Emergency material storage site selection method based on plateau forest fire risk evaluation

Abstract

The invention provides an emergency material storage site selection method based on plateau forest fire risk evaluation. The method comprises the following steps: quantifying the fire risk of each region in a plateau forest according to a plateau forest fire risk evaluation system by adopting an entropy weight method; based on the fire risk of each region, establishing an emergency material storage site selection model; and based on an ICD-NSGA-II algorithm, solving the emergency material storage site selection model to obtain an optimal site selection result of the emergency material storage. The entropy weight method is adopted to quantify the fire risk of each region in the plateau forest according to the plateau forest fire risk evaluation system, so that the accuracy of fire risk quantification is improved; based on the fire risk of each region, establishing an emergency material storage site selection model; and on the basis of the ICD-NSGA-II algorithm, solving the emergency material storage site selection model, and determining the optimal site selection result of the emergency material storage, so that the automation level of site selection of the emergency material storage is improved to a great extent, and the site selection accuracy and adaptability are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of computer data processing, and in particular to a method for selecting a site for an emergency material reserve based on plateau forest fire risk assessment. Background Art

[0002] At present, forest fires are a high-frequency and highly destructive natural disaster that not only damages the ecological environment, but also threatens the safety of life and property, and exacerbates air pollution and climate change. As climate change leads to an increase in high temperature and drought weather, the risk of forest fires continues to rise. Rapid and efficient emergency rescue is crucial to disaster reduction, and the reasonable location of emergency material reserves is the key to ensuring timely rescue.

[0003] Traditionally, the location of emergency material reserves often focuses on transportation convenience and storage costs. However, the regionality, seasonality, and randomness of forest fires require comprehensive consideration of fire risks, so that emergency material reserves can be closer to high-risk areas, thereby improving response efficiency and reducing losses. In response to this, an improved method is urgently needed. Summary of the invention

[0004] One of the purposes of the present invention is to provide a method for site selection of emergency material reserves based on plateau forest fire risk assessment, which adopts the entropy weight method to quantify the fire risk of various regions in the plateau forest according to the plateau forest fire risk assessment system, thereby improving the accuracy of fire risk quantification; based on the fire risk of each region, an emergency material reserve site selection model is established; based on the ICD-NSGA-Ⅱ algorithm, the emergency material reserve site selection model is solved to determine the optimal site selection result of the emergency material reserve, which greatly improves the automation level of emergency material reserve site selection and improves the accuracy and adaptability of site selection.

[0005] An embodiment of the present invention provides a method for selecting a site for an emergency material reserve based on plateau forest fire risk assessment, comprising:

[0006] The entropy weight method was used to quantify the fire risk of each area in the plateau forest according to the plateau forest fire risk assessment system;

[0007] Establish a site selection model for emergency material storage based on the fire risks in each region;

[0008] Based on the ICD-NSGA-Ⅱ algorithm, the site selection model of the emergency material reserve warehouse is solved to obtain the optimal site selection result of the emergency material reserve warehouse.

[0009] Optionally, the entropy weight method is used to quantify the fire risk of each area in the plateau forest according to the plateau forest fire risk assessment system, including:

[0010] Taking each region as the evaluation object, the evaluation indicators in the plateau forest fire risk assessment system were extracted;

[0011] Create an evaluation matrix:

[0012]

[0013] Among them, X αβ is the data corresponding to the βth evaluation index under the αth evaluation object, α=1, 2, …, s; β=1, 2, …, t; s is the total number of evaluation objects, and t is the total number of evaluation indicators;

[0014] Standardize the evaluation matrix:

[0015] When the evaluation index is a positive index, Among them, x' αβ is the standardized data, min(x αβ ) is x αβ The minimum value, max(x αβ ) is x αβ The maximum value of

[0016] When the evaluation index is a negative indicator,

[0017] Calculate the normalized value p αβ :

[0018]

[0019] Calculate the entropy value e of the βth indicator β :

[0020]

[0021] Calculate the objective weight w of the βth indicator β :

[0022]

[0023] Calculate the comprehensive score r αβ :

[0024] r αβ =w β x αβ ,α=1,2,…,s; β=1,2,…,t;

[0025] The comprehensive score is used as the fire risk of the corresponding evaluation object; the larger the comprehensive score, the greater the risk level of the fire risk.

[0026] Optional model for selecting the location of emergency material storage depots based on fire risks in different regions, including:

[0027]

[0028] Among them, z1 and z2 are the objective functions, max z1 and minz2 are the maximum and minimum values ​​of the objective functions respectively, and r i represents the risk factor of forest fire in the i-th demand point, i.e., the fire risk, f(d ij ) is the support satisfaction function, a j represents the fixed cost of setting up an emergency reserve at location j, b j represents the storage cost per unit capacity of the emergency reserve at location j, c j represents the storage capacity of the emergency reserve at location j, u represents the unit transportation cost, q i represents the material demand at demand point i, d ij represents the transportation distance from the jth emergency reserve to the ith demand point, x j and ij is a decision variable, which is either 0 or 1. J The total number of emergency reserves established.

[0029] Optionally, the emergency material storage depot location selection model is subject to the following constraints:

[0030] Each demand point will have a reserve pool responsible for it;

[0031] Each demand point is managed by only one reserve pool;

[0032] Only after the reserve is established can it provide services to demand points;

[0033] The number of material storage depots established is 3.

[0034] Optionally, the ICD-NSGA-Ⅱ algorithm includes:

[0035] Step S301: randomly initialize a population; the population is a site selection plan for an emergency material storage depot;

[0036] Step S302: sort the population into different non-dominated levels, label each individual according to its non-dominated level and crowding distance, and evaluate each solution based on maximizing support satisfaction and minimizing total cost;

[0037] Step S303: According to the non-dominated level, dominance intensity and crowding distance of the individuals in the population, the elite individuals are selected to directly enter the next generation population through the elite retention strategy;

[0038] Step S304: using arithmetic crossover operator crossover and mutation to generate a child population from a parent population. In the crossover process, the rationality of the location of the emergency material reserve can be maintained, and mutation can randomly change the location of some reserve warehouses, increase the diversity of solutions, and prevent falling into a local optimum;

[0039] Step S305: Mix the elite individuals in the parent population with the child population to form the next generation population;

[0040] Step S306: Determine whether the current evolutionary generation meets the set generation. If so, the output result, i.e., the optimal storage depot location selection plan, is terminated. Otherwise, repeat steps S302 to S305. This solution is based on the multi-objective optimization method of genetic algorithm, which can find the optimal emergency material storage depot location selection plan while maximizing support satisfaction and minimizing costs. The key steps include: fast non-dominated sorting to evaluate the pros and cons of the solution; elite retention strategy to retain excellent individuals; crossover and mutation to increase population diversity and avoid local optimality; and gradually optimize the solution through algebraic iteration until the termination condition is met.

[0041] Optionally, in step S302, when calculating the congestion distance, the following calculation formula is used for calculation:

[0042]

[0043] In the formula, i D is the crowding distance, is the g-th objective function value of the h-th individual; and are the g-th objective function values ​​of the h-1th individual and the h+1th individual respectively; M is the number of objective functions, i d is the traditional crowding distance.

[0044] Optionally, in step S304, an arithmetic crossover operator is introduced, and its calculation formula is as follows:

[0045]

[0046] Wherein, η+μ=1, η and μ are random numbers uniformly distributed in [0, 1]; and are the real number codes of the two individual decision variables to be crossed in the zth generation, and are the real number codes of the two individual decision variables to be crossed in the z+1th generation respectively; by restricting the value range of η and μ, it is ensured that individuals are no longer limited to selecting crossovers near the unilateral area, so that the search ability of the improved algorithm is significantly improved, and the diversity in population selection is enhanced.

[0047] Optionally, the plateau forest fire risk assessment system includes: primary indicators and secondary indicators.

[0048] Optionally, the first-level indicators include: meteorological indicators, geographical indicators, forest land indicators and economic indicators.

[0049] Optionally, the secondary indicators include: average temperature, average precipitation, average wind speed, and relative humidity corresponding to the meteorological indicators in the primary indicators;

[0050] and, the altitude and slope corresponding to the geographical indicators in the first-level indicators;

[0051] And, the forest coverage rate and forest resource density corresponding to the forest land indicators in the first-level indicators;

[0052] As well as the GDP and unit fire protection investment corresponding to the economic indicators in the first-level indicators.

[0053] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description and the accompanying drawings.

[0054] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] 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:

[0056] Figure 1 A schematic diagram of a method for selecting a site for an emergency material reserve based on plateau forest fire risk assessment in an embodiment of the present invention;

[0057] Figure 2 Flow chart of the ICD-NSGA-Ⅱ algorithm in an embodiment of the present invention;

[0058] Figure 3 A schematic diagram of a site selection result of an emergency material reserve based on plateau forest fire risk assessment in an embodiment of the present invention;

[0059] Figure 4 A comparison diagram of the iteration results of the cost objective function between the prior art and the algorithm of the present invention in an embodiment of the present invention;

[0060] Figure 5 This is a comparison chart of the iterative results of the satisfaction objective function between the prior art and the algorithm of the present invention in an embodiment of the present invention. DETAILED DESCRIPTION

[0061] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0062] The embodiment of the present invention provides a method for selecting a site for an emergency material reserve based on plateau forest fire risk assessment. Figure 1 As shown, including:

[0063] S1: The entropy weight method was used to quantify the fire risk of each area in the plateau forest according to the plateau forest fire risk assessment system;

[0064] S2: Establish a site selection model for emergency material storage based on the fire risk in each region;

[0065] S3: Based on the ICD-NSGA-Ⅱ algorithm, the site selection model of the emergency material reserve warehouse is solved to obtain the optimal site selection result of the emergency material reserve warehouse.

[0066] The entropy weight method is used to quantify the fire risk of various areas in the plateau forest according to the plateau forest fire risk assessment system, including:

[0067] Taking each region as the evaluation object, the evaluation indicators in the plateau forest fire risk assessment system were extracted;

[0068] Create an evaluation matrix:

[0069]

[0070] Among them, X αβ is the data corresponding to the βth evaluation index under the αth evaluation object, α=1, 2, …, s; β=1, 2, …, t; s is the total number of evaluation objects, and t is the total number of evaluation indicators;

[0071] Standardize the evaluation matrix:

[0072] When the evaluation index is a positive index, Among them, x' αβ is the standardized data, min(x αβ ) is x αβ The minimum value, max(x αβ ) is x αβ The maximum value of

[0073] When the evaluation index is a negative indicator,

[0074] Calculate the normalized value p αβ :

[0075]

[0076] Calculate the entropy value e of the βth indicator β :

[0077]

[0078] Calculate the objective weight w of the βth indicator β :

[0079]

[0080] Calculate the comprehensive score r αβ :

[0081] r αβ =w β x αβ ,α=1,2,…,s; β=1,2,…,t;

[0082] The comprehensive score is used as the fire risk of the corresponding evaluation object; the larger the comprehensive score, the greater the risk level of the fire risk.

[0083] The site selection model for emergency material storage depots based on the fire risks in various regions includes:

[0084]

[0085] Among them, z1 and z2 are the objective functions, max z1 and minz2 are the maximum and minimum values ​​of the objective functions respectively, and r i represents the risk factor of forest fire in the i-th demand point, i.e., the fire risk, f(d ij ) is the support satisfaction function, a j represents the fixed cost of setting up an emergency reserve at location j, b j represents the storage cost per unit capacity of the emergency reserve at location j, cj represents the storage capacity of the emergency reserve at location j, u represents the unit transportation cost, q i represents the material demand at demand point i, d ij represents the transportation distance from the jth emergency reserve to the ith demand point, x j and ij is a decision variable, which is either 0 or 1. J The total number of emergency reserves established.

[0086] The site selection model for emergency material storage is subject to the following constraints:

[0087] Each demand point will have a reserve pool responsible for it;

[0088] Each demand point is managed by only one reserve pool;

[0089] Only after the reserve is established can it provide services to demand points;

[0090] The number of material storage depots established is 3.

[0091] The ICD-NSGA-II algorithm includes:

[0092] Step S301: randomly initialize a population; the population is a site selection plan for an emergency material storage depot;

[0093] Step S302: sort the population into different non-dominated levels, label each individual according to its non-dominated level and crowding distance, and evaluate each solution based on maximizing support satisfaction and minimizing total cost;

[0094] Step S303: According to the non-dominated level, dominance intensity and crowding distance of the individuals in the population, the elite individuals are selected to directly enter the next generation population through the elite retention strategy;

[0095] Step S304: using arithmetic crossover operator crossover and mutation to generate a child population from a parent population. In the crossover process, the rationality of the location of the emergency material reserve can be maintained, and mutation can randomly change the location of some reserve warehouses, increase the diversity of solutions, and prevent falling into a local optimum;

[0096] Step S305: Mix the elite individuals in the parent population with the child population to form the next generation population;

[0097] Step S306: Determine whether the current evolutionary generation satisfies the set generation. If so, the process ends and the output result, i.e., the optimal storage depot location selection plan, is output. Otherwise, repeat steps S302 to S305.

[0098] In step S302, when calculating the congestion distance, the following calculation formula is used:

[0099]

[0100] In the formula, i D is the crowding distance, is the g-th objective function value of the h-th individual; and are the g-th objective function values ​​of the h-1th individual and the h+1th individual respectively; and are the minimum and maximum values ​​of the gth objective function respectively; M is the number of objective functions, i d is the traditional crowding distance.

[0101] In step S304, an arithmetic crossover operator is introduced, and its calculation formula is as follows:

[0102]

[0103] Wherein, η+μ=1, η and μ are random numbers uniformly distributed in [0, 1]; and are the real number codes of the two individual decision variables to be crossed in the zth generation, and are the real number codes of the two individual decision variables to be crossed in the z+1th generation.

[0104] The plateau forest fire risk assessment system includes: primary indicators and secondary indicators.

[0105] The first-level indicators include: meteorological indicators, geographical indicators, forest land indicators and economic indicators.

[0106] The secondary indicators include: average temperature, average precipitation, average wind speed, and relative humidity corresponding to the meteorological indicators in the primary indicators;

[0107] and, the altitude and slope corresponding to the geographical indicators in the first-level indicators;

[0108] And, the forest coverage rate and forest resource density corresponding to the forest land indicators in the first-level indicators;

[0109] As well as the GDP and unit fire protection investment corresponding to the economic indicators in the first-level indicators.

[0110] In the above technical scheme, a plateau forest fire risk assessment system is first constructed, and the entropy weight method is used to quantify the fire risk in each region; the fire risk is used as an important factor in the site selection model, and the material support satisfaction maximization and total cost minimization are comprehensively considered to construct a multi-objective optimization site selection model; based on the NSGA-Ⅱ algorithm, improvements are made in the crossover operator and congestion calculation, and the ICD-NSGA-Ⅱ algorithm is proposed; the ICD-NSGA-Ⅱ algorithm is used to solve and obtain the optimal site selection result of the emergency material reserve. A forest fire risk assessment system is constructed to quantify the fire risk and integrate it into the site selection model of the emergency material reserve, comprehensively considering the material support satisfaction and cost minimization. Through the ICD-NSGA-Ⅱ algorithm, the optimal site selection of the emergency material reserve is successfully planned, which improves the efficiency of emergency rescue.

[0111] The objective function of the emergency material storage depot location selection model is expressed as follows:

[0112]

[0113] Among them, z1 and z2 are the objective functions, max z1 and minz2 are the maximum and minimum values ​​of the objective functions respectively, and r irepresents the risk factor of forest fire in the i-th demand point, i.e., the fire risk, f(d ij ) is the support satisfaction function, a j represents the fixed cost of setting up an emergency reserve at location j, b j represents the storage cost per unit capacity of the emergency reserve at location j, cj represents the storage capacity of the emergency reserve at location j, u represents the unit transportation cost, q i represents the material demand at demand point i, d ij represents the transportation distance from the jth emergency reserve to the ith demand point, x j and ij is a decision variable, which is either 0 or 1.

[0114] The support satisfaction function is as follows:

[0115]

[0116] If the distance d between the material storage warehouse and the demand point ij When it is lower than d1, the satisfaction of demand point j is 1; if d ij If it is greater than d3, the satisfaction is considered to be 0. To establish this function, we mainly need to establish d1 <d ij ≤d2 and d2 <d ij Function f(d ij ).

[0117] The parameter k in the formula describes the sensitivity of demand point j to the material support distance. When k = 1, the function is a linear function. As long as the material support distance changes between [d1, d3], the satisfaction of demand point j with material rescue will decrease linearly; when 0 < k < 1, f(d ij ) is a convex function. When k>1, the function is a concave function. Therefore, the satisfaction of the demand point with respect to relief supplies can be expressed by the function f(d ij ) is a comprehensive description; d1 and d2 are setting parameters.

[0118] The crowding distance of the traditional NSGA2 algorithm only focuses on the distance between adjacent individuals. Individuals with large crowding distance differences on different sub-goals have a lower probability of being inherited, which is not conducive to maintaining the distribution of the solution set. The traditional distance formula is:

[0119]

[0120] in, is the g-th objective function value of the h-th one; and are the minimum and maximum values ​​of the g-th objective function respectively; M is the number of objective functions.

[0121] Therefore, this application adopts a new crowding distance that takes variance into consideration to improve the convergence and distribution of the algorithm. The calculation formula is as follows:

[0122]

[0123] In the formula, i D is the crowding distance, is the g-th objective function value of the h-th individual; and are the g-th objective function values ​​of the h-1th individual and the h+1th individual respectively; and are the minimum and maximum values ​​of the gth objective function respectively; M is the number of objective functions, i d is the traditional crowding distance;

[0124] The arithmetic crossover operator is introduced, and its calculation formula is as follows:

[0125]

[0126] Wherein, η+μ=1, η and μ are random numbers uniformly distributed in [0, 1]; and are the real number codes of the two individual decision variables to be crossed in the zth generation, and are the real number codes of the two individual decision variables to be crossed in the z+1th generation; by restricting the value range of η and μ, it is ensured that individuals are no longer limited to selecting crossovers near the unilateral region, which significantly improves the search ability of the improved algorithm and enhances the diversity in population selection

[0127] Algorithm flow:

[0128] Step 1: Randomly initialize the population;

[0129] Step 2: Perform fast non-dominated sorting on the population and divide it into different non-dominated levels. Each individual is labeled according to its non-dominated level and crowding distance.

[0130] Step 3: According to the non-dominated level, dominance intensity and crowding distance of the individuals in the population, the elite individuals are selected to directly enter the next generation of the population through the elite retention strategy;

[0131] Step 4: Use arithmetic crossover operator to perform crossover and mutation to generate offspring population from parent population;

[0132] Step 5: Mix the elite individuals in the parent population with the offspring population to form the next generation population;

[0133] Step 6: Determine whether the current evolutionary generation satisfies the set generation. If so, end the output process. Otherwise, repeat Step 2 to Step 5.

[0134] The flowchart of the ICD-NSGA-Ⅱ algorithm is as follows Figure 2 The schematic diagram of the site selection results of the emergency material storage depot based on the plateau forest fire risk assessment is shown in Figure 3 shown.

[0135] Taking 16 cities and autonomous prefectures in Yunnan Province as an example, Figure 3 The site selection results show that the emergency material reserve in the northwest is set up in Dali, which is a high-risk area and can quickly support areas with higher forest fire risks, while radiating to five cities: Diqing, Nujiang, Lijiang, Dehong, and Baoshan; the emergency material reserve in Pu'er in southern Yunnan is used as the site selection center, radiating to four cities around Lincang, Xishuangbanna, and Yuxi; the forest fire material reserve in southern Yunnan is set up in Kunming. Although the forest fire risk in Kunming is not high, it has an excellent geographical location and can radiate to five cities: Chuxiong, Honghe, Wenshan, Qujing, and Zhaotong. Kunming is very close to Chuxiong, which has a higher risk, and can provide material support in the first time when a forest fire occurs. From the above, it can be seen that the site selection research method of the emergency material reserve based on forest fire risk assessment in this application can be well applied to Yunnan Province, a province with a high incidence of forest fires.

[0136] Table 2 is a comparison of the results of 50 experiments. According to the data, the ICD-NSGA-II algorithm is superior to the traditional NSGA-Ⅱ algorithm in terms of both the average running time of the algorithm and the results obtained. Therefore, the ICD-NSGA-II algorithm has higher solution efficiency and better results.

[0137] Table 2 50 experimental results

[0138]

[0139] Compared with the traditional NSGA-II algorithm, the ICD-NSGA-II algorithm shows obvious advantages in site selection results. Its time satisfaction is significantly improved, the total site selection cost is further reduced, and it better meets the actual needs of emergency material demand points. This shows that the site selection results optimized by the ICD-NSGA-II algorithm have strong advantages in efficiency and economy, and have high feasibility and practical value.

[0140] Figure 4 and Figure 5 Comparison of iteration graphs of different algorithms. Figure 4 and Figure 5It can be seen that the convergence of the improved ICD-NSGA-Ⅱ algorithm is stronger than that of the traditional NSGA-Ⅱ algorithm.

[0141] By constructing a forest fire risk assessment system and quantifying forest fire risks, combined with the ICD-NSGA-Ⅱ algorithm, the scientific site selection of emergency material reserves is achieved. This method not only improves rescue efficiency and cost-effectiveness, but also provides effective decision-making support for forest fire emergency management, and enhances the scientificity and accuracy of emergency response. Specifically, this method can ensure that when a forest fire occurs, emergency supplies can be delivered to the affected area more quickly and accurately, reducing the losses caused by the fire. At the same time, by optimizing the site selection model and algorithm, the model's solution efficiency and the reliability of the results are also improved, providing new ideas and methods for the site selection of emergency material reserves in other regions, which has important theoretical and practical value.

[0142] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A method for selecting a site for emergency material storage based on plateau forest fire risk assessment, characterized in that: include: The entropy weight method was used to quantify the fire risk of each area in the plateau forest according to the plateau forest fire risk assessment system; Establish a site selection model for emergency material storage based on the fire risks in each region; Based on the ICD-NSGA-Ⅱ algorithm, the site selection model of the emergency material reserve warehouse is solved to obtain the optimal site selection result of the emergency material reserve warehouse.

2. The method for selecting a site for emergency material storage based on plateau forest fire risk assessment according to claim 1, characterized in that: The entropy weight method is used to quantify the fire risk of various areas in the plateau forest according to the plateau forest fire risk assessment system, including: Taking each region as the evaluation object, the evaluation indicators in the plateau forest fire risk assessment system were extracted; Create an evaluation matrix: Among them, X αβ is the data corresponding to the βth evaluation index under the αth evaluation object, α=1, 2, …, s; β=1, 2, …, t; s is the total number of evaluation objects, and t is the total number of evaluation indicators; Standardize the evaluation matrix: When the evaluation index is a positive index, Among them, x' αβ is the standardized data, min(x αβ ) is x αβ The minimum value, max(x αβ ) is x αβ The maximum value of When the evaluation index is a negative indicator, Calculate the normalized value p αβ : Calculate the entropy value e of the βth indicator β : Calculate the objective weight w of the βth indicator β : Calculate the comprehensive score r αβ : r αβ =w β x αβ ,α=1,2,…,s;β=1,2,…,t; The comprehensive score is used as the fire risk of the corresponding evaluation object; the larger the comprehensive score, the greater the risk level of the fire risk.

3. The method for selecting a site for emergency material storage based on plateau forest fire risk assessment according to claim 2, characterized in that: The site selection model for emergency material storage depots based on the fire risks in various regions includes: Among them, z1 and z2 are the objective functions, max z1 and minz2 are the maximum and minimum values ​​of the objective functions respectively, and r i represents the risk factor of forest fire in the i-th demand point, i.e., the fire risk, f(d ij ) is the support satisfaction function, a j represents the fixed cost of setting up an emergency reserve at location j, b j represents the storage cost per unit capacity of the emergency reserve at location j, cj represents the storage capacity of the emergency reserve at location j, u represents the unit transportation cost, q i represents the material demand at demand point i, d ij represents the transportation distance from the jth emergency reserve to the ith demand point, x j and ij is a decision variable, which is either 0 or 1. J The total number of emergency reserves established.

4. The method for selecting a site for emergency material storage based on plateau forest fire risk assessment according to claim 3, characterized in that: The site selection model for emergency material storage is subject to the following constraints: Each demand point will have a reserve pool responsible for it; Each demand point is managed by only one reserve pool; Only after the reserve is established can it provide services to demand points; The number of material storage depots established is 3.

5. The method for selecting a site for emergency material storage based on plateau forest fire risk assessment according to claim 1, characterized in that: The ICD-NSGA-II algorithm includes: Step S301: randomly initialize a population; the population is a site selection plan for an emergency material storage depot; Step S302: sort the population into different non-dominated levels, label each individual according to its non-dominated level and crowding distance, and evaluate each solution based on maximizing support satisfaction and minimizing total cost; Step S303: According to the non-dominated level, dominance intensity and crowding distance of the individuals in the population, the elite individuals are selected to directly enter the next generation population through the elite retention strategy; Step S304: using arithmetic crossover operator crossover and mutation to generate a child population from a parent population. In the crossover process, the rationality of the location of the emergency material reserve can be maintained, and mutation can randomly change the location of some reserve warehouses, increase the diversity of solutions, and prevent falling into a local optimum; Step S305: Mix the elite individuals in the parent population with the child population to form the next generation population; Step S306: Determine whether the current evolutionary generation satisfies the set generation. If so, the process ends and the output result, i.e., the optimal storage depot location selection plan, is output. Otherwise, repeat steps S302 to S305.

6. The method for selecting a site for emergency material storage based on plateau forest fire risk assessment according to claim 5, characterized in that: In step S302, when calculating the congestion distance, the following calculation formula is used: In the formula, i D is the crowding distance, f g h is the g-th objective function value of the h-th individual, then and are the g-th objective function values ​​of the h-1th individual and the h+1th individual respectively; M is the number of objective functions, i d is the traditional crowding distance.

7. The method for selecting a site for emergency material storage based on plateau forest fire risk assessment according to claim 5, characterized in that: In step S304, an arithmetic crossover operator is introduced, and its calculation formula is as follows: Wherein, η+μ=1, η and μ are random numbers uniformly distributed in [0, 1]; and are the real number codes of the two individual decision variables to be crossed in the zth generation, and are the real number codes of the two individual decision variables to be crossed in the z+1th generation.

8. The method for selecting a site for emergency material storage based on plateau forest fire risk assessment according to claim 1, characterized in that: The plateau forest fire risk assessment system includes: primary indicators and secondary indicators.

9. The method for selecting a site for emergency material storage based on plateau forest fire risk assessment according to claim 8, characterized in that: The first-level indicators include: meteorological indicators, geographical indicators, forest land indicators and economic indicators.

10. The method for selecting a site for emergency material storage based on plateau forest fire risk assessment according to claim 9, characterized in that: The secondary indicators include: average temperature, average precipitation, average wind speed, and relative humidity corresponding to the meteorological indicators in the primary indicators; and, the altitude and slope corresponding to the geographical indicators in the first-level indicators; And, the forest coverage rate and forest resource density corresponding to the forest land indicators in the first-level indicators; As well as the GDP and unit fire protection investment corresponding to the economic indicators in the first-level indicators.

Images