A smart firefighting path planning method based on ant colony optimization algorithm

Abstract

The present invention discloses a smart firefighting path planning method based on ant colony optimization algorithm, including S1, collecting key information of the fire scene in real time through a smart firefighting system; S2, using a geographic information system to obtain detailed data of terrain, building layout, roads and other infrastructure; S3, using an ant colony optimization algorithm to initialize path search, wherein the algorithm simulates ants releasing pheromones to mark the paths they have walked; S4, dynamically adjusting the intensity and decay rate of pheromones according to the collected real-time data, and optimizing the path search direction of ants; S5, evaluating the safety, speed and traffic capacity of each feasible path, and selecting the path with the highest comprehensive score as the recommended rescue path; S6, applying machine learning technology to analyze historical path selection data, and continuously optimizing the parameter settings and path evaluation mechanism of the ant colony algorithm. The present invention has the advantages of quickly responding to changing environments and optimizing rescue efficiency and safety.

Description

Technical Field

[0001] The present invention relates to the technical field of firefighting path planning, and in particular to an intelligent firefighting path planning method based on an ant colony optimization algorithm. Background Art

[0002] With the rapid development of urbanization and the increase in population density, urban fire safety faces unprecedented challenges. When a fire occurs, rapid and effective rescue actions are the key to saving lives and reducing property losses. However, there are multiple problems in traditional fire path planning methods, which seriously affect rescue efficiency and safety. Specifically, the existing technology has obvious deficiencies in the following aspects:

[0003] 1. Lack of dynamic environmental adaptability: Traditional firefighting path planning methods are often designed based on static data and are difficult to adapt to the rapid changes in the fire scene environment. For example, factors such as the spread of fire, new obstacles, and changing road conditions are often not taken into account immediately, resulting in the rescue path no longer being the optimal choice.

[0004] 2. The trade-off between efficiency and safety: In emergency situations where it is urgent to reach the fire scene quickly, traditional methods often sacrifice the safety of the route for speed, or delay rescue opportunities due to excessive emphasis on safety. This non-dynamic trade-off method is difficult to meet the dual needs of efficiency and safety in actual rescue operations.

[0005] 3. Lack of highly integrated intelligent system support: Existing rescue route planning mostly relies on scattered information sources and single technical means. For example, the GIS system operates independently and is not deeply integrated with intelligent decision-making tools such as machine learning, which limits the data-driven ability and response speed of decision-making.

[0006] 4. Limitations of rescue decision-making: Traditional firefighting path planning lacks a mechanism to learn and optimize from past actions. Although each rescue operation accumulates rich experience and data, it has not been effectively used to improve the decision-making quality and response speed of future rescue operations.

[0007] Therefore, how to provide an intelligent fire fighting path planning method based on ant colony optimization algorithm is a problem that technicians in this field need to solve urgently. Summary of the invention

[0008] The main purpose of the present invention is to propose a smart firefighting path planning method based on the ant colony optimization algorithm, which utilizes the natural simulation characteristics of the ant colony algorithm (ACO), combined with the smart firefighting system, geographic information system (GIS), multi-objective optimization and artificial intelligence technology to achieve fast, effective and safe firefighting rescue path planning. By simulating the path selection mechanism of ants looking for food, the algorithm can efficiently find the rescue path and automatically adjust the path according to the dynamic changes of the fire environment. The present invention collects key information of the fire scene in real time, such as temperature, smoke density and building structure integrity, combined with real-time traffic conditions and terrain data, to provide the best path selection for rescue operations. This method not only improves the speed of rescue operations, but also significantly improves the safety and traffic efficiency of the rescue path through an intelligent dynamic adjustment mechanism.

[0009] According to an embodiment of the present invention, a smart firefighting path planning method based on an ant colony optimization algorithm is characterized by comprising the following steps:

[0010] S1. Collect key information of the fire scene in real time through the smart fire protection system, including temperature, smoke density, building structure integrity and surrounding traffic network conditions;

[0011] S2. Use geographic information systems to obtain detailed data on terrain, building layout, roads and other infrastructure, and transmit this data to the path planning system;

[0012] S3, using the ant colony optimization algorithm to initialize the path search, where the algorithm simulates ants releasing pheromones to mark the paths they have traveled;

[0013] S4, dynamically adjust the intensity and attenuation rate of pheromones based on the real-time data collected to optimize the path search direction of ants;

[0014] S5. Evaluate the safety, speed and traffic capacity of each feasible path, and select the path with the highest comprehensive score as the recommended rescue path;

[0015] S6. Apply machine learning technology to analyze historical path selection data and continuously optimize the parameter settings and path evaluation mechanism of the ant colony algorithm.

[0016] Optionally, the S1 specifically includes:

[0017] S11. Deploy a sensor network in the predetermined potential fire area, and each sensor measures the temperature T, smoke density D and building structure integrity index I:

[0018] T = f(t, x, y, z);

[0019] D = g(t, x, y, z);

[0020] I = h(t, x, y, z);

[0021] Where t represents the measurement time, (x, y, z) represents the spatial coordinates of the sensor;

[0022] S12, the sensor sends the measurement data to the central data processing system at a preset time interval Δt, and the data includes the specific position (x, y, z) coordinates and the measurement time t:

[0023] Δt=t i+1 -t i ;

[0024] Among them, t i and t i+1 Respectively represent the time points of two consecutive data transmissions;

[0025] S13. The central data processing system uses a weighted moving average method to calculate the real-time effective value of the data reported by each sensor. The weight is determined by the inverse proportion of the sensor's distance to the estimated location of the fire source:

[0026]

[0027]

[0028] Among them, V avg is the weighted average, V i and w i are the measurement value and weight of the i-th sensor, d i is the distance from the sensor to the fire source;

[0029] S14. Analyze the collected temperature T and smoke density D data in real time, and use the preset critical threshold to judge the severity of the fire source and its diffusion speed:

[0030] If T > T critical or D>D critical , it is considered a serious fire;

[0031] Among them, T critical and D critical They are the critical temperature and critical smoke density thresholds, respectively, used to calibrate emergency situations;

[0032] S15. Evaluate the impact of fire on building safety through real-time monitoring of the building structural integrity index:

[0033] I = α·M + β·A - γ·H;

[0034] Among them, M represents the fire resistance coefficient of building materials, A represents the age attenuation coefficient of the building, H represents the heat received by the building, and α, β, and γ are adjustment coefficients;

[0035] S16. Integrate the collected temperature, smoke, and building integrity data with real-time traffic network status information to assess and update possible rescue paths and their obstacles.

[0036] Optionally, the S2 specifically includes:

[0037] S21. Collect terrain data of the target area through a geographic information system, including terrain height H(x, y), terrain type T(x, y) and land cover type C(x, y), where (x, y) represents a geographic coordinate point;

[0038] S22, collecting building layout information of the target area, including the building location P (x, y), the number of floors L, the building purpose U and the building fire resistance level R;

[0039] S23. Collect information on roads and other infrastructure in the target area, including road types D type (x, y), road width W(x, y) and road condition S(x, y), where (x, y) represents a geographic coordinate point to describe the physical location and status of the road;

[0040] S24. Utilize GIS data, combined with the real-time location of the fire scene and rescue teams, to update the rescue route planning database, integrate all collected GIS data, and create a dynamically updated map database to support real-time planning and adjustment of rescue routes.

[0041] Optionally, the S3 specifically includes:

[0042] S31, initialize the ant colony optimization algorithm, deploy the virtual ant colony in the fire rescue geographic information system, and specify the starting point for each ant as the current location of the rescue team and the target point as the fire scene:

[0043] Starting point = rescue team location (x s ,y s );

[0044] End point = fire location (x f ,y f );

[0045] S32, set the initial pheromone concentration τ on all potential rescue paths 0 , simulating the natural behavior of ants leaving pheromones on their paths:

[0046]

[0047] Among them, τ(x, y) represents the pheromone concentration at the location (x, y), τ 0 is the initial pheromone concentration setting value;

[0048] S33, when the ant is searching for a path, it determines its next path based on the relative distance from the current position to the target point and the pheromone concentration, and uses the probability function P ij To select the path:

[0049]

[0050]

[0051] Among them, P ij (t) is the probability of an ant moving from position i to position j at time t, τ ij (t) is the pheromone concentration on path ij, η ij is the heuristic factor of path ij, d ij is the distance from i to j, ∈ is a small constant to prevent division by zero, α and β are parameters that regulate the importance and heuristic factors of pheromones;

[0052] S34. After the ant reaches the target point, it updates the pheromone concentration on the path according to the conditions on its path to reflect the quality of the path:

[0053] τ ij (t+1)=(1-ρ)·τ ij (t)+Δτ ij ;

[0054]

[0055] Among them, τ ij (t+1) is the updated pheromone concentration, ρ is the evaporation rate of pheromone, Δτ ij is the amount of pheromone left by the ant on path ij, Q is the pheromone intensity constant, L ij is the length of the path ij traveled by the ant;

[0056] S35. After multiple rounds of iterations, the ant colony algorithm compares the pheromone concentrations of each path and finally determines the path with the highest pheromone concentration as the optimal rescue path.

[0057] Optionally, the S4 specifically includes:

[0058] S41, real-time monitoring of fire environment changes, including temperature T(t), smoke concentration D(t) and the state of variable obstacles O(t);

[0059] S42. Dynamically adjust the evaporation rate ρ(t) of pheromone according to real-time monitoring data:

[0060]

[0061] Among them, ρ0 is the initial evaporation rate, λ and σ are adjustment factors, which respectively represent the influence of temperature, smoke concentration and obstacle status on the evaporation rate of pheromone;

[0062] S43. Update the heuristic factor η in the ant colony algorithm ij (t), taking into account the directness, safety and environmental factors of the route:

[0063]

[0064] H(i,j,t)=k·(T(i,j,t)+D(i,j,t)+m·O(i,j,t));

[0065] Among them, d ij is the straight-line distance from node i to node j, H(i, j, t) is the path penalty factor considering environmental hazards, k and m are adjustment coefficients, T(i, j, t) and D(i, j, t) are the average temperature and smoke concentration on the path respectively, and O(i, j, t) is the state of obstacles on the path;

[0066] S44, real-time adjustment of path selection probability P ij (t):

[0067]

[0068] S45. Through the intelligent system, the real-time environment and path status data are continuously fed back to the central control system for in-depth data analysis and path optimization.

[0069] Optionally, the S5 specifically includes:

[0070] S51. Each possible rescue route is scored for safety, speed, and capacity, with each factor being evaluated according to a specific weighting factor:

[0071] (P) = w 1 ·S(P)+w 2 ·V(P)+w 3 A(P);

[0072] Where P represents the path, S(P) is the safety score of the path, V(P) is the speed score of the path, A(P) is the capacity score of the path, and w 1 , w 2 , w 3 are the weights of these three factors respectively;

[0073] S52. Safety score S(P) is based on the fire intensity, structural stability and smoke density along the path:

[0074]

[0075] Among them, T represents the average temperature on the path, D represents the average smoke concentration, O represents the state of structural obstacles, and f1 is the function of safety risk;

[0076] S53. Speed ​​score V(P) is based on the estimated movement speed of the rescue team on the path:

[0077]

[0078] Among them, L represents the total length of the path, and t represents the expected travel time;

[0079] S54. The capacity score A(P) is assessed based on the width of the path, traffic restrictions and the size of the rescue team:

[0080] A(P) = k·(wr);

[0081] Among them, w is the average width of the path, r is the width of the obstacle on the path, and k is an adjustment factor;

[0082] S55. Select the path with the highest comprehensive score as the recommended rescue path, update the path information in real time to respond to environmental changes, and feed back the selected rescue path to the rescue team through the smart fire protection system.

[0083] Optionally, the S6 specifically includes:

[0084] S61. Use machine learning technology to analyze the data of historical rescue missions, identify patterns and extract useful information, optimize the parameters of the ant colony algorithm and the path evaluation mechanism, and adjust the model according to changes in rescue success rate, path selection efficiency, and environmental factors:

[0085]

[0086] Where N is the number of samples, y i is the actual rescue effect score, is the predicted rescue effectiveness score;

[0087] S62. Implement multi-objective optimization, taking into account the time efficiency, safety, and resource utilization of the path, adjust these objectives by setting weights and priorities, and dynamically update them according to real-time conditions:

[0088] Score = α·E t +β·E s +y·E r ;

[0089] Among them, E t 、E s and E rThey represent the scores of time efficiency, safety, and resource utilization, respectively, and α, β, and γ are the corresponding weight factors;

[0090] S63. According to the real-time monitored environmental changes, the system will automatically adjust the pheromone update rules of the ant colony algorithm:

[0091] τ new =(1-ρ)·τ old +Δτ;

[0092]

[0093] Among them, τ old and τ new are the pheromone concentrations before and after the update, ρ is the evaporation rate of pheromone, Q is the constant of pheromone increase, and Cost is the path cost evaluation.

[0094] The beneficial effects of the present invention are:

[0095] (1) The present invention combines the ant colony optimization algorithm (ACO) with the intelligent fire protection system and the geographic information system (GIS) to provide real-time monitoring and dynamic adjustment of the fire environment and rescue path. This integrated approach allows the system to quickly adapt to changes in the fire, new obstacles and real-time traffic conditions, ensuring that the rescue path updated at any time is optimal. This significantly improves the response speed of the rescue team to sudden changes, allowing the rescue operation to make the best path adjustment in the first time, thereby effectively shortening the time to arrive at the scene and avoiding potential new dangers.

[0096] (2) The present invention significantly improves the safety of the rescue path through intelligent path planning technology and optimizes the route of the rescue team. Through in-depth analysis and real-time updating of the fire environment, the system can avoid dangerous areas and select safe and feasible paths, which not only protects the safety of the rescue team but also improves the survival rate of the people. In addition, the multi-objective optimization algorithm enables the rescue path to achieve the best balance between speed, safety and resource utilization efficiency, thereby maximizing the effective use of resources and enhancing the overall efficiency of the rescue operation.

[0097] (3) The present invention uses machine learning technology to analyze historical rescue data, which not only improves the accuracy of path planning, but also makes the rescue decision-making process more intelligent. The system can automatically learn from previous successful rescue cases, identify the most effective action mode, and automatically recommend the optimal path in similar situations in the future. This self-learning and adaptive mechanism enables the system to continuously optimize algorithms, improve decision-making quality, and predict and respond to more complex and changing rescue scenarios.

[0098] (4) While ensuring the real-time transmission of rescue path information, the present invention also pays attention to the security and confidentiality of data. By using advanced encryption technology and security protocols, it ensures that all communications and data exchanges in rescue operations are fully protected, preventing the leakage of sensitive information, and enhancing the security of rescue operations. BRIEF DESCRIPTION OF THE DRAWINGS

[0099] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0100] Figure 1 This is a general flow chart of a smart fire fighting path planning method based on ant colony optimization algorithm proposed by the present invention;

[0101] Figure 2 A framework diagram of the integration of a smart fire fighting system and a geographic information system for a smart fire fighting path planning method based on an ant colony optimization algorithm proposed by the present invention;

[0102] Figure 3 A schematic diagram of the pheromone update mechanism of the ant colony optimization algorithm in the intelligent fire path planning of the intelligent fire path planning method based on the ant colony optimization algorithm proposed by the present invention;

[0103] Figure 4 This is a flowchart of the application of machine learning technology in the rescue path optimization of an intelligent fire path planning method based on ant colony optimization algorithm proposed in the present invention. DETAILED DESCRIPTION

[0104] The present invention will now be described in further detail with reference to the accompanying drawings. These drawings are simplified schematic diagrams, which only illustrate the basic structure of the present invention in a schematic manner, and therefore only show the components related to the present invention.

[0105] refer to Figure 1-Figure 4 , a smart fire fighting path planning method based on ant colony optimization algorithm, characterized in that it includes the following steps:

[0106] S1. Collect key information of the fire scene in real time through the smart fire protection system, including temperature, smoke density, building structure integrity and surrounding traffic network conditions;

[0107] In this implementation, S1 specifically includes:

[0108] S11. Deploy a sensor network in the predetermined potential fire area, and each sensor measures the temperature T, smoke density D and building structure integrity index I:

[0109] T = f(t, x, y, z);

[0110] D = g(t, x, y, z);

[0111] I = h(t, x, y, z);

[0112] Where t represents the measurement time, (x, y, z) represents the spatial coordinates of the sensor;

[0113] S12, the sensor sends the measurement data to the central data processing system at a preset time interval Δt, and the data includes the specific position (x, y, z) coordinates and the measurement time t:

[0114] Δt=t i+1 -t i ;

[0115] Among them, t i and t i+1 Respectively represent the time points of two consecutive data transmissions;

[0116] S13. The central data processing system uses a weighted moving average method to calculate the real-time effective value of the data reported by each sensor. The weight is determined by the inverse proportion of the sensor's distance to the estimated location of the fire source:

[0117]

[0118]

[0119] Among them, V avg is the weighted average, V i and w i are the measurement value and weight of the i-th sensor, d i is the distance from the sensor to the fire source;

[0120] S14. Analyze the collected temperature T and smoke density D data in real time, and use the preset critical threshold to judge the severity of the fire source and its diffusion speed:

[0121] If T > T critical or D>D critical , it is considered a serious fire;

[0122] Among them, T critical and D critical They are the critical temperature and critical smoke density thresholds, respectively, used to calibrate emergency situations;

[0123] S15. Evaluate the impact of fire on building safety through real-time monitoring of the building structural integrity index:

[0124] I = α·M + β·A - γ·H;

[0125] Among them, M represents the fire resistance coefficient of building materials, A represents the age attenuation coefficient of the building, H represents the heat received by the building, and α, β, and γ are adjustment coefficients;

[0126] S16. Integrate the collected temperature, smoke, and building integrity data with real-time traffic network status information to assess and update possible rescue paths and their obstacles.

[0127] S2. Use geographic information systems to obtain detailed data on terrain, building layout, roads and other infrastructure, and transmit this data to the path planning system;

[0128] In this implementation, S2 specifically includes:

[0129] S21. Collect terrain data of the target area through a geographic information system, including terrain height H(x, y), terrain type T(x, y) and land cover type C(x, y), where (x, y) represents a geographic coordinate point;

[0130] S22, collecting building layout information of the target area, including the building location P (x, y), the number of floors L, the building purpose U and the building fire resistance level R;

[0131] S23. Collect information on roads and other infrastructure in the target area, including road types D type (x, y), road width W(x, y) and road condition S(x, y), where (x, y) represents a geographic coordinate point to describe the physical location and status of the road;

[0132] S24. Utilize GIS data, combined with the real-time location of the fire scene and rescue teams, to update the rescue route planning database, integrate all collected GIS data, and create a dynamically updated map database to support real-time planning and adjustment of rescue routes.

[0133] S3, using the ant colony optimization algorithm to initialize the path search, where the algorithm simulates ants releasing pheromones to mark the paths they have traveled;

[0134] In this implementation, S3 specifically includes:

[0135] S31, initialize the ant colony optimization algorithm, deploy the virtual ant colony in the fire rescue geographic information system, and specify the starting point for each ant as the current location of the rescue team and the target point as the fire scene:

[0136] Starting point = rescue team location (x s ,y s );

[0137] End point = fire location (x f ,y f);

[0138] S32, set the initial pheromone concentration τ on all potential rescue paths 0 , simulating the natural behavior of ants leaving pheromones on their paths:

[0139]

[0140] Among them, τ(x, y) represents the pheromone concentration at the location (x, y), τ 0 is the initial pheromone concentration setting value;

[0141] S33, when the ant is searching for a path, it determines its next path based on the relative distance from the current position to the target point and the pheromone concentration, and uses the probability function P ij To select the path:

[0142]

[0143]

[0144] Among them, P ij (t) is the probability of an ant moving from position i to position j at time t, τ ij (t) is the pheromone concentration on path ij, η ij is the heuristic factor of path ij, d ij is the distance from i to j, ∈ is a small constant to prevent division by zero, α and β are parameters that regulate the importance and heuristic factors of pheromones;

[0145] S34. After the ant reaches the target point, it updates the pheromone concentration on the path according to the conditions on its path to reflect the quality of the path:

[0146] τ ij (t+1)=(1-ρ)·τ ij (t)+Δτ ij ;

[0147]

[0148] Among them, τ ij (t+1) is the updated pheromone concentration, ρ is the evaporation rate of pheromone, Δτ ij is the amount of pheromone left by the ant on path ij, Q is the pheromone intensity constant, L ij is the length of the path ij traveled by the ant;

[0149] S35. After multiple rounds of iterations, the ant colony algorithm compares the pheromone concentrations of each path and finally determines the path with the highest pheromone concentration as the optimal rescue path.

[0150] S4, dynamically adjust the intensity and attenuation rate of pheromones based on the real-time data collected to optimize the path search direction of ants;

[0151] In this implementation, S4 specifically includes:

[0152] S41, real-time monitoring of fire environment changes, including temperature T(t), smoke concentration D(t) and the state of variable obstacles O(t);

[0153] S42. Dynamically adjust the evaporation rate ρ(t) of pheromone according to real-time monitoring data:

[0154] ρ(t)=ρ 0 ·(1-e -λ·(T(t)+D(t)+σ·O(t)) );

[0155] Among them, ρ 0 is the initial evaporation rate, λ and σ are adjustment factors, which respectively represent the influence of temperature, smoke concentration and obstacle status on the evaporation rate of pheromone;

[0156] S43. Update the heuristic factor η in the ant colony algorithm ij (t), taking into account the directness, safety and environmental factors of the route:

[0157]

[0158] H(i,j,t)=k·(T(i,j,t)+D(i,j,t)+m·O(i,j,t));

[0159] Among them, d ij is the straight-line distance from node i to node j, H(i, j, t) is the path penalty factor considering environmental hazards, k and m are adjustment coefficients, T(i, j, t) and D(i, j, t) are the average temperature and smoke concentration on the path respectively, and O(i, j, t) is the state of obstacles on the path;

[0160] S44, real-time adjustment of path selection probability P ij (t):

[0161]

[0162] S45. Through the intelligent system, the real-time environment and path status data are continuously fed back to the central control system for in-depth data analysis and path optimization.

[0163] S5. Evaluate the safety, speed and traffic capacity of each feasible path, and select the path with the highest comprehensive score as the recommended rescue path;

[0164] In this implementation, S5 specifically includes:

[0165] S51. Each possible rescue route is scored for safety, speed, and capacity, with each factor being evaluated according to a specific weighting factor:

[0166] (P)=W 1 ·S(P)+w 2 V(P)+W 3 A(P);

[0167] Where P represents the path, S(P) is the safety score of the path, V(P) is the speed score of the path, A(P) is the capacity score of the path, and w 1 , w 2 , W 3 are the weights of these three factors respectively;

[0168] S52. Safety score S(P) is based on the fire intensity, structural stability and smoke density along the path:

[0169]

[0170] Among them, T represents the average temperature on the path, D represents the average smoke concentration, O represents the state of structural obstacles, and f1 is the function of safety risk;

[0171] S53. Speed ​​score V(P) is based on the estimated movement speed of the rescue team on the path:

[0172]

[0173] Among them, L represents the total length of the path, and t represents the expected travel time;

[0174] S54. The capacity score A(P) is assessed based on the width of the path, traffic restrictions and the size of the rescue team:

[0175] A(P) = k·(wr);

[0176] Among them, w is the average width of the path, r is the width of the obstacle on the path, and k is an adjustment factor;

[0177] S55. Select the path with the highest comprehensive score as the recommended rescue path, update the path information in real time to respond to environmental changes, and feed back the selected rescue path to the rescue team through the smart fire protection system.

[0178] S6. Apply machine learning technology to analyze historical path selection data and continuously optimize the parameter settings and path evaluation mechanism of the ant colony algorithm.

[0179] In this implementation, S6 specifically includes:

[0180] S61. Use machine learning technology to analyze the data of historical rescue missions, identify patterns and extract useful information, optimize the parameters of the ant colony algorithm and the path evaluation mechanism, and adjust the model according to changes in rescue success rate, path selection efficiency, and environmental factors:

[0181]

[0182] Where N is the number of samples, y i is the actual rescue effect score, is the predicted rescue effectiveness score;

[0183] S62. Implement multi-objective optimization, taking into account the time efficiency, safety, and resource utilization of the path, adjust these objectives by setting weights and priorities, and dynamically update them according to real-time conditions:

[0184] Score = α·E t +β·E s +γ·E r ;

[0185] Among them, E t 、E s and E r They represent the scores of time efficiency, safety, and resource utilization, respectively, and α, β, and γ are the corresponding weight factors;

[0186] S63. According to the real-time monitored environmental changes, the system will automatically adjust the pheromone update rules of the ant colony algorithm:

[0187] τ new =(1-ρ)·τ old +Δτ;

[0188]

[0189] Among them, τ old and τ new are the pheromone concentrations before and after the update, ρ is the evaporation rate of pheromone, Q is the constant of pheromone increase, and Cost is the path cost evaluation.

[0190] Embodiment 1:

[0191] In order to fully verify the effectiveness and advantages of the present invention, this embodiment is applied to a major fire rescue operation in a downtown area. The downtown area has a complex structure with high-rise buildings, dense commercial facilities and a busy transportation network. In such an environment, traditional fire path planning methods often lead to rescue delays and safety hazards due to lack of flexibility and adaptability, especially when the situation at the fire scene changes rapidly, the rescue path is often difficult to adjust in time.

[0192] In this embodiment, the rescue center uses an intelligent firefighting path planning system based on the ant colony optimization algorithm, which integrates the intelligent firefighting system, geographic information system (GIS) and real-time environmental monitoring technology. The system dynamically generates and adjusts the optimal rescue path by collecting key data in real time, such as the location of the fire source, smoke density, traffic status, etc. The deployment and operation of the system is aimed at improving rescue efficiency and safety while reducing the impact on traffic and public order.

[0193] The fire occurred on a weekend night in a shopping mall in the city center. Due to the particularity of the time and location of the incident, the area was densely populated, the fire spread rapidly, and the situation was extremely serious. After receiving the alarm, the rescue center immediately activated the intelligent fire path planning system of the present invention.

[0194] The system first analyzed the latest fire scene information and surrounding environment data, and evaluated the feasibility and safety of different rescue paths. After the initial path selection, the system optimized the calculation based on the ant colony algorithm and updated the rescue path in real time. In addition, the system also took into account the type of rescue vehicle and the required rescue equipment to ensure that the selected path can support the rapid passage of large rescue vehicles. The comparison of rescue operation efficiency before and after the implementation of this system is as follows:

[0195] Table 1 Rescue efficiency improvement report

[0196] Data Category Before deploying the system After deploying the system Rescue arrival time 22 minutes 15 minutes Rescue route adjustment times 3 times 1 time Rescue success rate 68％ 89％ Traffic impact during rescue high middle Environmental adaptability adjustment efficiency 8 minutes 3 minutes Safety accident rate of rescue workers 12％ 4％

[0197] As shown in Table 1, the rescue arrival time was significantly shortened from the traditional 22 minutes to 15 minutes, the number of rescue path adjustments was reduced, and the rescue success rate was increased from 68% to 89%, indicating that the optimization of the rescue path directly improved the rescue efficiency and on-site safety. In addition, the system's rapid response capability was significantly improved, and the environmental adaptability adjustment efficiency was shortened from 8 minutes to 3 minutes, effectively reducing the impact of the rescue operation on the surrounding traffic and significantly reducing the safety accident rate of rescuers.

[0198] The present invention effectively responds to the complex and ever-changing urban fire rescue needs through intelligent and automated rescue path planning. Through real-time dynamic path planning, it not only improves the success rate of rescue operations, but also ensures the safety of personnel during the rescue process, maximizes the effective use of resources, significantly improves the overall level of urban fire rescue, and provides strong technical support for modern urban fire safety management.

[0199] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A smart firefighting path planning method based on ant colony optimization algorithm, characterized in that: The steps include: S1. Collect key information of the fire scene in real time through the smart fire protection system, including temperature, smoke density, building structure integrity and surrounding traffic network conditions; S2. Use geographic information systems to obtain detailed data on terrain, building layout, roads and other infrastructure, and transmit this data to the path planning system; S3, using the ant colony optimization algorithm to initialize the path search, where the algorithm simulates ants releasing pheromones to mark the paths they have traveled; S4, dynamically adjust the intensity and attenuation rate of pheromones based on the real-time data collected to optimize the path search direction of ants; S5. Evaluate the safety, speed and traffic capacity of each feasible path, and select the path with the highest comprehensive score as the recommended rescue path; S6. Apply machine learning technology to analyze historical path selection data and continuously optimize the parameter settings and path evaluation mechanism of the ant colony algorithm; The S6 specifically includes: S61. Use machine learning technology to analyze the data of historical rescue missions, identify patterns and extract useful information, optimize the parameters of the ant colony algorithm and the path evaluation mechanism, and adjust the model according to changes in rescue success rate, path selection efficiency, and environmental factors: Where N is the number of samples, y i is the actual rescue effect score, is the predicted rescue effectiveness score; S62. Implement multi-objective optimization, taking into account the time efficiency, safety, and resource utilization of the path, adjust these objectives by setting weights and priorities, and dynamically update them according to real-time conditions: Score=α1·E t +β1·E s +γ1·E r ; Among them, E t 、E s and E r They represent the scores of time efficiency, safety, and resource utilization, respectively, and α1, β1, and γ1 are the corresponding weight factors; S63. According to the real-time monitored environmental changes, the system will automatically adjust the pheromone update rules of the ant colony algorithm: t new =(1-ρ)·τ old +Δt; Among them, τ old and τ new are the pheromone concentrations before and after the update, ρ is the evaporation rate of pheromone, Q is the constant of pheromone increase, and Cost is the path cost evaluation.

2. The intelligent fire fighting path planning method based on ant colony optimization algorithm according to claim 1 is characterized in that: The S1 specifically includes: S11. Deploy a sensor network in the predetermined potential fire area, and each sensor measures the temperature T, smoke density D and building structure integrity index I: T = f(t,x,y,z); D = g(t,x,y,z); I = h(t,x,y,z); Where t represents the measurement time, (x, y, z) represents the spatial coordinates of the sensor; S12, the sensor sends the measurement data to the central data processing system at a preset time interval Δt. The data includes the specific position (x, y, z) coordinates and the measurement time t: Δt=t i+1 -t i ; Among them, t i and t i+1 Respectively represent the time points of two consecutive data transmissions; S13. The central data processing system uses a weighted moving average method to calculate the real-time effective value of the data reported by each sensor. The weight is determined by the inverse proportion of the sensor's distance to the estimated location of the fire source: Among them, V avg is the weighted average, V i and w i are the measurement value and weight of the i-th sensor, d i is the distance from the sensor to the fire source; S14. Analyze the collected temperature T and smoke density D data in real time, and use the preset critical threshold to judge the severity of the fire source and its diffusion speed: If T>T critical or D>D critical , it is judged as a serious fire; Among them, T critical and D critical They are the critical temperature and critical smoke density thresholds, respectively, used to calibrate emergency situations; S15. Evaluate the impact of fire on building safety through real-time monitoring of the building structural integrity index I: I = α2·M+β2·A-γ2·H; Among them, M represents the fire resistance coefficient of building materials, A represents the age attenuation coefficient of the building, H represents the heat received by the building, and α2, β2, and γ2 are adjustment coefficients; S16. Integrate the collected temperature, smoke, and building integrity data with real-time traffic network status information to assess and update possible rescue paths and their obstacles.

3. The intelligent fire fighting path planning method based on ant colony optimization algorithm according to claim 2 is characterized in that: The S2 specifically includes: S21. Collect terrain data of the target area through a geographic information system, including terrain height H(x, y), terrain type T(x, y) and land cover type C(x, y), where (x, y) represents a geographic coordinate point; S22, collecting building layout information of the target area, including the building location P(x, y), the number of floors L, the building purpose U and the building fire resistance level R; S23. Collect information on roads and other infrastructure in the target area, including road types D type (x, y), road width W(x, y) and road condition S(x, y), where (x, y) represents the geographic coordinate point to describe the physical location and status of the road; S24. Utilize GIS data, combined with the real-time location of the fire scene and rescue teams, to update the rescue route planning database, integrate all collected GIS data, and create a dynamically updated map database to support real-time planning and adjustment of rescue routes.

4. The intelligent fire fighting path planning method based on ant colony optimization algorithm according to claim 3 is characterized in that: The S3 specifically includes: S31, initialize the ant colony optimization algorithm, deploy the virtual ant colony in the fire rescue geographic information system, and specify the starting point for each ant as the current location of the rescue team and the target point as the fire scene: Starting point = rescue team location (x s ,y s ); End point = fire location (x f ,y f ); S32. Set the initial pheromone concentration τ0 on all potential rescue paths to simulate the natural behavior of ants leaving pheromones on the paths: Among them, τ(x,y) represents the pheromone concentration at the location (x,y), and τ0 is the initial pheromone concentration setting value; S33, when the ant is searching for a path, it determines its next path based on the relative distance from the current position to the target point and the pheromone concentration, and uses the probability function P ij To select the path: Among them, P ij (t) is the probability of an ant moving from position i to position j at time t, τ ij (t) is the pheromone concentration on path ij, η ij is the heuristic factor of path ij, d ij is the distance from i to j, ∈ is a small constant to prevent division by zero, α and β are parameters that regulate the importance and heuristic factors of pheromones; S34. After the ant reaches the target point, it updates the pheromone concentration on the path according to the conditions on its path to reflect the quality of the path: t ij (t+1)=(1-ρ)·τ ij (t)+Δτ ij ; Among them, τ ij (t+1) is the updated pheromone concentration, ρ is the evaporation rate of pheromone, Δτ ij is the amount of pheromone left by the ant on path ij, Q is the pheromone intensity constant, L ij is the length of the path ij traveled by the ant; S35. After multiple rounds of iterations, the ant colony algorithm compares the pheromone concentrations of each path and finally determines the path with the highest pheromone concentration as the optimal rescue path.

5. The intelligent fire fighting path planning method based on ant colony optimization algorithm according to claim 4 is characterized in that: The S4 specifically includes: S41, real-time monitoring of fire environment changes, including temperature T(t), smoke concentration D(t) and the state of variable obstacles O(t); S42. Dynamically adjust the evaporation rate ρ(t) of pheromone according to real-time monitoring data: ρ(t)=ρ0·(1-e -λ·(T(t)+D(t)+σ·O(t))) ; Among them, ρ0 is the initial evaporation rate, λ and σ are adjustment factors, which respectively represent the influence intensity of temperature, smoke concentration and obstacle state on the pheromone evaporation rate; S43. Update the heuristic factor η in the ant colony algorithm ij (t), taking into account the directness, safety and environmental factors of the route: H(i,j,t)=k·(T(i,j,t)+D(i,j,t)+m·O(i,j,t)); Among them, d ij is the straight-line distance from node i to node j, H(i,j,t) is the path penalty factor considering environmental hazards, k and m are adjustment coefficients, T(i,j,t) and D(i,j,t) are the average temperature and smoke concentration on the path respectively, and O(i,j,t) is the state of obstacles on the path; S44, real-time adjustment of transfer probability P ij (t): S45. Through the intelligent system, the real-time environment and path status data are continuously fed back to the central control system for in-depth data analysis and path optimization.

6. The intelligent fire fighting path planning method based on ant colony optimization algorithm according to claim 5 is characterized in that: The S5 specifically includes: S51. Each possible rescue route is scored for safety, speed, and capacity, with each factor being evaluated according to a specific weighting factor: (P)=w1·S(P)+w2·V(P)+w3·A(P); Among them, P represents the path, S(P) is the safety score of the path, V(P) is the speed score of the path, A(P) is the capacity score of the path, and w1, w2, and w3 are the weights of these three factors respectively; S52. Safety score S(P) is based on the fire intensity, structural stability and smoke density along the path: Among them, T represents the average temperature on the path, D represents the average smoke concentration, O represents the state of structural obstacles, and f1 is the function of safety risk; S53. Speed ​​score V(P) is based on the estimated movement speed of the rescue team on the path: Among them, L represents the total length of the path, and t represents the expected travel time; S54. The capacity score A(P) is assessed based on the width of the path, traffic restrictions and the size of the rescue team: A(P) = k·(wr); Among them, w is the average width of the path, r is the width of the obstacle on the path, and k is an adjustment factor; S55. Select the path with the highest comprehensive score as the recommended rescue path, update the path information in real time to respond to environmental changes, and feed back the selected rescue path to the rescue team through the smart fire protection system.

Images