A data management and processing system and method based on cloud platform

Abstract

The present invention relates to the field of data processing technology, and more specifically, to a cloud platform-based data management and processing system and method. The system identifies dual-source damage features, calibrates the non-exceeded damage features and their spatial distribution on a target bridge, and assesses the potential for risk evolution based on environmental erosion indicators and load fatigue accumulation indicators, thereby locating each structural damage item. A nonlinear weighted superposition model and cascade effect analysis are used to construct a comprehensive risk fitting function for each structural damage item relative to the target bridge under the multi-factor coupling of traffic, environment, and materials within a predicted time domain. This function is used to determine the time point at which each structural damage item reaches a risk threshold, plan the next maintenance interval for the target bridge, and continuously monitor the actual risk evolution of each structural damage item, thereby achieving adaptive optimization of maintenance decisions, effectively improving the confidence level of maintenance interval decisions, and providing strong data support for bridge safety assurance.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a data management and processing system and method based on a cloud platform. Background Art

[0002] Amidst the surge of digitalization, cloud platforms, with their powerful storage and computing capabilities, have become a key enabler for efficient data management and processing across numerous industries. In transportation infrastructure, bridges, as crucial transportation hubs, are crucial for their safe and stable operation. With the increasing number of bridges being built and their service life increasing, a vast amount of data related to bridge structural health, traffic flow, and environmental factors is continuously generated. How to effectively manage and utilize this data and accurately determine bridge maintenance intervals or timing has become a core issue in ensuring bridge safety, extending service life, and reducing maintenance costs.

[0003] Prior art also includes solutions for analyzing bridge maintenance timing. For example, Chinese patent publication number CN118094415B describes a bridge network maintenance decision-making method and system based on bridge service life. This method sets bridge maintenance parameters throughout the lifecycle, acquires bridge service data, and combines multiple maintenance time points to predict the total carbonization depth of the bridge over its lifecycle under certain maintenance measures. A carbonization depth threshold is set and bridge maintenance parameters are adjusted so that the total carbonization depth over the lifecycle is less than the threshold. This helps select the appropriate time to implement preventive maintenance measures for the bridge, providing an effective preventive management strategy and decision-making tool for urban bridge maintenance management.

[0004] In addition, Chinese patent publication number CN118886333B discloses an intelligent decision-making method and system for bridge maintenance. This method obtains historical bridge maintenance record data and historical bridge traffic record data for analysis to determine bridge damage impact data. Based on a preset calculation model, the method determines the working interval between the last maintenance work and the previous maintenance work according to the bridge damage impact data, and determines bridge maintenance recommendations based on the working interval. In this way, the bridge maintenance time can be predicted, ensuring that the bridge is maintained in a timely manner before problems occur, thereby improving the bridge's service life and safety.

[0005] Although the above two schemes propose solutions for bridge maintenance timing analysis, they still have certain limitations. Specifically, they are as follows: 1. In the existing technology, bridge maintenance timing analysis mainly relies on professional experience testing and recent repair damage data, which carries the risk of missing potential damage items. In addition, the repaired defects cannot accurately represent the structural degradation trend due to the time lag, resulting in a lack of dynamic damage evolution basis for maintenance interval period decisions.

[0006] 2. Although existing bridge maintenance timing analysis technologies have initially integrated the impact of multi-dimensional factors such as traffic loads, environmental erosion, and material properties on the evolution of potential damage, their core is mostly based on a simplified linear weighted superposition algorithm and ignores the chain reaction mechanism of damage. As a result, maintenance timing planning lacks a quantitative assessment of the hidden risks caused by the damage cascade effect, resulting in a decrease in the confidence level of maintenance interval period decisions.

[0007] 3. Existing technologies lack a mechanism for continuously optimizing and tracking bridge maintenance opportunities, which may cause maintenance activities to lag behind actual needs, thereby limiting the effective implementation of bridge health management throughout its life cycle. Summary of the Invention

[0008] In view of this, in order to solve the problems raised in the above background technology, a data management and processing system and method based on a cloud platform are proposed.

[0009] The technical solution adopted by the present invention to solve its technical problems is: First, the present invention provides a data management and processing system based on a cloud platform, including: a structural damage location module, a multi-factor coupling risk prediction module, a maintenance interval period planning module and a maintenance interval period optimization module.

[0010] The structural damage location module is connected to the multi-factor coupling risk prediction module, the multi-factor coupling risk prediction module is connected to the maintenance interval period planning module, and the maintenance interval period planning module is connected to the maintenance interval period optimization module.

[0011] The structural damage location module is used to retrieve the current maintenance operation log of the target bridge. Through dual-source damage feature recognition of image data and monitoring data, it locates the structural areas of the target bridge that have not exceeded the damage limit but have the potential for evolution, and marks them as various structural damage items.

[0012] The multi-factor coupling risk prediction module is used to construct a comprehensive risk fitting function for each structural damage item relative to the target bridge under the multi-factor coupling of traffic, environment, and materials within the prediction time domain by introducing the cascade effect analysis between structural damage items based on the nonlinear weighted superposition model.

[0013] The maintenance interval planning module is used to solve the time node when each structural damage item reaches the risk threshold based on the comprehensive risk fitting function, and plan the interval period for the next maintenance of the target bridge.

[0014] The maintenance interval optimization module is used to continuously monitor the actual risk evolution of each structural damage item, correct the comprehensive risk fitting function based on the predicted risk error, and optimize and provide feedback on the next maintenance interval of the target bridge.

[0015] In a second aspect, the present invention provides a data management and processing method based on a cloud platform, including: S1. Retrieving the current maintenance operation log of the target bridge, and through dual-source damage feature recognition of image data and monitoring data, locating the various structural areas in the target bridge that have not exceeded the damage limit but have evolution potential, and marking them as various structural damage items.

[0016] S2. Based on the nonlinear weighted superposition model, by introducing the cascade effect analysis between structural damage items, a comprehensive risk fitting function for each structural damage item relative to the target bridge is constructed under the multi-factor coupling of traffic, environment, and materials within the prediction time domain.

[0017] S3. Calculate the time point at which each structural damage item reaches the risk threshold based on the comprehensive risk fitting function, and plan the interval period for the next maintenance of the target bridge.

[0018] S4. Continuously monitor the actual risk evolution of each structural damage item, correct the comprehensive risk fitting function based on the predicted risk error, and optimize and provide feedback on the interval period for the next maintenance of the target bridge.

[0019] Compared with the prior art, the embodiments of the present invention have at least the following advantages or beneficial effects: (1) The present invention identifies the damage characteristics of the target bridge that are not exceeded by the limit and maps the spatial location area of the target bridge where they are located through dual-source damage feature recognition, and judges the possible evolution of risks based on environmental erosion indicators and load fatigue accumulation indicators, thereby locating the damage items of each structure, effectively avoiding the limitations of the prior art that relies on empirical detection or maintained disease items, and providing a more complete and accurate data basis for subsequent maintenance decisions.

[0020] (2) Based on the nonlinear weighted superposition model, the present invention constructs an explicit risk fitting function for each structural damage item relative to the target bridge under the multi-factor coupling of traffic, environment and materials in the prediction time domain, which more accurately depicts the evolution law of damage in the prediction time domain, thereby improving the accuracy of risk prediction.

[0021] (3) The present invention reveals the inherent chain relationship of damage evolution by identifying the collection of precursor damage items of structural damage items, and adopts the conditional probability transfer model to quantify the implicit risk transfer weight of the precursor damage items. After superposition, a comprehensive risk fitting function is obtained to achieve a comprehensive, accurate and dynamic assessment of the damage risk of bridge structures.

[0022] (4) The present invention continuously optimizes and tracks the target bridge maintenance timing by establishing a mechanism, so that maintenance activities can be carried out in a timely manner according to actual conditions, providing strong support for achieving efficient management and safety assurance throughout the entire life cycle of the bridge. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The present invention is further described with reference to the accompanying drawings. However, the embodiments in the accompanying drawings do not constitute any limitation to the present invention. A person skilled in the art can obtain other drawings based on the following drawings without creative effort.

[0024] Figure 1 A schematic diagram of module connections of a cloud platform-based data management and processing system provided by one embodiment of the present invention.

[0025] Figure 2 A flowchart of a cloud platform-based data management and processing method provided in accordance with an embodiment of the present invention.

[0026] Figure 3 This is a specific logic diagram for introducing cascade effect analysis between structural damage items into the multi-factor coupling risk prediction module of the present invention.

[0027] Figure 4 A schematic diagram of the structure of a computer device provided in one embodiment of the present invention. DETAILED DESCRIPTION

[0028] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0029] Reference Figure 1 As shown, the first aspect of the present invention provides a data management and processing system based on a cloud platform, including: a structural damage location module, a multi-factor coupling risk prediction module, a maintenance interval planning module and a maintenance interval optimization module.

[0030] The structural damage location module is connected to the multi-factor coupling risk prediction module, the multi-factor coupling risk prediction module is connected to the maintenance interval period planning module, and the maintenance interval period planning module is connected to the maintenance interval period optimization module.

[0031] The structural damage location module is used to retrieve the current maintenance operation log of the target bridge and, through dual-source damage feature recognition using image data and monitoring data, locate various structural areas of the target bridge that have not exceeded the damage limit but have the potential for evolution, and mark them as various structural damage items.

[0032] In a preferred embodiment of the present invention, the specific analysis process of the structural damage location module includes: extracting the appearance image set of each component in the current maintenance operation log of the target bridge, capturing the visual features of each image in the appearance image set of each component, comparing the visual features of each image in the appearance image set with the preset standard visual damage feature library of the target bridge component type to which it belongs through a feature matching algorithm, retrieving the visual damage features matched by each image in the appearance image set of each component, further quantifying the damage parameters corresponding to the visual damage features, and if the damage parameters are less than their preset warning thresholds, marking the visual damage features as non-exceeding-limit damage features.

[0033] It should be noted that the damage parameters corresponding to the above-mentioned visual damage characteristics mainly depend on the damage type to which the visual damage characteristics belong. The following examples provide representative damage parameters corresponding to visual damage characteristics under different damage types.

[0034] The damage parameters corresponding to the visual damage characteristics of cracks include but are not limited to the maximum extension distance along the crack path, the maximum / average width of the crack opening, the extension depth of the crack perpendicular to the surface, the angle between the crack extension direction and the main axis of the structure, the total length of cracks per unit area, the average distance between adjacent parallel cracks, and the number of forks at the end of the crack.

[0035] The damage parameters corresponding to the visual damage characteristics of rust include but are not limited to rust area, rust pit density, average rust depth, and maximum local rust depth.

[0036] The damage parameters corresponding to the visual damage characteristics of concrete spalling / hollowing include but are not limited to spalling area, spalling depth, hollowing area and edge fragmentation.

[0037] The requirement for the above-mentioned visual damage characteristics to be damage characteristics that do not exceed the limit is that all of its damage parameters are smaller than the corresponding preset warning thresholds.

[0038] The monitoring data set of each component in the current maintenance operation log of the target bridge is extracted. The monitoring data set contains the measured values of each monitoring indicator. The monitoring data set is compared with the preset standard threshold library of monitoring indicators for the target bridge component type to which it belongs. The monitoring indicators with deviations in the measured values in the monitoring data set are identified, and the measured value deviations are associated with the corresponding abnormal damage characteristics. The abnormal parameters of the corresponding abnormal damage characteristics are further quantified. If the abnormal parameters are less than their preset warning thresholds, the abnormal damage characteristics are marked as within the limit damage characteristics.

[0039] It should be noted that the association of measured numerical deviations with corresponding abnormal damage characteristics is primarily based on bridge design specifications and health monitoring standards. Senior professionals in the field apply their expertise and experience to establish a statistical correlation system between monitoring indicators and damage characteristics. For example, abnormal damage characteristics related to support settlement / deformation are associated with measured deviation monitoring indicators including: abnormal support displacement (support settlement causing beam tilt), abnormal support strain (support deformation causing stress redistribution), and abnormal support vibration frequency (support failure causing changes in overall stiffness). The corresponding abnormal parameters are settlement, tilt angle, and support displacement time history.

[0040] In a preferred embodiment of the present invention, the specific analysis process of the structural damage location module also includes: constructing a three-dimensional coordinate grid of the target bridge based on the laser point cloud data, and mapping each non-exceeding damage feature to the spatial position area of the corresponding target bridge component.

[0041] Based on the environmental erosion indicators and load fatigue accumulation indicators of the spatial location area of the target bridge where each non-exceeded damage feature is located, each non-exceeded damage feature is evaluated to determine whether it has the potential for risk evolution. If a non-exceeded damage feature is judged to have the potential for risk evolution, the spatial location area of the target bridge where the non-exceeded damage feature is located is regarded as a structural area of the target bridge with non-exceeded damage but with evolution potential. At the same time, a label for the non-exceeded damage feature is attached, thereby locating the structural areas of the target bridge with non-exceeded damage but with evolution potential.

[0042] It should be noted that the specific judgment logic for whether the above-mentioned non-exceeded damage features have the possibility of risk evolution is as follows: based on the historical environmental monitoring log of the target bridge, the regular numerical range of each environmental parameter of the spatial location area of the target bridge where each non-exceeded damage feature is located is obtained; based on the preset damage-environment association mapping table, the sensitive environmental parameter sequence of the damage type to which each non-exceeded damage feature belongs is retrieved; if the spatial location area of the target bridge where the non-exceeded damage feature is located involves its sensitive environmental parameters, it means that the spatial location area of the target bridge where the non-exceeded damage feature is located is the environmental sensitive domain of the damage type to which it belongs; on this basis, if the regular numerical range of the sensitive environmental parameters reaches the preset erosion standard threshold, the output environmental erosion indicator flag of the spatial location area of the target bridge where the non-exceeded damage feature is located is 1, otherwise the output is 0.

[0043] Based on the historical traffic monitoring logs of the target bridge, the high-frequency load ratio (the average daily frequency of exceeding the target bridge design load by 30%), load fluctuation amplitude (maximum / minimum load ratio, used to reflect fatigue damage sensitivity), and load time series characteristics (number of consecutive overload cycles) of the spatial location area of the target bridge where each non-exceeded damage feature is located are obtained. If the high-frequency load ratio, load fluctuation amplitude, and load time series characteristics of the spatial location area of the target bridge where the non-exceeded damage feature is located are all greater than or equal to their corresponding preset thresholds, the load fatigue accumulation indicator flag of the spatial location area of the target bridge where the non-exceeded damage feature is located is output as 1, otherwise the output is 0.

[0044] When the load fatigue accumulation indicator flag or the environmental erosion indicator flag of the target bridge spatial position area where the non-exceeding damage feature is located is output as 1, the non-exceeding damage feature is judged to have the possibility of risk evolution. When the load fatigue accumulation indicator flag and the environmental erosion indicator flag of the target bridge spatial position area where the non-exceeding damage feature is located are both output as 0, the non-exceeding damage feature is judged not to have the possibility of risk evolution.

[0045] The embodiment of the present invention uses dual-source damage feature identification to calibrate the non-exceeded damage features of the target bridge and map the spatial location area of the target bridge where they are located. It then assesses the possible evolution of risks based on environmental erosion indicators and load fatigue accumulation indicators, and locates each structural damage item. This effectively avoids the limitations of existing technologies that rely on empirical testing or maintained disease items, and provides a more complete and accurate data basis for subsequent maintenance decisions.

[0046] The multi-factor coupling risk prediction module is used to construct a comprehensive risk fitting function for each structural damage item relative to the target bridge under the multi-factor coupling of traffic, environment and materials within the prediction time domain by introducing the cascade effect analysis between structural damage items based on a nonlinear weighted superposition model.

[0047] In a preferred embodiment of the present invention, the specific analysis process of the multi-factor coupling risk prediction module includes: constructing independent risk fitting functions of each structural damage item relative to the target bridge under the effects of traffic load, environmental erosion, and material performance degradation in the prediction time domain, and marking them in order. ,in is the time variable, is the number of each structural damage item, , through the nonlinear weighted superposition model Obtain the explicit risk fitting function of each structural damage item under the multi-factor coupling of traffic, environment and material in the prediction time domain, where is the number of each factor affecting the damage item of the target bridge structure, , is the first item affecting the damage of the target bridge structure. The preset weight coefficients of the factors, is the preset coupling coefficient, which is used to quantify the strength of multi-factor interactions.

[0048] It should be noted that in the above nonlinear weighted superposition model is a linear weighted term, which is used to reflect the risk contribution of the structural damage item under the independent effects of traffic load factors, environmental erosion factors, and material performance degradation factors. Mainly based on a series of experimental data, the variance contribution ratio of traffic load factors, environmental erosion factors, and material performance degradation factors to the damage rate is calculated using regression analysis. The ratio of the variance contribution ratio of each factor to the sum of the variance contribution ratios of all factors to the damage rate is used as the weight coefficient. It is specially noted that the variance contribution ratio is the square value of the standardized regression coefficient.

[0049] It is a nonlinear coupling term, which is used to reflect the additional risk increment of the structural damage item when it is affected by traffic load factors, environmental erosion factors, and material performance degradation factors. This can be obtained using machine learning optimization methods. Specifically, historical damage data for the target bridge, including but not limited to records of crack development, material aging, and other types of damage over time, can be extracted as a dataset for training the machine learning model. A loss function, such as mean squared error, is constructed to quantify the difference between the model's predicted values and the actual observed values. This loss function is then minimized using an optimization algorithm, and the simulated value of the coupling coefficient corresponding to the minimized damage function is used as the preset coupling coefficient.

[0050] In a preferred embodiment of the present invention, the The specific construction process includes: retrieving historical traffic monitoring logs to analyze the typical traffic flow intervals of the target bridge in each time period of each day within the prediction time domain, using this as a constraint condition, using Monte Carlo simulation to generate random traffic flows, simulating the random traffic changes of different vehicle weights, speeds and lane distributions passing through the target bridge in the prediction time domain every day, analyzing the cumulative damage characteristic values of each structural damage item under the action of traffic loads on each day in the prediction time domain through simulation performance data, and determining its risk coefficient relative to the target bridge, and importing the risk coefficient time series data into Matlab software, thereby generating an independent risk fitting function for each structural damage item under the action of traffic loads in the prediction time domain relative to the target bridge.

[0051] It should be noted that the specific analysis method for the typical traffic flow intervals of each time period every day within the prediction time domain of the above-mentioned target bridge is as follows: the traffic flow data of each time period of each day within each reference time threshold are retrieved from the historical traffic monitoring log, and the calculated mean of the traffic flow data of the same time period of each day within each reference time threshold is used as the median value of the typical traffic flow interval, the maximum traffic flow and the minimum traffic flow of the same time period of each reference time threshold are collected, and the difference between the maximum traffic flow and the minimum traffic flow is used as the traffic flow span, and the calculated mean of the traffic flow span of each reference time threshold is used as the typical traffic flow interval span, thereby obtaining the typical traffic flow interval of each time period every day within the prediction time domain of the target bridge. It should be noted that the time span of each reference time threshold is the same as that of the prediction time domain, and each reference time domain can be the same time period of the corresponding prediction time domain in each historical year or a fixed time span pushed forward from the current time node.

[0052] The specific analysis method for the cumulative damage characteristic values of the above-mentioned structural damage items under traffic loads on each day within the prediction time domain is as follows: the original material stress-life curve formula (without the influence of material degradation performance) of the target bridge component position where each structural damage item is located in the current maintenance operation log of the target bridge is retrieved, and combined with Miner's linear cumulative damage theory, the cumulative damage characteristic values of each structural damage item under traffic loads on each day within the prediction time domain are calculated. The stress values of each day in the prediction time domain are directly derived from the simulation performance data of the Monte Carlo simulation.

[0053] The cumulative risk damage characteristic threshold of each damage type of each structural damage item under traffic load, which is set by system development, is extracted. The ratio of the cumulative damage characteristic value of each structural damage item under traffic load on each day within the prediction time domain to its corresponding cumulative risk damage characteristic threshold is used as the risk coefficient relative to the target bridge.

[0054] In a preferred embodiment of the present invention, the The specific construction process includes: retrieving historical environmental monitoring logs to analyze the predicted values of each environmental parameter of the target bridge on each day within the prediction time domain; determining the sensitive environmental parameter sequence of each structural damage item and the preset correlation factors of each sensitive environmental parameter based on the preset damage-environment correlation mapping table; analyzing the cumulative damage characteristic value of each structural damage item under the action of environmental erosion on each day within the prediction time domain; similarly determining its risk coefficient relative to the target bridge; and further generating an independent risk fitting function for each structural damage item under the action of environmental erosion within the prediction time domain relative to the target bridge.

[0055] It should be noted that the specific analysis method of the predicted values of each environmental parameter on each day in the prediction time domain of the above-mentioned target bridge can be achieved by outlining the curve of the change of each environmental parameter of the target bridge over time through the actual values of each environmental parameter in the historical time domain in the historical environmental monitoring log, and then obtaining the best fitting function of the change of each environmental parameter of the target bridge over time, and importing the time amount of each day in the prediction time domain into it to obtain the corresponding predicted value.

[0056] The specific analysis method of the cumulative damage characteristic value under environmental erosion on each day in the prediction time domain of each structural damage item is as follows: each sensitive environmental parameter in the sensitive environmental parameter sequence of each structural damage item is normalized, and the product of the normalized sensitive environmental parameter value and its corresponding preset correlation factor is used as the damage contribution of the sensitive environmental parameter. The sum of the damage contributions of each sensitive environmental parameter on a single day can be used as the single-day damage characteristic value of the structural damage item, and the damage characteristic value of each day in the prediction time domain of the structural damage item is determined. , according to the formula The cumulative damage characteristic value under environmental erosion on each day in the structural damage prediction time domain is obtained, where is the number of each day in the forecast time domain, , To preset seasonal correction factors (e.g. when freeze-thaw occurs frequently in winter ,summer ).

[0057] For example, assuming that each sensitive environmental parameter in the sensitive environmental parameter sequence of steel bar corrosion damage of the target bridge is humidity and its preset correlation factors , salt spray and its preset correlation factors The forecast time range is 30 days, and the seasonal correction factor is preset. ,The environmental data of the first five days are shown in Table 1.

[0058] Table 1: Environmental data for the previous 5 days

[0059]

[0060] It is further necessary to add that The specific construction process includes: determining the material performance indicators involved in the target bridge component position of each structural damage item, based on the current life of the material performance at the target bridge component position of each structural damage item recorded in the latest maintenance report of the target bridge, clarifying the performance attenuation trend of the materials involved in the target bridge component position of each structural damage item of the target bridge within the prediction time domain, obtaining the corresponding cumulative damage characteristic value relative to each structural damage item, further obtaining the risk coefficient relative to the target bridge, and generating an independent risk fitting function for each structural damage item relative to the target bridge under the action of material performance degradation within the prediction time domain.

[0061] The embodiment of the present invention is based on a nonlinear weighted superposition model to construct an explicit risk fitting function for each structural damage item relative to the target bridge under the multi-factor coupling of traffic, environment and materials in the prediction time domain, so as to more accurately characterize the evolution law of the damage in the prediction time domain, thereby improving the accuracy of risk prediction.

[0062] Reference Figure 3 As shown, in a preferred embodiment of the present invention, the specific analysis process of the multi-cause coupling risk prediction module further includes: randomly selecting a structural damage item and marking it as a target damage item; searching for upstream structural damage items that have a cascade effect with the target damage item from other structural damage items other than the target damage item through a preset bridge damage causal network; and forming the target damage item. Collection of precursor damage items , is the number of each precursor damage item, .

[0063] It should be noted that the bridge damage causal network is a causal relationship knowledge base based on a graph model, which describes the induction, conduction and dependency relationships between the various structural damage items of the bridge in the form of a directed graph. The cascade effect is specifically expressed as the deterioration of a certain structural damage item triggering the accelerated development of downstream structural damage items through a domino-like chain reaction, forming a damage propagation chain. The bridge damage causal network of the present invention is composed of various levels of cascade chains including nodes (representing damage feature types), directed edges (representing causal directions) and preset edge weights (representing causal strengths between adjacent nodes), as well as preset independent occurrence weights of various damage features. The cascade chain can be exemplified by the scouring of the abutment foundation. Uneven settlement of bridge piers Main beam deflection exceeds limit The bridge deck pavement is cracked.

[0064] Transfer model via conditional probabilities Calculate the implicit risk transfer weight of each precursor damage item to the target damage item, where For the The probability of the target damage item occurring under the condition of the occurrence of the precursor damage item is: 、 Respectively The probability of the independent occurrence of the precursor damage item and the target damage item is calculated, and the implicit risk transfer weight of each precursor damage item is superimposed on the explicit risk fitting function corresponding to the target damage item. , the specific expression formula is ,in For the The explicit risk fitting function of the precursor damage item is used to generate the comprehensive risk fitting function of the target damage item under the coupling of traffic, environment and materials in the prediction time domain.

[0065] It should be noted that the specific calculation logic of the above conditional probability transfer model is: transform the set of predecessor damage items of the target damage item into a cascade chain, expressed as ,So for The cumulative value of the edge weights, For the Each precursor damage item is preset with independent occurrence weights. The cumulative value of the product of the preset independent occurrence weight of the target damage item and the preset independent occurrence weights of its upstream structural damage items on the same side.

[0066] For example, if the cascade chain is , The corresponding preset independent occurrence weights are 0.1, 0.2, and 0.05, then is 0.4, is 0.154, and the calculation process is 0.05+0.4*0.2+0.1*0.24, =0.26, the calculation process is 0.1*0.6+0.2, and the implicit risk transfer weight of the first precursor damage item to the target damage item is calculated. .

[0067] It's important to note that in the application of the aforementioned conditional probability transfer model, a preset lower limit is typically set to ensure the rationality and reliability of the calculation results. This lower limit serves as a threshold for the model output, addressing uncertainty or data sparsity in extreme cases. Specifically, when the calculated result of the conditional probability transfer model falls below this preset lower limit, the system automatically adopts this preset lower limit as the final calculation result, aiming to prevent risk misjudgments or decision-making errors caused by underestimating probabilities.

[0068] The embodiment of the present invention reveals the inherent chain relationship of damage evolution by identifying the collection of precursor damage items of structural damage items, and adopts the conditional probability transfer model to quantify the implicit risk transfer weight of the precursor damage items. After superposition, a comprehensive risk fitting function is obtained to achieve a comprehensive, accurate and dynamic assessment of the damage risk of bridge structures.

[0069] The maintenance interval planning module is used to solve the time node when each structural damage item reaches the risk threshold based on the comprehensive risk fitting function, and plan the interval period for the next maintenance of the target bridge.

[0070] In a preferred embodiment of the present invention, the specific analysis process of the maintenance interval planning module includes: obtaining the predicted interval period of the time node when each structural damage item reaches the risk threshold relative to the current time node, and using the difference between the shortest predicted interval period and the preset reserved buffer period as the interval period for the next maintenance of the target bridge.

[0071] The maintenance interval optimization module is used to continuously monitor the actual risk evolution of each structural damage item, correct the comprehensive risk fitting function based on the predicted risk error, and optimize and provide feedback on the next maintenance interval of the target bridge.

[0072] In a preferred embodiment of the present invention, the specific analysis process of the maintenance interval optimization module includes: formulating a monitoring frequency plan based on the interval period of the next maintenance of the target bridge in accordance with the principle of increasing risk gradient, and analyzing the actual risk coefficient of each structural damage item relative to the target bridge at the target monitoring time node based on the cumulative damage characteristic value fed back by actual monitoring.

[0073] Based on the predicted risk coefficient fed back by the comprehensive risk fitting function of each structural damage item relative to the target bridge under the multi-factor coupling of traffic, environment and materials in the prediction time domain for the target monitoring time node, the predicted risk error of each structural damage item at the target monitoring time node is calculated. If the predicted risk error of a structural damage item at the target monitoring time node is greater than the preset reasonable risk error threshold, the comprehensive risk fitting function of the structural damage item is corrected, and the corrected comprehensive risk fitting functions of each structural damage item are sorted out to re-plan the interval period of the next maintenance of the target bridge.

[0074] It should be noted that the predicted risk error at the monitoring time node of each of the above-mentioned structural damage project targets is the difference between the predicted risk coefficient and the actual risk coefficient.

[0075] It should also be noted that the specific method of correcting the comprehensive risk fitting function of the structural damage item is to traverse the actual risk coefficients of the target monitoring time node and its previous monitoring time nodes, and adjust the posterior probability through the Bayesian method to obtain the comprehensive risk fitting function parameters.

[0076] The embodiment of the present invention continuously optimizes and tracks the target bridge maintenance timing by establishing a mechanism, so that maintenance activities can be carried out in a timely manner according to actual conditions, providing strong support for achieving efficient management and safety assurance throughout the entire life cycle of the bridge.

[0077] It should be added that all preset parameters involved in the embodiments of the present invention are derived from system development and implantation, and can be directly extracted from the system cloud database.

[0078] Reference Figure 2 As shown, the second aspect of the present invention provides a data management and processing method based on a cloud platform, including: S1. Retrieving the current maintenance operation log of the target bridge, and through dual-source damage feature recognition of image data and monitoring data, locating the various structural areas in the target bridge that have not exceeded the damage limit but have evolution potential, and marking them as various structural damage items.

[0079] S2. Based on the nonlinear weighted superposition model, by introducing the cascade effect analysis between structural damage items, a comprehensive risk fitting function for each structural damage item relative to the target bridge is constructed under the multi-factor coupling of traffic, environment, and materials within the prediction time domain.

[0080] S3. Determine the time point at which each structural damage item reaches the risk threshold based on the comprehensive risk fitting function, and plan the interval period for the next maintenance of the target bridge.

[0081] S4. Continuously monitor the actual risk evolution of each structural damage item, correct the comprehensive risk fitting function based on the predicted risk error, and optimize and provide feedback on the interval period for the next maintenance of the target bridge.

[0082] The embodiment of the present invention provides a data management and processing method based on a cloud platform. Its implementation principle and technical effects are the same as those of the aforementioned system embodiment. For the sake of brief description, for matters not mentioned in the method embodiment, please refer to the corresponding content in the aforementioned system embodiment.

[0083] In an exemplary embodiment, a computer device is provided. The computer device may be a server or a terminal. The internal structure diagram thereof may be as follows: Figure 4 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, I / O) and a communication interface. The processor, memory and input / output interface are connected via a system bus, and the communication interface is connected to the system bus via the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The database of the computer device is used to store matching data sets of the test sea area. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a data management and processing method based on a cloud platform is implemented.

[0084] Those skilled in the art will understand that Figure 4 The structure shown in the figure is merely a block diagram of a portion of the structure related to the solution of the present invention and does not limit the computer device to which the solution of the present invention is applied. A specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement. In an exemplary embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the steps of the above-mentioned method embodiments are implemented.

[0085] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0086] In an exemplary embodiment, a computer program product is provided, including a computer program. When the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0087] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in the present invention are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0088] Those skilled in the art will appreciate that all or part of the processes in the above-described method embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the above-described method embodiments. Any reference to memory, database, or other media used in the embodiments provided herein may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory may include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0089] The database involved in each embodiment provided by the present invention may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, distributed databases based on blockchain. The processor involved in each embodiment provided by the present invention may be, but is not limited to, a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic unit, a data processing logic unit based on quantum computing, etc.

[0090] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0091] This document uses specific examples to illustrate the principles and implementation methods of the present invention. The above examples are only intended to help understand the method and core concept of the present invention. At the same time, those skilled in the art will find that the specific implementation methods and application scopes may vary based on the concept of the present invention. In summary, the contents of this specification should not be construed as limiting the present invention.

Claims

1. A data management and processing system based on a cloud platform, characterized in that: The system includes: The structural damage location module retrieves the current maintenance log of the target bridge and uses dual-source damage feature recognition from image data and monitoring data to locate structural areas of the target bridge that have not exceeded damage limits but have the potential to evolve, marking them as structural damage items. The multi-factor coupling risk prediction module is used to construct a comprehensive risk fitting function for each structural damage item relative to the target bridge under the multi-factor coupling of traffic, environment, and materials within the prediction time domain by introducing the cascade effect analysis between structural damage items based on the nonlinear weighted superposition model. The specific analysis process of the multi-factor coupling risk prediction module includes: constructing independent risk fitting functions of each structural damage item relative to the target bridge under the effects of traffic load, environmental erosion, and material performance degradation in the prediction time domain, and marking them in order. ,in is the time variable, is the number of each structural damage item, , through the nonlinear weighted superposition model Obtain the explicit risk fitting function of each structural damage item under the multi-factor coupling of traffic, environment and material in the prediction time domain, where is the number of each factor affecting the damage item of the target bridge structure, , is the first item affecting the damage of the target bridge structure. The preset weight coefficients of the factors, is the preset coupling coefficient, which is used to quantify the strength of multi-factor interaction; The specific analysis process of the multi-cause coupling risk prediction module further includes: randomly selecting a structural damage item and marking it as a target damage item; searching for upstream structural damage items that have a cascade effect with the target damage item from other structural damage items other than the target damage item through a preset bridge damage causal network, and forming a collection of precursor damage items of the target damage item; The implicit risk transfer weights of each precursor damage item for the target damage item are calculated using a conditional probability transfer model. These implicit risk transfer weights are then added to the explicit risk fitting function corresponding to the target damage item. This generates a comprehensive risk fitting function for the target damage item within the prediction time domain under the coupling effects of multiple factors: traffic, environment, and materials. The maintenance interval planning module is used to calculate the time point when each structural damage item reaches the risk threshold based on the comprehensive risk fitting function, and plan the next maintenance interval of the target bridge; The maintenance interval optimization module is used to continuously monitor the actual risk evolution of each structural damage item, correct the comprehensive risk fitting function based on the predicted risk error, and optimize and provide feedback on the next maintenance interval of the target bridge.

2. The cloud platform-based data management and processing system according to claim 1, characterized in that: The specific analysis process of the structural damage location module includes: extracting the appearance image set of each component in the current maintenance operation log of the target bridge, capturing the visual features of each image in the appearance image set of each component, comparing the visual features of each image in the appearance image set with a preset standard visual damage feature library of the target bridge component type to which it belongs through a feature matching algorithm, retrieving the visual damage features matched by each image in the appearance image set of each component, further quantifying the damage parameter corresponding to the visual damage feature, and marking the visual damage feature as a damage feature that does not exceed the limit if the damage parameter is less than its preset warning threshold; The monitoring data set of each component in the current maintenance operation log of the target bridge is extracted. The monitoring data set contains the measured values of each monitoring indicator. The monitoring data set is compared with the preset standard threshold library of monitoring indicators for the target bridge component type to which it belongs. The monitoring indicators with deviations in the measured values in the monitoring data set are identified, and the measured value deviations are associated with the corresponding abnormal damage characteristics. The abnormal parameters of the corresponding abnormal damage characteristics are further quantified. If the abnormal parameters are less than their preset warning thresholds, the abnormal damage characteristics are marked as within the limit damage characteristics.

3. The cloud platform-based data management and processing system according to claim 2, characterized in that: The specific analysis process of the structural damage location module also includes: constructing a three-dimensional coordinate grid of the target bridge based on the laser point cloud data, and mapping each non-exceeded damage feature to the spatial location area of the corresponding target bridge component; Based on the environmental erosion indicators and load fatigue accumulation indicators of the spatial location area of the target bridge where each non-exceeded damage feature is located, each non-exceeded damage feature is evaluated to determine whether it has the potential for risk evolution. If a non-exceeded damage feature is judged to have the potential for risk evolution, the spatial location area of the target bridge where the non-exceeded damage feature is located is regarded as a structural area of the target bridge with non-exceeded damage but with evolution potential. At the same time, a label for the non-exceeded damage feature is attached, thereby locating the structural areas of the target bridge with non-exceeded damage but with evolution potential.

4. The cloud platform-based data management and processing system according to claim 3, characterized in that: described The specific construction process includes: retrieving historical traffic monitoring logs to analyze the typical traffic flow intervals of the target bridge at each time period during the daily prediction time domain, using this as a constraint condition, using Monte Carlo simulation to generate random traffic flows, analyzing the cumulative damage characteristic values of each structural damage item under the action of traffic loads on each day during the prediction time domain through simulated performance data, and determining its risk coefficient relative to the target bridge, importing the risk coefficient time series data into Matlab software, and thus generating an independent risk fitting function for each structural damage item under the action of traffic loads within the prediction time domain relative to the target bridge.

5. The cloud platform-based data management and processing system according to claim 4, characterized in that: described The specific construction process includes: retrieving historical environmental monitoring logs to analyze the predicted values of each environmental parameter of the target bridge on each day within the prediction time domain; determining the sensitive environmental parameter sequence of each structural damage item and the preset correlation factors of each sensitive environmental parameter based on the preset damage-environment correlation mapping table; analyzing the cumulative damage characteristic value of each structural damage item under the action of environmental erosion on each day within the prediction time domain; similarly determining its risk coefficient relative to the target bridge; and further generating an independent risk fitting function for each structural damage item under the action of environmental erosion within the prediction time domain relative to the target bridge.

6. The cloud platform-based data management and processing system according to claim 1, characterized in that: The specific analysis process of the maintenance interval planning module includes: obtaining the predicted interval period of the time node when each structural damage item reaches the risk threshold relative to the current time node, and using the difference between the shortest predicted interval period and the preset reserved buffer period as the interval period for the next maintenance of the target bridge.

7. The cloud platform-based data management and processing system according to claim 1, characterized in that: The specific analysis process of the maintenance interval optimization module includes: formulating a monitoring frequency plan based on the interval of the next maintenance of the target bridge according to the principle of increasing risk gradient, and analyzing the actual risk coefficient of each structural damage item relative to the target bridge at the target monitoring time node; Based on the predicted risk coefficient fed back by the comprehensive risk fitting function of each structural damage item relative to the target bridge under the multi-factor coupling of traffic, environment and materials in the prediction time domain for the target monitoring time node, the predicted risk error of each structural damage item at the target monitoring time node is calculated. If the predicted risk error of a structural damage item at the target monitoring time node is greater than the preset reasonable risk error threshold, the comprehensive risk fitting function of the structural damage item is corrected, and the corrected comprehensive risk fitting functions of each structural damage item are sorted out to re-plan the interval period of the next maintenance of the target bridge.

8. A data management and processing method based on a cloud platform, characterized in that: The method includes: S1. Retrieve the current maintenance log of the target bridge and, through dual-source damage feature recognition using image data and monitoring data, locate structural areas of the target bridge that have not exceeded damage limits but have the potential to evolve, and mark them as structural damage items. S2. Based on a nonlinear weighted superposition model, by introducing the cascade effect analysis between structural damage items, a comprehensive risk fitting function for each structural damage item relative to the target bridge is constructed under the multi-factor coupling of traffic, environment, and materials within the prediction time domain. The specific analysis process includes: constructing the independent risk fitting function of each structural damage item relative to the target bridge under the effects of traffic load, environmental erosion, and material performance degradation in the prediction time domain, and marking them in order. ,in is the time variable, is the number of each structural damage item, , through the nonlinear weighted superposition model Obtain the explicit risk fitting function of each structural damage item under the multi-factor coupling of traffic, environment and material in the prediction time domain, where is the number of each factor affecting the damage item of the target bridge structure, , is the first item affecting the damage of the target bridge structure. The preset weight coefficients of the factors, is the preset coupling coefficient, which is used to quantify the strength of multi-factor interaction; The specific analysis process also includes: randomly selecting a structural damage item and marking it as the target damage item; using a preset bridge damage causal network, searching for upstream structural damage items that have a cascade effect with the target damage item from all other structural damage items except the target damage item to form a collection of predecessor damage items of the target damage item; The implicit risk transfer weights of each precursor damage item for the target damage item are calculated using a conditional probability transfer model. These implicit risk transfer weights are then added to the explicit risk fitting function corresponding to the target damage item. This generates a comprehensive risk fitting function for the target damage item within the prediction time domain under the coupling effects of multiple factors: traffic, environment, and materials. S3. Determine the time point at which each structural damage item reaches the risk threshold based on the comprehensive risk fitting function, and plan the next maintenance interval for the target bridge; S4. Continuously monitor the actual risk evolution of each structural damage item, correct the comprehensive risk fitting function based on the predicted risk error, and optimize and provide feedback on the interval period for the next maintenance of the target bridge.

Images