A method and device for dynamic detection of safety risks in ancient buildings

Abstract

This invention discloses a method and apparatus for dynamic detection of safety risks of ancient buildings. The method includes: acquiring first influencing indicators of multiple factors affecting the risk of the ancient building to be detected; constructing a set of disaster-causing factors and a set of assessment factors based on the first influencing indicators; determining the influencing factors of the ancient building to be detected and second influencing indicators of these factors based on the disaster-causing factors and assessment factors, and determining the conditional probability of the second influencing indicators; calculating the probability distribution of the second influencing indicators based on their conditional probabilities and observed values; updating the probability distribution; and detecting the risk of the ancient building to be detected based on the updated probability distribution to obtain the risk detection result. This invention can predict and assess the future safety of an area.

Description

Technical Field

[0001] This invention relates to the field of risk detection technology, and in particular to a method and device for dynamic detection of safety risks in ancient buildings. Background Technology

[0002] Ancient buildings are mostly made of wood or brick and wood, which have poor resistance to fire and earthquakes. However, as ancient buildings are continuously developed for tourism and cultural preservation, the number of valuable cultural relics and electrical equipment such as electricity and communications is constantly increasing. Climate change is causing rising temperatures and more severe weather such as rainstorms and lightning. The number of human factors, such as managers and tourists, is also increasing. Activities such as burning incense and worshipping Buddha are unavoidable. The complexity of management is constantly increasing. Therefore, all factors, including people, environment, and management, make the risks of ancient buildings remain high. Summary of the Invention

[0003] The present invention aims to at least partially solve one of the technical problems in the related art.

[0004] Therefore, the evaluation process of this invention is coupled with a BN model to obtain dynamic BN topologies for different time periods. This invention provides a dynamic evaluation method for optimizing the risk management of ancient building systems, and can predict the future safety of the evaluation area.

[0005] To achieve the above objectives, this invention proposes a dynamic detection method for the safety risks of ancient buildings, comprising:

[0006] Obtain the first impact indicators of multiple factors affecting the risk of the ancient building to be detected, and construct a set of disaster-causing factors and a set of assessment factors based on the first impact indicators;

[0007] Based on the disaster-causing factor set and the assessment factor set, determine the influencing factors of the ancient building to be tested and the second influencing index of the influencing factors of the ancient building to be tested, and determine the conditional probability of the second influencing index;

[0008] Based on the conditional probability of the second influence index and the observed value of the second influence index, the probability distribution of the second influence index is calculated.

[0009] The probability distribution result is updated, and the risk of the ancient building to be detected is detected based on the updated probability distribution result to obtain the risk detection result of the ancient building to be detected.

[0010] In addition, the dynamic detection method for safety risks of ancient buildings according to the above embodiments of the present invention may also have the following additional technical features:

[0011] Furthermore, in one embodiment of the present invention, the first impact indicator includes risk indicators of human, object, and environmental factors and management assessment indicators of management factors; the disaster-causing factor set includes static risk, semi-dynamic risk, and dynamic risk; the second impact indicator includes parent nodes and child nodes of multiple factors.

[0012] Furthermore, in one embodiment of the present invention, the formula for calculating the probability distribution result of the second influencing index is as follows:

[0013]

[0014] Among them, [A1,A2,A3,...,A n ,B1,B2,B3,...,B n C1, C2, C3, ..., C n ,D1,D2,D3,...,D n That is, U is the state of the node set, P a (X i ) is X i The state of the parent node, P(X) i |P a (X i )) indicates that the parent node is in state P. a (X i Under the condition that the child node's state is X i The conditional probability at that time.

[0015] Furthermore, in one embodiment of the present invention, the calculation formula for detecting the risk of the ancient building to be detected based on the updated probability distribution results, and obtaining the risk detection result of the ancient building to be detected, is as follows:

[0016]

[0017] Where P(U|E) is the posterior probability of the fire, P(E) is the new evidence, P(E|U) is the conditional probability, and P(U) is the prior probability.

[0018] Furthermore, in one embodiment of the present invention, the method further includes: classifying the static risks, semi-dynamic risks, and dynamic risks; encoding the building entities and load-bearing structures in the ancient building to be detected according to the classification results; establishing a feature parameter library for the ancient building to be detected; obtaining the probability of risk occurrence based on the risk detection results and the feature parameter library; optimizing the indicators of the multiple factors according to the probability of risk occurrence to obtain indicator optimization results; ranking the combinations of multiple factors based on the indicator optimization results to obtain a factor combination ranking result; and determining the risk status of the ancient building to be detected based on the factor combination ranking result.

[0019] To achieve the above objectives, another aspect of the present invention provides a dynamic detection device for the safety risks of ancient buildings, comprising:

[0020] The indicator acquisition module is used to acquire the first impact indicators of various factors affecting the risk of the ancient building to be detected, and to construct a disaster-causing factor set and an assessment factor set based on the first impact indicators.

[0021] The probability determination module is used to determine the influencing factors of the ancient building to be tested and the second influencing index of the influencing factors of the ancient building to be tested based on the disaster-causing factor set and the evaluation factor set, and to determine the conditional probability of the second influencing index.

[0022] The indicator calculation module is used to calculate the probability distribution result of the second influence indicator based on the conditional probability of the second influence indicator and the observed value of the second influence indicator;

[0023] The risk detection module is used to update the probability distribution results, and to detect the risk of the ancient building to be detected based on the updated probability distribution results, so as to obtain the risk detection result of the ancient building to be detected.

[0024] The method and apparatus for dynamic detection of safety risks of ancient buildings according to embodiments of the present invention can predict and assess the future safety of a region.

[0025] Additional aspects and advantages of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. Attached Figure Description

[0026] The above and / or additional aspects and advantages of the present invention will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein:

[0027] Figure 1 This is a flowchart of a dynamic detection method for safety risks of ancient buildings according to an embodiment of the present invention;

[0028] Figure 2 This is a framework diagram for MEMM ancient building risk analysis according to an embodiment of the present invention;

[0029] Figure 3 This is a flowchart of the risk assessment process for ancient buildings according to an embodiment of the present invention;

[0030] Figure 4 This is a framework diagram for fire risk assessment of ancient buildings according to an embodiment of the present invention;

[0031] Figure 5 This is a schematic diagram illustrating the risk classification of ancient buildings according to an embodiment of the present invention;

[0032] Figure 6This is a schematic diagram illustrating another risk classification of ancient buildings according to an embodiment of the present invention;

[0033] Figure 7 A fire protection rating GIS map according to an embodiment of the present invention;

[0034] Figure 8 This is a schematic diagram of the structure of the dynamic detection device for safety risks of ancient buildings according to an embodiment of the present invention. Detailed Implementation

[0035] It should be noted that, unless otherwise specified, the embodiments and features described in the present invention can be combined with each other. The present invention will now be described in detail with reference to the accompanying drawings and embodiments.

[0036] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0037] The following description, with reference to the accompanying drawings, describes a method and apparatus for dynamic detection of safety risks in ancient buildings according to embodiments of the present invention.

[0038] Figure 1 This is a flowchart of the dynamic detection method for safety risks of ancient buildings according to an embodiment of the present invention.

[0039] like Figure 1 As shown, the method includes, but is not limited to, the following steps:

[0040] S1, obtain the first impact indicators of multiple factors of the risk of the ancient building to be detected, and construct the disaster-causing factor set and the assessment factor set based on the first impact indicators;

[0041] S2, based on the disaster-causing factor set and the assessment factor set, determine the influencing factors of the ancient building to be tested and the second influencing index of the influencing factors of the ancient building to be tested, and determine the conditional probability of the second influencing index;

[0042] S3, Based on the conditional probability of the second influence index and the observed value of the second influence index, calculate the probability distribution result of the second influence index;

[0043] S4, Update the probability distribution results, and conduct risk detection on the ancient building to be detected based on the updated probability distribution results to obtain the risk detection results of the ancient building to be detected.

[0044] The embodiments of the present invention will now be described in detail with reference to the accompanying drawings.

[0045] Specifically, this invention categorizes the risks of ancient buildings into four aspects: Man, Materials, Environment, and Management. The "Man-Materials-Environment" factors are triggering factors, while the "Management" factors are intervention factors. This is achieved through the MEMM ancient building risk analysis framework, such as... Figure 2 As shown.

[0046] Furthermore, such as Figure 3 As shown, an initial assessment layer is formed based on factors such as ancient buildings, vegetation, and rivers. Building upon this, a "material" impact assessment layer is formed by considering the layout of fixed assets, including the type of cultural relic, building structure, and electrical connection methods. Environmental factors such as weather, time of day, and season are then introduced to form a "material + environment" impact assessment layer. Subsequently, "human" characteristics are embedded to form a "material + environment + human" impact assessment layer. Next, "management" factors are superimposed to form a "material + environment + human + management" impact assessment layer, after which dynamic adjustments are made. Internally, adjustments are made to management resources oriented towards "human" or layout adjustments towards "material," while externally, management policies oriented towards "human" are adjusted. After multiple rounds of internal and external adjustments, a management assessment result under the influence of "material, environment, human, and management" is finally formed.

[0047] Furthermore, the sequential superposition of factors such as objects, environment, and people constitutes the static, semi-dynamic, and dynamic systems of ancient architecture, such as... Figure 3 As shown, this leads to static, semi-dynamic, and dynamic risks associated with ancient buildings. Clearly defining and classifying these risk characteristics will greatly facilitate the subsequent establishment of a feature coding library.

[0048] Static risks (Materials): The static risks of ancient buildings mainly concern the building structure and its load-bearing structures. The building structure possesses spatial characteristics such as its footprint and functional zoning. The artifacts displayed inside, including porcelain, ironware, calligraphy, paintings, and clay sculptures, along with the display cases that house and protect these artifacts, and the fire prevention, security, and electrical equipment, collectively constitute the load-bearing structure. The building structure, its load-bearing structures, and their layout together form the static system of the ancient building, and the risks inherent in this static system are termed static risks.

[0049] The static risks of ancient buildings are not static, but relatively static. The risks to the physical structure of an ancient building will change slowly over time. The load-bearing structure of an ancient building may be affected by the need for exhibitions, such as the movement of cultural relics, display cases, electrical equipment, etc., or the adjustment of the layout. All of these changes will alter the static risks of the ancient building, but overall, these changes are slow and occasional.

[0050] Semi-dynamic risks (Environment): The semi-dynamic risks of ancient buildings mainly refer to the risks caused by environmental factors, including the impact of meteorological, vegetation, and water system factors on the static system of the ancient building. Meteorological factors include temperature, humidity, rainfall, lightning, and wind. Vegetation factors include vegetation coverage, vegetation type, and vegetation height. Water system factors include water system distance and layout.

[0051] The methods used here to characterize environmental factors typically involve collecting data on the impact of meteorological, vegetation, and water system factors on the static system of ancient buildings, as described above. However, in special circumstances, such as when statistical data on a particular ancient building is not affected by conventional factors, factors like month, time, region, and incense burning can be used as substitutes. Among these, statistical data on fire occurrences by month, time, and region can, to some extent, reflect the impact of meteorological and water system factors on ancient buildings. For example, ancient buildings are prone to fire during dry, hot, windy, and lightning-prone weather (in June, July, and August). During the day, especially around noon (11:00-13:00), temperatures are at their daily peak, and there is high foot traffic and electrical appliance usage, increasing the risk of fire in ancient buildings. Environmental factors are characterized by their relatively stable nature over time, ranging from hours to months, falling between static and dynamic; therefore, they are classified as semi-dynamic influencing factors. The ancient building system, when combined with the influence of environmental factors, becomes a semi-dynamic system, and changes in these factors can trigger semi-dynamic risks for the ancient building.

[0052] Dynamic Risk (Man): The dynamic risk of ancient buildings mainly refers to the uncertainties caused by people. Especially in scenic spots and historical sites, the high density of visitors and the large flow of people pose the greatest risks to the safety of the ancient building system. For example, careless use of fire (burning incense during worship), smoking, arson, minors playing with fire, and violations of operating procedures during production can all lead to fires. In addition, abnormal human behavior such as carving on artifacts, theft, and climbing can also bring unpredictable and irreversible risks to ancient buildings. Therefore, the real-time changes and unpredictability of human behavior make human factors dynamic, meaning that the impact of people on the ancient building system is also dynamic. An ancient building system with the added influence of human factors becomes a dynamic system, and changes in human factors will alter the dynamic risk status of the ancient building.

[0053] Management Assessment Factors: Management assessment factors for ancient buildings primarily refer to management policies and resources addressing static, semi-dynamic, and dynamic risks such as fire risk and abnormal human behavior. For example, regarding static risks, this includes fire prevention measures and fire monitoring equipment for the building itself. For semi-dynamic risks, it includes the location and placement of waterways (i.e., fire stations). For dynamic risks, it includes equipment and emergency plans for identifying abnormal behaviors such as theft and arson, or for identifying hazard sources. Management assessment factors are inherently dynamic and adjust according to different risk factors. Internally, they involve adjusting management resources; externally, they involve changing management policies, thereby reducing the adverse effects of static, semi-dynamic, and dynamic risks on ancient buildings.

[0054] Furthermore, through field research, literature review, and expert consultation, a set of disaster-causing factors considering the "object-environment-human" model was obtained, along with a set of "management" assessment factors based on fire protection resources and fire management. This constructed a risk analysis framework considering the "object-environment-human-management" model, as shown in Table 1. When selecting specific nodes for implementing the MEMM analysis framework, the principles of objectivity, comprehensiveness, and operability must be followed.

[0055] Table 1

[0056]

[0057]

[0058] In constructing the conditional probabilities of each factor, special types of nodes, such as ancient building structures, can be divided into three states: wooden structure, brick-wood structure, and other structures. The most basic node state can be divided into two states: present / absent. Based on the aforementioned analytical framework (disaster-causing factor set + assessment and management set), the risks to be assessed and the corresponding risk indicators of the assessment object are determined. Through historical statistical data, expert decision-making, and other methods, the conditional probabilities of the risk indicators in the MEMM analytical framework are determined.

[0059] Taking fire risk as an example, the process of constructing the disaster-causing and assessment factor set is described. The basic requirements for constructing nodes are shown in Table 2. The most basic node state is divided into two states: present and absent. Special types of nodes have two or more states. In the MEMM-BN network, risk indicators with uncertainty are represented by nodes, and the relationships between nodes are represented by lines with arrows. The arrows point inward to the parent node and outward to the child node.

[0060] Table 2

[0061] serial number root node Parent node Child node state Remark 1 Risk Source Factor A of the object Yes / No 2 Risk Source Environmental Factor B Yes / No 3 Risk Source Human Factors C Yes / No 4 Risk Source Indicator An At least 2 5 Risk Source Indicator Bn At least 2 6 Risk Source Indicator Cn At least 2 7 Risk Source Factor D of the pipe Yes / No 8 Risk Source Indicator Dn At least 2

[0062] Furthermore, each node has a different state value reflecting the probability of each node. The MEMM-BN model is initially based on the process of objects, environment, people, and management. Based on the observed values ​​of risk indicators and prior knowledge of their interrelationships, it solves the probability of ancient buildings being affected by disasters and calculates the joint probability distribution under the conditional dependence of risk indicators, as shown in Equation (1):

[0063]

[0064] Among them, [A1,A2,A3,...,A n ,B1,B2,B3,...,B n C1, C2, C3, ..., C n ,D1,D2,D3,...,D n That is, U is the state of the node set, P a (X i ) is X i The state of the parent node, P(X) i |P a (X i )) indicates that the parent node is in state P. a (X i Under the condition that the child node's state is X i The conditional probability at that time.

[0065] Taking ancient building fire accidents as an example, the following seven indicators were identified as influencing factors: "Material" factors include the building structure, fire load, fire resistance, electrical short circuits, light bulb burning, careless use of electrical equipment, and other electrical factors; "Human" factors include six indicators: careless use of fire, minors playing with fire, smoking, arson by key personnel, and production operations; and "Environmental" factors include four indicators: weather, season, time, and region. Management factors, as intervention factors, interact with human, material, and environmental factors. Optimization through management methods can reduce the dynamic and static risks of ancient buildings, thus initially constructing a risk assessment framework for ancient building fires. Figure 4 As shown.

[0066] Table 3

[0067]

[0068]

[0069] Furthermore, by visiting ancient buildings, conducting document research, and consulting expert think tanks, the probability of occurrence of each node can be statistically analyzed. If the probability of a child node's direct influencing factor on its parent node cannot be directly obtained, such as the lack of statistical data on the probability of wind speed causing a fire, then the probability of the child node's influence on the parent and root nodes can be obtained through indirect factors. For example, the influence of month, time, region, and weather conditions can be used to replace direct factors such as humidity and temperature, indirectly reflecting the impact of direct factors from probability statistics.

[0070] Furthermore, after constructing a preliminary MEMM-BN model using prior knowledge, based on... Figure 3 The management assessment layer's internal / external measures within the process utilize management factors to achieve "macro-control, resource optimization, and early warning and prevention" of risk sources related to "people, materials, and environment." Figure 4 As shown, new monitoring values ​​are generated. The prior probability distribution is updated to obtain the posterior probability distribution, thereby realizing the assessment of the dynamic and static risks of ancient buildings based on the posterior probability distribution. The calculation principle is shown in Equation (2).

[0071]

[0072] In the formula, P(U|E) is the posterior probability of the fire, P(E) is the new evidence, P(E|U) is the conditional probability, and P(U) is the prior probability.

[0073] After the initial MEMM model was built, a case of fire in an ancient building was selected for verification. The status of each node was entered into the factor table as shown in Table 4. At this time, the influence of human factors was not introduced. The posterior probability of the accident was calculated to be 67.6% by the MEMM-BN model, which proves that the model construction factors and the model probability calculation principle are reasonable.

[0074] Table 4

[0075]

[0076] Furthermore, the risk management assessment process for ancient buildings is itself a dynamic adjustment behavior that changes with the regulation of different risk factors. It involves internal management resource regulation and external management policy changes, thereby reducing the adverse effects of static, semi-dynamic, and dynamic risks on ancient buildings.

[0077] Taking static risk as an example, a static risk characteristic parameter database is established by encoding the architectural entities and load-bearing structures in ancient buildings (groups). The risks of ancient buildings (groups) are divided into two categories, further subdivided into several major categories, minor categories, primary categories, and secondary categories. The classification code includes a category code, a major category code, a minor category code, a primary category code, and a secondary category code, each consisting of a five-digit code. Its structure is as follows: Figure 5 As shown.

[0078] Category codes and major category codes use sequential numeric codes, represented by 1 to 9 respectively, with other codes represented by 9. Minor category codes, first-level category codes, and second-level category codes use sequential numeric codes, represented by 01 to 99, with other codes represented by 99. Codes with fewer than eight digits are padded with 0s to maintain an eight-digit code structure. For example: Ancient building entity (category) - 10000000; Building structural attributes (major category) - 11000000; Influencing factors (minor category) - 11050000; Wooden structure (first-level category) - 11050100; Mortise and tenon structure (secondary category) - 11050101. Figure 6 As shown.

[0079] For semi-dynamic risks, the first and second digits (category and major category) are distinguished by lowercase letters a to z. Similarly, for dynamic risks, the first and second digits (category and major category) are distinguished by uppercase letters A to Z. The coding rules for subsequent subcategories, first-level categories, and second-level categories are consistent with those for static risks. Furthermore, for ease of use, the subcategory 01 number for all three risk types is uniformly assigned as a location coordinate, with the first-level and second-level categories corresponding to the longitude and latitude of the risk occurrence, respectively. Therefore, the risk feature library based on these three states will be coded according to the aforementioned rules, thereby establishing a feature coding library for the assessment objects.

[0080] Furthermore, after assessing the dynamic and static risks of ancient buildings using the MEMM-BN method, the probability of risk occurrence corresponding to different influencing factors within a specific category can be obtained. At this point, the risk feature library outputs multiple codes, containing risk location information and the potential degree of risk. Subsequently, based on management policy optimization or management resource allocation, such as changes in management factors like regulations / operating procedures / accident prevention methods / emergency measures, for example, optimizing the quantity and layout of objects to reduce static risks; monitoring environmental factors to achieve real-time monitoring and early warning to reduce semi-dynamic risks; changing management policies to optimize the number of management personnel, duty locations, and passenger evacuation routes to reduce instantaneous passenger flow, thereby reducing dynamic risks caused by human factors. Then, the optimized information is re-entered into the MEMM-BN model for verification, and the verification results are subsequently re-coded in the risk feature library.

[0081] In the feature library, influencing factors are categorized as follows: objects (10%), environment (20%), people (40%), and management (30%). Corresponding to the risk occurrence probability calculated by the MEMM-BN model, the codes in the features are automatically sorted using machine learning, and the top 10-20 codes for each of the four factors (people, objects, environment, and management) are listed. Simultaneously, the system autonomously identifies strongly correlated influencing factors, identifies the highest risk combinations under the aforementioned proportions, and sorts the given combinations. Therefore, by sorting individual and combined factors in the risk feature library, the risk status of ancient buildings can be obtained. Combined with GIS, risk sources or corresponding management probability maps can be obtained. Figure 7 As shown.

[0082] The method for dynamic detection of safety risks of ancient buildings proposed in this invention can predict and assess the future safety of a region.

[0083] To achieve the above embodiments, such as Figure 8 As shown, this embodiment also provides a dynamic detection device 10 for the safety risks of ancient buildings. The device 10 includes an indicator acquisition module 100, a probability determination module 200, an indicator calculation module 300, and a risk detection module 400.

[0084] The indicator acquisition module 100 is used to acquire the first impact indicators of various factors of the risk of the ancient building to be detected, and to construct a disaster-causing factor set and an assessment factor set based on the first impact indicators;

[0085] The probability determination module 200 is used to determine the influencing factors of the ancient building to be tested and the second influencing index of the influencing factors of the ancient building to be tested based on the disaster-causing factor set and the assessment factor set, and to determine the conditional probability of the second influencing index.

[0086] The indicator calculation module 300 is used to calculate the probability distribution result of the second influence indicator based on the conditional probability of the second influence indicator and the observed value of the second influence indicator.

[0087] The risk detection module 400 is used to update the probability distribution results. Based on the updated probability distribution results, the risk of the ancient building to be detected is detected, and the risk detection results of the ancient building to be detected are obtained.

[0088] Furthermore, the first impact indicator includes risk indicators of human, object, and environmental factors, as well as management assessment indicators of management factors; the set of disaster-causing factors includes static risk, semi-dynamic risk, and dynamic risk; the second impact indicator includes parent nodes and child nodes of multiple factors.

[0089] Furthermore, the formula for calculating the probability distribution result of the second influence index of the probability determination module 200 is as follows:

[0090]

[0091] Among them, [A1,A2,A3,...,A n ,B1,B2,B3,...,B n C1, C2, C3, ..., C n ,D1,D2,D3,...,D n That is, U is the state of the node set, P a (X i ) is X i The state of the parent node, P(X) i |Pa (X i )) indicates that the parent node is in state P. a (X i Under the condition that the child node's state is X i The conditional probability at that time.

[0092] Furthermore, the calculation formula for the aforementioned risk detection module 400 is as follows:

[0093]

[0094] Where P(U|E) is the posterior probability of the fire, P(E) is the new evidence, P(E|U) is the conditional probability, and P(U) is the prior probability.

[0095] Furthermore, the aforementioned device 10 also includes:

[0096] The parameter library establishment module is used to classify static risks, semi-dynamic risks and dynamic risks, and encode the building entities and load-bearing structures in the ancient buildings to be tested based on the classification results, thereby establishing a feature parameter library for the ancient buildings to be tested.

[0097] The indicator optimization module is used to obtain the probability of risk occurrence based on the risk detection results and the feature parameter library, and to optimize the indicators of multiple factors according to the probability of risk occurrence to obtain the indicator optimization results.

[0098] The combination ranking module is used to rank multiple combinations of factors based on the results of indicator optimization, obtain the factor combination ranking results, and determine the risk status of the ancient building to be detected based on the factor combination ranking results.

[0099] The dynamic detection device for safety risks of ancient buildings proposed in this embodiment of the invention can predict and assess the future safety of a region.

[0100] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0101] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this invention, "a plurality of" means at least two, such as two, three, etc., unless otherwise explicitly specified.

Claims

1. A method for dynamic detection of safety risks in ancient buildings, characterized in that, Includes the following steps: First impact indicators of multiple factors affecting the risks of ancient buildings to be detected are obtained. A set of disaster-causing factors and a set of assessment factors are constructed based on the first impact indicators. The first impact indicators include risk indicators of human, object, and environmental factors and management assessment indicators of management factors. The set of disaster-causing factors includes static risks, semi-dynamic risks, and dynamic risks. Based on the disaster-causing factor set and the assessment factor set, determine the influencing factors of the ancient building to be tested and the second influencing index of the influencing factors of the ancient building to be tested, and determine the conditional probability of the second influencing index; the second influencing index includes parent nodes and child nodes of multiple factors; Based on the conditional probability of the second influence index and the observed value of the second influence index, the probability distribution of the second influence index is calculated. Update the probability distribution result, and detect the risk of the ancient building to be detected based on the updated probability distribution result to obtain the risk detection result of the ancient building to be detected. Also includes: By classifying the static risks, semi-dynamic risks, and dynamic risks, and encoding the building entities and load-bearing structures in the ancient buildings to be detected based on the classification results, a feature parameter library for the ancient buildings to be detected is established. Based on the risk detection results and the feature parameter library, the probability of risk occurrence is obtained. The indicators of the multiple factors are optimized according to the probability of risk occurrence to obtain the indicator optimization results. Based on the indicator optimization results, the combinations of multiple factors are sorted to obtain the factor combination sorting results. The risk status of the ancient building to be detected is determined according to the factor combination sorting results.

2. The method according to claim 1, characterized in that, The formula for calculating the probability distribution of the second influencing indicator is as follows: in, Right now The state of the node set. for The state of the parent node, This indicates that the parent node is in a certain state. Under the condition that the child node state is The conditional probability at that time.

3. The method according to claim 1, characterized in that, The formula for calculating the risk detection result of the ancient building to be detected based on the updated probability distribution is as follows: in, Let be the post-fire probability. As new evidence, For conditional probability, This represents the prior probability.

4. A dynamic detection device for safety risks of ancient buildings, characterized in that, include: The indicator acquisition module is used to acquire the first impact indicators of various factors affecting the risk of the ancient building to be detected, and to construct a disaster-causing factor set and an assessment factor set based on the first impact indicators. The probability determination module is used to determine the influencing factors of the ancient building to be tested and the second influencing index of the influencing factors of the ancient building to be tested based on the disaster-causing factor set and the assessment factor set, and to determine the conditional probability of the second influencing index; the first influencing index includes risk indicators of human, object, and environmental factors and management assessment indicators of management factors; the disaster-causing factor set includes static risk, semi-dynamic risk and dynamic risk; The indicator calculation module is used to calculate the probability distribution result of the second influence indicator based on the conditional probability of the second influence indicator and the observed value of the second influence indicator; the second influence indicator includes parent nodes and child nodes of multiple factors; The risk detection module is used to update the probability distribution result, detect the risk of the ancient building to be detected based on the updated probability distribution result, and obtain the risk detection result of the ancient building to be detected. The parameter library establishment module is used to classify the static risks, semi-dynamic risks and dynamic risks, encode the building entities and load-bearing structures in the ancient building to be detected according to the classification results, and establish the feature parameter library of the ancient building to be detected. The indicator optimization module is used to obtain the probability of risk occurrence based on the risk detection results and the feature parameter library, and to optimize the indicators of the multiple factors according to the probability of risk occurrence to obtain the indicator optimization result; The combination sorting module is used to sort multiple factor combinations based on the optimization results of the indicators, obtain factor combination sorting results, and determine the risk status of the ancient building to be detected based on the factor combination sorting results.

5. The apparatus according to claim 4, characterized in that, The formula for calculating the probability distribution result of the second influence index of the probability determination module is as follows: in, Right now The state of the node set. for The state of the parent node, This indicates that the parent node is in a certain state. Under the condition that the child node state is The conditional probability at that time.

6. The apparatus according to claim 5, characterized in that, The calculation formula for the risk detection module is as follows: in, Let be the post-fire probability. As new evidence, For conditional probability, This represents the prior probability.

Images