Bridge disease development trend and mechanism judgment method and system

Abstract

The application discloses a bridge disease development trend and mechanism judgment method and system, and the method comprises the following steps: constructing a multi-source evidence fusion system, which comprises a basic evidence layer, a time sequence evidence layer and a knowledge support layer. Based on the system, the basic, time sequence and knowledge matching evidence of the bridge to be diagnosed is collected, and the disease development trend is judged by combining quantitative and qualitative methods: quantitative analysis obtains the time sequence change rule of key parameters through a preset model, and qualitative determination divides the trend into at least three change states according to a preset rule. Combined with the evidence and the disease mechanism model library, the mechanism type is determined through the coincidence degree calculation and the integrity verification, the risk assessment is carried out by coupling the trend result, and finally the related results are output to form a standardized mechanism analysis file. The application provides reliable support for bridge maintenance decision.

Description

Technical Field

[0001] This invention belongs to the field of bridge structural health monitoring technology, and more specifically, relates to a method and system for judging the development trend and mechanism of bridge defects. Background Technology

[0002] In recent years, artificial intelligence technology has been increasingly applied in the field of bridge defect detection. Devices such as drones, LiDAR, and cameras can automatically collect large amounts of bridge images and point cloud data. Combined with deep learning models, these can quickly identify surface damage such as cracks, spalling, and corrosion, significantly improving the efficiency and coverage of defect detection. However, the current level of intelligent bridge defect diagnosis remains limited to defect identification. Many practical problems still need to be addressed in key areas such as future trend analysis, defect mechanism analysis, and risk assessment.

[0003] Traditional bridge defect diagnosis methods often rely on fragmented and singular sources of evidence, depending on localized data from single tests. They lack a systematic integration of the current objective state of the defect, its historical evolution, and professional diagnostic knowledge, resulting in incomplete data sources for diagnostic analysis and hindering accurate trend judgment and mechanism identification. In terms of trend assessment, existing methods mostly employ single quantitative calculations or qualitative descriptions, failing to balance the accuracy of parameter changes with the flexibility to adapt to different types of defects. This makes it difficult to comprehensively and accurately reveal the evolutionary patterns of defects over time, thus affecting the scientific prediction of defect development trends.

[0004] More importantly, traditional methods lack standardized logic and unified judgment criteria in determining the mechanism of bridge defects and assessing risks. Mechanism identification relies heavily on human experience, resulting in high subjectivity, insufficient accuracy, and vague risk level classification, making it difficult to clearly define the causes, scope of impact, and degree of safety risk of defects. Furthermore, due to the lack of systematic knowledge support and scientific analytical processes, the standardization and reliability of diagnostic results are difficult to guarantee, failing to meet the stringent requirements of engineering review and providing strong support for bridge maintenance decisions. These problems not only affect the efficiency and quality of bridge defect diagnosis but may also lead to unreasonable allocation of maintenance resources and even delays in addressing potential safety hazards, adversely affecting the structural safety and service life of bridges. Therefore, there is an urgent need for a technology that can address the above-mentioned problems in determining the development trend and mechanism of bridge defects, improving the scientific rigor, standardization, and reliability of bridge defect diagnosis. Summary of the Invention

[0005] This invention aims to address the problems of limited evidence sources, one-sided trend analysis, vague mechanism judgment, and subjective risk assessment in existing bridge defect diagnosis. By integrating multi-dimensional evidence and professional knowledge, and employing scientific analysis methods, it achieves accurate judgment of defect development trends, standardized adaptation of mechanism types, and reasonable classification of risk levels, thereby improving the comprehensiveness, accuracy, and standardization of diagnostic results and providing reliable support for bridge maintenance decisions.

[0006] In view of the above-mentioned defects or improvement needs of the existing technology, as a first aspect of the present invention, the present invention provides a method for judging the development trend and mechanism of bridge defects, including:

[0007] S1. Construct a multi-source evidence fusion system, the fusion system including a basic evidence layer for providing data on the current objective state of the disease, a temporal evidence layer for providing data related to the dynamic evolution of the disease, and a knowledge support layer for providing professional knowledge and practical basis for the diagnosis of bridge diseases;

[0008] S2. Based on the multi-source evidence fusion system, collect basic evidence, temporal evidence and knowledge matching evidence corresponding to the bridge to be diagnosed, and conduct disease development trend analysis by combining quantitative analysis and qualitative judgment; quantitative analysis obtains the temporal change law of key disease parameters through a preset parameter change rate calculation model; qualitative judgment divides the development trend into at least three change states according to preset classification rules.

[0009] S3. Based on the collected multi-source evidence and disease mechanism model library, an adaptation analysis is performed. The appropriate disease mechanism type is determined by evidence fit calculation and correlation integrity verification. The risk level assessment is carried out in combination with the development trend judgment results and disease mechanism type.

[0010] S4. Output the results of disease development trend determination, mechanism adaptation conclusion, evidence fit and risk level assessment results, forming a standardized mechanism analysis document.

[0011] Furthermore, in S1, the basic evidence layer is configured with quantitative characteristic data, spatial distribution information and apparent state information of bridge defects; the temporal evidence layer is configured with historical detection data, maintenance and treatment records and environmental load time-series data related to bridge defects; and the knowledge support layer is configured with bridge industry standards, defect mechanism model library and engineering practice case set.

[0012] Furthermore, the disease mechanism model library is constructed based on professional knowledge related to bridge disease diagnosis, and includes the correlation conditions, manifestations and causal analysis of at least two types of coupled diseases.

[0013] Furthermore, the specific process of quantitative analysis in S2 is as follows:

[0014] Based on the availability of historical monitoring data, a corresponding calculation method is used to determine the disease development trend. When only one period of historical monitoring data is available, the basic annualized rate of change of key disease parameters is calculated. The calculation formula is: ,in This is the current detection parameter value. These are historical detection parameter values. The time interval between two tests;

[0015] When multiple historical monitoring data are available, calculate the weighted average annualized rate of change of key disease parameters. The specific steps are as follows:

[0016] Set the historical detection time point as ,and The corresponding parameter value is , Given the current detection time; calculate the instantaneous annualized rate of change for each adjacent detection period. , The calculation formula is: ,in , where is the time interval between adjacent detections;

[0017] For each Assign weights The weight is inversely proportional to the time distance from the end of the time period to the present, and the calculation formula is as follows: ,in For the first The interval between the current detection time and the present time. To prevent division by zero of small constants;

[0018] Through formula Calculate the weighted average annualized rate of change ;

[0019] Based on the rate of change results, trend classification is performed sequentially: when... or When, the corresponding trend is improvement and recovery; when or At that time, the corresponding trend is rapid development; when or At that time, the corresponding trend is slow development; when or At that time, the corresponding trend is towards stability.

[0020] Furthermore, the specific process of qualitative analysis in S2 is as follows:

[0021] When disease parameters cannot be quantified, a text analysis method based on semantic rules and keyword matching is used to determine the disease development trend by comparing the current and historical detection descriptions. Specifically, this includes:

[0022] Construct a semantic dictionary of disease development: Establish keyword sets corresponding to different development trend categories, with each set containing words or word combinations that match the characteristics of that trend;

[0023] Text processing: The current and historical detection description texts are segmented into words and matched with the keyword set in the semantic dictionary mentioned above;

[0024] Trend determination: Based on the set of keywords matched by the current detection description, the disease development trend is determined according to the preset priority order;

[0025] Output results: The trend results obtained from the determination will be output as the qualitative analysis results of the disease development trend.

[0026] Furthermore, the process for determining the appropriate disease mechanism type in S3 is as follows:

[0027] First, calculate the core evidence matching rate. The calculation formula is: , This represents the number of key pieces of evidence matched in the current disease data. The total amount of core evidence representing the definition of the disease mechanism model;

[0028] Next, calculate the basic matching degree. A piecewise nonlinear function is used, and the formula is:

[0029]

[0030] Subsequently, the disease development trend was defined, including... , , , Four categories, For rapid development, For slow development, In order to achieve stability, To improve and restore;

[0031] Determine the trend correction coefficient based on the disease development trend. The corresponding rule is hour , hour , hour , hour ;

[0032] Then through the formula Calculate the overall matching degree Then set the matching degree including , , , Level 4 For a high degree of matching, For a moderate match, The match is relatively poor. The match is low.

[0033] Based on overall matching degree The rules for determining the degree of matching are as follows: The degree of matching is , The degree of matching is , The degree of matching is , The degree of matching is ;

[0034] The disease mechanism model type with the highest matching degree is finally output as the appropriate disease mechanism type.

[0035] Furthermore, the risk level in S3 is divided into at least three level ranges, and the classification is based on the functional importance of the structural component where the disease is located, the degree of mechanism matching, and the development trend. The specific classification process is as follows:

[0036] Determine the functional importance level of the structural components where the defects are located: Identify the functional positioning of the structural components where the defects are located in the bridge system, and classify the structural components into two categories: core functional components that bear the main load-bearing function and auxiliary functional components that bear secondary or auxiliary functions.

[0037] Obtain key assessment parameters: obtain the grade range corresponding to the degree of matching of disease mechanism, and the evolutionary state parameters corresponding to the disease development trend;

[0038] Risk level classification: Based on preset multi-parameter coupling judgment rules, a comprehensive judgment is made by combining the functional importance level of structural components, the degree of mechanism matching, and the parameters of disease development trend.

[0039] Furthermore, the standardized mechanism analysis document in S4 includes modules for bridge basic information, development trend analysis, mechanism adaptation conclusions, risk level assessment, and supporting materials index, with each module presented in an orderly manner according to logical connections.

[0040] The bridge basic information module covers the core parameters of the bridge and detection-related information, providing a prerequisite for adapting the results to different scenarios.

[0041] The development trend analysis module records data on changes in disease parameters, qualitative judgment criteria, and the status of change, clarifying the source of corresponding time-series evidence.

[0042] The mechanism adaptation conclusion module lists the adapted disease mechanism type, related conditions and cause analysis, explains the evidence fit calculation and correlation integrity verification, and marks the professional supporting materials on which the judgment is based.

[0043] The risk level assessment module clarifies the risk level results and classification criteria, and analyzes the core risk factors, scope of impact, and potential hazards.

[0044] The supporting materials index module compiles a list of original data for various types of evidence, a summary of historical records, and a directory of cited materials, ensuring that the data sources, basis, and logical chain of the analysis process can be traced.

[0045] As a second aspect of the present invention, the present invention also provides a system for judging the development trend and mechanism of bridge defects, comprising:

[0046] A multi-source evidence fusion system construction unit is used to construct a multi-source evidence fusion system, which includes a basic evidence layer for providing data on the current objective state of the disease, a temporal evidence layer for providing data on the dynamic evolution of the disease, and a knowledge support layer for providing professional knowledge and practical basis for the diagnosis of bridge diseases.

[0047] The evidence collection and trend analysis unit is used to collect basic evidence, temporal evidence and knowledge matching evidence corresponding to the bridge to be diagnosed based on the multi-source evidence fusion system, and to conduct disease development trend analysis by combining quantitative analysis and qualitative judgment. The quantitative analysis obtains the temporal change law of key disease parameters through a preset parameter change rate calculation model. The qualitative judgment divides the development trend into at least three change states according to preset classification rules.

[0048] The mechanism adaptation and risk assessment unit is used to perform adaptation analysis based on the collected multi-source evidence and disease mechanism model library. It determines the adapted disease mechanism type through evidence fit calculation and correlation integrity verification, and conducts risk level assessment based on the development trend judgment results and disease mechanism type.

[0049] The standardized analysis document output unit is used to output the results of disease development trend determination, mechanism adaptation conclusion, evidence fit and risk level assessment, forming a standardized mechanism analysis document.

[0050] As a third aspect of the present invention, the present invention also provides a computer-readable storage medium having a computer program stored thereon, the computer program being executed by a processor of any of the bridge defect development trend and mechanism judgment methods described in the present invention.

[0051] In summary, compared with the prior art, the above-described technical solutions conceived by this invention can achieve the following beneficial effects:

[0052] 1. The bridge defect development trend and mechanism judgment method of the present invention systematically integrates current objective state data of defects, dynamic evolution-related data, and professional knowledge and practical basis for bridge diagnosis by constructing a multi-source evidence fusion system comprising a basic evidence layer, a temporal evidence layer, and a knowledge support layer. The basic evidence layer provides core data such as the quantitative characteristics, spatial distribution, and apparent state of defects; the temporal evidence layer covers historical inspection, maintenance records, and environmental load time-series information; and the knowledge support layer encompasses industry standards, defect mechanism model libraries, and engineering case studies. These three types of evidence layers complement each other and work synergistically to effectively solve the problems of single and fragmented evidence sources in traditional methods, ensuring the comprehensiveness and reliability of data sources for trend judgment and mechanism adaptation, and providing solid data and knowledge support for subsequent analysis.

[0053] 2. The bridge disease development trend and mechanism judgment method of the present invention adopts a combination of quantitative analysis and qualitative judgment to judge the disease development trend. It uses a preset parameter change rate calculation model to mine the temporal change patterns of key disease parameters and classifies the trend into at least three change states according to preset classification rules. This dual analysis mode utilizes the precision of quantitative calculation to capture the details of dynamic parameter changes, while the flexibility of qualitative judgment adapts to the trend characteristics of different types of diseases. It effectively avoids the limitations of a single analysis method, and can more accurately and comprehensively reveal the disease evolution pattern, providing a scientific trend basis for subsequent risk level assessment and treatment plan formulation.

[0054] 3. The bridge defect development trend and mechanism judgment method of this invention, through adaptation analysis based on multi-source evidence and defect mechanism model library, combined with evidence fit calculation and correlation integrity verification to determine the defect mechanism type, and then integrates the trend judgment results to carry out risk level assessment and divide it into at least three level intervals. This process strictly follows professional knowledge and industry standards, achieving accurate matching of defect mechanisms and scientific definition of risk levels, solving the pain points of vague mechanism judgment and subjective risk assessment in traditional methods, ensuring the standardization and rationality of analysis results, and outputting standardized mechanism analysis documents, providing direct and reliable technical support for subsequent scaling optimization and treatment plan formulation of bridge defects. Attached Figure Description

[0055] Figure 1 This is a flowchart illustrating the bridge defect development trend and mechanism judgment method according to an embodiment of the present invention.

[0056] Figure 2 This is a schematic diagram illustrating relevant evidence for the hinge joint failure-single plate stress mechanism model in an embodiment of the present invention;

[0057] Figure 3 This is a schematic diagram of the beam-slab deflection recovery force analysis according to an embodiment of the present invention; wherein, This represents the measured value of the misalignment at one end of the beam; This indicates the measured value of the misalignment at the end of the beam at the other end; This indicates the measured value of the mid-span misalignment.

[0058] Figure 4 This is a schematic diagram illustrating the risk of beam-slab fracture caused by stress on a single slab, according to an embodiment of the present invention.

[0059] Figure 5 This is a schematic diagram illustrating relevant evidence for the plate end shear crack-shear insufficiency mechanism model in an embodiment of the present invention;

[0060] Figure 6 This is a schematic diagram of the shear crack morphology according to an embodiment of the present invention;

[0061] Figure 7 This is a schematic diagram of a transverse crack in the base plate formed by shear cracks according to an embodiment of the present invention;

[0062] Figure 8 This is a system unit diagram of an embodiment of the present invention. Detailed Implementation

[0063] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention. Furthermore, the technical features involved in the various embodiments of this invention described below can be combined with each other as long as they do not conflict with each other.

[0064] Example 1

[0065] Please refer to Figure 1 This embodiment 1 provides a method for judging the development trend and mechanism of bridge defects, including:

[0066] S1. Construct a multi-source evidence fusion system, the fusion system including a basic evidence layer for providing data on the current objective state of the disease, a temporal evidence layer for providing data related to the dynamic evolution of the disease, and a knowledge support layer for providing professional knowledge and practical basis for the diagnosis of bridge diseases;

[0067] S2. Based on the multi-source evidence fusion system, collect basic evidence, temporal evidence and knowledge matching evidence corresponding to the bridge to be diagnosed, and conduct disease development trend analysis by combining quantitative analysis and qualitative judgment; quantitative analysis obtains the temporal change law of key disease parameters through a preset parameter change rate calculation model; qualitative judgment divides the development trend into at least three change states according to preset classification rules.

[0068] S3. Based on the collected multi-source evidence and disease mechanism model library, an adaptation analysis is performed. The appropriate disease mechanism type is determined by evidence fit calculation and correlation integrity verification. The risk level assessment is carried out in combination with the development trend judgment results and disease mechanism type.

[0069] S4. Output the results of disease development trend determination, mechanism adaptation conclusion, evidence fit and risk level assessment results, forming a standardized mechanism analysis document.

[0070] This embodiment 1 further elaborates on the above steps.

[0071] (1) Construction of a multi-source evidence fusion system

[0072] The judgment method in this embodiment requires a multi-source evidence fusion system as the core data and knowledge support. This fusion system is composed of three layers: basic evidence layer, temporal evidence layer, and knowledge support layer. Each of the three layers performs its own function and complements the others, providing a comprehensive, systematic and reliable basis for subsequent disease trend judgment and mechanism analysis.

[0073] The foundational evidence layer of the multi-source evidence fusion system is responsible for receiving and structuring direct evidence from current bridge defects. Its recorded content directly reflects the current objective state of bridge defects and serves as the basic data source for defect analysis. The evidence configured in this layer includes three core types of information: quantitative characteristic data, spatial distribution information, and apparent state information.

[0074] Taking the on-site inspection of a hollow slab bridge as an example, the basic evidence layer records quantitative indicators such as the length and maximum width of the crack in the bottom slab at the mid-span of beam #1, and specific values ​​such as the area of ​​concrete spalling in pier #2. It also clearly marks the spatial location of various defects, such as the crack being located at L / 3 of the bottom slab of beam #1 in the first span, and the spalling area being located on the water-facing side of pier #2. Furthermore, it describes the appearance of the defects in detail, such as water seepage and calcification at the crack location, and exposed rebar and corrosion at the spalled area of ​​the pier. This information can intuitively present the current development status of the defects, providing accurate current status references for subsequent analysis.

[0075] The core function of the temporal evidence layer is to manage evidence data related to the time dimension. By integrating relevant information from different time points, it enables full-process tracking of the dynamic evolution of defects. To ensure the orderly management and efficient retrieval of data, the system establishes an independent spatiotemporal database for each bridge, specifically for associating and storing three types of time-related data: historical inspection data, maintenance records, and environmental load time-series data. Taking the hollow slab bridge as an example, the temporal evidence layer retrieves the inspection record of the crack in beam #1 in 2022 and compares it with the current crack data to intuitively present the changes in the crack over a period of time. It also records information on maintenance work such as partial plastering repairs carried out on pier #2 in 2023, clarifying the intervention measures taken for the defects. In addition, environmental load time-series data such as annual precipitation and extreme temperatures at the bridge site are also included in this layer. This data provides crucial evidence for analyzing the impact of environmental factors on the development of defects.

[0076] The knowledge support layer provides professional theoretical and practical support for the multi-source evidence fusion system. Its core component is the disease mechanism model library, which also includes bridge industry standards and engineering practice case studies to provide professional basis for disease mechanism judgment. The disease mechanism model library is built based on professional knowledge related to bridge disease diagnosis and includes the correlation conditions, manifestations, and causal analyses of at least two types of coupled diseases. Each model corresponds to a specific disease type and evolution mechanism.

[0077] Taking the hinge joint failure-single slab stress model (M1) and the mid-span bending crack-insufficient bearing capacity model (M2) as examples, the hinge joint failure-single slab stress model (M1) clearly identifies core evidence such as longitudinal through cracks in the bridge deck, misalignment between beams and slabs, water seepage and whitening along the entire length of the hinge joint, and significant deflection of the single slab when vehicles pass. When both longitudinal through cracks in the bridge deck and water seepage and whitening along the entire length of the hinge joint are simultaneously present in the field test data, the model can be triggered with a high probability of matching. The mid-span bending crack-insufficient bearing capacity model (M2) uses transverse cracks in the bottom slab in the mid-span area, vertical bending cracks in the web (wider at the bottom and narrower at the top), and excessive or continuously increasing deflection as core evidence, and is specifically used to assess the bearing capacity of the main beam. In addition to the disease mechanism model library, the knowledge support layer also includes industry standard provisions such as the "Standard for Technical Condition Assessment of Highway Bridges". These standard provisions can serve as important bases for determining the severity scale and risk threshold of diseases, ensuring that subsequent trend analysis and mechanism analysis work meet the requirements of industry standards.

[0078] Through the coordinated operation of the above three-layer structure, the multi-source evidence fusion system can achieve comprehensive integration of bridge disease status data, evolution process data, and professional support data, laying a solid data and knowledge foundation for subsequent disease development trend analysis, mechanism model adaptation analysis, and risk assessment.

[0079] (2) Evidence collection and trend analysis

[0080] Based on the established multi-source evidence fusion system, we will carry out the analysis of the development trend of bridge defects. The core idea is to collect basic evidence, time-series evidence and knowledge matching evidence corresponding to the bridge to be diagnosed, and to achieve accurate judgment of the development trend of defects by combining quantitative analysis and qualitative judgment, so as to provide reliable trend basis for subsequent mechanism analysis and risk assessment.

[0081] Quantitative analysis relies on the availability of historical monitoring data. The appropriate calculation method is selected based on the completeness of the data to obtain the temporal variation patterns of key disease parameters. The specific process is as follows:

[0082] Based on the availability of historical monitoring data, a corresponding calculation method is used to determine the disease development trend. When only one period of historical monitoring data is available, the basic annualized rate of change of key disease parameters is calculated. The calculation formula is: ,in This is the current detection parameter value. These are historical detection parameter values. The time interval between two tests;

[0083] When multiple historical monitoring data are available, calculate the weighted average annualized rate of change of key disease parameters. The specific steps are as follows:

[0084] Set the historical detection time point as ,and The corresponding parameter value is , Given the current detection time; calculate the instantaneous annualized rate of change for each adjacent detection period. , The calculation formula is: ,in , where is the time interval between adjacent detections;

[0085] For each Assign weights The weight is inversely proportional to the time distance from the end of the time period to the present, and the calculation formula is as follows: ,in For the first The interval between the current detection time and the present time. To prevent division by zero of small constants;

[0086] Through formula Calculate the weighted average annualized rate of change ;

[0087] Based on the rate of change results, trend classification is performed sequentially: when... or When, the corresponding trend is improvement and recovery; when or At that time, the corresponding trend is rapid development; when or At that time, the corresponding trend is slow development; when or At that time, the corresponding trend is towards stability.

[0088] Taking the width parameter of the bottom slab crack at the mid-span of beam #1 of a hollow slab bridge as an example, if the measured width in 2022 and the current measured width in 2024 are known, with a time interval of 2 years, the basic annualized change rate is calculated to be 12.5%. Combined with the classification rules, the development trend of this crack is quantitatively determined to be trending towards stability. If the crack also has measurement data from 2020, a multi-period weighted calculation process needs to be initiated to calculate the instantaneous annualized change rate for the two time periods of 2020-2022 and 2022-2024, assigning corresponding weights according to the weighting principle, and finally calculating the weighted average annualized change rate to more objectively present the development trend of the crack over multiple years.

[0089] Qualitative judgment is suitable for scenarios where disease parameters cannot be quantified. In this case, a text analysis method based on semantic rules and keyword matching is used to determine the disease's development trend by comparing the text information of the current detection description with that of historical detection descriptions. The specific operation process consists of four core steps:

[0090] The first step is to construct a semantic dictionary of disease development, which contains four sets of keywords corresponding to different development trends:

[0091] Keywords related to rapid development: These include developmental words combined with adverbs of strong degree, or words indicating rapid development, such as "significantly expanded", "obviously added", "rapidly connected", "severely aggravated", "rapidly developed", "drastically deteriorated", etc.

[0092] Keywords for slow development: including developmental words combined with adverbs of weak degree or developmental words alone, such as "slightly expanded", "minorly added", "partially connected", "slightly intensified", "expanded", "newly added", etc.

[0093] Keywords indicating a trend toward stability: These include words that indicate a stable or slightly stable state, such as "stable," "unchanged," "maintained," "slight," "local," "small amount," "basically unchanged," etc.

[0094] Improvement and recovery keywords: including words that indicate repair or improvement, such as "repair", "improve", "reduce", "close", "heal", "reduce", "recover", etc.

[0095] The second step is to carry out text processing, which involves segmenting the current detection description text and the historical detection description text into words, and then matching the segmented words with the four categories of keywords in the semantic dictionary.

[0096] The third step is to determine the trend. Based on the set of keywords matched in the current detection description text, the disease development trend is determined according to the preset priority order, from high to low: rapid development, slow development, improvement and recovery, and trend towards stability.

[0097] The fourth step is to output the qualitative trend results, and take the determined trend as the final conclusion of the qualitative analysis.

[0098] For example, a bridge abutment was historically described as having "slight water seepage traces on the back of the abutment," while the current description states that "the seepage area on the back of the abutment has significantly expanded, accompanied by obvious calcification deposits." The system performs text analysis: the current description matches "expanded" and its modifier "significant," classifying it as a "rapidly developing keyword"; the historical description's "slight" falls under the category of a "tending towards stability keyword." Based on priority rules (rapid development > slow development > improvement and recovery > tending towards stability), the system directly determines the disease's development trend as "rapid development."

[0099] After completing the quantitative analysis and qualitative assessment, the results of the two analyses need to be compared and verified. If the quantitative analysis results are consistent with the qualitative assessment results, then the result is directly adopted as the final conclusion on the development trend of the disease. If the two analysis results differ, for example, the quantitative analysis determines that the disease is trending towards stability, while the qualitative assessment determines that it is developing rapidly, then the system will default to the more conservative assessment result, i.e., rapid development, and at the same time increase the level of attention given to the disease in the subsequent mechanism analysis and risk assessment stages, thereby ensuring the rigor of bridge disease assessment.

[0100] (3) Mechanism adaptation and risk assessment

[0101] After completing the assessment of the development trend of the disease, it is necessary to further combine the collected multi-source evidence with the disease mechanism model library to conduct an adaptation analysis. By calculating the evidence fit and verifying the integrity of the correlation, the mechanism type that best matches the current disease is determined. Then, combined with the previously obtained development trend assessment results and the finally determined disease mechanism type, a disease risk level assessment is carried out to clarify the degree of impact of the disease on the safety of the bridge structure.

[0102] The core of mechanism adaptation analysis is to determine the degree of matching between the current disease characteristics and various disease mechanism models in the mechanism model library through multi-dimensional index calculation. First, the core evidence matching rate is calculated. The calculation formula is: , This represents the number of key pieces of evidence matched in the current disease data. The total amount of core evidence representing the definition of the disease mechanism model;

[0103] Next, calculate the basic matching degree. A piecewise nonlinear function is used, and the formula is:

[0104]

[0105] Subsequently, the disease development trend was defined, including... , , , Four categories, For rapid development, For slow development, In order to achieve stability, To improve and restore;

[0106] Determine the trend correction coefficient based on the disease development trend. The corresponding rule is hour , hour , hour , hour ;

[0107] Then through the formula Calculate the overall matching degree Then set the matching degree including , , , Level 4 For a high degree of matching, For a moderate match, The match is relatively poor. The match is low.

[0108] Based on overall matching degree The rules for determining the degree of matching are as follows: The degree of matching is , The degree of matching is , The degree of matching is , The degree of matching is ;

[0109] The disease mechanism model type with the highest matching degree is finally output as the appropriate disease mechanism type.

[0110] For example, suppose there is a crack at the mid-span of beam #1 ( The trend (approaching stability) requires mechanistic matching. The system compared its characteristics with a mechanistic model library and found it conformed to the "mid-span bending crack-insufficient bearing capacity model (M2)". This model defines the total number of core pieces of evidence. The current data matches three of the criteria (location in the mid-span, transverse crack, and signs of web extension), therefore the matching rate is [missing information]. Calculate the basic matching degree. :

[0111]

[0112] The disease's development trend is "tending towards stability," with a trend correction coefficient. Calculate the overall matching degree. :

[0113]

[0114] because The system determines that the match between the model and the model is "low match". The system outputs the M2 model as the best fit, but indicates that the match confidence is average.

[0115] After completing the mechanism adaptation analysis and clarifying the disease mechanism type, the risk level assessment was carried out. The risk level was divided into three levels: high risk, medium risk and low risk. The classification was based on three core indicators: the functional importance of the structural component where the disease is located, the degree of mechanism matching, and the disease development trend.

[0116] The first step is to determine the functional importance of the structural components where the defects are located. Based on the functional positioning of the structural components in the bridge system, they are divided into two categories: important structural components and secondary structural components. Among them, the superstructure load-bearing components, piers, abutments, foundations, supports and other components that bear the main load-bearing function are important structural components, while the railings, sidewalks, drainage systems, lighting signs and other components that bear secondary or auxiliary functions are secondary structural components.

[0117] The second step is to obtain key assessment parameters, specifically including the degree of mechanism matching obtained from mechanism adaptation analysis, and the disease development trend parameters obtained from trend analysis.

[0118] The third step is to implement risk level classification and conduct a comprehensive judgment in strict accordance with the preset multi-parameter coupling judgment rules.

[0119] The determination of a high-risk level requires the simultaneous fulfillment of three conditions: the disease is located in an important structural component, the degree of mechanism matching is high or medium, and the development trend is rapid.

[0120] The determination of medium risk level requires meeting any corresponding condition but not the high risk condition. The specific conditions include: the disease is located in an important structural component, the development trend is slow and the degree of mechanism matching is high or medium; the disease is located in an important structural component, the development trend is towards stabilization and the degree of mechanism matching is high; the disease is located in a minor structural component, the development trend is rapid and the degree of mechanism matching is high.

[0121] The determination of a low-risk level requires meeting any corresponding condition but not the high- or medium-risk conditions. Specific conditions include: the disease is located on a secondary structural component and its development trend is not rapid; the disease is located on an important structural component and its mechanism matching degree is low or very low; and the development trend of the disease is improvement and recovery.

[0122] Finally, the results of the assessment are used as the risk level of the bridge defects, providing a precise basis for subsequent bridge defect scaling, maintenance plan formulation, and other work.

[0123] Continuing with the case of the mid-span crack in beam #1, a risk assessment is conducted based on the corresponding logic. First, the importance of the component is determined: beam #1 is a load-bearing upper structure and is therefore an important structural component. The known mechanism matching degree M = 0.595 (belonging to the category of "low matching degree"), and the development trend is "tending towards stability".

[0124] Applying the risk level classification rules: This disease does not meet the high-risk conditions; the medium-risk conditions include "the disease is located on an important structural component, and..." The condition states that "the development trend is not rapid," but since M=0.595<0.60, this condition is not met. Checking the low-risk conditions, one criterion is "the defect is located on an important structural component, but the mechanism matching degree is low or very low (<0.60)," which is fully met. Therefore, the final risk level of this crack is assessed as "low risk." This result means that although it is located on a critical component, the current risk is controllable because its development is stable and its matching degree with the severe mechanism model is not high.

[0125] (4) Standardized analysis document output

[0126] After completing the entire process of assessing disease development trends, analyzing mechanistic fit, and evaluating risk levels, all analytical conclusions and relevant data must be systematically integrated to output a standardized mechanistic analysis document containing disease development trend determination results, mechanistic fit conclusions, evidence fit, and risk level assessment results. The core value of this document lies in transforming scattered detection data, analytical processes, and final conclusions into structured, traceable, and formal diagnostic data, providing direct and reliable support for subsequent bridge maintenance decision-making and maintenance prioritization.

[0127] The standardized mechanism analysis document follows the principle of logical connection and orderly presentation, covering five core modules. Each module independently carries specific information, while also being interconnected to form a complete analysis chain.

[0128] The first module is the Bridge Basic Information Module. This module is a prerequisite for scenario adaptation in the entire analysis document. Its core function is to clarify the core background information of the bridge to which the defect belongs, ensuring that the analysis conclusions accurately correspond to the specific bridge scenario. This module comprehensively covers the bridge's core parameters and inspection-related information. The core bridge parameters include basic attributes such as bridge name, structural type (e.g., hollow slab bridge, continuous beam bridge), span dimensions, construction year, and design load level. Inspection-related information includes the specific date of the inspection, the inspection unit, the inspection personnel, and the technical methods used (e.g., visual inspection, ultrasonic testing). This complete record of information allows readers to quickly and clearly grasp the basic background of the defect analysis, providing scenario support for understanding subsequent analysis conclusions.

[0129] The second module is the development trend analysis module. This module focuses on the analysis process and final conclusions of disease development trends, ensuring the transparency and verifiability of trend judgment results. The module clearly presents relevant analysis information for each disease in tabular form, specifically including disease parameter changes, qualitative judgment criteria, and the final state of change. It also clearly indicates the temporal evidence source for each data point. For diseases using quantitative analysis, the table fully records the changes in key parameters (such as parameter values ​​at different detection time points, correlation analysis results of change rates, etc.). For diseases using qualitative analysis, it details the core criteria for qualitative judgment, namely, the keywords matched after text segmentation, and their respective keyword categories. Finally, the table clearly indicates the development trend conclusion of the disease (such as rapid development, slow development, trending towards stability, improvement and recovery), and notes that the data source is the temporal evidence layer in a multi-source evidence fusion system, ensuring that the trend analysis results are traceable to the original data.

[0130] The third module is the mechanism adaptation conclusion module. This module is a systematic review of the mechanism adaptation analysis process and results, with the core being to clarify the intrinsic causal relationships of the disease.

[0131] This embodiment presents two examples related to the mechanism model: the first example is the hinge joint failure-single slab stress system model; this model aims to identify the systemic risk state of "single slab stress" caused by the complete or partial failure of the hinge joint structure, leading to the loss of lateral connection in the bridge, and the diagnostic goal is to provide early warning of the most dangerous load redistribution pattern. The model triggering depends on direct and indirect evidence chains: direct evidence includes... Figure 2 The concrete spalling at the hinge joint shown in Figure a, and Figure 2 The seepage and whitening phenomena at the hinge joint shown in Figure b; indirect evidence includes Figure 2The longitudinal through cracks in the bridge deck caused by stress on a single slab in section C, and Figure 2 The beam-slab misalignment and deflection are shown in section d. (Reference) Figure 3 The stress state of a single slab can be further confirmed by measuring the deflection value (deflection value = mid-span misalignment - slab end misalignment, used for beam-slab deflection restoring force analysis), with a focus on the mid-span deflection value and the misalignment dimensions of adjacent beams and slabs at the slab ends. The causes of this mechanism model mainly involve structural defects in small hinge joints, insufficient construction quality, and heavy overloading, with a high risk level because it can directly lead to a surge in load effects and easily trigger events such as... Figure 4 The diagram illustrates catastrophic consequences such as shear fracture of beams and slabs.

[0132] Another example is the plate end shear crack-shear insufficiency model; this model focuses on identifying insufficient shear capacity of the inclined section near the beam end support, and is a key model for early warning of brittle failure, a high-risk precursor. The core defect is the appearance of web cracks perpendicular to the horizontal plane. Diagonal cracks, typical photos can be found Figure 5 In severe cases, it can develop into something like... Figure 5 The plate shown in b is completely transversely fractured at the end. Figure 6 (The diagram illustrating the morphology of shear cracks) is the core illustration defining the morphological features of this model. Figure 7 The mechanism by which shear cracks penetrate to the bottom slab was further revealed. The main causes of this model include excessively thin web dimensions and insufficient shear reinforcement. Because it belongs to a brittle failure mode, its development may be rapid, so the risk level is high, requiring the triggering of emergency response procedures.

[0133] Meanwhile, the module details the disease mechanism types for each disease, including specific mechanism model names (e.g., mid-span bending crack - insufficient bearing capacity model, hinge joint failure - single-slab stress model, etc.); it also fully explains the analysis process related to the matching degree, clearly presenting the results of evidence fit calculation (e.g., number of core evidence matches, total number of core evidences, evidence fit-related indicators, basic matching degree, trend correction coefficient, comprehensive matching degree, etc.), and the verification of correlation integrity (e.g., the matching integrity of core evidence, whether there is any missing key evidence, etc.); finally, it clearly marks the matching degree level between the disease and the adapted mechanism model (e.g., high, medium, low, low matching degree), and details the conformity of the core evidence, that is, the specific matching details between the current disease data and the core evidence of the mechanism model. In addition, the module also marks the professional supporting materials used in the judgment process, such as the specific model number of the disease mechanism model library, the related engineering practice case number, etc., to ensure that the mechanism adaptation conclusions are supported by solid professional evidence.

[0134] The fourth module is the risk level assessment module. This module directly presents the degree of risk impact of defects and is the core module supporting maintenance decisions. The module first clarifies the final risk level result (high risk, medium risk, or low risk) for each defect. Then, it clearly lists the specific clauses of the risk level classification criteria that the defect meets. For example, if a defect is assessed as low risk, it will clearly state "Meets low risk conditions: the defect is located on an important structural component, and the mechanism matching degree is low (overall matching degree less than 0.60)," making the basis for risk classification clear at a glance and avoiding vague statements. At the same time, the module also conducts in-depth analysis of the core risk factors (such as the main defect characteristics, development trends, or mechanism types that lead to the risk), the scope of risk impact (such as the impact on local bridge components, the potential impact on the overall load-bearing capacity of the bridge, etc.), and potential hazards (such as structural damage and safety hazards that may be caused by long-term development), providing a targeted basis for the formulation of subsequent maintenance measures.

[0135] The fifth module is the Supporting Documents Index module. This module is crucial for ensuring the traceability and verifiability of the entire analysis process. Its core function is to summarize all original evidence and cited materials involved in the analysis. The module compiles various types of original evidence data lists (such as original data records from this test, original data collected by sensors, etc.), historical record summaries (such as summaries of relevant paragraphs in historical test reports, summaries of historical maintenance and treatment records, etc.), and lists of cited materials (such as the names and specific clause numbers of bridge industry standards and specifications, referenced engineering practice case numbers, and relevant material numbers from the disease mechanism model library, etc.). To improve traceability efficiency, each supporting document is configured with a corresponding hyperlink or unique index. Hyperlinks provide direct access to electronic versions of original test photos, complete historical reports, and the original text of standards and specifications; indexes allow for quick retrieval of paper versions of supporting documents. This ensures that every data source, every judgment criterion, and the entire logical chain in the analysis process can be accurately verified and traced, guaranteeing the authority and credibility of the analysis conclusions.

[0136] Through the systematic integration of the five core modules mentioned above, the standardized mechanism analysis document transforms the originally scattered detection data and fragmented analysis process into a logically rigorous, clearly evidenced, and traceable formal diagnostic report. This document not only clearly presents the development trend, internal mechanism, and risk level of the defects, but also provides bridge maintenance managers with comprehensive and accurate decision-making basis, helping them to scientifically formulate maintenance plans, rationally prioritize maintenance, and effectively ensure the safe and stable operation of bridge structures.

[0137] Example 2

[0138] Please refer to Figure 8 This embodiment 2 provides a system for judging the development trend and mechanism of bridge defects, including:

[0139] A multi-source evidence fusion system construction unit is used to construct a multi-source evidence fusion system, which includes a basic evidence layer for providing data on the current objective state of the disease, a temporal evidence layer for providing data on the dynamic evolution of the disease, and a knowledge support layer for providing professional knowledge and practical basis for the diagnosis of bridge diseases.

[0140] The evidence collection and trend analysis unit is used to collect basic evidence, temporal evidence and knowledge matching evidence corresponding to the bridge to be diagnosed based on the multi-source evidence fusion system, and to conduct disease development trend analysis by combining quantitative analysis and qualitative judgment. The quantitative analysis obtains the temporal change law of key disease parameters through a preset parameter change rate calculation model. The qualitative judgment divides the development trend into at least three change states according to preset classification rules.

[0141] The mechanism adaptation and risk assessment unit is used to perform adaptation analysis based on the collected multi-source evidence and disease mechanism model library. It determines the adapted disease mechanism type through evidence fit calculation and correlation integrity verification, and conducts risk level assessment based on the development trend judgment results and disease mechanism type.

[0142] The standardized analysis document output unit is used to output the results of disease development trend determination, mechanism adaptation conclusion, evidence fit and risk level assessment, forming a standardized mechanism analysis document.

[0143] Example 3

[0144] This embodiment 3 also provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, it can implement any step of a method for judging the development trend and mechanism of bridge defects.

[0145] The computer-readable storage medium may include various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0146] For a description of the computer-readable storage medium provided in this application, please refer to the above method embodiments; further details will not be repeated here.

[0147] Those skilled in the art will readily understand that the above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for judging the development trend and mechanism of bridge defects, characterized in that, include: S1. Construct a multi-source evidence fusion system, the fusion system including a basic evidence layer for providing data on the current objective state of the disease, a temporal evidence layer for providing data related to the dynamic evolution of the disease, and a knowledge support layer for providing professional knowledge and practical basis for the diagnosis of bridge diseases; S2. Based on the multi-source evidence fusion system, collect basic evidence, temporal evidence and knowledge matching evidence corresponding to the bridge to be diagnosed, and use a combination of quantitative analysis and qualitative judgment to conduct disease development trend analysis. Quantitative analysis uses a pre-defined parameter change rate calculation model to obtain the temporal variation patterns of key disease parameters; The qualitative judgment is based on a pre-defined classification rule, which divides the development trend into at least three categories of change states. S3. Based on the collected multi-source evidence and disease mechanism model library, an adaptation analysis is performed. The appropriate disease mechanism type is determined by evidence fit calculation and correlation integrity verification. The risk level assessment is carried out in combination with the development trend judgment results and disease mechanism type. S4. Output the results of disease development trend determination, mechanism adaptation conclusion, evidence fit and risk level assessment results, and form a standardized mechanism analysis document; The quantitative analysis is based on the availability of historical detection data. The corresponding calculation method is selected according to the completeness of the data in order to obtain the temporal variation pattern of the disease parameters. The qualitative judgment is applicable to scenarios where disease parameters cannot be quantified. In this case, a text analysis method based on semantic rules and keyword matching is used to judge the development trend of the disease by comparing the text information of the current detection description with that of the historical detection description. After completing the quantitative analysis and qualitative judgment, the results of the two types of analysis need to be compared and verified. If the quantitative analysis results are consistent with the qualitative judgment results, then the results will be directly adopted as the final conclusion on the disease development trend; if there are differences between the two types of analysis results, the more conservative judgment result will be adopted by default, and the disease will be given higher attention in subsequent mechanism analysis and risk assessment.

2. The method for judging the development trend and mechanism of bridge defects according to claim 1, characterized in that, The S1 basic evidence layer is configured with quantitative characteristic data, spatial distribution information and apparent state information of bridge defects; the temporal evidence layer is configured with historical detection data, maintenance and treatment records and environmental load time series data related to bridge defects; the knowledge support layer is configured with bridge industry standards, defect mechanism model library and engineering practice case set.

3. The method for judging the development trend and mechanism of bridge defects according to claim 2, characterized in that, The disease mechanism model library is built based on professional knowledge related to bridge disease diagnosis and includes at least two types of coupled diseases, their correlation conditions, manifestations and causes.

4. The method for judging the development trend and mechanism of bridge defects according to claim 1, characterized in that, The specific process of quantitative analysis in S2 is as follows: Based on the availability of historical monitoring data, the corresponding calculation method is used to determine the disease development trend; When only one period of historical monitoring data is available, calculate the basic annualized rate of change of key disease parameters. The calculation formula is: ,in This is the current detection parameter value. These are historical detection parameter values. The time interval between two tests; When multiple historical monitoring data are available, calculate the weighted average annualized rate of change of key disease parameters. The specific steps are as follows: Set the historical detection time point as ,and The corresponding parameter value is , This is the current detection time; Calculate the instantaneous annualized rate of change for each adjacent inspection period. , The calculation formula is: ,in , where is the time interval between adjacent detections; For each Assign weights The weight is inversely proportional to the time distance from the end of the time period to the present, and the calculation formula is as follows: ,in For the first The interval between the current detection time and the present time. To prevent division by zero of small constants; Through formula Calculate the weighted average annualized rate of change ; Based on the rate of change results, trend classification is performed sequentially: when... or When, the corresponding trend is improvement and recovery; when or At that time, the corresponding trend is rapid development; when or At that time, the corresponding trend is slow development; when or At that time, the corresponding trend is towards stability.

5. The method for judging the development trend and mechanism of bridge defects according to claim 1, characterized in that, The specific process of qualitative determination in S2 is as follows: When disease parameters cannot be quantified, a text analysis method based on semantic rules and keyword matching is used to determine the disease development trend by comparing the current and historical detection descriptions. Specifically, this includes: Construct a semantic dictionary of disease development: Establish keyword sets corresponding to different development trend categories, with each set containing words or word combinations that match the characteristics of that trend; Text processing: The current and historical detection description texts are segmented into words and matched with the keyword set in the semantic dictionary mentioned above; Trend determination: Based on the set of keywords matched by the current detection description, the disease development trend is determined according to the preset priority order; Output results: The trend results obtained from the determination will be output as the qualitative analysis results of the disease development trend.

6. The method for judging the development trend and mechanism of bridge defects according to claim 1, characterized in that, The process for determining the appropriate disease mechanism type in S3 is as follows: First, calculate the core evidence matching rate. The calculation formula is: , This represents the number of key pieces of evidence matched in the current disease data. The total amount of core evidence representing the definition of the disease mechanism model; Next, calculate the basic matching degree. A piecewise nonlinear function is used, and the formula is: Subsequently, the disease development trend was defined, including... , , , Four categories, For rapid development, For slow development, In order to achieve stability, To improve and restore; Determine the trend correction coefficient based on the disease development trend. The corresponding rule is hour , hour , hour , hour ; Then through the formula Calculate the overall matching degree Then set the matching degree including , , , Level 4 For a high degree of matching, For a moderate match, The match is relatively poor. The match is low. Based on overall matching degree The rules for determining the degree of matching are as follows: The degree of matching is , The degree of matching is , The degree of matching is , The degree of matching is ; The disease mechanism model type with the highest matching degree is finally output as the appropriate disease mechanism type.

7. The method for judging the development trend and mechanism of bridge defects according to claim 1, characterized in that, The risk level in S3 is divided into at least three levels, and the classification is based on the functional importance of the structural component where the disease is located, the degree of mechanism matching, and the development trend. The specific classification process is as follows: Determine the functional importance level of the structural components where the defects are located: Identify the functional positioning of the structural components where the defects are located in the bridge system, and classify the structural components into two categories: core functional components that bear the main load-bearing function and auxiliary functional components that bear secondary or auxiliary functions. Obtain key assessment parameters: obtain the grade range corresponding to the degree of matching of disease mechanism, and the evolutionary state parameters corresponding to the disease development trend; Risk level classification: Based on preset multi-parameter coupling judgment rules, a comprehensive judgment is made by combining the functional importance level of structural components, the degree of mechanism matching, and the parameters of disease development trend.

8. The method for judging the development trend and mechanism of bridge defects according to claim 1, characterized in that, The standardized mechanism analysis document in S4 includes modules for bridge basic information, development trend analysis, mechanism adaptation conclusions, risk level assessment and supporting materials index, with each module presented in an orderly manner according to logical connections. The bridge basic information module covers the core parameters of the bridge and detection-related information, providing a prerequisite for adapting the results to different scenarios. The development trend analysis module records data on changes in disease parameters, qualitative judgment criteria, and the status of change, clarifying the source of corresponding time-series evidence. The mechanism adaptation conclusion module lists the adapted disease mechanism type, related conditions and cause analysis, explains the evidence fit calculation and correlation integrity verification, and marks the professional supporting materials on which the judgment is based. The risk level assessment module clarifies the risk level results and classification criteria, and analyzes the core risk factors, scope of impact, and potential hazards. The supporting materials index module compiles a list of original data for various types of evidence, a summary of historical records, and a directory of cited materials, ensuring that the data sources, basis, and logical chain of the analysis process can be traced.

9. A system for judging the development trend and mechanism of bridge defects, used to implement the method for judging the development trend and mechanism of bridge defects as described in claim 1, characterized in that, include: A multi-source evidence fusion system construction unit is used to construct a multi-source evidence fusion system, which includes a basic evidence layer for providing data on the current objective state of the disease, a temporal evidence layer for providing data on the dynamic evolution of the disease, and a knowledge support layer for providing professional knowledge and practical basis for the diagnosis of bridge diseases. The evidence collection and trend analysis unit is used to collect basic evidence, temporal evidence and knowledge matching evidence corresponding to the bridge to be diagnosed based on the multi-source evidence fusion system, and to conduct disease development trend analysis by combining quantitative analysis and qualitative judgment. Quantitative analysis uses a pre-defined parameter change rate calculation model to obtain the temporal variation patterns of key disease parameters; The qualitative judgment is based on a pre-defined classification rule, which divides the development trend into at least three categories of change states. The mechanism adaptation and risk assessment unit is used to perform adaptation analysis based on the collected multi-source evidence and disease mechanism model library. It determines the adapted disease mechanism type through evidence fit calculation and correlation integrity verification, and conducts risk level assessment based on the development trend judgment results and disease mechanism type. The standardized analysis document output unit is used to output the results of disease development trend determination, mechanism adaptation conclusion, evidence fit and risk level assessment, forming a standardized mechanism analysis document.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, The computer program is executed by a processor as described in any one of claims 1-8: a method for judging the development trend and mechanism of bridge defects.

Images