of the computer program in the AI-based smart lighting collaborative control device.

[0101] The AI-based smart lighting collaborative control device can be a computing device such as a desktop computer, laptop, handheld computer, or cloud server. The AI-based smart lighting collaborative control device may include, but is not limited to, a processor and memory. Those skilled in the art will understand that the AI-based smart lighting collaborative control device may also include input / output devices, network access devices, buses, etc.

[0102] The processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor. The processor is the control center of the AI-based smart lighting collaborative control device, connecting all parts of the device via various interfaces and lines.

[0103] The memory can be used to store the computer programs and / or modules. The processor implements various functions of the AI-based smart lighting collaborative control device by running or executing the computer programs and / or modules stored in the memory, and by calling data stored in the memory. The memory may mainly include a program storage area and a data storage area. The program storage area may store the operating system, at least one application program required for a function, etc.; the data storage area may store data created according to the operation of the controller, etc. In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as hard disk, memory, plug-in hard disk, smart media card (SMC), secure digital card (SD), flash card, at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0104] The modules integrated into the AI-based intelligent lighting collaborative control device, if implemented as software functional units and sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the above embodiments can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc.

[0105] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. The storage medium can be a magnetic disk, optical disk, read-only memory (ROM), or random access memory (RAM), etc.

[0106] The above description represents the preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of the present invention, and these improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A smart lighting collaborative control method based on artificial intelligence, characterized in that, The method includes: Obtain the current operating status of each lamp, the ambient lighting status of the corresponding area, and the preset lighting engineering parameters; Based on the current operating state, the ambient lighting state, and the lighting engineering parameters, a basic executable constraint interval is generated for each lamp, and all the basic executable constraint intervals constitute a basic executable constraint set. Obtain a preset adjacency list, which records the set of adjacent lamps and the corresponding coupling weights for each lamp; Using the set of adjacent lamps, the coupling weights, and the set of basic executable constraints, the basic executable constraint interval of each lamp is collaboratively pruned to generate a system-level collaborative constraint interval for each lamp. All the system-level collaborative constraint intervals constitute a system-level collaborative constraint set. Within the system-level collaborative constraint range of each lamp, the target control value of each lamp is determined by constrained least squares calculation, combining the current operating state and neighborhood trend value, to form a lighting control scheme. Based on the first-order inertial model discretization logic, the actual control value of each lamp is calculated using the target control value, the current operating state, and the preset execution coefficient, and then sent to the corresponding lamp driver interface for adjustment.

2. The intelligent lighting collaborative control method based on artificial intelligence according to claim 1, characterized in that, The specific steps for generating the basic executable constraint interval for each lamp include: Map the ambient lighting state to a control scale consistent with the current operating state; The mapped ambient lighting state and the current operating state are weighted and combined according to a preset ratio to obtain a combined mapping value; Read the minimum allowable adjustment boundary, the maximum allowable adjustment boundary, and the allowable offset range per single cycle from the lighting engineering parameters; Centered on the combined mapping value, and in conjunction with the minimum allowable adjustment boundary, the maximum allowable adjustment boundary, and the single-cycle allowable offset range, the lower and upper boundaries of the basic executable constraint interval are determined.

3. The intelligent lighting collaborative control method based on artificial intelligence according to claim 2, characterized in that, The lighting engineering parameters also include scene mode parameters, which are used to adjust the relative weight ratio of the current running state deviation term and the neighborhood trend value deviation term in the constrained least squares calculation.

4. The intelligent lighting collaborative control method based on artificial intelligence according to claim 1, characterized in that, The specific steps for collaboratively pruning the basic executable constraint interval of each lamp using the adjacent lamp set, the coupling weight, and the basic executable constraint set include: Read the allowable offset range for a single cycle from the lighting engineering parameters; Iterate through the set of adjacent lamps for each lamp, and for each adjacent lamp, calculate the interval expansion amplitude by multiplying the coupling weight by the single-cycle allowable offset range; Using the aforementioned range expansion, the basic executable constraint range of the adjacent lamps is symmetrically expanded to obtain a compatible range; Perform interval intersection operation between the basic executable constraint interval of the lamp itself and the compatible intervals corresponding to all the adjacent lamps; The maximum value of all lower boundaries in the intersection operation result of the interval is taken as the new lower boundary, and the minimum value of all upper boundaries is taken as the new upper boundary, thus obtaining the system-level collaborative constraint interval.

5. The intelligent lighting collaborative control method based on artificial intelligence according to claim 4, characterized in that, The adjacency list is stored in the controller configuration file or the host computer configuration table. The adjacency list is configured according to the grid division of the lighting area, the definition of the workstation area, or the connection relationship of the corridor.

6. The intelligent lighting collaborative control method based on artificial intelligence according to claim 1, characterized in that, The steps for calculating the neighborhood trend value include: Read the center point of the system-level collaborative constraint interval for each adjacent lamp in the adjacent lamp set, where the center point is the average of the lower and upper boundaries of the system-level collaborative constraint interval; The neighborhood trend value is obtained by using the coupling weight to calculate the weighted average of the center point.

7. The intelligent lighting collaborative control method based on artificial intelligence according to claim 1, characterized in that, The specific steps for determining the target control value for each lamp through constrained least squares calculation include: Construct a cost function, which includes a weighted sum of a first deviation square and a second deviation square, wherein the first deviation square is the square of the difference between the candidate control value and the current operating state, and the second deviation square is the square of the difference between the candidate control value and the neighborhood trend value. The constraint condition is set such that the candidate control value must be within the system-level collaborative constraint interval; Find the extreme points of the cost function under unconstrained conditions; Determine whether the extreme point is located within the system-level collaborative constraint interval. If the extreme point is located within the system-level collaborative constraint interval, then the extreme point is determined as the target control value. If the extreme point is less than the lower boundary of the system-level collaborative constraint interval, then the lower boundary is determined as the target control value. If the extreme point is greater than the upper boundary of the system-level collaborative constraint interval, then the upper boundary is determined as the target control value.

8. The intelligent lighting collaborative control method based on artificial intelligence according to claim 1, characterized in that, The specific steps for calculating the actual control value of each lamp based on the first-order inertial model discretization logic include: Calculate the difference between the target control value and the current operating state; Multiply the difference by the execution coefficient to obtain the adjustment increment; The current operating state is added to the adjustment increment to obtain the actual control value; The actual control value is written into the lighting driver interface, and the current operating status of the next cycle is updated to the actual control value.

9. The intelligent lighting collaborative control method based on artificial intelligence according to claim 1, characterized in that, The ambient lighting status is obtained by an ambient lighting acquisition device set in the lighting area, which includes an illuminance sensor or a color temperature sensor.

10. An intelligent lighting collaborative control system based on artificial intelligence, characterized in that, The system includes: The data acquisition module is used to obtain the current operating status of each lamp, the ambient lighting status of the corresponding area, and the preset lighting engineering parameters; The basic constraint generation module is used to generate the basic executable constraint range for each lamp based on the current operating state, the ambient lighting state, and the lighting engineering parameters, and to form a basic executable constraint set. The collaborative constraint construction module is used to obtain a preset adjacency list, and use the set of adjacent lamps and coupling weights in the adjacency list to collaboratively prune the basic executable constraint set to generate a system-level collaborative constraint set. The control scheme generation module is used to determine the target control value of each lamp by constrained least squares calculation within the limited range of the system-level collaborative constraint set, combined with the current operating state and neighborhood trend value, to form a lighting control scheme. The execution adjustment module is used to calculate the actual control value of each lamp based on the first-order inertial model discretization logic, using the target control value, the current operating state, and the preset execution coefficient, and then send it to the corresponding lamp driver interface for adjustment.

Images