Method and device for predicting requirements of emergency rescue equipment

Abstract

The embodiment of the invention provides a method and device for predicting the demand of emergency rescue equipment, and relates to the technical field of emergency and computer, and the method comprises the steps: obtaining the accident process information of a target region, and determining the demand of the equipment according to the accident process information; constructing an equipment demand system structure according to the equipment demand and the system structure layout; obtaining constraint conditions, and optimizing the equipment overall performance and the equipment total cost of the equipment demand system structure according to the constraint conditions to obtain a multi-objective optimization model; and solving the target optimization model according to the constraint condition and a genetic algorithm to obtain the emergency rescue equipment requirement of the target area. The method realizes reasonable allocation of emergency resources.

Description

Technical Field

[0001] The present invention relates to the field of emergency and computer technology, and in particular to a method and device for predicting demand for emergency rescue equipment. Background Art

[0002] The mission characteristics and laws of coal mine emergency rescue determine that emergency rescue equipment will inevitably develop in the direction of intelligence, lightweight, modularization, standardization, and environmental adaptability, which is the "four modernizations and one quality" development direction of equipment in the coal mine field. As an evaluation indicator, it is mainly used to measure the changes in the capabilities of the equipment system that may affect the entire equipment emergency system.

[0003] With the rapid development of the economy, the demand for mineral resources continues to increase, and mine accidents are becoming more and more frequent. Mine accidents not only pose a serious threat to the life safety of miners, but also cause huge losses. Therefore, it has become an urgent task to strengthen mine emergency management, improve the emergency rescue capabilities of mine accidents, and ensure the safety of miners' lives. Emergency rescue equipment is a decisive factor that restricts the completion of emergency rescue tasks. It is of great significance to propose a set of scientific and reasonable emergency rescue equipment demand prediction and configuration methods in the coal mine field to improve the quality of emergency rescue tasks.

[0004] At present, in the field of coal mine emergency, the types of emergency rescue equipment are complex and diverse. Different types of emergency rescue equipment are selected for different types of accidents. There are problems such as chaotic classification of equipment and insufficient equipment coverage in emergency rescue work. The equipment configuration structure is not standardized and reasonable, resulting in insufficient equipment types for each enterprise team during disaster rescue. At the same time, due to the lack of a systematic equipment configuration structure, it takes time to select rescue equipment, resulting in the inability to carry out rescue work smoothly and affecting the rescue time. Summary of the invention

[0005] The purpose of the embodiments of the present invention is to provide a method and device for predicting the demand for emergency rescue equipment, which method realizes the reasonable allocation of emergency resources.

[0006] In order to achieve the above object, an embodiment of the present invention provides a method for predicting demand for emergency rescue equipment, the method comprising: Obtaining accident process information of the target area, and determining equipment requirements based on the accident process information; constructing an equipment requirement architecture according to the equipment requirement and the architecture layout; Obtaining constraint conditions, optimizing the overall performance and total cost of equipment of the equipment requirement system structure according to the constraint conditions, and obtaining a multi-objective optimization model; The target optimization model is solved according to the constraint conditions and the genetic algorithm to obtain the emergency rescue equipment requirements of the target area.

[0007] Optionally, the accident process information includes: abnormal and dangerous situation response process information of production site personnel, internal emergency response process information of the production enterprise, and accident rescue process information of professional rescue teams.

[0008] Optionally, determining equipment requirements according to the accident process information includes: Based on Hall's three-dimensional structural model theory, the equipment system is divided into five dimensions: rescue subject, mission stage, spatial dimension, equipment function, and accident type; Obtain information on accident emergency rescue processes in the mining field, and further organize and divide them according to their use time, use location, use personnel, use functions and use scenarios; Obtain the rescue subject requirements of the accident process information, obtain the corresponding mission stage requirements based on the rescue subject requirements, obtain the corresponding equipment function requirements based on the mission stage requirements, and obtain the corresponding equipment requirement group based on the equipment function requirements.

[0009] Optionally, the equipment requirement architecture includes a rescue subject layer, a mission phase layer, an equipment function layer, and an equipment requirement layer.

[0010] Optionally, the acquisition constraint condition includes: Determining the equipment requirement of the equipment requirement using a multiple linear regression equation; The equipment demand includes general equipment demand and special equipment demand; The general equipment quantity and the special equipment requirement quantity serve as constraints of the equipment requirement system architecture.

[0011] Optionally, optimizing the total equipment capacity and total equipment cost of the equipment requirement architecture according to the constraint conditions includes: Maximizing the total equipment capacity of the equipment requirement architecture; Minimizing the total equipment cost of the equipment requirement architecture; The total equipment capacity = equipment performance × corresponding equipment quantity; Total equipment cost = cost of a single piece of equipment × corresponding equipment quantity.

[0012] Optionally, the maximization process of the total equipment capacity includes: ; The minimization process of the total equipment cost includes: ; in, is the first objective function, is the performance of a certain equipment, i represents the i-th equipment type, i is equal to n at most, n is the number of decision variables, is the decision variable, is the second objective function, The cost of a certain equipment.

[0013] On the other hand, the present invention also provides a device for predicting the demand for emergency rescue equipment, the device comprising: An acquisition module, used to acquire accident process information of a target area and determine equipment requirements according to the accident process information; A first processing module is used to construct an equipment requirement architecture according to the equipment requirement and the architecture layout; The second processing module is used to obtain constraint conditions, and optimize the overall equipment performance and total equipment cost of the equipment requirement system structure according to the constraint conditions to obtain a multi-objective optimization model; The third processing module is used to solve the target optimization model according to the constraint conditions and the genetic algorithm to obtain the emergency rescue equipment demand of the target area.

[0014] Optionally, determining equipment requirements according to the accident process information includes: Based on Hall's three-dimensional structural model theory, the equipment system is divided into five dimensions: rescue subject, mission stage, spatial dimension, equipment function, and accident type; Obtain information on accident emergency rescue processes in the mining field, and further organize and divide them according to their use time, use location, use personnel, use functions and use scenarios; Obtain the rescue subject requirements of the accident process information, obtain the corresponding mission stage requirements based on the rescue subject requirements, obtain the corresponding equipment function requirements based on the mission stage requirements, and obtain the corresponding equipment requirement group based on the equipment function requirements.

[0015] Optionally, the acquisition constraint condition includes: Determining the equipment requirement of the equipment requirement using a multiple linear regression equation; The equipment demand includes general equipment demand and special equipment demand; The general equipment quantity and the special equipment requirement quantity serve as constraints of the equipment requirement system architecture.

[0016] Optionally, optimizing the total equipment capacity and total equipment cost of the equipment requirement architecture according to the constraint conditions includes: Maximizing the total equipment capacity of the equipment requirement architecture; Minimizing the total equipment cost of the equipment requirement architecture; The total equipment capacity = equipment performance × corresponding equipment quantity; Total equipment cost = single equipment cost × corresponding equipment quantity; The maximization process of the total equipment capacity includes: ; The minimization process of the total equipment cost includes: ; in, is the first objective function, is the performance of a certain equipment, i represents the i-th equipment type, i is equal to n at most, n is the number of decision variables, is the decision variable, is the second objective function, The cost of a certain equipment.

[0017] A method for predicting emergency rescue equipment demand of the present invention comprises: obtaining accident process information of a target area, determining equipment demand according to the accident process information; constructing an equipment demand architecture according to the equipment demand and architecture layout; obtaining constraint conditions, optimizing the total equipment capacity and total equipment cost of the equipment demand architecture according to the constraint conditions, and obtaining a multi-objective optimization model; solving the target optimization model according to the constraint conditions and a genetic algorithm, and obtaining the emergency rescue equipment demand of the target area. The method establishes a rescue team equipment configuration model based on a multi-objective optimization algorithm, realizes the optimal selection of schemes under the rescue team as the configuration subject structure, and is conducive to the rational allocation of emergency resources.

[0018] Other features and advantages of the embodiments of the present invention will be described in detail in the subsequent detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The accompanying drawings are used to provide a further understanding of the embodiments of the present invention and constitute a part of the specification. Together with the following specific implementations, they are used to explain the embodiments of the present invention, but do not constitute a limitation on the embodiments of the present invention. In the accompanying drawings: Figure 1 It is a flow chart of a method for predicting demand for emergency rescue equipment of the present invention; Figure 2 is a schematic diagram of a flow chart of Embodiment 2 of the present invention; Figure 3 is a schematic diagram of a specific flow chart of step S1 in the second embodiment of the present invention; Figure 4 is a schematic diagram of a specific flow chart of step S2 of the second embodiment of the present invention; Figure 5 is a schematic diagram of a specific flow chart of step S3 of the second embodiment of the present invention; Figure 6 is a schematic diagram of a specific flow chart of step S4 in the second embodiment of the present invention; Figure 7 A schematic diagram of the system structure of coal mine accident emergency rescue equipment requirements of the present invention; Figure 8 It is a schematic diagram of a device for predicting the demand for emergency rescue equipment according to the present invention.

[0020] Description of Reference Numerals 100-A device for predicting the need for emergency rescue equipment; 200-Get module; 300-first processing module; 400-second processing module; 500-the third processing module. DETAILED DESCRIPTION

[0021] The specific implementation of the embodiment of the present invention is described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation described here is only used to illustrate and explain the embodiment of the present invention, and is not used to limit the embodiment of the present invention.

[0022] It should be noted that the acquisition, transmission, storage, use, and processing of data in the technical solution of this application are in compliance with the relevant provisions of national laws and regulations. In the embodiments of this application, some existing solutions in the industry such as certain software, components, and models may be mentioned, which should be considered as exemplary. Their purpose is only to illustrate the feasibility of implementing the technical solution of this application, but it does not mean that the applicant has or will necessarily use the solution.

[0023] Embodiment 1 Figure 1 is a flow chart of a method for predicting emergency rescue equipment demand of the present invention, such as Figure 1 As shown, a method for predicting emergency rescue equipment demand of the present invention includes: Step S101 is to obtain accident process information of a target area and determine equipment requirements according to the accident process information.

[0024] Specifically, the accident process information includes: abnormal and dangerous situation response process information of production site personnel, internal emergency response process information of production enterprises, and accident rescue process information of professional rescue teams.

[0025] According to a specific implementation method, determining equipment requirements based on the accident process information includes: dividing the equipment system according to five dimensions: rescue subject, mission stage, spatial dimension, equipment function, and accident type based on Hall three-dimensional structural model theory; obtaining accident emergency rescue process information in the mining field, and further organizing and dividing it according to its usage time, usage location, user, usage function and usage scenario; obtaining the rescue subject requirements of the accident process information, obtaining the corresponding mission stage requirements based on the rescue subject requirements, obtaining the corresponding equipment function requirements based on the mission stage requirements, and obtaining the corresponding equipment requirement group based on the equipment function requirements.

[0026] Obtain information on the emergency rescue process of accidents in the mining field, and conduct a multi-dimensional analysis of equipment requirements based on the Hall 3D structure. Specifically, based on the emergency rescue link of coal mine accidents, it is divided into three stages: response to abnormal dangerous situations of production site personnel, internal emergency disposal of production enterprises, and accident rescue by professional rescue teams; The equipment system is divided into five dimensions: rescue subject, mission stage, spatial dimension, equipment function, and accident type. Based on the Hall three-dimensional structure, a multi-dimensional analysis of equipment requirements is conducted to obtain the rescue subject-mission stage-equipment function-equipment requirements under the overall mission goal of coal mine accident emergency rescue.

[0027] Based on the Hall three-dimensional structural model theory, the original time dimension, knowledge dimension, and logic dimension are effectively adapted and expanded, and the equipment system is divided according to five dimensions: rescue subject, mission stage, spatial dimension, equipment function, and accident type. Starting from the dimension of rescue subject, the equipment system is divided into three categories based on the complexity of rescue, namely, equipment for responding to abnormal dangerous situations of production site personnel, emergency response equipment within production enterprises, and accident rescue equipment for professional rescue teams; starting from the dimension of mission stage, the equipment system is divided into four categories based on the emergency management stage of emergencies, namely, prevention equipment, preparation equipment, response equipment, and recovery equipment; starting from the spatial dimension, the equipment system is divided into four categories based on the spatial level of emergency management of emergencies, namely, high-altitude equipment, ground equipment, underground equipment, and underwater equipment; starting from the equipment function, the equipment system is divided into prediction and warning equipment, individual protection equipment, communication equipment, and other equipment based on the specific functions of emergency equipment. There are eight major categories of equipment, including information equipment, fire-fighting and rescue equipment, medical rescue equipment, transportation equipment, engineering rescue equipment, and emergency technical equipment. The eight categories of equipment functions are further divided into several subcategories, including hazard source identification, disaster reporting, emergency rescue, disaster area reconnaissance, information analysis, emergency operations, self-rescue, resource allocation, base establishment, accident record analysis and management, accident level determination, life support, post-resettlement, maintaining public order, and on-site cleanup. From the dimension of accident type, based on the five major natural disasters in coal mines, the equipment system is divided into five categories: special equipment for gas accidents, special equipment for mine fire accidents, special equipment for roof accidents, special equipment for flood accidents, and special equipment for coal dust accidents.

[0028] From the perspective of the rescue subject, the equipment functions are decomposed layer by layer according to the mission stage, reflecting the hierarchical relationship between the emergency rescue equipment systems. For example, the rescue subjects include the production site personnel's abnormal dangerous situation response (A), the production enterprise's internal emergency disposal (B), and the professional rescue team's accident rescue (C). On the basis of establishing the rescue subject structure framework, the tasks under the five stages of prevention, preparation, response and recovery are decomposed. For example, the tasks under the production site personnel's abnormal dangerous situation response (A) include dangerous situation investigation (A1), information reporting (A2), response disposal (A3), rescue and escape (A4) and on-site recovery (A5).

[0029] On the basis of the decomposition and analysis of the rescue subject-task stage, starting from the equipment emergency development life cycle and the emergency methods directly or indirectly involved, the eight equipment functions of prediction and warning equipment, individual protection equipment, communication and information equipment, fire fighting and rescue equipment, medical rescue equipment, transportation equipment, engineering rescue equipment, and emergency technical equipment are further sorted and divided. For example, in the task stage dimension, the equipment functions of the tasks under the task stage dimension, such as the danger investigation A1, information reporting A2, response and disposal A3, rescue and escape A4, and on-site recovery A5, correspond to the hazard source identification capability, disaster reporting capability, emergency rescue capability, self-rescue capability, and post-disaster management capability; Based on the analysis of rescue subject-mission phase-equipment function, the equipment requirements are summarized, such as the hazard identification capability, disaster reporting capability, emergency rescue capability, self-rescue capability, and post-disaster management capability among the equipment functions. The equipment requirements correspond to detection equipment, alarm equipment, communication equipment, tool spare parts, personal protective equipment, medical and logistics support equipment.

[0030] Step S102 is to construct an equipment requirement architecture according to the equipment requirement and the architecture layout.

[0031] Specifically, the equipment requirement system structure includes a rescue subject layer, a mission phase layer, an equipment function layer, and an equipment requirement layer.

[0032] According to a specific implementation method, the equipment requirements are analyzed based on the rescue links to obtain the equipment required by the production site, production enterprise and professional rescue team when carrying out emergency rescue work; according to the system architecture layout, a coal mine accident emergency rescue equipment requirement system architecture is generally formed, including the rescue subject layer, task stage layer, equipment function layer and equipment requirement layer.

[0033] Based on the analysis of equipment requirements in the rescue phase, we can obtain the equipment required by the production site, production enterprise and professional rescue team when carrying out emergency rescue work. For example, the equipment demand analysis of the production site is shown in Table 1.

[0034] According to the architecture layout, the overall coal mine accident emergency rescue equipment demand architecture is formed, including the rescue subject layer, task stage layer, equipment function layer, and equipment demand layer. The construction concepts of the architecture include relevance, integrity, functionality, and scalability.

[0035] Table 1:

[0036] The equipment demand analysis of production enterprises is shown in Table 2.

[0037] Table 2:

[0038] The equipment demand analysis of professional rescue teams is shown in Table 3.

[0039] Table 3:

[0040] Step S103 is to obtain constraint conditions, and optimize the overall equipment performance and total equipment cost of the equipment requirement architecture according to the constraint conditions to obtain a multi-objective optimization model.

[0041] Specifically, the acquisition of constraint conditions includes: using a multivariate linear regression equation to determine the equipment requirement quantity of the equipment requirement; the equipment requirement quantity includes a general equipment quantity and a special equipment quantity; the general equipment quantity and the special equipment quantity serve as constraint conditions for the equipment requirement system architecture.

[0042] According to a specific implementation method, the total equipment capacity and total equipment cost of the equipment requirement system structure are optimized according to the constraint conditions, including: maximizing the total equipment capacity of the equipment requirement system structure; minimizing the total equipment cost of the equipment requirement system structure; the total equipment capacity = equipment performance × corresponding equipment quantity; the total equipment cost = single equipment cost × corresponding equipment quantity.

[0043] The maximization process of the total equipment capacity includes: ; The minimization process of the total equipment cost includes: ;in, is the first objective function, is the performance of a certain equipment, i represents the i-th equipment type, i is equal to n at most, n is the number of decision variables, is the decision variable, is the second objective function, The cost of a certain equipment.

[0044] The present invention introduces a multivariate linear regression equation to constrain equipment demand, and on this basis constructs a multi-objective optimization model with the goals of maximizing the overall performance of equipment and minimizing the total cost of equipment.

[0045] Specifically, considering that the mine rescue team is responsible for the rescue equipment needs of k coal mines in the surrounding area, the mine rescue team is used as the supply point of rescue equipment for k coal mines, and a multi-objective optimization model is introduced to determine its decision variables; the maximum total equipment capability and the minimum total equipment cost are used as the objective function of the model; the "four modernizations and one quality" development direction of equipment intelligence, lightweight, modularization, standardization, and environmental adaptability is used as the standard for judging the total equipment capability, and its weight and score are calculated; the multivariate linear regression equation is used to determine the equipment demand, and the general equipment and special equipment demand constraints are used as the constraints of the model respectively; the above decision variables, objective functions and constraints are introduced to establish a multi-objective optimization model for emergency equipment configuration.

[0046] Assuming that a mine rescue team provides information about a certain rescue equipment for the k coal mines it is responsible for, and their values ​​are to be optimized, the mathematical model uses the number of rescue equipment configurations corresponding to the k coal mines as the optimization variable x, and n variables composed of x can constitute a variable set X. The specific mathematical expression of the decision variable is as follows: , where X is a set of variables, is the decision variable, i.e. the number of individuals of the nth coal mine rescue equipment, is the n-dimensional feasible solution domain.

[0047] The objective function of the model is to maximize the total equipment capability and minimize the total equipment cost. The maximized total equipment capability can be explained as: total equipment capability = equipment performance × corresponding equipment quantity. If there are n types of equipment, the total equipment capability is accumulated n times; the specific mathematical expression of the maximized total equipment capability is as follows: , where is the first objective function, is the performance of a certain equipment, i represents the i-th equipment type, i is equal to n at most, n is the number of decision variables, is the decision variable.

[0048] The minimized total equipment cost can be interpreted as: total equipment cost = single equipment cost × corresponding equipment quantity. If there are n types of equipment, the total equipment cost is accumulated n times. For economic considerations, the total equipment cost is required to be minimized while meeting the emergency rescue quantity and performance requirements. The mathematical relationship of the second objective function can be established. The specific mathematical expression of the minimized total equipment cost is as follows: , is the second objective function, is the cost of a certain equipment, i represents the i-th equipment type, i is equal to n at most, n is the number of decision variables, The decision variable is the "four modernizations and one quality" development direction of equipment intelligence, lightweight, modularization, standardization, and environmental adaptability is used as the standard for judging the total equipment capability, and its weight and score are calculated: the total equipment capability can be obtained by quantifying the performance of the equipment; among them, the equipment performance is characterized by three secondary indicators: the equipment's own nature, rescue capability, and maintainability. The equipment's own nature is characterized by five third-level indicators: intelligence, lightweight, standardization, modularization, and environmental adaptability. The equipment's rescue efficiency is characterized by three third-level indicators: startup speed, reliability, and operability. The equipment's maintainability is characterized by two third-level indicators: maintenance frequency and maintenance difficulty.

[0049] The calculation of equipment performance can be expressed as: equipment performance = equipment properties × weight 1 + equipment rescue efficiency × weight 2 + equipment maintainability × weight 3; the specific mathematical expression of equipment performance is as follows: , is the performance of a certain equipment, i represents the i-th equipment type, i is equal to n at most, j is the number of secondary evaluation indicators, j is equal to 3 at most, is the weight of the secondary index of a certain equipment performance, Score the secondary index of a certain equipment performance. Among them, the importance comparison method is used to determine the numerical value of the secondary index weight; the secondary index of equipment performance includes the equipment's own properties, rescue capabilities, and maintainability, and the third-level index is constructed again for further analysis; the equipment's own properties include the equipment's intelligence, lightweight, standardization, modularization, and environmental adaptability, that is, four modernizations and one property, which can be expressed as: equipment's own properties = intelligence × weight 1 + lightweight × weight 2 + standardization × weight 3 + modularization × weight 4 + environmental adaptability × weight 5.

[0050] Equipment rescue efficiency includes the startup speed, reliability and operability of the equipment, which can be expressed as: Equipment rescue efficiency = startup speed × weight 1 + reliability × weight 2 + operability × weight 3; Equipment maintainability includes maintenance frequency and maintenance difficulty, which can be expressed as: Equipment maintainability = maintenance frequency × weight 1 + maintenance difficulty × weight 2; The specific mathematical expression of the score of the secondary indicators of equipment performance (equipment's own properties, rescue capability, maintainability) is as follows: , is the score of the secondary index of a certain equipment performance, i represents the i-th equipment type, i is equal to n at most, k is the number of the third-level evaluation indexes, and the value of k is 2, 3, 5, Score the three-level performance indicators of a certain equipment. It is the weight of the three-level evaluation index of a certain equipment performance.

[0051] The weights are determined by the hierarchical analysis method: the equipment performance is divided into three secondary indicators: the equipment's own properties, usage efficiency and maintainability. The equipment's own properties are further divided into five third-level indicators: equipment intelligence, lightweight, lightweight, modularization and environmental adaptability. The equipment's usage efficiency can be divided into three third-level indicators: startup speed, usage function and daily maintenance. Maintainability is divided into two third-level indicators: maintenance frequency and maintenance difficulty.

[0052] Construct a judgment matrix: compare and assign values ​​to the importance of indicators in pairs, and use the 1~9 scaling method to determine the specific value of each indicator to construct a judgment matrix.

[0053] After constructing the judgment matrix, the weight value of each indicator factor can be calculated according to each weight value. The indicator weight vector , the weight calculation formula is: , where is the maximum eigenvalue of the judgment matrix, w is the corresponding The feature vector of .

[0054] Taking a certain equipment as an example, to determine the weight of its equipment performance, we first need to construct the judgment matrix U and calculate its maximum eigenvalue , the eigenvector is Then, the judgment matrices U1, U2, and U3 are constructed in the order of the secondary and tertiary indicators. Calculate the maximum eigenvalue , the eigenvector is ; Calculate its maximum eigenvalue , the eigenvector is ; Calculate its maximum eigenvalue , the eigenvector is ; Entropy weight method to correct weights: including data standardization, indicator entropy weight calculation, and comprehensive weight calculation. The corrected weight results are as follows:

[0055]

[0056]

[0057]

[0058] The equipment types under the flooding accident type include special equipment (water pumps ) and general equipment (mine rescue vehicles , Combat uniform , Intercom , Life detector , oxygen respirator ), and score their own equipment performance respectively, with a full score of 10 points, and determine the data assignment standard in combination with different secondary indicators; taking equipment intelligence as an example, the higher the degree of intelligence, the higher the score, and the score decreases as the degree of intelligence decreases. The scoring standard is: 9~10 points represent that the equipment has a high degree of intelligence, 6~8 points represent that the equipment has a high degree of intelligence, 3~5 points represent that the equipment has an insufficient degree of intelligence, and 1~2 points represent that the equipment has a low degree of intelligence or even no intelligence; the maintainability of the equipment is generally the opposite. The higher the maintenance frequency and the greater the maintenance difficulty, the corresponding score The lower the score, the more important it is. The scoring standard is: 9-10 points represent that the equipment maintenance frequency is very low and the maintenance difficulty is very small, 6-8 points represent that the equipment maintenance frequency is relatively low and the maintenance difficulty is relatively small, 3-5 points represent that the equipment maintenance frequency is relatively high and the maintenance difficulty is relatively large, 1-2 points represent that the equipment maintenance frequency is very high and the maintenance difficulty is very large; the factors affecting the performance of the equipment are scored according to their importance, with a full score of 9 points, among which 1-9 points represent different importance rankings, which will be converted according to the importance later, 9 points - absolutely important, 7 points - obviously important, 5 points - generally important, 3 points - slightly important, 1 point - not important.

[0059] The equipment demand is determined by the multivariate linear regression equation, and the demand constraints of general equipment and special equipment are used as the constraints of the model respectively: starting from the factors affecting the disaster situation of coal mine disasters, specific factors affecting the disaster situation and equipment demand are selected, namely, accident risk characteristic indicators and accident environment characteristic indicators. The accident environment characteristic indicator value is used as the quantitative value of the objective environmental impact caused by the accident, and the accident risk characteristic indicator value is used as the quantitative value of the change in accident risk level; among them, the accident risk characteristic indicator value and the accident environment characteristic indicator value are used as actual values, which can be flexibly replaced according to different accident types.

[0060] Aiming at the constraint of general equipment demand, the multivariate linear regression analysis theory is used to determine the minimum value of general equipment that should be equipped for accident rescue in each coal mine by establishing a linear relationship between the number of trapped people, the number of rescue teams, accident environment characteristic indicators and the demand for general equipment. Based on typical rescue cases of historical accidents in coal mine k, the accident environment characteristic indicator parameters and historical data of general equipment demand in coal mine k are collected and used as sample training data to construct a multivariate linear regression model, and the multivariate linear regression equation for predicting the number of general equipment is obtained, which can be expressed as: , In the formula, is the predicted demand for general emergency rescue equipment, a0 is the regression coefficient of general equipment, a1, a2, and a3 are the corresponding number of trapped people Number of rescue teams , Accident environment characteristic index value The least squares estimate of the regression coefficient reflects the linear influence of the corresponding independent variable on the dependent variable. Substituting the actual values ​​of the accident environment characteristic index parameters, the number of trapped people and the number of rescue teams of coal mine k into the multivariate linear regression equation for the prediction of the number of general equipment, the predicted demand for general equipment for emergency rescue in coal mine k can be obtained; on the basis of determining the demand for general equipment for emergency rescue in coal mine k, the specific mathematical expression of the demand constraint condition for the number of general equipment is as follows: , In the formula, The demand for general emergency rescue equipment in coal mines. is a general equipment decision variable of coal mine k. In view of the demand for special equipment, the multivariate linear regression analysis theory is used to determine the minimum value of special equipment that should be equipped for accident rescue in each coal mine by establishing a linear relationship between accident risk characteristic indicators and the demand for special equipment; based on typical rescue cases of historical accidents in coal mine k, the accident risk characteristic indicator parameters and historical data on the demand for special equipment in coal mine k are collected, and used as sample training data to construct a multivariate linear regression model, and the multivariate linear regression equation for predicting the number of special equipment is obtained, which can be expressed as: , In the formula, is the predicted demand for special emergency rescue equipment in coal mine k, b0 is the regression coefficient of special equipment, b1, b2, b3, b4, b5, and b6 are the least squares estimates of the regression coefficients of the corresponding accident risk characteristic index values, which reflect the linear influence of the corresponding independent variables on the dependent variables.

[0061] Substituting the actual values ​​of the accident risk characteristic index parameters of coal mine k into the multivariate linear regression equation for special equipment quantity prediction, the predicted demand for special emergency rescue equipment in coal mine k can be obtained; on the basis of determining the demand for special emergency rescue equipment in coal mine k, the specific mathematical expression of the special equipment quantity demand constraint condition is as follows: , In the formula, Forecast the demand for a special equipment for coal mine k, is the decision variable of a special equipment k in coal mine. The above decision variables, objective functions and constraints are introduced to establish a multi-objective optimization model for emergency equipment configuration.

[0062] Step S104 is to solve the target optimization model according to the constraint conditions and the genetic algorithm to obtain the emergency rescue equipment requirements of the target area.

[0063] According to a specific implementation method, based on the multi-objective functions and constraints of the model, an improved NSGA-II genetic algorithm is introduced to solve the objective function, thereby formulating an optimization plan for the equipment configuration of the mine rescue team.

[0064] Specifically, considering that this problem is an NP-hard problem and is suitable for using a heuristic algorithm to find a suboptimal solution to the problem, and the optimization model is a multi-objective optimization model, the NSGA-II genetic algorithm is selected for solving it; based on the NSGA-II genetic algorithm, the established multi-objective optimization model of emergency equipment configuration is solved, and the number of emergency equipment configurations of the mine rescue team is determined within the set constraints, thereby formulating an equipment configuration optimization plan for the mine rescue team.

[0065] The present invention effectively optimizes the equipment structure and quantity prediction configuration through the analysis of rescue process and equipment requirements, the construction of structural system, the establishment of quantity prediction model and the establishment of equipment configuration optimization model, and can obtain objective and effective prediction results, thus providing reliable guarantee for the standardized management of mine emergency rescue equipment and the rational allocation of resources.

[0066] Embodiment 2 Figure 2 is a schematic diagram of a flow chart of Embodiment 2 of the present invention, such as Figure 2As shown in the figure, the accident emergency rescue process information in the mining field is obtained, and the equipment requirements are analyzed in multiple dimensions based on the Hall 3D structure. Figure 3 As shown in the figure, based on the emergency rescue link of coal mine accidents, it is divided into three stages: response to abnormal dangerous situations of production site personnel, emergency disposal within the production enterprise, and accident rescue by professional rescue teams; the equipment system is divided into five dimensions according to rescue subject, mission stage, spatial dimension, equipment function, and accident type; based on the Hall three-dimensional structure, a multi-dimensional analysis of equipment requirements is conducted to obtain the rescue subject-mission stage-equipment function-equipment requirements under the task goal of emergency rescue of coal mine accidents. Figure 4 As shown in the figure, by analyzing the equipment requirements based on the rescue links, the equipment required by the production site, production enterprise and professional rescue team when carrying out emergency rescue work is obtained; according to the system architecture layout, a coal mine accident emergency rescue equipment requirement system architecture is generally formed, including the rescue subject layer, task stage layer, equipment function layer and equipment requirement layer.

[0067] Taking the decision-making quantity of emergency equipment for water seepage accidents as an example, the representative special equipment of mine rescue team i (water pump ) and general equipment (mine rescue vehicles , Combat uniform , Intercom , Life detector , oxygen respirator ) configuration is used as the research object for example application. It is known that the mine rescue team i is responsible for a total of 5 surrounding coal mines, that is, the specific mathematical expression of the decision variable is as follows: .

[0068] Water Pump , Mine rescue vehicle , Combat uniform , Intercom , Life detector , oxygen respirator The unit costs are RMB 40,000, RMB 490,000, RMB 50,000, RMB 50,000, RMB 87,000 and RMB 18,000 respectively.

[0069] like Figure 5As shown in the figure, considering that the mine rescue team is responsible for the rescue equipment needs of k coal mines in the surrounding area, the mine rescue team is used as the supply point of k coal mine rescue equipment, and a multi-objective optimization model is introduced to determine its decision variables; the maximum total equipment capability and the minimum total equipment cost are used as the objective function of the model; the development direction of the equipment "four modernizations and one quality" is used as the standard for judging the equipment capability, and its weight and score are calculated. For example, the performance of its own equipment is scored, and the full score is 10 points. The data assignment standard is determined by combining different secondary indicators; taking equipment intelligence as an example, the higher the degree of intelligence, the higher the score, and the score decreases as the degree of intelligence decreases. The scoring standard is: 9~10 points represent a high degree of equipment intelligence, 6~8 points represent a high degree of equipment intelligence, 3~5 points represent an insufficient degree of equipment intelligence, and 1~2 points represent a low degree of equipment intelligence or even no intelligence. The maintainability of equipment is generally the opposite. The higher the maintenance frequency and the greater the maintenance difficulty, the lower the corresponding score. The scoring standard is: 9~10 points represent that the equipment maintenance frequency is very low and the maintenance difficulty is very small, 6~8 points represent that the equipment maintenance frequency is low and the maintenance difficulty is not large, 3~5 points represent that the equipment maintenance frequency is high and the maintenance difficulty is large, and 1~2 points represent that the equipment maintenance frequency is very high and the maintenance difficulty is very large.

[0070] The factors that affect the performance of the equipment are scored for importance, with a full score of 9 points. 1-9 points represent different importance rankings, which will be converted based on the importance later. 9 points - absolutely important, 7 points - obviously important, 5 points - moderately important, 3 points - slightly important, and 1 point - not important. The performance evaluation of the equipment itself is shown in Table 4.

[0071] Table 4:

[0072] The importance ranking of factors affecting equipment performance is shown in Table 5.

[0073] Table 5:

[0074] Aiming at the constraint of the demand for general equipment, the multivariate linear regression analysis theory is used to determine the minimum value of general equipment that should be equipped for accident rescue in each coal mine by establishing a linear relationship among the characteristic indicators of the accident environment, the number of trapped people, the number of rescue teams and the demand for general equipment.

[0075] Set the general equipment under the flooding accident type to include mine rescue vehicles , Combat uniform , Intercom , Life detector , oxygen respirator , the accident environment characteristic indicators (i.e., water seepage), the number of trapped people, and the number of rescue teams that affect the demand for emergency equipment for water seepage accidents are selected as the independent variables of the multivariate linear regression model, and the demand for general equipment in coal mine k is the dependent variable. Taking coal mine 1, which is responsible for mine rescue team i, as an example, based on the typical rescue cases of historical water seepage accidents that occurred in coal mine 1, the historical data of various indicator parameters and general equipment demand are collected.

[0076] The standardized data is used as sample training data to construct a multivariate linear regression model, obtain the multivariate linear regression equation for general equipment demand prediction, and establish the general equipment demand constraint inequality:

[0077]

[0078]

[0079]

[0080]

[0081] In the formula, The number of trapped people, The number of rescue teams, is the water permeability (10,000 cubic meters). Similarly, we can get the constraint inequality of the general equipment demand for coal mines 2, 3, 4, and 5.

[0082] Set the special equipment under the flooding accident type to be a water pump , the accident risk characteristic indicators that affect the demand for emergency equipment for water seepage accidents (including mine hydrogeological conditions, maximum water inflow, normal water inflow, water richness of aquifer, aquifer thickness, and depth of mining fracture zone) are selected as independent variables of the multivariate linear regression model, and the demand for k water pumps in coal mines is the dependent variable.

[0083] Taking Coal Mine 1, which is under the charge of Mine Rescue Team i, as an example, based on typical rescue cases of historical water seepage accidents that occurred in Coal Mine 1, the historical data of various indicator parameters and water pump demand are collected and standardized.

[0084] The standardized data is used as sample training data to construct a multivariate linear regression model, and the multivariate linear regression equation for special equipment demand prediction is obtained:

[0085] In the formula, is the demand for water pumps in coal mine 1, units, d1 is the hydrogeological type of the mine, d2 is the maximum water inflow, m³ / h, d3 is the normal water inflow, m³ / h, d4 is the water richness of the aquifer, d5 is the thickness of the aquifer, m, and d6 is the depth of the mining fracture zone, m. Similarly, the predicted demand for special equipment water pumps in coal mines 2, 3, 4, and 5 can be obtained.

[0086] The above decision variables, objective functions and constraints are introduced to establish a multi-objective optimization model for emergency equipment configuration. According to the multi-objective function and constraints of the model, the improved NSGA-II genetic algorithm is introduced to solve the objective function, so as to formulate an optimization plan for the equipment configuration of the mine rescue team (such as Figure 6 The specific operations are as follows: Considering that this problem is an NP-hard problem, it is suitable to use a heuristic algorithm to solve the suboptimal solution of the problem. At the same time, the optimization model belongs to a multi-objective optimization model, so the NSGA-II genetic algorithm is selected for solution: the algorithm process includes chromosome encoding design and decoding examples, initial population generation, fitness function design, fast non-dominated sorting, crowding distance calculation, genetic operation, business strategy, and termination criteria. Based on the NSGA-II genetic algorithm, the multi-objective optimization model of emergency equipment configuration is solved, and the number of emergency equipment configurations of the mine rescue team is determined within the set constraints, so as to formulate an optimization plan for the equipment configuration of the mine rescue team.

[0087] MATLAB software was used for optimization and solution. The above data were input into the prepared solution code. The number of iterations was selected as 100, 300, 500, and 800 generations, the number of decision variables was 6, and the number of objective functions was 2 for simulation calculations. Finally, the optimal solution set for the number of emergency equipment based on the multi-objective optimization model was output.

[0088] like Figure 7 As shown in the figure, by analyzing the data exported by the software, it can be seen that the fitting effect is best when the number of iterations is 500. The value of the decision variable (coal mine emergency rescue equipment) output at this time can be seen. The trend of the change in the optimal configuration quantity can be seen. At this time, the optimal balance between cost and performance can be achieved under the premise of meeting the demand for coal mine rescue equipment. The data of the five surrounding coal mines that mine rescue team i is responsible for are brought into the model for solution, and their respective optimal configuration quantities can be obtained, as shown in Table 6.

[0089] Table 6:

[0090] Therefore, the mine rescue team i should be equipped with water pumps, mine ambulances, combat uniforms, walkie-talkies, life detectors, and oxygen respirators in the quantities of 9 units, 2 vehicles, 70 sets, 15 units, 2 units, and 10 units.

[0091] Embodiment 3 Figure 8 Schematic diagram of a method for predicting emergency rescue equipment demand of the present invention. Figure 8 As shown, the present invention also proposes a device 100 for predicting emergency rescue equipment needs, which includes: an acquisition module 200, used to obtain accident process information of a target area, and determine equipment needs based on the accident process information; a first processing module 300, used to construct an equipment demand architecture based on the equipment needs and the architecture layout; a second processing module 400, used to obtain constraints, and optimize the overall equipment performance and total equipment cost of the equipment demand architecture based on the constraints to obtain a multi-objective optimization model; a third processing module 500, used to solve the target optimization model based on the constraints and a genetic algorithm to obtain the emergency rescue equipment needs of the target area.

[0092] According to a specific implementation method, the equipment requirements are determined according to the accident process information, including: dividing the equipment system according to the five dimensions of rescue subject, task stage, spatial dimension, equipment function, and accident type based on the Hall three-dimensional structure model theory; obtaining the emergency rescue process information of accidents in the mining field, and further sorting and dividing it according to its use time, use location, user, use function and use scenario; obtaining the rescue subject requirements of the accident process information, obtaining the corresponding task stage requirements according to the rescue subject requirements, obtaining the corresponding equipment function requirements according to the task stage requirements, and obtaining the corresponding equipment requirement group according to the equipment function requirements. The acquisition of constraint conditions includes: determining the equipment requirement quantity of the equipment requirement using a multivariate linear regression equation; the equipment requirement quantity includes a general equipment quantity and a special equipment quantity; the general equipment quantity and the special equipment quantity are used as constraints for the equipment requirement system structure.

[0093] The optimizing the total equipment capacity and total equipment cost of the equipment requirement system structure according to the constraint conditions includes: maximizing the total equipment capacity of the equipment requirement system structure; minimizing the total equipment cost of the equipment requirement system structure; the total equipment capacity = equipment performance × corresponding equipment quantity; the total equipment cost = single equipment cost × corresponding equipment quantity; the maximization of the total equipment capacity includes: ; The minimization process of the total equipment cost includes: ; in, is the first objective function, is the performance of a certain equipment, i represents the i-th equipment type, i is equal to n at most, n is the number of decision variables, is the decision variable, is the second objective function, The cost of a certain equipment.

[0094] A method for predicting emergency rescue equipment demand of the present invention comprises: obtaining accident process information of a target area, determining equipment demand according to the accident process information; constructing an equipment demand architecture according to the equipment demand and architecture layout; obtaining constraint conditions, optimizing the overall equipment performance and total equipment cost of the equipment demand architecture according to the constraint conditions, and obtaining a multi-objective optimization model; solving the target optimization model according to the constraint conditions and a genetic algorithm, and obtaining the emergency rescue equipment demand of the target area. The method establishes a rescue team equipment configuration model based on a multi-objective optimization algorithm, realizes the optimal selection of schemes under the rescue team as the configuration subject structure, and is conducive to the rational allocation of emergency resources.

[0095] On the other hand, an embodiment of the present invention provides a storage medium having a program stored thereon, which implements the method for predicting the demand for emergency rescue equipment when executed by a processor.

[0096] An embodiment of the present invention provides a processor, which is used to run a program, wherein the method for predicting the demand for emergency rescue equipment is executed when the program is running.

[0097] The embodiment of the present invention provides a device, the device includes a processor, a memory, and a program stored in the memory and executable on the processor, and the processor implements the following steps when executing the program: obtaining accident process information of a target area, determining equipment requirements according to the accident process information; constructing an equipment requirement architecture according to the equipment requirements and the architecture layout; obtaining constraint conditions, optimizing the total equipment capacity and total equipment cost of the equipment requirement architecture according to the constraint conditions, and obtaining a multi-objective optimization model; solving the target optimization model according to the constraint conditions and a genetic algorithm, and obtaining the emergency rescue equipment requirements of the target area. The device in this article can be a server, a PC, a PAD, a mobile phone, etc.

[0098] The present application also provides a computer program product, which, when executed on a data processing device, is suitable for executing a program that initializes the following method steps: obtaining accident process information of a target area, and determining equipment requirements based on the accident process information; constructing an equipment requirement architecture based on the equipment requirements and the architecture layout; obtaining constraints, and optimizing the total equipment capacity and total equipment cost of the equipment requirement architecture based on the constraints to obtain a multi-objective optimization model; solving the target optimization model based on the constraints and a genetic algorithm to obtain the emergency rescue equipment requirements for the target area.

[0099] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0100] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0101] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0102] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0103] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0104] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0105] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0106] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0107] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A method for predicting demand for emergency rescue equipment, characterized in that: The method includes: Obtaining accident process information of the target area, and determining equipment requirements based on the accident process information; constructing an equipment requirement architecture according to the equipment requirement and the architecture layout; Obtaining constraint conditions, optimizing the overall performance and total cost of equipment of the equipment requirement system structure according to the constraint conditions, and obtaining a multi-objective optimization model; The target optimization model is solved according to the constraint conditions and the genetic algorithm to obtain the emergency rescue equipment requirements of the target area.

2. The method according to claim 1, characterized in that The accident process information includes: abnormal and dangerous situation response process information of production site personnel, internal emergency response process information of production enterprises, and accident rescue process information of professional rescue teams.

3. The method according to claim 1, characterized in that The determining of equipment requirements according to the accident process information includes: Based on Hall's three-dimensional structural model theory, the equipment system is divided into five dimensions: rescue subject, mission stage, spatial dimension, equipment function, and accident type; Obtain information on accident emergency rescue processes in the mining field, and further organize and divide them according to their use time, use location, use personnel, use functions and use scenarios; Obtain the rescue subject requirements of the accident process information, obtain the corresponding mission stage requirements based on the rescue subject requirements, obtain the corresponding equipment function requirements based on the mission stage requirements, and obtain the corresponding equipment requirement group based on the equipment function requirements.

4. The method according to claim 1, characterized in that: The equipment requirement system structure includes a rescue subject layer, a mission phase layer, an equipment function layer, and an equipment requirement layer.

5. The method according to claim 1, characterized in that The acquisition constraints include: Determining the equipment requirement of the equipment requirement using a multiple linear regression equation; The equipment demand includes general equipment demand and special equipment demand; The general equipment quantity and the special equipment requirement quantity serve as constraints of the equipment requirement system architecture.

6. The method according to claim 1, characterized in that The optimizing the total equipment capacity and the total equipment cost of the equipment requirement system structure according to the constraint conditions includes: Maximizing the total equipment capacity of the equipment requirement architecture; Minimizing the total equipment cost of the equipment requirement architecture; The total equipment capacity = equipment performance × corresponding equipment quantity; Total equipment cost = cost of a single piece of equipment × corresponding equipment quantity.

7. The method according to claim 6, characterized in that The maximization process of the total equipment capacity includes: ; The minimization process of the total equipment cost includes: ; in, is the first objective function, is the performance of a certain equipment, i represents the i-th equipment type, i is equal to n at most, n is the number of decision variables, is the decision variable, is the second objective function, The cost of a certain equipment.

8. A device for predicting the demand for emergency rescue equipment, characterized in that: The device includes: An acquisition module, used to acquire accident process information of a target area and determine equipment requirements according to the accident process information; A first processing module is used to construct an equipment requirement architecture according to the equipment requirement and the architecture layout; The second processing module is used to obtain constraint conditions, and optimize the total equipment capacity and total equipment cost of the equipment requirement system structure according to the constraint conditions to obtain a multi-objective optimization model; The third processing module is used to solve the target optimization model according to the constraint conditions and the genetic algorithm to obtain the emergency rescue equipment demand of the target area.

9. The device according to claim 8, characterized in that The determining of equipment requirements according to the accident process information includes: Based on Hall's three-dimensional structural model theory, the equipment system is divided into five dimensions: rescue subject, mission stage, spatial dimension, equipment function, and accident type; Obtain information on accident emergency rescue processes in the mining field, and further organize and divide them according to their use time, use location, use personnel, use functions and use scenarios; Obtain the rescue subject requirements of the accident process information, obtain the corresponding mission stage requirements based on the rescue subject requirements, obtain the corresponding equipment function requirements based on the mission stage requirements, and obtain the corresponding equipment requirement group based on the equipment function requirements.

10. The device according to claim 8, characterized in that The acquisition constraints include: Determining the equipment requirement of the equipment requirement using a multiple linear regression equation; The equipment demand includes general equipment demand and special equipment demand; The general equipment quantity and the special equipment requirement quantity serve as constraints of the equipment requirement system architecture.

Images