Subway station emergency material management method based on material configuration dynamic optimization model

Abstract

The invention relates to the technical field of subway station emergency management, and discloses a subway station emergency material management method based on a material configuration dynamic optimization model, which comprises the following steps of: constructing an emergency event static database through emergency event historical data, and establishing a corresponding relationship among emergency event types, emergency material types and emergency material quantity; generating a basic inventory; screening core predictive factors by combining principal component analysis and a neural network model, collecting real-time monitoring data of the core predictive factors, and constructing a dynamic database; establishing a material allocation dynamic optimization model, calculating a matching coefficient between a potential emergency event and a historical case, generating a total potential inventory, mapping the basic inventory and the total potential inventory item by item, selecting a maximum value, and generating a dynamic inventory; finally, an emergency material digital management warehouse is constructed, and full-life-cycle management of purchasing, warehousing, using, maintaining and scrapping is achieved. According to the invention, the scientificity and accuracy of emergency material allocation are improved, and the emergency response capability of the subway station is enhanced.

Description

Technical Field

[0001] The present invention relates to the technical field of subway station emergency management, and in particular, to a subway station emergency material management method based on a dynamic optimization model of material allocation. Background Art

[0002] As an important part of the urban transportation system, the subway can significantly improve the travel convenience of citizens, expand the travel radius, and enhance the operation efficiency of the city, and has become the main artery of urban transportation. As an underground closed transportation hub, once an emergency occurs in a subway station, it will lead to adverse consequences such as the paralysis of the subway operation order and the large-scale detention of passengers. A reasonable allocation of emergency materials can significantly improve the response efficiency to emergency incidents, ensure the smooth progress of rescue work, and at the same time minimize the losses and hazards brought by emergency incidents. Therefore, it is of great significance to manage the emergency materials of subway stations in a scientific and efficient manner to ensure the continuity of the subway system operation, guarantee the safety of people's lives and property, and maintain social stability.

[0003] However, with the increasing requirements for the emergency handling ability and response speed in the subway industry, and the more obvious trend of intelligent and digital transformation in the subway industry, the traditional subway station emergency material management method has become increasingly difficult to meet the actual needs and industry requirements: (1) The structural contradiction between static allocation and dynamic risks; The traditional subway station emergency material allocation is usually pre-planned according to general standards, which is difficult to adapt to the diversity, randomness, uncertainty and other characteristics of subway emergency incidents. This leads to a systematic mismatch between the static-mode emergency material allocation and the dynamically changing risks (such as bad weather, passenger flow fluctuations, equipment failures, etc.) during the operation process.

[0004] (2) The problem of supply-demand imbalance in emergency material allocation; The types, quantities, etc. of the emergency materials configured in subway stations are all executed according to the preset plan, without considering the differential allocation required by some stations due to differences in passenger flow density or the particularity of the surrounding environment (such as flood prone areas near water). This results in the long-term idleness and even invalidation of materials in low-risk stations, causing waste and losses, while high-risk stations may face problems such as material shortages due to sudden demands, leading to a reduction in rescue efficiency.

[0005] (3) The stubborn problem of information silos in traditional management methods; Due to the low digital level of the current emergency material management method in subway stations, a large amount of data records rely on paper ledgers manually registered. In case of sudden emergency events, the information transmission efficiency of paper documents is low, which is prone to cause delayed judgment or misjudgment. At the same time, data information such as material inventory, equipment system, and monitoring sensors is fragmented and not interconnected, resulting in low efficiency in the collection, sharing, and utilization of information related to material allocation, thus weakening the emergency response ability.

[0006] It can be seen that there are many unsolved problems in the current emergency management work of subway stations.

[0007] Therefore, there is an urgent need to design a subway station emergency material management method based on a dynamic optimization model of material allocation to digitally upgrade the traditional subway station emergency material management method. By comprehensively considering the historical data and real-time monitoring data of various sudden emergency events, and through data fusion to drive the dynamic optimization and precise adaptation of emergency resource allocation, it provides a solid guarantee for the safe operation of the subway system. Summary of the Invention

[0008] To solve the above technical problems, the present invention provides a subway station emergency material management method based on a dynamic optimization model of material allocation, which significantly improves the response efficiency of subway stations to emergency events. At the same time, it reduces redundant inventory through the extreme value selection algorithm and lowers the operation cost.

[0009] The present invention provides a subway station emergency material management method based on a dynamic optimization model of material allocation, including the following steps: Step S1, obtaining the historical data of emergency events of multiple subway stations in the same area and constructing a static database of emergency events; Step S2, according to the industry emergency material allocation standard, establishing the corresponding relationship between the types of emergency events, the types of emergency materials, and the quantity of emergency materials for subway stations of the same category, and generating the basic inventory; Step S3, based on the static database of emergency events, determining the set of prediction factors for various emergency events; Step S4, collecting the real-time monitoring data of the set of prediction factors and constructing a dynamic database of emergency events; Step S5, establishing a dynamic optimization model of material allocation, calculating the matching coefficient between potential emergency events and historical cases based on the real-time monitoring data of the dynamic database of emergency events, and generating the total potential inventory; Step S6, mapping the basic inventory and the total potential inventory item by item and selecting the maximum value to generate the dynamic inventory; Step S7, based on the static database of emergency events, the dynamic inventory, and the dynamic optimization model of material allocation, constructing a digital management warehouse for emergency materials to realize the full life cycle management of emergency materials.

[0010] Further, in the step S1, the historical data of subway station emergency events specifically includes: the category to which the subway station belongs, the type of emergency event, the occurrence time of the emergency event, the types and quantities of emergency supplies used, the triggering factors of the emergency event, the development and evolution process of the emergency event, the termination conditions of the emergency event, environmental correlation factors, and impact loss data.

[0011] Further, determining the prediction factor set for various types of emergency events based on the emergency event static database specifically includes: Step S31: For each type of emergency event, extract the event triggering elements, environmental correlation factors, and emergency response data of historical cases from the static database; Step S32: Conduct multi-dimensional spatio-temporal correlation analysis on the event triggering elements, environmental correlation factors, and emergency response data, and construct a correlation matrix including equipment status parameters, environmental monitoring time series data, and emergency response; Step S33: Use the principal component analysis method to calculate the importance of each candidate parameter, and screen the parameters whose importance exceeds the preset threshold as the core prediction factors; Step S34: Verify the prediction accuracy of the core prediction factors for the occurrence of emergency events through a neural network model, and form the final prediction factor set when the accuracy reaches the preset standard.

[0012] Further, the step S5 specifically includes: Step S51: Calculate the matching coefficient between potential emergency events and historical cases based on the real-time monitoring data of the emergency event dynamic database; Step S52: Execute a hierarchical response strategy according to the preset matching coefficient threshold range, including three modes: material configuration adjustment, early warning monitoring, and maintaining the original configuration; Step S53: Aggregate the potential inventory of each emergency event category according to the hierarchical response strategy to generate the total potential inventory.

[0013] Further, the step S52 specifically includes: When the matching coefficient is in the range of 60%-100%, adjust the configuration, including: adopting the material requirements of the corresponding historical case; when the matching coefficient is in the range of 40%-60%, conduct early warning monitoring, including: temporarily not adjusting, but marking it as an event that needs to be dynamically monitored; when the matching coefficient is lower than 40%, maintain the original configuration, including: keeping the basic inventory unchanged.

[0014] Further, the calculation method of the matching coefficient is: Step S511: Normalize the historical data of the prediction factors for various types of emergency events in the emergency event static database, map the prediction factor values to the [0,1] interval through the range normalization formula, and construct a standardized prediction factor matrix ; Step S512: For a certain type of emergency event in the same category of subway stations in the static emergency event database, calculate the convergence coefficient C of each prediction factor l , and the specific calculation formula is: ; Among them, C l represents the convergence coefficient of the l-th prediction factor; m represents that there are m historical cases of a certain type of emergency event in the same category of subway stations in the static emergency event database; k represents the k-th historical case; represents the value of the l-th prediction factor of the k-th historical case after standardization; Step S513: Calculate the weight of each prediction factor based on the convergence coefficient , and the specific calculation formula is: ; Among them, represents the weight of the -th prediction factor; l represents the l-th prediction factor; n represents the total number of prediction factors; Step S514: Based on the real-time monitoring data of the prediction factors of the same type of emergency events in the dynamic emergency event database, construct a one-dimensional matrix of the prediction factors of potential emergency events , and calculate its weighted Euclidean distance D k from each historical case. The specific formula is: ; Among them, D k represents the weighted Euclidean distance between the prediction factors of potential emergency events and the k-th historical case; represents the value of the l-th prediction factor of potential emergency events; represents the value of the l-th prediction factor of the k-th historical case; Step S515: Calculate the matching coefficient S through the weighted Euclidean distance. The specific calculation formula is: ; Among them, S represents the matching coefficient between potential emergency events and historical cases.

[0015] Furthermore, the calculation formula for range normalization processing is: ; Among them, represents the value of the l-th prediction factor of the k-th historical case after standardization; f ml represents the value of the l-th prediction factor of the m-th historical case; f kl represents the value of the l-th prediction factor of the k-th historical case, and min and max respectively take the minimum and maximum values of this prediction factor column.

[0016] Furthermore, the generation of the total potential inventory adopts an extreme value selection algorithm, specifically: performing a union operation on the material requirements of multiple categories of potential emergency events; retaining the maximum demand of the same type of materials in each event scenario.

[0017] Furthermore, in step S7, constructing a digital management warehouse includes: step S71, configuring emergency materials for actual subway stations according to the dynamic inventory; step S72, establishing an information ledger for the entire life cycle including procurement, warehousing, use, maintenance, and scrapping; step S73, real-time monitoring of emergency material data and triggering at least two of the inventory warning, overdue warning, and quality alarm mechanisms.

[0018] The embodiments of the present invention have the following technical effects: 1. By combining the characteristics of emergency events, matching and mapping the multivariate real-time monitoring data with the historical cases in the static databases of each emergency event, generating the dynamic inventory of materials, on the basis of ensuring sufficient reserves of emergency materials, quantifying the material requirements under different categories of sudden emergency events, realizing the transformation of material allocation from "fixed design" to "precision data-driven", and significantly optimizing the accuracy of emergency material allocation.

[0019] 2. By establishing a dynamic optimization model for material allocation, real-time collecting monitoring data information such as the status data of each station device, sensor data, passenger flow density data, meteorological data, seismic data, etc., according to the matching results with historical data, early warning of emergencies in advance, assisting in quickly adjusting the emergency material allocation, solving the problem of insufficient adaptation of the traditional preset mode of materials to dynamic risk scenarios, and comprehensively enhancing the ability of subway stations to respond to dynamic risks.

[0020] 3. Through the dynamic risk assessment of emergency events, over-allocation of materials is avoided, inventory redundancy is reduced; the full life cycle management of materials, through functions such as overdue warning, effectively reduces the expired loss rate of materials; the emergency response ability is enhanced, the losses caused by sudden emergency events are reduced, and the operation cost of subway stations is effectively reduced.

[0021] 4. By establishing a digital file for the entire life cycle of emergency materials, a complete material data chain is formed, eliminating the fragmentation problem of traditional paper records; cross-system multi-source data fusion analysis is carried out, multi-dimensional data correlation relationships are constructed, and the digital comprehensive upgrade of emergency material management from information fragmentation and isolated operation to data collaboration is realized. Description of the Drawings

[0022] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following will briefly introduce the drawings required for the description of the specific embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0023] Figure 1 It is a flowchart of a subway station emergency material management method based on a dynamic optimization model of material allocation provided by an embodiment of the present invention; Figure 2 It is a schematic diagram of the modules of a subway station emergency material management system based on a dynamic optimization model of material allocation provided by an embodiment of the present invention. Specific Embodiments

[0024] To make the objectives, technical solutions and advantages of the present invention clearer, the following will clearly and completely describe the technical solutions of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of them. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope protected by the present invention.

[0025] Figure 1 It is a flowchart of a subway station emergency material management method based on a dynamic optimization model of material allocation provided by an embodiment of the present invention. Refer to Figure 1 , specifically including: Step S1: Obtain the historical data of emergency events of multiple subway stations in the same area and construct a static database of emergency events.

[0026] In some embodiments, in step S1, the historical data of subway station emergency events specifically includes: the category to which the subway station belongs, the type of emergency event, the occurrence time of the emergency event, the types and quantities of emergency materials used, the triggering factors of the emergency event, the development and evolution process of the emergency event, the termination conditions of the emergency event, environmental correlation factors, and impact loss data.

[0027] Exemplarily, historical data of emergency incidents at subway stations can be collected from channels such as internal records of subway operation companies, duty logs and surveillance videos at each station, historical records of emergency response platforms or dispatching centers, statistical data released by government and industry regulatory agencies, and other relevant sources (such as passenger complaints, news reports, etc.). For each emergency incident, the following detailed information needs to be collected: the category of the subway station, such as underground station, ground station, elevated station, etc.; the type of the emergency incident, such as fire, flood, earthquake, equipment failure, etc.; the occurrence time, a time stamp accurate to the minute level; the types and quantities of emergency supplies used, including but not limited to fire extinguishers, first aid kits, sandbags, etc.; the triggering factors of the emergency incident, such as electrical failures, natural disasters, vandalism, etc.; the development and evolution process, a detailed description of how the incident developed from the beginning to the end; the termination conditions, the criteria for the incident to be confirmed as resolved; environmental and related factors, factors such as weather conditions and surrounding environmental characteristics that may affect the development of the incident; impacts and losses, including casualties, economic losses, duration of operation interruption, etc.

[0028] Standardize the collected data to ensure the consistency and accuracy of the data. For missing or incomplete information, it can be filled through supplementary investigations or by using reasonable estimation methods. At the same time, enter this information into a structured database to form a preliminary static database of emergency incidents.

[0029] Step S2, according to the industry emergency supply allocation standard, for subway stations of the same category, establish the corresponding relationship among the types of emergency incidents, the types of emergency supplies, and the quantities of emergency supplies to generate the basic inventory.

[0030] Specifically, the industry emergency supply allocation standard includes, but is not limited to, the industry standard JT / T 1409-2022 "Basic Requirements for the Construction of Urban Rail Transit Operation Emergency Capability", etc. Taking this specification as an example, the established basic inventory , where i, j ≥ 1; for subway stations of the same category, the specific categories include underground stations, ground stations, elevated stations, etc., and the basic inventory R B in which t B,i is the set of types of emergency incidents, v B,j is the set of types of emergency supplies, and q B,ij is the quantity of the jth type of emergency supply under the ith type of emergency incident. The partial basic inventory is as follows: .

[0031] Step S3, based on the static database of emergency incidents, determine the set of prediction factors for various types of emergency incidents.

[0032] In some embodiments, based on the emergency event static database, a set of prediction factors for various types of emergency events is determined, specifically including: Step S31, for each type of emergency event, extract the event trigger elements, environmental correlation factors, and emergency response data of historical cases from the static database; Step S32, perform multi-dimensional spatio-temporal correlation analysis on the event trigger elements, environmental correlation factors, and emergency response data to construct a correlation matrix including equipment status parameters, environmental monitoring time series data, and emergency response; Step S33, use the principal component analysis method to calculate the importance of each candidate parameter, and select the parameters whose importance exceeds the preset threshold as the core prediction factors; Step S34, verify the prediction accuracy of the core prediction factors for the occurrence of emergency events through a neural network model, and form a final set of prediction factors when the accuracy reaches the preset standard.

[0033] Specifically, for each type of emergency event, from the static database: event trigger elements, such as electrical failures, natural disasters, etc.; environmental correlation factors, such as weather conditions, surrounding environmental characteristics, etc.; emergency response data, including which emergency supplies were used and their quantities, and what emergency measures were taken, etc. These data will be used as the basic materials for constructing prediction factors. Analyze the extracted data. The specific steps are as follows: equipment status parameters, collect the status parameters of the internal facilities of the subway station related to the event, such as the load situation of the power system, the working efficiency of the drainage pump, etc.; environmental monitoring time series data, obtain and organize the environmental monitoring data provided by local meteorological departments, seismic monitoring departments, etc., such as rainfall, wind speed, temperature changes, etc.; emergency response, record and analyze the time series data of various response measures taken after the occurrence of the emergency event. Then, construct a correlation matrix, which aims to reflect the interaction relationship between different parameters in the time and space dimensions.

[0034] Use principal component analysis (PCA) to evaluate the importance of each candidate parameter and select the most representative parameters as the core prediction factors. First, standardize the data of all candidate parameters so that their mean is 0 and variance is 1 to eliminate the influence of different scales. Then, transform the original data into a new coordinate system, where each new coordinate axis corresponds to a principal component. Calculate the variance proportion explained by each principal component, and retain those principal components whose cumulative explained variance proportion reaches the preset threshold (such as 80%). According to the retained principal components, reverse map back to the original variable space to identify the original variables with higher contribution degrees as the core prediction factors.

[0035] Build or select a suitable neural network model and train it with existing historical data. Input the selected core prediction factors into the model, run the model, and analyze the output results. Determine the effectiveness of these factors based on the prediction accuracy of the model. Usually, a preset standard (e.g., an accuracy rate of over 80%) can be set. When this standard is met, confirm these factors as the final set of prediction factors.

[0036] Exemplarily, assume that the type of emergency being processed is a flood disaster at a subway station. Extract historical cases of all flood disasters in the past few years from the static database, including triggering factors (such as heavy rain), environmental correlation factors (such as the height of surface water accumulation), and emergency response data (such as the number of sandbags). Conduct multi-dimensional spatio-temporal correlation analysis on these data, considering factors such as the working status of the internal drainage system of the subway station and the external real-time rainfall. Use principal component analysis (PCA) to calculate the weights of each factor and select the most important ones as core prediction factors. Finally, test the effectiveness of these prediction factors through the trained neural network model to ensure that it can accurately predict future possible flood disasters.

[0037] Based on the historical data of emergency incidents in the static database, summarize the occurrence rules, influencing factors, and changing trends of emergency incidents according to the different characteristics of various emergency incidents, so as to determine the set of prediction factors for various emergency incidents. the set of prediction factors Some fragments are as follows.

[0038]

[0039] Step S4, collect the real-time monitoring data of the set of prediction factors and build a dynamic database of emergency incidents.

[0040] In this embodiment, the real-time monitoring data of each prediction factor comes from local meteorological departments, local earthquake monitoring departments, local water conservancy departments, in-station water level gauges, in-station cameras, various sensors in the station, and various equipment control systems in the station.

[0041] Step S5, establish a dynamic optimization model for material allocation. Based on the real-time monitoring data of the dynamic database of emergency incidents, calculate the matching coefficient between potential emergency incidents and historical cases, and generate the total potential inventory.

[0042] In some embodiments, step S5 specifically includes: Step S51, calculate the matching coefficient between potential emergency incidents and historical cases based on the real-time monitoring data of the dynamic database of emergency incidents; Furthermore, the calculation method of the matching coefficient is: Step S511: Normalize the historical data of the prediction factors for various emergency events in the static emergency event database. Map the prediction factor values to the interval [0, 1] through the range normalization formula, and construct a normalized prediction factor matrix ; In this embodiment, the calculation formula for the range normalization process is: ; where represents the value of the l-th prediction factor of the k-th historical case after normalization; f ml represents the value of the l-th prediction factor of the m-th historical case; f kl represents the value of the l-th prediction factor of the k-th historical case, and min and max respectively take the minimum and maximum values of this prediction factor column.

[0043] Step S512: For a certain type of emergency event in the same category of subway stations in the static emergency event database, calculate the convergence coefficient C l of each prediction factor. The specific calculation formula is: ; where C l represents the convergence coefficient of the l-th prediction factor; m represents that there are m historical cases of a certain type of emergency event in the same category of subway stations in the static emergency event database; k represents the k-th historical case; represents the value of the l-th prediction factor of the k-th historical case after normalization; Step S513: Calculate the weights of each prediction factor based on the convergence coefficient . The specific calculation formula is: ; where represents the weight of the -th prediction factor; l represents the l-th prediction factor; n represents the total number of prediction factors; Step S514: Based on the real-time monitoring data of the prediction factors of the same type of emergency events in the dynamic emergency event database, construct a one-dimensional matrix of the prediction factors of potential emergency events , and calculate its weighted Euclidean distance D k from each historical case. The specific formula is: ; where D k represents the weighted Euclidean distance between the prediction factors of potential emergency events and the k-th historical case; represents the value of the l-th prediction factor of potential emergency events; represents the value of the l-th prediction factor of the k-th historical case; Step S515, calculate the matching coefficient S through the weighted Euclidean distance, and the specific calculation formula is: ; where S represents the matching coefficient between the potential emergency event and the historical case. Step S52, execute the hierarchical response strategy according to the preset matching coefficient threshold interval, including three modes: material configuration adjustment, early warning monitoring, and maintaining the original configuration; Optionally, step S52 specifically includes: When the matching coefficient is in the range of 60%-100%, adjust the configuration, including: adopting the material requirements of the corresponding historical case; when the matching coefficient is in the range of 40%-60%, conduct early warning monitoring, including: do not adjust temporarily, but mark it as an event that needs to be dynamically monitored; when the matching coefficient is lower than 40%, maintain the original configuration, including: keeping the basic inventory unchanged. Step S53, aggregate the potential inventory of each emergency event category according to the hierarchical response strategy to generate the total potential inventory.

[0044] In some embodiments, the generation of the total potential inventory adopts the extreme value selection algorithm, specifically: perform a union operation on the material requirements of multiple categories of potential emergency events; retain the maximum demand of the same type of material in each event scenario.

[0045] Exemplarily, taking the flood control emergency event of the underground station as an example, the calculation process of the matching coefficient is as follows: For the flood control emergency event of the underground station, there are = 5 prediction factors, namely {maximum rainfall per hour, 24-hour rainfall, water depth of the entrance and exit, water depth inside the station, drainage pump load rate}, and there are = 10 historical cases in the static database. According to the historical data, construct the prediction factor matrix , then ; Map the prediction factor values to the [0,1] interval through the range normalization formula to construct the normalized prediction factor matrix ; ; Judge the data volatility of each normalized prediction factor, and calculate the convergence coefficient C of the l -th normalized prediction factor, ; Calculate the weight of the -th normalized prediction factor, ; Obtain , , , , .

[0046] Construct a one-dimensional matrix of the predictive factors of potential emergency events based on the real-time monitoring data of the predictive factors of similar emergency events (underground station flood control emergency events) in the emergency event dynamic database , calculate its weighted Euclidean distance D from each historical case k ; ; Obtain D1 = 9.29, D2 = 3.03, D3 = 4.17, D4 = 0.57, D5 = 13.35, D6 = 17.01, D7 = 4.76, D8 = 2.08, D9 = 27.53, D 10 = 33.30.

[0047] Calculate the matching coefficient through the weighted Euclidean distance, and obtain S1 = 9.72%, S2 = 24.84%, S3 = 19.32%, S4 = 63.72%, S5 = 6.97%, S6 = 5.55%, S7 = 17.36%, S8 = 32.48%, S9 = 3.50%, S 10 = 2.92%.

[0048] For the underground station flood control emergency event, the matching coefficient The largest value is for the 4th case, 60% < = 63.72% < 100%, then use the material demand situation of the 4th case as the potential inventory of the underground station flood control emergency event of this station.

[0049] Calculate the potential inventory of various types of emergency events in turn , and generate the total potential inventory , and some fragments are shown as follows: .

[0050] Step S6, map the base inventory and the total potential inventory item by item and select the maximum value to generate the dynamic inventory.

[0051] Specifically, if the total potential inventory has been generated, map each item of the base inventory and the total potential inventory one by one, and perform element-wise maximum value selection. Take the obtained result as the dynamic inventory , and some fragments of the dynamic inventory are shown as follows: .

[0052] Step S7: Based on the static emergency event database, the dynamic emergency event database, and the dynamic optimization model for material allocation, construct a digital management warehouse for emergency supplies to achieve the full-life cycle management of emergency supplies.

[0053] In some embodiments, in step S7, constructing the digital management warehouse includes: step S71, configuring the emergency supplies for the actual subway station according to the dynamic inventory; that is, according to the dynamic inventory , determine the types and quantities of emergency supplies, and promptly make corresponding allocations in the actual subway station.

[0054] Step S72, establish an information ledger for the full-life cycle including the links of procurement, warehousing, use, maintenance, and scrapping; Specifically, dynamically track each link of emergency supplies from procurement, warehousing, use, inventory taking, maintenance until scrapping, and record the information ledger of the full-life cycle of emergency supplies in the background database. The ledger mainly includes, but is not limited to, information such as the type, specification model, quantity, functional use, quality, space-based distribution, service life, and previous usage conditions of emergency supplies.

[0055] Step S73, monitor the emergency supply data in real time and trigger at least two of the warning mechanisms of inventory warning, overdue warning, and quality alarm.

[0056] Monitor the emergency supply data in real time, conduct multi-dimensional statistics and intelligent analysis at the same time, and automatically give warnings and alarms, including inventory warning, overdue warning, maintenance due warning, environmental quality alarm, etc.

[0057] Through the construction of a static emergency event database and a dynamic database, combined with predictive factor analysis, matching coefficient calculation, and hierarchical response strategies, the present invention realizes the accurate mapping of emergency supply requirements and historical cases, the transformation of emergency supply allocation from "static setting" to "dynamic adjustment", and generates a dynamic inventory covering multiple event scenarios by combining the extreme value selection algorithm. Based on the intelligent matching of real-time monitoring data and historical cases, it reduces the material allocation error, breaks through the traditional static allocation mode, and improves the scientificity and accuracy of emergency supply allocation; through the hierarchical warning mechanism and full-process data drive, it improves the response speed and risk coverage rate of emergencies; by using the redundancy elimination algorithm and full-life cycle digital management, it effectively avoids the problems of material redundancy or shortage; and also realizes the full-life cycle management of emergency supplies through the digital management warehouse, enhances the response ability of subway stations to emergencies and the resource utilization efficiency, and has significant safety benefits and management value.

[0058] The embodiment of the present invention also provides a subway station emergency supply management system based on the dynamic optimization model for material allocation. See Figure 2 , including the following modules: A static database construction module, which is used to obtain the historical data of emergency events of multiple subway stations in the same area and construct a static database of emergency events; A basic inventory generation module, which is used to establish the corresponding relationship among emergency event types, emergency material types and emergency material quantities for subway stations of the same category according to the industry emergency material allocation standard, and generate the basic inventory; A prediction factor set construction module, which is used to determine the prediction factor set of various emergency events based on the static database of emergency events; A dynamic database construction module, which is used to collect the real-time monitoring data of the prediction factor set and construct a dynamic database of emergency events; A dynamic optimization model establishment module for material allocation, which is used to establish a dynamic optimization model for material allocation, calculate the matching coefficient between potential emergency events and historical cases based on the real-time monitoring data of the dynamic database of emergency events, and generate the total potential inventory; A dynamic inventory generation module, which is used to map the basic inventory and the total potential inventory item by item and select the maximum value to generate the dynamic inventory; An emergency material digital management warehouse construction module, which is used to construct an emergency material digital management warehouse based on the static database of emergency events, the dynamic database of emergency events and the dynamic optimization model for material allocation, and realize the full life cycle management of emergency materials.

[0059] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements on some or all of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the technical solutions of the embodiments of the present invention.

Claims

1. A subway station emergency material management method based on a dynamic optimization model for material allocation, characterized in that It includes the following steps: Step S1: Obtain the historical data of emergency events of multiple subway stations in the same area, and construct a static database of emergency events; Step S2: According to the industry emergency material allocation standard, for subway stations of the same category, establish the corresponding relationship among the types of emergency events, the types of emergency materials, and the quantity of emergency materials, and generate the basic inventory; Step S3: Based on the static database of emergency events, determine the set of prediction factors for various emergency events; Step S4: Collect the real-time monitoring data of the set of prediction factors, and construct a dynamic database of emergency events; Step S5: Establish a dynamic optimization model for material allocation. Based on the real-time monitoring data of the dynamic database of emergency events, calculate the matching coefficient between potential emergency events and historical cases, and generate the total potential inventory; Step S6: Map the basic inventory and the total potential inventory item by item and select the maximum value to generate the dynamic inventory; Step S7: Based on the static database of emergency events, the dynamic inventory, and the dynamic optimization model for material allocation, construct a digital management warehouse for emergency materials.

2. The subway station emergency material management method based on the dynamic optimization model of material allocation according to claim 1, wherein In the step S1, the historical data of subway station emergency events specifically includes: the category to which the subway station belongs, the type of emergency event, the occurrence time of the emergency event, the types and quantities of emergency materials used, the triggering factors of the emergency event, the development and evolution process of the emergency event, the termination conditions of the emergency event, environmental correlation factors, and impact loss data.

3. The subway station emergency material management method based on the dynamic optimization model of material allocation according to claim 1, characterized in that, Based on the static database of emergency events, determining the set of prediction factors for various emergency events specifically includes: Step S31: For each type of emergency event, extract the event triggering elements, environmental correlation factors, and emergency response data of historical cases from the static database; Step S32: Conduct multi-dimensional spatio-temporal correlation analysis on the event triggering elements, environmental correlation factors, and emergency response data, and construct a correlation matrix including equipment status parameters, environmental monitoring time series data, and emergency response; Step S33: Use the principal component analysis method to calculate the importance of each candidate parameter, and screen the parameters with importance exceeding the preset threshold as the core prediction factors; Step S34: Verify the prediction accuracy of the core prediction factors for the occurrence of emergency events through a neural network model, and form the final set of prediction factors when the accuracy reaches the preset standard.

4. The subway station emergency material management method based on the dynamic optimization model of material allocation according to claim 1, characterized in that, The step S5 specifically includes: Step S51: Based on the real-time monitoring data of the dynamic database of emergency events, calculate the matching coefficient between potential emergency events and historical cases; Step S52: Execute a hierarchical response strategy according to the preset matching coefficient threshold interval, including three modes: material allocation adjustment, early warning monitoring, and maintaining the original configuration; Step S53: According to the hierarchical response strategy, aggregate the potential inventories of each emergency event category to generate the total potential inventory.

5. The subway station emergency material management method based on the dynamic optimization model of material allocation according to claim 4, characterized in that, The step S52 specifically includes: When the matching coefficient is in the range of 60% - 100%, adjust the configuration, including: adopting the material requirements of the corresponding historical cases; when the matching coefficient is in the range of 40% - 60%, conduct early warning monitoring, including: not adjusting temporarily, but marking the events that need to be dynamically monitored; when the matching coefficient is below 40%, maintain the original configuration, including: keeping the basic inventory unchanged.

6. The subway station emergency material management method based on the dynamic optimization model of material allocation according to claim 4, characterized in that, The calculation method of the matching coefficient is as follows: Step S511, perform normalization processing on the historical data of prediction factors for various emergency events in the emergency event static database, map the prediction factor values to the interval [0, 1] through the range normalization formula, and construct a standardized prediction factor matrix ; Step S512: For a certain type of emergency event in subway stations of the same category in the emergency event static database, calculate the convergence coefficient of each prediction factor C l , and the specific calculation formula is as follows: ； Among them, C l represents the convergence coefficient of the l th predictor; m represents that there are m historical cases of a certain type of emergency event in the same category of subway stations in the static database of emergency events; k represents the kth historical case; represents the value of the lth predictor of the kth historical case after standardization; Step S513, calculate the weights of each prediction factor based on the convergence coefficient , and the specific calculation formula is as follows: ； Among them, represents the weight of the th predictor; l represents the lth predictor; n represents the total number of predictors. Step S514, construct a one-dimensional matrix of the predictive factors of potential emergency events based on the real-time monitoring data of the predictive factors of similar emergency events in the emergency event dynamic database , and calculate its weighted Euclidean distance D from each historical case k , and the specific formula is: ； Among them, D k represents the weighted Euclidean distance between the predictors of potential emergency events and the k-th historical case; represents the l-th predictor value of the potential emergency event; represents the l-th predictor value of the k-th historical case; Step S515, calculate the matching coefficient S through the weighted Euclidean distance, and the specific calculation formula is: ； Among them, S represents the matching coefficient between the potential emergency event and the historical case.

7. The subway station emergency material management method based on the dynamic optimization model of material allocation according to claim 6, characterized in that, The calculation formula for the range standardization process is: ； Among them, represents the l-th predictor value of the k-th historical case after standardization; f ml represents the l-th predictor value of the m-th historical case; f kl represents the l-th predictor value of the k-th historical case, where min and max are respectively the minimum and maximum values of the predictor column.

8. The subway station emergency material management method based on the dynamic optimization model of material allocation according to claim 4, characterized in that The generation of the total potential inventory adopts the extreme value selection algorithm, specifically: perform a union operation on the material requirements of multiple categories of potential emergency events; retain the maximum demand of the same type of material in each event scenario.

9. The subway station emergency material management method based on the dynamic optimization model of material allocation according to claim 1, characterized in that, In step S7, constructing a digital management warehouse includes: step S71, configuring the emergency materials of the actual subway station according to the dynamic inventory; step S72, establishing a full - life - cycle information ledger including procurement, warehousing, use, maintenance, and scrapping links; step S73, real - time monitoring of emergency material data and triggering at least two of the warning mechanisms of inventory warning, overdue warning, and quality alarm.

Images