CN-115392689-B - Dynamic detection method and device for security risk of ancient building

CN115392689BCN 115392689 BCN115392689 BCN 115392689BCN-115392689-B

Abstract

The invention discloses a dynamic detection method and device for the security risk of an ancient building, wherein the method comprises the steps of obtaining first influence indexes of various factors of the risk of the ancient building to be detected, constructing a disaster-causing factor set and an evaluation factor set according to the first influence indexes, determining influence factors of the ancient building to be detected and second influence indexes of the influence factors of the ancient building to be detected according to the disaster-causing factor set and the evaluation factor set, determining conditional probability of the second influence indexes, calculating probability distribution results of the second influence indexes based on the conditional probability of the second influence indexes and observation values of the second influence indexes, updating the probability distribution results, detecting the risk of the ancient building to be detected according to the updated probability distribution results, and obtaining risk detection results of the ancient building to be detected. The invention can predict the future safety of the evaluation area.

Inventors

PAN RUI
CHEN JIANGUO
YU SHUIPING
WANG XIAOMENG
LIU CHUNHUI
ZHANG HENG
SUN ZHANHUI
YUAN HONGYONG
HU JUN
TIAN FENGSHI
HUANG LIDA
HUANG MENGYAO
CHEN TAO

Assignees

清华大学
北京辰安科技股份有限公司

Dates

Publication Date: 20260505
Application Date: 20220823

Claims (6)

1. The dynamic detection method for the historic building safety risk is characterized by comprising the following steps of: Acquiring a first influence index of a plurality of factors of the ancient building risk to be detected, and constructing a disaster causing factor set and an evaluation factor set according to the first influence index, wherein the first influence index comprises a risk index of an artificial, an object and an environmental factor and a management evaluation index of a management factor; Determining influence factors of the ancient building to be detected and second influence indexes of the influence factors of the ancient building to be detected according to the disaster causing factor set and the evaluation factor set, and determining conditional probability of the second influence indexes, wherein the second influence indexes comprise father nodes and child nodes of various factors; calculating a probability distribution result of the second influence index based on the conditional probability of the second influence index and the observed value of the second influence index; Updating the probability distribution result, and detecting the risk of the ancient building to be detected according to the updated probability distribution result to obtain a risk detection result of the ancient building to be detected; Further comprises: The method comprises the steps of classifying static risks, semi-dynamic risks and dynamic risks, encoding building entities and bearing objects in the ancient building to be detected according to classification results, establishing a characteristic parameter library of the ancient building to be detected, obtaining risk occurrence probability based on the risk detection results and the characteristic parameter library, optimizing indexes of various factors according to the risk occurrence probability to obtain an index optimization result, sorting various factor combinations based on the index optimization result to obtain a factor combination sorting result, and determining the risk condition of the ancient building to be detected according to the factor combination sorting result.
2. The method of claim 1, wherein the probability distribution result of the second impact indicator is calculated by the following formula: Wherein, the I.e. In order to be the state of the node set, Is that Is used to determine the state of the parent node of (c), Representing the state as parent node Under the condition of (1), the child node state is Conditional probability at that time.
3. The method of claim 1, wherein the detecting the risk of the ancient building to be detected according to the updated probability distribution result includes the following calculation formula of the risk detection result of the ancient building to be detected: Wherein, the For the posterior probability of a fire, As a new evidence of the fact that, In order to be a conditional probability of a probability, Is a priori probability.
4. The utility model provides a ancient building safety risk dynamic detection device which characterized in that includes: The system comprises an index acquisition module, a disaster-causing factor set and an evaluation factor set, wherein the index acquisition module is used for acquiring a first influence index of various factors of the risk of the ancient building to be detected and constructing the disaster-causing factor set and the evaluation factor set according to the first influence index; The probability determining module is used for determining the influence factors of the ancient building to be detected and the second influence indexes of the influence factors of the ancient building to be detected according to the disaster causing factor set and the evaluation factor set, and determining the conditional probability of the second influence indexes, wherein the first influence indexes comprise risk indexes of people, objects and environmental factors and management evaluation indexes of management factors; The index calculation module is used for calculating a probability distribution result of the second influence index based on the conditional probability of the second influence index and the observed value of the second influence index, wherein the second influence index comprises father nodes and child nodes of various factors; the risk detection module is used for updating the probability distribution result, detecting the risk of the ancient building to be detected according to the updated probability distribution result, and obtaining a risk detection result of the ancient building to be detected; The parameter library establishing module is used for establishing a characteristic parameter library of the ancient building to be detected by classifying the static risk, the semi-dynamic risk and the dynamic risk and encoding building entities and bearing objects in the ancient building to be detected according to classification results; The index optimization module is used for obtaining risk occurrence probability based on the risk detection result and the characteristic parameter library, and optimizing indexes of the multiple factors according to the risk occurrence probability to obtain an index optimization result; and the combination ordering module is used for ordering the multiple factor combinations based on the index optimization result to obtain a factor combination ordering result, and determining the historic building risk condition to be detected according to the factor combination ordering result.
5. The apparatus of claim 4, wherein the probability distribution result of the second impact indicator of the probability determination module is calculated by the formula: Wherein, the I.e. In order to be the state of the node set, Is that Is used to determine the state of the parent node of (c), Representing the state as parent node Under the condition of (1), the child node state is Conditional probability at that time.
6. The apparatus of claim 5, wherein the risk detection module has a calculation formula: Wherein, the For the posterior probability of a fire, As a new evidence of the fact that, In order to be a conditional probability of a probability, Is a priori probability.

Description

Dynamic detection method and device for security risk of ancient building Technical Field The invention relates to the technical field of risk detection, in particular to a dynamic detection method and device for security risk of an ancient building. Background The ancient architecture is mostly wood structure, brick wood structure, and the performance of resisting risks such as fire prevention antidetonation is relatively poor, but along with the purpose such as the ancient architecture is constantly developed and is used for tourism visit and cultural development inheritance, electrical equipment such as valuable relics, circular telegram communication are constantly extended, the weather becomes warm and leads to temperature to rise, abnormal bad weather such as heavy rain lightning increases, personnel factors such as manager and visitor are constantly increased, behaviors such as incense and praying are difficult to avoid, management complexity is constantly aggravated, and consequently, factors in each aspect of personage's ring canal all make the risk of ancient architecture high. Disclosure of Invention The present invention aims to solve at least one of the technical problems in the related art to some extent. For this purpose, the evaluation process of the invention obtains dynamic BN topologies of different time periods corresponding to the coupled BN model. The invention provides a dynamic evaluation method for optimizing the risk management of the historic building system, and the future safety of an evaluation area can be predicted. In order to achieve the above objective, in one aspect, the present invention provides a method for dynamically detecting security risk of ancient architecture, comprising: acquiring a first influence index of a plurality of factors of the ancient building risk to be detected, and constructing a disaster causing factor set and an evaluation factor set according to the first influence index; determining influence factors of the ancient building to be detected and a second influence index of the influence factors of the ancient building to be detected according to the disaster causing factor set and the evaluation factor set, and determining the conditional probability of the second influence index; calculating a probability distribution result of the second influence index based on the conditional probability of the second influence index and the observed value of the second influence index; updating the probability distribution result, and detecting the risk of the ancient building to be detected according to the updated probability distribution result to obtain a risk detection result of the ancient building to be detected. In addition, the method for dynamically detecting the security risk of the ancient architecture according to the above embodiment of the present invention may further have the following additional technical features: Further, in one embodiment of the invention, the first impact index comprises a risk index of an artificial, an object and an environmental factor and a management evaluation index of a management factor, the disaster-causing factor set comprises a static risk, a semi-dynamic risk and a dynamic risk, and the second impact index comprises father nodes and child nodes of a plurality of factors. Further, in an embodiment of the present invention, a calculation formula of the probability distribution result of the second impact indicator is: Wherein ,[A1,A2,A3,...,An,B1,B2,B3,...,Bn,C1,C2,C3,...,Cn,D1,D2,D3,...,Dn] is the state of node set, P a(Xi) is the state of the parent node of X i, and P (X i|Pa(Xi)) represents the conditional probability when the child node state is X i under the condition that the parent node state is P a(Xi). Further, in an embodiment of the present invention, the detecting the risk of the ancient building to be detected according to the updated probability distribution result, and the calculation formula of the risk detection result of the ancient building to be detected is: Wherein, P (U|E) is the posterior probability of fire, P (E) is new evidence, P (E|U) is conditional probability, and P (U) is prior probability. Further, in one embodiment of the invention, the method further comprises the steps of classifying the static risk, the semi-dynamic risk and the dynamic risk, encoding building entities and carriers in the ancient building to be detected according to classification results, establishing a characteristic parameter library of the ancient building to be detected, obtaining risk occurrence probability based on the risk detection results and the characteristic parameter library, optimizing indexes of the multiple factors according to the risk occurrence probability to obtain an index optimization result, sorting the multiple factor combinations based on the index optimization result to obtain a factor combination sorting result, and determining the risk condition of the ancient building to be detect