Bridge performance evaluation and life prediction method based on big data analysis

Abstract

The invention provides a bridge performance evaluation and life prediction method based on big data analysis, and relates to the technical field of bridge preventive maintenance in highway engineering, and the method comprises the steps: obtaining three-dimensional scanning data of an old bridge and a new bridge under a common service condition, and combining with complex service conditions such as dynamic load, temperature difference, creep shrinkage, etc. And the dynamic response of the connection part in an actual use environment can be accurately simulated and evaluated. Especially under the condition of common service of new and old bridges, the degradation and damage of the connection part are particularly significant, and by combining with a big data technology, the progress of material aging is tracked in real time, and possible hidden damage of the connection part is helped to be predicted. By constructing the aging factor, the damage index and the corrosion index and associating the aging factor, the damage index and the corrosion index with the connection coordination index graph, a specific rigidity loss factor can be provided for each connection unit, the performance degradation degree of the bridge connection part is reflected, and a scientific basis is provided for subsequent reinforcement and maintenance strategies.

Description

Technical Field

[0001] The present invention relates to the technical field of preventive maintenance of bridges in highway engineering, and specifically to a method for bridge performance evaluation and life prediction based on big data analysis. Background Technique

[0002] With the rapid development of the transportation industry, China's economic society has made remarkable progress in recent years. However, many early-built highway bridges are no longer able to meet the current and future traffic demands due to the sharp increase in traffic volume, and there is an urgent need for widening and upgrading. As a core component of the highway transportation network, bridges play a crucial role in highway reconstruction and expansion projects. Especially those bridges that have been in service for many years, under long-term overloaded operation, the early design usually did not take into account the impact of the current surge in traffic volume, resulting in the gradual emergence of the phenomenon of "premature aging" of bridge performance.

[0003] In addition, restricted by the early construction technology and the lag of maintenance technology, although many bridges seemingly still remain in good condition in the conventional technical condition assessment, in fact, the degradation and aging problems of local structures have quietly emerged. Especially in some connection parts, there may be hidden safety hazards, and these problems are difficult to be detected in time during routine inspections. The existence of these problems not only affects the normal use of the bridge but also threatens the safe operation of the bridge. To sum up, with structural degradation, the connection points of old and new bridges are usually the parts where the performance degradation is most significant. Especially in the case of co-service, the aging process of the connection part is closely related to the performance of the whole bridge. Therefore, for the safety hazard assessment and prediction of the co-service connection part, there is an urgent need to propose a method for bridge performance evaluation and life prediction based on big data analysis to reduce the prediction of hidden safety hazards in the connection part.

[0004] The above information disclosed in the background art section is only used to enhance the understanding of the background of the present disclosure, and thus it may include information that does not constitute the prior art known to those of ordinary skill in the art. Summary of the Invention

[0005] The purpose of the present invention is to provide a method for bridge performance evaluation and life prediction based on big data analysis to solve the problems raised in the above background art.

[0006] To achieve the above purpose, the present invention provides the following technical solutions: A method for bridge performance evaluation and life prediction based on big data analysis, and the specific steps include: Step 1: Obtain the 3D scan data of the connection structure of the old bridge and the new bridge under the condition of co - service, conduct mesh division to form a number of connection units, establish a finite - element model, simulate the real - service conditions of vehicle load, temperature difference, and creep shrinkage, and construct the displacement vector of the i - th connection unit ; Step 2: Preset the displacement - coordination limit value. When the displacement vector of the i - th connection unit is compared with the displacement - coordination limit value, obtain the first connection - coordination evaluation result, and construct the initial connection - coordination index diagram; Step 3: Collect the service life, external cracks, cavities, and rust conditions of the materials in the connection units to establish a material - degradation data set; combine the initial connection - coordination index diagram, use a convolutional neural network to construct a bridge service - performance evolution model. After inputting the material - degradation data set into the bridge service - performance evolution model for training, construct the aging factor 、damage index and rust index of the i - th connection unit. After correlation, obtain the stiffness - loss factor of the i - th connection unit, and perform degradation correction on the displacement vector of the i - th connection unit to obtain the second coordination index of the i - th connection unit, and correct the initial connection - coordination index diagram to obtain the second connection - coordination index diagram, so as to output the prediction results and corresponding strategies of the old bridge during the co - service period of the old and new bridges.

[0007] Furthermore, Step 1 includes: S11: Use a laser scanner to conduct a full - range scan of the connection structure of the old bridge and the new bridge under the condition of co - service, obtain 3D scan data, establish a finite - element model of the connection structure based on the 3D data, and perform material assignment and boundary - condition setting on the connection structure; S12: Conduct mesh division on the connection structure in the finite - element model to form a number of discrete connection units, and each connection unit is marked as the i - th connection unit; S13: After simulating the real - service conditions of vehicle load, temperature difference, and creep shrinkage in the finite - element model, apply the load vector to each connection unit, and collect the thermal strain caused by the temperature difference , creep stress and shrinkage stress , and construct the displacement vector of the i - th connection unit in the finite - element model.

[0008] Furthermore, Step S13 includes: S131: Collect and obtain the elastic modulus E of the material used for the i - th connection unit; S132. Apply boundary conditions and vehicle loads: Collect historical data, obtain the average vehicle load of the historical data, and convert it into a force vector on nodes or surfaces according to the average vehicle load, and apply it as an external mechanical load to the connection unit nodes or unit surfaces of the finite element model to form a load vector. ; S133. Use the temperature sensors installed on the bridge to monitor the temperature changes at different times and positions, and obtain the linear expansion coefficients of concrete and steel bars in the bridge components through material test reports or standard data. , and calculate the temperature difference according to the thermal expansion theory. The thermal strain caused. ; Convert the thermal strain into thermal stress, and calculate the thermal load in combination with the material elastic modulus E. S134. Collect and use the strain sensors installed on the bridge to monitor the deformation of the reinforced concrete structure in the bridge components under long-term loads in real time, pay attention to the influence of creep and shrinkage on the connection unit, and calculate the creep thermal deformation. ; S135. The shrinkage strain is related to time, calculate and obtain the shrinkage strain. ; S136. Convert the calculated creep thermal deformation and shrinkage strain into stress, and use the elastic modulus E of the material for conversion to obtain the creep stress and shrinkage stress .

[0009] Further, step S13 also includes: S137. Add the load vector obtained in S131 - 136, the thermal strain caused by the temperature difference , the creep stress and the shrinkage stress to obtain the total load vector and apply it to the i-th connection unit of the finite element model. Use the finite element analysis method according to the finite element equation to solve and obtain the displacement vector of the i-th connection unit; where, is the original stiffness matrix of the i-th connection unit.

[0010] Further, step two includes: S21. Extract the displacement vector of the i-th connection unit from the finite element model. S22. Preset the displacement coordination limit , the maximum allowable displacement value set according to design specifications or engineering experience, represents the maximum acceptable displacement of each connection unit under normal use conditions, including is the maximum allowable displacement component of the i-th connection unit in the x, y, and z directions; S23. Compare the displacement vector of the i-th connection unit with the displacement coordination limit to obtain the coordination index of the i-th connection unit; S24. Evaluate and obtain the coordination evaluation result of the i-th connection unit through the coordination index of the i-th connection unit, including: when , it means that the connection unit is within the allowable range of deformation, and the coordination evaluation result label is qualified; When , it means that the connection unit exceeds the limit, and the coordination evaluation result label is the first unqualified; When , it means that the connection unit exceeds the limit, and the coordination evaluation result label is the second unqualified, and the second unqualified has a greater risk than the first unqualified; S25. Mark the coordination index of each connection unit in the finite element model and draw a line chart to obtain the initial connection coordination index chart, and generate a first warning signal for the first unqualified; And generate a second warning signal for the second unqualified, and mark it with different colors in the initial connection coordination index chart.

[0011] Further, step three includes: S31. Obtain the service life, external cracks, cavities, and rust conditions of the j-th material in the i-th connection unit from experimental data, literature, or on-site monitoring, and establish a material degradation data set; S32. Use a convolutional neural network to construct an initial convolutional neural network model, train and test the initial convolutional neural network model with the material degradation data set, and use the trained initial convolutional neural network model as the bridge service performance evolution model. At the same time, use the intermediate layer output of the bridge service performance evolution model as a feature vector to identify the feature information in the material degradation data set, and train and test the bridge service performance evolution model through the obtained feature information, and use the trained bridge service performance evolution model for data operation prediction.

[0012] Further, step three also includes: S33. Input the material degradation data set into the trained bridge service performance evolution model to construct the aging factor of the i-th connection unit; S34. Use an ultrasonic sensor to monitor the number and area of cracks and voids in the j-th material of the i-th connection unit, and input them into the trained bridge service performance evolution model to construct the damage index of the i-th connection unit ; S35. Use a corrosion sensor to monitor the corrosion depth and the area of the corrosion layer of the j-th material of the i-th connection unit, and input them into the trained bridge service performance evolution model to construct the corrosion index of the i-th connection unit 。

[0013] Furthermore, Step 3 also includes: Step 3 also includes: S36. Extract the aging factor , damage index and corrosion index of the i-th connection unit obtained in S33 - S34. After dimensionless processing, obtain the stiffness loss factor of the i-th connection unit; S37. According to the stiffness loss factor of the i-th connection unit, correct the original stiffness matrix of the i-th connection unit in S137 to obtain the corrected second stiffness matrix ; S38. Use the corrected second stiffness matrix and the total load vector to calculate the corrected second displacement vector of the i-th connection unit; Obtain the corrected second coordination index of the i-th connection unit, obtained by the method in Steps S22 - S23. Obtain the ratio of the second displacement vector of the i-th connection unit and the displacement coordination limit . According to the second coordination index of the i-th connection unit, correct the initial connection coordination index diagram to obtain the second connection coordination index diagram.

[0014] Furthermore, Step 3 also includes: S38. Evaluate the second coordination index of the i-th connection unit to obtain a second prediction result, including: When , it means that the connection unit is within the allowable range of deformation, and the coordination evaluation result label is qualified; When , it means that the connection unit exceeds the limit and there is a first deterioration risk; When , indicating that the connection unit is exceeding the limit and there is a second deterioration risk, and the second deterioration risk is greater than the first deterioration risk; S39. Summarize the connection units with the first deterioration risk and the second deterioration risk into a deterioration connection point group.

[0015] Furthermore, S39 includes: S391. Extract the second coordination index of the second deterioration risk of the deterioration connection point group , sort them from high to low to generate the first maintenance sorting points, and generate the first strategy, including: applying 50%-80% coating protection to the area of the connection unit affected by corrosion, for the connection points with reduced load-bearing capacity, using reinforcement materials or steel bars for reinforcement, with a reinforcement rate of 60%-70%, and restricting traffic in the range of 3-5 meters of the connection unit area to reduce the vehicle load-bearing capacity by 40%-60%; S392. Extract the second coordination index of the first deterioration risk in the deterioration connection point group , sort them from high to low to generate the second maintenance sorting points, and generate the second strategy, including: applying 20%-40% coating protection to the area of the connection unit affected by corrosion, for the connection points with reduced load-bearing capacity, using reinforcement materials or steel bars for reinforcement, with a reinforcement rate of 20%-40%, and restricting traffic in the range of 2-4 meters of the connection unit area to reduce the vehicle load-bearing capacity by 10%-30%.

[0016] Compared with the prior art, the beneficial effects of the present invention are: by obtaining the three-dimensional scan data of the old bridge and the new bridge under the co-service conditions, and combining complex service conditions such as dynamic load, temperature difference and creep shrinkage, it is possible to accurately simulate and evaluate the dynamic response of the connection part under the actual use environment. Especially in the case of the co-service of the old bridge and the new bridge, the degradation and damage of the connection part are particularly significant, and it is difficult for traditional methods to comprehensively evaluate this process. However, this method can effectively identify potential safety hazards through detailed simulation modeling and real-time monitoring.

[0017] The present invention also collects the service life, cracks, cavities and corrosion conditions of the materials in the connection unit, and combines convolutional neural network technology to construct a bridge service performance evolution model, which can more comprehensively evaluate the degradation of the materials. Traditional evaluation methods usually have difficulty in comprehensively and meticulously analyzing the degradation process of materials, while this method can combine big data technology to track the progress of material aging in real time and help predict potential hidden damages that may occur in the connection part. By constructing an aging factor, a damage index and a corrosion index and correlating them with the connection coordination index diagram, a specific stiffness loss factor can be provided for each connection unit. This calculation can more accurately reflect the performance degradation degree of the bridge connection part and provide a scientific basis for subsequent reinforcement and maintenance strategies. Description of the Drawings

[0018] Figure 1 This is a schematic diagram of the overall method steps of the present invention. Specific embodiments

[0019] To make the objectives, technical solutions and advantages of the present invention more clear and understandable, the present invention will be further described in detail below in conjunction with specific embodiments.

[0020] It should be noted that unless otherwise defined, the technical terms or scientific terms used in the present invention should have the ordinary meanings understood by those with ordinary skills in the field to which the present invention belongs. The "first", "second" and similar terms used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. Terms such as "including" or "comprising" mean that the elements or objects appearing before this term cover the elements or objects listed after this term and their equivalents, without excluding other elements or objects. Terms such as "connected" or "coupled" are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Upper", "lower", "left", "right", etc. are only used to represent relative positional relationships, and when the absolute position of the object being described changes, the relative positional relationship may also change accordingly.

[0021] Embodiment 1;

[0022] Please refer to Figure 1 , the present invention provides a technical solution: a method for bridge performance evaluation and life prediction based on big data analysis, and the specific steps include: Step 1: Obtain the three-dimensional scan data of the connection structure of the old bridge and the new bridge under the condition of co-service, perform mesh division to form a number of connection units, establish a finite element model, simulate the real service conditions of vehicle load, temperature difference and creep shrinkage, and construct the displacement vector of the i-th connection unit ; Step 2: Preset the displacement coordination limit value. When the displacement vector of the i-th connection unit is compared with the displacement coordination limit value, obtain the first connection coordination evaluation result, and construct the initial connection coordination index diagram; Step 3: Collect the service life, external cracks, cavities and corrosion conditions of the materials in the connection units, and establish a material degradation data set; combine the initial connection coordination index diagram, use a convolutional neural network to construct a bridge service performance evolution model, input the material degradation data set into the bridge service performance evolution model for training, and construct the aging factor , damage index and corrosion index of the i-th connection unit. After correlation, obtain the stiffness loss factor , and perform degradation correction on the displacement vector of the i-th connection unit to obtain the second coordination index of the i-th connection unit , and correct the initial connection coordination index diagram to obtain the second connection coordination index diagram, so as to output the prediction results and corresponding strategies of the old bridge during the co-service period of the old and new bridges.

[0023] In this embodiment, by obtaining the three-dimensional scanning data of the old bridge and the new bridge under co-service conditions, and combining complex service conditions such as dynamic load, temperature difference, and creep shrinkage, the dynamic response of the connection part under the actual use environment can be accurately simulated and evaluated. Especially in the case of the co-service of the old and new bridges, the degradation and damage of the connection part are particularly significant, and it is difficult for traditional methods to comprehensively evaluate this process. However, through detailed simulation modeling and real-time monitoring, this method can effectively identify potential safety hazards.

[0024] Traditional bridge evaluation methods mainly rely on static models and manual inspections, and cannot effectively reflect the dynamic changes of bridges during actual service. However, through the comparison of displacement vectors and coordination limits, this method can obtain the coordination evaluation results of the connection part in real time, providing a more accurate basis for the dynamic monitoring of the bridge state. This is of great practical significance for timely discovering and correcting performance changes caused by aging or damage.

[0025] By collecting the service life, cracks, cavities, and corrosion conditions of the materials in the connection unit, and combining convolutional neural network technology, a bridge service performance evolution model can be constructed to more comprehensively evaluate the degradation of the materials. Traditional evaluation methods usually have difficulty in comprehensively and carefully analyzing the degradation process of materials, while this method can combine big data technology to track the progress of material aging in real time, helping to predict potential hidden damages that may occur in the connection part. By constructing aging factors, damage indices, and corrosion indices and correlating them with the connection coordination index diagram, a specific stiffness loss factor can be provided for each connection unit. This calculation can more accurately reflect the performance degradation degree of the bridge connection part, providing a scientific basis for subsequent reinforcement and repair strategies.

[0026] Through the corrected connection coordination index diagram, accurate prediction results of the old bridge during the co-service period of the old and new bridges can be output. This method can predict the remaining service life of the bridge according to the aging and damage conditions of the bridge connection part and provide corresponding strategic suggestions. For example, when there is significant degradation in the connection part, repairs or reinforcements can be carried out in advance to avoid accidents. Through this method, the degradation status of the connection part of the bridge can be monitored in real time during the bridge service process, thereby effectively reducing the occurrence of potential safety hazards. Compared with traditional regular inspection methods, this method can identify potential structural problems in advance through dynamic data collection and big data analysis, avoiding sudden bridge failures or accidents caused by hidden damages.

[0027] Embodiment 2. This embodiment is an explanatory description carried out in Embodiment 1. Specifically, Step 1 includes: S11. Use a laser scanner to perform an all-round scan of the connection structure between the old bridge and the new bridge under the condition of co-service, obtain three-dimensional scan data, establish a finite element model of the connection structure based on the three-dimensional data, and perform material assignment and boundary condition setting for the connection structure; Different types of connection units may use different materials, and the physical properties of each material are assigned, specifically including Poisson's ratio and density assignment: Describe the degree of deformation in the vertical direction when the material is stressed in one direction. The Poisson's ratio of steel is generally 0.3, and that of concrete is 0.2 - 0.25; The density of steel is usually 7.85 g / cm³, and that of concrete is 2.4 g / cm³; The boundary condition setting specifically includes: Set fixed supports or support points at both ends of the bridge. Fixed supports are usually set as fully constrained to limit their displacements in all directions; Degree-of-freedom constraints of support nodes, for example, constrain the displacements and rotations of the X-axis, Y-axis, and Z-axis at the nodes; A sliding support allows the structure to displace in one direction while imposing constraints in another direction. A typical sliding support allows the bridge to slide freely along the bridge deck direction but restricts displacements perpendicular to the bridge deck.

[0028] By performing mesh division on the connection structure, the discretization of each connection unit helps to accurately analyze the mechanical responses of each part, especially in terms of local stress or material degradation. Finer mesh division can obtain higher solution accuracy and avoid errors caused by over-simplification.

[0029] S12. Perform mesh division on the connection structure in the finite element model to form a number of discrete connection units, and each connection unit is marked as the i-th connection unit; Each connection unit can be analyzed independently, so as to accurately capture the performance changes of the local structure, especially the small changes that may occur during the long-term service of the bridge. This is very important for early detection of potential safety hazards.

[0030] S13. After simulating the actual service conditions of vehicle loads, temperature differences, and creep and shrinkage in the finite element model, apply a load vector to each connection unit and collect the thermal strain caused by the temperature difference the creep stress and the shrinkage stress and construct the displacement vector Simulating complex working conditions such as vehicle loads, temperature differences, creep, and shrinkage helps to comprehensively understand the responses of bridge connection structures under the action of various external factors. By applying actual vehicle loads, temperature differences, creep, and shrinkage effects, the simulation situation of the bridge can be effectively compared with the actual service situation, helping to predict the long-term performance changes of the structure. This helps to improve the accuracy and reliability of the model and better reflects the changes of the bridge under different service conditions.

[0031] Step S13 includes: S131. Collect and obtain the elastic modulus E of the materials used in the i-th connection unit; The elastic modulus E of the materials includes: concrete with a strength of C30, and the elastic modulus is 30 GPa; Concrete with a strength of C40, and the elastic modulus is 32.5 GPa; Concrete with a strength of C50, and the elastic modulus is 34.5 GPa; Concrete with a strength of C60, and the elastic modulus is 36.5 GPa; Concrete with a strength of C70, and the elastic modulus is 38.0 GPa; Concrete with a strength of C80, and the elastic modulus is 40.0 GPa; Structural steel of HRB335, HRB400, and HRB500 models, and the elastic modulus is 200 - 210 GPa; Prestressed steel, and the elastic modulus is 195 - 200 GPa; Assigning values to the elastic moduli of concrete with different strength grades and steel bars of different models can accurately simulate the roles of different materials in bridge connection structures. Considering the heterogeneity and different degradation rates between materials, more detailed analysis results can be provided.

[0032] S132. Apply boundary conditions and vehicle loads: Collect historical data, obtain the average vehicle load of the historical data, and convert it into a force vector at nodes or on surfaces according to the average vehicle load, and apply it as an external mechanical load to the connection unit nodes or unit surfaces of the finite element model to form a load vector ; Collect and analyze historical vehicle load data, making the application of loads more in line with the actual situation and avoiding the possible assumption deviations in traditional methods. By converting vehicle loads into load vectors at nodes or unit surfaces, the impact of traffic flow changes on the bridge can be simulated more accurately.

[0033] S133. Use the temperature sensors installed on the bridge to monitor the temperature changes at different times and positions, obtain the linear expansion coefficients of concrete and steel bars in the bridge components through material test reports or standard data , and calculate the temperature difference according to the thermal expansion theory resulting in thermal strain : ; Convert the thermal strain into thermal stress, and combine with the material elastic modulus E to calculate the thermal load : ; By monitoring the temperature difference changes at different positions of the bridge and combining with the linear expansion coefficient of the material, the thermal strain and thermal stress caused by the temperature difference to the bridge structure can be accurately calculated. This provides data support for the early warning of bridge damage caused by temperature difference, especially crucial for the safety monitoring of bridges under extreme weather conditions.

[0034] S134. Collect and utilize the strain sensors installed on the bridge to monitor the deformation of the reinforced concrete structure in the bridge components under long-term loads in real time, pay attention to the influence of creep and shrinkage on the connection unit, and calculate the creep thermal change : ; Among them, is the creep coefficient, which changes with time and is represented by the creep function; is the instantaneous strain caused by the initial load, that is, the strain that occurs immediately in the structure when the load is applied; S135. The shrinkage strain is related to time, and calculate and obtain the shrinkage strain : ; Among them, represents the current time, that is, the time calculated from the start of concrete pouring, represents the shrinkage strain at the reference time of 28 days after concrete pouring, is the age of concrete pouring, which is the reference time; S136. Convert the calculated creep thermal change and shrinkage strain into stress, and use the elastic modulus E of the material for conversion to obtain the creep stress and shrinkage stress : ; .

[0035] By monitoring the deformation of the reinforced concrete in the bridge components, the influence of creep effect on the long-term performance of the bridge can be evaluated. Creep and shrinkage stresses have important influences on aging and deformation accumulation, and this step provides detailed calculation support for the performance of the bridge under long-term dynamic load conditions.

[0036] Step S13 also includes: S137. The load vectors obtained in S131 - 136 , the temperature difference -induced thermal strain , creep stress and shrinkage stress are added to obtain the total load vector applied to the i-th connecting element of the finite element model. Using the finite element analysis method, according to the finite element equation , to solve the finite element equation to obtain the displacement vector of the i-th connecting element ; where is the original stiffness matrix of the i-th connecting element.

[0037] In this embodiment, all mechanical effects (such as vehicle load, temperature difference, creep, and shrinkage stress, etc.) are integrated into a load vector and applied to the connecting element, which helps to comprehensively evaluate the response of the bridge structure under various working conditions. Through this process, a more comprehensive performance evaluation result can be obtained.

[0038] Embodiment 3. This embodiment is an explanatory description carried out in Embodiment 2. Specifically, Step 2 includes: S21. Extract the displacement vector of the i-th connecting element from the finite element model , and the expression is: ; where are the displacement components of the i-th connecting element in the x, y, and z directions respectively; S22. Preset the displacement coordination limit , the maximum allowable displacement value set according to the design specification or engineering experience, representing the maximum acceptable displacement of each connecting element under normal use, and the expression is: ; where are the maximum allowable displacement components of the i-th connecting element in the x, y, and z directions respectively; S23. Compare the displacement vector of the i-th connecting element with the displacement coordination limit to obtain the coordination index of the i-th connecting element: ; where represents the modulus of the displacement vector of the i-th connecting element in each direction, represents the modulus of the displacement coordination limit of the i-th connecting element; S24. Evaluate and obtain the coordination evaluation result of the i-th connecting element through the coordination index of the i-th connecting element, including: when It indicates that within the allowable range of deformation of the connection unit, the coordinated evaluation result label is qualified; When it indicates that the connection unit exceeds the limit value, and the coordinated evaluation result label is the first unqualified; When it indicates that the connection unit exceeds the limit, and the coordinated evaluation result label is the second unqualified, and the second unqualified has a greater risk than the first unqualified; S25. Mark the coordination index of each connection unit in the finite element model, draw a line chart to obtain the initial connection coordination index chart, and generate a first warning signal for the first unqualified; And generate a second warning signal for the second unqualified, and mark it with different colors in the initial connection coordination index chart.

[0039] In this embodiment, extracting the displacement vector of each connection unit provides detailed structural response data for subsequent analysis. By obtaining the displacement components, the deformation of the connection unit under actual working conditions can be comprehensively evaluated, providing an intuitive basis for the safety assessment of the structure. By decomposing into displacement components in the x, y, and z directions, the mechanical behavior of each connection unit can be described in detail. This helps to capture the deformation that may occur in local areas of the structure and avoid structural problems caused by ignoring details.

[0040] Comparing the displacement vector with the displacement coordination limit value and calculating the coordination index helps to quantitatively evaluate the deformation degree of each connection unit. The coordination index provides a numerical index for the evaluation of structural deformation, making the comparison and analysis more intuitive and accurate. The calculated coordination index can provide detailed deformation performance for each connection unit, facilitating the identification of which connection units exceed the predetermined allowable range from the overall perspective. This provides a strong basis for subsequent decision-making.

[0041] Embodiment 4. This embodiment is an explanatory description based on Embodiment 3. Specifically, Step 3 includes: S31. Obtain the service life, external cracks, cavities, and corrosion conditions of the jth material in the ith connection unit from experimental data, literature, or on-site monitoring, and establish a material degradation data set; the external cracks, cavities, and corrosion conditions are obtained through on-site monitoring; the material degradation data set not only provides a data basis for modeling but also provides a practical basis for the maintenance and evaluation of the bridge. These data can help engineers make scientific decisions and prioritize the treatment of those structural parts with severe degradation.

[0042] S32. Use a convolutional neural network to construct an initial convolutional neural network model, train and test the initial convolutional neural network model with a material degradation dataset, and use the trained initial convolutional neural network model as a bridge service performance evolution model. At the same time, use the output of the middle layer of the bridge service performance evolution model as a feature vector to identify the feature information in the material degradation dataset, and train and test the bridge service performance evolution model with the obtained feature information. Divide the material degradation dataset into a training set and a validation set (for example, 80% training set, 20% validation set). Input the training dataset, calculate the output of the model through forward propagation, and use a loss function to calculate the error. Use the backpropagation algorithm to adjust the network parameters to minimize the loss function. The weights and biases in the network are updated in each iteration. Evaluate the model performance using the validation set at the end of each epoch to detect overfitting. After training, save the convolutional neural network model and its weights for subsequent use.

[0043] Use the trained bridge service performance evolution model for data operation prediction. Based on the CNN model, key features can be extracted through the output of the middle layer, further improving the prediction accuracy of the model. This prediction can identify the degradation trend of materials earlier and provide early warnings for bridge maintenance and reinforcement.

[0044] S33. Input the material degradation dataset into the trained bridge service performance evolution model, and construct the aging factor of the i-th connection unit through the following formula : ; In the formula, m represents the number of materials contained in the i-th connection unit, j represents the material number, j = 1, 2,..., m; represents the service life shared by all materials of the i-th connection unit, represents the maximum reference life, represents the age index of the j-th material, represents the initial strength of the j-th material, represents the strength of the j-th material after time t, represents the weight value of the j-th material's age, represents the weight value of the j-th material due to strength attenuation; by constructing the aging factor and combining factors such as the age and strength of different materials, the degree of material aging can be comprehensively reflected. The aging factor provides an effective indicator for evaluating the health status of each connection unit and can quantify the impact of material degradation on the structural performance.

[0045] S34. Use an ultrasonic sensor to monitor the number and area of cracks and voids in the j-th material of the i-th connection unit, and input them into the trained bridge service performance evolution model. The damage index of the i-th connection unit is constructed by the following formula : ; In the formula, represents the number of cracks in the j-th material of the i-th connection unit, represents the number of voids in the j-th material of the i-th connection unit; represents the crack area of the j-th material of the i-th connection unit; represents the void area of the j-th material of the i-th connection unit; , , and respectively represent the maximum acceptable number of cracks, the maximum acceptable number of voids, the maximum acceptable crack area, and the maximum acceptable void area of the j-th material of the i-th connection unit. represents the weight value of the j-th material; Monitoring the number and area of cracks and voids using an ultrasonic sensor can obtain the damage condition of the material in real time, and input the data into the model to obtain the damage index. This index can accurately evaluate the degradation of material performance caused by defects such as cracks and voids, and help judge the safety of the structure.

[0046] S35. Use a corrosion sensor to monitor the corrosion depth and corrosion layer area of the j-th material of the i-th connection unit, and input them into the trained bridge service performance evolution model. The corrosion index of the i-th connection unit is constructed by the following formula : ; In the formula, represents the corrosion depth of the j-th material of the i-th connection unit; represents the corrosion layer area of the j-th material of the i-th connection unit; and respectively represent the maximum acceptable corrosion depth and the maximum acceptable corrosion layer area of the j-th material of the i-th connection unit. Monitoring the corrosion depth and corrosion layer area through a corrosion sensor can effectively capture the structural degradation caused by corrosion, and timely evaluate the strength and load-bearing capacity of the material. The corrosion index can accurately reflect the impact of environmental factors on material degradation.

[0047] S36. Extract the aging factor , damage index and corrosion index of the i-th connection unit obtained in S33 - S34. After dimensionless processing, calculate the stiffness loss factor of the i-th connection unit through the following formula : ; Among them, , and are the weight values of the aging factor , damage index and rust index of the i-th connection unit respectively. The larger the stiffness loss factor, the more the stiffness of the structure degrades with the aging, damage or rust of the material, resulting in a larger displacement under the same load. By calculating the comprehensive influence of the aging factor, damage index and rust index, the stiffness loss factor is obtained. The calculation of this factor enables the quantitative evaluation of the decline process of the structural stiffness and can predict the performance change without directly damaging the structure.

[0048] S37. According to the stiffness loss factor of the i-th connection unit, correct the original stiffness matrix of the i-th connection unit in S137. The corrected second stiffness matrix : ; Among them, as increases, the value of the stiffness matrix decreases, thus reflecting the degradation of the material; S38. Use the corrected second stiffness matrix and the total load vector to calculate the corrected second displacement vector of the i-th connection unit: ; Solve the above equation to obtain the calculated corrected second displacement vector Obtain the corrected second coordination index of the i-th connection unit, obtained by the method in steps S22 - S23. Obtain the ratio of the second displacement vector of the i-th connection unit and the displacement coordination limit . According to the corrected second coordination index of the i-th connection unit, correct the initial connection coordination index diagram to obtain the second connection coordination index diagram.

[0049] In this embodiment, based on the stiffness loss factor, the original stiffness matrix is corrected, which can accurately reflect the influence of material degradation on the structural stiffness. Through this correction, the calculation results of the model can be closer to the actual situation, thereby improving the reliability of subsequent analysis. By dynamically correcting the stiffness matrix, the structural model can be adjusted at any time according to the actual monitoring data, enabling the structural behavior to reflect the current degradation state in real time and providing an effective basis for maintenance work.

[0050] Embodiment 5. This embodiment is an explanatory illustration based on Embodiment 3. Specifically, Step 3 further includes: S38. Evaluate the second coordination index of the i-th connection unit to obtain a second prediction result, including: When , it indicates that the connection unit is within the allowable range of deformation, and the coordination evaluation result label is qualified; When , it indicates that the connection unit exceeds the limit and there is a first deterioration risk; When , it indicates that the connection unit exceeds the limit and there is a second deterioration risk, and the second deterioration risk is greater than the first deterioration risk; S39. And summarize the connection units with the first deterioration risk and the second deterioration risk into a deteriorated connection point group.

[0051] S391. Extract the second coordination index of the second deterioration risk of the deteriorated connection point group , sort them from high to low to generate a first maintenance sorting point, and generate a first strategy, including: applying 50%-80% coating protection to the area affected by corrosion of the connection unit, for the connection points with reduced load-bearing capacity, using reinforcement materials or steel bars for reinforcement, with a reinforcement rate of 60%-70%, and restricting the traffic within a range of 3-5 meters around the connection unit area, reducing the vehicle load-bearing capacity by 40%-60%; S392. Extract the second coordination index of the first deterioration risk in the deteriorated connection point group , sort them from high to low to generate a second maintenance sorting point, and generate a second strategy, including: applying 20%-40% coating protection to the area affected by corrosion of the connection unit, for the connection points with reduced load-bearing capacity, using reinforcement materials or steel bars for reinforcement, with a reinforcement rate of 20%-40%, and restricting the traffic within a range of 2-4 meters around the connection unit area, reducing the vehicle load-bearing capacity by 10%-30% within a range of 10-30% of the vehicle load-bearing capacity.

[0052] In this embodiment, the evaluation of the second coordination index can more precisely detect whether the connection unit is within the deformed safety range. By classifying and evaluating different levels of qualified, first deterioration risk, and second deterioration risk, the degree of bridge damage can be refined, ensuring that the risk assessment is more accurate and detailed. Through the grading of the second coordination index, clear early warning information can be provided for bridge managers. For connection units with a relatively high deterioration risk, more urgent maintenance or repair instructions can be issued in a timely manner, thereby reducing the probability of accidents. By aggregating connection units with a deterioration risk into a deterioration connection point group, these potential high-risk areas can be centrally monitored and managed, reducing the complexity of individual processing and improving the risk management efficiency. Sorting according to the second coordination index from high to low to generate maintenance sorting points ensures that the most severely deteriorated connection units can be repaired first. This ordered sorting provides a clear priority for maintenance decisions, ensuring that the repair work can be carried out in an orderly manner. For connection units with a second deterioration risk, specific repair strategies are proposed, including 50%-80% coating protection, 60%-70% reinforcement rate, traffic restriction measures, etc. These measures can effectively prevent further damage and ensure structural safety. The revised plan significantly improves the overall effect of bridge management through refined deterioration risk assessment, precise maintenance strategies, and efficient resource allocation. Although the original plan could evaluate the deformation of connection units, it lacked precise identification and differential management of different types of deterioration risks. After revision, through multi-dimensional evaluation and the formulation of specific strategies, it can more effectively extend the service life of the bridge, improve safety, optimize resource allocation, and enhance the overall maintenance efficiency.

[0053] It should be noted that all calculation formulas in this application document adopt regression analysis including but not limited to machine learning algorithms to deeply analyze relevant parameters collected, identify their natural trends and interrelationships. Using professional software such as the Scikit-learn library in Python or the R language, a mathematical model matching the data is automatically generated. Then, the performance of the model is objectively evaluated through methods such as cross-validation, and combined with continuous feedback and optimization, to ensure that the created formula truly reflects the internal laws of the data, thereby ensuring its effectiveness and accuracy, and ensuring that the calculation process conforms to the constraints of natural laws rather than being based on artificially set rules.

[0054] The technical solution of the present invention can be embodied in the form of a software product in essence or in the part that contributes to the prior art. This computer software product can be stored in a computer-readable storage medium, such as a floppy disk, read-only memory (ROM), random access memory (RAM), flash memory, hard disk, or optical disc of a computer, etc., and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods of various embodiments of the present invention.

[0055] The logic and / or steps represented in the flowchart or described in other ways herein, for example, can be considered as a definite sequence list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other systems that can fetch and execute instructions from the instruction execution system, apparatus, or device), or used in combination with these instruction execution systems, apparatus, or devices. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transmit a program for use by or in combination with an instruction execution system, apparatus, or device.

[0056] It should be noted that the above embodiments are only used to illustrate the technical solution of the present invention and not to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solution of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solution of the present invention, and all of them should be covered by the scope of the claims of the present invention.

[0057] It should be noted that the above embodiments are only used to illustrate the technical solution of the present invention and not to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solution of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solution of the present invention, and all of them should be covered by the scope of the claims of the present invention.

Claims

1. A method for bridge performance evaluation and life prediction based on big data analysis, characterized in that The specific steps include: Step 1: Obtain the three-dimensional scanning data of the connection structure of the old bridge and the new bridge under the condition of co-service, perform mesh division to form a number of connection units, establish a finite element model, simulate the actual service conditions of vehicle load, temperature difference and creep shrinkage, and construct the displacement vector of the i-th connection unit ; Step 2: Preset a displacement coordination limit value. When the displacement vector of the i-th connection unit is compared with the displacement coordination limit value, a first connection coordination evaluation result is obtained, and an initial connection coordination index diagram is constructed. Step 3: Collect the service life, external cracks, cavities, and corrosion conditions of the materials in the connection unit, and establish a material degradation data set; combine the initial connection coordination index diagram, and use a convolutional neural network to construct a bridge service performance evolution model. After inputting the material degradation data set into the bridge service performance evolution model for training, construct the aging factor of the i-th connection unit , damage index , and corrosion index . After correlation, obtain the stiffness loss factor of the i-th connection unit , and perform degradation correction on the displacement vector of the i-th connection unit to obtain the second coordination index of the i-th connection unit , and correct the initial connection coordination index diagram to obtain the second connection coordination index diagram, so as to output the prediction results and corresponding strategies of the old bridge during the co-service period of the new and old bridges.

2. The method for bridge performance evaluation and life prediction based on big data analysis according to claim 1, characterized in that: Step 1 includes: S11. Use a laser scanner to perform a full - scale scan of the connection structure of the old bridge and the new bridge under the condition of co - service, obtain three - dimensional scan data, establish a finite - element model of the connection structure based on the three - dimensional data, and assign materials and set boundary conditions for the connection structure; S12. Mesh the connection structure in the finite - element model to form a number of discrete connection units, and each connection unit is marked as the i - th connection unit; S13. After simulating the actual service conditions of vehicle loads, temperature differences, and creep and shrinkage in the finite element model, apply the load vector to each connection unit , and collect the thermal strain caused by the temperature difference , creep stress , and shrinkage stress . Construct the displacement vector of the i-th connection unit in the finite element model .

3. A method for bridge performance evaluation and life prediction based on big data analysis according to claim 2, characterized in that: Step S13 includes: S131. Collect and obtain the elastic modulus E of the material used for the i - th connection unit; S132. Apply boundary conditions and vehicle loads: Collect historical data, obtain the average vehicle load of the historical data, and convert it into a force vector at nodes or on surfaces, which is applied as an external mechanical load to the connection unit nodes or unit surfaces of the finite element model to form a load vector. ; S133. Use the temperature sensors installed on the bridge to monitor the temperature changes at different times and locations, and obtain the linear expansion coefficients of concrete and steel bars in the bridge components through material test reports or standard data , and calculate the temperature difference according to the thermal expansion theory caused thermal strain ; Convert the thermal strain into thermal stress, and combine with the material elastic modulus E to calculate the thermal load ; S134. Collect and utilize the strain sensors installed on the bridge to monitor in real time the deformation of the reinforced concrete structure in the bridge components under long-term loads, pay attention to the influence of creep and shrinkage on the connection unit, and calculate creep thermal deformation ; S135. The shrinkage strain is related to time, and the shrinkage strain is calculated and obtained. ; S136. Convert the calculated creep thermal strain and shrinkage strain into stress, and perform the conversion using the elastic modulus E of the material to obtain the creep stress and shrinkage stress .

4. A method for bridge performance evaluation and life prediction based on big data analysis according to claim 3, characterized in that: Step S13 also includes: S137. Add the load vectors obtained in S131 - 136 , temperature difference induced thermal strain , creep stress and shrinkage stress to obtain the total load vector and apply it to the i-th connecting element of the finite element model. Using the finite element analysis method and according to the finite element equation , solve to obtain the displacement vector of the i-th connecting element from the obtained finite element equation; where is the original stiffness matrix of the i-th connecting element.

5. A method for bridge performance evaluation and life prediction based on big data analysis according to claim 4, characterized in that: Step 2 includes: S21. Extract the displacement vector of the i-th connection unit from the finite element model ; S22. Preset displacement coordination limit , which is the maximum allowable displacement value set according to design specifications or engineering experience, representing the maximum acceptable displacement of each connection unit under normal use conditions, including being the maximum allowable displacement components of the i-th connection unit in the x, y, and z directions; S23. Compare the displacement vector of the $i$-th connection unit with the displacement coordination limit to obtain the coordination index of the $i$-th connection unit ; S24. Coordination index of the i-th connection unit Evaluate to obtain the coordination evaluation result of the i-th connection unit, including: when , it indicates that the connection unit is within the allowable range of deformation, and the coordination evaluation result label is qualified; When , it means that the connection unit exceeds the limit value, and the coordination evaluation result label is the first non-conformance; When , it means that the connection unit exceeds the limit, and the coordination evaluation result label is the second non-conformance, and the second non-conformance has a greater risk than the first non-conformance; S25. Mark the coordination index of each connection unit in the finite - element model, draw a line graph to obtain the initial connection coordination index graph, and generate a first warning signal for the first non - compliance; And generate a second warning signal for the second non - compliance, and mark it with different colors in the initial connection coordination index graph.

6. The method for bridge performance evaluation and life prediction based on big data analysis according to claim 5, characterized in that: Step 3 includes: S31. Obtain the service life, external cracks, cavities, and corrosion conditions of the j - th material in the i - th connection unit from experimental data, literature, or on - site monitoring, and establish a material degradation data set; S32. Use a convolutional neural network to construct an initial convolutional neural network model, train and test the initial convolutional neural network model with the material degradation data set, and use the trained initial convolutional neural network model as the bridge service performance evolution model. At the same time, use the output of the middle layer of the bridge service performance evolution model as a feature vector to identify the feature information in the material degradation data set, and train and test the bridge service performance evolution model with the obtained feature information, and use the trained bridge service performance evolution model for data operation prediction.

7. A method for bridge performance evaluation and life prediction based on big data analysis according to claim 6, characterized in that: Step 3 also includes: S33. Input the material degradation dataset into the trained bridge service performance evolution model to construct the aging factor of the i-th connection unit ; S34. Use an ultrasonic sensor to monitor the number and area of cracks and voids in the j-th material of the i-th connection unit, and input them into the trained bridge service performance evolution model to construct the damage index of the i-th connection unit ; S35. Monitor the corrosion depth and corrosion layer area of the j-th material of the i-th connection unit using a corrosion sensor, input them into the trained bridge service performance evolution model, and construct the corrosion index of the i-th connection unit .

8. A method for bridge performance evaluation and life prediction based on big data analysis according to claim 7, characterized in that: Step 3 also includes: S36. Extract the aging factor of the i-th connection unit obtained from S33 - S34 , damage index and corrosion index . After dimensionless processing, obtain the stiffness loss factor of the i-th connection unit ; S37. According to the stiffness loss factor of the i-th connection unit , the original stiffness matrix of the i-th connection unit in S137 is corrected to obtain the corrected second stiffness matrix ; S38. Use the corrected second stiffness matrix and the total load vector to calculate the corrected second displacement vector of the i-th connection element ; Obtain the second coordination index of the corrected ith connection unit , obtained according to the method of steps S22 - S23, and obtain the second displacement vector of the ith connection unit and the displacement coordination limit value by taking the ratio. According to the second coordination index of the ith connection unit correct the initial connection coordination index diagram to obtain the second connection coordination index diagram.

9. A method for bridge performance evaluation and life prediction based on big data analysis according to claim 7, characterized in that: The said step 3 also includes: S38. Evaluate the second coordination index of the $i$-th connection unit to obtain a second prediction result, including: When , it means that the connection unit is within the allowable range of deformation, and the coordinated evaluation result label is qualified; When , it indicates that the connection unit exceeds the limit value and there is a first deterioration risk; When , it indicates that the connection unit exceeds the limit and there is a second deterioration risk, and the second deterioration risk is greater than the first deterioration risk; S39. Summarize the connection units with the first deterioration risk and the second deterioration risk into a deteriorated connection point group.

10. A method for bridge performance evaluation and life prediction based on big data analysis according to claim 9, characterized in that: S39 includes: S391. Extract the second coordination index of the second deterioration risk in the deteriorated connection point group , sort them from high to low to generate the first maintenance sorting points, and generate the first strategy, including: applying 50%-80% coating protection to the area of the connection unit affected by corrosion, for the connection points with reduced bearing capacity, using reinforcement materials or steel bars for reinforcement, with a reinforcement rate of 60%-70%, and restricting the traffic within a range of 3-5 meters in the area of the connection unit to reduce the vehicle load by 40%-60%; S392. Extract the second coordination index of the first deterioration risk in the deteriorated connection point group , sort them from high to low to generate the second maintenance sorting points, and generate the second strategy, including: applying 20%-40% coating protection to the area of the connection unit affected by corrosion, for the connection points with reduced load-bearing capacity, using reinforcement materials or steel bars for reinforcement, with a reinforcement rate of 20%-40%, and restricting the traffic within a range of 2-4 meters in the area of the connection unit to reduce the vehicle load-bearing capacity by 10%-30%.

Images