CN-122022569-A - Emergency deduction method, system, medium and product for severe weather of rail transit

CN122022569ACN 122022569 ACN122022569 ACN 122022569ACN-122022569-A

Abstract

A method, a system, a medium and a product for emergency deduction in severe weather of rail transit relate to the technical field of data processing. In the method, real-time weather and operation data are acquired, and an initial toughness score is calculated through a preset toughness evaluation index system. And (3) establishing a dynamic coupling model by combining weather forecast data, and calculating toughness score change through time step deduction. When the toughness change rate exceeds the threshold, the system automatically adjusts the operating parameters and updates the score. And identifying critical time and corresponding conditions when the toughness score is lower than the threshold value for the first time from the deduction result, and screening candidate emergency schemes from the strategy library according to the critical time and the corresponding conditions. And finally, evaluating the toughness recovery effect of each candidate strategy by utilizing a genetic algorithm, and selecting an optimal emergency strategy. By implementing the technical scheme provided by the application, the emergency decision accuracy of the rail transit can be improved.

Inventors

Lin Bingpiao
CHEN LINJUN

Assignees

北京知达客信息技术有限公司

Dates

Publication Date: 20260512
Application Date: 20260121

Claims (10)

1. A method for emergency deduction of severe weather in rail transit, the method comprising: Acquiring real-time meteorological data and real-time operation data of rail transit; calculating an initial toughness score through a preset toughness assessment index system based on the real-time meteorological data and the real-time operation data, wherein the preset toughness assessment index system comprises equipment toughness dimension, passenger flow toughness dimension and line toughness dimension; Acquiring weather forecast data, and establishing a dynamic coupling model based on the weather forecast data; based on the initial toughness score and the weather forecast data, deducting according to time steps through the dynamic coupling model, calculating a toughness score and a toughness change rate at each time step, adjusting operation parameters when the toughness change rate exceeds a change rate threshold value, and reversely updating the toughness score through the dynamic coupling model to obtain a deduction result; extracting the moment when the toughness score is lower than a toughness threshold value for the first time from the deduction result as a toughness critical moment, and acquiring meteorological conditions and a target toughness score corresponding to the toughness critical moment; screening candidate emergency strategies from an emergency strategy library based on the meteorological conditions and the target toughness scores; And re-deducting from the critical moment of toughness through the dynamic coupling model aiming at each candidate emergency strategy to obtain a toughness scoring sequence, calculating a toughness recovery effect index by adopting a genetic algorithm based on the toughness scoring sequence, and selecting an optimal emergency strategy.
2. The method of claim 1, wherein calculating an initial toughness score based on the real-time weather data and the real-time operational data by a preset toughness assessment index system comprises: based on the wind speed and the temperature in the real-time meteorological data, calculating a wind resistance stability coefficient of a power supply system and a vehicle braking performance attenuation rate in the toughness dimension of the equipment as toughness indexes; Determining the fault recovery time length of the signal system as a toughness index based on equipment fault records in the real-time operation data; based on the station passenger flow and the transfer passenger flow in the real-time operation data, calculating station evacuation efficiency, the detention number ratio and the overline transfer bearing rate in the passenger flow toughness dimension as toughness indexes; Calculating the traffic capacity reduction rate, the fault influence range and the line recovery time in the line toughness dimension as toughness indexes based on the wind speed and the precipitation amount in the real-time meteorological data and the train running speed in the real-time running data; And carrying out normalization processing on each toughness index and carrying out weighted summation on preset weights corresponding to each toughness index to obtain the initial toughness score.
3. The method of claim 2, wherein the establishing a dynamic coupling model based on the weather forecast data comprises: extracting a meteorological parameter time sequence in the meteorological prediction data, wherein the meteorological parameter time sequence comprises a wind speed sequence, a precipitation sequence and a temperature sequence; Determining a mapping relation between the meteorological parameter time sequence and each toughness index based on the toughness evaluation index system, and determining a feedback adjustment relation between each toughness index and operation parameters, wherein the operation parameters comprise train running speed and departure interval; and cascading and combining the mapping relation as a forward propagation module and the feedback adjustment relation as a reverse adjustment module to construct the dynamic coupling model.
4. The method of claim 1, wherein the deriving by the dynamic coupling model in time steps based on the initial toughness score and the weather forecast data, calculating a toughness score and a toughness change rate at each time step, adjusting operating parameters when the toughness change rate exceeds a threshold, and updating the toughness score by the dynamic coupling model in reverse, comprises: For the current time step, weather forecast data of a moment corresponding to the current time step are extracted, the weather forecast data are input into the dynamic coupling model, and the influence quantity of the weather forecast data on each toughness index is determined; updating each toughness index based on the influence quantity, and carrying out weighted summation on each updated toughness index to obtain a toughness score of the corresponding moment of the current time step; Calculating the toughness change rate based on the toughness score of the moment corresponding to the current time step and the toughness score of the previous moment; when the absolute value of the toughness change rate is larger than a change rate threshold value, extracting an index item with the largest toughness index reduction in the toughness evaluation index system; Calculating an operation parameter adjustment coefficient according to the toughness change rate and the index item, and adjusting the operation parameter of the moment corresponding to the current time step based on the operation parameter adjustment coefficient; Inputting the adjusted operation parameters into the dynamic coupling model, reversely calculating the improvement quantity of each toughness index in the toughness evaluation index system, compensating each toughness index based on the improvement quantity, and carrying out weighted summation on each compensated toughness index to obtain the target toughness score of the current time step.
5. The method of claim 1, wherein the screening candidate emergency policies from an emergency policy library based on the meteorological conditions and the target toughness score comprises: Extracting applicable scene parameters of each emergency strategy from the emergency strategy library, wherein the applicable scene parameters comprise a meteorological condition range, a meteorological type and a toughness scoring applicable interval; matching the weather type corresponding to the weather condition with the weather type of each emergency strategy, and determining initial candidate emergency strategies of the same weather type; judging whether the meteorological conditions fall into the meteorological condition range of each initial candidate emergency strategy; judging whether the target toughness scores fall into the toughness score applicable intervals of the initial candidate emergency strategies or not; And if the meteorological conditions fall into the meteorological condition range of the initial candidate emergency strategy and the target toughness score falls into the toughness score applicable range of the initial candidate emergency strategy, taking the initial candidate emergency strategy as a final candidate emergency strategy.
6. The method of claim 1, wherein calculating a toughness recovery effect index and selecting an optimal contingency strategy using a genetic algorithm based on the toughness scoring sequence comprises: Extracting strategy parameters of the candidate emergency strategies aiming at each candidate emergency strategy, wherein the strategy parameters comprise a speed limit value, a diversion line, a temporary shutdown site and evacuation capacity parameters; Taking the strategy parameters as constraint conditions of operation parameters, and re-executing a deduction process from the toughness critical moment through the dynamic coupling model to obtain a toughness scoring sequence after the candidate emergency strategy is implemented; Calculating a recovery time period required for recovering the toughness score from the toughness critical moment to above the toughness threshold value based on the toughness score sequence; calculating an integral area surrounded by a toughness grading curve and a time axis in a recovery process in the toughness grading sequence; taking the recovery time length and the integral area as input parameters, and carrying out population iteration through a preset genetic algorithm to obtain an adaptability value of the candidate emergency strategy; And selecting the candidate emergency strategy with the highest fitness value as the optimal emergency strategy.
7. The method of claim 1, wherein after selecting the optimal contingency strategy, further comprising: Based on the optimal emergency strategy, extracting a time period with the toughness score lower than the toughness threshold value in the toughness score sequence as an emergency response time window; Generating a staged execution scheme in the emergency response time window according to the strategy parameters of the optimal emergency strategy, wherein the staged execution scheme comprises a preparation stage, an implementation stage and a recovery stage time node and corresponding operation adjustment instructions; determining the type and the quantity of emergency resources to be allocated at each stage in the staged execution scheme based on the change distribution of each toughness index in the toughness evaluation index system; Integrating the staged execution scheme with the types and the quantity of emergency resources to be allocated in each stage, generating an emergency plan document, and issuing the emergency plan document to the dispatching personnel of the rail transit.
8. A rail transit inclement weather emergency deduction system comprising one or more processors and a memory coupled to the one or more processors, the memory to store computer program code comprising computer instructions that the one or more processors invoke to cause the rail transit inclement weather emergency deduction system to perform the method of any one of claims 1-7.
9. A computer readable storage medium comprising instructions which, when run on a rail transit severe weather emergency deduction system, cause the rail transit severe weather emergency deduction system to perform the method of any one of claims 1-7.
10. A computer program product, characterized in that the computer program product, when run on a rail transit severe weather emergency deduction system, causes the rail transit severe weather emergency deduction system to perform the method of any one of claims 1-7.

Description

Emergency deduction method, system, medium and product for severe weather of rail transit Technical Field The application relates to the technical field of data processing, in particular to a method, a system, a medium and a product for emergency deduction in severe weather of rail transit. Background With the continuous advancement of the urban process, rail transit has become an important support for the public travel of modern cities. Under the high-density urban environment, the rail transit system forms a complex networked operation system through interconnection of a plurality of lines, so that emergency deduction in severe weather becomes a key subject of rail transit operation. At present, a scene simulation mode is generally adopted by a rail transit operation unit to carry out emergency deduction of severe weather. These deductions simulate the operation state of the system by constructing a typical weather scene, and the expert team makes a study and judgment on the possible system influence based on experience. When extreme weather is predicted, operators can take corresponding emergency measures according to the deduction result. However, in practical applications, as the rail transit network is continuously expanded, the influence of severe weather on the system presents high dynamics and uncertainty. In this case, it is difficult to accurately reflect the real-time change of the system state by only static deduction of the preset scene. Particularly, when the system is faced with variable meteorological conditions, due to lack of deep analysis on actual operation data of the system, a large deviation exists between a deduction result and an actual situation, and the accuracy of emergency decision is reduced. Disclosure of Invention The application provides a method, a system, a medium and a product for emergency deduction in severe weather of rail transit, which can improve the accuracy of emergency decision of the rail transit. In a first aspect of the application, a method for emergency deduction of severe weather of rail transit is provided, comprising the following steps: Acquiring real-time meteorological data and real-time operation data of rail transit; calculating an initial toughness score through a preset toughness assessment index system based on the real-time meteorological data and the real-time operation data, wherein the preset toughness assessment index system comprises equipment toughness dimension, passenger flow toughness dimension and line toughness dimension; Acquiring weather forecast data, and establishing a dynamic coupling model based on the weather forecast data; based on the initial toughness score and the weather forecast data, deducting according to time steps through the dynamic coupling model, calculating a toughness score and a toughness change rate at each time step, adjusting operation parameters when the toughness change rate exceeds a change rate threshold value, and reversely updating the toughness score through the dynamic coupling model to obtain a deduction result; extracting the moment when the toughness score is lower than a toughness threshold value for the first time from the deduction result as a toughness critical moment, and acquiring meteorological conditions and a target toughness score corresponding to the toughness critical moment; screening candidate emergency strategies from an emergency strategy library based on the meteorological conditions and the target toughness scores; And re-deducting from the critical moment of toughness through the dynamic coupling model aiming at each candidate emergency strategy to obtain a toughness scoring sequence, calculating a toughness recovery effect index by adopting a genetic algorithm based on the toughness scoring sequence, and selecting an optimal emergency strategy. By adopting the technical scheme, the real-time meteorological data and real-time operation data of the rail transit are obtained, the initial toughness score is calculated based on the multi-dimensional toughness evaluation index system, and the dynamic coupling model is built by combining with the meteorological prediction data, so that the operation state of the system in severe weather can be reflected in real time. By deducting according to time step length, the toughness score and the toughness change rate are calculated in real time, when the toughness change rate exceeds a threshold value, the operation parameters are dynamically adjusted, the toughness score is reversely updated, and the dynamic change process of the system state can be accurately simulated. And the critical moment that the toughness score is lower than the threshold value for the first time is extracted, candidate emergency strategies are screened based on the meteorological conditions and the target toughness score at the moment, the candidate strategies are evaluated and optimized by combining a genetic algorithm, and the optimal emergency strategy is finally