Regional lighting control method and system

Abstract

The present invention relates to the field of lighting control and discloses a regional lighting control method and system. The method comprises: obtaining device status information, light intensity, and occupant image information for each sub-area of ​​a target area; determining the sub-area based on the building layout and functional use of the target area; identifying the occupant activity type and location based on occupant image data; obtaining the static lighting requirements for each sub-area of ​​the target area; the static lighting requirements including brightness value and color temperature; inputting the occupant location, activity type, light intensity, and static lighting requirements for each sub-area into a lighting demand prediction model; the lighting demand prediction model outputs the expected lighting requirements for each sub-area; and generating a lighting control strategy based on the expected lighting requirements for each sub-area, combined with lighting comfort and lighting equipment life, as an optimization target. This method has the following effects: meeting the lighting requirements of occupants in different activity scenarios.

Description

Technical Field

[0001] The present invention relates to the field of lighting control, and in particular to a method and system for regional lighting control. Background Art

[0002] With the continuous development of intelligent buildings and green energy-saving concepts, lighting control systems are evolving towards intelligentization. Traditional regional lighting control is usually managed by unified settings or timed switches.

[0003] In recent years, intelligent lighting systems based on sensor networks and image recognition have gradually emerged. However, such systems often only consider whether there are people or no people, ignoring the differentiated impact of the specific types of activities of people in different scenarios on lighting needs.

[0004] How to solve the above technical problems is a technical difficulty that needs to be overcome by those skilled in the art. Summary of the Invention

[0005] The present invention provides a method and system for controlling regional lighting to at least partially solve the above technical problems.

[0006] In a first aspect, in order to solve the above technical problems, the present invention provides a method for controlling regional lighting, comprising:

[0007] Obtaining device status information, light intensity, and personnel image information for each sub-area of ​​the target area; the sub-areas are determined based on the building layout and functional use of the target area;

[0008] identifying a person's activity type and a person's location based on the person image data;

[0009] Obtaining static lighting requirements of each sub-area of ​​the target area; the static lighting requirements include brightness value and color temperature;

[0010] Inputting the personnel positions, personnel activity types, light intensity and static lighting requirements of each sub-area into a lighting demand prediction model; the lighting demand prediction model outputs the expected lighting requirements of each sub-area;

[0011] Generate lighting control strategies based on the expected lighting needs of each sub-area combined with lighting comfort and lighting equipment life as optimization goals;

[0012] The lighting control strategy is converted into a control instruction and sent to the lighting control terminal. The lighting control terminal controls the operation of the lighting equipment in each sub-area based on the control instruction.

[0013] In an optional embodiment, a lighting control strategy is generated based on the expected lighting demand of each sub-area in combination with lighting comfort and lighting equipment life as an optimization goal, including:

[0014] Constructing a lighting comfort evaluation function; the lighting comfort evaluation function evaluates the lighting comfort of each sub-area based on illumination uniformity, glare index, and color temperature adaptability;

[0015] Obtain the cumulative operating time, number of on / off times, load status, and historical maintenance records of lighting equipment in each sub-area to assess the life loss rate of lighting equipment;

[0016] Calculate lighting energy consumption for each sub-area based on expected lighting demand;

[0017] The lighting energy consumption, lighting comfort evaluation results and equipment life loss rate are weighted and combined to form a multi-objective optimization function;

[0018] Setting optimization variables; the optimization variables include the brightness setting value, color temperature setting value and dimming rate of each sub-area;

[0019] Setting optimization constraints, wherein the optimization constraints include a minimum illumination threshold, a maximum allowable color temperature range, and a maximum number of switches per day;

[0020] The multi-objective optimization function is iteratively solved to obtain the optimal lighting control parameter combination.

[0021] In an optional embodiment, iteratively solving the multi-objective optimization function to obtain an optimal lighting control parameter combination as a lighting control strategy includes:

[0022] S301. Set the number of particles, search space dimension, inertia weight, individual learning factor, and social learning factor. The number of particles represents the total number of particles simultaneously participating in the optimization in the search space. The position of each particle represents a combination of the brightness setting value, color temperature setting value, and dimming rate of a group of subregions. The search space dimension corresponds to the brightness setting value, color temperature setting value, and dimming rate of each subregion. The inertia weight is initially set to 0.8 to enhance global exploration capability, and is gradually reduced to 0.4 in subsequent iterations to accelerate convergence. The individual learning factor and the social learning factor are both set to 1.5 to adjust the particle's dependence on its own historical optimal solution and the group optimal solution.

[0023] S302. Calculate the corresponding multi-objective optimization function value for each particle position, which is recorded as a fitness value; wherein the multi-objective optimization function value is obtained by weighted summation of the lighting energy consumption value, the lighting comfort evaluation result, and the equipment life loss rate;

[0024] S303: If the fitness value of the current particle position is higher than its historical optimal position, the individual optimal solution of the particle is updated to the current particle position; if the fitness value of the current particle position is higher than the optimal solution of the entire particle group, the group optimal solution is updated to the current particle position;

[0025] S304, adjusting the moving speed of the particle in the search space according to the inertia weight, the guiding direction of the individual optimal solution and the group optimal solution;

[0026] Repeat S301-S304 until the preset maximum number of iterations is reached to obtain the optimal lighting control parameter combination.

[0027] In an optional embodiment, the construction of the multi-objective optimization function further includes:

[0028] Obtaining real-time electricity price data for the target area's power grid; the real-time electricity price data includes peak and valley time periods, electricity prices for each time period, and tiered pricing thresholds;

[0029] Based on the expected lighting demand and real-time electricity price data of each sub-area, calculate the electricity cost and total energy consumption cost under different lighting control parameter combinations;

[0030] Setting energy-saving target constraints, including the upper limit of total energy consumption per day, the maximum allowable energy consumption ratio during peak power hours, and the tiered electricity price warning power consumption;

[0031] The electricity cost and total energy consumption cost of the period are weightedly combined with the lighting energy consumption, lighting comfort evaluation results and equipment life loss rate to form a multi-objective optimization function.

[0032] In an optional embodiment, the method further includes:

[0033] Based on the building layout and functional use of the target area, each sub-area is divided into a first area and a second area; the first area includes office areas, meeting areas, and exhibition areas; the second area includes corridors, entrances, and stairwells;

[0034] When a person is detected entering the first area, the image information of the person collected by the camera is analyzed to determine the type of activity. When a person is detected entering the second area, the infrared pyroelectric sensor is used to identify the person's position and movement direction and set the activity type to passage.

[0035] Static lighting requirement parameters are set for the first area and the second area respectively.

[0036] In an optional embodiment, the method further includes:

[0037] Get the average stay time of people in each sub-area;

[0038] For each pair of adjacent sub-regions, the current brightness value and color temperature value are obtained respectively, and the illumination difference and color temperature difference between the adjacent sub-regions are calculated;

[0039] Calculating a visual adaptation evaluation value when moving from one sub-area to another sub-area based on the illuminance difference, the color temperature difference, and the average residence time;

[0040] Traverse all the paths that people move between different sub-areas and the frequency of people flow on each path, and take a weighted average of all visual adaptation evaluation values ​​to obtain the overall visual adaptation index;

[0041] When constructing the lighting comfort evaluation function, the lighting comfort of each sub-area is evaluated based on the visual adaptation index, illumination uniformity, glare index and color temperature adaptability.

[0042] In an optional embodiment, the method further includes:

[0043] Constructing a lighting equipment life prediction model, the input of which includes historical operating data of lighting equipment in each sub-area, current load status, cumulative number of switching times, operating environment temperature and humidity, power supply voltage fluctuation amplitude, and lamp aging coefficient; the lighting equipment life prediction model predicts the aging trend and remaining service life of the equipment;

[0044] Generates a device health score based on the prediction results; triggers a maintenance alert when the device health score falls below a preset threshold;

[0045] When generating a lighting control strategy, the usage frequency of lighting devices with low health status scores is reduced, and the lighting load is distributed to lighting devices with high health status scores to achieve load balancing.

[0046] Specifically, the equipment health status score generated based on the prediction results can be obtained in the following ways: obtaining the prediction results from the equipment status prediction model. The prediction results include but are not limited to at least one of the following: the probability of future equipment failure, the remaining service life of the equipment, and the abnormal level of the key parameters of the equipment; according to the type and distribution characteristics of the prediction results, select the corresponding scoring mapping method to convert the prediction results into a quantitative score value between 0 and 100 points. Commonly used mapping methods include: linear mapping method can be used to quantify the prediction results into the remaining service life of the equipment; equipment health status score , where P is the remaining service life, Min is the minimum value within the acceptable range; Max is the upper limit of the equipment life; the equipment health status score can also be obtained by segmenting the abnormality level of the key parameters of the equipment, and different abnormality levels correspond to different scores.

[0047] In a second aspect, the present invention provides an area lighting control system, comprising:

[0048] The first processing module is configured to obtain device status information, light intensity, and personnel image information of each sub-area of ​​the target area; the sub-areas are determined based on the building layout and functional use of the target area;

[0049] A second processing module is configured to: identify a person's activity type and a person's location based on the person image data;

[0050] The third processing module is configured to obtain static lighting requirements of each sub-area of ​​the target area, wherein the static lighting requirements include brightness value and color temperature;

[0051] A fourth processing module is configured to input the occupant positions, occupant activity types, light intensity, and static lighting requirements of each sub-area into a lighting demand prediction model; the lighting demand prediction model outputs an expected lighting requirement for each sub-area;

[0052] A fifth processing module is configured to generate a lighting control strategy based on the expected lighting demand of each sub-area in combination with lighting comfort and lighting equipment life as an optimization target;

[0053] The sixth processing module is configured to convert the lighting control strategy into a control instruction and send the instruction to the lighting control terminal, and the lighting control terminal controls the operation of the lighting equipment in each sub-area based on the control instruction.

[0054] Compared with the prior art, the present invention has at least the following beneficial effects: meeting the lighting needs of people in different activity scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 is a flow chart of a method for controlling regional lighting provided by the first embodiment of the present invention;

[0056] Figure 2 This is a block diagram of a regional lighting control system provided by the second embodiment of the present invention. DETAILED DESCRIPTION

[0057] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0058] Reference Figure 1A first embodiment of the present invention provides a method for controlling regional lighting, comprising the following steps:

[0059] S101: Obtain device status information, light intensity, and occupant image information for each sub-area of ​​a target area. The sub-areas are determined based on the building layout and functional use of the target area. Specifically, a target area is an area requiring lighting control, such as an office building, a shopping mall, or a school.

[0060] Sub-areas are used to divide units based on the building layout and functional use of the target area.

[0061] S102: Identify the activity type and location of a person based on the person image data.

[0062] S103: Obtain static lighting requirements for each sub-area of ​​the target area; the static lighting requirements include brightness and color temperature. Specifically, static lighting requirements are pre-defined basic lighting requirements based on the functional use of the sub-area, including appropriate brightness and color temperature. For example, an office area may require higher brightness and a cool color temperature, while a rest area may require lower brightness and a warm color temperature.

[0063] S104: Inputting the personnel positions, personnel activity types, light intensity, and static lighting requirements of each sub-area into a lighting demand prediction model; the lighting demand prediction model outputs the expected lighting requirements of each sub-area;

[0064] S105, generating a lighting control strategy based on the expected lighting demand of each sub-area combined with lighting comfort and lighting equipment life as an optimization target;

[0065] S106: Convert the lighting control strategy into a control instruction and send it to the lighting control terminal. The lighting control terminal controls the operation of the lighting equipment in each sub-area based on the control instruction.

[0066] Specifically, the target area is divided into various sub-areas, and the device status information, light intensity, and personnel image information of the sub-areas are obtained. By analyzing the personnel image information, the activity type and location of the personnel are identified. Combined with the predetermined static lighting requirements of each sub-area, this data is input into the lighting demand prediction model to predict the expected lighting needs of each sub-area. Taking lighting comfort and lighting equipment life as optimization goals, a lighting control strategy is generated based on the expected lighting needs. The control strategy is converted into control instructions and sent to the lighting control terminal to control the lighting equipment. The lighting control strategy takes into account both lighting comfort to meet the lighting needs of personnel in different activity scenarios and the life of the lighting equipment, avoiding damage caused by frequent and unreasonable adjustments of the equipment. Compared with traditional fixed lighting modes, it can effectively reduce energy consumption and reduce unnecessary lighting on time; at the same time, it improves the activity experience of personnel in the target area.

[0067] In one embodiment, human activity types include office work, meetings, phone conversations, exhibition presentations, and walking around. Many cameras now have built-in image analysis and recognition capabilities, allowing direct access to the camera's analysis results. If custom functionality is required, the camera's image information combined with a pose estimation algorithm (such as OpenPose) can be used to analyze body movements and interactions with surrounding objects to determine the human activity type.

[0068] In one embodiment, the method further comprises:

[0069] Based on the building layout and functional use of the target area, each sub-area is divided into a first area and a second area; the first area includes office areas, meeting areas, and exhibition areas; the second area includes corridors, entrances, and stairwells;

[0070] When a person is detected entering the first area, the image information of the person collected by the camera is analyzed to determine the type of activity. When a person is detected entering the second area, the infrared pyroelectric sensor is used to identify the person's position and movement direction and set the activity type to passage.

[0071] Static lighting requirement parameters are set for the first area and the second area respectively.

[0072] Specifically, cameras analyze human body movements and object interactions in the first area (offices, conference rooms, exhibition areas, etc.). Infrared pyroelectric sensors capture the real-time location and direction of movement of people in the second area (corridors, entrances, stairwells, etc.), setting the "pass" activity type and triggering dynamic lighting strategies. Independent static lighting demand parameters are set for each area, meeting the lighting needs of complex activities in the first area while reducing costs through low-power sensing control in the second area. Static lighting demand parameters are the parameters for static lighting requirements. As mentioned above, these include brightness and color temperature values.

[0073] In one embodiment, a lighting control strategy is generated based on the expected lighting demand of each sub-area in combination with lighting comfort and lighting equipment life as an optimization goal, including:

[0074] A lighting comfort evaluation function is constructed; this function evaluates the lighting comfort of each sub-area based on illumination uniformity, glare index, and color temperature adaptability. Specifically, the lighting comfort evaluation function uses three core indicators: illumination uniformity (the uniformity of illumination values ​​at each point in the area; higher values ​​indicate more balanced light distribution); glare index (a measure of the degree to which strong light causes discomfort to the human eye; lower values ​​indicate better visual comfort); and color temperature adaptability (the degree to which the lighting color temperature matches the function of the scene, such as 5000K cool white light for office scenes and 3000K warm yellow light for rest scenes). This function comprehensively evaluates whether the sub-area lighting meets human visual comfort needs.

[0075] The cumulative operating time, number of on-off cycles, load status, and historical maintenance records of lighting equipment in each sub-area are collected to assess the equipment's lifespan loss rate. Specifically, the equipment lifespan loss rate is a quantitative indicator of the aging of lighting equipment. It assesses the current equipment lifespan degradation by analyzing the cumulative operating time (the total operating hours of the equipment since its commissioning), the number of on-off cycles (frequent starting and stopping accelerates the wear of electronic components), the load status (long-term overloaded operation shortens the lifespan), and historical maintenance records (maintenance frequency and quality affect equipment health).

[0076] Calculate lighting energy consumption for each sub-area based on expected lighting demand;

[0077] The lighting energy consumption, lighting comfort evaluation results and equipment life loss rate are weighted and combined to form a multi-objective optimization function. Specifically, the multi-objective optimization function is a comprehensive optimization model formed by weighting the three objective functions of lighting energy consumption, lighting comfort evaluation results and equipment life loss rate.

[0078] Setting optimization variables; the optimization variables include the brightness setting value, color temperature setting value and dimming rate of each sub-area;

[0079] Setting optimization constraints, wherein the optimization constraints include a minimum illumination threshold, a maximum allowable color temperature range, and a maximum number of switches per day;

[0080] The multi-objective optimization function is iteratively solved to obtain the optimal lighting control parameter combination.

[0081] Specifically, the lighting comfort evaluation function based on illumination uniformity, glare index and color temperature adaptability can dynamically adjust light distribution and color temperature according to the type of personnel activities. For example, the office area automatically adapts to 5000K cool white light to meet the needs of concentration, and the rest area switches to 2800K warm light to create a relaxing atmosphere and improve visual comfort. The life loss rate is evaluated by the cumulative operating time and number of switches of the equipment, and combined with constraints such as the maximum number of switches per day, frequent start and stop and overload operation are avoided. The energy consumption is calculated according to the expected lighting demand and integrated into the multi-objective optimization function, and the brightness set value and dimming rate are adjusted to strike a balance between energy saving, comfort and equipment protection.

[0082] In one embodiment, iteratively solving the multi-objective optimization function to obtain an optimal lighting control parameter combination as a lighting control strategy includes:

[0083] S301. Set the number of particles, search space dimension, inertia weight, individual learning factor, and social learning factor. The number of particles represents the total number of particles simultaneously participating in the optimization in the search space. The position of each particle represents the combination of the brightness setting value, color temperature setting value, and dimming rate for a group of subregions. The search space dimension corresponds to the brightness setting value, color temperature setting value, and dimming rate for each subregion. The inertia weight is initially set to 0.8 to enhance global exploration and is gradually reduced to 0.4 in subsequent iterations to accelerate convergence. The individual learning factor and social learning factor are both set to 1.5 to adjust the particle's dependence on its own historical optimal solution and the group optimal solution. Specifically, the search space dimension is the number of variables in the optimization problem. Each subregion has three optimization variables (brightness, color temperature, and dimming rate). If there are n subregions, the search space dimension is 3n. The inertia weight controls the degree to which a particle retains its previous velocity. A larger weight (e.g., an initial value of 0.8) facilitates global search, while a smaller weight (e.g., a final value of 0.4) facilitates local precision.

[0084] S302. Calculate the corresponding multi-objective optimization function value for each particle position, denoted as the fitness value. The multi-objective optimization function value is a weighted sum of the lighting energy consumption value, the lighting comfort evaluation result, and the equipment life loss rate. Specifically, the fitness value is an indicator for evaluating the quality of the particle position and is calculated using the multi-objective optimization function.

[0085] S303: If the fitness value of the current particle position is higher than its historical optimal position, the individual optimal solution of the particle is updated to the current particle position; if the fitness value of the current particle position is higher than the optimal solution of the entire particle group, the group optimal solution is updated to the current particle position;

[0086] S304, adjusting the moving speed of the particle in the search space according to the inertia weight, the guiding direction of the individual optimal solution and the group optimal solution;

[0087] Repeat S301-S304 until the preset maximum number of iterations is reached to obtain the optimal lighting control parameter combination.

[0088] Specifically, a high initial inertia weight enables particles to explore the solution space extensively, avoiding local optima. As iterations progress, the weight is reduced to 0.4, allowing the algorithm to focus its search near the optimal region. By comprehensively considering energy consumption, comfort, and device lifespan through a fitness function, the particle swarm algorithm automatically finds the optimal balance between the three. For example, comfort requirements are prioritized during busy hours, while energy conservation and device protection are emphasized during unoccupied periods.

[0089] In one embodiment, the construction of the multi-objective optimization function further includes:

[0090] Obtaining real-time electricity price data for the target area's power grid; the real-time electricity price data includes peak and valley time periods, electricity prices for each time period, and tiered pricing thresholds;

[0091] Based on the expected lighting demand and real-time electricity price data of each sub-area, calculate the electricity cost and total energy consumption cost under different lighting control parameter combinations;

[0092] Setting energy-saving target constraints, including the upper limit of total energy consumption per day, the maximum allowable energy consumption ratio during peak power hours, and the tiered electricity price warning power consumption;

[0093] The electricity cost and total energy consumption cost of the period are weightedly combined with the lighting energy consumption, lighting comfort evaluation results and equipment life loss rate to form a multi-objective optimization function.

[0094] Specifically, based on peak-valley time periods and a tiered pricing mechanism, the system can moderately increase the operating power of equipment in non-critical areas during low-price periods to meet potential demand, while dynamically reducing non-essential lighting energy consumption during peak hours, thereby reducing electricity costs. By weightedly optimizing time-of-day electricity costs, total energy costs, and existing comfort and equipment life targets, energy efficiency is improved while ensuring lighting comfort and equipment health.

[0095] In one embodiment, the method further comprises:

[0096] Get the average stay time of people in each sub-area;

[0097] For each pair of adjacent sub-regions, the current brightness value and color temperature value are obtained respectively, and the illumination difference and color temperature difference between the adjacent sub-regions are calculated;

[0098] Calculating a visual adaptation evaluation value when moving from one sub-area to another sub-area based on the illuminance difference, the color temperature difference, and the average residence time;

[0099] Traverse all the paths that people move between different sub-areas and the frequency of people flow on each path, and take a weighted average of all visual adaptation evaluation values ​​to obtain the overall visual adaptation index;

[0100] When constructing the lighting comfort evaluation function, the lighting comfort of each sub-area is evaluated based on the visual adaptation index, illumination uniformity, glare index and color temperature adaptability.

[0101] Specifically, the visual adaptation evaluation value is calculated based on the average stay time of people, the illumination and color temperature differences between adjacent sub-areas, and the overall visual adaptation index is generated by combining the frequency weighting of the people's flow path, effectively avoiding visual fatigue caused by sudden changes in light; after integrating the visual adaptation index into the lighting comfort evaluation function, the system can dynamically adjust the lighting parameters of adjacent areas to ensure a natural transition of light during the movement of people, significantly improving spatial coherence and visual comfort.

[0102] The visual adaptation rating is used to assess the visual adaptation difficulty experienced by a person when moving between two sub-areas with different lighting conditions. A larger visual adaptation rating indicates a greater adaptation difficulty, while a smaller visual adaptation rating indicates a smaller adaptation difficulty. The visual adaptation rating is based on the illuminance difference ΔL and color temperature difference ΔC between adjacent sub-areas, as well as the dwell time t. , is the average illuminance of the starting sub-area; L2 is the average illuminance of the target sub-area. For example, if you enter a corridor with an illuminance of 300 lux from an office with an illuminance of 500 lux, ΔL=200 lux. ; is the average color temperature of the starting sub-area, C2 is the average color temperature of the target sub-area, for example, when entering a lounge with a color temperature of 3000K from an office area with a color temperature of 6000K, ΔC=3000K; the average residence time t represents the average residence time of a person in the target sub-area, which is used to reflect the time factor of the visual adaptation process. The longer the average residence time t is, the smaller the visual adaptation evaluation value is. In one implementation, the visual adaptation evaluation value is , is the brightness change weight coefficient, which is a constant; is the color temperature change weight coefficient, which is a constant; is the visual adaptation time constant, which is a constant; Used to indicate initial visual impact, It indicates that over time, the human eye gradually adapts to the new environment and the discomfort is reduced.

[0103] In order to evaluate the visual adaptation comfort between all lighting sub-areas in a building space, a weighted average method based on path traversal and personnel flow frequency is used to calculate the overall visual adaptation index; for all possible movement paths between sub-areas, the corresponding VAD value and the personnel flow frequency of the path are calculated respectively, and then a weighted average is performed according to the frequency to obtain the overall visual adaptation index (GVAI) of the entire space. In one implementation method, all possible paths between sub-areas are traversed, and the corresponding VAD value is calculated for each path; the personnel flow frequency of each path is counted. And calculate the total flow F, , the personnel flow frequency on each path can be obtained by collecting image data through a camera device; ;Will Converted to the global visual adaptation index GVAI, in one implementation, When GVAI is close to 1, it indicates that the overall visual comfort of the environment is high; when GVAI is close to 0, it indicates that the overall visual adaptation is poor.

[0104] In one embodiment, the method further comprises:

[0105] Constructing a lighting equipment life prediction model, the input of which includes historical operating data of lighting equipment in each sub-area, current load status, cumulative number of switching times, operating environment temperature and humidity, power supply voltage fluctuation amplitude, and lamp aging coefficient; the lighting equipment life prediction model predicts the aging trend and remaining service life of the equipment;

[0106] Generates a device health score based on the prediction results; triggers a maintenance alert when the device health score falls below a preset threshold;

[0107] When generating a lighting control strategy, the usage frequency of lighting devices with low health status scores is reduced, and the lighting load is distributed to lighting devices with high health status scores to achieve load balancing.

[0108] Reference Figure 2 A second embodiment of the present invention provides a regional lighting control system, comprising:

[0109] The first processing module is configured to obtain device status information, light intensity, and personnel image information of each sub-area of ​​the target area; the sub-areas are determined based on the building layout and functional use of the target area;

[0110] A second processing module is configured to: identify a person's activity type and a person's location based on the person image data;

[0111] The third processing module is configured to obtain static lighting requirements of each sub-area of ​​the target area, wherein the static lighting requirements include brightness value and color temperature;

[0112] A fourth processing module is configured to input the occupant positions, occupant activity types, light intensity, and static lighting requirements of each sub-area into a lighting demand prediction model; the lighting demand prediction model outputs an expected lighting requirement for each sub-area;

[0113] A fifth processing module is configured to generate a lighting control strategy based on the expected lighting demand of each sub-area in combination with lighting comfort and lighting equipment life as an optimization target;

[0114] The sixth processing module is configured to convert the lighting control strategy into a control instruction and send the instruction to the lighting control terminal, and the lighting control terminal controls the operation of the lighting equipment in each sub-area based on the control instruction.

[0115] It should be noted that an area lighting control system provided by an embodiment of the present invention is used to execute all the process steps of an area lighting control method of the above embodiment. The working principles and beneficial effects of the two correspond one to one, and thus will not be described in detail.

[0116] The specific embodiments described above further illustrate the objectives, technical solutions, and beneficial effects of the present invention. It should be understood that the above descriptions are merely specific embodiments of the present invention and are not intended to limit the scope of protection of the present invention. In particular, it should be noted that any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included within the scope of protection of the present invention for those skilled in the art.

Claims

1. A method for controlling regional lighting, characterized in that: include: Obtaining device status information, light intensity, and personnel image information for each sub-area of ​​the target area; the sub-areas are determined based on the building layout and functional use of the target area; identifying the activity type and location of the person based on the person image information; Obtaining static lighting requirements of each sub-area of ​​the target area; the static lighting requirements include brightness value and color temperature; Inputting the personnel positions, personnel activity types, light intensity and static lighting requirements of each sub-area into a lighting demand prediction model; the lighting demand prediction model outputs the expected lighting requirements of each sub-area; Generate lighting control strategies based on the expected lighting needs of each sub-area combined with lighting comfort and lighting equipment life as optimization goals; Converting the lighting control strategy into a control instruction and sending it to the lighting control terminal, which controls the operation of the lighting equipment in each sub-area based on the control instruction; Based on the expected lighting needs of each sub-area, combined with lighting comfort and lighting equipment life, a lighting control strategy is generated for optimization goals, including: Constructing a lighting comfort evaluation function; the lighting comfort evaluation function evaluates the lighting comfort of each sub-area based on illumination uniformity, glare index, and color temperature adaptability; Obtain the cumulative operating time, number of on / off times, load status, and historical maintenance records of lighting equipment in each sub-area to assess the life loss rate of lighting equipment; Calculate lighting energy consumption for each sub-area based on expected lighting demand; The lighting energy consumption, lighting comfort evaluation results and equipment life loss rate are weighted and combined to form a multi-objective optimization function; Setting optimization variables; the optimization variables include the brightness setting value, color temperature setting value and dimming rate of each sub-area; Setting optimization constraints, wherein the optimization constraints include a minimum illumination threshold, a maximum allowable color temperature range, and a maximum number of switches per day; Iteratively solving the multi-objective optimization function to obtain an optimal lighting control parameter combination; iteratively solving the multi-objective optimization function to obtain an optimal lighting control parameter combination as a lighting control strategy, including: S301. Set the number of particles, search space dimension, inertia weight, individual learning factor, and social learning factor. The number of particles represents the total number of particles simultaneously participating in the optimization in the search space. The position of each particle represents a combination of the brightness setting value, color temperature setting value, and dimming rate of a group of subregions. The search space dimension corresponds to the brightness setting value, color temperature setting value, and dimming rate of each subregion. The inertia weight is initially set to 0.8 to enhance global exploration capability, and is gradually reduced to 0.4 in subsequent iterations to accelerate convergence. The individual learning factor and the social learning factor are both set to 1.5 to adjust the particle's dependence on its own historical optimal solution and the group optimal solution. S302. Calculate the corresponding multi-objective optimization function value for each particle position, which is recorded as a fitness value; wherein the multi-objective optimization function value is obtained by weighted summation of the lighting energy consumption value, the lighting comfort evaluation result, and the equipment life loss rate; S303: If the fitness value of the current particle position is higher than its historical optimal position, the individual optimal solution of the particle is updated to the current particle position; if the fitness value of the current particle position is higher than the optimal solution of the entire particle group, the group optimal solution is updated to the current particle position; S304, adjusting the moving speed of the particle in the search space according to the inertia weight, the guiding direction of the individual optimal solution and the group optimal solution; Repeat S301-S304 until a preset maximum number of iterations is reached to obtain the optimal lighting control parameter combination; The construction of the multi-objective optimization function also includes: Obtaining real-time electricity price data for the target area's power grid; the real-time electricity price data includes peak and valley time periods, electricity prices for each time period, and tiered pricing thresholds; Based on the expected lighting demand and real-time electricity price data of each sub-area, calculate the electricity cost and total energy consumption cost under different lighting control parameter combinations; Setting energy-saving target constraints, including the upper limit of total energy consumption per day, the maximum allowable energy consumption ratio during peak hours, and the tiered electricity price warning power consumption; The electricity cost and total energy consumption cost of the period are weightedly combined with the lighting energy consumption, lighting comfort evaluation results and equipment life loss rate to form a multi-objective optimization function.

2. The method for controlling regional lighting according to claim 1, wherein: The method further comprises: Based on the building layout and functional use of the target area, each sub-area is divided into a first area and a second area; the first area includes office areas, meeting areas, and exhibition areas; the second area includes corridors, entrances, and stairwells; When a person is detected entering the first area, the image information of the person collected by the camera is analyzed to determine the type of activity. When a person is detected entering the second area, the infrared pyroelectric sensor is used to identify the person's position and movement direction and set the activity type to passage. Static lighting requirement parameters are set for the first area and the second area respectively.

3. The method for controlling regional lighting according to claim 2, wherein: The method further comprises: Get the average stay time of people in each sub-area; For each pair of adjacent sub-regions, the current brightness value and color temperature value are obtained respectively, and the illumination difference and color temperature difference between the adjacent sub-regions are calculated; Calculating a visual adaptation evaluation value when moving from one sub-area to another sub-area based on the illuminance difference, the color temperature difference, and the average residence time; Traverse all the paths that people move between different sub-areas and the frequency of people flow on each path, and take a weighted average of all visual adaptation evaluation values ​​to obtain the overall visual adaptation index; When constructing the lighting comfort evaluation function, the lighting comfort of each sub-area is evaluated based on the visual adaptation index, illumination uniformity, glare index and color temperature adaptability.

4. The method for controlling regional lighting according to claim 3, wherein: The method further comprises: Constructing a lighting equipment life prediction model, the input of which includes historical operating data of lighting equipment in each sub-area, current load status, cumulative number of switching times, operating environment temperature and humidity, power supply voltage fluctuation amplitude, and lamp aging coefficient; the lighting equipment life prediction model predicts the aging trend and remaining service life of the equipment; Generates a device health score based on the prediction results; triggers a maintenance alert when the device health score falls below a preset threshold; When generating a lighting control strategy, the usage frequency of lighting devices with low health status scores is reduced, and the lighting load is distributed to lighting devices with high health status scores to achieve load balancing.

5. A regional lighting control system, used to implement the method according to any one of claims 1 to 4, characterized in that: include: The first processing module is configured to obtain device status information, light intensity, and personnel image information of each sub-area of ​​the target area; the sub-areas are determined based on the building layout and functional use of the target area; A second processing module is configured to: identify the activity type and location of a person based on the person image information; The third processing module is configured to obtain static lighting requirements of each sub-area of ​​the target area, wherein the static lighting requirements include brightness value and color temperature; A fourth processing module is configured to input the occupant positions, occupant activity types, light intensity, and static lighting requirements of each sub-area into a lighting demand prediction model; the lighting demand prediction model outputs an expected lighting requirement for each sub-area; A fifth processing module is configured to generate a lighting control strategy based on the expected lighting demand of each sub-area in combination with lighting comfort and lighting equipment life as an optimization target; The sixth processing module is configured to convert the lighting control strategy into a control instruction and send the instruction to the lighting control terminal, and the lighting control terminal controls the operation of the lighting equipment in each sub-area based on the control instruction.

Images