CN118070982A

CN118070982A - Prediction method and device for selection of station passenger stairs in flood scene

Info

Publication number: CN118070982A
Application number: CN202410471952.5A
Authority: CN
Inventors: 杨晓霞; 吕垚; 董海荣; 魏金丽; 吴继成; 邢艳召; 雷琴; 马浩; 黄帅; 张永亮; 宋帅; 曲大义; 周波; 康元磊
Original assignee: Qingdao University of Technology; China Railway Construction Electrification Bureau Group Co Ltd; Third Engineering Co Ltd of China Railway Construction Electrification Bureau Group Co Ltd; Operation Management Co Ltd of China Railway Construction Electrification Bureau Group Co Ltd; National Institute of Natural Hazards
Current assignee: Qingdao University of Technology; China Railway Construction Electrification Bureau Group Co Ltd; Third Engineering Co Ltd of China Railway Construction Electrification Bureau Group Co Ltd; Operation Management Co Ltd of China Railway Construction Electrification Bureau Group Co Ltd; National Institute of Natural Hazards
Priority date: 2024-04-19
Filing date: 2024-04-19
Publication date: 2024-05-24

Abstract

The embodiment of the application discloses a prediction method and a prediction device for the selection of a station passenger escalator in a flood scene. One embodiment of the method comprises the following steps: emergency stair facility information, main stair facility information, passenger information and flood scene information of the underground station are acquired; inputting the acquired emergency stair facility information, main stair facility information, passenger information and flood scene information into a pre-constructed estimation model; and determining an estimated value of the percentage of the passenger flow of the emergency stairs selected to be used in the flood scene to the total cross section passenger flow according to the output of the estimated model. The embodiment can assist workers to reasonably arrange personnel to evacuate, improves the effective utilization rate of vertical evacuation facilities in emergency, and provides support for safe evacuation of personnel in underground stations.

Description

Prediction method and device for selection of station passenger stairs in flood scene

Technical Field

The embodiment of the application relates to the technical field of computers, in particular to a prediction method and a prediction device for selecting a station passenger building and an escalator in a flood scene.

Background

Along with the rapid development of rail transit, a large number of stations built underground appear in cities to save the overground space, the underground stations belong to semi-closed relative airtight spaces, once underground work accidents such as urban flood disasters or drainage system faults, underground water infiltration and the like occur, flood possibly enters the inside of a rail transit road network system from the underground stations and goes through a communication area, people staying underground must be evacuated to a safe area in time at the moment, and otherwise casualties can be caused. Main stairs and escalators are the main vertical evacuation facilities to and from underground stations. Under the condition that the underground station personnel density is high and the evacuation facilities connecting the underground space and the ground are limited, the position of the escalator is easy to form a congestion point, so that the congestion point becomes a main bottleneck section in the emergency evacuation process. The escalator is stopped and used as an emergency stair in a flood scene, but the use rate of the emergency stair is different from that of the main stair due to the fact that parameters of the emergency stair and the main stair, such as anti-slip degree, inclination angle parameters, stair width and the like, are different, and the phenomenon of congestion is easy to be aggravated due to the imbalance of the use rates of the emergency stair and the main stair. Therefore, analysis and estimation of the utilization rate of the emergency stairway of the underground station in the flood scene are necessary for rapid evacuation of passengers staying underground in the emergency.

Disclosure of Invention

The embodiment of the application provides a prediction method and a prediction device for the selection of a station passenger escalator in a flood scene.

In a first aspect, some embodiments of the present application provide a method for predicting a selection of a passenger escalator in a station in a flood scene, the method comprising: emergency stair facility information, main stair facility information, passenger information and flood scene information of the underground station are acquired; inputting the acquired emergency stair facility information, main stair facility information, passenger information and flood scene information into a pre-constructed estimation model, wherein the estimation model is used for representing the corresponding relation between the emergency stair facility information, main stair facility information, passenger information and flood scene information of the underground station and the estimated value of the emergency stair utilization rate of the underground station in the flood scene; and determining an estimated value of the percentage of the passenger flow of the emergency stairs selected to be used in the flood scene to the passenger flow of the total cross section according to the output of the estimated model.

In some embodiments, the dataset for constructing the estimation model is obtained by: constructing a hydrodynamic simulation system of an underground station to obtain flood scene information; constructing a three-dimensional simulation scene of an emergency stair and a main stair node of an underground station based on the emergency stair facility information, the main stair facility information and pedestrian simulation software of a discrete event simulation principle; and adding the simulation object into the three-dimensional simulation scene to simulate, so as to obtain the data set, wherein the data set comprises simulation values of different emergency stair facility information, main stair facility information, passenger information, flood scene information and corresponding emergency stair utilization rate of the underground station.

In some embodiments, the emergency stair facility information includes an emergency stair slip, an emergency stair height, an emergency stair width, an emergency stair dip parameter, an emergency stair step height, an emergency stair layout form, the main stair facility information includes a main stair slip, a main stair height, a main stair width, a main stair dip parameter, a main stair step height, and a main stair layout form, the passenger information includes a passenger number, a passenger gender, an age structure, and the flood scenario information includes a water depth, and a water flow speed on the emergency stair and the main stair; and adding the simulation object into the three-dimensional simulation scene for simulation to obtain the data set, wherein the method comprises the following steps of: based on the hydrodynamic simulation system, simulating to obtain the water depth and the water flow speed on the emergency stairs and the main stairs; the travelling speed of the passenger under the influence of the flood is determined by the following formula:

Wherein v _i is walking speed, M is Hong Shuili with unit width, a and b are preset constants, D is flood depth, g is gravity acceleration, and v _f is water flow speed on emergency stairs and main stairs; based on the three-dimensional simulation scene, setting the number of passengers, the gender of the passengers and the age structure, and combining the travelling speed of the passengers under the influence of floods to obtain the simulation value of the percentage of the passenger flow of the emergency stairs to the total cross section passenger flow.

In some embodiments, the estimation model is constructed by: obtaining a basic estimation model based on the random forest model, and optimizing the basic estimation model through a snow ablation optimization algorithm; training the optimized model by using the simulation data to obtain the estimation model.

In some embodiments, the deriving the base estimation model based on the random forest model includes: resampling based on a Bootstrap method, randomly generating N groups of training samples, and generating a decision tree for each group of training samples; when the splitting attribute of each non-leaf node of the decision tree is selected, a random method is used, and M attributes are selected from M sample total attributes to be used as a total attribute set of the current node; machine learning is carried out, and nodes are split in a best classification mode in the selected m attributes; and selecting an average value of N groups of training sample results as an estimation result of the model in the machine learning process.

In some embodiments, the optimizing the base estimation model by a snow-ablation optimization algorithm includes: initializing a snow ablation optimization algorithm, and setting a value range of optimized parameters, wherein the optimized parameters comprise the number of decision trees and the selected feature numbers in a basic estimation model; optimizing the number of decision trees and the selected feature number parameters in the initial estimation model by using a snow ablation optimization algorithm, taking the number of decision trees and the selected feature number parameters as a group of candidate solutions of the snow ablation optimization algorithm, calculating a fitness value, and updating the optimal particles; and obtaining a candidate solution corresponding to an optimal value in an objective function of the snow ablation optimization algorithm through iterative calculation, and taking the obtained candidate solution as the decision tree number and the selected feature number parameter in the estimation model to finish the optimization of the model.

In some embodiments, the training the optimized model with the simulation data to obtain the estimation model includes: dividing the data set into a training set and a testing set; preprocessing data in the training set and the testing set, wherein the preprocessing comprises cleaning, standardization, conversion and coding of the data; selecting and extracting the skid resistance, the height, the width and the inclination angle parameters, the height, the layout form, the number, the gender and the age structure of passengers, the water depth and the water flow speed on the emergency stairs and the main stairs in the data set, and selecting the percentage of the passenger flow of the emergency stairs in the flood scene to the passenger flow of the total cross section as model output characteristics for training and testing the model; training the model by using a training set, and finding out the best fitting result by continuously adjusting model parameters; and evaluating the model obtained by training by using the test set to verify the generalization capability and performance of the model, optimizing and optimizing the model according to the evaluation result, improving the estimation capability and accuracy of the model and completing the training of the estimation model.

In some embodiments, the snow-ablation optimization algorithm includes an initialization phase comprising the steps of: randomly generating a batch of particles as an initial population, the initial population represented by the following matrix:

Where N represents the size of the population, dim represents the dimension of the solution space, L and U indicate the lower and upper bounds of the solution space, respectively, The random numbers in interval [0,1 ].

In some embodiments, the snow ablation optimization algorithm includes an exploration phase comprising the steps of: obtaining Brownian motion step length based on probability density function of normal distribution with mean value of 0 and variance of 1:

Based on the potential area in the Brownian motion exploration search space, the position update formula in the exploration process is as follows:

wherein, Represents the t-th iteration of the i-th particle,/>Represents the t +1 iteration of the ith particle,Vector representing random numbers based on gaussian distribution representing brownian motion, sign/>Representing a multiplication item by item,/>Representing the random number between [0,1 ]/>Representing the current optimal solution,/>Is an individual randomly selected from elite population of the population,/>Representing centroid position of population,/>The mathematical expression of (2) is as follows:

wherein, And/>Representing the second and third best individuals in the current population, respectively,/>Representing centroid position of top 50% individuals of fitness value rank,/>The mathematical expression of (2) is as follows:

Where N ₁ represents the number of leaders and N ₁ is equal in number to half the overall population size during each iteration Randomly selecting from the set consisting of the current best solution, the second best individual, the third best individual, and the centroid position of the leader.

In some embodiments, the snow-ablation optimization algorithm includes a mining phase comprising the steps of: the snow melt rate was calculated by the following equation:

wherein M is the snow melting rate, T is the daily average temperature, T _max is the termination condition, DDF is the gradient-day factor, the value range is 0.35 to 0.6, and in each iteration, the mathematical expression of the DDF value to be updated is as follows:

the location update of the mining phase is performed by the following formula:

wherein, Representing a random number selected from [ -1,1], in cross terms/>AndWith the help of the current best search agent and the information of the mass center position of the group, the individuals are more likely to utilize the area with more hopeful best solution; the snow ablation algorithm adopts a double-population mechanism, the whole population is randomly divided into two sub-populations with equal size at the early stage of iteration, the whole population is denoted as p, the two sub-populations are denoted as pop1 and pop2 respectively, pop1 is responsible for exploration, pop2 is assigned to be used, the two populations are the same in size at first, pop2 is gradually lowered in the subsequent iteration, and pop1 is correspondingly increased; the complete position update equation of the snow ablation algorithm is:

wherein, And/>Individuals in pop1 and pop2 are indexed throughout the location matrix for a set.

In a second aspect, some embodiments of the present application provide a prediction apparatus for selecting a passenger escalator in a station in a flood scene, the apparatus comprising: an acquisition unit configured to acquire emergency stair facility information, main stair facility information, passenger information, and flood scene information of an underground station; the estimating unit is configured to input the acquired emergency stair facility information, main stair facility information, passenger information and flood scene information into a pre-constructed estimating model, wherein the estimating model is used for representing the corresponding relation between the emergency stair facility information, main stair facility information, passenger information and flood scene information of the underground station and the estimated value of the emergency stair utilization rate of the underground station in the flood scene; and the determining unit is configured to determine an estimated value of the percentage of the passenger flow of the emergency stairway used by the underground station in the flood scene to the total cross section passenger flow according to the output of the estimated model.

In some embodiments, the apparatus further comprises a simulation unit configured to obtain training sample data and/or test sample data of the estimation model by: constructing a hydrodynamic simulation system of an underground station to obtain flood scene information; constructing a three-dimensional simulation scene of an emergency stair and a main stair node of an underground station based on the emergency stair facility information, the main stair facility information and pedestrian simulation software of a discrete event simulation principle; and adding the simulation object into the three-dimensional simulation scene to simulate, so as to obtain the data set, wherein the data set comprises simulation values of different emergency stair facility information, main stair facility information, passenger information, flood scene information and corresponding emergency stair utilization rate of the underground station.

In some embodiments, the emergency stair facility information includes an emergency stair slip, an emergency stair height, an emergency stair width, an emergency stair dip parameter, an emergency stair step height, an emergency stair layout form, the main stair facility information includes a main stair slip, a main stair height, a main stair width, a main stair dip parameter, a main stair step height, and a main stair layout form, the passenger information includes a passenger number, a passenger gender, an age structure, and the flood scenario information includes a water depth, and a water flow speed on the emergency stair and the main stair; and the simulation unit is further configured to: based on the hydrodynamic simulation system, simulating to obtain the water depth and the water flow speed on the emergency stairs and the main stairs; the travelling speed of the passenger under the influence of the flood is determined by the following formula:

In some embodiments, the apparatus further comprises a model building unit configured to build the estimation model by: obtaining a basic estimation model based on the random forest model, and optimizing the basic estimation model through a snow ablation optimization algorithm; training the optimized model by using the simulation data to obtain the estimation model.

In some embodiments, the model building unit is further configured to: obtaining a basic estimation model based on the random forest model, including: resampling based on Bootstrap method includes randomly generating N groups of training samples, and generating a decision tree for each group of training samples; when the splitting attribute of each non-leaf node of the decision tree is selected, a random method is used, and M attributes are selected from M sample total attributes to be used as a total attribute set of the current node; machine learning is carried out, and nodes are split in a best classification mode in the selected m attributes; and selecting an average value of N groups of training sample results as an estimation result of the model in the machine learning process.

In some embodiments, the model building unit is further configured to: initializing a snow ablation optimization algorithm, and setting a value range of optimized parameters, wherein the optimized parameters comprise the number of decision trees and the selected feature numbers in a basic estimation model; optimizing the number of decision trees and the selected feature number parameters in the initial estimation model by using a snow ablation optimization algorithm, taking the number of decision trees and the selected feature number parameters as a group of candidate solutions of the snow ablation optimization algorithm, calculating a fitness value, and updating the optimal particles; and obtaining a candidate solution corresponding to an optimal value in an objective function of the snow ablation optimization algorithm through iterative calculation, and taking the obtained candidate solution as the decision tree number and the selected feature number parameter in the estimation model to finish the optimization of the model.

In some embodiments, the model building unit is further configured to: dividing the data set into a training set and a testing set; preprocessing data in the training set and the testing set, wherein the preprocessing comprises cleaning, standardization, conversion and coding of the data; selecting and extracting the skid resistance, the height, the width and the inclination angle parameters, the height, the layout form, the number, the gender and the age structure of passengers, the water depth and the water flow speed on the emergency stairs and the main stairs in the data set, and selecting the percentage of the passenger flow of the emergency stairs in the flood scene to the passenger flow of the total cross section as model output characteristics for training and testing the model; training the model by using a training set, and finding out the best fitting result by continuously adjusting model parameters; and evaluating the model obtained by training by using the test set to verify the generalization capability and performance of the model, optimizing and optimizing the model according to the evaluation result, improving the estimation capability and accuracy of the model and completing the training of the estimation model.

the location update of the mining phase is performed by the following formula:

In a third aspect, some embodiments of the present application provide an apparatus comprising: one or more processors; and a storage device having one or more programs stored thereon, which when executed by the one or more processors cause the one or more processors to implement the method as described in the first aspect.

In a fourth aspect, some embodiments of the application provide a computer readable medium having stored thereon a computer program which when executed by a processor implements a method as described in the first aspect.

According to the prediction method and the prediction device for the selection of the passenger stairs of the station in the flood scene, the emergency stair facility information, the main stair facility information, the passenger information and the flood scene information of the underground station are obtained; inputting the acquired emergency stair facility information, main stair facility information, passenger information and flood scene information into a pre-constructed estimation model, wherein the estimation model is used for representing the corresponding relation between the emergency stair facility information, main stair facility information, passenger information and flood scene information of the underground station and the estimated value of the emergency stair utilization rate of the underground station in the flood scene; according to the output of the estimation model, an estimated value of the percentage of the passenger flow of the emergency stairs to the total cross section passenger flow is determined, so that personnel can be assisted to reasonably arrange personnel evacuation, the effective utilization rate of the underground station vertical evacuation facility in an emergency situation is improved, and support is provided for the safe evacuation and evacuation of the personnel.

Drawings

Other features, objects and advantages of the present application will become more apparent upon reading of the detailed description of non-limiting embodiments, made with reference to the accompanying drawings in which:

FIG. 1 is a diagram of some exemplary system architecture in which the present application may be used;

FIG. 2 is a flow chart of one embodiment of a predictive method of station passenger escalator selection in a flood scenario in accordance with the present application;

FIG. 3 is a schematic view of a three-dimensional simulation scenario of an emergency stair and a main stair node in an application scenario of an embodiment of the present application;

FIG. 4 is a schematic diagram of a three-dimensional simulation scenario with simulated individual emergency stairway and main stairway nodes in an application scenario according to an embodiment of the application;

FIG. 5 is a flow chart of a snow ablation optimization algorithm in one application scenario of an embodiment of the present application;

FIG. 6 is a schematic diagram of one embodiment of a predictive device for station passenger escalator selection in flood scenarios in accordance with the present application;

Fig. 7 is a schematic diagram of a computer system suitable for use in implementing some embodiments of the application.

Detailed Description

In order to enable the person skilled in the art to better understand the estimation method, a specific implementation method and the attached drawings are combined to clearly describe and explain a prediction method of the selection of the passenger stairs of the station in the flood scene. It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the application. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.

It should be understood that the term "and/or" as used in the present specification and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes such combinations. In addition, in the description of the present specification and the appended claims, the terms "first," "second," and "third," etc. are used merely to distinguish between descriptions, and are not to be construed as indicating or implying relative importance. It should be noted that, without conflict, the embodiments of the present application and features of the embodiments may be combined with each other. The application will be described in detail below with reference to the drawings in connection with embodiments.

Fig. 1 shows an exemplary system architecture 100 of an embodiment of a prediction method of station passenger escalator selection in flood scenarios or a prediction apparatus of station passenger escalator selection in flood scenarios to which the present application may be applied.

As shown in fig. 1, a system architecture 100 may include terminal devices 101, 102, 103, a network 104, and a server 105. The network 104 is used as a medium to provide communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, among others.

The user may interact with the server 105 via the network 104 using the terminal devices 101, 102, 103 to receive or send messages or the like. Various client applications, such as a data processing class application, a simulation modeling class application, etc., may be installed on the terminal devices 101, 102, 103.

The terminal devices 101, 102, 103 may be hardware or software. When the terminal devices 101, 102, 103 are hardware, they may be various electronic devices with display screens, including but not limited to smartphones, tablets, laptop and desktop computers, and the like. When the terminal devices 101, 102, 103 are software, they can be installed in the above-listed electronic devices. Which may be implemented as a plurality of software or software modules, or as a single software or software module. The present invention is not particularly limited herein.

The server 105 may be a server providing various services, for example, a background server providing support for applications installed on the terminal devices 101, 102, 103, and the server 105 may acquire emergency stairway facility information, main stairway facility information, passenger information, and flood scene information of an underground station; inputting the acquired emergency stair facility information, main stair facility information, passenger information and flood scene information into a pre-constructed estimation model, wherein the estimation model is used for representing the corresponding relation between the emergency stair facility information, main stair facility information, passenger information and flood scene information of the underground station and the estimated value of the emergency stair utilization rate of the underground station in the flood scene; and determining an estimated value of the percentage of the passenger flow of the emergency stairs selected to be used in the flood scene to the passenger flow of the total cross section according to the output of the estimated model.

It should be noted that, the prediction method for selecting a passenger escalator in a flood scene provided by the embodiment of the present application may be executed by the server 105, or may be executed by the terminal devices 101, 102, 103, and accordingly, the prediction device for selecting a passenger escalator in a flood scene may be set in the server 105, or may be set in the terminal devices 101, 102, 103.

The server may be hardware or software. When the server is hardware, the server may be implemented as a distributed server cluster formed by a plurality of servers, or may be implemented as a single server. When the server is software, it may be implemented as a plurality of software or software modules (e.g., to provide distributed services), or as a single software or software module. The present invention is not particularly limited herein.

It should be understood that the number of terminal devices, networks and servers in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.

With continued reference to fig. 2, a flow 200 of one embodiment of a method of predicting a station passenger escalator selection in a flood scenario according to the present application is shown. The prediction method for selecting the passenger stairs of the station in the flood scene comprises the following steps:

Step 201, emergency stair facility information, main stair facility information, passenger information and flood scene information of an underground station are acquired.

In this embodiment, a prediction method execution body (for example, a server or a terminal shown in fig. 1) of a station passenger escalator selection in a flood scene may first acquire emergency stair facility information, main stair facility information, passenger information, and flood scene information of a target underground station. The underground station may be any underground station whose emergency stairway use rate is to be estimated, for example, a subway station in a disaster prone area.

The passenger information may include data affecting the moving speed of the passenger, such as a passenger's character attribute, a passenger type, a passenger age, a passenger health degree, etc., and the passenger's character attribute may include middle-aged and young passengers, non-middle-aged and young passengers, adult males, adult females, old people, whether to take a child, etc., and data affecting the evacuation of the passenger, such as the number of passengers, the passenger position, etc. Passenger information can be obtained by analyzing video monitoring data of underground stations, and can also be obtained by means of questionnaires, field surveys and the like.

Flood scenario information may include data that may affect passenger movement speed, such as water depth, water flow speed, precipitation, underground station drainage speed, etc. The precipitation data can be obtained through meteorological data, and the data such as water flow speed, water depth and the like can be calculated according to a formula or can be determined through simulation software. The emergency stair facility information and the main stair facility information may include construction information of the main stair facility and the emergency stair facility, for example, emergency stair and main stair skid resistance, emergency stair and main stair height, emergency stair and main stair width, emergency stair and main stair inclination angle parameters, emergency stair and main stair step height and emergency stair and main stair layout form, and the data may be obtained by construction or management units of underground stations or may be obtained by field investigation.

Step 202, inputting the acquired emergency stair facility information, main stair facility information, passenger information and flood scene information into a pre-constructed estimation model.

In this embodiment, the estimation model is used to characterize the correspondence between emergency stair facility information, main stair facility information, passenger information and flood scene information of the underground station and the estimated value of the emergency stair utilization rate of the underground station in the flood scene, and the initial estimation model can be trained through training samples to obtain the estimation model. The training sample can be obtained by simulation through simulation software, can be obtained through historical evacuation data of the underground station, and can also be obtained through experiments. The initial estimation model can be established based on a random forest algorithm or other deep learning models, and can be further adjusted and trained through algorithms such as a particle swarm optimization algorithm, an ant colony optimization algorithm and the like to obtain a final estimation model.

In some alternative implementations of the present embodiment, the dataset used to construct the estimation model is obtained by: constructing a hydrodynamic simulation system of an underground station to obtain flood scene information; constructing a three-dimensional simulation scene of an emergency stair and a main stair node of an underground station based on pedestrian simulation software of the emergency stair facility information, the main stair facility information and a discrete event simulation principle; and adding the simulation object into a three-dimensional simulation scene to simulate, so as to obtain the data set, wherein the data set comprises simulation values of different emergency stair facility information, main stair facility information, passenger information, flood scene information and corresponding emergency stair utilization rate of the underground station. Referring to fig. 3, fig. 3 is a schematic diagram of a three-dimensional simulation scenario of an emergency stair and a main stair node, and fig. 3 includes two main stairs and two emergency stairs. Referring to fig. 4, fig. 4 adds a simulated individual to a three-dimensional simulation scene of an emergency stairway and main stairway node.

Pedestrian simulation software based on discrete event simulation principle is adopted to construct three-dimensional simulation scenes of emergency stairs and main stair nodes of the underground station corresponding to actual scenes, the three-dimensional simulation models of the emergency stairs and the main stair nodes constructed based on social force models are used for simulation, and the social force models can accurately simulate individual motions, so that the reliability of the obtained data is high. As an example, MIKE software can be used to build an underground station flood model to obtain the in-station flood depth and the main stairway and emergency stairway flood flow rate. In addition, a three-dimensional simulation model of the emergency stairs and the main stair nodes in the underground station can be constructed by utilizing MassMotion software, massmotion software simulates the motions of pedestrians based on the social force model so as to adapt to the conditions of dynamic changes in the physical environment (such as avoiding obstacles and other pedestrians), and a route cost method is used for searching routes, so that the motion rule of the passengers can be truly simulated. Adopting individual motion simulation software MassMotion based on a social force model, corresponding to an on-site Scene, constructing a model through a Scene module, and modeling an emergency stair and a main stair node in an underground station; setting an activity event through an 'Activities' module, and setting the character attribute of an individual; the method is characterized in that the escalator is assumed to stop running and serve as an emergency stair when flood occurs, and Simulation of pedestrian movement is performed through a Simulation module to obtain two different facility selection behaviors corresponding to the emergency stair and a main stair when people are up-going to evacuate, so that an estimated value of the utilization rate of the emergency stair of the underground station in a specific flood scene is obtained.

In some alternative implementations of the present embodiments, the emergency stair facility information, the main stair facility information, the information including emergency stair and main stair skid resistance, emergency stair and main stair height, emergency stair and main stair width, emergency stair and main stair inclination parameters, emergency stair and main stair step height, and emergency stair and main stair layout forms, the passenger information including passenger number, passenger gender, age structure, flood scenario information including water depth, and water flow speed on the emergency stair and main stair; and adding the simulation object into a three-dimensional simulation scene for simulation to obtain the data set, wherein the method comprises the following steps of: based on the hydrodynamic simulation system, simulating to obtain the water depth and the water flow speed on the emergency stairs and the main stairs; the travelling speed of the passenger under the influence of the flood is determined by the following formula:

Wherein v _i is walking speed, M is Hong Shuili with unit width, a and b are preset constants, D is flood depth, g is gravity acceleration, and v _f is water flow speed on emergency stairs and main stairs; based on the three-dimensional simulation scene, setting the number of passengers, the gender and the age structure of the passengers, and combining the travelling speed of the passengers under the influence of floods to obtain the corresponding simulation value of the emergency stair utilization rate of the underground station.

In the implementation mode, after the speed of the pedestrian influenced by flood is obtained, the speed of the pedestrian can be used as one of input characteristics to obtain the simulated emergency stair utilization rate of the underground station in the simulation scene of the constructed emergency stair and the main stair node together with other input variables, and the percentage of the passenger flow of the emergency stair selected to be used by simulation to the passenger flow of the total cross section is used as an output variable, so that a complete data set required by the training and testing estimation model is obtained.

In some alternative implementations of the present embodiment, the estimation model is constructed by: obtaining a basic estimation model based on the random forest model, and optimizing the basic estimation model through a snow ablation optimization algorithm; training the optimized model by using the simulation data to obtain an estimated model. The snow ablation optimization algorithm (SAO) is a new physical-based algorithm which is inspired by sublimation and melting behaviors of snow in nature, simulates the sublimation and melting behaviors of the snow, and has the advantage of realizing the trade-off between diversity and convergence of groups. The random forest algorithm is a (parallel) integrated algorithm formed by decision trees, belongs to the Bagging type, and is widely applied to various business scenes by combining a plurality of weak classifiers and voting or averaging the final result, so that the result of the overall model has higher accuracy and generalization performance and good stability. However, the estimation performance of the random forest algorithm is greatly affected by parameters such as the number of decision trees and the number of selected features, and if the parameter optimizing capability is insufficient and the local searching capability is poor, the problems of low estimation accuracy, poor generalization capability and the like are easily caused. Therefore, the application adopts a snow ablation optimization algorithm to carry out iterative optimization on the number of decision trees and the selected feature numbers in the random forest model. In addition, the characteristics of emergency stairs and main stairs facilities, passenger flow conditions and flood parameters in the test set can be input into the model after training, an estimated value of the percentage of passenger flow of the emergency stairs selected to be used in corresponding crowds to the total cross section passenger flow is obtained, a mean square error is calculated to evaluate the effectiveness of the model, and an estimated model for the utilization rate of the emergency stairs of the underground station can be obtained.

In some optional implementations of the present embodiment, optimizing the base estimation model by a snow-ablation optimization algorithm includes: initializing a snow ablation optimization algorithm, and setting a value range of optimized parameters, wherein the optimized parameters comprise the number of decision trees and the selected feature number; optimizing the number of decision trees and the selected feature number parameters in the initial estimation model by using a snow ablation optimization algorithm, taking the number of decision trees and the selected feature number parameters as a group of candidate solutions of the snow ablation optimization algorithm, calculating a fitness value, and updating the optimal particles; and obtaining a candidate solution corresponding to an optimal value in an objective function of the snow ablation optimization algorithm through iterative calculation, and taking the obtained candidate solution as the decision tree number and the selected feature number parameter in the estimation model to finish the optimization of the model. The result of the random forest classification model depends on the selection of the number (N) of decision trees and the selected feature number (m) to a great extent, so that the two parameters are effectively optimized by adopting a snow ablation algorithm, and the accuracy of the estimation model can be improved.

In addition, the number of the input features, the number of the features to be estimated and the computing resources can be used for determining the number of decision trees in the estimation model and the upper limit and the lower limit of the feature numbers, the input features can be selected from three aspects of emergency stairs and main stair facility characteristics, passenger flow conditions and flood characteristics, for example, emergency stairs and main stair anti-skid, emergency stairs and main stair heights, emergency stairs and main stair widths, emergency stairs and main stair inclination parameters, emergency stairs and main stair step heights and emergency stairs and main stair layout forms can be selected; passenger number, passenger gender, age configuration; the depth of flood in the station, the flow rate of flood on the emergency stairway and the main stairway, and the characteristic to be estimated can be the percentage of the passenger flow rate of the selected emergency stairway to the total cross section passenger flow rate.

In some optional implementations of the present embodiment, deriving the base estimation model based on the random forest model includes: resampling based on a Bootstrap method, randomly generating N groups of training samples, and generating a decision tree for each group of training samples; when the splitting attribute of each non-leaf node of the decision tree is selected, a random method is used, and M attributes are selected from M sample total attributes to be used as a total attribute set of the current node; machine learning is carried out, and nodes are split in a best classification mode in the selected m attributes; and selecting an average value of N groups of training sample results as an estimation result of the model in the machine learning process. The bootstrapping method is a resampling technique that estimates the statistical properties of samples by extracting a plurality of samples from an original sample and performing a statistical analysis on the samples. It is typically used to estimate statistics of samples, such as mean, variance, confidence interval, etc.

In some optional implementations of the present embodiment, training the optimized model with the simulation data to obtain the estimated model includes: dividing the data set into a training set and a testing set; preprocessing the data in the training set and the testing set, wherein the preprocessing comprises cleaning, standardization, conversion and coding of the data; selecting and extracting the emergency stairway and main stairway skid resistance, the emergency stairway and main stairway height, the emergency stairway and main stairway width, the emergency stairway and main stairway inclination angle parameters, the emergency stairway and main stairway step height, the emergency stairway and main stairway layout form, the number of passengers, the gender of the passengers, the age structure, the water depth and the water flow speed on the emergency stairway and main stairway as model input characteristics, and selecting the percentage of the passenger flow of the emergency stairway to the passenger flow of the total cross section as model output characteristics for training and testing the model at the underground station under the flood scene; training the model by using a training set, and finding out the best fitting result by continuously adjusting model parameters; and evaluating the model obtained by training by using the test set to verify the generalization capability and performance of the model, optimizing and optimizing the model according to the evaluation result, improving the estimation capability and accuracy of the model and completing the training of the estimation model.

In some alternative implementations of the present embodiment, the snow-ablation optimization algorithm includes an initialization phase that includes the steps of: randomly generating a batch of particles as an initial population, the initial population being represented by the following matrix:

In some alternative implementations of the present embodiment, the snow-ablation optimization algorithm includes an exploration phase that includes the steps of: obtaining Brownian motion step length based on probability density function of normal distribution with mean value of 0 and variance of 1:

In some alternative implementations of the present embodiment, the snow-ablation optimization algorithm includes a mining phase that includes the steps of: the snow melt rate was calculated by the following equation:

the location update of the mining phase is performed by the following formula:

wherein, Representing a random number selected from [ -1,1], in cross terms/>AndWith the help of the current best search agent and the information of the mass center position of the group, the individuals are more likely to utilize the area with more hopeful best solution; the snow ablation algorithm adopts a double-population mechanism, the whole population is randomly divided into two sub-populations with equal size at the early stage of iteration, the whole population is denoted as p, the two sub-populations are denoted as pop1 and pop2 respectively, pop1 is responsible for exploration, pop2 is assigned to be executed and utilized, the two populations are the same in size at first, pop2 is gradually lowered in the subsequent iteration, and pop1 is correspondingly increased; the complete position update equation for the snow ablation algorithm is:

And 203, determining the utilization rate of the emergency stairway of the underground station in the flood scene according to the output of the estimation model.

In this embodiment, the estimation model may directly output an estimated value of the percentage of the passenger flow rate of the underground station in the flood scene, which selects to use the emergency stairs, to the passenger flow rate of the total cross section.

The method provided by the embodiment of the application obtains the main stair facility information, the emergency stair facility information, the passenger information and the flood scene information of the underground station; inputting the acquired main stair facility information, emergency stair facility information, passenger information and flood scene information into a pre-constructed estimation model, wherein the estimation model is used for representing the corresponding relation between the emergency stair facility information, the main stair facility information, the passenger information and the flood scene information of the underground station and the estimated value of the emergency stair utilization rate of the underground station in the flood scene; according to the output of the estimation model, an estimated value of the percentage of the passenger flow of the emergency stairway used by the underground station in the flood scene to the total cross section passenger flow is determined, personnel evacuation can be reasonably arranged by assisting workers, the effective utilization rate of the vertical evacuation facility is improved, and support is provided for safe evacuation of individuals in the underground station in the emergency.

With continued reference to fig. 5, fig. 5 shows a schematic flow chart of a snow ablation optimization algorithm in an application scenario according to an embodiment of the present application, including:

Initialization phase in SAO (Initialization stage)

The initialization phase randomly generates a batch of particles as an initial population. The entire population is typically represented by a matrix of N and Dim columns, where N represents the size of the population and Dim represents the dimension of the solution space.

L and U indicate the lower and upper bounds of the solution space respectively,The random numbers in interval [0,1 ].

Stage of SAO exploration (Exploration stage):

When snow or liquid water converted from snow is converted into steam, the search object exhibits a highly dispersed characteristic due to irregular movement. In this stage, brownian motion can be used to simulate such a random process. For standard brownian motion, the step size is obtained based on a probability density function of a normal distribution with a mean of 0 and a variance of 1. The associated math is expressed as follows:

brownian motion can explore some potential areas in the search space, and can well reflect the diffusion of water vapor particles in the search space. The location update formula during exploration is as follows:

wherein, Represents the t-th iteration of the i-th particle,/>Represents the t +1 iteration of the ith particle,Vector representing random numbers based on gaussian distribution representing brownian motion, sign/>Representing a multiplication item by item,/>Representing the random number between [0,1 ]/>Representing the current optimal solution,/>Is an individual randomly selected from elite population of the population,/>Representing the centroid position of the population. The corresponding mathematical expression is as follows:

And/> Representing the second and third best individuals in the current population, respectively,/>Representing centroid positions of top 50% of individuals with fitness values ranked. In this study, the top 50% of individuals with fitness values ranked are named leaders. Furthermore,/>The calculation can be performed by the following mathematical expression:

N ₁ represents the number of leaders, N ₁ is equal in number to half the overall population size, during each iteration Randomly selecting from the set consisting of the current best solution, the second best individual, the third best individual, and the centroid position of the leader.

Production stage of SAO (Exploitation stage):

the mining phase of SAO is characterized by encouraging search agents to develop high quality solutions around the current best solution when snow is converted to liquid water by melting behavior, rather than expanding with highly dispersed features in the solution space. As one of the most classical snow-melting models, the gradient-day method is used to reflect the snow-melting process. The general form of the method is as follows:

/>

M is snow melting rate, T is daily average temperature, T _max is termination condition, DDF is gradient-day factor, the value range is 0.35 to 0.6, and in each iteration, the mathematical expression of DDF value to be updated is as follows:

in SAO, the snow melt rate is calculated using the following equation:

in the SAO mining phase, the location update equation is as follows:

Representing a random number selected from [ -1,1], which parameter facilitates communication between individuals. At this stage, in the cross term/> And/>With the help of the current best search agent and the information of the centroid position of the population, individuals are more likely to utilize areas where the best solution is more likely to occur.

Dual population mechanism of SAO algorithm (Dual-population mechanism):

To achieve a tradeoff between development and exploration, the SAO algorithm uses a binary population mechanism. Some of the liquid water converted from snow in the natural process of snow ablation may also be converted to steam for the exploration process. That is, over time, the likelihood of an individual performing irregular movements with highly dispersed features increases. The algorithm then gradually trends towards exploring the solution space. The binary population mechanism in the snow ablation optimization algorithm reflects this: at the early stage of the iteration, the whole population is randomly divided into two equal-sized sub-populations. Known as a dual population mechanism. We represent the entire population as p and these two subspecies as pop1 and pop2.pop1 is responsible for the survey, pop2 is assigned to perform the utilization, initially the two populations are the same size, pop2 gradually decreases in subsequent iterations, and pop1 increases in size accordingly.

In summary, the complete position update equation of the snow ablation algorithm is:

Since the whole population is actually a position matrix, the above formula And/>Representing the index of individuals in a set of pop1 and pop2 throughout the location matrix.

With further reference to fig. 6, as an implementation of the method shown in the foregoing drawings, the present application provides an embodiment of a prediction apparatus for selecting a passenger escalator in a station in a flood scene, where the embodiment of the apparatus corresponds to the embodiment of the method shown in fig. 2, and the apparatus may be specifically applied to various electronic devices.

As shown in fig. 6, the prediction apparatus 600 for selecting a passenger escalator in a station in a flood scene according to the present embodiment includes: an acquisition unit 601, an estimation unit 602, and a determination unit 603. The system comprises an acquisition unit, a control unit and a control unit, wherein the acquisition unit is configured to acquire emergency stair facility information, main stair facility information, passenger information and flood scene information of an underground station; the estimating unit is configured to input the acquired emergency stair facility information, main stair facility information, passenger information and flood scene information into a pre-constructed estimating model, wherein the estimating model is used for representing the corresponding relation between the emergency stair facility information, the main stair facility information, the passenger information and the flood scene information of the underground station and the estimated value of the emergency stair utilization rate of the underground station in the flood scene; and the determining unit is configured to determine an estimated value of the percentage of the passenger flow of the emergency stairway selected to be used by the underground station in the flood scene to the total cross section passenger flow according to the output of the estimated model.

In this embodiment, specific processes of the obtaining unit 601, the estimating unit 602, and the determining unit 603 of the prediction apparatus 600 for selecting a passenger escalator in a station in a flood scene may refer to step 201, step 202, and step 203 in the corresponding embodiment of fig. 2.

In some optional implementations of the present embodiment, the apparatus further comprises a simulation unit configured to obtain training sample data and/or test sample data of the estimation model by: constructing a hydrodynamic simulation system of an underground station to obtain flood scene information; constructing a three-dimensional simulation scene of an emergency stair and a main stair node of an underground station based on pedestrian simulation software of the emergency stair facility information, the main stair facility information and a discrete event simulation principle; and adding the simulation object into a three-dimensional simulation scene to simulate, so as to obtain the data set, wherein the data set comprises simulation values of different emergency stair facility information, main stair facility information, passenger information, flood scene information and corresponding emergency stair utilization rate of the underground station.

In some alternative implementations of the present embodiments, the emergency stair facility information, the main stair facility information, the information including emergency stair and main stair skid resistance, emergency stair and main stair height, emergency stair and main stair width, emergency stair and main stair inclination parameters, emergency stair and main stair step height, and emergency stair and main stair layout forms, the passenger information including passenger number, passenger gender, age structure, flood scenario information including water depth, and water flow speed on the emergency stair and main stair; and a simulation unit further configured to: based on the hydrodynamic simulation system, simulating to obtain the water depth and the water flow speed on the emergency stairs and the main stairs; the travelling speed of the passenger under the influence of the flood is determined by the following formula:

Wherein v _i is walking speed, M is Hong Shuili with unit width, a and b are preset constants, D is flood depth, g is gravity acceleration, and v _f is water flow speed on emergency stairs and main stairs; based on the three-dimensional simulation scene, setting the number of passengers, the gender and the age structure of the passengers, and combining the travelling speed of the passengers under the influence of floods to obtain the simulation value of the percentage of the passenger flow of the emergency stairs to the passenger flow of the total cross section.

In some optional implementations of the present embodiment, the apparatus further comprises a model building unit configured to build the estimation model by: obtaining a basic estimation model based on the random forest model, and optimizing the basic estimation model through a snow ablation optimization algorithm; training the optimized model by using the simulation data to obtain an estimated model.

In some optional implementations of the present embodiment, the model building unit is further configured to: initializing a snow ablation optimization algorithm, and setting a value range of optimized parameters, wherein the optimized parameters comprise the number of decision trees and the selected feature number; optimizing the number of decision trees and the selected feature number parameters in the initial estimation model by using a snow ablation optimization algorithm, taking the number of decision trees and the selected feature number parameters as a group of candidate solutions of the snow ablation optimization algorithm, calculating a fitness value, and updating the optimal particles; and obtaining a candidate solution corresponding to an optimal value in an objective function of the snow ablation optimization algorithm through iterative calculation, and taking the obtained candidate solution as the decision tree number and the selected feature number parameter in the estimation model to finish the optimization of the model.

In some optional implementations of the present embodiment, the model building unit is further configured to: obtaining a basic estimation model based on a random forest model, wherein the basic estimation model comprises resampling based on a Bootstrap method, randomly generating N groups of training samples, and generating a decision tree for each group of training samples; when the splitting attribute of each non-leaf node of the decision tree is selected, a random method is used, and M attributes are selected from M sample total attributes to be used as a total attribute set of the current node; machine learning is carried out, and nodes are split in a best classification mode in the selected m attributes; and selecting an average value of N groups of training sample results as an estimation result of the model in the machine learning process.

In some optional implementations of the present embodiment, the model building unit is further configured to: dividing the data set into a training set and a testing set; preprocessing the data in the training set and the testing set, wherein the preprocessing comprises cleaning, standardization, conversion and coding of the data; selecting and extracting the emergency stair and main stair skid resistance, the emergency stair and main stair height, the emergency stair and main stair width, the emergency stair and main stair inclination angle parameters, the emergency stair and main stair step height, the emergency stair and main stair layout form, the number of passengers, the gender of the passengers, the age structure, the water depth and the water flow speed on the emergency stair and the main stair as model input characteristics, and selecting the percentage of the passenger flow of the emergency stair to the passenger flow of the total cross section in the underground station in the flood scene as model output characteristics for training and testing the model; training the model by using a training set, and finding out the best fitting result by continuously adjusting model parameters; and evaluating the model obtained by training by using the test set to verify the generalization capability and performance of the model, optimizing and optimizing the model according to the evaluation result, improving the estimation capability and accuracy of the model and completing the training of the estimation model.

wherein, And/>Representing the second and third best individuals in the current population, respectively,/>Representing centroid position of top 50% individuals of fitness value rank,/>The mathematical expression of (2) is as follows: /(I)

Where N ₁ represents the number of leaders and N ₁ is equal in number to half the overall population size during each iterationRandomly selecting from the set consisting of the current best solution, the second best individual, the third best individual, and the centroid position of the leader.

the location update of the mining phase is performed by the following formula:

Referring now to FIG. 7, there is illustrated a schematic diagram of a computer system 700 suitable for use in implementing a server or terminal of an embodiment of the present application. The server or terminal illustrated in fig. 7 is merely an example, and should not be construed as limiting the functionality and scope of use of the embodiments of the present application.

As shown in fig. 7, the computer system 700 includes a Central Processing Unit (CPU) 701, which can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM) 702 or a program loaded from a storage section 708 into a Random Access Memory (RAM) 703. In the RAM 703, various programs and data required for the operation of the system 700 are also stored. The CPU 701, ROM 702, and RAM 703 are connected to each other through a bus 704. An input/output (I/O) interface 705 is also connected to bus 704.

The following components may be connected to the I/O interface 705: including an input portion 706 such as a keyboard, mouse, etc.; an output portion 707 including a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, a speaker, and the like; a storage section 708 including a hard disk or the like; and a communication section 709 including a network interface card such as a LAN card, a modem, or the like. The communication section 709 performs communication processing via a network such as the internet. The drive 710 is also connected to the I/O interface 705 as needed. A removable medium 711 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 710 as necessary, so that a computer program read therefrom is mounted into the storage section 708 as necessary.

In particular, according to embodiments of the present disclosure, the processes described above with reference to flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method shown in the flowcharts. In such an embodiment, the computer program may be downloaded and installed from a network via the communication portion 709, and/or installed from the removable medium 711. The above-described functions defined in the method of the present application are performed when the computer program is executed by a Central Processing Unit (CPU) 701. It should be noted that the computer readable medium according to the present application may be a computer readable signal medium or a computer readable medium, or any combination of the two. The computer readable medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples of the computer-readable medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In the present application, however, the computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, with the computer-readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.

Computer program code for carrying out operations of the present application may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, smalltalk, C ++ and conventional procedural programming languages, such as the C-language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computer (for example, through the Internet using an Internet service provider).

The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The units involved in the embodiments of the present application may be implemented in software or in hardware. The described units may also be provided in a processor, for example, described as: a processor includes an acquisition unit, an estimation unit, and a determination unit. The names of these units do not constitute a limitation on the unit itself in some cases, and for example, the acquisition unit may also be described as "a unit configured to acquire emergency stairway facility information, main stairway facility information, passenger information, and flood scene information of an underground station".

As another aspect, the present application also provides a computer-readable medium that may be contained in the apparatus described in the above embodiments; or may be present alone without being fitted into the device. The computer readable medium carries one or more programs which, when executed by the apparatus, cause the apparatus to: emergency stair facility information, main stair facility information, passenger information and flood scene information of the underground station are acquired; inputting the acquired emergency stair facility information, main stair facility information, passenger information and flood scene information into a pre-constructed estimation model, wherein the estimation model is used for representing the corresponding relation between the emergency stair facility information, main stair facility information, passenger information and flood scene information of the underground station and the estimated value of the emergency stair utilization rate of the underground station in the flood scene; and determining an estimated value of the percentage of the passenger flow of the emergency stairway selected to be used by the underground station in the flood scene to the passenger flow of the total cross section according to the output of the estimated model.

The above description is only illustrative of the preferred embodiments of the present application and of the principles of the technology employed. It will be appreciated by persons skilled in the art that the scope of the application referred to in the present application is not limited to the specific combinations of the technical features described above, but also covers other technical features formed by any combination of the technical features described above or their equivalents without departing from the inventive concept described above. Such as the above-mentioned features and the technical features disclosed in the present application (but not limited to) having similar functions are replaced with each other.

Claims

1. A prediction method for selecting a station passenger building escalator in a flood scene comprises the following steps:

Emergency stair facility information, main stair facility information, passenger information and flood scene information of the underground station are acquired;

Inputting the acquired emergency stair facility information, main stair facility information, passenger information and flood scene information into a pre-constructed estimation model, wherein the estimation model is used for representing the corresponding relation between the emergency stair facility information, main stair facility information, passenger information and flood scene information of the underground station and the estimated value of the emergency stair utilization rate of the underground station in the flood scene;

And determining an estimated value of the percentage of the passenger flow of the emergency stairway used by the underground station in the flood scene to the total cross section passenger flow according to the output of the estimated model.

2. The method of claim 1, wherein the dataset for constructing the estimation model is obtained by:

constructing a hydrodynamic simulation system of an underground station to obtain flood scene information;

Constructing a three-dimensional simulation scene of an emergency stair and a main stair node of an underground station based on the emergency stair facility information, the main stair facility information and pedestrian simulation software of a discrete event simulation principle, wherein the emergency stair comprises an escalator stopped in a flood scene;

And adding the simulation object into the three-dimensional simulation scene to simulate, so as to obtain the data set, wherein the data set comprises simulation values of different emergency stair facility information, main stair facility information, passenger information, flood scene information and the percentage of the passenger flow of the selected emergency stair to the passenger flow of the total cross section.

3. The method of claim 2, wherein the emergency stair facility information comprises an emergency stair slip, an emergency stair height, an emergency stair width, an emergency stair dip parameter, an emergency stair step height, an emergency stair run form, the main stair facility information comprises a main stair slip, a main stair height, a main stair width, a main stair dip parameter, a main stair step height, and a main stair run form, the passenger information comprises a passenger number, a passenger gender, an age structure, and the flood scenario information comprises a water depth and a water flow speed on an emergency stair and a main stair; and adding the simulation object into the three-dimensional simulation scene for simulation to obtain the data set, wherein the method comprises the following steps of:

Based on the hydrodynamic simulation system, simulating to obtain the water depth and the water flow speed on the emergency stairs and the main stairs;

the travelling speed of the passenger under the influence of the flood is determined by the following formula:

；

Wherein v _i is walking speed, M is Hong Shuili with unit width, a and b are preset constants, D is flood depth, g is gravity acceleration, and v _f is water flow speed on emergency stairs and main stairs;

Based on the three-dimensional simulation scene, setting the number of passengers, the gender of the passengers and the age structure, and combining the travelling speed of the passengers under the influence of floods to obtain the simulation value of the percentage of the passenger flow of the emergency stairs to the total cross section passenger flow.

4. The method of claim 2, wherein the estimation model is constructed by:

obtaining a basic estimation model based on the random forest model;

Optimizing the basic estimation model through a snow ablation optimization algorithm;

training the optimized model by using the simulation data to obtain the estimation model.

5. The method of claim 4, wherein the deriving a base estimation model based on a random forest model comprises:

Resampling based on a Bootstrap method, randomly generating N groups of training samples, and generating a decision tree for each group of training samples;

When the splitting attribute of each non-leaf node of the decision tree is selected, a random method is used, and M attributes are selected from M sample total attributes to be used as a total attribute set of the current node;

machine learning is carried out, and nodes are split in a best classification mode in the selected m attributes;

and selecting an average value of N groups of training sample results as an estimation result of the model in the machine learning process.

6. The method of claim 4, wherein the optimizing the base estimation model by a snow-ablation optimization algorithm comprises:

Initializing a snow ablation optimization algorithm, and setting a value range of optimized parameters, wherein the optimized parameters comprise the number of decision trees and the selected feature numbers in a basic estimation model;

Optimizing the number of decision trees and the selected feature number parameters in the basic estimation model by using a snow ablation optimization algorithm, taking the number of decision trees and the selected feature number parameters as a group of candidate solutions of the snow ablation optimization algorithm, calculating a fitness value, and updating optimal particles;

And obtaining a candidate solution corresponding to an optimal value in an objective function of the snow ablation optimization algorithm through iterative calculation, and taking the obtained candidate solution as the decision tree number and the selected feature number parameter in the estimation model to finish the optimization of the model.

7. The method of claim 4, wherein training the optimized model with simulation data results in the estimated model, comprising:

dividing the data set into a training set and a testing set;

preprocessing data in the training set and the testing set, wherein the preprocessing comprises cleaning, standardization, conversion and coding of the data;

Selecting and extracting the emergency stairway and main stairway skid resistance, the emergency stairway and main stairway height, the emergency stairway and main stairway width, the emergency stairway and main stairway inclination angle parameters, the emergency stairway and main stairway step height, the emergency stairway and main stairway layout form, the number of passengers, the gender of the passengers, the age structure, the water depth and the water flow speed on the emergency stairway and main stairway as model input characteristics, and selecting the percentage of the passenger flow of the emergency stairway to the passenger flow of the total cross section as model output characteristics for training and testing the model at the underground station under the flood scene;

training the model by using a training set, and finding out the best fitting result by continuously adjusting model parameters;

And evaluating the model obtained by training by using the test set to verify the generalization capability and performance of the model, optimizing and optimizing the model according to the evaluation result, improving the estimation capability and accuracy of the model and completing the training of the estimation model.

8. The method of claim 6, wherein the snow-ablation optimization algorithm includes an initialization phase comprising the steps of:

Randomly generating a batch of particles as an initial population, the initial population represented by the following matrix:

；

wherein Z represents a matrix of the initial population, N represents a size of the population, dim represents a dimension of the solution space, L and U respectively indicate a lower bound and an upper bound of the solution space, The random numbers in interval [0,1 ].

9. The method of claim 8, wherein the snow ablation optimization algorithm includes an exploration phase comprising the steps of:

obtaining Brownian motion step length based on probability density function of normal distribution with mean value of 0 and variance of 1:

；

10. The method of claim 9, wherein the snow-ablation optimization algorithm includes a mining phase comprising the steps of:

the snow melt rate was calculated by the following equation:

；

the location update of the mining phase is performed by the following formula:

；

wherein, Representing a random number selected from [ -1,1], in cross terms/>AndWith the help of the current best search agent and the information of the mass center position of the group, the individuals are more likely to utilize the area with more hopeful best solution; and

The snow ablation optimization algorithm adopts a double-population mechanism, the whole population is randomly divided into two sub-populations with equal size at the early stage of iteration, the whole population is denoted as p, the two sub-populations are denoted as pop1 and pop2 respectively, pop1 is responsible for exploration, pop2 is assigned to be executed and utilized, the two populations are the same in size at first, pop2 is gradually lowered in the subsequent iteration, and pop1 is correspondingly increased; the complete position update equation of the snow ablation optimization algorithm is as follows:

；

11. A predictive device for station passenger escalator selection in flood scenes, comprising:

An acquisition unit configured to acquire emergency stair facility information, main stair facility information, passenger information, and flood scene information of an underground station;

An estimation unit configured to input the acquired emergency stair facility information, main stair facility information, passenger information, and flood scene information to a pre-constructed estimation model, wherein the estimation model is used for representing a correspondence between the emergency stair facility information, main stair facility information, passenger information, and flood scene information of the underground station and a percentage of passenger traffic of a selected use emergency stair to total cross-section passenger traffic;

and the determining unit is configured to determine an estimated value of the percentage of the passenger flow of the emergency stairway used by the underground station in the flood scene to the total cross section passenger flow according to the output of the estimated model.