A method, system, device and storage medium for designing indoor lighting in a substation

Abstract

The present invention relates to the field of lighting design technology, and discloses a method, system, device, and storage medium for substation indoor lighting design, including obtaining real-time data, spatial feature data, and meteorological data of the substation, and inputting them into an illumination prediction model to obtain illumination demand values ​​for each area of ​​the substation; inputting illumination demand values ​​and environmental parameters into a lamp selection model to obtain an initial lamp layout plan; establishing a three-dimensional simulation model of the substation based on the substation design drawings and the initial lamp layout plan, and performing iterative simulation to obtain an optimized lamp layout plan; using a clustering algorithm to perform cluster analysis on the optimized lamp layout plan to obtain several lamp groups, and setting an independent power distribution circuit for each lamp group; and generating a control strategy corresponding to each lamp group based on the illumination demand value. By integrating dynamic prediction, multi-objective optimization, and intelligent control technologies, the present invention significantly improves the design accuracy, energy efficiency, and operation and maintenance convenience of the lighting system.

Description

Technical Field

[0001] The present invention relates to the technical field of lighting design, and in particular to a method, system, equipment and storage medium for designing indoor lighting in a substation. Background Art

[0002] At present, the indoor lighting system of substations is mainly designed based on industry standards, using empirical formula estimation combined with two-dimensional plane layout methods. The limitations of these conventional methods are, on the one hand, insufficient design accuracy. Existing technologies rely on simplified illumination calculation formulas and do not fully consider the response to spatial heterogeneity. Their lighting indicators are difficult to meet the needs of high-precision light environments in substations. On the other hand, key indicator verification is missing. There is a lack of quantitative simulation verification methods for key parameters affecting visual comfort. The design results cannot be verified by visualization tools, which can easily cause problems such as excessive glare or light color distortion in actual scenes. In addition, existing methods also have problems with low energy efficiency and intelligence levels. Existing methods mostly rely on manual experience for the layout of indoor lamps in substations, which can easily lead to excessive lighting power density. In addition, there is a lack of dynamic control mechanism, and it is impossible to optimize the control of lamps according to the actual environment, resulting in energy waste and increased operation and maintenance costs. Summary of the Invention

[0003] In order to solve the above technical problems, the present invention provides a substation indoor lighting design method, system, equipment and storage medium, which can solve the problems of low accuracy and high energy consumption in the existing substation indoor lighting system design method, thereby improving the indoor lighting quality of the substation and reducing the energy consumption of the substation.

[0004] In a first aspect, the present invention provides a method for designing indoor lighting for a substation, the method comprising:

[0005] Obtaining real-time data, spatial feature data, and meteorological data of the substation, and inputting them into a preset illumination prediction model to obtain the illumination demand value of each area of ​​the substation. The real-time data includes ambient light data, personnel activity data, and energy consumption data. The illumination prediction model is constructed based on a neural network model;

[0006] Inputting the illumination requirement value and environmental parameters into a preset lamp selection model to obtain an initial lamp layout plan, wherein the lamp selection model is constructed based on a random forest algorithm, and the initial lamp layout plan includes initial lamp types and initial lamp parameters;

[0007] Establishing a three-dimensional simulation model of the substation based on the substation design drawings and the initial lighting layout plan, and iteratively simulating the three-dimensional simulation model according to preset standards to obtain an optimized lighting layout plan;

[0008] A clustering algorithm is used to perform cluster analysis on the lamp layout optimization scheme to obtain a number of lamp groups, and an independent power distribution circuit is set for each lamp group;

[0009] According to the illumination requirement value, fuzzy reasoning is used to generate a control strategy corresponding to each lamp group.

[0010] Furthermore, the step of iteratively simulating the three-dimensional simulation model according to a preset standard to obtain a lamp layout optimization solution includes:

[0011] The three-dimensional simulation model is iteratively simulated using the minimization of the sum of squared errors between each simulation standard and the corresponding preset standard as the objective function and the lamp layout parameters as the optimization variables to obtain a lamp layout optimization solution. The lamp layout parameters include lamp spacing, installation height, and number of lamps.

[0012] The objective function is expressed by the following formula:

[0013]

[0014] Where, E sim Indicates the average illumination simulation value, E std Indicates the average illumination standard value, UGR sim Indicates glare simulation value, UGR std Indicates the glare standard value, U sim Indicates the illumination uniformity simulation value, U std Indicates the standard value of illumination uniformity, LPD sim Indicates the lighting power density simulation value, LPD std Indicates the standard value of lighting power density.

[0015] Furthermore, the step of using a clustering algorithm to perform cluster analysis on the lamp layout optimization scheme to obtain a plurality of lamp groups, and setting an independent power distribution circuit for each lamp group includes:

[0016] Taking each lamp as a node, the edge weights between adjacent nodes are calculated based on power correlation, spatial distance, and usage frequency synchronization, and a lamp structure diagram is constructed based on the nodes and edge weights;

[0017] Using a modularity optimization algorithm to divide the lamp structure diagram into communities, obtaining a plurality of first communities;

[0018] Merging the first communities according to community power differences and community spatial distances to obtain a plurality of second communities, and obtaining corresponding lamp groups based on the second communities;

[0019] The loop capacity of each lamp group is determined based on the total lamp power and a preset capacity safety margin, and a path planning algorithm is used to perform cable path planning to obtain a lamp cable routing layout for the lamp group.

[0020] Furthermore, the edge weight is expressed by the following formula:

[0021]

[0022] Where w ij represents the edge weight between node i and node j, P i and P j Denote the power of node i and node j respectively, D ij represents the Euclidean distance between node i and node j, f i and f j Represent the usage frequency of node i and node j respectively, P max Indicates the maximum power, D max Indicates the maximum distance, f max represents the maximum frequency, α represents the power weight, β represents the distance weight, and γ represents the frequency weight.

[0023] Furthermore, the step of using a path planning algorithm to perform cable path planning to obtain a lamp cable routing layout of the lamp group includes:

[0024] According to the edge weight of the second community corresponding to each lamp group, the actual path cost function is constructed;

[0025] Construct a heuristic function based on the Euclidean distance between the nodes of the second community corresponding to each lighting group and the obstacle data around the nodes;

[0026] Obtaining a total cost function according to the actual path cost function and the heuristic function;

[0027] According to the total cost function, the A-star algorithm is used to perform iterative calculations to obtain the shortest path corresponding to each lamp group;

[0028] Obtaining a lamp cable routing layout for each lamp group based on the shortest path;

[0029] The actual path cost function is expressed by the following formula:

[0030]

[0031] Where g(n) represents the actual path cost function of the current node n, w ij Represents the edge weight between node i and node j, Path(start→n) represents the path from the starting node start to the current node n;

[0032] The heuristic function is expressed by the following formula:

[0033]

[0034] Where h(n) represents the heuristic function of the current node n, x n and y n Indicates the coordinate value of the current node n, x g and y g represents the coordinate value of the target node g, λ represents the obstacle coefficient, and ρ(n) represents the obstacle density around the current node n;

[0035] The total cost function is expressed as follows:

[0036]

[0037] Where f(n) represents the total cost function of the current node n.

[0038] Furthermore, the step of generating a control strategy corresponding to each lamp group using fuzzy reasoning according to the illumination requirement value includes:

[0039] Generate a meteorological disturbance factor according to meteorological data, and generate a control matrix according to the real-time data of the substation, the illumination demand value and the meteorological disturbance factor;

[0040] The control matrix is ​​input into a preset fuzzy rule library for fuzzy matching to obtain an output value, and the output value is converted into a dimming level and a switching instruction.

[0041] Furthermore, after the step of converting the output value into a dimming level and a switching instruction, the method further includes:

[0042] According to preset conditions, the scene mode of the substation is determined, and the corresponding scene control strategy is selected according to the scene mode, wherein the scene mode includes daily mode, energy-saving mode, emergency mode and night mode;

[0043] The dimming level and the switching instruction are modified based on the scene control strategy as a constraint condition.

[0044] In a second aspect, the present invention provides a substation indoor lighting design system, the system comprising:

[0045] An illumination prediction module is used to obtain real-time data, spatial feature data, and meteorological data of the substation, and input a preset illumination prediction model to obtain the illumination demand value of each area of ​​the substation. The real-time data includes ambient light data, personnel activity data, and energy consumption data. The illumination prediction model is constructed based on a neural network model;

[0046] a layout design module, configured to input the illumination requirement value and environmental parameters into a preset lamp selection model to obtain an initial lamp layout plan, wherein the lamp selection model is constructed based on a random forest algorithm, and the initial lamp layout plan includes initial lamp types and initial lamp parameters;

[0047] a layout optimization module, configured to establish a three-dimensional simulation model of the substation based on the substation design drawings and the initial lighting layout plan, and iteratively simulate the three-dimensional simulation model according to preset standards to obtain an optimized lighting layout plan;

[0048] A circuit design module is used to perform cluster analysis on the lighting fixture layout optimization scheme using a clustering algorithm to obtain a number of lighting fixture groups, and set an independent power distribution circuit for each lighting fixture group;

[0049] The strategy generation module is used to generate a control strategy corresponding to each lamp group based on the illumination requirement value by using fuzzy reasoning.

[0050] In a third aspect, an embodiment of the present invention further provides a computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above method when executing the computer program.

[0051] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the steps of the above method when executed by a processor.

[0052] The present invention provides a method, system, device and storage medium for substation indoor lighting design. The present invention can achieve high-precision light environment design through multi-parameter collaborative simulation and dynamic demand prediction, and can achieve energy saving and consumption reduction through intelligent grouping control and load balancing optimization. It can plan cable paths through an improved A-star algorithm and integrate fuzzy logic control to generate intelligent control strategies, and can achieve adaptive dynamic regulation of the lighting system. By integrating dynamic prediction, multi-objective optimization and intelligent control technology, the present invention can significantly improve the design accuracy, energy efficiency and operation and maintenance convenience of the lighting system. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] Figure 1 1 is a flow chart of a method for designing indoor lighting for a substation according to an embodiment of the present invention;

[0054] Figure 2 Schematic diagram of the structure of the substation indoor lighting design system according to an embodiment of the present invention;

[0055] Figure 3 is an internal structural diagram of a computer device according to an embodiment of the present invention;

[0056] Reference numerals:

[0057] 10. Illumination prediction module; 20. Layout design module; 30. Layout optimization module; 40. Loop design module; 50. Strategy generation module. DETAILED DESCRIPTION

[0058] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0059] See also Figure 1 A first embodiment of the present invention provides a method for designing indoor lighting for a substation, comprising steps S10 to S50:

[0060] Step S10: acquiring real-time data, spatial feature data, and meteorological data of the substation, and inputting a preset illumination prediction model to obtain illumination demand values ​​for each area of ​​the substation. The real-time data includes ambient light data, personnel activity data, and energy consumption data. The illumination prediction model is constructed based on a neural network model.

[0061] Step S20: Inputting the illumination requirement value and environmental parameters into a preset lamp selection model to obtain an initial lamp layout plan, wherein the lamp selection model is constructed based on a random forest algorithm, and the initial lamp layout plan includes initial lamp types and initial lamp parameters;

[0062] Step S30: establishing a three-dimensional simulation model of the substation based on the substation design drawings and the initial lighting layout plan, and iteratively simulating the three-dimensional simulation model according to preset standards to obtain an optimized lighting layout plan;

[0063] Step S40, performing cluster analysis on the lamp layout optimization scheme using a clustering algorithm to obtain a plurality of lamp groups, and setting an independent power distribution circuit for each lamp group;

[0064] Step S50 : generating a control strategy corresponding to each lamp group using fuzzy reasoning according to the illumination requirement value.

[0065] In the present invention, the lighting brightness requirements of different areas of the substation are first analyzed and predicted. The illumination prediction model used is constructed based on a neural network model. Preferably, the illumination prediction model is constructed based on a long short-term memory neural network LSTM or a transformer model Transformer. The input data of the illumination prediction model include real-time data, spatial feature data and meteorological data of the substation. The real-time data includes ambient light data, personnel activity data and energy consumption data, etc. The meteorological data includes temperature, humidity, natural light intensity, etc. The output data of the model is the illumination demand value of each area of ​​the substation in the future period. The various areas of the substation refer to functional areas obtained by dividing the substation according to different functions, including control rooms, distribution rooms, etc. It should be noted that the structure and training process of the illumination prediction model in this embodiment can refer to the structure and training method of conventional neural network models, and are not too limited here.

[0066] After the illumination demand values ​​for different areas of the substation are predicted using the illumination prediction model, the lamp selection model is used to select the lamp type and parameters for each area based on the illumination demand values ​​and the actual environmental parameters of the substation, thereby obtaining an initial lamp layout plan. Specifically, in this embodiment, a random forest algorithm is preferably used to construct the lamp selection model. The input features of this model include the illumination demand value and environmental parameters. The environmental parameters include the functional area and the reflectance coefficient and spatial area of ​​each area. The random forest model randomly samples the original data set to form multiple different sample data sets. Then, multiple different decision tree models are built based on these sample data sets. Finally, the final result is obtained based on the average value or voting results of these decision tree models. In this embodiment, multiple decision trees are established and an integrated voting method is used to vote from the results of the multiple decision trees to select the initial lamp type and lamp parameters. The lamp parameters here include luminous flux, installation height, lamp spacing, lamp quantity, and maintenance factor. Finally, the initial lamp layout plan is determined based on the initial lamp type and lamp parameters.

[0067] A 3D simulation model was then constructed based on the initial lighting layout plan and the substation's 2D design drawings. Specifically, the 2D substation floor plan was first processed using AutoCAD to extract key information such as room dimensions and door and window locations. A detailed model was then created using SketchUp / BIM. Luminaire and environmental parameters were converted into structured data recognizable by DIALux. Luminaire parameters included luminous flux, mounting height, luminaire spacing, number of luminaires, and maintenance factor. Environmental parameters included functional areas, the reflectance coefficient for each area, and the spatial area. Luminous flux refers to the total luminous output of the luminaire; mounting height refers to the height of the luminaire from the ground; luminaire spacing refers to the lateral distance between luminaires; the maintenance factor is the luminous decay coefficient, which is used to correct for luminous flux loss after long-term use; the reflectance coefficient includes the reflectance of the ceiling, walls, and floor to light. The spatial area is represented by the room dimensions (length, width, and height). These parameters were then organized into a file structure recognizable by DIALux, such as JSON or CSV. These data files are then imported into DIALux via API calls or plugins to create a room model. Luminaires are then arranged in batches according to coordinates determined by the luminaire spacing, and their properties, including luminous flux, power, and light distribution curves, are designed. The simulation environment is then configured, including the light source model and mesh accuracy. For example, IES / LDT files are used to define the luminaire light distribution curves, and the mesh density is set to pre-set specifications. The specific steps for building a 3D model can be found in the general DIALux software build process and will not be detailed here.

[0068] In a preferred embodiment, after constructing the three-dimensional simulation model, the three-dimensional simulation model is iteratively optimized according to preset standards to obtain a lamp layout optimization solution. The specific optimization steps include:

[0069] The objective function is to minimize the sum of square errors between each simulation standard and the corresponding preset standard, and the lamp layout parameters are used as optimization variables. The three-dimensional simulation model is iteratively simulated to obtain a lamp layout optimization solution. The lamp layout parameters include lamp spacing, installation height and number of lamps.

[0070] In this embodiment, preset standard values ​​for key indicators are first set according to industry standards. These key indicators include average illuminance, glare value, illuminance uniformity, and lighting power density, and standard values ​​for these key indicators are set. Simulated values ​​for the key indicators of the three-dimensional simulation model are then calculated. Average illuminance is calculated using the luminous flux method: average illuminance = total luminous flux of the light source * utilization factor * maintenance factor / area. Illuminance uniformity is calculated using the point illuminance method, which calculates illuminance values ​​point by point and then calculates illuminance uniformity by taking the ratio of minimum illuminance to average illuminance. Glare value can be calculated using the CIE glare value formula.

[0071] The objective function is established based on the sum of squares of the errors between the preset standard value and the simulated value:

[0072]

[0073] Where, E sim Indicates the average illumination simulation value, E std Indicates the average illumination standard value, UGR sim Indicates glare simulation value, UGR std Indicates the glare standard value, U sim Indicates the illumination uniformity simulation value, U std Indicates the standard value of illumination uniformity, LPD sim Indicates the lighting power density simulation value, LPD std Indicates the standard value of lighting power density.

[0074] According to the above objective function, the three-dimensional simulation model is iteratively optimized with the lamp spacing, installation height and number of lamps as optimization variables. During the iteration, the gradient descent method can be used to adjust the variable step size for iteration, or the exhaustive method can be used to traverse all possible parameter combinations within a reasonable range until the objective function is less than the threshold or the maximum number of iterations is reached. The optimized lamp type and optimized lamp parameters are obtained, thereby determining the lamp layout optimization plan.

[0075] Regarding the lamp layout optimization solution, the present invention divides the lamps into multiple logically related lamp groups through cluster analysis, and then sets an independent power distribution circuit for each lamp group, where the power distribution circuit includes circuit capacity and cable routing.

[0076] In a preferred embodiment, a K-means clustering algorithm (K-Means algorithm) is used to cluster the matrix of lamp characteristics, using lamp power, usage frequency, and location coordinates as the lamp feature matrix. This matrix is ​​then clustered to identify lamp groups. The power distribution circuit capacity is then designed based on the total lamp power of each lamp group. Based on the coordinates of each lamp in each lamp group, the cable routing plan for each lamp group is calculated with minimizing cable length as the objective function. Specifically, the total lamp power P within the lamp group is calculated and then expanded by a preset capacity safety margin, such as 1.2, to obtain the power distribution circuit capacity P', i.e., P' = P * 1.2. Cable routing is then planned based on the lamp location coordinates to minimize total cable length. A minimum spanning tree algorithm is used to determine the number of shortest paths connecting all lamps. Finally, the spanning tree is traversed, branching paths are merged, and a cable routing plan is generated.

[0077] Since the K-Means algorithm has an initial centroid dependency problem, if the initial centroid is not selected properly, the algorithm may fall into a local optimal solution and thus fail to find a better global solution. Therefore, in another preferred embodiment, the present invention uses an improved community discovery algorithm based on graph theory to group lamps and a path planning algorithm to determine cable routing. The specific steps include:

[0078] Taking each lamp as a node, the edge weights between adjacent nodes are calculated based on power correlation, spatial distance, and usage frequency synchronization, and a lamp structure diagram is constructed based on the nodes and edge weights;

[0079] Using a modularity optimization algorithm to divide the lamp structure diagram into communities, obtaining a plurality of first communities;

[0080] Merging the first communities according to community power differences and community spatial distances to obtain a plurality of second communities, and obtaining corresponding lamp groups based on the second communities;

[0081] The loop capacity of each lamp group is determined based on the total lamp power and a preset capacity safety margin, and a path planning algorithm is used to perform cable path planning to obtain a lamp cable routing layout for the lamp group.

[0082] In this embodiment, the graph is constructed and edge weights are defined first. Specifically, each lamp is regarded as a node, and the power correlation, spatial distance, and usage frequency synchronization between adjacent nodes are comprehensively considered to define edge weights. The edge weight calculation formula is:

[0083]

[0084] Where w ij represents the edge weight between node i and node j, P i and P j Denote the power of node i and node j respectively, D ij represents the Euclidean distance between node i and node j, f i and f j Represent the usage frequency of node i and node j respectively, P max Indicates the maximum power, D max Indicates the maximum distance, f max represents the maximum frequency, α represents the power weight, β represents the distance weight, and γ represents the frequency weight, and α+β+γ=1.

[0085] In the above formula, the meaning of power weight is grouping based on power difference, for example, high-power lamps can be powered centrally; the meaning of distance weight is grouping based on spatial distance, for example, adjacent lamps can be divided into the same circuit; the meaning of frequency weight is grouping based on frequency synchronization, for example, coordinated control of high-frequency lamps.

[0086] Based on node and edge weights, a lighting fixture structure graph is constructed. A modularity optimization algorithm is then used to partition the nodes in the graph into communities. Modularity is a core metric used to assess the quality of community partitioning in complex network analysis. Its core concept is to compare the number of edges within a community in an actual network with the expected value under random conditions. A larger modularity value indicates denser internal connections and sparser external connections. In this embodiment, an iterative optimization algorithm (Louvain algorithm) is employed based on a defined modularity Q. The Louvain algorithm iteratively partitions nodes into communities and optimizes the modularity score at each iteration to find the optimal community partitioning. The Louvain algorithm consists of two phases: a local optimization phase and a community merging phase. In the local optimization phase, each node is initialized as an independent community. Then, all nodes are traversed, attempting to move the node to an adjacent community. The move that maximizes Q gain is selected, and this process is repeated until Q no longer improves. In the community merging phase, each community is merged into a supernode, with the edge weight being the sum of the edge weights between the original communities. These two phases are repeated until no further merging is possible, resulting in a community partitioning.

[0087] In order to avoid the waste of loop capacity due to excessive division and improve the practicality of the project, in this embodiment, after obtaining multiple first communities through the Louvain algorithm, it is necessary to dynamically merge each first community. The merging conditions include community power difference constraints and community space distance constraints. Specifically, first calculate the total power difference of lamps between the two communities c1 and c2, and determine whether the total power difference of lamps is less than the difference threshold. The total power difference of lamps P c The expression is:

[0088] ‌

[0089] Where, P c1 represents the total power of the lamps in community c1, P c2 Indicates the total power of the lamps in community c2, Represents the maximum function.

[0090] Then the centroid distance between the two communities is calculated, and it is determined whether the centroid distance is less than the distance threshold.

[0091] If the total power difference between the two communities is less than the difference threshold and the centroid distance is less than the distance threshold, the two communities are merged, the modularity Q is recalculated, and iterative optimization is continued based on the Louvain algorithm until the final community grouping is obtained, with each community corresponding to a lamp group.

[0092] Based on the community division results, independent power distribution circuits are designed and cable routing is optimized. For power distribution circuit design, the total power of each lighting group is first calculated. Then, based on a preset capacity safety margin, the total power of the lighting is expanded to obtain the circuit capacity. For cable routing, in a preferred embodiment, the A-star algorithm is used for cable path planning. The specific steps include:

[0093] According to the edge weight of the second community corresponding to each lamp group, the actual path cost function is constructed;

[0094] Construct a heuristic function based on the Euclidean distance between the nodes of the second community corresponding to each lighting group and the obstacle data around the nodes;

[0095] Obtaining a total cost function according to the actual path cost function and the heuristic function;

[0096] According to the total cost function, the A-star algorithm is used to perform iterative calculations to obtain the shortest path corresponding to each lamp group;

[0097] According to the shortest path, the lamp cable routing layout of each lamp group is obtained.

[0098] In this embodiment, for each lamp group, a total cost function is first established. In the A-star algorithm, the total cost function consists of two parts: the actual path cost function and the heuristic function. The actual path cost refers to the actual accumulated path cost from the starting node to the current node n. In this embodiment, the actual path cost is expressed as the sum of all edge weights in the second community corresponding to the lamp group:

[0099]

[0100] Where g(n) represents the actual path cost function of the current node n, w ij Represents the edge weight between node i and node j, and Path(start→n) represents the path from the starting node start to the current node n.

[0101] The heuristic function represents the estimated minimum cost from the current node n to the target node. In this embodiment, the estimated minimum cost is expressed as the Euclidean distance between the current node n and the target node g, also known as the end point g. The obstacle density factor is introduced to dynamically modify the estimated minimum cost. The formula is expressed as follows:

[0102]

[0103] Where h(n) represents the heuristic function of the current node n, x n and y n Indicates the coordinate value of the current node n, x g and y g represents the coordinate value of the target node g, λ represents the obstacle coefficient, and ρ(n) represents the obstacle density around the current node n.

[0104] In the heuristic function, the Euclidean distance is calculated using the node coordinate values, and the obstacle influence factor is introduced. The obstacle influence factor includes the obstacle influence coefficient and the obstacle density. The obstacle influence coefficient is a preset value. The larger the value, the greater the impact of the obstacle on path planning, and the more inclined to bypass the obstacle. The obstacle density represents the number of obstacles per unit area around the current node n. The obstacle density can be obtained through grid map statistics, that is, the number of obstacles within a circle with a radius of 1 meter with node n as the center is counted, and the number of obstacles is divided by the area of ​​the circle to obtain the obstacle density.

[0105] Adding the above two formulas together, we can get the total cost function f(n):

[0106]

[0107] Finally, the A-star algorithm is used to search and solve the total cost function, thereby obtaining the shortest path connecting all nodes within the lighting group. Based on this shortest path, cable routing is planned to obtain the lighting cable routing layout. It should be noted that the search and solution steps using the A-star algorithm can be referred to the conventional solution steps and will not be repeated here.

[0108] In this embodiment, the total cost function of the conventional A-star algorithm is improved, and the spatial, electrical and frequency characteristics are integrated into the actual path cost function, which can achieve coordinated optimization of path length, load balancing and operation and maintenance costs. For the heuristic function, on the basis of conventional geometric distance, dynamic obstacle perception is performed by introducing obstacle influencing factors, so that cable routing prioritizes detours around high-risk areas, enhancing safety and adaptability in complex environments.

[0109] In a preferred embodiment, in order to enhance the safety of path planning, a distance safety margin constraint is added, that is, an expansion radius is set, and in the original obstacle grid map, the obstacle boundary is expanded outward by the expansion radius to generate a safety map, and then path planning is performed based on the safety map to ensure that the actual distance between the cable and the obstacle is greater than or equal to the expansion radius. After the path planning is completed, the distance between each node on the planned path and the nearest obstacle is checked. If the distance is less than the expansion radius, the path is considered invalid and needs to be replanned. In this way, the path can be forced to maintain a safe distance from the obstacle, thereby avoiding operation and maintenance risks.

[0110] After designing an independent power distribution circuit for each lighting group, a fuzzy inference algorithm is used to generate a control strategy for each lighting group based on the predicted illumination demand value. The specific steps include:

[0111] Generate a meteorological disturbance factor according to meteorological data, and generate a control matrix according to the real-time data of the substation, the illumination demand value and the meteorological disturbance factor;

[0112] The control matrix is ​​input into a preset fuzzy rule library for fuzzy matching to obtain an output value, and the output value is converted into a dimming level and a switching instruction.

[0113] In this embodiment, fuzzy logic control is used to generate a control strategy. First, a meteorological disturbance factor is generated based on real-time meteorological data. This factor is used to dynamically correct natural lighting. For example, if it is set to 1.0 on a sunny day, the factor is set to 0.6. A dynamic input control matrix is ​​then generated based on the substation's real-time data, the illumination demand, and the meteorological disturbance factor. The real-time data here includes ambient lighting data, human activity data, and energy consumption data. The input variables of the control matrix include illumination deviation (i.e., the difference between the illumination demand and the ambient lighting data), human activity intensity (determined by the human activity data's density per unit area), and the meteorological disturbance factor. In other words, the control matrix uses both ambient lighting data and human activity data from the real-time data. The input variables of the control matrix are then fuzzified, converting them into semantic variables that can be processed by the fuzzy logic system.

[0114] The output variables of the fuzzy logic system are defined as dimming levels and on / off commands. The dimming level is the percentage of lamp brightness, and the on / off command is the on / off state of the lamp group. Membership functions are also defined. For example, the illumination deviation is divided into five fuzzy sets, using triangular or trapezoidal functions. The activity intensity is divided into three fuzzy sets, and the dimming level is divided into four levels. The specific membership functions can be flexibly set according to actual conditions and are not limited here.

[0115] On the basis of the above definitions of input and output variables and membership functions, based on expert experience or historical data, with input variables as conditions and output variables as actions, the logical rules between input and output variables are defined to build a fuzzy rule base.

[0116] Then, fuzzy reasoning is performed on the control matrix according to the logical rules in the fuzzy rule base to obtain the corresponding output value. Then, through defuzzification, the output value is converted into an accurate dimming signal and switch instruction. Specifically, the control matrix is ​​input into the membership function, the minimum value is taken as the trigger strength of the rule, the trigger strength of all rules is combined, and the maximum value is taken as the final fuzzy output. The centroid method is used for defuzzification to obtain the accurate dimming level:

[0117]

[0118] In the formula, S represents the dimming level, n represents the number of rules, μ i Indicates the triggering strength of the i-th rule, S i Indicates the center value of the dimming level corresponding to the i-th rule.

[0119] Then, a switch instruction is generated according to the dimming level. For example, if the dimming level is greater than the level threshold, the switch instruction is turned on, otherwise, the switch instruction is turned off.

[0120] In a preferred embodiment, in order to achieve dynamic switching of control strategies based on multiple scenarios, the present invention pre-sets different scenario modes as constraints of the control strategy and dynamically adjusts the control strategy. The specific steps include:

[0121] According to preset conditions, the scene mode of the substation is determined, and the corresponding scene control strategy is selected according to the scene mode, wherein the scene mode includes daily mode, energy-saving mode, emergency mode and night mode;

[0122] The dimming level and the switching instruction are modified based on the scene control strategy as a constraint condition.

[0123] In this embodiment, a plurality of different scene modes are first set, and a different scene control strategy is set for each scene mode, wherein the scene modes include daily mode, energy-saving mode, emergency mode and night mode. The judgment of the scene mode includes: determining the daily mode and night mode according to time, determining whether to enter the energy-saving mode according to the sensor data of the power system, and entering the emergency mode if a power system failure occurs. The priorities of these modes are: emergency > night > energy-saving > daily, and the current scene mode of the substation is determined according to the priority.

[0124] For daily mode, there are no constraints on dimming levels and switching instructions in its scene control strategy; for energy-saving mode, the upper limit of the dimming level is limited to the scene setting value range, such as the dimming level is less than 50%; for emergency mode, all lighting groups are forced to turn on at full power and the dimming level is 100%; for night mode, only the lighting groups for safety lighting are turned on, and the upper and lower limits of the dimming level are also limited.

[0125] Based on the above scenario modes, when controlling lamps, the current scenario mode of the substation is first determined, and the corresponding scenario control strategy is selected based on the scenario mode. Then, the dimming level and switching instructions obtained through the above fuzzy reasoning are determined to be within the scope of the scenario control strategy. If so, the lamp group is controlled according to the dimming level and switching instructions obtained by fuzzy reasoning. Otherwise, the dimming level and switching instructions are modified based on the scenario control strategy as a constraint. For example, if the dimming level obtained through fuzzy reasoning is 70%, but the upper limit of the dimming level is 50% in energy-saving mode, the dimming level will be corrected to 50% before controlling the lamp group.

[0126] The control strategy generation method of this embodiment can ensure the stability of different scenarios while retaining the flexibility of real-time dynamic adjustment, thereby achieving a balance between safety, energy saving and comfort of the substation lighting system.

[0127] This embodiment provides a substation indoor lighting design method that achieves high-precision light environment design through multi-parameter collaborative simulation and dynamic demand prediction, achieves significant energy saving and consumption reduction through intelligent grouping control and load balancing optimization, and can intuitively verify key indicators through three-dimensional simulation, solving the non-visualization defect of traditional two-dimensional design. It also improves the efficiency of lighting design through prediction, simulation and iterative closed-loop optimization. At the same time, the present invention plans cable paths through an improved A-star algorithm and integrates fuzzy logic control to generate intelligent control strategies, thereby achieving adaptive dynamic regulation of the lighting system, thereby significantly improving the design accuracy, energy efficiency and operation and maintenance convenience of the lighting system.

[0128] See also Figure 2 Based on the same inventive concept, a second embodiment of the present invention provides a substation indoor lighting design system, comprising:

[0129] The illumination prediction module 10 is used to obtain real-time data, spatial feature data, and meteorological data of the substation, and input a preset illumination prediction model to obtain the illumination demand value of each area of ​​the substation. The real-time data includes ambient light data, personnel activity data, and energy consumption data. The illumination prediction model is constructed based on a neural network model;

[0130] a layout design module 20 for inputting the illumination requirement value and environmental parameters into a preset lamp selection model to obtain an initial lamp layout plan, wherein the lamp selection model is constructed based on a random forest algorithm, and the initial lamp layout plan includes initial lamp types and initial lamp parameters;

[0131] a layout optimization module 30 for establishing a three-dimensional simulation model of the substation based on the substation design drawings and the initial lighting layout plan, and performing iterative simulation on the three-dimensional simulation model according to preset standards to obtain an optimized lighting layout plan;

[0132] A circuit design module 40 is configured to perform cluster analysis on the lighting fixture layout optimization scheme using a clustering algorithm to obtain a plurality of lighting fixture groups, and to set an independent power distribution circuit for each lighting fixture group;

[0133] The strategy generation module 50 is configured to generate a control strategy corresponding to each lamp group based on the illumination requirement value by using fuzzy reasoning.

[0134] The technical features and effects of the substation indoor lighting design system proposed in the embodiments of the present invention are the same as those of the method proposed in the embodiments of the present invention and are not further elaborated here. Each module in the aforementioned substation indoor lighting design system can be implemented in whole or in part through software, hardware, or a combination thereof. Each of these modules can be embedded in or independent of a processor in a computer device in hardware form, or stored in a computer device memory in software form, allowing the processor to call and execute the corresponding operations of each module.

[0135] In addition, an embodiment of the present invention further provides a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above method when executing the computer program.

[0136] See also Figure 3, an internal structure diagram of a computer device in one embodiment, the computer device can specifically be a terminal or a server. The computer device includes a processor, a memory, a network interface, a display, and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a method for designing indoor lighting for a substation is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a key, trackball, or touchpad provided on the computer device housing, or an external keyboard, touchpad, or mouse.

[0137] It can be understood by those skilled in the art that Figure 3 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computing device may include more or fewer components than shown in the figure, or combine certain components, or have the same component arrangement.

[0138] In addition, an embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which implements the steps of the above method when the computer program is executed by a processor.

[0139] In summary, an embodiment of the present invention proposes a method, system, device and storage medium for designing indoor lighting in a substation. The method obtains real-time data, spatial feature data and meteorological data of the substation and inputs a preset illumination prediction model to obtain illumination demand values ​​for each area of ​​the substation. The real-time data includes ambient light data, personnel activity data and energy consumption data. The illumination prediction model is constructed based on a neural network model; the illumination demand value and environmental parameters are input into a preset lamp selection model to obtain an initial lamp layout plan. The lamp selection model is constructed based on a random forest algorithm, and the initial lamp layout plan includes an initial lamp type and initial lamp parameters; according to the substation design drawings and the initial lamp layout plan, a three-dimensional simulation model of the substation is established, and the three-dimensional simulation model is iteratively simulated according to preset standards to obtain a lamp layout optimization plan; a clustering algorithm is used to perform cluster analysis on the lamp layout optimization plan to obtain several lamp groups, and an independent distribution circuit is set for each lamp group; according to the illumination demand value, fuzzy reasoning is used to generate a control strategy corresponding to each lamp group. The present invention realizes high-precision lighting environment design through multi-parameter collaborative simulation and dynamic demand prediction. It plans cable paths through the improved A-star algorithm and integrates fuzzy logic control to generate intelligent control strategies, thereby realizing adaptive dynamic regulation of lighting fixtures. The present invention significantly improves the design accuracy, energy efficiency and operation and maintenance convenience of the lighting system by integrating dynamic prediction, multi-objective optimization and intelligent control technology.

[0140] Each embodiment in this specification is described in a progressive manner, and the same or similar parts of each embodiment can be directly referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment. It should be noted that the various technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the various technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0141] The above-described embodiments merely represent several preferred implementations of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the patent. It should be noted that a person skilled in the art could make several improvements and substitutions without departing from the technical principles of the present invention, and these improvements and substitutions should also be considered within the scope of protection of the present application. Therefore, the scope of protection of the present patent application shall be based on the scope of protection of the claims.

Claims

1. A method for designing indoor lighting for a substation, characterized in that: include: Obtaining real-time data, spatial feature data, and meteorological data of the substation, and inputting them into a preset illumination prediction model to obtain the illumination demand value of each area of ​​the substation. The real-time data includes ambient light data, personnel activity data, and energy consumption data. The illumination prediction model is constructed based on a neural network model; Inputting the illumination requirement value and environmental parameters into a preset lamp selection model to obtain an initial lamp layout plan, wherein the lamp selection model is constructed based on a random forest algorithm, and the initial lamp layout plan includes initial lamp types and initial lamp parameters; Establishing a three-dimensional simulation model of the substation based on the substation design drawings and the initial lighting layout plan, and iteratively simulating the three-dimensional simulation model according to preset standards to obtain an optimized lighting layout plan; A clustering algorithm is used to perform cluster analysis on the lamp layout optimization scheme to obtain a number of lamp groups, and an independent power distribution circuit is set for each lamp group; Based on the illumination requirement value, fuzzy reasoning is used to generate a control strategy corresponding to each lamp group, including: Generate a meteorological disturbance factor according to meteorological data, and generate a control matrix according to the real-time data of the substation, the illumination demand value and the meteorological disturbance factor; The control matrix is ​​input into a preset fuzzy rule library for fuzzy matching to obtain an output value, and the output value is converted into a dimming level and a switching instruction.

2. The substation indoor lighting design method according to claim 1, characterized in that: The step of iteratively simulating the three-dimensional simulation model according to a preset standard to obtain a lamp layout optimization solution includes: The three-dimensional simulation model is iteratively simulated using the minimization of the sum of squared errors between each simulation standard and the corresponding preset standard as the objective function and the lamp layout parameters as the optimization variables to obtain a lamp layout optimization solution. The lamp layout parameters include lamp spacing, installation height, and number of lamps. The objective function is expressed by the following formula: Where, E sim Indicates the average illumination simulation value, E std Indicates the average illumination standard value, UGR sim Indicates glare simulation value, UGR std Indicates the glare standard value, U sim Indicates the illumination uniformity simulation value, U std Indicates the standard value of illumination uniformity, LPD sim Indicates the lighting power density simulation value, LPD std Indicates the standard value of lighting power density.

3. The substation indoor lighting design method according to claim 1, characterized in that: The step of using a clustering algorithm to perform cluster analysis on the lamp layout optimization scheme to obtain a plurality of lamp groups, and setting an independent power distribution circuit for each lamp group includes: Taking each lamp as a node, the edge weights between adjacent nodes are calculated based on power correlation, spatial distance, and usage frequency synchronization, and a lamp structure diagram is constructed based on the nodes and edge weights; Using a modularity optimization algorithm to divide the lamp structure diagram into communities, obtaining a plurality of first communities; Merging the first communities according to community power differences and community spatial distances to obtain a plurality of second communities, and obtaining corresponding lamp groups based on the second communities; The loop capacity of each lamp group is determined based on the total lamp power and a preset capacity safety margin, and a path planning algorithm is used to perform cable path planning to obtain a lamp cable routing layout for the lamp group.

4. The substation indoor lighting design method according to claim 3, characterized in that: The edge weight is expressed by the following formula: Where w ij represents the edge weight between node i and node j, P i and P j Denote the power of node i and node j respectively, D ij represents the Euclidean distance between node i and node j, f i and f j Represent the usage frequency of node i and node j respectively, P max Indicates the maximum power, D max Indicates the maximum distance, f max represents the maximum frequency, α represents the power weight, β represents the distance weight, and γ represents the frequency weight.

5. The method for designing indoor lighting for a substation according to claim 3, characterized in that: The step of using a path planning algorithm to perform cable path planning to obtain the lamp cable routing layout of the lamp group includes: According to the edge weight of the second community corresponding to each lighting group, the actual path cost function is constructed; Construct a heuristic function based on the Euclidean distance between the nodes of the second community corresponding to each lighting group and the obstacle data around the nodes; Obtaining a total cost function according to the actual path cost function and the heuristic function; According to the total cost function, the A-star algorithm is used to perform iterative calculations to obtain the shortest path corresponding to each lamp group; Obtaining a lamp cable routing layout for each lamp group based on the shortest path; The actual path cost function is expressed by the following formula: Where g(n) represents the actual path cost function of the current node n, w ij Represents the edge weight between node i and node j, Path(start→n) represents the path from the starting node start to the current node n; The heuristic function is expressed by the following formula: Where h(n) represents the heuristic function of the current node n, x n and y n Indicates the coordinate value of the current node n, x g and y g represents the coordinate value of the target node g, λ represents the obstacle coefficient, and ρ(n) represents the obstacle density around the current node n; The total cost function is expressed as follows: Where f(n) represents the total cost function of the current node n.

6. The method for designing indoor lighting of a substation according to claim 1, characterized in that: After the step of converting the output value into a dimming level and a switching instruction, the method further includes: According to preset conditions, the scene mode of the substation is determined, and the corresponding scene control strategy is selected according to the scene mode, wherein the scene mode includes daily mode, energy-saving mode, emergency mode and night mode; The dimming level and the switching instruction are modified based on the scene control strategy as a constraint condition.

7. A substation indoor lighting design system, characterized in that: include: An illumination prediction module is used to obtain real-time data, spatial feature data, and meteorological data of the substation, and input a preset illumination prediction model to obtain the illumination demand value of each area of ​​the substation. The real-time data includes ambient light data, personnel activity data, and energy consumption data. The illumination prediction model is constructed based on a neural network model; a layout design module, configured to input the illumination requirement value and environmental parameters into a preset lamp selection model to obtain an initial lamp layout plan, wherein the lamp selection model is constructed based on a random forest algorithm, and the initial lamp layout plan includes initial lamp types and initial lamp parameters; a layout optimization module, configured to establish a three-dimensional simulation model of the substation based on the substation design drawings and the initial lighting layout plan, and iteratively simulate the three-dimensional simulation model according to preset standards to obtain an optimized lighting layout plan; A circuit design module is used to perform cluster analysis on the lighting fixture layout optimization scheme using a clustering algorithm to obtain a number of lighting fixture groups, and set an independent power distribution circuit for each lighting fixture group; A strategy generation module is used to generate a control strategy corresponding to each lamp group based on the illumination requirement value using fuzzy reasoning, including: Generate a meteorological disturbance factor according to meteorological data, and generate a control matrix according to the real-time data of the substation, the illumination demand value and the meteorological disturbance factor; The control matrix is ​​input into a preset fuzzy rule library for fuzzy matching to obtain an output value, and the output value is converted into a dimming level and a switching instruction.

8. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images