Bridge disease diagnosis and maintenance measure recommendation method

Abstract

The invention relates to the technical field of bridge disease diagnosis and maintenance, in particular to a bridge disease diagnosis and maintenance measure recommendation method which comprises the following steps: constructing a bridge disease database which comprises feature data and cause data of various types of bridge diseases and maintenance measure data matched with the various types of diseases; receiving field disease information of a target bridge input by a user, wherein the field disease information comprises a disease type and a disease characteristic parameter; performing matching analysis on the field disease information and data in the bridge disease database, and diagnosing a disease cause of the target bridge based on a matching result; according to the diagnosed disease causes, one or more maintenance measures corresponding to the disease causes are called from the bridge disease database and output as recommended schemes, and a complete data link from disease detection to maintenance decision is established by constructing the standardized bridge disease database and a matching mechanism.

Description

Technical Field

[0001] This invention relates to the field of bridge disease diagnosis and maintenance technology, specifically a method for recommending bridge disease diagnosis and maintenance measures. Background Technology

[0002] As a core component of transportation infrastructure, the structural health of bridges is directly related to public safety and economic operation. Traditional bridge defect diagnosis and maintenance mainly rely on regular manual inspections. Inspectors discover defects such as cracks, corrosion, and deformation through visual inspection, tapping, and simple instrument measurement. Based on their personal experience, they judge the severity of the defects, then manually record and formulate preliminary maintenance recommendations.

[0003] This method has many limitations. For example, it relies on the professional level and experience of the inspectors. Different people may have subjective differences in their judgment of the same disease, resulting in inconsistent and inaccurate diagnostic results. Moreover, manual inspection is inefficient. For large bridges or a large number of road and bridge assets, it is difficult to achieve full coverage and high-frequency inspection, and it is easy to miss key diseases. At the same time, disease diagnosis and maintenance measures are separate, and there is a lack of a systematic method that directly and quickly links disease characteristics with scientific and standardized maintenance strategies. Summary of the Invention

[0004] To overcome the shortcomings of existing technologies, this invention proposes a method for diagnosing bridge defects and recommending maintenance measures. By constructing a standardized bridge defect database and matching mechanism, a complete data link is established from defect detection to maintenance decision-making. Structured data replaces manual experience-based judgment, effectively improving the objectivity of diagnosis, the standardization of decision-making, and the efficiency of execution, thus forming a systematic solution.

[0005] The technical solution adopted by this invention to solve its technical problem is: a method for recommending bridge defects and maintenance measures, comprising the following steps:

[0006] Step S1: Construct a bridge defect database, which includes characteristic data, causal data, and maintenance measures data matching various types of bridge defects.

[0007] Step S2: Receive on-site defect information of the target bridge input by the user, wherein the on-site defect information includes defect type and defect characteristic parameters;

[0008] Step S3: Match and analyze the on-site defect information with the data in the bridge defect database, and diagnose the causes of defects in the target bridge based on the matching results;

[0009] Step S4: Based on the diagnosed causes of the defects, retrieve and output one or more maintenance measures corresponding to the causes of the defects from the bridge defect database as recommended solutions.

[0010] Preferably, in step S2, the on-site disease information is input via a mobile terminal application using one or more of the following methods: form selection, image upload, and parameter input.

[0011] Preferably, in step S2, when inputting via image upload, the method further includes the step of performing image recognition on the uploaded disease image and automatically extracting disease feature parameters from the image.

[0012] Preferably, the matching analysis in step S3 includes: comparing the on-site defect feature parameters with the feature thresholds pre-stored in the bridge defect database, and determining the severity level of the defect based on the comparison results.

[0013] Preferably, the recommended schemes output in step S4 are prioritized according to the severity level.

[0014] Preferably, the method further includes step S5: generating and outputting a standardized maintenance report containing the on-site disease information, disease diagnosis conclusions, and the recommended scheme.

[0015] Preferably, the maintenance measures data in the bridge defect database includes information on the materials, equipment, labor hours, and cost estimates required for each measure.

[0016] Preferably, the method further includes step S6: recording and storing historical data for each diagnosis and recommendation, and predicting the development trend of the target bridge's defects based on the historical data.

[0017] Preferably, the data in the bridge defect database is constructed based on bridge industry standards, expert experience, and historical case data.

[0018] An electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: when the processor executes the program, it implements the steps of the method described above.

[0019] The beneficial effects of this invention are as follows:

[0020] This invention establishes a complete data link from disease detection to maintenance decision-making by constructing a standardized bridge disease database and matching mechanism. By replacing manual experience-based judgment with structured data, it effectively improves the objectivity of diagnosis, the standardization of decision-making, and the efficiency of execution, thus forming a systematic solution. Attached Figure Description

[0021] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0022] Figure 1 This is a flowchart of the method of the present invention. Detailed Implementation

[0023] To make the technical means, creative features, objectives and effects of this invention easier to understand, the invention will be further described below in conjunction with specific embodiments.

[0024] like Figure 1 As shown, in one embodiment of the present invention, a method for diagnosing bridge defects and recommending maintenance measures is provided, including the following steps: Step S1: Construct a bridge defect database, which includes characteristic data, causal data, and maintenance measure data matching various types of bridge defects.

[0025] Step S2: Receive the on-site defect information of the target bridge input by the user. The on-site defect information includes the defect type and defect characteristic parameters.

[0026] Step S3: Match and analyze the on-site defect information with the data in the bridge defect database, and diagnose the causes of defects in the target bridge based on the matching results;

[0027] Step S4: Based on the diagnosed causes of the defects, retrieve one or more maintenance measures corresponding to the causes of the defects from the bridge defect database as recommended solutions.

[0028] Among them, the bridge disease database refers to a structured dataset that stores the characteristics, causes and corresponding maintenance measures of bridge diseases. Specifically, it can be implemented by combining relational databases with knowledge graph technology. By integrating industry standards, expert experience and historical case data, the bridge disease database is formed. This bridge disease database provides unified data support for subsequent diagnosis and solves the problem of fragmented experience in existing technologies.

[0029] On-site defect information refers to the actual bridge inspection data collected through mobile terminals. Specifically, it can be obtained through a combination of form selection, image upload, and parameter input. That is, crack width parameters are automatically extracted through image recognition to realize the structured input of inspection data and ensure the objectivity and comprehensiveness of the diagnostic basis.

[0030] Matching analysis refers to the calculation process of comparing on-site data with pre-stored thresholds in the database. Specifically, it can be implemented using a rule engine or machine learning model, that is, comparing the crack width with the allowable value in the specification to determine the severity level, and replacing manual experience judgment with data-driven approach.

[0031] The maintenance measure recommendation refers to the operation of automatically associating pre-set solutions based on the diagnosis results. Specifically, it uses a database query interface to call the pre-stored measure data, that is, matching the grouting reinforcement solution according to the cause of the crack.

[0032] This invention establishes a complete data link from disease detection to maintenance decision-making by constructing a standardized bridge disease database and matching mechanism. By replacing manual experience-based judgment with structured data, it effectively improves the objectivity of diagnosis, the standardization of decision-making, and the efficiency of execution, thus forming a systematic solution.

[0033] The working process and principle of this invention are as follows: First, a bridge defect database is constructed, containing characteristic data, causal data, and maintenance measures matching various types of bridge defects. This bridge defect database serves as a knowledge base, providing support for subsequent diagnosis and decision-making. Next, the system receives on-site defect information of the target bridge input by the user, including defect type and defect characteristic parameters. This information serves as input data for diagnosis. Then, the received on-site defect information is matched and analyzed with the data in the bridge defect database. By comparing the on-site characteristic parameters with the pre-stored data in the database, an objective diagnosis of the defect's cause is achieved. Finally, based on the diagnosed defect cause, one or more maintenance measures corresponding to the defect cause are retrieved from the bridge defect database and output as recommended solutions. This method replaces subjective experience judgment with data-driven approaches, realizing a complete chain from defect detection to maintenance decision-making.

[0034] As a preferred embodiment, the specific implementation of the present invention is as follows: First, a bridge defect database is constructed, which includes characteristic data of various bridge defects such as cracks, corrosion, and deformation, such as crack width, length, and depth; corrosion area and depth; deformation amount, etc.; causal data, such as overload, material aging, and environmental erosion; and maintenance measures data matching various defects, such as crack grouting, steel reinforcement corrosion protection, and structural reinforcement. Second, the target bridge on-site defect information input by the user is received through a mobile terminal application. For example, for cracks appearing on the main beam of the bridge, the defect type is input as crack, and the characteristic parameters include crack width of 0.3 mm, length of 500 mm, and depth of 5 mm. Then, this on-site defect information is matched and analyzed with the data in the bridge defect database. By comparing the parameters such as crack width, length, and depth, it is diagnosed that the cause of the crack may be structural stress concentration caused by vehicle overload. Finally, based on the diagnosed cause of structural stress concentration caused by overload, corresponding maintenance measures are retrieved from the bridge defect database and output, such as crack grouting repair and strengthening bridge load-bearing capacity monitoring as recommended solutions.

[0035] In some of the solutions described above in this invention, the traditional manual input method suffers from low efficiency and inconsistent data formats. Furthermore, the single input mode cannot meet the multi-dimensional collection needs of complex disease characteristics, which can easily lead to the omission of key parameters or human error in information entry, thereby affecting the accuracy of subsequent matching analysis.

[0036] In response, this invention further proposes that on-site disease information be input via a mobile terminal application using one or more of the following methods: form selection, image upload, and parameter input.

[0037] The form selection allows for structured input of disease types through preset standardized options, namely, setting crack morphology options in the drop-down menu to include three types: transverse cracks, longitudinal cracks, and mesh cracks; the image upload function obtains disease images by calling the mobile terminal camera or local album interface, allowing users to take photos of cracks and automatically attach GPS location information; the parameter input uses numerical input boxes to force the collection of quantitative data, such as the crack width input box which limits the value unit to millimeters and only accepts values ​​in the range of 0.1-50mm;

[0038] When the three input methods are used in combination, the form triggers the corresponding parameter input fields after the type of defect is selected. For example, after selecting the concrete spalling type, the two required parameters, spalling area and depth, are automatically displayed. At the same time, the image upload component is activated to require the addition of a photo of the spalling surface morphology. The mobile terminal application dynamically associates different input methods through interface controls and automatically generates a standardized data package containing text, images, and values ​​when the data is submitted. The field structure of this data package directly corresponds to the storage format of the bridge defect database.

[0039] Specifically, during the disease information collection process, the form selection component guides users step-by-step to determine the location and type of disease through a hierarchical menu. For example, users can first select the bridge pier area and then select the crack subtype, effectively avoiding semantic ambiguity caused by free text input. After the user uploads a disease image, the application automatically compresses the image to a specified resolution and adds a timestamp, for example, adjusting the photo size to 1920×1080 pixels and saving it in JPG format.

[0040] The parameter input fields constrain the data format through input validation rules. For example, the crack length field restricts the input to positive integers, and the maximum value does not exceed the total length of the bridge deck. The data generated by the three input methods is encapsulated into a JSON format data stream during transmission. Text options are mapped to enumerated fields, images are converted to Base64 encoded strings, and numerical parameters are stored as floating-point data. This structured data stream can be directly parsed by the matching and analysis module without manual data cleaning or format conversion, enabling rapid comparison of disease feature parameters with pre-stored thresholds in the database. Through multimodal input constraints on mobile terminals, the flexibility of on-site inspection is preserved, while technical means are used to enforce the complete collection of key parameters. For example, if the user does not fill in the crack width parameter, the system will prevent data submission and prompt that a required field is missing.

[0041] In some of the solutions described above in this invention, on-site disease information is input via image upload to improve data collection efficiency. However, in this process, manual visual inspection or manual input of disease feature parameters is prone to subjective judgment errors, and it is difficult to quickly and accurately extract key parameters for complex disease features, resulting in low efficiency of subsequent matching analysis.

[0042] In response, this invention further proposes that when inputting via image upload, it also includes a step of performing image recognition on the uploaded disease image and automatically extracting disease feature parameters from the image.

[0043] The image recognition process employs convolutional neural networks to locate and segment the diseased area, and uses the U-Net architecture to achieve pixel-level crack detection. Simultaneously, morphological operations are combined to calculate the area ratio of the rusted region. During feature parameter extraction, the crack width can be measured using a sub-pixel edge detection algorithm with an accuracy of up to 0.1 mm. The error in calculating the rusted area is controlled within 5%. After standardized preprocessing, the diseased images are uniformly scaled to 1024×1024 pixels and converted to grayscale images to eliminate illumination interference. The extracted feature parameters are stored in a structured data format, including numerical parameters and classification labels, which directly correspond to the feature threshold fields in the disease database.

[0044] Specifically, when a user uploads images of damaged areas via a mobile device, the system automatically triggers an image processing flow. First, distortion correction and noise filtering are performed on the original image. Then, a trained deep learning model identifies damaged areas such as cracks and rust spots. For cracks, width data is sampled every 10 pixels along their extension direction, and the maximum value is used as a feature parameter. For rusted areas, the percentage of the component's surface area is calculated as a quantitative indicator. These parameters are automatically populated into the damage feature form, sharing the same data structure as manually input parameters, and can directly participate in subsequent matching analysis. By comparing the image recognition results with pre-stored typical damage features in the database, the system can quickly determine whether the crack propagation pattern is transverse or longitudinal, and whether the rust distribution is point corrosion or flaking, thereby improving the accuracy of causal diagnosis.

[0045] In some of the above-mentioned solutions of the present invention, it is proposed to match and analyze on-site disease information with database to diagnose the causes of disease. To this end, the present invention further proposes that the matching analysis includes comparing on-site disease characteristic parameters with pre-stored characteristic thresholds in the bridge disease database, and determining the severity level of the disease based on the comparison results.

[0046] The feature threshold comparison mechanism is implemented by setting quantitative indicators corresponding to different types of defects. For example, the crack width threshold can be set to three levels: 0.2 mm, 0.5 mm, and 1.0 mm. When the detected value exceeds the current threshold, the corresponding severity judgment is triggered. The severity classification logic adopts a multi-level classification system, dividing defects into three levels: minor, moderate, and severe. Each level corresponds to a different maintenance response mechanism. During the comparison process, the feature thresholds in the database are derived from statistical analysis of industry standards and historical cases. For example, the concrete carbonation depth threshold is set to 6 mm according to the "Standard for Evaluation of Technical Condition of Highway Bridges".

[0047] Specifically, during the matching analysis process, the disease characteristic parameters collected on-site are first compared with the characteristic thresholds in the database item by item. For example, when a crack width of 0.8 mm is detected, the system automatically matches the threshold range of more than 0.5 mm but less than 1.0 mm and judges it as a moderately severe level.

[0048] Subsequently, a disease level identifier is generated according to the preset grading rules. For example, the medium level is associated with the secondary response code. This level identifier is passed to the maintenance measure recommendation module, triggering the corresponding priority ranking rules. For example, the secondary response code automatically retrieves the repair plan that needs to be implemented within 30 days. By converting the threshold comparison results into standardized level data, the severity of different diseases is made comparable. For example, when there are both cracks with a width of 0.3 mm and carbonization with a depth of 5 mm, the system can determine them as mild and medium levels respectively according to the degree of their respective threshold exceedance, and then generate differentiated maintenance suggestions. This effectively eliminates the fluctuation of human experience judgment. For example, different inspectors may make different qualitative judgments on the same 0.6 mm crack, while the system achieves consistency of evaluation results by fixing the threshold.

[0049] In some of the above-mentioned solutions of the present invention, it is proposed to compare the on-site disease feature parameters with the feature thresholds pre-stored in the bridge disease database to determine the severity level of the disease. In this regard, the present invention further proposes that the recommended solution output in step S4 be prioritized according to the severity level.

[0050] The priority ranking is achieved by establishing a mapping relationship between severity levels and preset weight coefficients. The weight coefficients can be set to a numerical range between 0.5 and 1.5. When the severity level is 3, a weight value of 1.2 is assigned, and when the level is 1, a weight value of 0.8 is assigned. During the ranking process, maintenance measures are assigned weight values ​​corresponding to the severity level. A descending order of recommendation list is generated through numerical comparison. This ranking logic is integrated into the database query module and is automatically triggered when the maintenance measure data is called, so that the output recommendation scheme is directly presented as an ordered sequence.

[0051] Specifically, when the system detects a severity level of 3, the corresponding reinforcement measures in the database are assigned higher weights; for example, steel plate reinforcement or carbon fiber cloth repair measures are ranked at the top of the recommendation list. When the severity level is 1, preventative measures such as crack sealing or coating protection are prioritized. During the ranking process, the correspondence between weight coefficients and severity levels is established by querying a relational table in the database, which stores the priority rules for measure types corresponding to different levels. By embedding the ranking algorithm into the database call process, the system can simultaneously complete priority calculation when outputting recommended solutions, without requiring additional data processing steps.

[0052] In some of the solutions described above in this invention, the manual recording and formulation of maintenance suggestions leads to information dispersion, inconsistent formats, easy omission of key data, and inability to quickly generate structured reports for subsequent maintenance reference, which affects the standardization of maintenance decisions and execution efficiency. In response, this invention further proposes to generate and output standardized maintenance reports that include on-site disease information, disease diagnosis conclusions, and recommended solutions.

[0053] The standardized maintenance report integrates three types of data through a preset template: on-site disease information must include disease type, size, location, and detection time; disease diagnosis conclusions must cite the cause code and severity level obtained from database matching analysis; and recommended solutions must list maintenance measure numbers, implementation steps, and related causal basis. Furthermore, during the report generation process, the comparison results of disease characteristic parameters with database thresholds are automatically mapped to the severity indicator in the diagnosis conclusion, such as triggering a level 3 warning indicator when the crack width exceeds 5 mm. The priority ranking logic of recommended solutions is related to the severity level; when a level 2 or higher warning appears in the diagnosis conclusion, the corresponding measures are automatically displayed at the top of the report.

[0054] Specifically, the standardized maintenance report is output in electronic document format, with its content automatically filled in by the system without manual editing. After on-site defect information is collected via mobile terminal, the diagnostic conclusions generated by matching with the database are synchronously written into the designated fields of the report. The recommended solutions retrieve the corresponding measure items from the database based on the cause codes in the diagnostic conclusions. For example, when the diagnostic conclusion shows that steel corrosion has caused concrete spalling, the report automatically associates two types of measures in the database: anti-corrosion treatment and crack sealing, and calculates the required material usage based on the spalling area. Thus, the report content is structured and stored during the data collection stage, and each field is linked through a unique identifier to ensure information traceability. This solution, through a unified output format, makes maintenance reports of different bridges comparable, facilitating subsequent statistical analysis and maintenance plan development.

[0055] In some of the solutions described above in this invention, if the database only contains a basic description of maintenance measures without covering the resource information required for specific implementation, the recommended maintenance solutions will lack operability, making it impossible for decision-makers to directly assess the implementation costs, required working hours, and resource conditions of the measures. Due to incomplete information, it may be difficult to quickly select an economically reasonable and feasible solution, thereby affecting the efficiency and accuracy of maintenance decisions. In this regard, this invention further proposes that the maintenance measure data in the bridge disease database include the materials, equipment, working hours, and cost estimation information required for each measure.

[0056] The material information is standardized by listing concrete grade, steel bar specifications, and usage parameters. For example, the usage of C40 concrete is calculated as 0.15-0.25 cubic meters per square meter based on the crack repair area. The equipment information includes the grouting machine model, the accuracy index of the crack width measuring instrument, and the crane tonnage parameters. The accuracy of the crack width measuring instrument must reach 0.02 mm. The working time data is divided into the preparation stage and the construction stage, and is recorded separately for different types of work. The concrete curing process requires continuous inspection for 4 hours a day for 7 days. The cost estimation information automatically generates a budget table by associating the unit price of materials with the quantity of work. For example, the cost of steel bar rust removal is included in the cost at 800-1200 yuan per ton. The material list and equipment parameters jointly constrain the feasibility of construction conditions. The working time data and cost information form a multi-dimensional decision matrix. When the disease diagnosis module outputs a crack width exceeding 2 mm, the database prioritizes calling the solution that includes high-pressure grouting machine and epoxy resin materials.

[0057] Specifically, during the bridge defect database construction phase, various maintenance measures are broken down into material consumption lists, equipment configuration tables, work hour allocation schemes, and cost calculation models. When a user inputs defect information such as a crack length of 3 meters and a width of 2.5 millimeters, the matching analysis module calls the crack repair measure data in the database and filters out measures that simultaneously meet the crack width threshold and the grouting machine working pressure ≥8MPa. In the output recommended scheme, the material item for epoxy resin grouting method includes 8 kg of epoxy resin and a curing agent ratio of 1:0.3; the equipment item requires an electric grouting machine with an output pressure of 10MPa; the work hour item indicates a 3-person team working continuously for 6 hours; and the cost item shows material costs of 960 yuan and labor costs of 1800 yuan. By comparing the equipment availability, work hour window, and budget limit of different schemes, decision-makers can directly select the maintenance scheme with the highest matching degree with current resources, avoiding repeated adjustments to the scheme due to missing information.

[0058] In some of the solutions described above in this invention, a method for diagnosing and recommending bridge defects based on a bridge defect database has been proposed. However, in the process of multiple diagnoses and recommendations, due to the lack of accumulation and analysis of historical data, it is impossible to continuously track the development pattern of defects in the target bridge, resulting in the inability to dynamically assess the evolution trend of defects based on the time dimension, making it difficult to predict potential risks in advance and formulate preventive maintenance strategies. In this regard, this invention further proposes a step S6: recording and storing historical data of each diagnosis and recommendation, and predicting the development trend of defects in the target bridge based on the historical data.

[0059] The historical data records include disease type, characteristic parameters, diagnosis time, cause conclusions, and maintenance measures implementation results. The data storage adopts a structured database, and each record is associated with the unique identifier and timestamp of the target bridge. Disease development trend prediction is achieved through time series analysis, that is, using a sliding window to statistically analyze the rate of change of characteristic parameters, or predicting the growth trend of crack width over time based on a regression model. The historical data is linked with the threshold data in the bridge disease database. When the prediction result exceeds the preset safety threshold, an early warning signal is triggered. The maintenance measure recommendation scheme adds preventive maintenance suggestions, such as adding reinforcement measures before the predicted crack expansion.

[0060] Specifically, the characteristic parameters of each diagnosis, the conclusions of its causes, and the effects of the maintenance measures are stored as time-stamped data units, forming a timeline of the bridge's disease evolution. By extracting the changes in characteristic parameters at different time points, the rate of disease development is calculated and a trend curve is fitted. For example, the growth model of concrete carbonation depth is analyzed on a three-month cycle. When the prediction results show that a certain disease parameter will exceed the safety threshold within the next six months, the system automatically generates a preventive maintenance plan and adjusts the maintenance priority. The combination of historical data with industry standard thresholds and material performance degradation models in the original database enables the prediction results to reflect the combined effects of bridge material aging and load changes, thereby improving the accuracy of the prediction.

[0061] In some of the solutions described above in this invention, it is further proposed that the data of the bridge disease database be constructed based on bridge industry standards, expert experience and historical case data.

[0062] Among them, bridge industry standard data is used to set the threshold for disease characteristics and the basic standards for maintenance measures. For example, the allowable value for crack width can be set to 0.2 mm according to the durability design standard for concrete structures in the standard. Expert experience data is transformed into causal association rules through knowledge graph technology. Specifically, when the beam deflection exceeds 1 / 600 of the span, an early warning condition of increased steel corrosion probability is automatically associated. Historical case data is stored in a structured manner to record real treatment, including material usage, labor consumption, and post-repair monitoring data. For example, in a case of abnormal cable force in a cable-stayed bridge, the empirical data that the stress distribution returned to normal after adjusting the tension to 105% of the design value was included in the database. The three types of data complement each other in matching analysis. Industry standard data ensures the compliance of diagnostic benchmarks, expert experience data expands the logical dimension of causal reasoning, and historical case data provides the basis for verifying the effectiveness of measures.

[0063] Specifically, after receiving on-site damage information, the industry-standard data first performs compliance checks on characteristic parameters. For example, when a crack width of 0.3 mm is detected, an alarm is automatically triggered indicating that the threshold exceeds the standard. Then, it calls upon association rules from expert experience data, combining parameters such as environmental humidity and load history to deduce the potential causes of alkali-aggregate reaction or overload fatigue. Finally, it matches treatment plans for similar working conditions in the historical case library, prioritizing the recommended maintenance measures that have been validated and offer the best cost-effectiveness. Through hierarchical processing of multi-source data, it avoids diagnostic biases caused by a single data source and uses empirical data to select more applicable maintenance plans, enabling the database to dynamically adapt to the differentiated needs of different regions, structural types, and operating environments.

[0064] In another embodiment of the present invention, an electronic device is also proposed, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it performs the following steps: constructing a bridge defect database, the bridge defect database including characteristic data, causal data, and maintenance measure data matching various types of bridge defects; receiving on-site defect information of a target bridge input by a user, the on-site defect information including defect type and defect characteristic parameters; matching and analyzing the on-site defect information with the data in the bridge defect database, and diagnosing the cause of the defect of the target bridge based on the matching results; calling and outputting one or more maintenance measures corresponding to the defect cause as recommended solutions from the bridge defect database according to the diagnosed defect cause; generating and outputting a standardized maintenance report containing the on-site defect information, defect diagnosis conclusion, and recommended solutions; recording and storing historical data of each diagnosis and recommendation, and predicting the defect development trend of the target bridge based on the historical data.

[0065] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The embodiments and descriptions in the specification are merely illustrative of the principles of the invention. Various changes and modifications can be made to the invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the present invention as claimed. The scope of protection of the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for diagnosing bridge defects and recommending maintenance measures, characterized in that: Includes the following steps: Step S1: Construct a bridge defect database, which includes characteristic data, causal data, and maintenance measures data matching various types of bridge defects. Step S2: Receive on-site defect information of the target bridge input by the user, wherein the on-site defect information includes defect type and defect characteristic parameters; Step S3: Match and analyze the on-site defect information with the data in the bridge defect database, and diagnose the causes of defects in the target bridge based on the matching results; Step S4: Based on the diagnosed causes of the defects, retrieve and output one or more maintenance measures corresponding to the causes of the defects from the bridge defect database as recommended solutions.

2. The method for recommending bridge defects and maintenance measures according to claim 1, characterized in that: In step S2, the on-site disease information is input through a mobile terminal application using one or more of the following methods: form selection, image upload, and parameter input.

3. The method for recommending bridge defects and maintenance measures according to claim 2, characterized in that: In step S2, when input is via image upload, the method further includes performing image recognition on the uploaded disease image and automatically extracting disease feature parameters from the image.

4. The method for recommending bridge defects and maintenance measures according to claim 1, characterized in that: The matching analysis in step S3 includes: comparing the on-site defect feature parameters with the feature thresholds pre-stored in the bridge defect database, and determining the severity level of the defect based on the comparison results.

5. The method for recommending bridge defects and maintenance measures according to claim 4, characterized in that: The recommended solutions output in step S4 are prioritized according to the severity level.

6. The method for recommending bridge defects and maintenance measures according to claim 1, characterized in that: It also includes step S5: generating and outputting a standardized maintenance report containing the on-site disease information, disease diagnosis conclusions, and the recommended scheme.

7. The method for diagnosing bridge defects and recommending maintenance measures according to claim 1, characterized in that: The maintenance measures data in the bridge defect database include information on the materials, equipment, labor hours, and cost estimates required for each measure.

8. The method for diagnosing bridge defects and recommending maintenance measures according to claim 1, characterized in that: It also includes step S6: recording and storing historical data for each diagnosis and recommendation, and predicting the development trend of the target bridge's defects based on the historical data.

9. The method according to claim 1, characterized in that, The bridge defect database is built based on bridge industry standards, expert experience, and historical case data.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, it implements the steps of the method as described in any one of claims 1 to 9.

Images