A method and device for robust optimization of fire extinguishing paths in fire scenarios

Abstract

The embodiment of the present application proposes a method and device for robust optimization of fire extinguishing paths in fire scenarios, the method comprising: obtaining fire dynamics parameters corresponding to preset fire conditions in a preset building; establishing a fire extinguishing path robust optimization model for the building in the fire scenario based on the fire dynamics parameters; obtaining a fire extinguishing path robust optimization result in the building fire scenario through the fire extinguishing path robust optimization model and the Ivy optimization algorithm improved by the Newton-Raphson optimization algorithm. The method establishes a fire extinguishing path robust optimization model based on fire dynamics parameters, and optimizes the results based on the Ivy optimization algorithm improved by the Newton-Raphson optimization algorithm, ensuring the stability, reliability and practical operation value of the formulated fire extinguishing path optimization strategy.

Description

Technical Field

[0001] The present application relates to the field of emergency safety technology, and in particular to a method and device for robust optimization of fire extinguishing paths in fire scenarios. Background Art

[0002] At present, urbanization has become the development trend of the current society. More and more people live in cities. In the process of urbanization, buildings are an important part of public transportation, and their safety and emergency response capabilities are particularly important. However, fire is one of the major disasters that buildings may face. Once it occurs, its rapid spread and the heat radiation it produces pose a serious threat to the life safety of pedestrians and workers. In order to effectively deal with building fires, improve fire extinguishing efficiency and reduce losses, the study of pedestrian evacuation in buildings under fire scenarios needs to be paid attention to. A robust optimization method for fire extinguishing paths under fire scenarios has emerged.

[0003] Existing research has explored the optimization of fire extinguishing paths in fire scenarios, but it does not take into account the uncertainty of fire heat radiation and the generated combustion products in the fire scenario for workers in the fire extinguishing process. The solutions of the fire extinguishing path schemes are often too conservative, which may lead to poor fire extinguishing effects in practical problems. In order to overcome the shortcomings of existing research and improve the reliability and flexibility of fire extinguishing path optimization, technicians in the field are in urgent need of a fire extinguishing path optimization method in fire scenarios that can take into account the interference of uncertain factors in the fire extinguishing process.

[0004] Therefore, a better method is now needed to solve this technical problem. Summary of the invention

[0005] In view of the defects in the prior art, the present application proposes a method and device for robust optimization of fire extinguishing paths in fire scenarios.

[0006] Specifically, this application proposes the following specific embodiments:

[0007] The embodiment of the present application proposes a method for robust optimization of fire extinguishing paths in a fire scenario, including:

[0008] Obtaining fire dynamics parameters corresponding to a preset fire situation in a preset building;

[0009] Establishing a fire extinguishing path robust optimization model for the building under the fire scenario based on the fire dynamics parameters;

[0010] The robust optimization result of the fire extinguishing path in the building fire scenario is obtained by using the fire extinguishing path robust optimization model and the ivy optimization algorithm improved by the Newton-Raphson optimization algorithm.

[0011] In the embodiment of the present application, the obtaining of fire dynamics parameters corresponding to a preset fire situation in a preset building includes:

[0012] Obtaining structural data of a preset building;

[0013] Establishing a simulation model inside the building based on the structural data and a preset fire dynamics model;

[0014] Obtaining fire point location and heat radiation data from a preset fire situation through the simulation model in the building;

[0015] The fire point position and the thermal radiation data are used as fire dynamics parameters.

[0016] In an embodiment of the present application, the fire extinguishing path robust optimization model for the building in the fire scenario is established based on the fire dynamics parameters, including:

[0017] Importing the fire dynamics parameters into the simulation model obtained by modeling the building, simulating fire combustion by following the law of conservation of mass, the law of conservation of energy and the law of conservation of momentum, analyzing the movement of smoke, the temperature and the changes in the concentration of toxic gases when a fire occurs in the building, so as to determine the fire extinguishing path cost, the labor cost target and the fire rescue value target;

[0018] Establishing an initial model based on the fire extinguishing path cost, the labor cost target and the fire rescue value target;

[0019] Obtaining an uncertainty set of constraints of the initial model;

[0020] The uncertainty set of the constraint conditions is transformed to obtain a box-polyhedron fluctuation set of the uncertainty set;

[0021] The box-polyhedron fluctuation set of the uncertainty set is transformed to obtain a cone representation of the box-polyhedron fluctuation set;

[0022] converting the semi-infinite constraint of the constraint condition into a cone constraint according to the cone representation of the box-polyhedron fluctuation set;

[0023] Performing variable elimination and substitution processing on each feasible solution in the cone constraint to obtain a linear equivalent form of the initial model constraint condition;

[0024] A robust optimization model of the fire extinguishing path of the building under the fire scenario is established based on the linear equivalent form of the initial model constraint conditions and the initial model.

[0025] In the embodiment of the present application, the initial model is established based on the fire extinguishing path cost, the labor cost target and the fire rescue value target, which is expressed by the following formula:

[0026] ;

[0027] ;

[0028] ;

[0029] ;

[0030] ;

[0031] ;

[0032] ;

[0033] ;

[0034] in, Indicates that the decision variable is affected by the uncertainty set, It represents the uncertainty of the time it takes for workers to extinguish the fire. It is expressed as the uncertainty of the workers’ travel time; is the weight corresponding to the worker's path cost, is the weight corresponding to the labor cost of the staff, is the weight corresponding to the rescue value of the fire; , The fire fighting team assembled, , is the collection of all nodes, , It is a collection of all fire points; Representation Node and The distance between is a decision variable. If the fire fighting team passes through the path , then it is equal to 1, otherwise it is 0; If the fire point Fire Fighting Team If it is eliminated, it is equal to 1, otherwise it is 0; For fire point The rescue value; is the decay formula of the rescue value of the fire point, For fire point The decay coefficient of rescue value; , is an auxiliary variable; Indicates that the staff extinguished the fire point The time required to extinguish the fire; Indicates that the staff from the fire point To the fire site Journey time; is a decision variable, if the fire point If it is extinguished, it is equal to 1, otherwise it is 0; is a decision variable. If the fire fighting team passes through the path , then it is equal to 1, otherwise it is 0; It is represented as the uncertainty set of the travel time between workers’ fire nodes; It is represented as the uncertainty set of the fire extinguishing time of the staff; , Representation Node Travel time between or fire point The number of deviation vectors of fire extinguishing time; Ensure that each fire point must be extinguished by one and only one group of workers; , It means that the staff must start from the starting point and return to the starting point to finish; It means that after the workers put out the fire, they leave from here to ensure the continuity of the route; Fire Fighting Team Arrival at the fire site time; Fire Fighting Team Arrival at the fire site time.

[0035] In the embodiment of the present application, the uncertainty set of the travel time between the fire nodes of the staff is and the uncertainty set of the firefighting time of the staff It is expressed by the following formula:

[0036] ;

[0037] ;

[0038] in, Representation Node The predicted value of the travel time between Indicates the fire point Prediction of fire extinguishing time; , The set of real numbers; Representation Node Nominal value of travel time between Indicates the fire point Nominal value of fire extinguishing time; Representation Node Deviation vector of travel time between them; Indicates the fire point Deviation vector of fire extinguishing time; is the uncertainty set of the travel time between nodes The control parameter of , is the travel time uncertainty budget coefficient, , Indicates the working group A collection of paths you have traveled; For fire point Uncertainty set of fire extinguishing time The control parameter of , For fire point Fire extinguishing time uncertainty budget coefficient, , Indicates the working group A collection of fire spots you have experienced; , Representation Node Travel time between or fire point The number of deviation vectors of fire extinguishing time;

[0039] The box-polyhedron fluctuation set of the uncertainty set is obtained by transforming the uncertainty set of the initial model constraint conditions, which is expressed by the following formula:

[0040] ;

[0041] ;

[0042] in, The box-polyhedron fluctuation set represented as the uncertainty set of travel time between workers’ fire nodes; It is represented as a box-polyhedron fluctuation set of the uncertain set of firefighting time of the workers; is represented as the set of real numbers;

[0043] The box-polyhedron fluctuation set according to the uncertainty set is transformed to obtain a cone representation of the box-polyhedron fluctuation set, which is represented by the following formula:

[0044]

[0045] , and , so its dual cone is ;

[0046] , and , so its dual cone is ;

[0047]

[0048] , and , so its dual cone is ;

[0049] , and , so its dual cone is ;

[0050] in, and is an auxiliary variable;

[0051] The constraints of the initial model are represented by the cone representation of the box-polyhedron wave set. , The semi-infinite constraint is transformed into a cone constraint, which is expressed by the following formula:

[0052] ;

[0053] , , ;

[0054] , ;

[0055] ;

[0056] Among them, , ,in , ;

[0057] , ;

[0058] , , ;

[0059] , ;

[0060] ;

[0061] Among them, , ,in , ;

[0062] Variable elimination and substitution are performed for each feasible solution in the cone constraint to obtain a linear equivalent form of the initial model constraint condition, which is expressed by the following formula:

[0063]

[0064] , ,

[0065] in, ,

[0066] , ,

[0067] , ,

[0068] in, , .

[0069] In the embodiment of the present application, the fire extinguishing path robust optimization result in the building fire scenario is obtained by improving the ivy optimization algorithm through the fire extinguishing path robust optimization model and the Newton-Raphson optimization algorithm, including:

[0070] The fire extinguishing path robust optimization model is solved by improving the Ivy optimization algorithm based on the Newton-Raphson optimization algorithm to obtain a potential high-quality solution area;

[0071] Use global search to search for potential high-quality solution areas. When a potential optimal solution area is found, switch to the NRBO algorithm to perform local search on the potential optimal solution area to obtain the cost function of the current fire point where the staff is located for the selectable fire points.

[0072] The next node is determined by selecting the one with the smallest cost function until the optimized fire extinguishing path is obtained as the robust optimization result of the fire extinguishing path in the building fire scenario.

[0073] In the embodiment of the present application, the improved Ivy optimization algorithm based on the Newton-Raphson optimization algorithm solves the fire extinguishing path robust optimization model to obtain potential high-quality solution areas, including:

[0074] Solving the fire extinguishing path robust optimization model based on the improved ivy optimization algorithm of the Newton-Raphson optimization algorithm to determine the initial position of the ivy population in the search space;

[0075] Based on the initial position, the ivy population growth is performed based on the ivy optimization algorithm;

[0076] Based on the sunlight source in the ivy optimization algorithm, determine the movement mode of each member of the ivy population using other members during the growth of the ivy population;

[0077] Determine the results of the members of the ivy population searching for the optimal solution in the surrounding area as the potential high-quality solution area.

[0078] In the embodiment of the present application, the initial position of the ivy population in the search space is determined by the following formula:

[0079]

[0080] Among them, the vector with dimension D of uniformly distributed random numbers in the interval [0,1] is represented by express; and are the upper and lower bounds of the search space respectively. The Hadamard product of two vectors is represented by the operation “⊙”;

[0081] The ivy population growth based on the ivy optimization algorithm is performed based on the initial position, which is determined by the following formula:

[0082]

[0083] in, is the growth rate, is the growth rate, is the correction factor for deviation growth, the vector and Represents a discrete-time system (time and time )’s growth rate, Is the interval The random real numbers in ), is a random number of a random variable whose probability density function is equal to , The dimension is The random vector is a random number from a standard Gaussian (normal) distribution;

[0084] Based on the sunlight source in the ivy optimization algorithm, the movement mode of each member of the ivy population using other members during the growth of the ivy population is determined by the following formula:

[0085]

[0086]

[0087] in, is a vector whose components are vectors The absolute value of the components of ” is a vector Divide by vector Hadamard division of

[0088] The result of finding the optimal solution for the surrounding area by members of the ivy population is determined by the following formula:

[0089]

[0090] .

[0091] In the embodiment of the present application, the global search is used to search for potential high-quality solution areas. When a potential optimal solution area is found, the NRBO algorithm is switched to perform a local search for the potential optimal solution area to obtain a cost function of the current fire point where the staff is located for the selectable fire points, including:

[0092] Search for potential high-quality solution areas based on Newton-Raphson search rules;

[0093] When a potential optimal solution area is found, the algorithm is switched to the NRBO algorithm to perform a local search on the potential optimal solution area, and the cost function of the current fire point where the staff is located for the selectable fire points is obtained;

[0094] The Newton-Raphson based search rule is expressed as follows:

[0095] ;

[0096] ;

[0097] ;

[0098] ;

[0099] ;

[0100] in, Represents a normally distributed random number with a mean of 0 and a variance of 1; and is used and The positions of the two vectors generated; Indicates the worst position, Indicates the best position; and express A random number between and The values ​​of are not equal; By updating The new vector position is obtained; a and b are A random number between

[0101] The trap avoidance operator in the NRBO algorithm is expressed as follows:

[0102]

[0103]

[0104] in, Indicates the best position; and They are and A consistent random number between ; Indicates the current iteration number; and is a random number; adaptive function The value of Changes between.

[0105] The embodiment of the present application also proposes a device for robust optimization of fire extinguishing paths in fire scenarios, including a processor, in which an executable file for executing the above method is stored.

[0106] The embodiment of the present application proposes a method and device for robust optimization of fire extinguishing paths in fire scenarios, the method comprising: obtaining fire dynamics parameters corresponding to preset fire conditions in a preset building; establishing a fire extinguishing path robust optimization model for the building in the fire scenario based on the fire dynamics parameters; obtaining a fire extinguishing path robust optimization result in a building fire scenario through the fire extinguishing path robust optimization model and the Ivy optimization algorithm improved by the Newton-Raphson optimization algorithm. The method establishes a fire extinguishing path robust optimization model based on fire dynamics parameters, and optimizes the results based on the Ivy optimization algorithm improved by the Newton-Raphson optimization algorithm, ensuring the stability, reliability and practical operation value of the formulated fire extinguishing path optimization strategy. BRIEF DESCRIPTION OF THE DRAWINGS

[0107] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0108] Figure 1 A flowchart of a method for robust optimization of fire extinguishing paths in a fire scenario proposed in an embodiment of the present application;

[0109] Figure 2 A simulation model diagram of pedestrian evacuation in a building in a method for robust optimization of fire extinguishing paths in a fire scenario proposed in an embodiment of the present application;

[0110] Figure 3 A fire heat radiation distribution diagram of a fire dynamics software in a method for robust optimization of a fire extinguishing path in a fire scenario proposed in an embodiment of the present application;

[0111] Figure 4 A schematic diagram of the structural framework of a model output optimization algorithm in a method for robust optimization of fire extinguishing paths in a fire scenario proposed in an embodiment of the present application. DETAILED DESCRIPTION

[0112] In the following, various embodiments of the present disclosure will be described more fully. The present disclosure may have various embodiments, and adjustments and changes may be made therein. However, it should be understood that there is no intention to limit the various embodiments of the present disclosure to the specific embodiments disclosed herein, but rather the present disclosure should be understood to cover all adjustments, equivalents and / or alternatives that fall within the spirit and scope of the various embodiments of the present disclosure.

[0113] The terms used in the various embodiments of the present disclosure are only used for the purpose of describing specific embodiments and are not intended to limit the various embodiments of the present disclosure. As used herein, the singular form is intended to also include the plural form, unless the context clearly indicates otherwise. Unless otherwise defined, all terms (including technical terms and scientific terms) used herein have the same meaning as the meanings commonly understood by ordinary technicians in the field to which the various embodiments of the present disclosure belong. The terms (such as the terms defined in the generally used dictionary) will be interpreted as having the same meaning as the contextual meaning in the relevant technical field and will not be interpreted as having an idealized meaning or an overly formal meaning, unless clearly defined in the various embodiments of the present disclosure.

[0114] Example 1

[0115] The present application embodiment proposes a method for robust optimization of fire extinguishing paths in fire scenarios, such as Figure 1 As shown, the following steps are included:

[0116] Step 101. Obtaining fire dynamics parameters corresponding to a preset fire situation in a preset building;

[0117] Step 102: Establish a fire extinguishing path robust optimization model for a building in a fire scenario based on fire dynamics parameters;

[0118] Step 103. Obtain the robust optimization result of the fire extinguishing path in the building fire scenario through the fire extinguishing path robust optimization model and the ivy optimization algorithm improved by the Newton-Raphson optimization algorithm.

[0119] Specifically, the step 101 of obtaining the fire dynamics parameters corresponding to the preset fire situation in the preset building includes:

[0120] Acquire preset structural data of the building; the specific structural data may be, for example, 2D or 3D structural data of the building, and the specific data format may be CAD format or other data formats.

[0121] A simulation model inside the building is established based on the structural data and a preset fire dynamics model; specifically, the fire dynamics model can be fire dynamics software.

[0122] The fire point location and heat radiation data are obtained from the preset fire situation through the simulation model in the building; specifically, different fire situations correspond to the fire point location and heat radiation.

[0123] The fire point location and thermal radiation data are used as fire dynamics parameters.

[0124] Furthermore, in step 102, a robust optimization model of fire extinguishing paths for buildings in fire scenarios is established based on fire dynamics parameters, including:

[0125] Import the fire dynamics parameters into the simulation model obtained by modeling the building, simulate the fire combustion by following the law of conservation of mass, energy and momentum, analyze the movement of smoke, temperature and changes in toxic gas concentration when a fire occurs in the building, so as to determine the fire extinguishing path cost, labor cost target and fire rescue value target;

[0126] Specifically, the location, quantity and thermal radiation parameters of the initial fire of the building can be obtained. In this embodiment, the location, quantity and thermal radiation parameters of the initial fire, after obtaining the known conditions, set the grid and boundary conditions in the software, set the model to complete the building modeling, and the model simulates the fire combustion by following the law of conservation of mass, the law of conservation of energy and the law of conservation of momentum, and analyzes the movement of smoke, the temperature and the changes in the concentration of toxic gases. For the building scene studied in the present invention, the basic equations include:

[0127]

[0128]

[0129]

[0130] in, is the gas density, is the velocity vector, is the sensible enthalpy. is the pressure, defined as . T is the temperature, is the ideal gas constant, is the molecular weight of the gas mixture. q is the heat release rate per unit volume, is the heat flux vector, is the dissipation function. is gravity and velocity, is the external vector, is the viscous stress tensor of the Newtonian fluid.

[0131] also, The rescue value of the fire rescue value target will be affected by the location of the fire point and the importance of the pedestrian evacuation node. The calculation formula is as follows:

[0132]

[0133] in, , A collection of all pedestrian evacuation nodes; Indicates the fire point and evacuation nodes The distance between Indicates evacuation node Number of people passing through.

[0134] is the fire point rescue value decay coefficient, which will be affected by the initial heat radiation of the fire point. The calculation formula is as follows:

[0135]

[0136] in, For fire point Thermal radiation at time 0.

[0137] Establish an initial model based on fire extinguishing path cost, labor cost target and fire rescue value target;

[0138] An initial model is established based on the fire extinguishing path cost, labor cost target, and fire rescue value target, which is expressed by the following formula:

[0139] ;

[0140] ;

[0141] ;

[0142] ;

[0143] ;

[0144] ;

[0145] ;

[0146] ;

[0147] in, Indicates that the decision variable is affected by the uncertainty set, It represents the uncertainty of the time it takes for workers to extinguish the fire. It is expressed as the uncertainty of the workers’ travel time; is the weight corresponding to the worker's path cost, is the weight corresponding to the labor cost of the staff, is the weight corresponding to the rescue value of the fire; , The fire fighting team assembled, , is the collection of all nodes, , It is a collection of all fire points; Representation Node and The distance between is a decision variable. If the fire fighting team passes through the path , then it is equal to 1, otherwise it is 0; If the fire point Fire Fighting Team If it is eliminated, it is equal to 1, otherwise it is 0; Indicates that the staff extinguished the fire point The time required to extinguish the fire; Indicates that the staff from the fire point To the fire site Journey time; is a decision variable, if the fire point If it is extinguished, it is equal to 1, otherwise it is 0; is a decision variable. If the fire fighting team passes through the path , then it is equal to 1, otherwise it is 0; For fire point The rescue value; is the decay formula of the rescue value of the fire point, For fire point The decay coefficient of rescue value; , is an auxiliary variable; It is represented as the uncertainty set of the travel time between workers’ fire nodes; It is represented as the uncertainty set of the fire extinguishing time of the staff; , Representation Node Travel time between or fire point The number of deviation vectors of fire extinguishing time; Ensure that each fire point must be extinguished by one and only one group of workers; , It means that the staff must start from the starting point and return to the starting point to finish; It means that after the workers put out the fire, they leave from here to ensure the continuity of the route; Fire Fighting Team Arrival at the fire site time; Fire Fighting Team Arrival at the fire site time; fire point i is the previous point of fire point j.

[0148] The uncertainty set of the travel time between the workers' fire nodes is and the uncertainty set of the firefighting time of the staff It is expressed by the following formula:

[0149] ;

[0150] ;

[0151] in, Representation Node The predicted value of the travel time between Indicates the fire point Prediction of fire extinguishing time; , The set of real numbers; Representation Node Nominal value of travel time between Indicates the fire point Nominal value of fire extinguishing time; Representation Node Deviation vector of travel time between them; Indicates the fire point Deviation vector of fire extinguishing time; is the uncertainty set of the travel time between nodes The control parameter of , is the travel time uncertainty budget coefficient, , Indicates the working group A collection of paths you have traveled; For fire point Uncertainty set of fire extinguishing time The control parameter of , For fire point Fire extinguishing time uncertainty budget coefficient, , Indicates the working group A collection of fire spots you have experienced; , Representation Node Travel time between or fire point The number of deviation vectors of fire extinguishing time.

[0152] Obtain the uncertainty set of initial model constraints;

[0153] The box-polyhedron fluctuation set of the uncertainty set is obtained by transforming the uncertainty set of the constraint conditions;

[0154] Specifically, the box-polyhedron fluctuation set of the uncertainty set is obtained by transforming the uncertainty set of the constraint conditions, which is expressed by the following formula:

[0155] ;

[0156] ;

[0157] in, The box-polyhedron fluctuation set represented as the uncertainty set of travel time between workers’ fire nodes; It is represented as a box-polyhedron fluctuation set of the uncertain set of firefighting time of the workers; is represented as the set of real numbers;

[0158] According to the box-polyhedron fluctuation set of the uncertainty set, the cone representation of the box-polyhedron fluctuation set is obtained by transformation processing;

[0159] Specifically, the box-polyhedron fluctuation set of the uncertainty set is transformed to obtain the cone representation of the box-polyhedron fluctuation set, which is expressed by the following formula:

[0160]

[0161] , and , so its dual cone is ;

[0162] , and , so its dual cone is ;

[0163]

[0164] , and , so its dual cone is ;

[0165] , and , so its dual cone is ;

[0166] in, and is an auxiliary variable;

[0167] According to the cone representation of the box-polyhedron wave set, the constraints of the initial model (constraints are: , ) is transformed from a semi-infinite constraint into a cone constraint;

[0168] Specifically, according to the cone representation of the box-polyhedron wave set, the constraints of the initial model are , The semi-infinite constraint is transformed into a cone constraint, which is expressed by the following formula:

[0169] ;

[0170] , , ;

[0171] , ;

[0172] ;

[0173] Among them, , ,in , ;

[0174] , ;

[0175] , , ;

[0176] , ;

[0177] ;

[0178] Among them, , ,in , ;

[0179] Eliminate and replace variables for each feasible solution in the cone constraint to obtain the linear equivalent form of the initial model constraint condition;

[0180] Specifically, for each feasible solution in the cone constraint, variable elimination and substitution processing is performed to obtain uncertain linear inequality results. Specifically, according to each feasible solution, the variable , Eliminate, you can get , , and use , To replace , . Set the variable , Eliminate, you can get , , and use , To replace , ;

[0181] It is expressed by the following formula:

[0182]

[0183] , ,

[0184] in, ,

[0185] , ,

[0186] , ,

[0187] in, , .

[0188] Based on the linear equivalent form of the initial model constraints and the initial model, a robust optimization model of the fire extinguishing path of a building in a fire scenario is established.

[0189] Since the constructed box-polyhedron uncertain parameter fluctuation set in the model cannot be solved directly, it is necessary to perform a cone representation on the uncertain parameter fluctuation set. According to its cone representation, its semi-infinite constraints can be converted into cone constraints. By eliminating and replacing the parameters, the equivalent linear form of the box-polyhedron uncertain parameter fluctuation set is finally obtained, and the robust optimization model of the fire extinguishing path in the final building fire scenario is obtained.

[0190] Furthermore, the robust optimization results of the fire extinguishing path in the building fire scenario are obtained through the fire extinguishing path robust optimization model and the Ivy optimization algorithm improved by the Newton-Raphson optimization algorithm, including:

[0191] The fire extinguishing path robust optimization model is solved by using the improved Ivy optimization algorithm based on the Newton-Raphson optimization algorithm to obtain the potential high-quality solution area.

[0192] Use global search to search for potential high-quality solution areas. When a potential optimal solution area is found, switch to the NRBO (Newton-Raphson-based optimizer) algorithm to perform local search on the potential optimal solution area to obtain the cost function of the current fire point where the staff is located for the selectable fire points.

[0193] The next node is determined by selecting the one with the smallest cost function until the optimized fire extinguishing path is obtained as the robust optimization result of the fire extinguishing path in the building fire scenario.

[0194] Specifically, the fire extinguishing path robust optimization model is solved by the improved Ivy optimization algorithm based on the Newton-Raphson optimization algorithm, and potential high-quality solution areas are obtained, including:

[0195] The fire extinguishing path robust optimization model is solved by the improved Ivy optimization algorithm based on the Newton-Raphson optimization algorithm to determine the initial position of the Ivy population in the search space.

[0196] Furthermore, the initial position of the ivy population in the search space is determined by the following formula:

[0197]

[0198] Among them, the vector with dimension D of uniformly distributed random numbers in the interval [0,1] is represented by express; and are the upper and lower bounds of the search space, respectively. The Hadamard product of two vectors (also called element-wise product, denoted as “.∗” in MATLAB) is denoted by the operation “⊙”;

[0199] Based on the initial position, the ivy population growth is performed based on the ivy optimization algorithm;

[0200] Furthermore, ivy is a creeping plant that grows over time, and assuming that the growth rate of the ivy plant is a function of time; the ivy population growth based on the ivy optimization algorithm is performed based on the initial position and is determined by the following formula:

[0201]

[0202] in, is the growth rate, is the growth rate, is the correction factor for deviation growth, the vector and Represents a discrete-time system (time and time )’s growth rate, Is the interval The random real numbers in ), is a random number of a random variable whose probability density function is equal to , The dimension is The random vector is a random number from a standard Gaussian (normal) distribution;

[0203] Access to sunlight: It is crucial for the overall health of ivy in nature to find a surface to attach to (e.g., a wall, rock, or tree) in order to climb toward the sunlight. In wild forests, young ivy can appropriately choose to grow toward the nearest tree, and often another old ivy that has already found support. In this way, ivy can gradually fill in large, continuous forest areas. Fortunately for other tree species in the forest, the climbing of young ivy on old ivy results in only the strongest of the entire group of young and old ivy surviving, almost regardless of their age.

[0204] The following equation describes the members How to use members Climb and move logically in the direction of the light source;

[0205] Based on the sunlight source in the ivy optimization algorithm, determine the movement mode of each member of the ivy population using other members during the growth of the ivy population;

[0206] Specifically, based on the sunlight source in the ivy optimization algorithm, the movement mode of each member of the ivy population using other members during the growth of the ivy population is determined by the following formula:

[0207]

[0208]

[0209] in, is a vector whose components are vectors The absolute value of the components of ” is a vector Divide by vector Hadamard division (also called element-wise division, represented as ". / " in MATLAB);

[0210] Determine the results of the members of the ivy population searching for the optimal solution in the surrounding area as the potential high-quality solution area.

[0211] Specifically, the results of members in the ivy population finding the optimal solution in the surrounding area are determined by the following formula: Spread and evolution of ivy plants: Globally roam through the search space to find the nearest and most important neighbors After the stage of Try to directly follow the best member of the entire population I Best , which is equivalent to member I Best Look for a better optimal solution around. This stage is expressed in the following mathematical formula:

[0212]

[0213] Current Members Growth rate The new value of is calculated by the following formula:

[0214] .

[0215] Furthermore, the global search is used to search for potential high-quality solution areas. When the potential optimal solution area is found, the NRBO algorithm is switched to perform a local search for the potential optimal solution area to obtain the cost function of the current fire point where the staff is located for the selectable fire points, including:

[0216] Search for potential high-quality solution areas based on Newton-Raphson search rules;

[0217] When a potential optimal solution area is found, the algorithm is switched to the NRBO algorithm to perform a local search on the potential optimal solution area, and the cost function of the current fire point where the staff is located for the selectable fire points is obtained;

[0218] The Newton-Raphson based search rule is expressed as follows:

[0219] ;

[0220] ;

[0221] ;

[0222] ;

[0223] ;

[0224] in, Represents a normally distributed random number with a mean of 0 and a variance of 1; and is used and The positions of the two vectors generated; Indicates the worst position, Indicates the best position; and express A random number between and The values ​​of are not equal; By updating The new vector position is obtained; a and b are A random number between

[0225] Specifically, the Newton-Raphson search rule: NRSR is proposed based on the concept of the Newton-Raphson method, which is intended to promote exploration trends and accelerate convergence.

[0226] The trap avoidance operator in the NRBO algorithm is expressed as follows:

[0227]

[0228]

[0229] in, Indicates the best position; and They are and A consistent random number between ; Indicates the current iteration number; and is a random number; adaptive function The value of Changes between.

[0230] Specifically, the trap avoidance operator (TAO) can improve the effectiveness of NRBO in dealing with practical problems and avoid local optimality.

[0231] As shown in the figure, the NRBO algorithm is used to perform local search and fitness evaluation to obtain the optimal solution; then survivor selection is performed: if the fitness value after update is better than the fitness value before update, replacement occurs; when the maximum number of iterations is reached, the operation ends.

[0232] IVYA simulates the coordinated and orderly growth, diffusion and evolution of ivy populations, which is modeled through a differential equation and data-intensive experimental process. IVYA uses the knowledge of nearby ivy to determine the growth direction and simulates the behavior of ivy in nature by selecting the nearest and healthiest neighbors. Using the global search capability of the ivy algorithm, an extensive search is performed in the entire solution space to find potential high-quality solution areas; when a potential optimal solution area is found, the NRBO algorithm is switched to a local search; using NRBO's fast convergence characteristics and high-precision search capabilities, the area is searched finely to find a more accurate optimal solution.

[0233] like Figure 4 As shown, the specific implementation steps are as follows:

[0234] 1. Initialize and generate the ivy population, obtain the optimal fitness of the initialized population, and define the population with the optimal fitness as the optimal population;

[0235] 2. Ivy population according to the given time function Over time is a growth over time;

[0236] 3. The ivy population gets sunlight to grow, and its members Utilize members Climb and move logically in the direction of the light source;

[0237] 4. Spread and evolve among members Globally roam through the search space to find the nearest and most important neighbors After the stage of Try to directly follow the best member of the entire population , which is equivalent to the member Looking for a better optimal solution around;

[0238] 5. Use the global search to find the potential optimal solution area, and switch to the NRBO algorithm for local search;

[0239] 6. Use the NRBO algorithm to perform local search and adaptability evaluation to obtain the optimal solution;

[0240] 7. Trap Avoidance Operator (TAO): Improves the effectiveness of NRBO in dealing with practical problems and avoids local optimality;

[0241] 8. When the maximum number of iterations is reached, the operation ends.

[0242] In general, the Ivy optimization algorithm and the Newton-Raphson optimization algorithm combine the advantages of both to improve optimization performance. The Ivy algorithm is generally known for its unique search mechanism and global optimization capabilities, while NRBO achieves efficient search and the ability to avoid local optimality through the Newton-Raphson search rule (NRSR) and the trap avoidance operator (TAO). When combining the two, you can consider using the global search strategy of the Ivy algorithm to initialize the population or guide the search direction, while using NRBO's NRSR to accelerate convergence and accurately explore the feasible area. In addition, the use of TAO helps to maintain population diversity during the search process and further avoid falling into local optimality. This combination is expected to show stronger search capabilities and robustness on complex optimization problems.

[0243] Example 2

[0244] Embodiment 2 of the present application further discloses a device for robust optimization of fire extinguishing paths in fire scenarios, characterized in that it includes a processor in which an executable file for executing any of the methods described in Embodiment 1 is stored.

[0245] The embodiment of the present application proposes a method and device for robust optimization of fire extinguishing paths in fire scenarios, the method comprising: obtaining fire dynamics parameters corresponding to preset fire conditions in a preset building; establishing a fire extinguishing path robust optimization model for the building in the fire scenario based on the fire dynamics parameters; obtaining a fire extinguishing path robust optimization result in a building fire scenario through the fire extinguishing path robust optimization model and the Ivy optimization algorithm improved by the Newton-Raphson optimization algorithm. The method establishes a fire extinguishing path robust optimization model based on fire dynamics parameters, and optimizes the results based on the Ivy optimization algorithm improved by the Newton-Raphson optimization algorithm, ensuring the stability, reliability and practical operation value of the formulated fire extinguishing path optimization strategy.

[0246] Those skilled in the art will appreciate that the accompanying drawings are merely schematic diagrams of a preferred implementation scenario, and the modules or processes in the accompanying drawings are not necessarily required for implementing the present application.

[0247] Those skilled in the art will appreciate that the modules in the device in the implementation scenario can be distributed in the device in the implementation scenario according to the implementation scenario description, or can be changed accordingly and located in one or more devices different from the implementation scenario. The modules in the above implementation scenario can be combined into one module, or can be further split into multiple sub-modules.

[0248] The above application serial numbers are for description only and do not represent the advantages or disadvantages of the implementation scenarios.

[0249] The above disclosure only discloses several specific implementation scenarios of the present application. However, the present application is not limited thereto, and any changes that can be conceived by technicians in this field should fall within the scope of protection of the present application.

Claims

1. A method for robust optimization of fire extinguishing paths in fire scenarios, characterized in that: include: Obtaining fire dynamics parameters corresponding to a preset fire situation in a preset building; Establishing a fire extinguishing path robust optimization model for the building under the fire scenario based on the fire dynamics parameters; The robust optimization result of the fire extinguishing path in the building fire scenario is obtained by using the fire extinguishing path robust optimization model and the ivy optimization algorithm improved by the Newton-Raphson optimization algorithm; The method of establishing a fire extinguishing path robust optimization model for the building in the fire scenario based on the fire dynamics parameters includes: Importing the fire dynamics parameters into the simulation model obtained by modeling the building, simulating fire combustion by following the law of conservation of mass, the law of conservation of energy and the law of conservation of momentum, analyzing the movement of smoke, the temperature and the changes in the concentration of toxic gases when a fire occurs in the building, so as to determine the fire extinguishing path cost, the labor cost target and the fire rescue value target; Establishing an initial model based on the fire extinguishing path cost, the labor cost target and the fire rescue value target; Obtaining an uncertainty set of constraints of the initial model; The uncertainty set of the constraint conditions is transformed to obtain a box-polyhedron fluctuation set of the uncertainty set; The box-polyhedron fluctuation set of the uncertainty set is transformed to obtain a cone representation of the box-polyhedron fluctuation set; converting the semi-infinite constraint of the constraint condition into a cone constraint according to the cone representation of the box-polyhedron fluctuation set; Performing variable elimination and substitution processing on each feasible solution in the cone constraint to obtain a linear equivalent form of the initial model constraint condition; Establishing a fire extinguishing path robust optimization model for the building under the fire scenario based on the linear equivalent form of the initial model constraint conditions and the initial model; The initial model is established based on the fire extinguishing path cost, the labor cost target and the fire rescue value target, which is expressed by the following formula: Among them, x ijr (f, t) indicates that the decision variable is affected by the uncertainty set, f represents the uncertainty of the firefighting time of the staff, and t represents the uncertainty of the travel time of the staff; λ1 is the weight corresponding to the path cost of the staff, λ2 is the weight corresponding to the labor cost of the staff, and λ3 is the weight corresponding to the rescue value of the fire; m∈R={1,2,…,m}, R is the set of firefighting teams, n∩N={0,1,2,…,n}, N is the set of all nodes, n∈N f ={1,2,…,n},N f is the collection of all fire points; d ij represents the distance between fire points i and j; x ijr is a decision variable. If the firefighting team passes through the path between fire points i and j, it is equal to 1, otherwise it is 0; ir If the fire point i is extinguished by the fire fighting team r, it is equal to 1, otherwise it is 0; m j is the rescue value of fire point j; is the decay formula of the rescue value of the fire point, l j is the decay coefficient of rescue value of fire point j; T ij 、T fi is an auxiliary variable; t fi It represents the fire extinguishing time required for the staff to extinguish the fire point i; t ij It is represented as the travel time of the staff from fire point i to fire point j; x i is a decision variable. If the fire point i is extinguished, it is equal to 1, otherwise it is 0; x ij is a decision variable. If the firefighting team passes through the path between fire points i and j, it is equal to 1, otherwise it is 0; It is represented as the uncertainty set of the travel time between workers’ fire nodes; It is represented as the uncertainty set of the fire extinguishing time of the staff; l∈L, L represents the number of deviation vectors of the travel time between fire points i and j or the fire extinguishing time of fire point i; Ensure that each fire point must be extinguished by one and only one group of workers; It means that the staff must start from the starting point and return to the starting point to finish; It means that after the workers put out the fire, they leave from here to ensure the continuity of the path; ir represents the time when the firefighting team r arrives at the fire point i; t jr It represents the time when the fire fighting team r arrives at the fire point j; The uncertainty set of the travel time between the fire nodes of the staff and the uncertainty set of the firefighting time of the staff It is expressed by the following formula: in, represents the predicted value of the travel time between fire points i and j; represents the predicted value of fire extinguishing time at fire point i; The set of real numbers; represents the nominal value of the travel time between fire points i and j; represents the nominal value of the extinguishing time of fire point i; β∈{β 1 ,β 2 ,…,β l } represents the deviation vector of the travel time between fire points i and j; a∈{a 1 ,a 2 ,…,a l } represents the deviation vector of the extinguishing time of fire point i; is the uncertainty set of the travel time between fire points The control parameter of θ t is the travel time uncertainty budget coefficient, θ t ∈[0,1],D r represents the set of paths experienced by work group r; is the uncertainty set of the extinguishing time of fire point i The control parameter of θ f is the uncertainty budget coefficient of fire extinguishing time at fire point i, θ f ∈[0,1],N r represents the set of fire points experienced by the working group r; l∈L, L represents the number of deviation vectors of the travel time between fire points i and j or the fire extinguishing time of fire point i; The box-polyhedron fluctuation set of the uncertainty set is obtained by transforming the uncertainty set of the initial model constraint conditions, which is expressed by the following formula: in, The box-polyhedron fluctuation set represented as the uncertainty set of travel time between workers’ fire nodes; It is represented as a box-polyhedron fluctuation set of the uncertain set of firefighting time of the workers; is represented as the set of real numbers; The box-polyhedron fluctuation set according to the uncertainty set is transformed to obtain a cone representation of the box-polyhedron fluctuation set, which is represented by the following formula: H1β=[β;0],h1=[0 L×1 ; 1] and So its dual cone is P2α=[α;θ],P2=[0 L×1 Γ r f ]and So its dual cone is P1α = [α; 0], p1 = [0 L×1 ; 1] and So its dual cone is P2α = [α; 0], P2 = [0 L×1 ; Γ r f and So its dual cone is Among them, z and y are auxiliary variables; According to the cone representation of the box-polyhedron wave set, the constraints of the initial model are The semi-infinite constraint is transformed into a cone constraint, which is expressed by the following formula: ||λ1||1≤π1,||λ2|| ∞ ≤π2 Among them, in, ||η1||1≤τ1,||η2|| ∞ ≤τ2 Among them, let y 1 =[η1;τ1],y 2 =[η2;τ2], where Variable elimination and substitution are performed for each feasible solution in the cone constraint to obtain a linear equivalent form of the initial model constraint condition, which is expressed by the following formula: among them,x l =λ1,μ=λ2 Among them, φ=eta1 and ω=eta2.

2. The method according to claim 1, characterized in that The obtaining of fire dynamics parameters corresponding to a preset fire situation in a preset building includes: Obtaining structural data of a preset building; Establishing a simulation model inside the building based on the structural data and a preset fire dynamics model; Obtaining fire point location and heat radiation data from a preset fire situation through the simulation model in the building; The fire point position and the thermal radiation data are used as fire dynamics parameters.

3. The method according to claim 1, characterized in that The fire extinguishing path robust optimization result in the building fire scenario is obtained by using the fire extinguishing path robust optimization model and the improved ivy optimization algorithm of the Newton-Raphson optimization algorithm, including: The fire extinguishing path robust optimization model is solved by using an ivy optimization algorithm improved by the Newton-Raphson optimization algorithm to obtain a potential high-quality solution region; Use global search to search for potential high-quality solution areas. When a potential optimal solution area is found, switch to the NRBO algorithm to perform local search on the potential optimal solution area to obtain the cost function of the current fire point where the staff is located for the selectable fire points. The next node is determined by selecting the one with the smallest cost function until the optimized fire extinguishing path is obtained as the robust optimization result of the fire extinguishing path in the building fire scenario.

4. The method according to claim 3, characterized in that The Ivy optimization algorithm improved based on the Newton-Raphson optimization algorithm solves the fire extinguishing path robust optimization model to obtain potential high-quality solution areas, including: Solving the fire extinguishing path robust optimization model based on the improved ivy optimization algorithm of the Newton-Raphson optimization algorithm to determine the initial position of the ivy population in the search space; Based on the initial position, the ivy population growth is performed based on the ivy optimization algorithm; Based on the sunlight source in the ivy optimization algorithm, determine the movement mode of each member of the ivy population using other members during the growth of the ivy population; Determine the results of the members of the ivy population searching for the optimal solution in the surrounding area as the potential high-quality solution area.

5. The method according to claim 4, characterized in that The initial position of the ivy population in the search space is determined by the following formula: I i =I min +rand(1,D)⊙(I max -I min ), i = 1, ..., Npop, where the vector of dimension D of uniformly distributed random numbers in the interval [0, 1] is represented by rand(1, D); I max and I min are the upper and lower bounds of the search space respectively. The Hadamard product of two vectors is represented by the operation "⊙"; The ivy population growth based on the ivy optimization algorithm is performed based on the initial position, which is determined by the following formula: ΔGv i (t+1)=rand 2 ⊙(N(1,D)⊙ΔGv i (t)) Among them, Gv is the growth rate, and the vector ΔGv i (t) and ΔGv i (t+1) represents the growth rate of the discrete time system, rand is a random real number in the interval [0.1], rand 2 is a random number of a random variable whose probability density function is equal to N(1,D) represents a random vector with dimension D, which is a random number in the standard Gaussian distribution; Based on the sunlight source in the ivy optimization algorithm, the movement mode of each member of the ivy population using other members during the growth of the ivy population is determined by the following formula: Where |N(1,D)| is a vector whose components are the absolute values ​​of the components of vector N(1,D). is the Hadamard division of vector u by vector v; The result of finding the optimal solution for the surrounding area by members of the ivy population is determined by the following formula: 。 6. The method according to claim 4, characterized in that The method uses global search to search for potential high-quality solution areas. When a potential optimal solution area is found, the method switches to the NRBO algorithm to perform local search for the potential optimal solution area, and obtains the cost function of the current fire point where the staff is located for the selectable fire points, including: Search for potential high-quality solution areas based on Newton-Raphson search rules; When a potential optimal solution area is found, the algorithm is switched to the NRBO algorithm to perform a local search on the potential optimal solution area, and the cost function of the current fire point where the staff is located for the selectable fire points is obtained; The Newton-Raphson based search rule is expressed as follows: y w =r1×(Mean(Z n+1 +x n )+r1×Δx); y b =r1×(Mean(Z n+1 +x n )-r1×Δx); Among them, randn represents a normally distributed random number with a mean of 0 and a variance of 1; y w and b is to use Z(n+1) and x n The positions of the two vectors generated; X w Indicates the worst position, X b Indicates the best position; r1 and r2 represent random numbers between (0,1), and the values ​​of r1 and r2 are not equal; By updating The new vector position is obtained; a and b are random numbers between (0,1); The trap avoidance operator in the NRBO algorithm is expressed as follows: Among them, x b represents the optimal position; θ1 and θ2 are consistent random numbers between (-1,1) and (-0.5,0.5) respectively; represents the current iteration number; μ1 and μ2 are random numbers; the value of the adaptive function δ varies between [-1,1].

7. A device for robust optimization of fire extinguishing paths in fire scenarios, characterized in that: The invention comprises a processor storing an executable file for executing the method according to any one of claims 1 to 6.

Images