Auxiliary decision-making method for urban subway waterlogging risk management based on Bayesian network
Through the method of combining Bayesian network and multi-algorithm, a subway flooding risk assessment model is constructed, which solves the problem of insufficient comprehensive consideration of factors in the traditional method, and improves the accuracy and efficiency of subway flooding risk prediction and decision-making.
Patent Information
- Application Number
- CN202410476717.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-04-19
- Publication Date
- 2024-12-06
- Estimated Expiration
- 2044-04-19
AI Technical Summary
Traditional subway flooding risk prediction methods rely on historical data and expert experience, and the accuracy is limited by data integrity and expert subjective judgment, and lack the ability to comprehensively consider multiple factors.
Using Bayesian network-based method, a risk assessment model is constructed by acquiring and preprocessing subway flooding data, combining water flow prediction and drainage assessment, a flood risk treatment auxiliary decision-making model is constructed, and autoregressive algorithm, long-term and short-term neural network and fuzzy evaluation is used. The algorithm performs risk assessment and decision optimization.
It improves the accuracy and decision-making support for subway flooding risk prediction, realizes scientific and effective treatment of subway flooding risks, and improves the accuracy and efficiency of operation and management.
Smart Images

Figure CN118428528B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of decision-making, and in particular to an auxiliary decision-making method for urban subway waterlogging risk management based on a Bayesian network. Background Art
[0002] Traditional subway flooding risk prediction methods mainly rely on historical data and expert experience. The accuracy of this method is limited by the integrity of the data and the subjective judgment of experts. In recent years, with the rapid development of big data and artificial intelligence technology, new solutions have been provided for the prediction of subway flooding risks. Among them, Bayesian networks, as a powerful uncertainty reasoning tool, can comprehensively consider the influence of multiple factors and express the relationship between factors in a probabilistic way. Therefore, they have broad application prospects in the field of risk prediction.
[0003] Based on the above background, the present invention proposes an auxiliary decision-making method for urban subway waterlogging risk management based on Bayesian network. The method can comprehensively consider factors such as meteorology, geology, and drainage system, and realize accurate prediction and timely management of subway waterlogging risk by constructing a Bayesian network model. The method not only improves the accuracy of prediction, but also provides scientific and effective decision-making support for subway operation management departments. Summary of the invention
[0004] The purpose of the present invention is to provide an auxiliary decision-making method for urban subway waterlogging risk management based on Bayesian network.
[0005] To achieve the above object, the present invention is implemented according to the following technical solutions:
[0006] The present invention comprises the following steps:
[0007] Acquire waterlogging data and basic data of subways in target cities, and pre-process the waterlogging data; the waterlogging data includes historical waterlogging data, meteorological data, and monitoring data;
[0008] The first evaluation data and the second evaluation data are obtained by preprocessing the waterlogging data; the first evaluation data represents the water flow prediction value of the target city subway; the second evaluation data represents the available drainage capacity of the target city subway; the water flow prediction value is the water flow prediction value based on the monitoring data and the meteorological data; the drainage capacity is the available drainage volume based on the basic data and the monitoring data;
[0009] Performing risk assessment on the first assessment data and the second assessment data using a risk level to obtain a risk value, and adjusting the risk value according to the monitoring data to obtain a risk degree;
[0010] A waterlogging risk management auxiliary decision-making model is constructed according to the risk level to optimize the waterlogging risk management auxiliary decision-making.
[0011] Furthermore, the method for predicting water flow based on the monitoring data and the meteorological data includes inputting the monitoring data and the meteorological data into a water flow prediction model to obtain the predicted amount of water flow entering the subway; the water flow prediction model is constructed using an autoregressive algorithm and a long-short term neural network algorithm.
[0012] Furthermore, the method for determining the available drainage volume based on the basic data and the monitoring data includes:
[0013] The drainage setting of the basic data is used as a reference standard to obtain the difference between the initial water volume of the drainage channel and the water volume at the end of the drainage channel in the monitoring data;
[0014] When the initial water volume of the drainage channel in the monitoring data is greater than or equal to the reference standard, if the difference is less than 10%, the channel reference standard is used as the drainage volume of the current drainage pipe, otherwise the water volume at the end of the drainage channel is used as the drainage volume of the current drainage pipe;
[0015] When the initial water volume in the drainage channel in the monitoring data is less than the reference standard, if the difference is lower than 13.1%, the channel reference standard will be used as the drainage volume of the current drainage pipe. If the difference is between 13.1% and 100%, the channel reference standard minus the difference will be used as the drainage volume of the current drainage pipe. If the difference is 100%, the drainage volume of the current drainage pipe is 0.
[0016] Furthermore, the method of performing risk assessment on the first assessment data and the second assessment data using risk levels includes:
[0017] The subway is attacked by waterlogging in three stages: early warning preparation, initial waterlogging, and severe waterlogging. An attack state matrix is constructed based on the risk factors of subway waterlogging. The risk factors are used as nodes to calculate the risk value:
[0018]
[0019] The danger level of node w is a w , the attack result of node w is The attack phase of node w is c w , the attack state of node w is d w , the number and severity of danger, attack results, attack stages and attack states are The weights are ψ1, ψ2, ψ3, and ψ4;
[0020] According to the risk factor, the direction of the result is added and the weight of the node directed edge is calculated:
[0021]
[0022] The total number of attack states is N * , the maximum danger level of node w in the attack state i is a iw,max , the risk value of node w attacking state i is The probability that node y is in attack state i after node w attacks is The danger level of attacking node w in state i is a wi , the attack constant is z, and the expected risk of node w attacking node y is
[0023] Construct a directed weighted network based on directed risk factors and calculate the average value of the path capture nodes:
[0024]
[0025] The number of other nodes captured from node w is The path to capture other nodes from node w is The average probability of attacking other nodes from node w is Starting from node w The probability of the path that may endanger other nodes being attacked is Q wl ;
[0026] Calculate the average probability of being compromised:
[0027]
[0028] The node w is passed through The probability of a path being attacked is The number of possible paths for node w to be captured is The average probability of node i being attacked is
[0029] Construct a weighted directed graph based on the directed weighted network and calculate the importance index of the node:
[0030]
[0031] The importance index of node w is ε w , the first balance factor is θ1, the second balance factor is θ2, the natural constant is e, and the weight of the node w sending outward connections is S ot (w), the weight of node w receiving the connection is S in (w), the attack coefficient is υ;
[0032] Calculate the weighted risk expectation of the node:
[0033]
[0034] The weighted risk expectation of node w is The probability that node w is in attack state i is The weighting factor is λ, and the risk value of the node is calculated as:
[0035]
[0036] The first balance coefficient is The second balance coefficient is The risk value of node w is
[0037] Furthermore, the method of adjusting the risk value according to the monitoring data to obtain the risk level includes:
[0038] Calculate the risk importance of monitoring data:
[0039]
[0040] The risk importance of the jth monitoring data is The number of the jth monitoring data is k, and the contribution of the jth monitoring data is The risk tolerance of the jth monitoring data is The damage degree of the previous rainfall risk of the jth monitoring data is The intensity factor of the jth monitoring data is χ j ;
[0041] The monitoring data with risk importance greater than 0.362 are integrated into risk data, and the risk level is calculated based on the risk data:
[0042]
[0043] The risk level of the cth rainfall condition is U c , the j-th risk data value of the c-th rainfall condition is f cj , the standard value of the j-th risk data is The risk importance of the jth risk data of the cth rainfall condition is The optimization factor for the cth rainfall condition is ζ c , the number of risk data for the cth rainfall condition j is k, and the risk value of the cth rainfall condition
[0044] Furthermore, a method for constructing a waterlogging risk management auxiliary decision-making model according to the risk level includes:
[0045] Taking the risk level as the decision criterion of the auxiliary decision-making model for waterlogging risk management:
[0046] When the risk level is less than 0.29, the risk level is level 1; when the risk level is greater than 0.29 and less than 0.53, the risk level is level 2; when the risk level is greater than 0.53 and less than 0.71, the risk level is level 3; when the risk level is greater than 0.71 and less than 0.89, the risk level is level 4; when the risk level is greater than 0.89 and less than 1, the risk level is special level;
[0047] The auxiliary decision-making model for waterlogging risk management includes association rule mining algorithm, Bayesian network algorithm, long short-term memory network algorithm, and fuzzy evaluation algorithm;
[0048] The association rule mining algorithm selects important data based on the degree of association of waterlogging data;
[0049] The Bayesian network algorithm establishes the basic structure of the Bayesian network based on important data; takes risk factors as nodes of the Bayesian network; assigns probability to the state of each node; sets general risk factor nodes, decision nodes and utility nodes to obtain the first risk level;
[0050] The short-term memory network algorithm makes predictions based on the time characteristics of important data to obtain the second risk level;
[0051] The fuzzy evaluation algorithm fuses the first risk degree and the second risk degree to obtain the risk degree.
[0052] Furthermore, the method for optimizing the auxiliary decision-making for waterlogging risk management includes:
[0053] Randomly generate multiple searchers and calculate their positions:
[0054]
[0055] The update position of the a-th searcher in the s-th dimension is The position of the a-th searcher in the s-th dimension is The random number is r, the sign function is sign(·), and the objective function value of the a-th searcher is The position of the p-th searcher in the s-th dimension is The p-th search sub-objective function value is
[0056] Calculate the updated position and mutation individuals of the searcher:
[0057]
[0058]
[0059] The updated objective function value of the a-th searcher is The position of the searcher after the first phase update is The random numbers are r1, r2, r3, r4, r5, the random number function is rd(·), and the random individuals of the t-th iteration population are The mutant individual of the a-th searcher in the t-th iteration population is
[0060] Compute the search subposition for the move:
[0061]
[0062] The position of the searcher that moves in the sth dimension is The position of the b-th searcher in the s-th dimension is The position of the vth searcher in the sth dimension is The objective function value of the first searcher is The objective function of the κ-th searcher is
[0063] Calculate the scale factor:
[0064]
[0065] The scaling factor for the tth iteration is η t , the maximum value of the scale factor is η max , the minimum value of the proportionality factor is η min , the control parameter is β, and the maximum number of iterations is t max , the maximum linear coefficient is H, and the search sub-position after the attack is calculated:
[0066]
[0067] The search sub-position after the second stage update is The objective function value of the a-th searcher move is The objective function value is Calculate the updated variant individuals:
[0068]
[0069] The random numbers are r6, r7, and r8 respectively, and the mutant individual after the maximum number of iterations of the a-th searcher is updated is The position of the maximum number of iterations of random number r6 is The position of the maximum number of iterations of random number r7 is The position of the maximum number of iterations of random number r8 is The coefficient of variation is χ.
[0070] In a second aspect, an embodiment of the present application further provides an electronic device, including:
[0071] A processor; and a memory arranged to store computer executable instructions, which when executed cause the processor to perform the method steps described in the first aspect.
[0072] In a third aspect, an embodiment of the present application further provides a computer-readable storage medium, which stores one or more programs. When the one or more programs are executed by an electronic device including multiple applications, the electronic device executes the method steps described in the first aspect.
[0073] The beneficial effects of the present invention are:
[0074] The present invention is an auxiliary decision-making method and system for urban subway waterlogging risk management based on Bayesian network. Compared with the prior art, the present invention has the following technical effects:
[0075] The present invention can improve the accuracy of auxiliary decision-making for urban subway waterlogging risk disposal through preprocessing, water flow prediction, available drainage, risk assessment, risk value adjustment, model construction and model optimization steps, thereby improving the precision of auxiliary decision-making for urban subway waterlogging risk disposal, optimizing auxiliary decision-making for urban subway waterlogging risk disposal, which can greatly save resources and improve work efficiency, and can realize intelligent auxiliary decision-making for urban subway waterlogging risk disposal, and perform risk correction on auxiliary decision-making for urban subway waterlogging risk disposal in real time, which is of great significance to auxiliary decision-making for urban subway waterlogging risk disposal, can adapt to auxiliary decision-making for urban subway waterlogging risk disposal with different standards and different auxiliary decision-making needs for urban subway waterlogging risk disposal, and has a certain universality. BRIEF DESCRIPTION OF THE DRAWINGS
[0076] Figure 1 It is a flowchart of the steps of the auxiliary decision-making method for urban subway waterlogging risk treatment based on Bayesian network of the present invention;
[0077] Figure 2 It is a schematic diagram of the structure of an electronic device in an embodiment of this specification. DETAILED DESCRIPTION
[0078] The present invention is further described below by means of specific embodiments. The illustrative embodiments and descriptions of the present invention are used to explain the present invention but are not intended to limit the present invention.
[0079] The Bayesian network-based urban subway waterlogging risk management auxiliary decision-making method and system of the present invention comprises the following steps:
[0080] like Figure 1 As shown, in this embodiment, the following steps are included:
[0081] Acquire waterlogging data and basic data of subways in target cities, and pre-process the waterlogging data; the waterlogging data includes historical waterlogging data, meteorological data, and monitoring data;
[0082] The first evaluation data and the second evaluation data are obtained by preprocessing the waterlogging data; the first evaluation data represents the water flow prediction value of the target city subway; the second evaluation data represents the available drainage capacity of the target city subway; the water flow prediction value is the water flow prediction value based on the monitoring data and the meteorological data; the drainage capacity is the available drainage volume based on the basic data and the monitoring data;
[0083] Performing risk assessment on the first assessment data and the second assessment data using a risk level to obtain a risk value, and adjusting the risk value according to the monitoring data to obtain a risk degree;
[0084] A waterlogging risk management auxiliary decision-making model is constructed according to the risk level to optimize the waterlogging risk management auxiliary decision-making.
[0085] In this embodiment, the method for predicting water flow based on the monitoring data and the meteorological data includes inputting the monitoring data and the meteorological data into a water flow prediction model to obtain the predicted amount of water flow entering the subway; the water flow prediction model is constructed using an autoregressive algorithm and a long-short term neural network algorithm.
[0086] In this embodiment, the method for determining the available drainage volume based on the basic data and the monitoring data includes:
[0087] The drainage setting of the basic data is used as a reference standard to obtain the difference between the initial water volume of the drainage channel and the water volume at the end of the drainage channel in the monitoring data;
[0088] When the initial water volume of the drainage channel in the monitoring data is greater than or equal to the reference standard, if the difference is less than 10%, the channel reference standard is used as the drainage volume of the current drainage pipe, otherwise the water volume at the end of the drainage channel is used as the drainage volume of the current drainage pipe;
[0089] When the initial water volume in the drainage channel in the monitoring data is less than the reference standard, if the difference is lower than 13.1%, the channel reference standard will be used as the drainage volume of the current drainage pipe. If the difference is between 13.1% and 100%, the channel reference standard minus the difference will be used as the drainage volume of the current drainage pipe. If the difference is 100%, the drainage volume of the current drainage pipe is 0.
[0090] In this embodiment, the method of performing risk assessment on the first assessment data and the second assessment data using risk levels includes:
[0091] The subway is attacked by waterlogging in three stages: early warning preparation, initial waterlogging, and severe waterlogging. An attack state matrix is constructed based on the risk factors of subway waterlogging. The risk factors are used as nodes to calculate the risk value:
[0092]
[0093] The danger level of node w is a w , the attack result of node w is The attack phase of node w is c w , the attack state of node w is d w , the number and severity of danger, attack results, attack stages and attack states are The weights are ψ1, ψ2, ψ3, and ψ4;
[0094] According to the risk factor, the direction of the result is added and the weight of the node directed edge is calculated:
[0095]
[0096] The total number of attack states is N * , the maximum danger level of node w in the attack state i is a iw,max , the risk value of node w attacking state i is The probability that node y is in attack state i after node w attacks is The danger level of attacking node w in state i is a wi , the attack constant is z, and the expected risk of node w attacking node y is
[0097] Construct a directed weighted network based on directed risk factors and calculate the average value of the path capture nodes:
[0098]
[0099] The number of other nodes captured from node w is The path to capture other nodes from node w is The average probability of attacking other nodes from node w is Starting from node w The probability of the path that may endanger other nodes being attacked is
[0100] Calculate the average probability of being compromised:
[0101]
[0102] The node w is passed through The probability of a path being attacked is The number of possible paths for node w to be captured is The average probability of node i being attacked is
[0103] Construct a weighted directed graph based on the directed weighted network and calculate the importance index of the node:
[0104]
[0105] The importance index of node w is ε w , the first balance factor is θ1, the second balance factor is θ2, the natural constant is e, and the weight of the node w sending outward connections is S ot (w), the weight of node w receiving the connection is S in (w), the attack coefficient is υ;
[0106] Calculate the weighted risk expectation of the node:
[0107]
[0108] The weighted risk expectation of node w is The probability that node w is in attack state i is The weighting factor is λ, and the risk value of the node is calculated as:
[0109]
[0110] The first balance coefficient is The second balance coefficient is The risk value of node w is
[0111] In this embodiment, the method of adjusting the risk value according to the monitoring data to obtain the risk level includes:
[0112] Calculate the risk importance of monitoring data:
[0113]
[0114] The risk importance of the jth monitoring data is The number of the jth monitoring data is k, and the contribution of the jth monitoring data is The risk tolerance of the jth monitoring data is The damage degree of the previous rainfall risk of the jth monitoring data is The intensity factor of the jth monitoring data is χ j ;
[0115] The monitoring data with risk importance greater than 0.362 are integrated into risk data, and the risk level is calculated based on the risk data:
[0116]
[0117] The risk level of the cth rainfall condition is U c , the j-th risk data value of the c-th rainfall condition is f cj , the standard value of the j-th risk data is The risk importance of the jth risk data of the cth rainfall condition is The optimization factor for the cth rainfall condition is ζ c , the number of risk data for the cth rainfall condition j is k, and the risk value of the cth rainfall condition
[0118] In this embodiment, the method for constructing a waterlogging risk management auxiliary decision-making model according to the risk level includes:
[0119] Taking the risk level as the decision criterion of the auxiliary decision-making model for waterlogging risk management:
[0120] When the risk level is less than 0.29, the risk level is level 1; when the risk level is greater than 0.29 and less than 0.53, the risk level is level 2; when the risk level is greater than 0.53 and less than 0.71, the risk level is level 3; when the risk level is greater than 0.71 and less than 0.89, the risk level is level 4; when the risk level is greater than 0.89 and less than 1, the risk level is special level;
[0121] The auxiliary decision-making model for waterlogging risk management includes association rule mining algorithm, Bayesian network algorithm, long short-term memory network algorithm, and fuzzy evaluation algorithm;
[0122] The association rule mining algorithm selects important data based on the degree of association of waterlogging data;
[0123] The Bayesian network algorithm establishes the basic structure of the Bayesian network based on important data; takes risk factors as nodes of the Bayesian network; assigns probability to the state of each node; sets general risk factor nodes, decision nodes and utility nodes to obtain the first risk level;
[0124] The short-term memory network algorithm makes predictions based on the time characteristics of important data to obtain the second risk level;
[0125] The fuzzy evaluation algorithm fuses the first risk degree and the second risk degree to obtain the risk degree.
[0126] In this embodiment, the method for optimizing the auxiliary decision-making for waterlogging risk management includes:
[0127] Randomly generate multiple searchers and calculate their positions:
[0128]
[0129] The update position of the a-th searcher in the s-th dimension is The position of the a-th searcher in the s-th dimension is The random number is r, the sign function is sign(·), and the objective function value of the a-th searcher is The position of the p-th searcher in the s-th dimension is The p-th search sub-objective function value is
[0130] Calculate the updated position and mutation individuals of the searcher:
[0131]
[0132]
[0133] The updated objective function value of the a-th searcher is The position of the searcher after the first phase update is The random numbers are r1, r2, r3, r4, r5, the random number function is rd(·), and the random individuals of the t-th iteration population are The mutant individual of the a-th searcher in the t-th iteration population is
[0134] Compute the search subposition for the move:
[0135]
[0136] The position of the searcher that moves in the sth dimension is The position of the b-th searcher in the s-th dimension is The position of the vth searcher in the sth dimension is The objective function value of the first searcher is The objective function of the κ-th searcher is
[0137] Calculate the scale factor:
[0138]
[0139] The scaling factor for the tth iteration is η t , the maximum value of the scale factor is η max , the minimum value of the proportionality factor is η min , the control parameter is β, and the maximum number of iterations is t max , the maximum linear coefficient is H, and the search sub-position after the attack is calculated:
[0140]
[0141] The search sub-position after the second stage update is The objective function value of the a-th searcher move is The objective function value is Calculate the updated variant individuals:
[0142]
[0143] The random numbers are r6, r7, and r8 respectively, and the mutant individual after the maximum number of iterations of the a-th searcher is updated is The position of the maximum number of iterations of random number r6 is The position of the maximum number of iterations of random number r7 is The position of the maximum number of iterations of random number r8 is The coefficient of variation is χ.
[0144] Figure 2 This is a schematic diagram of the structure of an electronic device according to an embodiment of the present application. Figure 2 At the hardware level, the electronic device includes a processor, and optionally also includes an internal bus, a network interface, and a memory. The memory may include a memory, such as a high-speed random access memory (RAM), and may also include a non-volatile memory (non-volatile memory), such as at least one disk storage. Of course, the electronic device may also include hardware required for other services.
[0145] The processor, network interface and memory can be interconnected through an internal bus, which can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 2 Only one bidirectional arrow is used in the diagram, but this does not mean that there is only one bus or only one type of bus.
[0146] The memory is used to store the program. Specifically, the program may include a program code, and the program code includes a computer operation instruction. The memory may include a memory and a non-volatile memory, and provides instructions and data to the processor.
[0147] The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it, forming an auxiliary decision-making device for urban subway waterlogging risk treatment based on the Bayesian network at the logical level. The processor executes the program stored in the memory and is specifically used to execute any of the aforementioned auxiliary decision-making methods for urban subway waterlogging risk treatment based on the Bayesian network.
[0148] The above application Figure 1 The Bayesian network-based urban subway waterlogging risk disposal auxiliary decision-making method disclosed in the illustrated embodiment can be applied to a processor or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by an integrated logic circuit of hardware in the processor or an instruction in software form. The above processor may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The steps of the method disclosed in the embodiments of the present application can be directly embodied as being executed by a hardware decoding processor, or executed by a combination of hardware and software modules in a decoding processor. The software module can be located in a storage medium mature in the art, such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware.
[0149] The electronic device may also perform Figure 1 A Bayesian network-based decision-making method for urban subway waterlogging risk management is proposed. Figure 1 The functions of the illustrated embodiment will not be described in detail in the embodiments of the present application.
[0150] An embodiment of the present application also proposes a computer-readable storage medium, which stores one or more programs, and the one or more programs include instructions. When the instructions are executed by an electronic device including multiple applications, they execute any of the aforementioned Bayesian network-based urban subway waterlogging risk management auxiliary decision-making methods.
[0151] 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 in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.
[0152] 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.
[0153] 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 comprising 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.
[0154] 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 in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.
[0155] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.
[0156] The memory may include non-permanent storage 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.
[0157] 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 magnetic 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.
[0158] 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.
[0159] 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 in combination with 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.) that contain computer-usable program code.
[0160] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims
1. A Bayesian network-based decision-making aid method for urban subway waterlogging risk management, characterized in that: The following steps are involved: Acquire waterlogging data and basic data of subways in target cities, and pre-process the waterlogging data; the waterlogging data includes historical waterlogging data, meteorological data, and monitoring data; The first evaluation data and the second evaluation data are obtained by using the preprocessed waterlogging data; the first evaluation data represents the predicted value of water flow in the subway of the target city; The second evaluation data represents the available drainage capacity of the target city subway; the water flow prediction value is the water flow prediction value based on the monitoring data and the meteorological data; The drainage capacity is the available drainage volume based on the basic data and the monitoring data; including: The subway is attacked by waterlogging in three stages: early warning preparation, initial waterlogging, and severe waterlogging. An attack state matrix is constructed based on the risk factors of subway waterlogging. The risk factors are used as nodes to calculate the risk value: The danger level of node w is a w , the attack result of node w is The attack phase of node w is c w , the attack state of node w is d w , the sum of the number of danger levels, attack results, attack stages, and attack states is m, and the weights are ψ1, ψ2, ψ3, and ψ4 respectively; According to the risk factor, the direction of the result is added and the weight of the node directed edge is calculated: The total number of attack states is N * , the maximum danger level of node w in the attack state i is a wi,max , the risk value of node w attacking state i is The probability that node y is in attack state i after node w attacks is The danger level of attacking node w in state i is a wi , the attack constant is z, and the expected risk of node w attacking node y is Construct a directed weighted network based on directed risk factors and calculate the average value of the path capture nodes: The number of nodes captured from node w is n, the path of capturing other nodes from node w is l, and the average probability of capturing other nodes from node w is The probability of the lth path from node w that may endanger other nodes is Q wl ; Calculate the average probability of being compromised: The probability that node w is captured through the lth path is The number of possible paths for node w to be captured is n1, and the average probability of node i being captured is Construct a weighted directed graph based on the directed weighted network and calculate the importance index of the node: The importance index of node w is ε w , the first balance factor is θ1, the second balance factor is θ2, the natural constant is e, and the weight of the node w sending outward connections is S ot (w), the weight of node w receiving the connection is S in (w), the attack coefficient is υ; Calculate the weighted risk expectation of the node: The weighted risk expectation of node w is The probability that node w is in attack state i is The weighting factor is λ, and the risk value of the node is calculated as: The first balance coefficient is The second balance coefficient is The risk value of node w is Performing risk assessment on the first assessment data and the second assessment data using a risk level to obtain a risk value, and adjusting the risk value according to the monitoring data to obtain a risk degree; including: Calculate the risk importance of monitoring data: The risk importance of the jth monitoring data is The number of the jth monitoring data is k, and the contribution of the jth monitoring data is u j , the risk tolerance of the jth monitoring data is The damage degree of the previous rainfall risk of the jth monitoring data is The intensity factor of the jth monitoring data is χ j ; The monitoring data with risk importance greater than 0.362 are integrated into risk data, and the risk level is calculated based on the risk data: The risk level of the cth rainfall condition is U c , the j-th risk data value of the c-th rainfall condition is f cj , the standard value of the j-th risk data is The risk importance of the jth risk data of the cth rainfall condition is The optimization factor for the cth rainfall condition is ζ c , the number of risk data for the cth rainfall condition jth is Risk value of the cth rainfall condition According to the risk level, a waterlogging risk handling auxiliary decision model is constructed to optimize the waterlogging risk handling auxiliary decision; including: Taking the risk level as the decision criterion of the auxiliary decision-making model for waterlogging risk management: When the risk level is less than 0.29, the risk level is level 1; when the risk level is greater than 0.29 and less than 0.53, the risk level is level 2; when the risk level is greater than 0.53 and less than 0.71, the risk level is level 3; when the risk level is greater than 0.71 and less than 0.89, the risk level is level 4; when the risk level is greater than 0.89 and less than 1, the risk level is special level; The auxiliary decision-making model for waterlogging risk management includes association rule mining algorithm, Bayesian network algorithm, long short-term memory network algorithm, and fuzzy evaluation algorithm; The association rule mining algorithm selects important data based on the degree of association of waterlogging data; The Bayesian network algorithm establishes the basic structure of the Bayesian network based on important data; takes risk factors as nodes of the Bayesian network; assigns probability to the state of each node; sets general risk factor nodes, decision nodes and utility nodes to obtain the first risk level; The short-term memory network algorithm makes predictions based on the time characteristics of important data to obtain the second risk level; The fuzzy evaluation algorithm fuses the first risk degree and the second risk degree to obtain the risk degree.
2. According to claim 1, the Bayesian network-based urban subway waterlogging risk management auxiliary decision-making method is characterized by: The method for predicting water flow based on the monitoring data and the meteorological data comprises inputting the monitoring data and the meteorological data into a water flow prediction model to obtain the predicted amount of water flow entering the subway; the water flow prediction model is constructed using an autoregressive algorithm and a long-short term neural network algorithm.
3. According to claim 1, the Bayesian network-based urban subway waterlogging risk management auxiliary decision-making method is characterized by: The method for available drainage based on the basic data and the monitoring data comprises: The drainage setting of the basic data is used as a reference standard to obtain the difference between the initial water volume of the drainage channel and the water volume at the end of the drainage channel in the monitoring data; When the initial water volume of the drainage channel in the monitoring data is greater than or equal to the reference standard, if the difference is less than 10%, the channel reference standard is used as the drainage volume of the current drainage pipe, otherwise the water volume at the end of the drainage channel is used as the drainage volume of the current drainage pipe; When the initial water volume in the drainage channel in the monitoring data is less than the reference standard, if the difference is lower than 13.1%, the channel reference standard will be used as the drainage volume of the current drainage pipe. If the difference is between 13.1% and 100%, the channel reference standard minus the difference will be used as the drainage volume of the current drainage pipe. If the difference is 100%, the drainage volume of the current drainage pipe is 0.
4. The Bayesian network-based decision-making auxiliary method for urban subway waterlogging risk management according to claim 1 is characterized in that: The method for optimizing the auxiliary decision-making for waterlogging risk management includes: Randomly generate multiple searchers and calculate their positions: The update position of the a-th searcher in the s-th dimension is The position of the a-th searcher in the s-th dimension is The random number is r, the sign function is sign(·), and the objective function value of the a-th searcher is The position of the p-th searcher in the s-th dimension is The p-th search sub-objective function value is Calculate the updated position and mutation individuals of the searcher: The updated objective function value of the a-th searcher is The position of the searcher after the first phase update is The random numbers are r1, r2, r3, r4, r5, the random number function is rd(·), and the random individuals of the t-th iteration population are The mutant individual of the a-th searcher in the t-th iteration population is Compute the search subposition for the move: The position of the searcher that moves in the sth dimension is The position of the b-th searcher in the s-th dimension is The position of the vth searcher in the sth dimension is The objective function value of the first searcher is The objective function of the κ-th searcher is Calculate the scale factor: The scaling factor for the tth iteration is η t , the maximum value of the scale factor is η max , the minimum value of the proportionality factor is η min , the control parameter is β, and the maximum number of iterations is t max , the maximum linear coefficient is H, and the search sub-position after the attack is calculated: The search sub-position after the second stage update is The objective function value of the a-th searcher move is The objective function value is Calculate the updated variant individuals: The random numbers are r6, r7, and r8 respectively, and the mutant individual after the maximum number of iterations of the a-th searcher is updated is The position of the maximum number of iterations of random number r6 is The position of the maximum number of iterations of random number r7 is The position of the maximum number of iterations of random number r8 is The coefficient of variation is χ.
Citation Information
Patent Citations
Risk analysis and evaluation method and device based on Bayesian network
CN112069726A
Flood disaster risk assessment method based on heterogenous multi-scale monitoring data
CN113256138A
Urban inland inundation disaster risk assessment method
CN114399204A
Method and system for acquiring influence degree of urban elements on waterlogging disaster loss
CN114595764A
Flood risk point assessment method and device based on urban water affair system
CN115471078A
