CN117236196B - Optimization method and system for point location layout of fire-fighting nozzle - Google Patents
Optimization method and system for point location layout of fire-fighting nozzle Download PDFInfo
- Publication number
- CN117236196B CN117236196B CN202311491673.7A CN202311491673A CN117236196B CN 117236196 B CN117236196 B CN 117236196B CN 202311491673 A CN202311491673 A CN 202311491673A CN 117236196 B CN117236196 B CN 117236196B
- Authority
- CN
- China
- Prior art keywords
- fire
- target
- solution set
- solution
- spray head
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 66
- 238000005457 optimization Methods 0.000 title claims abstract description 27
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 40
- 230000000694 effects Effects 0.000 claims abstract description 39
- 230000002068 genetic effect Effects 0.000 claims abstract description 36
- 238000012804 iterative process Methods 0.000 claims abstract description 6
- 239000000243 solution Substances 0.000 claims description 280
- 239000007921 spray Substances 0.000 claims description 120
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 49
- 230000006870 function Effects 0.000 claims description 23
- 230000008569 process Effects 0.000 claims description 23
- 238000005507 spraying Methods 0.000 claims description 23
- 230000008859 change Effects 0.000 claims description 18
- 239000012088 reference solution Substances 0.000 claims description 15
- 238000004364 calculation method Methods 0.000 claims description 9
- 238000010606 normalization Methods 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 6
- 238000012163 sequencing technique Methods 0.000 claims description 2
- 208000027418 Wounds and injury Diseases 0.000 abstract description 5
- 230000006378 damage Effects 0.000 abstract description 5
- 230000034994 death Effects 0.000 abstract description 5
- 231100000517 death Toxicity 0.000 abstract description 5
- 208000014674 injury Diseases 0.000 abstract description 5
- 230000006872 improvement Effects 0.000 abstract description 4
- 238000012545 processing Methods 0.000 abstract description 3
- 230000035772 mutation Effects 0.000 description 3
- 230000007480 spreading Effects 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000012530 fluid Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Abstract
The invention relates to the technical field of data processing, in particular to an optimization method and system for point location layout of a fire-fighting nozzle, comprising the following steps: obtaining a three-dimensional building model, using a genetic algorithm to obtain a plurality of initial solutions and solution sets corresponding to each initial solution, wherein the solution sets comprise three-dimensional coordinates of all fire-fighting nozzles distributed in the three-dimensional building model, so as to obtain a fire extinguishing effect corresponding to each solution set, thereby obtaining an optimal initial solution, counting a plurality of iterative solution sets obtained in an iterative process of the genetic algorithm by the optimal initial solution, and obtaining probability adjustment values corresponding to each fire-fighting nozzle according to the distances between the three-dimensional coordinates of each fire-fighting nozzle in all iterative solution sets, thereby obtaining an optimal fire-fighting nozzle point position layout. According to the invention, through self-adaptive initial solution, variation and crossover probability, optimization of the point location layout of the fire-fighting nozzle and improvement of the layout speed are realized, so that injury and death risks caused by fire disaster are reduced.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to an optimization method and system for point location layout of a fire-fighting nozzle.
Background
Fire sprinklers, commonly referred to as part of a sprinkler system, are a critical component in modern building fire protection systems. When fire starts, the spray head can respond to high temperature quickly and automatically to spray water onto the fire source. Timely water spraying can effectively control fire, avoid rapid spread of fire, and greatly reduce building and property loss. And provides time for person evacuation and reduces injuries and deaths due to fire. Genetic algorithms are typically used to obtain an optimal fire nozzle point placement.
The existing problems are as follows: when the parameters of the genetic algorithm are selected improperly, the algorithm operation is slow, and the obtained fire-fighting nozzle point positions are possibly unreasonable in layout, so that coverage is insufficient, and the partial areas of the fire spreading are possibly not sprayed in time, so that the fire continues to spread, and injury and death risks caused by the fire are increased.
Disclosure of Invention
The invention provides an optimization method and system for the point location layout of a fire-fighting nozzle, which are used for solving the existing problems.
The invention discloses an optimization method and system for the point location layout of a fire-fighting nozzle, and the optimization method and system adopts the following technical scheme:
an embodiment of the invention provides an optimization method for a fire sprinkler point location layout, which comprises the following steps:
building a three-dimensional model of any building by using the BIM model to obtain a three-dimensional building model, and equally dividing the three-dimensional building model into a plurality of cubes; in the three-dimensional building model, a genetic algorithm is used to obtain a plurality of initial solutions and a solution set corresponding to each initial solution; the solution set comprises three-dimensional coordinates of all fire sprinklers distributed in the three-dimensional building model;
marking any solution set as a target solution set; each fire-fighting nozzle corresponding to the target solution set is marked as a target nozzle; according to the three-dimensional coordinates of all cube center points and the target solution set, obtaining effective water spraying quantity corresponding to the target solution set; according to the effective water spraying amount corresponding to the target solution set and the distances among all target spray heads, obtaining a fire extinguishing effect corresponding to the target solution set;
in all the initial solutions, obtaining an optimal initial solution according to the fire extinguishing effects corresponding to all the solution sets; counting a plurality of iterative solution sets obtained by the optimal initial solution in the genetic algorithm iteration process, and obtaining a probability adjustment value corresponding to each fire-fighting nozzle according to the distance between the three-dimensional coordinates of each fire-fighting nozzle in all the iterative solution sets;
and obtaining the optimal fire-fighting nozzle point position layout according to the probability adjustment values and the optimal initial solution corresponding to all the fire-fighting nozzles.
Further, according to the three-dimensional coordinates of all cube center points and the target solution set, obtaining the effective water spraying amount corresponding to the target solution set, including the following specific steps:
in the three-dimensional building model, according to the three-dimensional coordinates of all cube center points and the target solution set, using an ANSYS Fluent simulator to obtain the water flow from each cube center point to each target spray head;
marking any cube center point as a target point;
counting the water flow from the target point to each target spray head, and recording the sum of the water flow from the target point to all the target spray heads as the total water quantity of the target point;
and (5) marking the sum of the total water volumes of all cube center points as the effective water spraying volume corresponding to the target solution set.
Further, according to the effective water spraying amount corresponding to the target solution set and the distances among all target spray heads, the fire extinguishing effect corresponding to the target solution set is obtained, and the method comprises the following specific steps:
in the three-dimensional building model, the distance between each target spray head and the target spray head closest to the target spray head is recorded as the closest distance of each target spray head;
and obtaining the fire extinguishing effect corresponding to the target solution set according to the nearest distance of all the target spray heads and the effective water spraying quantity corresponding to the target solution set.
Further, according to the nearest distances of all the target spray heads and the effective water spraying amount corresponding to the target solution set, a specific calculation formula corresponding to the fire extinguishing effect corresponding to the target solution set is obtained as follows:
wherein F is the fire extinguishing effect corresponding to the target solution set, D is the effective water spraying amount corresponding to the target solution set, E is the variance of the nearest distances of all target spray heads,u is the adjustment value of the preset exponential function, which is the exponential function based on the natural constant.
Further, in all the initial solutions, according to the fire extinguishing effects corresponding to all the solution sets, an optimal initial solution is obtained, which comprises the following specific steps:
and counting the maximum value in the fire extinguishing effect corresponding to the solution set corresponding to all the initial solutions, and marking the initial solution corresponding to the maximum value as the optimal initial solution.
Further, the method for obtaining the probability adjustment value corresponding to each fire-fighting nozzle according to the distances between the three-dimensional coordinates of each fire-fighting nozzle in all iterative solution sets by using a plurality of iterative solution sets obtained by the statistical optimal initial solution in the genetic algorithm iterative process comprises the following specific steps:
in the iterative process of the genetic algorithm, the iterative solution set obtained in the last iteration is recorded as an initial optimal solution set; recording any iteration solution set which is not the initial optimal solution set as a reference solution set;
any fire-fighting nozzle is marked as a main nozzle;
according to the three-dimensional coordinates of the main spray head corresponding to the initial optimal solution set and the reference solution set respectively, the distance between the initial optimal solution set and the reference solution set of the main spray head is recorded as the change distance of the main spray head;
the sum of the changing distances of all the fire-fighting nozzles is recorded as the distance between the initial optimal solution set and the reference solution set;
according to the distances between the initial optimal solution set and all other iterative solution sets respectively and the changing distances of the main spray heads corresponding to all other iterative solution sets respectively, obtaining a changing distance sequence of the main spray heads and the weight of each data in the changing distance sequence;
according to the weight of each datum in the change distance sequence of the main spray head, carrying out weighted fitting on the datum in the change distance sequence of the main spray head by using a least square method to obtain a fitting function;
in the changing distance sequence of the main spray head, inputting each data into an output value obtained in a fitting function, and marking the output value as a fitting value corresponding to each data in the changing distance sequence of the main spray head;
and obtaining a probability adjustment value corresponding to the main spray head according to all the data in the change distance sequence of the main spray head and the fitting value corresponding to the data.
Further, according to the distances between the initial optimal solution set and all other iterative solution sets and the changing distances of the main spray heads corresponding to the initial optimal solution set and all other iterative solution sets, obtaining a changing distance sequence of the main spray heads and the weight of each data in the changing distance sequence, the method comprises the following specific steps:
sequencing the distances between the initial optimal solution set and all other iterative solution sets from large to small to obtain a distance sequence;
sequentially counting the change distance of the main spray head corresponding to each data in the distance sequence to obtain a change distance sequence of the main spray head;
normalizing all data in the distance sequence by using a minimum maximum normalization method to obtain a normalized value of each data in the distance sequence;
and (3) marking the normalized value obtained by subtracting each datum in the distance sequence as the weight of the changing distance of the main spray head corresponding to each datum in the distance sequence.
Further, the specific calculation formula corresponding to the probability adjustment value corresponding to the main nozzle is obtained according to all the data in the change distance sequence of the main nozzle and the fitting value corresponding to the data, wherein the specific calculation formula corresponding to the probability adjustment value corresponding to the main nozzle is as follows:
wherein Q is a probability adjustment value corresponding to the main spray head,value of the x-th data in the sequence of changing distance for the main spray head, +.>Fitting value corresponding to the xth data in the changing distance sequence of the main spray head, wherein y is the data quantity in the changing distance sequence of the main spray head, +.>Is a linear normalization function.
Further, the obtaining the optimal fire-fighting nozzle point location layout according to the probability adjustment values and the optimal initial solutions corresponding to all the fire-fighting nozzles comprises the following specific steps:
multiplying the probability adjustment value corresponding to the main spray head by a preset crossover probability to obtain a new crossover probability corresponding to the main spray head;
multiplying the probability adjustment value corresponding to the main spray head by a preset variation probability to obtain a new variation probability corresponding to the main spray head;
and obtaining the optimal fire-fighting nozzle point position layout by using a genetic algorithm according to the new variation probability, the new crossover probability and the optimal initial solution of all the fire-fighting nozzles.
The invention also provides an optimization system for the fire sprinkler point position layout, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor executes the computer program stored in the memory so as to realize the steps of the optimization method for the fire sprinkler point position layout.
The technical scheme of the invention has the beneficial effects that:
in the embodiment of the invention, a three-dimensional building model is obtained, a genetic algorithm is used for obtaining a plurality of initial solutions and solution sets corresponding to each initial solution, and the solution sets comprise three-dimensional coordinates of all fire-fighting nozzles distributed in the three-dimensional building model, so that a fire-fighting effect corresponding to each solution set is obtained. And in all the initial solutions, obtaining an optimal initial solution according to fire extinguishing effects corresponding to all solution sets, wherein the optimal initial solution can ensure that the point position layout effect of the fire fighting nozzle obtained by a subsequent genetic algorithm is better. And counting a plurality of iterative solution sets obtained by the optimal initial solution in the genetic algorithm iterative process, and obtaining a probability adjustment value corresponding to each fire-fighting nozzle according to the distances among the three-dimensional coordinates of each fire-fighting nozzle in all the iterative solution sets. And obtaining the optimal fire-fighting nozzle point position layout according to the probability adjustment values and the optimal initial solution corresponding to all the fire-fighting nozzles. The operation speed of the genetic algorithm is improved by adjusting mutation and crossover probability. The invention realizes optimization of the point position layout of the fire-fighting nozzle and improvement of the layout speed through self-adaptive initial solution, variation and cross probability, and the excellent point position layout of the fire-fighting nozzle ensures that the sprinkler coverage of the fire-fighting nozzle is sufficient, and can effectively prevent fire from spreading, thereby reducing the injury and death risk caused by fire.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of the steps of an optimization method for fire sprinkler point placement according to the present invention.
Detailed Description
In order to further describe the technical means and effects adopted by the invention to achieve the preset aim, the following description refers to the specific implementation, structure, characteristics and effects of an optimizing method and system for fire-fighting nozzle point location layout according to the invention in combination with the accompanying drawings and the preferred embodiment. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The invention provides an optimization method and a system for the point location layout of a fire-fighting nozzle, and the optimization method and the system are specifically described below with reference to the accompanying drawings.
Referring to fig. 1, a flowchart of steps of a method for optimizing a fire sprinkler point layout according to an embodiment of the present invention is shown, the method includes the following steps:
step S001: building a three-dimensional model of any building by using the BIM model to obtain a three-dimensional building model, and equally dividing the three-dimensional building model into a plurality of cubes; in the three-dimensional building model, a genetic algorithm is used to obtain a plurality of initial solutions and a solution set corresponding to each initial solution; the solution set comprises three-dimensional coordinates of all fire sprinklers distributed in the three-dimensional building model.
According to the embodiment, through geometric analysis of the building model body and combination of coverage areas of single fire-fighting nozzles, the fire-fighting nozzle point position layout is completed by utilizing an optimization algorithm, when the fire-fighting nozzle point position layout is carried out by using the optimization algorithm, the spatial model of the building is often required to be rasterized, wherein when the construction is performed, if the grille is too small, the solving efficiency is too slow, and if the grille is too large, the accurate coordinates of the fire-fighting nozzle point position cannot be obtained.
In order to realize the point location layout of the fire sprinkler by adopting an optimized method, the building space model needs to be firstly rasterized, and when the building space model is rasterized, the building space model needs to be firstly acquired.
And constructing a three-dimensional model of any building by using the BIM model to obtain a three-dimensional building model. The Chinese name of the BIM model is a building information model, and the BIM model is a known technology, and a specific method is not described herein.
The number of blocks n set in this example is 100, and the number of fire-fighting nozzles B is 50, which is described as an example, but other values may be set in other embodiments, and this example is not limited thereto.
The three-dimensional building model is equally divided into n cubes with the same size.
It should be noted that the boundaries of the three-dimensional building model may not be divided into a complete cube, but it is still considered as a cube, with each cube being considered as each grid.
In the three-dimensional building model, according to the number of fire sprinklers, a genetic algorithm is used to obtain g initial solutions and solution sets corresponding to each initial solution. The solution set comprises three-dimensional coordinates of B fire fighting nozzles distributed in a three-dimensional building model. The genetic algorithm is a well-known technique, and a specific method is not described herein.
What needs to be described is: the number of initial solutions, the number of iterations, the crossover probability and the mutation probability are the main parameters of the genetic algorithm. The number g of initial solutions set in this embodiment is 20, the number of iterations is 100, the crossover probability is 0.5, and the mutation probability is 0.5, which is described as an example, but other values may be set in other embodiments, and this embodiment is not limited thereto. The solution set corresponding to each initial solution is a fire fighting nozzle point position layout in a three-dimensional building model obtained by a genetic algorithm.
Step S002: marking any solution set as a target solution set; each fire-fighting nozzle corresponding to the target solution set is marked as a target nozzle; according to the three-dimensional coordinates of all cube center points and the target solution set, obtaining effective water spraying quantity corresponding to the target solution set; and obtaining the fire extinguishing effect corresponding to the target solution set according to the effective water spraying amount corresponding to the target solution set and the distances among all the target spray heads.
After the preset parameters are completed, the fire extinguishing range of the single spray nozzle can be evaluated, and the initial grid corresponding to the spray nozzle point positions can be calculated by utilizing a genetic algorithm according to the fire extinguishing range of the single spray nozzle and the number of the spray nozzles. Because of the three-dimensional space, the fire extinguishing effects corresponding to different grids are different when the heights of the spray heads are different, and then, the objective function of the optimization algorithm is constructed according to the fire extinguishing effects corresponding to a single grid. And in the initial grid selection result, acquiring the whole objective function offset caused by different points in the grid, and correcting the objective function again to acquire the final fire sprinkler point position, thereby completing the optimization in the fire sprinkler point position layout process.
When evaluating the fire extinguishing effect of the fire-fighting nozzle and calculating the objective function corresponding to the current solution set, the embodiment selects and utilizes the simulator to simulate and acquire the water flow at each position away from the nozzle as the corresponding fire extinguishing effect.
And recording a solution set corresponding to any one initial solution as a target solution set. And marking each fire-fighting nozzle corresponding to the target solution as a target nozzle.
In the three-dimensional building model, according to the three-dimensional coordinates of all cube center points and the target solution set, an ANSYS Fluent simulator is used for obtaining the water flow from each cube center point to each target spray head. The ANSYS Fluent simulator is a well-known technique, and the specific method is not described here.
What needs to be described is: ANSYS Fluent is a fluid mechanics simulation software used to simulate and analyze various physical phenomena such as flow, heat transfer, chemical reactions, and the like. According to the embodiment, the ANSYS Fluent simulator is adopted to conduct a fire-fighting nozzle water spraying effect model, fire-fighting nozzle 3D model data are firstly input, conditions such as pressure inside the fire-fighting nozzle and external wind speed are set, after the fire-fighting nozzle sprays water for 3 seconds, the water spraying quantity of each fire-fighting nozzle on each cube center point in the three-dimensional building model is obtained, and the water flow from each cube center point to each target nozzle is obtained. The fire-fighting nozzle water spraying time set in this example is 3 seconds, and this is described as an example, and other values may be set in other embodiments, and this example is not limited thereto.
In the three-dimensional building model, any one cube center point is recorded as a target point.
And counting the water flow from the target point to each target spray head, and recording the sum of the water flow from the target point to all the target spray heads as the total water quantity of the target point.
The total water volume at the center point of each cube is obtained in the above manner. And (5) marking the sum of the total water quantity of all cube center points as the effective water spraying quantity D corresponding to the target solution set.
What needs to be described is: the larger the D value is, the larger the water spray amount is, the better the fire extinguishing effect is.
However, as the water amounts of the fire-fighting nozzles are linearly overlapped, the total water amount between different positions at the same height needs to be the same, and the distance interval value between the fire-fighting nozzles needs to be approximate, so that water is sprayed uniformly as much as possible between the fire-fighting nozzles when water is sprayed. Because the fire-fighting spray heads are multiple, each spray head is guaranteed to be approximate to the nearest spray head in distance, the distance value among the spray heads is approximate, and the spray heads are distributed uniformly.
In the three-dimensional building model, the distance between each target spray head and the nearest target spray head is recorded as the nearest distance of each target spray head.
What needs to be described is: taking the Euclidean distance to measure the distance value between two target nozzles may result in a partial building model being traversed, making the distance inconsistent with the actual distance. The distance between any two target nozzles is therefore: in a three-dimensional building model, the path length that the shortest person can pass from one target spray head to another target spray head.
From this, the calculation formula of the fire extinguishing effect F corresponding to the target solution set is known as follows:
wherein F is the fire extinguishing effect corresponding to the target solution set, D is the effective water spraying amount corresponding to the target solution set, E is the variance of the nearest distances of all target spray heads,the present embodiment uses +.>The inverse proportion relation and normalization processing are presented, an implementer can set an inverse proportion function and a normalization function according to actual conditions, u is an adjustment value of an exponential function, and the exponential function is prevented from prematurely tending to 0. Set +.>In the description of this example, other values may be set in other embodiments, and the present example is not limited thereto.
What needs to be described is: the smaller D is, the more uniform the distance among all the target spray heads corresponding to the target solution sets is, the better the fire extinguishing effect is, the larger D is, the better the fire extinguishing effect is, and thereforeAnd E, representing the fire extinguishing effect corresponding to the target solution set.
According to the mode, the fire extinguishing effect corresponding to the solution set corresponding to each initial solution is obtained.
Step S003: in all the initial solutions, obtaining an optimal initial solution according to the fire extinguishing effects corresponding to all the solution sets; and counting a plurality of iterative solution sets obtained by the optimal initial solution in the genetic algorithm iteration process, and obtaining a probability adjustment value corresponding to each fire-fighting nozzle according to the distance between the three-dimensional coordinates of each fire-fighting nozzle in all the iterative solution sets.
And counting the maximum value in the fire extinguishing effect corresponding to the solution set corresponding to all the initial solutions, and marking the initial solution corresponding to the maximum value as the optimal initial solution. And selecting an optimal result for the initial grid by a solution set corresponding to the optimal initial solution.
If the center point of the grid is used as the point position layout position of the fire sprinkler, the accuracy is not enough due to the fact that a larger grid is selected in the initial grid selection, and the optimal solution of the point position layout of the fire sprinkler corresponding to the three-dimensional building model is not necessarily caused.
Furthermore, the grid needs to be refined, but if the grid is directly refined for optimization, the final optimization efficiency can be slow, the approximate position can be quickly locked through the large grid, the calculated amount is reduced, and the solution set range corresponding to the three-dimensional coordinates of the fire fighting nozzle solved next time can be limited in the grid range corresponding to the initial grid selection result.
However, in the grid range corresponding to the initial grid selection result, if the action range of the solution set is limited, although the calculation amount of the fire-fighting nozzle point position layout can be further reduced, because the optimal solution is the only solution, in the initial fire-fighting nozzle point position layout grid selection by utilizing the genetic algorithm, the process that the solution set is continuously approximated to the optimal solution is approximated to the partial solution set that the refined solution set approximates to the optimal solution, so that the refined solution set can be approximated to the optimal solution more quickly, and the probability of variation and intersection of the effective solution set is reduced and the speed of the fire-fighting nozzle point position layout is improved by adjusting the approximation of each solution set in the refined solution set and the effective solution set in the initial grid selection process.
Further obtaining a solution set corresponding to the initial fire-fighting nozzle point position layout grid solved by a genetic algorithm, wherein one fire-fighting nozzle point position can obtain g three-dimensional coordinates in each iteration process of the solution set, and the iteration can obtain g three-dimensional coordinates due to the fact that the iteration frequency is 100Three-dimensional coordinates.
And for all the fire-fighting nozzles, acquiring g solution sets after m iterations corresponding to the m-th iteration, wherein the optimal solution corresponding to the initial fire-fighting nozzle point position layout grid is the solution set corresponding to the optimal initial solution. If the approximation between other solution sets corresponding to all fire-fighting nozzle points in the iterative process and the solution set corresponding to the optimal initial solution is directly utilized to solve the optimal solution, the approach of the optimal solution solved by final refinement to the solution set corresponding to the optimal initial solution rather than the optimal solution may be caused, and even the possibility of being in a local optimal solution may be caused.
And in the initial solution process of the fire-fighting nozzle point position layout grid, the solution set corresponding to the single solution in the mth iteration can predict the corresponding point position of the fire-fighting nozzle point position layout optimal solution through the change of the solution set, and the single solution in the process of finely solving the optimal solution is weighted according to the prediction result. And then, the approximation between a single solution and a predicted optimal solution of the fire nozzle point position layout in the optimal solution process of the fire nozzle point position layout is refined and solved, so that the refined iteration solving process is accelerated.
And obtaining 100 iteration solution sets obtained by the optimal initial solution in 100 iteration processes of the genetic algorithm.
What needs to be described is: other parameters and objective functions are unchanged during the solving process. In the three-dimensional building model, according to the number of fire-fighting nozzles, a genetic algorithm is used for solving, the iteration number of the genetic algorithm is 100, the crossover probability is 0.5, the variation probability is 0.5, and an iteration solution set after each iteration is obtained in 100 iteration processes corresponding to the optimal initial solution.
And in the 100 iterative solution sets, the iterative solution set corresponding to the last iteration is recorded as an initial optimal solution set. And recording any iteration solution set which is not the initial optimal solution set as a reference solution set.
Any one fire-fighting nozzle is marked as a main nozzle. And according to the three-dimensional coordinates of the main spray head corresponding to the initial optimal solution set and the reference solution set respectively, recording the distance between the initial optimal solution set and the reference solution set of the main spray head as the change distance of the main spray head. And (3) recording the sum of the changing distances of all the fire-fighting nozzles as the distance K between the initial optimal solution set and the reference solution set.
What needs to be described is: and when the K value is larger, the relation between the reference solution set and the optimal solution set is weaker, and if the K value is smaller, the relation between the fire-fighting nozzle point position corresponding to the reference solution set and the fire-fighting nozzle point position corresponding to the optimal solution set is stronger and the fire-fighting nozzle point position corresponding to the reference solution set is closer to the optimal solution set.
According to the mode, the distances between the initial optimal solution set and all other iterative solution sets and the changing distance of the corresponding main spray head are obtained in the 100 iterative solution sets.
Because the genetic algorithm generates new solutions through random coding of the solutions in the solving process, and then solves the optimal solutions, the iteration sequence is not important, and then the distances between the initial optimal solution set and all other iteration solution sets are sequenced from large to small to obtain a distance sequence. And sequentially counting the change distance of the main spray head corresponding to each data in the distance sequence to obtain the change distance sequence of the main spray head.
And normalizing all the data in the distance sequence to be within the [0,1] interval by using a minimum and maximum normalization method to obtain the normalized value of each data in the distance sequence. The minimum and maximum normalization method is a well-known technique, and a specific method is not described herein.
And marking the normalized value of each data in the distance sequence subtracted from one value as the weight of the changing distance of the main spray head corresponding to each data in the distance sequence, thereby obtaining the weight of each data in the changing distance sequence of the main spray head.
What needs to be described is: the smaller the distance between the initial optimal solution set and the other iterative solution sets, the larger the corresponding weight.
And carrying out weighted fitting on the changed distance sequence of the main spray head by using a least square method according to the weight of each datum in the changed distance sequence of the main spray head, so as to obtain a fitting function. The weighted fitting of the least squares method is a well-known technique, and the specific method is not described here.
And in the process of carrying out the refined solution, the distance value of the optimal solution corresponding to the single solution set in the refined solution process and the optimal solution corresponding to the initial fire nozzle point position layout grid acquisition process is added into a fitting function fitted by the element values of the corresponding solution sets at the same position in all the single solutions in the initial fire nozzle point position layout grid process, so as to obtain a corresponding fitting value, namely the predicted value of the fire nozzle point position corresponding to the current solution.
Therefore, each data in the changing distance sequence of the main spray head is sequentially input into the fitting function, and a fitting value corresponding to each data in the changing distance sequence of the main spray head is obtained.
The larger the difference value of the actual value of the fitting value is, the larger the difference between the distance value of the corresponding solution set in the single solution in the current refinement solution process at the same spray head and the global optimal solution is, the variation probability and the crossover probability of the corresponding solution set should be improved, if the smaller the difference value of the element value of the fitting value at the same position is, the smaller the difference between the distance value of the corresponding solution set in the single solution in the current refinement solution process at the same spray head and the global optimal solution is, the variation probability and the crossover probability of the corresponding solution set should be reduced.
Therefore, the calculation formula of the probability adjustment value Q corresponding to the main spray head is as follows:
wherein Q is a probability adjustment value corresponding to the main spray head,value of the x-th data in the sequence of changing distance for the main spray head, +.>And y is the data quantity in the change distance sequence of the main spray head. />Normalizing the data values to [0,1] as a linear normalization function]Within the interval.
What needs to be described is:the closer to 1, the closer to the global optimal solution the current distance value is, the lower the probability value of the required variance and crossover, the +.>The less the current distance value is close to 1, the less the current distance value is close to the global optimal solution, the higher the probability value of the required variation and crossover is, and the +.>The normalized value of (2) represents the probability adjustment value corresponding to the main spray head.
Step S004: and obtaining the optimal fire-fighting nozzle point position layout according to the probability adjustment values and the optimal initial solution corresponding to all the fire-fighting nozzles.
The product of Q and the crossover probability of 0.5 is recorded as the new crossover probability corresponding to the main spray head. And (5) marking the product of Q and the variation probability of 0.5 as a new variation probability corresponding to the main spray head.
According to the mode, the new variation probability and the new crossover probability of each fire sprinkler are obtained.
And obtaining the optimal fire-fighting nozzle point position layout by using a genetic algorithm according to the new variation probability, the new crossover probability and the optimal initial solution of all the fire-fighting nozzles. The genetic algorithm is a well-known technique, and a specific method is not described herein.
What needs to be described is: in the three-dimensional building model, according to the number of fire-fighting nozzles, the new variation probability, the new crossover probability and the optimal initial solution of all the fire-fighting nozzles are utilized, and the optimal initial solution is unique, so that a solution set obtained by using a genetic algorithm is unique, and the solution set comprises three-dimensional coordinates of all the fire-fighting nozzles distributed in the three-dimensional building model, so that the solution set is the layout of the optimal fire-fighting nozzle points. Therefore, the speed of solving the point position of the fire fighting nozzle corresponding to the optimal solution is improved, and the optimization in the process of solving the point position of the fire fighting nozzle by the genetic algorithm is completed.
The present invention has been completed.
In summary, in the embodiment of the present invention, a three-dimensional building model is obtained, and then a genetic algorithm is used to obtain a plurality of initial solutions and solution sets corresponding to each initial solution, where the solution sets include three-dimensional coordinates of all fire-fighting nozzles distributed in the three-dimensional building model, so as to obtain a fire-extinguishing effect corresponding to each solution set. And in all the initial solutions, according to the fire extinguishing effects corresponding to all the solution sets, obtaining an optimal initial solution, counting a plurality of iteration solution sets obtained in the genetic algorithm iteration process by the optimal initial solution, and according to the distances among the three-dimensional coordinates of each fire fighting nozzle in all the iteration solution sets, obtaining a probability adjustment value corresponding to each fire fighting nozzle. And obtaining the optimal fire-fighting nozzle point position layout according to the probability adjustment values and the optimal initial solution corresponding to all the fire-fighting nozzles. According to the invention, through self-adaptive initial solution, variation and crossover probability, optimization of the point location layout of the fire-fighting nozzle and improvement of the layout speed are realized, so that injury and death risks caused by fire disaster are reduced.
The invention also provides an optimizing system for the fire sprinkler point position layout, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor executes the computer program stored in the memory to realize the steps of the optimizing method for the fire sprinkler point position layout.
The above description is only of the preferred embodiments of the present invention and is not intended to limit the invention, but any modifications, equivalent substitutions, improvements, etc. within the principles of the present invention should be included in the scope of the present invention.
Claims (7)
1. An optimization method for the point location layout of a fire sprinkler, which is characterized by comprising the following steps:
building a three-dimensional model of any building by using the BIM model to obtain a three-dimensional building model, and equally dividing the three-dimensional building model into a plurality of cubes; in the three-dimensional building model, a genetic algorithm is used to obtain a plurality of initial solutions and a solution set corresponding to each initial solution; the solution set comprises three-dimensional coordinates of all fire sprinklers distributed in the three-dimensional building model;
marking any solution set as a target solution set; each fire-fighting nozzle corresponding to the target solution set is marked as a target nozzle; according to the three-dimensional coordinates of all cube center points and the target solution set, obtaining effective water spraying quantity corresponding to the target solution set; according to the effective water spraying amount corresponding to the target solution set and the distances among all target spray heads, obtaining a fire extinguishing effect corresponding to the target solution set;
in all the initial solutions, obtaining an optimal initial solution according to the fire extinguishing effects corresponding to all the solution sets; counting a plurality of iterative solution sets obtained by the optimal initial solution in the genetic algorithm iteration process, and obtaining a probability adjustment value corresponding to each fire-fighting nozzle according to the distance between the three-dimensional coordinates of each fire-fighting nozzle in all the iterative solution sets;
obtaining the optimal fire-fighting nozzle point position layout according to the probability adjustment values and the optimal initial solution corresponding to all the fire-fighting nozzles;
the method comprises the following specific steps of:
in the iterative process of the genetic algorithm, the iterative solution set obtained in the last iteration is recorded as an initial optimal solution set; recording any iteration solution set which is not the initial optimal solution set as a reference solution set;
any fire-fighting nozzle is marked as a main nozzle;
according to the three-dimensional coordinates of the main spray head corresponding to the initial optimal solution set and the reference solution set respectively, the distance between the initial optimal solution set and the reference solution set of the main spray head is recorded as the change distance of the main spray head;
the sum of the changing distances of all the fire-fighting nozzles is recorded as the distance between the initial optimal solution set and the reference solution set;
according to the distances between the initial optimal solution set and all other iterative solution sets respectively and the changing distances of the main spray heads corresponding to all other iterative solution sets respectively, obtaining a changing distance sequence of the main spray heads and the weight of each data in the changing distance sequence;
according to the weight of each datum in the change distance sequence of the main spray head, carrying out weighted fitting on the datum in the change distance sequence of the main spray head by using a least square method to obtain a fitting function;
in the changing distance sequence of the main spray head, inputting each data into an output value obtained in a fitting function, and marking the output value as a fitting value corresponding to each data in the changing distance sequence of the main spray head;
obtaining a probability adjustment value corresponding to the main spray head according to all data in the changed distance sequence of the main spray head and the fitting value corresponding to the data;
according to the distances between the initial optimal solution set and all other iterative solution sets and the changing distances of the main spray heads corresponding to the initial optimal solution set and all other iterative solution sets, obtaining a changing distance sequence of the main spray heads and the weight of each data in the changing distance sequence, comprising the following specific steps:
sequencing the distances between the initial optimal solution set and all other iterative solution sets from large to small to obtain a distance sequence;
sequentially counting the change distance of the main spray head corresponding to each data in the distance sequence to obtain a change distance sequence of the main spray head;
normalizing all data in the distance sequence by using a minimum maximum normalization method to obtain a normalized value of each data in the distance sequence;
the normalized value of each data in the distance sequence is subtracted and recorded as the weight of the changing distance of the main spray head corresponding to each data in the distance sequence;
the specific calculation formula corresponding to the probability adjustment value corresponding to the main spray head is obtained according to all the data in the change distance sequence of the main spray head and the fitting value corresponding to the data, wherein the specific calculation formula corresponding to the probability adjustment value corresponding to the main spray head is as follows:
wherein Q is a probability adjustment value corresponding to the main spray head,is the value of the x-th data in the changed distance sequence of the main spray head,fitting value corresponding to the xth data in the changing distance sequence of the main spray head, wherein y is the data quantity in the changing distance sequence of the main spray head, +.>Is a linear normalization function.
2. The optimizing method for fire-fighting nozzle point location layout according to claim 1, wherein the obtaining the effective water spraying amount corresponding to the target solution set according to the three-dimensional coordinates of all cube center points and the target solution set comprises the following specific steps:
in the three-dimensional building model, according to the three-dimensional coordinates of all cube center points and the target solution set, using an ANSYS Fluent simulator to obtain the water flow from each cube center point to each target spray head;
marking any cube center point as a target point;
counting the water flow from the target point to each target spray head, and recording the sum of the water flow from the target point to all the target spray heads as the total water quantity of the target point;
and (5) marking the sum of the total water volumes of all cube center points as the effective water spraying volume corresponding to the target solution set.
3. The optimizing method for fire-fighting nozzle point location layout according to claim 1, wherein the obtaining the fire-fighting effect corresponding to the target solution set according to the effective water spray amount corresponding to the target solution set and the distances between all target nozzles comprises the following specific steps:
in the three-dimensional building model, the distance between each target spray head and the target spray head closest to the target spray head is recorded as the closest distance of each target spray head;
and obtaining the fire extinguishing effect corresponding to the target solution set according to the nearest distance of all the target spray heads and the effective water spraying quantity corresponding to the target solution set.
4. The optimization method for the point location layout of the fire-fighting nozzle according to claim 3, wherein the specific calculation formula corresponding to the fire-fighting effect corresponding to the target solution set is obtained according to the nearest distance of all the target nozzles and the effective water spraying amount corresponding to the target solution set, and is as follows:
wherein F is the fire extinguishing effect corresponding to the target solution set, D is the effective water spraying amount corresponding to the target solution set, E is the variance of the nearest distances of all target spray heads,u is the adjustment value of the preset exponential function, which is the exponential function based on the natural constant.
5. The optimizing method for fire-fighting nozzle point location layout according to claim 1, wherein in all initial solutions, according to fire-fighting effects corresponding to all solution sets, an optimal initial solution is obtained, comprising the following specific steps:
and counting the maximum value in the fire extinguishing effect corresponding to the solution set corresponding to all the initial solutions, and marking the initial solution corresponding to the maximum value as the optimal initial solution.
6. The optimizing method for fire-fighting nozzle point position layout according to claim 1, wherein the obtaining the optimal fire-fighting nozzle point position layout according to the probability adjustment values and the optimal initial solutions corresponding to all fire-fighting nozzles comprises the following specific steps:
multiplying the probability adjustment value corresponding to the main spray head by a preset crossover probability to obtain a new crossover probability corresponding to the main spray head;
multiplying the probability adjustment value corresponding to the main spray head by a preset variation probability to obtain a new variation probability corresponding to the main spray head;
and obtaining the optimal fire-fighting nozzle point position layout by using a genetic algorithm according to the new variation probability, the new crossover probability and the optimal initial solution of all the fire-fighting nozzles.
7. An optimization system for a fire nozzle point layout comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the computer program when executed by the processor implements the steps of an optimization method for a fire nozzle point layout as claimed in any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311491673.7A CN117236196B (en) | 2023-11-10 | 2023-11-10 | Optimization method and system for point location layout of fire-fighting nozzle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311491673.7A CN117236196B (en) | 2023-11-10 | 2023-11-10 | Optimization method and system for point location layout of fire-fighting nozzle |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117236196A CN117236196A (en) | 2023-12-15 |
| CN117236196B true CN117236196B (en) | 2024-02-27 |
Family
ID=89088349
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311491673.7A Active CN117236196B (en) | 2023-11-10 | 2023-11-10 | Optimization method and system for point location layout of fire-fighting nozzle |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117236196B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN202459924U (en) * | 2012-02-08 | 2012-10-03 | 肖金贵 | Intelligent large public building fire-fighting system based on large-span spatial layout |
| CN108039014A (en) * | 2017-12-05 | 2018-05-15 | 成都猎维科技有限公司 | A kind of equipment of manually intelligent full filed detection fire behavior |
| CN115238356A (en) * | 2022-07-25 | 2022-10-25 | 睿建智慧科技(珠海)有限责任公司 | Design method of fire-fighting nozzle arrangement, computer device and computer readable storage medium |
| CN116663119A (en) * | 2023-06-06 | 2023-08-29 | 华电云南发电有限公司以礼河发电厂 | Layout method, device, equipment and storage medium based on water mist fire terminal |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060021766A1 (en) * | 2004-07-27 | 2006-02-02 | Tyco Fire Products Lp | Residential dry sprinkler design method and system with fire resistant plastic components |
| US20150265865A1 (en) * | 2014-03-19 | 2015-09-24 | Jeffrey J. Pigeon | Fire sprinkler system |
-
2023
- 2023-11-10 CN CN202311491673.7A patent/CN117236196B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN202459924U (en) * | 2012-02-08 | 2012-10-03 | 肖金贵 | Intelligent large public building fire-fighting system based on large-span spatial layout |
| CN108039014A (en) * | 2017-12-05 | 2018-05-15 | 成都猎维科技有限公司 | A kind of equipment of manually intelligent full filed detection fire behavior |
| CN115238356A (en) * | 2022-07-25 | 2022-10-25 | 睿建智慧科技(珠海)有限责任公司 | Design method of fire-fighting nozzle arrangement, computer device and computer readable storage medium |
| CN116663119A (en) * | 2023-06-06 | 2023-08-29 | 华电云南发电有限公司以礼河发电厂 | Layout method, device, equipment and storage medium based on water mist fire terminal |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117236196A (en) | 2023-12-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106390456B (en) | The generation method and device of role-act in game | |
| CN107457780B (en) | Method and device for controlling mechanical arm movement, storage medium and terminal equipment | |
| CN104922906B (en) | Action executes method and apparatus | |
| CN109299778B (en) | RCRSS rescue map partition calculation method based on cuckoo search algorithm | |
| JPWO2020159568A5 (en) | ||
| CN117236196B (en) | Optimization method and system for point location layout of fire-fighting nozzle | |
| CN108460172A (en) | Numerical value blast analogue method and its system | |
| CA3162812A1 (en) | System and method for risk sensitive reinforcement learning architecture | |
| CN114970302B (en) | Regional groundwater condition prediction method based on groundwater monitoring system | |
| CN112717420A (en) | Game formation generation method and system, storage medium and server | |
| CN113392539A (en) | Robot communication control method, system and equipment based on federal reinforcement learning | |
| CN108694465A (en) | Urban SOS Simulation Decision optimization method based on the Q study of SVM vector machines | |
| CN106844986B (en) | Deck layout calculation method based on improved genetic algorithm | |
| CN110665223A (en) | Game resource caching method, decision network training method and device | |
| CN105825267B (en) | A kind of indoor orientation method based on PSO-PGSA | |
| CN109493065A (en) | A kind of fraudulent trading detection method of Behavior-based control incremental update | |
| CN110457736B (en) | Markov chain based fire prediction in RCRSS | |
| CN111265871A (en) | Virtual object control method and device, equipment and storage medium | |
| Ali et al. | Statistical downscaling of precipitation and temperature using gene expression programming | |
| Chai et al. | Amazons Evaluation Optimization Strategy Based on PSO Algorithm | |
| CN114967679B (en) | Self-adaptive control method and system for fire-fighting robot path | |
| CN109116990A (en) | A kind of method, apparatus, equipment and the computer readable storage medium of mobile control | |
| KR102315842B1 (en) | System for providing carom billards guidance service using reinforcement learning of deep learning model | |
| CN108981707A (en) | The passive tracking multi-target method of case particle PHD is measured based on the time difference | |
| CN115270214A (en) | CAD (computer-aided design) -based spray point location planning method, device, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |