Corrosion environment bridge cable life prediction method and system based on data analysis

Abstract

The invention discloses a corrosion environment bridge cable life prediction method and system based on data analysis, and relates to the technical field of bridge engineering, the system collects environmental data and cable corrosion data in real time through an integrated sensor group, and the environmental data and the cable corrosion data are transmitted and preprocessed through a wireless network LoRa and then stored in a non-relational database NoSQL. The method comprises the following steps: extracting health feature data, calculating a cable health index Lfs, and carrying out preliminary evaluation on the cable health index Lfs and a preset cable safety threshold A; and if the inhaul cable is in a healthy state, triggering secondary evaluation, deeply analyzing surface characteristics and environmental characteristics of the inhaul cable, and calculating a surface corrosion influence index Bmy and an environmental influence index Hjx of the inhaul cable. And calculating a comprehensive corrosion rate prediction index FYC according to the indexes, and comparing the comprehensive corrosion rate prediction index FYC with a preset corrosion rate threshold B to generate corresponding early warning information. The system aims at monitoring and evaluating the corrosion state of the bridge inhaul cable in real time, improving the safety and reliability of a bridge and taking maintenance measures in time.

Description

Technical Field

[0001] This invention relates to the field of bridge engineering technology, specifically to a method and system for predicting the lifespan of bridge cables in corrosive environments based on data analysis. Background Technology

[0002] In the process of modern urbanization, bridges, as vital transportation infrastructure, not only bear the heavy responsibility of transportation but also support socio-economic development. However, with accelerated industrialization and intensified environmental pollution, bridge corrosion has become an increasingly serious problem, a significant factor restricting bridge safety and service life. Bridge construction often focuses on design and construction, while insufficient attention is paid to material corrosion and its impact during long-term operation. This has led to many bridges experiencing unforeseen safety hazards after decades of use, and even partial or complete structural failure. With increased awareness of infrastructure safety, countries have begun to emphasize bridge monitoring and maintenance, driving the development of related technologies.

[0003] Existing bridge cable corrosion prediction technologies still face numerous challenges. First, many traditional assessment methods rely on experience or periodic inspections, making real-time monitoring difficult and failing to adapt flexibly to changes in the actual environment. This inadequacy not only reduces maintenance efficiency and leads to delayed responses to corrosion, but can also cause accidents and incalculable losses when cable corrosion worsens. Second, due to a lack of accurate data collection and analysis, many assessment results are often flawed, making bridge maintenance decisions less scientific. This situation not only increases bridge maintenance costs but may also create safety hazards at critical moments, threatening traffic safety. Therefore, data-driven systems urgently need to fill this technological gap to achieve scientific and efficient bridge maintenance management. Summary of the Invention

[0004] To address the shortcomings of existing technologies, this invention provides a method and system for predicting the lifespan of bridge cables in corrosive environments based on data analysis, thus solving the problems mentioned in the background section.

[0005] To achieve the above objectives, the present invention is implemented through the following technical solution: a data analysis-based bridge cable life prediction system in corrosive environments, comprising a cable data acquisition module, a wireless storage module, a cable health analysis module, a cable corrosion analysis module, and a corrosion prediction and assessment module;

[0006] The cable data acquisition module collects environmental data and cable corrosion data in real time through an integrated sensor group installed on the cable. After encapsulating the environmental data and cable corrosion data, it obtains a data encapsulation packet and transmits the data encapsulation packet to the wireless storage module via the LoRa wireless network.

[0007] The wireless storage module is used to receive data encapsulation packets in real time, decapsulate the data encapsulation packets to extract environmental data and cable corrosion data, perform preprocessing to obtain cable safety dataset, and store the cable safety dataset in a local NoSQL database.

[0008] The cable health analysis module is used to extract cable safety datasets for feature analysis, obtain cable health feature data groups, summarize and calculate the extracted cable health feature data to obtain the cable health index Lfs, and then perform a preliminary evaluation with the preset cable safety threshold A, and trigger a secondary evaluation mechanism based on the evaluation results.

[0009] The cable corrosion analysis module is used to access the cable safety dataset when the cable is initially assessed as being in a healthy state, extract the cable surface feature data group and environmental feature data group, and perform summary calculations to obtain the cable surface corrosion impact index Bmy and the environmental impact index Hjx.

[0010] The corrosion prediction and assessment module is used to summarize and calculate the comprehensive corrosion rate prediction index FYC based on the obtained cable health index Lfs, cable surface corrosion impact index Bmy, and environmental impact index Hjx. Then, it performs a second assessment with the preset cable corrosion rate threshold B to deeply evaluate the cable corrosion rate and generate relevant early warning information based on the assessment results.

[0011] Preferably, the cable data acquisition module includes a data acquisition unit and a wireless transmission unit;

[0012] The data acquisition unit collects environmental data and cable corrosion data in real time through an integrated sensor group installed at various locations on the cable, and transmits the collected environmental data and cable corrosion data to the wireless transmission unit via the LoRa wireless network;

[0013] The integrated sensor group includes a chemical sensor, a surface roughness measuring instrument, a temperature and humidity sensor, a conductivity sensor, a gas sensor, an ultrasonic sensor, and a magnetic thickness sensor.

[0014] The wireless transmission unit is used to receive environmental data and cable corrosion data collected in real time by each sensor. It encapsulates the environmental data and cable corrosion data into a JSON format data package using a JSON encapsulation tool, and marks the environmental conditions, sensor ID, sensor measurement value, data type and collection timestamp on the data package. Then, it sends the data package to the wireless storage module in real time via the LoRa wireless network.

[0015] Preferably, the wireless storage module includes a data processing unit and a data storage unit;

[0016] The data processing unit is used to receive data packages in real time, parse the data packages using a JSON parsing tool, extract sensor measurement values ​​of environmental data and cable corrosion data from the JSON format data packages, and preprocess the sensor measurement values. The preprocessing includes using statistical methods to identify and delete outliers, data cleaning, noise filtering, and normalization to obtain a cable safety dataset.

[0017] The cable safety dataset includes a cable health characteristic data set, a cable surface characteristic data set, and an environmental characteristic data set.

[0018] The cable health characteristic data set includes the cable's factory diameter zj, cable's remaining diameter sh, chloride ion concentration cl, sulfate concentration so, and nitrate concentration no;

[0019] The cable surface feature data set includes cable surface roughness cc, coating integrity tc, and oxide layer thickness yh;

[0020] The environmental characteristic data set includes ambient temperature wd, ambient humidity sd, salinity concentration yf, and environmental corrosive pollutant concentration wr;

[0021] The data storage unit is used to store the preprocessed cable safety dataset into a local NoSQL database via an API port, and connects to the cable health analysis module and the cable corrosion analysis module via a LoRa wireless network to extract data from the cable safety dataset in real time.

[0022] Preferably, the cable health analysis module includes a cable health calculation unit and a cable health assessment unit;

[0023] The LAS health computing unit accesses the LAS security dataset via the LoRa wireless network, extracts LAS health feature data groups, and then performs aggregate calculations to obtain the LAS health index Lfs.

[0024] The Lfs health index is calculated using the following formula;

[0025]

[0026] Preferably, the cable health assessment unit is used to perform a preset cable safety threshold A based on historical cable health data in a local NoSQL database, and to conduct a preliminary comparison assessment with the obtained cable health index Lfs. Based on the assessment results, a secondary assessment mechanism is triggered. The specific assessment scheme is as follows.

[0027] When the cable health index Lfs < the preset cable safety threshold A, it indicates that the current cable is in a healthy state. At this time, the cable is maintained at a normal cycle and the second evaluation mechanism is triggered.

[0028] When the cable health index Lfs is greater than or equal to the preset cable safety threshold A, it indicates that the cable is in a dangerous state. At this time, the first warning message is generated and notified to relevant personnel through the alarm system so that emergency measures can be taken immediately for the cable.

[0029] Preferably, the cable corrosion analysis module is used to access the cable safety dataset via the LoRa wireless network and extract the cable surface feature data set and environmental feature data set when the cable is initially assessed as being in a healthy state;

[0030] The cable corrosion analysis module includes a cable surface corrosion calculation unit and an environmental impact calculation unit;

[0031] The cable surface corrosion calculation unit is used to perform summary calculations based on the acquired cable surface feature data set to obtain the cable surface corrosion influence index Bmy.

[0032] The corrosion impact index Bmy on the cable surface is calculated using the following formula;

[0033]

[0034] In the formula, k4 represents the material and environmental characteristic constants, which are obtained through experiments; k5 represents the influence coefficient of metal composition, which represents the corrosion resistance of different metals; and e represents an exponential function.

[0035] Preferably, the environmental impact calculation unit is used to perform summary calculations based on the acquired environmental characteristic data set to obtain the environmental impact index Hjx;

[0036] The environmental impact index Hjx is calculated using the following formula;

[0037]

[0038] In the formula, ln represents the logarithmic function, k1 represents the cable material property constant, a fixed value obtained through experimental data, k2 represents the temperature effect constant, reflecting the effect of temperature changes on corrosion, and k3 represents the contaminant threshold constant, providing a benchmark for the effect of contaminant concentration on corrosion, which is determined through experiments.

[0039] Preferably, the corrosion prediction and evaluation module includes a corrosion prediction calculation unit and a prediction and evaluation unit;

[0040] The corrosion prediction calculation unit is used to summarize and calculate the comprehensive corrosion rate prediction index FYC based on the obtained cable health index Lfs, cable surface corrosion impact index Bmy and environmental impact index Hjx.

[0041] The comprehensive corrosion rate prediction index FYC is calculated using the following formula;

[0042]

[0043] In the formula, w1, w2 and w3 represent the weighting coefficients of the cable health index Lfs, the cable surface corrosion impact index Bmy and the environmental impact index Hjx, respectively, and w1+w2+w3=1. The specific values ​​are set by the user. w4 represents the time decay coefficient and t represents the time variable.

[0044] Preferably, the prediction and evaluation unit is used to preset the cable corrosion rate threshold B, and perform a secondary comparison and evaluation with the obtained comprehensive corrosion rate prediction index FYC, and generate corresponding early warning information based on the evaluation results. The specific evaluation scheme is as follows.

[0045] When the comprehensive corrosion rate prediction index FYC ≤ the preset cable corrosion rate threshold B, it indicates that the current cable corrosion rate is normal and normal monitoring should be maintained.

[0046] When the comprehensive corrosion rate prediction index FYC is greater than the preset cable corrosion rate threshold B, it indicates that the current cable corrosion rate is abnormal. At this time, a second warning message is generated and the relevant personnel are notified through the alarm system to carry out relevant inspections and maintenance on the cable.

[0047] A data-driven method for predicting the life of bridge cables in corrosive environments includes the following steps:

[0048] Step 1: Collect environmental data and cable corrosion data in real time using an integrated sensor group installed on the cable. After encapsulating the environmental data and cable corrosion data, obtain the data encapsulation packet and transmit the data encapsulation packet to Step 2 via the LoRa wireless network.

[0049] Step 2: Receive data encapsulation packets in real time, decapsulate the data encapsulation packets to extract environmental data and cable corrosion data, perform preprocessing to obtain cable safety datasets, and store the cable safety datasets in a local NoSQL database.

[0050] Step 3: Extract the cable safety dataset for feature analysis to obtain cable health feature data set, summarize and calculate the extracted cable health feature data to obtain the cable health index Lfs, and then conduct a preliminary evaluation with the preset cable safety threshold A. Based on the evaluation results, trigger the secondary evaluation mechanism.

[0051] Step 4: Based on the preliminary assessment that the cable is in a healthy state, access the cable safety dataset, extract the cable surface feature data group and environmental feature data group, and perform summary calculations to obtain the cable surface corrosion impact index Bmy and environmental impact index Hjx.

[0052] Step 5: Based on the obtained cable health index Lfs, cable surface corrosion impact index Bmy, and environmental impact index Hjx, a comprehensive corrosion rate prediction index FYC is calculated. Then, a second evaluation is performed with the preset cable corrosion rate threshold B to deeply evaluate the cable corrosion rate, and relevant early warning information is generated based on the evaluation results.

[0053] This invention provides a method and system for predicting the life of bridge cables in corrosive environments based on data analysis. It has the following beneficial effects:

[0054] (1) The system's cable data acquisition module integrates an integrated sensor array to ensure comprehensive acquisition of environmental and cable corrosion data. This data is transmitted and stored via a LoRa wireless network, and then decrypted and preprocessed in the wireless storage module to generate a reliable cable safety dataset. This process not only improves the efficiency of data acquisition but also ensures the accuracy of the information, providing a solid data foundation for subsequent health analysis and assessment.

[0055] (2) The system's initial assessment, based on a comparison between the cable health index Lfs and the preset cable safety threshold A, can quickly identify healthy or potentially hazardous conditions. If the cable is in a hazardous state, an emergency warning will be triggered to ensure that relevant personnel can take timely countermeasures. The secondary assessment further analyzes the impact of cable surface characteristics and environmental factors on corrosion, using the obtained cable surface corrosion impact index Bmy and environmental impact index Hjx for comprehensive calculation. This dual assessment model greatly enhances the sensitivity to corrosion risks, making maintenance decisions more scientific and effective.

[0056] (3) This system provides bridge managers with a quantitative basis for maintenance strategies through the calculation and early warning mechanism of the Comprehensive Corrosion Rate Prediction Index (FYC). Utilizing different environmental data and material properties, the system can personalize maintenance frequency and strategies, thereby optimizing resource allocation and maintenance costs. This not only improves the operational safety of bridges but also enhances public trust in infrastructure, providing valuable reference for future engineering design and management. Overall, the system demonstrates significant innovative value in corrosion monitoring, risk assessment, and maintenance management, driving technological progress in the field of bridge engineering. Attached Figure Description

[0057] Figure 1 This is a schematic diagram of the data analysis-based bridge cable life prediction system in a corrosive environment according to the present invention.

[0058] Figure 2 This is a schematic diagram illustrating the steps of the data analysis-based method for predicting the lifespan of bridge cables in corrosive environments according to the present invention. Detailed Implementation

[0059] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0060] Example 1

[0061] Please see Figure 1 This invention provides a data analysis-based system for predicting the lifespan of bridge cables in corrosive environments. To achieve the above objectives, this invention employs the following technical solutions: including a cable data acquisition module, a wireless storage module, a cable health analysis module, a cable corrosion analysis module, and a corrosion prediction and assessment module.

[0062] The cable data acquisition module collects environmental data and cable corrosion data in real time through an integrated sensor group installed on the cable. After encapsulating the environmental data and cable corrosion data, it obtains a data encapsulation packet and transmits the data encapsulation packet to the wireless storage module via the LoRa wireless network.

[0063] The wireless storage module is used to receive data encapsulation packets in real time, decapsulate the data encapsulation packets to extract environmental data and cable corrosion data, perform preprocessing to obtain cable safety dataset, and store the cable safety dataset in a local NoSQL database.

[0064] The cable health analysis module is used to extract cable safety datasets for feature analysis, obtain cable health feature data groups, summarize and calculate the extracted cable health feature data to obtain the cable health index Lfs, and then perform a preliminary evaluation with the preset cable safety threshold A, and trigger a secondary evaluation mechanism based on the evaluation results.

[0065] The cable corrosion analysis module is used to access the cable safety dataset when the cable is initially assessed as being in a healthy state, extract the cable surface feature data group and environmental feature data group, and perform summary calculations to obtain the cable surface corrosion impact index Bmy and the environmental impact index Hjx.

[0066] The corrosion prediction and assessment module is used to summarize and calculate the comprehensive corrosion rate prediction index FYC based on the obtained cable health index Lfs, cable surface corrosion impact index Bmy, and environmental impact index Hjx. Then, it performs a second assessment with the preset cable corrosion rate threshold B to deeply evaluate the cable corrosion rate and generate relevant early warning information based on the assessment results.

[0067] In this embodiment, the data acquisition module utilizes integrated sensors to acquire environmental and corrosion data in real time and transmits it to the storage module via a LoRa wireless network, ensuring efficient data transmission and processing. This real-time capability significantly improves the response speed to the cable health status, enabling timely identification of potential corrosion risks and effectively reducing safety hazards. The wireless storage module is responsible for data desealing and preprocessing, forming a complete cable safety dataset. This process provides the foundation for subsequent health analysis, allowing the cable health analysis module to extract key features and calculate the health index Lfs, which is then used for preliminary evaluation against a preset cable safety threshold A. Through this multi-layered analysis mechanism, the system not only achieves accurate health assessment but also triggers targeted secondary assessments, ensuring appropriate maintenance measures are taken under different health conditions. The corrosion prediction and assessment module performs a comprehensive analysis based on the cable health index Lfs, the cable surface corrosion impact index Bmy, and the environmental impact index Hjx, calculating the corrosion rate prediction index FYC. This predictive capability enables managers to identify and respond to corrosion risks in a timely manner, thereby optimizing maintenance strategies and resource allocation. Compared with traditional technologies, this system has significant improvements in real-time performance, data processing, and risk assessment, promoting the intelligent and scientific management of bridge maintenance and improving the overall safety and operational efficiency of bridges.

[0068] Example 2

[0069] This embodiment is an explanation based on Embodiment 1. Please refer to it. Figure 1 Specifically: the cable data acquisition module includes a data acquisition unit and a wireless transmission unit;

[0070] The data acquisition unit collects environmental data and cable corrosion data in real time through an integrated sensor group installed at various locations on the cable, and transmits the collected environmental data and cable corrosion data to the wireless transmission unit via the LoRa wireless network;

[0071] The integrated sensor group includes a chemical sensor, a surface roughness measuring instrument, a temperature and humidity sensor, a conductivity sensor, a gas sensor, an ultrasonic sensor, and a magnetic thickness sensor.

[0072] The wireless transmission unit is used to receive environmental data and cable corrosion data collected in real time by each sensor. It encapsulates the environmental data and cable corrosion data into JSON format data packets using a JSON encapsulation tool, and marks the environmental conditions, sensor ID, sensor measurement value, data type and collection timestamp on the data packets. The data packets are then sent to the wireless storage module in real time via the LoRa wireless network.

[0073] In this embodiment, the cable data acquisition module integrates multiple sensors to achieve real-time monitoring and transmission of environmental and cable corrosion data. This system not only improves the comprehensiveness and accuracy of data acquisition but also achieves efficient data transmission and processing via the LoRa wireless network. The use of JSON-formatted environmental and corrosion data packets makes the data structure clearer, facilitating subsequent analysis and storage. This design can reflect the health status of the cables in real time, respond quickly to environmental changes, and significantly improve the safety and reliability of the structure. Furthermore, the system's flexibility and scalability provide a solid foundation for future intelligent monitoring and maintenance, promoting the digital transformation and intelligent management of bridge engineering.

[0074] Example 3

[0075] This embodiment is an explanation based on Embodiment 2. Please refer to it. Figure 1 Specifically: the wireless storage module includes a data processing unit and a data storage unit;

[0076] The data processing unit is used to receive data packages in real time, parse the data packages using a JSON parsing tool, extract sensor measurement values ​​of environmental data and cable corrosion data from the JSON format data packages, and preprocess the sensor measurement values. The preprocessing includes using statistical methods to identify and delete outliers, data cleaning, noise filtering, and normalization to obtain a cable safety dataset.

[0077] The cable safety dataset includes a cable health characteristic data set, a cable surface characteristic data set, and an environmental characteristic data set.

[0078] The cable health characteristic data set includes the cable's factory diameter zj, cable's remaining diameter sh, chloride ion concentration cl, sulfate concentration so, and nitrate concentration no;

[0079] The cable surface feature data set includes cable surface roughness cc, coating integrity tc, and oxide layer thickness yh;

[0080] The environmental characteristic data set includes ambient temperature wd, ambient humidity sd, salinity concentration yf, and environmental corrosive pollutant concentration wr;

[0081] The data storage unit is used to store the preprocessed cable safety dataset into a local NoSQL database via an API port, and connects to the cable health analysis module and the cable corrosion analysis module via a LoRa wireless network to extract data from the cable safety dataset in real time.

[0082] In this embodiment, by receiving and parsing data packets in real time, the data processing unit can efficiently extract sensor measurements and perform a series of preprocessing steps, such as outlier removal, data cleaning, and noise filtering, ensuring the accuracy and reliability of the data. The generated cable safety dataset covers health characteristics, surface characteristics, and environmental characteristics, providing a comprehensive foundation for structural health status assessment. This structured data storage method not only facilitates subsequent analysis and decision-making but also lays the foundation for real-time connection with the cable health analysis module and corrosion analysis module, thereby realizing intelligent monitoring and maintenance strategies, ensuring the safety and durability of the bridge, and promoting the transformation of engineering management towards digitalization and intelligence.

[0083] Example 4

[0084] This embodiment is an explanation based on Embodiment 3. Please refer to it. Figure 1 Specifically: the cable health analysis module includes a cable health calculation unit and a cable health assessment unit;

[0085] The LAS health computing unit accesses the LAS security dataset via the LoRa wireless network, extracts LAS health feature data groups, and then performs aggregate calculations to obtain the LAS health index Lfs.

[0086] The Lfs health index is calculated using the following formula;

[0087]

[0088] The cable health assessment unit is used to perform a preset cable safety threshold A based on historical cable health data in the local NoSQL database, and to conduct a preliminary comparison and assessment with the obtained cable health index Lfs. Based on the assessment results, a secondary assessment mechanism is triggered. The specific assessment scheme is as follows.

[0089] When the cable health index Lfs is less than the preset cable safety threshold A, it indicates that the cable is currently in a healthy state. At this time, the cable is maintained at a normal cycle and the second evaluation mechanism is triggered.

[0090] When the cable health index Lfs is greater than or equal to the preset cable safety threshold A, it indicates that the cable is in a dangerous state. At this time, the first warning message is generated and notified to relevant personnel through the alarm system so that emergency measures can be taken immediately for the cable.

[0091] In this embodiment, a security dataset is accessed via the LoRa wireless network to extract and calculate the cable health index Lfs, making health assessment more scientific and real-time. By comparing it with a preset safety threshold A, the system can not only effectively identify the health status of the cables but also quickly respond to potential safety hazards and trigger early warning mechanisms in a timely manner. When the cables are in a healthy state, normal maintenance can extend their service life; while in a dangerous state, the generation of the first warning information and the intervention of the alarm system ensure the efficiency of emergency response. This flexible early warning mechanism improves the intelligence level of structural safety management, greatly reduces the risk of accidents, and provides a more reliable basis for bridge maintenance decisions.

[0092] Example 5

[0093] This embodiment is an explanation based on Embodiment 4. Please refer to it. Figure 1 Specifically: the cable corrosion analysis module is used to access the cable safety dataset via the LoRa wireless network and extract the cable surface feature data set and environmental feature data set when the cable is initially assessed as being in a healthy state;

[0094] The cable corrosion analysis module includes a cable surface corrosion calculation unit and an environmental impact calculation unit;

[0095] The cable surface corrosion calculation unit is used to perform summary calculations based on the acquired cable surface feature data set to obtain the cable surface corrosion influence index Bmy.

[0096] The corrosion impact index Bmy on the cable surface is calculated using the following formula;

[0097]

[0098] In the formula, k4 represents the material and environmental characteristic constants, which are obtained through experiments; k5 represents the influence coefficient of metal composition; and e represents an exponential function.

[0099] The environmental impact calculation unit is used to perform summary calculations based on the acquired environmental characteristic data set to obtain the environmental impact index Hjx.

[0100] The environmental impact index Hjx is calculated using the following formula;

[0101]

[0102] In the formula, ln represents the logarithmic function, k1 represents the cable material property constant, k2 represents the temperature effect constant, and k3 represents the pollutant threshold constant.

[0103] In this embodiment, the cable corrosion analysis module provides comprehensive corrosion assessment and analysis capabilities by integrating cable surface feature and environmental feature data. When the cable condition is initially assessed as healthy, the module can efficiently access a secure dataset via the LoRa wireless network to extract key feature data. By calculating the cable surface corrosion impact index Bmy and the environmental impact index Hjx, the system can quantify the specific impact of corrosion risk and environmental factors on the cable. This data-driven approach not only improves the accuracy of predictions but also identifies potential risks in a timely manner, ensuring the safety and service life of the structure. Through this dynamic monitoring and assessment, the efficiency and scientific nature of bridge maintenance management are significantly improved, promoting the sustainable development of smart infrastructure.

[0104] Example 6

[0105] This embodiment is an explanation based on Embodiment 1. Please refer to it. Figure 1 Specifically: the corrosion prediction and evaluation module includes a corrosion prediction calculation unit and a prediction and evaluation unit;

[0106] The corrosion prediction calculation unit is used to summarize and calculate the comprehensive corrosion rate prediction index FYC based on the obtained cable health index Lfs, cable surface corrosion impact index Bmy and environmental impact index Hjx.

[0107] The comprehensive corrosion rate prediction index FYC is calculated using the following formula;

[0108]

[0109] In the formula, w1, w2 and w3 represent the weighting coefficients of the cable health index Lfs, the cable surface corrosion impact index Bmy and the environmental impact index Hjx, respectively, and w1+w2+w3=1. The specific values ​​are set by the user. w4 represents the time decay coefficient and t represents the time variable.

[0110] The prediction and evaluation unit is used to preset the cable corrosion rate threshold B, and perform a secondary comparison and evaluation with the obtained comprehensive corrosion rate prediction index FYC, and generate corresponding early warning information based on the evaluation results. The specific evaluation scheme is as follows.

[0111] When the comprehensive corrosion rate prediction index FYC ≤ the preset cable corrosion rate threshold B, it indicates that the current cable corrosion rate is normal and normal monitoring should be maintained.

[0112] When the comprehensive corrosion rate prediction index FYC is greater than the preset cable corrosion rate threshold B, it indicates that the current cable corrosion rate is abnormal. At this time, a second warning message is generated and the relevant personnel are notified through the alarm system to carry out relevant inspections and maintenance on the cable.

[0113] In this embodiment, the corrosion prediction and assessment module comprehensively analyzes the cable health index Lfs, the cable surface corrosion impact index Bmy, and the environmental impact index Hjx, and calculates the comprehensive corrosion rate prediction index FYC, significantly improving the monitoring capability of the cable condition. The innovation of this module lies in the introduction of a time decay coefficient, which dynamically reflects the corrosion status of the cable, ensuring that the prediction results are closer to the actual situation. Through secondary comparison and evaluation with a preset corrosion rate threshold B, the system can promptly identify abnormal corrosion rates and automatically generate early warning information, ensuring that relevant personnel can take swift action. This intelligent monitoring and assessment mechanism not only improves the safety of the bridge and reduces potential risks, but also provides a scientific basis for structural maintenance and management, promoting the efficiency and systematization of maintenance work, thereby extending the service life of the cables.

[0114] Example 7

[0115] Please refer to Figure 2 A data-based method for predicting the life of bridge cables in corrosive environments includes the following steps:

[0116] Step 1: Collect environmental data and cable corrosion data in real time using an integrated sensor group installed on the cable. After encapsulating the environmental data and cable corrosion data, obtain the data encapsulation packet and transmit the data encapsulation packet to Step 2 via the LoRa wireless network.

[0117] Step 2: Receive data encapsulation packets in real time, decapsulate the data encapsulation packets to extract environmental data and cable corrosion data, perform preprocessing to obtain cable safety datasets, and store the cable safety datasets in a local NoSQL database.

[0118] Step 3: Extract the cable safety dataset for feature analysis to obtain cable health feature data set, summarize and calculate the extracted cable health feature data to obtain the cable health index Lfs, and then conduct a preliminary evaluation with the preset cable safety threshold A. Based on the evaluation results, trigger the secondary evaluation mechanism.

[0119] Step 4: Based on the preliminary assessment that the cable is in a healthy state, access the cable safety dataset, extract the cable surface feature data group and environmental feature data group, and perform summary calculations to obtain the cable surface corrosion impact index Bmy and environmental impact index Hjx.

[0120] Step 5: Based on the obtained cable health index Lfs, cable surface corrosion impact index Bmy, and environmental impact index Hjx, a comprehensive corrosion rate prediction index FYC is calculated. Then, a second evaluation is performed with the preset cable corrosion rate threshold B to deeply evaluate the cable corrosion rate, and relevant early warning information is generated based on the evaluation results.

[0121] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A data analysis-based system for predicting the lifespan of bridge cables in corrosive environments, characterized in that: It includes a cable data acquisition module, a wireless storage module, a cable health analysis module, a cable corrosion analysis module, and a corrosion prediction and assessment module; The cable data acquisition module collects environmental data and cable corrosion data in real time through an integrated sensor group installed on the cable. After encapsulating the environmental data and cable corrosion data, it obtains a data encapsulation packet and transmits the data encapsulation packet to the wireless storage module via the LoRa wireless network. The wireless storage module is used to receive data encapsulation packets in real time, decapsulate the data encapsulation packets to extract environmental data and cable corrosion data, perform preprocessing to obtain cable safety dataset, and store the cable safety dataset in a local NoSQL database. The cable health analysis module is used to extract cable safety datasets for feature analysis, obtain cable health feature data groups, summarize and calculate the extracted cable health feature data groups to obtain the cable health index Lfs, and then perform a preliminary evaluation with the preset cable safety threshold A, and trigger a secondary evaluation mechanism based on the evaluation results. The cable corrosion analysis module is used to access the cable safety dataset when the cable is initially assessed as being in a healthy state, extract the cable surface feature data group and environmental feature data group, and perform summary calculations to obtain the cable surface corrosion impact index Bmy and the environmental impact index Hjx. The corrosion prediction and assessment module is used to summarize and calculate the comprehensive corrosion rate prediction index FYC based on the obtained cable health index Lfs, cable surface corrosion impact index Bmy, and environmental impact index Hjx. Then, it performs a second assessment with the preset cable corrosion rate threshold B to deeply evaluate the cable corrosion rate and generate relevant early warning information based on the assessment results.

2. The data analysis-based bridge cable life prediction system for corrosive environments according to claim 1, characterized in that: The cable data acquisition module includes a data acquisition unit and a wireless transmission unit; The data acquisition unit collects environmental data and cable corrosion data in real time through an integrated sensor group installed at various locations on the cable, and transmits the collected environmental data and cable corrosion data to the wireless transmission unit via the LoRa wireless network; The integrated sensor group includes a chemical sensor, a surface roughness measuring instrument, a temperature and humidity sensor, a conductivity sensor, a gas sensor, an ultrasonic sensor, and a magnetic thickness sensor. The wireless transmission unit is used to receive environmental data and cable corrosion data collected in real time by each sensor. It encapsulates the environmental data and cable corrosion data into a JSON format data package using a JSON encapsulation tool, and marks the environmental conditions, sensor ID, sensor measurement value, data type and collection timestamp on the data package. Then, it sends the data package to the wireless storage module in real time via the LoRa wireless network.

3. The data analysis-based bridge cable life prediction system for corrosive environments according to claim 2, characterized in that: The wireless storage module includes a data processing unit and a data storage unit; The data processing unit is used to receive data packages in real time, parse the data packages using a JSON parsing tool, extract sensor measurement values ​​of environmental data and cable corrosion data from the JSON format data packages, and preprocess the sensor measurement values. The preprocessing includes using statistical methods to identify and delete outliers, data cleaning, noise filtering, and normalization to obtain a cable safety dataset. The cable safety dataset includes a cable health characteristic data set, a cable surface characteristic data set, and an environmental characteristic data set. The cable health characteristic data set includes the cable's factory diameter zj, cable's remaining diameter sh, chloride ion concentration cl, sulfate concentration so, and nitrate concentration no; The cable surface feature data set includes cable surface roughness cc, coating integrity tc, and oxide layer thickness yh; The environmental characteristic data set includes ambient temperature wd, ambient humidity sd, salinity concentration yf, and environmental corrosive pollutant concentration wr; The data storage unit is used to store the preprocessed cable safety dataset into a local NoSQL database via an API port, and connects to the cable health analysis module and the cable corrosion analysis module via a LoRa wireless network to extract data from the cable safety dataset in real time.

4. The data analysis-based bridge cable life prediction system for corrosive environments according to claim 3, characterized in that: The cable health analysis module includes a cable health calculation unit and a cable health assessment unit; The LAS health computing unit accesses the LAS security dataset via the LoRa wireless network, extracts LAS health feature data groups, and then performs aggregate calculations to obtain the LAS health index Lfs. The Lfs health index is calculated using the following formula; 5. The data analysis-based bridge cable life prediction system for corrosive environments according to claim 4, characterized in that: The cable health assessment unit is used to perform a preset cable safety threshold A based on historical cable health data in the local NoSQL database, and to conduct a preliminary comparison and assessment with the obtained cable health index Lfs. Based on the assessment results, a secondary assessment mechanism is triggered. The specific assessment scheme is as follows. When the cable health index Lfs < the preset cable safety threshold A, it indicates that the current cable is in a healthy state. At this time, the cable is maintained at a normal cycle and the second evaluation mechanism is triggered. When the cable health index Lfs is greater than or equal to the preset cable safety threshold A, it indicates that the cable is in a dangerous state. At this time, the first warning message is generated and notified to relevant personnel through the alarm system so that emergency measures can be taken immediately for the cable.

6. The data analysis-based bridge cable life prediction system for corrosive environments according to claim 5, characterized in that: The cable corrosion analysis module is used to access the cable safety dataset via the LoRa wireless network and extract cable surface feature data set and environmental feature data set when the cable is initially assessed as being in a healthy state. The cable corrosion analysis module includes a cable surface corrosion calculation unit and an environmental impact calculation unit; The cable surface corrosion calculation unit is used to perform summary calculations based on the acquired cable surface feature data set to obtain the cable surface corrosion influence index Bmy. The corrosion impact index Bmy on the cable surface is calculated using the following formula; In the formula, k4 represents the material and environmental characteristic constants, which are obtained through experiments; k5 represents the influence coefficient of metal composition; and e represents an exponential function.

7. The data analysis-based bridge cable life prediction system for corrosive environments according to claim 6, characterized in that: The environmental impact calculation unit is used to perform summary calculations based on the acquired environmental characteristic data set to obtain the environmental impact index Hjx. The environmental impact index Hjx is calculated using the following formula; In the formula, ln represents the logarithmic function, k1 represents the cable material property constant, k2 represents the temperature effect constant, and k3 represents the pollutant threshold constant.

8. The data analysis-based bridge cable life prediction system for corrosive environments according to claim 1, characterized in that: The corrosion prediction and evaluation module includes a corrosion prediction calculation unit and a prediction and evaluation unit; The corrosion prediction calculation unit is used to summarize and calculate the comprehensive corrosion rate prediction index FYC based on the obtained cable health index Lfs, cable surface corrosion impact index Bmy and environmental impact index Hjx. The comprehensive corrosion rate prediction index FYC is calculated using the following formula; In the formula, w1, w2 and w3 represent the weighting coefficients of the cable health index Lfs, the cable surface corrosion impact index Bmy and the environmental impact index Hjx, respectively, and w1+w2+w3=1. The specific values ​​are set by the user. w4 represents the time decay coefficient and t represents the time variable.

9. The data analysis-based bridge cable life prediction system for corrosive environments according to claim 8, characterized in that: The prediction and evaluation unit is used to preset the cable corrosion rate threshold B, and perform a secondary comparison and evaluation with the obtained comprehensive corrosion rate prediction index FYC, and generate corresponding early warning information based on the evaluation results. The specific evaluation scheme is as follows. When the comprehensive corrosion rate prediction index FYC ≤ the preset cable corrosion rate threshold B, it indicates that the current cable corrosion rate is normal and normal monitoring should be maintained. When the comprehensive corrosion rate prediction index FYC is greater than the preset cable corrosion rate threshold B, it indicates that the current cable corrosion rate is abnormal. At this time, a second warning message is generated and the relevant personnel are notified through the alarm system to carry out relevant inspections and maintenance on the cable.

10. A method for predicting the lifespan of bridge cables in corrosive environments based on data analysis, comprising the data analysis-based method for predicting the lifespan of bridge cables in corrosive environments as described in any one of claims 1-9, characterized in that: Includes the following steps: Step 1: Collect environmental data and cable corrosion data in real time using an integrated sensor group installed on the cable. After encapsulating the environmental data and cable corrosion data, obtain the data encapsulation packet and transmit the data encapsulation packet to Step 2 via the LoRa wireless network. Step 2: Receive data encapsulation packets in real time, decapsulate the data encapsulation packets to extract environmental data and cable corrosion data, perform preprocessing to obtain cable safety datasets, and store the cable safety datasets in a local NoSQL database. Step 3: Extract the cable safety dataset for feature analysis to obtain cable health feature data set, summarize and calculate the extracted cable health feature data to obtain the cable health index Lfs, and then conduct a preliminary evaluation with the preset cable safety threshold A. Based on the evaluation results, trigger the secondary evaluation mechanism. Step 4: Based on the preliminary assessment that the cable is in a healthy state, access the cable safety dataset, extract the cable surface feature data group and environmental feature data group, and perform summary calculations to obtain the cable surface corrosion impact index Bmy and environmental impact index Hjx. Step 5: Based on the obtained cable health index Lfs, cable surface corrosion impact index Bmy, and environmental impact index Hjx, a comprehensive corrosion rate prediction index FYC is calculated. Then, a second evaluation is performed with the preset cable corrosion rate threshold B to deeply evaluate the cable corrosion rate, and relevant early warning information is generated based on the evaluation results.

Images