Track section water level prediction method and system based on BIM digital base
Through BIM digital base technology, a variety of data in the track interval are integrated to carry out water level prediction and correction optimization, solving the problems of water level prediction lag and inaccuracy in traditional methods, and achieving more accurate and reliable water level management.
Patent Information
- Application Number
- CN202311536205.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2023-11-16
- Publication Date
- 2024-11-15
- Estimated Expiration
- 2043-11-16
AI Technical Summary
The traditional orbital interval water level prediction method is based on limited data and experience, with lag and inaccuracy, resulting in unnecessary maintenance work and decision-making difficulties.
Using a BIM digital base method, soil permeability detection and water level impact assessment are carried out by obtaining geographical information, environmental information and meteorological data, water level prediction and correction optimization are carried out in combination with ground point water level observation data, and abnormal maintenance decisions are made.
Improve the accuracy and reliability of water level prediction, reduce potential damage, and provide the ability to respond quickly to hydrological risks and abnormal situations, ensuring safe and stable operation of orbital ranges.
Smart Images

Figure CN117521383B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of track water level prediction, and in particular to a track section water level prediction method and system based on a BIM digital base. Background Art
[0002] The safety and reliability of rail transit systems are crucial to cities and transportation operators. The water level in the track section is a key parameter that directly affects the stability and safety of trains. Different water level conditions can lead to track wear, railway accidents and other problems. Traditional water level prediction methods are usually based on limited data and experience, with a certain lag, which can lead to inaccurate predictions and unnecessary maintenance work, and are insufficient to support timely maintenance and decision-making. Summary of the invention
[0003] Based on this, it is necessary for the present invention to provide a track section water level prediction method based on a BIM digital base to solve at least one of the above technical problems.
[0004] To achieve the above purpose, a track section water level prediction method based on BIM digital base includes the following steps:
[0005] Step S1: Obtain geographic information data and environmental information data of the track section, and perform BIM fusion modeling on the geographic information data and environmental information data to obtain a BIM digital base model of the track section;
[0006] Step S2: Acquire meteorological information data of the track section; perform soil infiltration detection processing on the BIM digital base model of the track section according to the meteorological information data to obtain soil infiltration information data; perform water level impact assessment and analysis on the BIM digital base model of the track section according to the soil infiltration information data to obtain a soil infiltration water level impact factor;
[0007] Step S3: Observe and analyze the water level at the ground point on the BIM digital base model of the track section to obtain the horizontal displacement data of the water level at the ground point and the settlement data of the water level at the ground point; perform water level prediction processing on the BIM digital base model of the track section according to the horizontal displacement data of the water level at the ground point and the settlement data of the water level at the ground point to obtain the water level prediction data of the track section;
[0008] Step S4: Correct and optimize the water level prediction process of the track section water level prediction data according to the soil infiltration water level influencing factor to obtain the water level prediction correction optimization data; perform abnormal maintenance decision-making analysis on the water level prediction correction optimization data to obtain the water level abnormal maintenance decision plan; perform corresponding water level abnormal maintenance management operations according to the water level abnormal maintenance decision plan.
[0009] The present invention first collects geographic information data and environmental information data of the track section, which include geometric information of the track section, track drainage system, soil information, nearby building information, terrain environment information and other data, which helps to establish a comprehensive track section environmental data foundation for subsequent analysis and modeling. At the same time, these data are fused and modeled by using BIM (Building Information Modeling) technology to create a digital base model of the track section (track section BIM digital base model). This model integrates the geographic and environmental information of the track section, which can provide a basic platform guarantee for subsequent water level prediction and maintenance, and can also provide comprehensive basic data information, which is helpful for managing and planning water resources in the track section. Secondly, by obtaining the meteorological information data of the track section, meteorological data related to the track section can be accurately collected and provided. These data are crucial for predicting meteorological events and their potential impacts, such as the impact of rainfall on soil permeability. In addition, by using meteorological information data to perform penetration detection on the soil permeability in the track section BIM digital base model, it is helpful to determine the permeability of the soil in the track section BIM digital base model under different meteorological conditions, and at the same time provide information about the soil permeability under different meteorological conditions, so that the soil's ability to absorb water under different meteorological conditions can be understood. The water level impact assessment analysis of the track section BIM digital base model is also carried out by using the detected soil permeability information data, which can determine the influencing factors of soil permeability on the water level of the track section, thereby improving more accurate soil permeability information and helping to improve the accuracy of water level prediction. Then, by observing and analyzing the ground point water level of the track section BIM digital base model, it means that the corresponding sensor observations can be used to collect the ground point water level horizontal displacement data and ground point water level settlement data to reflect the changing trend of the ground water level in different time periods, providing rich information for the historical data of hydrological events, and also helping to more comprehensively understand the dynamic properties of the track section water level, including horizontal displacement and settlement, and providing key basic data for further analysis. In addition, by predicting the water level of the track section BIM digital base model with the ground point water level horizontal displacement data and ground point water level settlement data, the water level can be predicted and simulated by combining the existing ground water level change data with the BIM model, so as to timely understand the impact of possible future hydrological events on the track section, which helps to plan and implement effective water resources management measures, respond to potential hydrological risks in advance, and ensure the safe operation of the track section. Finally, the track section water level prediction data is corrected and optimized according to the soil infiltration water level influencing factors obtained previously to improve the accuracy of water level prediction. In addition, the corrected data is used for abnormal maintenance decision-making analysis to identify potential abnormal situations and provide corresponding abnormal maintenance decisions in a timely manner.Subsequently, according to the formulated water level abnormal maintenance decision plan, the corresponding water level abnormal maintenance management operations are carried out to ensure the safe and stable operation of the track section. This can improve the reliability of water level predictions, reduce potential damage, and provide the ability to quickly respond to hydrological risks and abnormal situations, thereby providing accurate water level predictions and necessary abnormal maintenance work.
[0010] Preferably, the present invention further provides a track section water level prediction system based on a BIM digital base, which is used to execute the track section water level prediction method based on a BIM digital base as described above. The track section water level prediction system based on a BIM digital base includes:
[0011] The digital base modeling module is used to obtain the geographic information data and environmental information data of the track section, and perform BIM fusion modeling on the geographic information data and environmental information data to obtain a BIM digital base model of the track section;
[0012] The soil infiltration water level impact detection module is used to obtain the meteorological information data of the track section, perform soil infiltration detection processing on the BIM digital base model of the track section according to the meteorological information data, and obtain soil infiltration information data; perform water level impact assessment and analysis on the BIM digital base model of the track section according to the soil infiltration information data, so as to obtain the soil infiltration water level impact factor;
[0013] The track section water level prediction module is used to observe and analyze the ground point water level of the track section BIM digital base model to obtain the ground point water level horizontal displacement data and ground point water level settlement data; the track section BIM digital base model is used to perform water level prediction processing according to the ground point water level horizontal displacement data and ground point water level settlement data, so as to obtain the track section water level prediction data;
[0014] The water level prediction abnormality maintenance module is used to correct and optimize the water level prediction process of the track section water level prediction data according to the soil infiltration water level influencing factor to obtain the water level prediction correction optimization data; perform abnormal maintenance decision-making analysis on the water level prediction correction optimization data to obtain the water level abnormality maintenance decision plan; and perform corresponding water level abnormality maintenance management operations according to the water level abnormality maintenance decision plan.
[0015] In summary, the present invention provides a track section water level prediction system based on a BIM digital base, and the track section water level prediction system based on the BIM digital base is composed of a digital base modeling module, a soil infiltration water level impact detection module, a track section water level prediction module, and a water level prediction abnormality maintenance module. It can realize any one of the track section water level prediction methods based on the BIM digital base described in the present invention, and is used to combine the operations between the computer programs running on each module to realize a track section water level prediction method based on the BIM digital base. The internal structures of the system cooperate with each other. By introducing the BIM digital base technology, the management of the track section is made more intelligent and visualized, and the efficiency and accuracy of water level prediction and maintenance are improved. The prediction accuracy of the track section water level is also achieved by using the permeability of the soil and the movement of the water level at the ground point. At the same time, by using abnormal alarms, it is ensured that action can be taken immediately when a water level abnormality occurs, thereby improving the safety of the track section. This can greatly reduce duplication of work and manpower investment, and can quickly and effectively provide a more accurate and efficient track section water level prediction process, thereby simplifying the operation process of the track section water level prediction system based on the BIM digital base. BRIEF DESCRIPTION OF THE DRAWINGS
[0016] Other features, objects and advantages of the present invention will become more apparent from the detailed description of non-limiting embodiments thereof made with reference to the following drawings:
[0017] Figure 1 It is a schematic diagram of the steps of the track section water level prediction method based on the BIM digital base of the present invention;
[0018] Figure 2 for Figure 1 Detailed step flow diagram of step S1;
[0019] Figure 3 for Figure 2 Detailed step flow chart of step S12 in FIG. DETAILED DESCRIPTION
[0020] The following is a clear and complete description of the technical method of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by technicians in this field without creative work are within the scope of protection of the present invention.
[0021] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.
[0022] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.
[0023] To achieve this, please refer to Figures 1 to 3 The present invention provides a track section water level prediction method based on BIM digital base, the method comprising the following steps:
[0024] Step S1: Obtain geographic information data and environmental information data of the track section, and perform BIM fusion modeling on the geographic information data and environmental information data to obtain a BIM digital base model of the track section;
[0025] Step S2: Acquire meteorological information data of the track section; perform soil infiltration detection processing on the BIM digital base model of the track section according to the meteorological information data to obtain soil infiltration information data; perform water level impact assessment and analysis on the BIM digital base model of the track section according to the soil infiltration information data to obtain a soil infiltration water level impact factor;
[0026] Step S3: Observe and analyze the water level at the ground point on the BIM digital base model of the track section to obtain the horizontal displacement data of the water level at the ground point and the settlement data of the water level at the ground point; perform water level prediction processing on the BIM digital base model of the track section according to the horizontal displacement data of the water level at the ground point and the settlement data of the water level at the ground point to obtain the water level prediction data of the track section;
[0027] Step S4: Correct and optimize the water level prediction process of the track section water level prediction data according to the soil infiltration water level influencing factor to obtain the water level prediction correction optimization data; perform abnormal maintenance decision-making analysis on the water level prediction correction optimization data to obtain the water level abnormal maintenance decision plan; perform corresponding water level abnormal maintenance management operations according to the water level abnormal maintenance decision plan.
[0028] In the embodiment of the present invention, please refer to Figure 1 As shown, it is a schematic diagram of the steps of the track section water level prediction method based on the BIM digital base of the present invention. In this example, the steps of the track section water level prediction method based on the BIM digital base include:
[0029] Step S1: Obtain geographic information data and environmental information data of the track section, and perform BIM fusion modeling on the geographic information data and environmental information data to obtain a BIM digital base model of the track section;
[0030] The embodiment of the present invention uses sensors and a geographic information system to collect and obtain information data such as geometric information of the track section, track drainage system information, map data, geographic coordinates, terrain information, etc., to provide geographic reference information of the track section, and collects and obtains information data such as soil information and nearby building information to understand the environmental conditions around the track section, thereby obtaining geographic information data and environmental information data. Then, by integrating the geographic information data and environmental information data into BIM (Building Information Modeling) software, a digital base model that represents the building structure, terrain, environmental characteristics, etc. of the track section in three dimensions is constructed, and finally a BIM digital base model of the track section is obtained.
[0031] Step S2: Acquire meteorological information data of the track section; perform soil infiltration detection processing on the BIM digital base model of the track section according to the meteorological information data to obtain soil infiltration information data; perform water level impact assessment and analysis on the BIM digital base model of the track section according to the soil infiltration information data to obtain a soil infiltration water level impact factor;
[0032] The embodiment of the present invention uses meteorological monitoring equipment to collect meteorological information within the track section, including rainfall, rainfall time, temperature, humidity, wind speed and other related data, thereby obtaining meteorological information data. Then, the soil permeability in the BIM digital base model of the track section is detected and analyzed by using the meteorological information data to analyze and determine the permeability of the soil in the BIM digital base model of the track section under rainfall conditions of different intensities, thereby obtaining soil permeability information data. Finally, the water level changes in the BIM digital base model of the track section are evaluated and analyzed in combination with the soil permeability information data to analyze the influence factors of different situations of soil permeability on water level changes under different rainfall conditions, and finally obtain the soil permeability water level influence factor.
[0033] Step S3: Observe and analyze the water level at the ground point on the BIM digital base model of the track section to obtain the horizontal displacement data of the water level at the ground point and the settlement data of the water level at the ground point; perform water level prediction processing on the BIM digital base model of the track section according to the horizontal displacement data of the water level at the ground point and the settlement data of the water level at the ground point to obtain the water level prediction data of the track section;
[0034] The embodiment of the present invention uses ground water level sensors (including water level horizontal movement sensors and water level settlement sensors) to electrically connect with the track section BIM digital base model to build a sensor network capable of observing the ground water level in real time. Then, the ground water level sensors in the sensor network are dynamically started at different observation times to collect data from the track section BIM digital base model to observe the changing trend of the ground water level in the track section BIM digital base model in different time periods, thereby obtaining the ground point water level horizontal displacement data and ground point water level settlement data. Finally, the water level in the track section BIM digital base model is predicted by using the changes in the ground point water level horizontal displacement data and the ground point water level settlement data to predict the future water level changes in the track section, and finally obtain the track section water level prediction data.
[0035] Step S4: Correct and optimize the water level prediction process of the track section water level prediction data according to the soil infiltration water level influencing factor to obtain the water level prediction correction optimization data; perform abnormal maintenance decision-making analysis on the water level prediction correction optimization data to obtain the water level abnormal maintenance decision plan; perform corresponding water level abnormal maintenance management operations according to the water level abnormal maintenance decision plan.
[0036] The embodiment of the present invention includes the influencing factors of the soil infiltration water level influencing factors as a key factor in the water level prediction process of the track section water level prediction data for evaluation and analysis, so that the water level prediction process can fully consider the influence of soil permeability on the water level, and then, by using the influence situation obtained by the analysis, the track section water level prediction data is corrected and optimized to reduce or eliminate the influence of the soil infiltration water level on the water level prediction, so as to more accurately reflect the actual water level situation of the track section, thereby obtaining the water level prediction correction optimization data. Next, the anomaly detection algorithm is used to perform anomaly detection and analysis on the corrected water level prediction correction optimization data, including the nature, location, severity, etc. of the water level anomaly, and based on the analysis of the water level anomaly, a corresponding water level anomaly maintenance decision plan is formulated, including changing the water level management strategy, starting flood control measures and other decisions to repair the water level anomaly, thereby obtaining a water level anomaly maintenance decision plan. Finally, the water level anomaly is handled by using the formulated water level anomaly maintenance decision plan to execute the corresponding water level anomaly maintenance management operation, including management decisions such as adjusting water level control facilities, strengthening monitoring, and unblocking drainage systems to ensure the stability and safety of the water level in the track section.
[0037] The present invention first collects geographic information data and environmental information data of the track section, which include geometric information of the track section, track drainage system, soil information, nearby building information, terrain environment information and other data, which helps to establish a comprehensive track section environmental data foundation for subsequent analysis and modeling. At the same time, these data are fused and modeled by using BIM (Building Information Modeling) technology to create a digital base model of the track section (track section BIM digital base model). This model integrates the geographic and environmental information of the track section, which can provide a basic platform guarantee for subsequent water level prediction and maintenance, and can also provide comprehensive basic data information, which is helpful for managing and planning water resources in the track section. Secondly, by obtaining the meteorological information data of the track section, meteorological data related to the track section can be accurately collected and provided. These data are crucial for predicting meteorological events and their potential impacts, such as the impact of rainfall on soil permeability. In addition, by using meteorological information data to perform penetration detection on the soil permeability in the track section BIM digital base model, it is helpful to determine the permeability of the soil in the track section BIM digital base model under different meteorological conditions, and at the same time provide information about the soil permeability under different meteorological conditions, so that the soil's ability to absorb water under different meteorological conditions can be understood. The water level impact assessment analysis of the track section BIM digital base model is also carried out by using the detected soil permeability information data, which can determine the influencing factors of soil permeability on the water level of the track section, thereby improving more accurate soil permeability information and helping to improve the accuracy of water level prediction. Then, by observing and analyzing the ground point water level of the track section BIM digital base model, it means that the corresponding sensor observations can be used to collect the ground point water level horizontal displacement data and ground point water level settlement data to reflect the changing trend of the ground water level in different time periods, providing rich information for the historical data of hydrological events, and also helping to more comprehensively understand the dynamic properties of the track section water level, including horizontal displacement and settlement, and providing key basic data for further analysis. In addition, by predicting the water level of the track section BIM digital base model with the ground point water level horizontal displacement data and ground point water level settlement data, the water level can be predicted and simulated by combining the existing ground water level change data with the BIM model, so as to timely understand the impact of possible future hydrological events on the track section, which helps to plan and implement effective water resources management measures, respond to potential hydrological risks in advance, and ensure the safe operation of the track section. Finally, the track section water level prediction data is corrected and optimized according to the soil infiltration water level influencing factors obtained previously to improve the accuracy of water level prediction. In addition, the corrected data is used for abnormal maintenance decision-making analysis to identify potential abnormal situations and provide corresponding abnormal maintenance decisions in a timely manner.Subsequently, according to the formulated water level abnormal maintenance decision plan, the corresponding water level abnormal maintenance management operations are carried out to ensure the safe and stable operation of the track section. This can improve the reliability of water level predictions, reduce potential damage, and provide the ability to quickly respond to hydrological risks and abnormal situations, thereby providing accurate water level predictions and necessary abnormal maintenance work.
[0038] Preferably, step S1 comprises the following steps:
[0039] Step S11: Acquire geographic information data and environmental information data of the track section;
[0040] Step S12: Performing data quality screening on the geographic information data and the environmental information data to obtain high-quality geographic information data and high-quality environmental information data;
[0041] Step S13: Perform three-dimensional map visualization processing on the high-quality geographic information data to obtain a three-dimensional geographic map of the track section;
[0042] Step S14: performing data association exploration and analysis on the three-dimensional geographic map of the track section and the high-quality data of environmental information to obtain the geographic environment association relationship of the track section;
[0043] Step S15: According to the geographical environment correlation of the track section, the BIM software is used to perform BIM fusion modeling processing on the three-dimensional geographical map of the track section and the high-quality data of environmental information to obtain a BIM digital base model of the track section.
[0044] As an embodiment of the present invention, refer to Figure 2 As shown, Figure 1 Detailed step flow diagram of step S1 in FIG. 1 , in this embodiment, step S1 includes the following steps:
[0045] Step S11: Acquire geographic information data and environmental information data of the track section;
[0046] The embodiments of the present invention use sensors and a geographic information system to collect and obtain information data such as the geometry of a track section, track drainage system information, map data, geographic coordinates, terrain information, etc., to provide geographic reference information of the track section, and collect and obtain information data such as soil information and nearby building information to understand the environmental conditions of the geographical surroundings of the track section, and ultimately obtain geographic information data and environmental information data.
[0047] Step S12: Performing data quality screening on the geographic information data and the environmental information data to obtain high-quality geographic information data and high-quality environmental information data;
[0048] The embodiments of the present invention remove low-quality data from geographic information data and environmental information data by using processing steps such as data cleaning, noise reduction, and quality screening to ensure the integrity, accuracy, and consistency of the data, and improve the quality and credibility of the geographic information data and environmental information data, ultimately obtaining high-quality geographic information data and high-quality environmental information data.
[0049] Step S13: Perform three-dimensional map visualization processing on the high-quality geographic information data to obtain a three-dimensional geographic map of the track section;
[0050] The embodiment of the present invention visualizes high-quality geographic information data by using geographic information system software, converts the high-quality geographic information data into a three-dimensional map showing the terrain, roads, tracks and other elements of the track section, and finally obtains a three-dimensional geographic map of the track section.
[0051] Step S14: performing data association exploration and analysis on the three-dimensional geographic map of the track section and the high-quality data of environmental information to obtain the geographic environment association relationship of the track section;
[0052] The embodiment of the present invention uses a data mining and analysis method to explore and analyze the three-dimensional geographic map of the track section and the high-quality data of environmental information, so as to explore the correlation between the geographic information of the track section and the environmental information, and finally obtain the geographic environment correlation of the track section.
[0053] Step S15: According to the geographical environment correlation of the track section, the BIM software is used to perform BIM fusion modeling processing on the three-dimensional geographical map of the track section and the high-quality data of environmental information to obtain a BIM digital base model of the track section.
[0054] The embodiment of the present invention integrates the geographic information in the three-dimensional geographic map of the track section and the environmental information and surrounding building information in the high-quality environmental information data into the BIM (Building Information Modeling) software by using the analyzed geographical environment association relationship of the track section, so as to construct a digital base model that represents the building structure, terrain, environmental characteristics, etc. of the track section in three dimensions, and finally obtains the BIM digital base model of the track section.
[0055] The present invention first obtains the geographic information data and environmental information data of the track section, which include the geometric information of the track section, the track drainage system information, the soil information, the nearby building information, the terrain environment information and other data, which helps to establish a comprehensive track section environment data foundation for subsequent analysis and modeling. Secondly, by performing data quality screening on the geographic information data and the environmental information data, the accuracy and reliability of the geographic information data and the environmental information data can be ensured through operations including data cleaning, noise removal, and solving data inconsistency, which can improve the credibility of the geographic information data and the environmental information data, thereby facilitating the accuracy of subsequent process analysis and modeling. Then, by performing three-dimensional map visualization processing on the high-quality geographic information data, the high-quality geographic information data can be used to create a three-dimensional geographic map of the track section. This visualization process can help to intuitively present the geographic features of the track section, such as roads, buildings, environment, etc., and can provide visual basic data for subsequent analysis, making the geographic data easier to understand and analyze. Next, by conducting data association exploration and analysis on the three-dimensional geographic map of the track section and the high-quality data of environmental information, the association between the three-dimensional geographic map of the track section and the environmental information can be identified, and the association between geographic data and environmental data can be further identified, which helps to understand the impact of environmental factors on geographical features, provides basic data for more in-depth research, and can also reveal the interaction between geographic data and environmental data, which helps to better understand the characteristics of the track section. Finally, by using the geographic environment association relationship of the track section, the three-dimensional geographic map of the track section and the high-quality data of environmental information are integrated into the BIM (Building Information Modeling) software to create a BIM digital base model of the track section. This model is a three-dimensional virtual representation that can include the building structure, terrain, environmental characteristics, etc. of the track section, which helps to plan, design and maintain the track section. At the same time, this model can be used to predict the water level of the track section, thereby improving the efficiency and sustainability of water level prediction in the track section.
[0056] Preferably, step S12 comprises the following steps:
[0057] Step S121: performing data cleaning processing on the geographic information data and the environmental information data to obtain geographic information cleansing data and environmental information cleansing data;
[0058] Step S122: performing noise reduction processing on the geographic information cleansing data and the environmental information cleansing data to obtain geographic information noise reduction data and environmental information noise reduction data;
[0059] Step S123: using a data quality metric calculation formula to perform quality calculation on the geographic information denoised data and the environmental information denoised data to obtain a geographic data quality metric value and an environmental data quality metric value;
[0060] Step S124: judging and screening the geographic information denoised data corresponding to the geographic data quality metric value and the environmental information denoised data corresponding to the environmental data quality metric value according to the preset data quality metric standard value to obtain high-quality geographic information data and high-quality environmental information data.
[0061] As an embodiment of the present invention, refer to Figure 3 As shown, Figure 2 Detailed step flow diagram of step S12 in the embodiment, step S12 includes the following steps:
[0062] Step S121: performing data cleaning processing on the geographic information data and the environmental information data to obtain geographic information cleansing data and environmental information cleansing data;
[0063] The embodiment of the present invention performs data cleaning operations such as removing duplicates, repairing missing values, and processing abnormal data on geographic information data and environmental information data respectively to ensure the integrity and accuracy of geographic information cleansing data and environmental information cleansing data, and finally obtains geographic information cleansing data and environmental information cleansing data.
[0064] Step S122: performing noise reduction processing on the geographic information cleansing data and the environmental information cleansing data to obtain geographic information noise reduction data and environmental information noise reduction data;
[0065] The embodiment of the present invention performs noise reduction processing on the cleaned geographic information cleaned data and the environmental information cleaned data by using noise reduction technology (such as filters, smoothing algorithms, interpolation, etc.) to reduce random or systematic noise in the geographic information cleaned data and the environmental information cleaned data, and finally obtains the geographic information noise reduction data and the environmental information noise reduction data.
[0066] Step S123: using a data quality metric calculation formula to perform quality calculation on the geographic information denoised data and the environmental information denoised data to obtain a geographic data quality metric value and an environmental data quality metric value;
[0067] The embodiment of the present invention forms a suitable data quality metric calculation formula by combining the integral calculation spatial domain parameters, quality index parameters, quality index change gradient, quality index standard deviation, quality index gradient influence coefficient, quality reference index parameter, quality reference index standard deviation, quality index similarity measurement function, quality index similarity adjustment parameter, quality index mean, quality reference index mean and related parameters of geographic information denoised data and environmental information denoised data to perform quality calculation on geographic information denoised data and environmental information denoised data, so as to quantitatively reflect the quality of geographic information denoised data and environmental information denoised data, and finally obtain geographic data quality metric value and environmental data quality metric value. In addition, the data quality metric calculation formula can also use any quality metric detection algorithm in the field to replace the quality calculation process, and is not limited to the data quality metric calculation formula.
[0068] Step S124: judging and screening the geographic information denoised data corresponding to the geographic data quality metric value and the environmental information denoised data corresponding to the environmental data quality metric value according to the preset data quality metric standard value to obtain high-quality geographic information data and high-quality environmental information data.
[0069] The embodiment of the present invention compares and judges the calculated geographic data quality metric value and the environmental data quality metric value according to the preset data quality metric standard value. If the geographic data quality metric value and the environmental data quality metric value are greater than or equal to the preset data quality metric standard value, it means that the data quality of the geographic information denoised data corresponding to the geographic data quality metric value and the environmental information denoised data corresponding to the environmental data quality metric value is high, then the geographic information denoised data corresponding to the geographic data quality metric value and the environmental information denoised data corresponding to the environmental data quality metric value are marked as geographic information high-quality data and environmental information high-quality data respectively; if the geographic data quality metric value and the environmental data quality metric value are less than the preset data quality metric standard value, it means that the data quality of the geographic information denoised data corresponding to the geographic data quality metric value and the environmental information denoised data corresponding to the environmental data quality metric value is low, then the geographic information denoised data corresponding to the geographic data quality metric value and the environmental information denoised data corresponding to the environmental data quality metric value are eliminated.
[0070] The present invention firstly performs data cleaning processing on geographic information data and environmental information data, including operations such as removing duplicates, repairing missing values, and processing abnormal data, which helps to ensure the integrity and accuracy of the data and can prepare the data for subsequent processing steps. In addition, the geographic information cleaning data and environmental information cleaning data obtained after cleaning can also improve the availability of data, reduce data errors and inconsistencies, and lay a foundation for improving data quality. Secondly, by performing noise reduction processing on the cleaned geographic information cleaning data and environmental information cleaning data, that is, removing interference and random noise in the data, this can include operations such as smoothing data, filtering, abnormal value detection and repair. By reducing random fluctuations in the data, the stability and reliability of the data can be improved, which helps to more accurately reflect geographic and environmental information, and at the same time, the data quality can be improved to make it more credible. Then, by using a suitable data quality metric calculation formula to perform quality calculation on the geographic information noise reduction data and the environmental information noise reduction data, the calculated value can reflect the quality of the data, including accuracy, integrity, consistency, reliability, etc. The effect of this step is to quantify the data quality, so that the credibility and applicability of the data can be better understood. Finally, the calculated geographic data quality metrics and environmental data quality metrics are judged and filtered by using the preset data quality metric values, which means that the data can be compared with the pre-set quality standards to filter out high-quality data. The effect of this step is to obtain a high-quality subset of geographic information and environmental data that is more suitable for subsequent analysis, modeling, and decision-making, which helps to improve the credibility of the data and thus ensure the accuracy of decisions and operations based on these data.
[0071] Preferably, the data quality metric calculation formula in step S123 is specifically:
[0072] ;
[0073] ;
[0074] ;
[0075] ;
[0076] In the formula, is the geographic data quality metric, The spatial domain parameters for the integral calculation of the geospatial denoised data are: is the quality index parameter of geographic information denoising data, The quality index change gradient of geographic information denoising data, is the standard deviation of the quality index of geographic information denoising data, is the quality index gradient influence coefficient of geographic information denoising data, It is the quality reference index parameter of geographic information noise reduction data. is the standard deviation of the quality reference index of geographic information noise reduction data, is the quality index similarity measurement function of geographic information denoising data, Adjust the parameters for the similarity of the quality indicators of geographic information denoising data, is the number of quality indicator parameters in geographic information denoising data, For the first Quality indicator parameters, is the mean value of the quality index of geographic information denoising data, For geographic information noise reduction data The quality reference index parameters corresponding to the quality index parameters are: is the mean value of the quality reference index of geographic information noise reduction data, is the correction value of the geographic data quality metric, is the environmental data quality metric, The spatial domain parameters for the integral calculation of the environmental information denoising data are: is the quality index parameter of environmental information denoising data, The quality index change gradient of the environmental information denoising data, is the standard deviation of the quality indicator of environmental information denoising data, is the quality index gradient influence coefficient of environmental information noise reduction data, It is the quality reference index parameter of environmental information noise reduction data. is the standard deviation of the quality reference indicator of environmental information noise reduction data, is the quality index similarity measurement function of environmental information denoising data, Adjust the parameters for the similarity of the quality indicators of the environmental information denoising data. is the number of quality indicator parameters in the environmental information denoising data, The first Quality indicator parameters, is the mean value of the quality index of the environmental information denoising data, The first The quality reference index parameters corresponding to the quality index parameters are: is the mean value of the quality reference index of environmental information noise reduction data, It is the correction value of the environmental data quality metric.
[0077] The present invention constructs a data quality metric calculation formula for performing quality calculation on geographic information denoised data and environmental information denoised data. The data quality metric calculation formula measures the degree of change of the quality indicator by using the quality indicator gradient influence coefficient to determine the influence of the gradient. The quality indicator standard deviation is used to measure the discreteness of the quality indicator. The smaller the standard deviation, the higher the data quality. The quality reference indicator standard deviation is used to measure the discreteness of the quality reference indicator. The quality indicator similarity measurement function is used to measure the similarity between quality indicators, while taking into account the correlation between data quality indicators. The quality indicator similarity adjustment parameter is also used to adjust the similarity measurement function to meet specific needs. In addition, correction values are introduced to correct errors or other influencing factors that occur during the measurement calculation process. In summary, the calculation formula can help improve the quality of geographic information and environmental information data by comprehensively considering the above parameters for comprehensive evaluation and calculation of geographic information denoised data and environmental information denoised data, so as to ensure the reliability and accuracy of subsequent analysis and application. The formula fully considers the geographic data quality metric value , spatial domain parameters of integral calculation of geographic information denoising data , quality index parameters of geographic information denoising data , the quality index change gradient of geographic information denoising data , standard deviation of quality indicators of geographic information noise reduction data , the quality index gradient influence coefficient of geographic information denoising data , quality reference index parameters of geographic information noise reduction data , standard deviation of quality reference index of geographic information noise reduction data , similarity measurement function of quality index of geographic information denoising data , similarity adjustment parameters of quality indicators of geographic information denoising data , the number of quality indicator parameters in geographic information denoising data , the first Quality index parameters , the mean value of the quality index of geographic information denoising data , the first The quality reference index parameters corresponding to the quality index parameters , the mean value of the quality reference index of geographic information noise reduction data , corrections to geographic data quality metrics , where the quality index parameters of the denoised data by geographic information are , quality reference index parameters of geographic information noise reduction data , the number of quality indicator parameters in geographic information denoising data , the first Quality index parameters , the mean value of the quality index of geographic information denoising data , the first The quality reference index parameters corresponding to the quality index parameters And the mean value of the quality reference index of geographic information noise reduction data A quality index similarity measurement function of geographic information denoising data is constructed relation According to the interrelationships among the above parameters, a geographic data quality metric is constructed. Functional relationship:
[0078] ;
[0079] Additionally, environmental data quality metrics are considered , spatial domain parameters of the integral calculation of environmental information denoising data , quality index parameters of environmental information denoising data , the quality index change gradient of environmental information denoising data , standard deviation of quality indicators of environmental information denoising data , the quality index gradient influence coefficient of environmental information noise reduction data , quality reference index parameters of environmental information noise reduction data , the standard deviation of the quality reference index of environmental information noise reduction data , quality index similarity measurement function of environmental information denoising data , quality index similarity adjustment parameters of environmental information denoising data , the number of quality indicator parameters in the environmental information denoising data , the first Quality index parameters , the mean value of quality index of environmental information denoising data , the environmental information denoising data The quality reference index parameters corresponding to the quality index parameters , the mean value of the quality reference index of environmental information noise reduction data , correction value of environmental data quality metric , where the quality index parameter of the noise-reduced data is , quality reference index parameters of environmental information noise reduction data , the number of quality indicator parameters in the environmental information denoising data , the first Quality index parameters , the mean value of quality index of environmental information denoising data , the environmental information denoising data The quality reference index parameters corresponding to the quality index parameters And the mean value of the quality reference index of environmental information noise reduction data It constitutes a quality index similarity measurement function of environmental information denoising data relation , a functional relationship is formed based on the mutual correlation between the above parameters:
[0080] ;
[0081] This formula can realize the quality calculation process of geographic information denoising data and environmental information denoising data. At the same time, through the correction value of geographic data quality metric value and corrections to environmental data quality metrics The introduction of can be adjusted according to the errors that occur during the calculation process, thereby improving the accuracy and stability of the data quality measurement calculation formula.
[0082] Preferably, step S2 comprises the following steps:
[0083] Step S21: Acquire meteorological information data of the track section;
[0084] The embodiment of the present invention collects meteorological information within the track section by using meteorological monitoring equipment, including rainfall, rainfall time, temperature, humidity, wind speed and other related data, and finally obtains meteorological information data.
[0085] Step S22: using a meteorological rainfall intensity calculation formula to perform intensity calculation on the meteorological information data to obtain a meteorological rainfall intensity value;
[0086] The embodiment of the present invention combines rainfall volume variable parameters, integral time variable parameters, rainfall intensity adjustment coefficients, rainfall probability density distribution parameters, rainfall integral change parameters, rainfall time mean, rainfall time standard deviation, rainfall probability density distribution gradient value, rainfall water density, rainfall water specific heat capacity, rainfall flow parameters and related parameters to form a suitable meteorological rainfall intensity calculation formula to perform intensity calculation on meteorological information data, so as to quantify the importance and impact of rainfall events in meteorological information data, and finally obtain a meteorological rainfall intensity value. In addition, the meteorological rainfall intensity calculation formula can also use any rainfall intensity detection algorithm in the art to replace the intensity calculation process, and is not limited to the meteorological rainfall intensity calculation formula.
[0087] Step S23: comparing and judging the meteorological rainfall intensity value according to a preset meteorological rainfall intensity threshold value to obtain a meteorological rainfall intensity judgment result; performing intensity level division processing on the meteorological information data corresponding to the meteorological rainfall intensity value according to the meteorological rainfall intensity judgment result to obtain meteorological rainfall intensity level data;
[0088] The embodiment of the present invention compares and judges the calculated meteorological rainfall intensity value according to a preset meteorological rainfall intensity threshold value, thereby obtaining a meteorological rainfall intensity judgment result to determine the level of rainfall intensity, such as light rain intensity, moderate rain intensity and heavy rain intensity (including rainstorm intensity). If the meteorological rainfall intensity judgment result is that the calculated meteorological rainfall intensity value is greater than the preset meteorological rainfall intensity threshold value, the intensity level of the meteorological information data corresponding to the meteorological rainfall intensity value is divided into a heavy rain intensity level. If the meteorological rainfall intensity judgment result is that the calculated meteorological rainfall intensity value is equal to the preset meteorological rainfall intensity threshold value, the intensity level of the meteorological information data corresponding to the meteorological rainfall intensity value is divided into a moderate rain intensity level. If the meteorological rainfall intensity judgment result is that the calculated meteorological rainfall intensity value is less than the preset meteorological rainfall intensity threshold value, the intensity level of the meteorological information data corresponding to the meteorological rainfall intensity value is divided into a light rain intensity level. The corresponding meteorological information data is classified according to the divided rainfall intensity levels, and finally the meteorological rainfall intensity level data is obtained.
[0089] Step S24: performing a permeability detection process on the soil permeability in the BIM digital base model of the track section according to the meteorological rainfall intensity level data to obtain soil permeability information data;
[0090] The embodiment of the present invention detects and analyzes the soil permeability in the BIM digital base model of the track section by using the corresponding meteorological rainfall intensity level data, so as to analyze and determine the permeability of the soil in the BIM digital base model of the track section under rainfall conditions of different intensities, and finally obtain soil permeability information data.
[0091] Step S25: Conduct water level impact assessment and analysis on the track section BIM digital base model based on the soil infiltration information data to obtain the soil infiltration water level impact factor.
[0092] The embodiment of the present invention evaluates and analyzes the water level changes in the BIM digital base model of the track section by combining soil permeability information data, so as to analyze the influencing factors of the water level changes under different rainfall conditions considering different conditions of soil permeability, and finally obtain the soil permeability water level influencing factors.
[0093] The present invention firstly obtains meteorological information data of the track section, including meteorological parameters such as rainfall, temperature, and humidity, and can accurately collect and provide meteorological data related to the track section. These data are crucial for predicting meteorological events and their potential impacts, such as the impact of rainfall on soil permeability. Secondly, the collected meteorological information data is intensity-calculated by using a suitable meteorological rainfall intensity calculation formula to calculate the rainfall intensity value of the meteorological information data. This value can represent the intensity of rainfall and help quantify the importance and impact of rainfall events. The effect of this step is to provide a quantitative measure of rainfall events, making it a basic data guarantee for subsequent decision-making. Then, by using a pre-set meteorological rainfall intensity threshold and comparing it with the calculated meteorological rainfall intensity value, a meteorological rainfall intensity judgment result is obtained. At the same time, according to the judgment result, the meteorological information data is divided into different rainfall intensity levels, so that the severity of the rainfall event can be better understood, thereby helping to more deeply understand the impact of meteorology on soil permeability in the track section in a hierarchical manner. Next, the soil permeability in the track section BIM digital base model is tested using different meteorological rainfall intensity level data, which helps determine the soil permeability in the track section BIM digital base model under different rainfall intensity conditions, and provides information about soil permeability under different rainfall intensity conditions, so that the soil's ability to absorb water under different meteorological conditions can be understood. Finally, the water level impact assessment analysis of the track section BIM digital base model is performed using the detected soil permeability information data, which can determine the influencing factors of soil permeability on the water level of the track section, thereby helping decision makers better understand the possibility of water level changes under different meteorological conditions, and also helping to take necessary measures to respond to potential water level rises or flood events.
[0094] Preferably, the meteorological rainfall intensity calculation formula in step S22 is specifically:
[0095] ;
[0096] In the formula, is the meteorological rainfall intensity value, For meteorological information data in volume and time The double integral space domain parameter on , is the rainfall volume variable parameter of the rainfall event in the meteorological information data, is the integral time variable parameter for intensity calculation, is the rainfall intensity adjustment coefficient of the rainfall event in the meteorological information data, is the rainfall probability density distribution parameter of the rainfall event in the meteorological information data, is the rainfall integral change parameter of the rainfall event in the meteorological information data, is the mean rainfall time of rainfall events in the meteorological information data, is the standard deviation of rainfall time of rainfall events in the meteorological information data, is an exponential function, is the gradient operator, is the gradient value of rainfall probability density distribution, is the rainfall density of the rainfall event in the meteorological information data, is the specific heat capacity of rainfall water in the rainfall event in the meteorological information data, is the rainfall event in the meteorological information data at time The rainfall flow parameters at It is the correction value of meteorological rainfall intensity.
[0097] The present invention constructs a meteorological rainfall intensity calculation formula for performing intensity calculation on meteorological information data, and the meteorological rainfall intensity calculation formula integrates rainfall information at different locations and times by considering the integration of spatial and temporal dimensions. The rainfall intensity of a rainfall event is adjusted by using a rainfall intensity adjustment coefficient, and the specific attributes of rainfall in the meteorological information data are also reflected. The probability distribution of the occurrence of a rainfall event is described by the rainfall probability density distribution, which plays a role of weight in the calculation. The rainfall integral change parameter represents the rainfall integral change of the rainfall event, that is, the total amount of rainfall, and this parameter reflects the overall impact of the rainfall event. The time distribution characteristics of the occurrence of the rainfall event are described by the rainfall time mean and the rainfall time standard deviation. The gradient of the rainfall probability density distribution is also considered by using the rainfall probability density distribution gradient value to describe the change of the probability density, which helps to capture the spatial distribution of rainfall. In addition, the rainfall flow parameter is used to represent the rainfall flow parameter of the rainfall event under the time condition, reflecting the dynamic change of the rainfall event. In addition, a correction value is introduced to correct errors or other influencing factors in the calculation. In summary, the calculation formula comprehensively considers multiple factors such as time, space, rainfall probability density distribution, rainfall amount, etc. to perform complex calculations on meteorological information data, which can more accurately describe the intensity of rainfall events and their temporal and spatial distribution characteristics, which provides detailed and accurate input data for subsequent water level impact assessment. , meteorological information data in volume and time The double integral space domain parameter on , the rainfall volume variable parameter of the rainfall event in the meteorological information data , integral time variable parameter for intensity calculation , the rainfall intensity adjustment coefficient of rainfall events in meteorological information data , the rainfall probability density distribution parameters of rainfall events in meteorological information data , the rainfall integral change parameter of the rainfall event in the meteorological information data , the mean rainfall time of rainfall events in meteorological information data , the standard deviation of rainfall time of rainfall events in meteorological information data , exponential function , the gradient operator , the gradient value of rainfall probability density distribution , rainfall water density of rainfall events in meteorological information data , the specific heat capacity of rainfall water in rainfall events in meteorological information data , the rainfall events in the meteorological information data are at time Rainfall flow parameters at , correction value of meteorological rainfall intensity value , according to the meteorological rainfall intensity value The correlation between the above parameters forms a functional relationship:
[0098] ;
[0099] This formula can realize the intensity calculation process of meteorological information data, and at the same time, the correction value of meteorological rainfall intensity value The introduction of can be adjusted according to the errors occurring in the calculation process, thereby improving the accuracy and applicability of the meteorological rainfall intensity calculation formula.
[0100] Preferably, step S25 comprises the following steps:
[0101] Step S251: monitoring and analyzing the water level change of the track section BIM digital base model to obtain the track section water level change data;
[0102] The embodiment of the present invention uses water level monitoring equipment to monitor the water level changes of the BIM digital base model of the track section in real time, and transmits the monitored data to the data processing system in real time for analysis to understand the changing trend, amplitude and efficiency of the water level, and finally obtain the water level change data of the track section.
[0103] Step S252: performing change relationship mining analysis on the soil infiltration information data and the track section water level change data to obtain a soil infiltration water level change relationship network;
[0104] The embodiment of the present invention analyzes soil permeability information data and track section water level change data by using association rule mining and analysis technology to mine the correlation and influence relationship between the change of track section water level and soil permeability, and finally obtains a soil permeability water level change relationship network.
[0105] Step S253: performing potential impact detection and analysis on the soil seepage water level change relationship network to obtain soil seepage water level change impact model data;
[0106] The embodiment of the present invention uses a potential impact detection method to detect and analyze key nodes and paths in the soil infiltration and water level change relationship network to analyze the most important impact of soil permeability on water level changes, and determine the impact relationship pattern between soil permeability and water level changes, and finally obtain soil infiltration and water level change impact pattern data.
[0107] Step S254: performing impact assessment analysis on the soil seepage water level change impact model data to obtain the soil seepage water level impact factor.
[0108] The embodiment of the present invention evaluates and analyzes different water level change influence patterns in the soil infiltration water level change influence pattern data to analyze and determine the influencing factors in the soil infiltration water level change influence pattern data that have an important influence on the water level change, and finally obtains the soil infiltration water level influence factor.
[0109] The present invention first monitors and analyzes the water level changes of the track section BIM digital base model, and can systematically record and analyze the water level change data of the track section. These data are not only digital representations, but also real-time responses to environmental changes. By monitoring the water level changes, it is possible to understand the fluctuation of the water level of the track section due to soil infiltration under different meteorological conditions, including the trend of rising and falling water. These data provide basic data for subsequent analysis and can help better understand the pattern and trend of water level changes. Secondly, by combining the soil infiltration information data and the track section water level change data, the change relationship mining analysis is carried out. This analysis aims to explore the relationship between soil permeability and water level changes, thereby establishing a soil permeability water level change relationship network. This network provides a comprehensive perspective that can reveal the complex interaction between soil permeability and water level changes. Through this processing step, the potential patterns and laws between soil permeability and water level changes can be identified, thereby providing a basis for subsequent impact analysis. Then, by performing potential impact detection analysis on the soil permeability water level change relationship network, the purpose of this analysis is to be able to identify the key nodes and paths in the change relationship network, which will have a significant impact on soil permeability and water level changes. By identifying these key factors, we can better understand the impact relationship between soil permeability and water level changes, which can help predict potential water level impact issues. Finally, by conducting an impact assessment analysis on the soil permeability water level change impact model data, the purpose of this analysis is to quantify the impact of different impact models on water level changes, and to quantitatively analyze the contribution of different impact model factors, thereby helping to understand the impact factors of each impact model factor, thereby providing basic data support for subsequent processing.
[0110] Preferably, step S3 comprises the following steps:
[0111] Step S31: electrically connecting the ground water level sensor to the track section BIM digital base model to form a track section ground water level observation sensor network;
[0112] The embodiment of the present invention uses ground water level sensors (including water level horizontal movement sensors and water level settlement sensors) to be electrically connected to the BIM digital base model of the track section in order to transmit data and control the sensors. At the same time, a sensor network capable of observing the ground water level in real time is constructed by configuring communication equipment and operating parameters between sensors, and it is ensured that the sensors can effectively communicate with the BIM digital base model of the track section, and finally a sensor network for ground water level observation in the track section is obtained.
[0113] Step S32: using the ground water level observation sensor network of the track section to perform dynamic time-lapse observation processing on the BIM digital base model of the track section, and obtaining the horizontal position and elevation data of the ground point water level at different observation times;
[0114] The embodiment of the present invention dynamically starts each ground water level sensor in the track section ground water level observation sensor network at different observation times to perform data acquisition and processing on the track section BIM digital base model, so as to observe the change trend of the ground water level in the track section BIM digital base model in different time periods, and finally obtain the horizontal position and elevation data of the ground point water level at different observation times.
[0115] Step S33: Comparing and analyzing the horizontal position and elevation data of the ground point water level at different observation times to obtain the horizontal displacement data of the ground point water level and the settlement data of the ground point water level;
[0116] The embodiment of the present invention compares and analyzes the horizontal position and elevation data of the ground point water level obtained at different observation times to calculate the lateral movement distance and vertical settlement of the ground point water level, and finally obtains the horizontal displacement data of the ground point water level and the settlement data of the ground point water level.
[0117] Step S34: performing water level deformation detection and analysis on the ground point water level horizontal displacement data and the ground point water level settlement data to obtain horizontal displacement and settlement deformation data;
[0118] The embodiment of the present invention detects and analyzes the horizontal displacement data of the water level at the ground point and the settlement data of the water level at the ground point by using the water level deformation analysis method, so as to analyze and identify the pattern and trend of the water level deformation, including the deformation in the horizontal displacement and settlement direction, and finally obtains the horizontal displacement and settlement deformation data.
[0119] Step S35: Perform water level prediction processing on the track section BIM digital base model according to the horizontal displacement and settlement deformation data to obtain track section water level prediction data.
[0120] The embodiment of the present invention predicts the water level in the BIM digital base model of the track section by using the water level changes of the horizontal displacement and settlement deformation data, so as to predict the future water level changes of the track section and finally obtain the water level prediction data of the track section.
[0121] The present invention firstly creates an observation sensor network of the ground water level in the track section by electrically connecting the ground water level sensor with the track section BIM digital base model. The formation of this network can monitor the ground water level in the track section BIM digital base model in real time. By combining the sensor data with the BIM model, a water level monitoring network with real-time data feedback is established, which helps to realize the timely perception of water level changes, improves the vigilance against potential hydrological risks, and provides important information for water resource management and track section safety. Secondly, by using the established track section ground water level observation sensor network to perform dynamic diachronic observation processing on the track section BIM digital base model, it means that the ground water level horizontal position and elevation data at different time points can be collected with the help of the track section ground water level observation sensor network, forming a series of observation data, which reflects the changing trend of the ground water level in different time periods, and provides rich information for the historical data of hydrological events. Through this step, multi-dimensional and multi-period ground water level data can be obtained, which helps to more comprehensively understand the dynamic nature of the track section water level. Then, by comparing and analyzing the horizontal position and elevation data of the ground water level at different observation times, this analysis helps to identify the changing trend of the ground water level, including horizontal displacement and settlement. By comparing the data at different time points, the relative change of the ground water level in the track section can be quantified, providing key basic data for further analysis. Next, the water level deformation detection analysis is performed on the horizontal displacement data of the ground water level and the ground water level settlement data. This analysis aims to identify the pattern and trend of water level deformation, including horizontal displacement and settlement. By analyzing these data, potential hydrological events, such as ground subsidence or surface displacement caused by water level changes, can be detected, which helps to warn of possible disaster risks in advance and ensure the safety of the track section and surrounding areas. Finally, by using the horizontal displacement and settlement deformation data obtained by analysis to predict the water level of the BIM digital base model of the track section, the water level can be predicted and simulated by combining the existing ground water level change data with the BIM model to understand the impact of possible future hydrological events on the track section, which helps to plan and implement effective water resources management measures, respond to potential hydrological risks in advance, and ensure the safety of the track section.
[0122] Preferably, step S4 comprises the following steps:
[0123] Step S41: performing correction evaluation and analysis on the water level prediction process of the track section water level prediction data according to the soil infiltration water level influence factor to obtain a water level prediction soil influence correction index;
[0124] The embodiment of the present invention incorporates the influencing factors of the soil infiltration water level influencing factors as a key factor into the water level prediction process of the track section water level prediction data for evaluation and analysis, so that the water level prediction process can fully consider the influence of the soil permeability on the water level, and expresses the degree of correction of the influence of soil infiltration on the water level prediction by calculating the correction index, and finally obtains the water level prediction soil influence correction index.
[0125] Step S42: performing influence correction optimization processing on the track section water level prediction data according to the water level prediction soil influence correction index to obtain water level prediction correction optimization data;
[0126] The embodiment of the present invention uses the calculated water level prediction soil influence correction index to correct and optimize the track section water level prediction data, so as to reduce or eliminate the influence of soil infiltration water level on water level prediction, so as to more accurately reflect the actual water level conditions of the track section, and finally obtain water level prediction corrected and optimized data.
[0127] Step S43: performing abnormal alarm monitoring and analysis on the water level prediction correction optimization data to obtain a water level abnormal alarm signal;
[0128] The embodiment of the present invention performs anomaly detection and analysis on the corrected water level prediction correction optimization data by using an anomaly detection algorithm to identify water level anomalies in the water level prediction correction optimization data in real time. When a water level anomaly is detected, a corresponding alarm signal is generated, and finally a water level anomaly alarm signal is obtained.
[0129] Step S44: performing maintenance decision-making analysis on the water level prediction correction optimization data according to the water level abnormality alarm signal to obtain a water level abnormality maintenance decision plan;
[0130] The embodiment of the present invention uses the water level abnormality alarm signal to perform a detailed analysis of the abnormal conditions in the corresponding water level prediction correction optimization data, including the nature, location, severity, etc. of the water level abnormality. Then, based on the analysis of the water level abnormality, a corresponding water level abnormality maintenance decision plan is formulated, including decisions such as changing the water level management strategy and initiating flood control measures to repair the water level abnormality, and finally a water level abnormality maintenance decision plan is obtained.
[0131] Step S45: Execute corresponding abnormal water level maintenance management operations according to the abnormal water level maintenance decision plan.
[0132] The embodiment of the present invention handles abnormal water level situations by using a formulated abnormal water level maintenance decision plan to execute corresponding abnormal water level maintenance management operations, including management decisions such as adjusting water level control facilities, strengthening monitoring, and unblocking drainage systems to ensure the stability and safety of the water level in the track section.
[0133] The present invention firstly uses the soil permeability water level influence factor to correct the water level prediction process of the track section water level prediction data, which means that the influence of soil permeability on water level prediction can be fully considered. Incorporating the soil permeability water level influence factor as a key factor into the water level prediction process helps to improve the accuracy of water level prediction, because soil permeability can significantly affect the change of water level. By evaluating the corrected data, a suitable water level prediction soil influence correction index can be obtained, which is an important reference indicator. Secondly, by using the water level prediction soil influence correction index to perform impact correction optimization processing on the track section water level prediction data, the influence of soil permeability can be considered according to the correction index, so that the water level prediction data can be adjusted more accurately to better reflect the actual situation. This process helps to improve the accuracy of water level prediction and reduce errors, thereby improving the hydrological risk management capabilities of the track section. Then, by performing abnormal alarm monitoring and analysis on the water level prediction correction optimization data, it means that the corrected water level prediction data can be monitored to find any abnormal situation. The obtained abnormal alarm signal can help to timely discover situations that are inconsistent with normal predictions, such as sudden floods or abnormal water level rise and fall, which helps to warn of potential water level disasters in track sections in advance and provide valuable information for emergency response. Next, the water level forecast correction optimization data is analyzed for maintenance decision making by using the water level abnormal alarm signal, which shows that when the water level forecast correction optimization data is abnormal, corresponding maintenance decisions can be made to deal with the abnormal water level problems, including changing the water level management strategy, launching flood control measures or performing maintenance work. By analyzing the abnormal situation, wise maintenance decisions can be made to reduce potential water level damage. Finally, the corresponding water level abnormal maintenance management operations are performed according to the formulated water level abnormal maintenance decision plan. Once the maintenance decision plan is determined, immediate action is required, which includes measures such as adjusting water level control facilities, strengthening monitoring, and unblocking drainage systems to ensure the safety and normal operation of the track section. This step is the action stage for actually responding to hydrological risks and abnormal situations, which helps to minimize the potential losses and safety risks of the water level in the track section.
[0134] Preferably, the present invention further provides a track section water level prediction system based on a BIM digital base, which is used to execute the track section water level prediction method based on a BIM digital base as described above. The track section water level prediction system based on a BIM digital base includes:
[0135] The digital base modeling module is used to obtain the geographic information data and environmental information data of the track section, and perform BIM fusion modeling on the geographic information data and environmental information data to obtain a BIM digital base model of the track section;
[0136] The soil infiltration water level impact detection module is used to obtain the meteorological information data of the track section, perform soil infiltration detection processing on the BIM digital base model of the track section according to the meteorological information data, and obtain soil infiltration information data; perform water level impact assessment and analysis on the BIM digital base model of the track section according to the soil infiltration information data, so as to obtain the soil infiltration water level impact factor;
[0137] The track section water level prediction module is used to observe and analyze the ground point water level of the track section BIM digital base model to obtain the ground point water level horizontal displacement data and ground point water level settlement data; the track section BIM digital base model is used to perform water level prediction processing according to the ground point water level horizontal displacement data and ground point water level settlement data, so as to obtain the track section water level prediction data;
[0138] The water level prediction abnormality maintenance module is used to correct and optimize the water level prediction process of the track section water level prediction data according to the soil infiltration water level influencing factor to obtain the water level prediction correction optimization data; perform abnormal maintenance decision-making analysis on the water level prediction correction optimization data to obtain the water level abnormality maintenance decision plan; and perform corresponding water level abnormality maintenance management operations according to the water level abnormality maintenance decision plan.
[0139] In summary, the present invention provides a track section water level prediction system based on a BIM digital base, and the track section water level prediction system based on the BIM digital base is composed of a digital base modeling module, a soil infiltration water level impact detection module, a track section water level prediction module, and a water level prediction abnormality maintenance module. It can realize any one of the track section water level prediction methods based on the BIM digital base described in the present invention, and is used to combine the operations between the computer programs running on each module to realize a track section water level prediction method based on the BIM digital base. The internal structures of the system cooperate with each other. By introducing the BIM digital base technology, the management of the track section is made more intelligent and visualized, and the efficiency and accuracy of water level prediction and maintenance are improved. The prediction accuracy of the track section water level is also achieved by using the permeability of the soil and the movement of the water level at the ground point. At the same time, by using abnormal alarms, it is ensured that action can be taken immediately when a water level abnormality occurs, thereby improving the safety of the track section. This can greatly reduce duplication of work and manpower investment, and can quickly and effectively provide a more accurate and efficient track section water level prediction process, thereby simplifying the operation process of the track section water level prediction system based on the BIM digital base.
[0140] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.
[0141] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.
Claims
1. A track section water level prediction method based on BIM digital base, characterized in that: The following steps are involved: Step S1: Obtain geographic information data and environmental information data of the track section, and perform BIM fusion modeling on the geographic information data and environmental information data to obtain a BIM digital base model of the track section; Step S2: Acquire meteorological information data of the track section; perform soil infiltration detection processing on the BIM digital base model of the track section according to the meteorological information data to obtain soil infiltration information data; perform water level impact assessment and analysis on the BIM digital base model of the track section according to the soil infiltration information data to obtain a soil infiltration water level impact factor; wherein step S2 includes the following steps: Step S21: Acquire meteorological information data of the track section; Step S22: Use the meteorological rainfall intensity calculation formula to calculate the meteorological information data to obtain the meteorological rainfall intensity value; wherein the meteorological rainfall intensity calculation formula is specifically: ; In the formula, is the meteorological rainfall intensity value, For meteorological information data in volume and time The double integral space domain parameter on , is the rainfall volume variable parameter of the rainfall event in the meteorological information data, is the integral time variable parameter for intensity calculation, is the rainfall intensity adjustment coefficient of the rainfall event in the meteorological information data, is the rainfall probability density distribution parameter of the rainfall event in the meteorological information data, is the rainfall integral change parameter of the rainfall event in the meteorological information data, is the mean rainfall time of rainfall events in the meteorological information data, is the standard deviation of rainfall time of rainfall events in the meteorological information data, is an exponential function, is the gradient operator, is the gradient value of rainfall probability density distribution, is the rainfall density of the rainfall event in the meteorological information data, is the specific heat capacity of rainfall water in the rainfall event in the meteorological information data, is the rainfall event in the meteorological information data at time The rainfall flow parameters at is the correction value of meteorological rainfall intensity; Step S23: comparing and judging the meteorological rainfall intensity value according to a preset meteorological rainfall intensity threshold value to obtain a meteorological rainfall intensity judgment result; performing intensity level division processing on the meteorological information data corresponding to the meteorological rainfall intensity value according to the meteorological rainfall intensity judgment result to obtain meteorological rainfall intensity level data; Step S24: performing a permeability detection process on the soil permeability in the BIM digital base model of the track section according to the meteorological rainfall intensity level data to obtain soil permeability information data; Step S25: performing water level impact assessment analysis on the track section BIM digital base model according to the soil penetration information data to obtain the soil penetration water level impact factor; Step S3: Observe and analyze the water level at the ground point on the BIM digital base model of the track section to obtain the horizontal displacement data of the water level at the ground point and the settlement data of the water level at the ground point; perform water level prediction processing on the BIM digital base model of the track section according to the horizontal displacement data of the water level at the ground point and the settlement data of the water level at the ground point to obtain the water level prediction data of the track section; Step S4: Correct and optimize the water level prediction process of the track section water level prediction data according to the soil infiltration water level influencing factor to obtain the water level prediction correction optimization data; perform abnormal maintenance decision-making analysis on the water level prediction correction optimization data to obtain the water level abnormal maintenance decision plan; perform corresponding water level abnormal maintenance management operations according to the water level abnormal maintenance decision plan.
2. The track section water level prediction method based on BIM digital base according to claim 1 is characterized in that: Step S1 includes the following steps: Step S11: Acquire geographic information data and environmental information data of the track section; Step S12: Performing data quality screening on the geographic information data and the environmental information data to obtain high-quality geographic information data and high-quality environmental information data; Step S13: Perform three-dimensional map visualization processing on the high-quality geographic information data to obtain a three-dimensional geographic map of the track section; Step S14: performing data association exploration and analysis on the three-dimensional geographic map of the track section and the high-quality data of environmental information to obtain the geographic environment association relationship of the track section; Step S15: According to the geographical environment correlation of the track section, the BIM software is used to perform BIM fusion modeling processing on the three-dimensional geographical map of the track section and the high-quality data of environmental information to obtain a BIM digital base model of the track section.
3. The track section water level prediction method based on BIM digital base according to claim 2 is characterized in that: Step S12 includes the following steps: Step S121: performing data cleaning processing on the geographic information data and the environmental information data to obtain geographic information cleansing data and environmental information cleansing data; Step S122: performing noise reduction processing on the geographic information cleansing data and the environmental information cleansing data to obtain geographic information noise reduction data and environmental information noise reduction data; Step S123: using a data quality metric calculation formula to perform quality calculation on the geographic information denoised data and the environmental information denoised data to obtain a geographic data quality metric value and an environmental data quality metric value; Step S124: judging and screening the geographic information denoised data corresponding to the geographic data quality metric value and the environmental information denoised data corresponding to the environmental data quality metric value according to the preset data quality metric standard value to obtain high-quality geographic information data and high-quality environmental information data.
4. The track section water level prediction method based on BIM digital base according to claim 3 is characterized in that: The data quality metric calculation formula in step S123 is specifically: ; ; ; ; In the formula, is the geographic data quality metric, The spatial domain parameters for the integral calculation of the denoised geospatial data are: is the quality index parameter of geographic information denoising data, The quality index change gradient of geographic information denoising data, is the standard deviation of the quality index of geographic information denoising data, is the quality index gradient influence coefficient of geographic information denoising data, It is the quality reference index parameter of geographic information noise reduction data. is the standard deviation of the quality reference index of geographic information noise reduction data, is the quality index similarity measurement function of geographic information denoising data, Adjust the parameters for the similarity of the quality indicators of geographic information denoising data, is the number of quality indicator parameters in geographic information denoising data, For the first Quality indicator parameters, is the mean value of the quality index of geographic information denoising data, For geographic information noise reduction data The quality reference index parameters corresponding to the quality index parameters are: is the mean value of the quality reference index of geographic information noise reduction data, is the correction value of the geographic data quality metric, is the environmental data quality metric, The spatial domain parameters for the integral calculation of the environmental information denoising data are: is the quality index parameter of environmental information denoising data, The quality index change gradient of the environmental information denoising data, is the standard deviation of the quality indicator of environmental information denoising data, is the quality index gradient influence coefficient of environmental information noise reduction data, It is the quality reference index parameter of environmental information noise reduction data. is the standard deviation of the quality reference indicator of environmental information noise reduction data, is the quality index similarity measurement function of environmental information denoising data, Adjust the parameters for the similarity of the quality indicators of the environmental information denoising data. is the number of quality indicator parameters in the environmental information denoising data, The first Quality indicator parameters, is the mean value of the quality index of the environmental information denoising data, The first The quality reference index parameters corresponding to the quality index parameters are: is the mean value of the quality reference index of environmental information noise reduction data, It is the correction value of the environmental data quality metric.
5. The track section water level prediction method based on BIM digital base according to claim 1 is characterized in that: Step S25 includes the following steps: Step S251: monitoring and analyzing the water level change of the track section BIM digital base model to obtain the track section water level change data; Step S252: performing change relationship mining analysis on the soil infiltration information data and the track section water level change data to obtain a soil infiltration water level change relationship network; Step S253: performing potential impact detection and analysis on the soil seepage water level change relationship network to obtain soil seepage water level change impact model data; Step S254: performing impact assessment analysis on the soil seepage water level change impact model data to obtain the soil seepage water level impact factor.
6. The track section water level prediction method based on BIM digital base according to claim 1 is characterized in that: Step S3 includes the following steps: Step S31: electrically connecting the ground water level sensor to the track section BIM digital base model to form a track section ground water level observation sensor network; Step S32: using the ground water level observation sensor network of the track section to perform dynamic time-lapse observation processing on the BIM digital base model of the track section, and obtaining the horizontal position and elevation data of the ground point water level at different observation times; Step S33: Comparing and analyzing the horizontal position and elevation data of the ground point water level at different observation times to obtain the ground point water level horizontal displacement data and the ground point water level settlement data; Step S34: performing water level deformation detection and analysis on the ground point water level horizontal displacement data and the ground point water level settlement data to obtain horizontal displacement and settlement deformation data; Step S35: Perform water level prediction processing on the track section BIM digital base model according to the horizontal displacement and settlement deformation data to obtain track section water level prediction data.
7. The track section water level prediction method based on BIM digital base according to claim 1 is characterized in that: Step S4 includes the following steps: Step S41: performing correction evaluation and analysis on the water level prediction process of the track section water level prediction data according to the soil infiltration water level influence factor to obtain a water level prediction soil influence correction index; Step S42: performing influence correction optimization processing on the track section water level prediction data according to the water level prediction soil influence correction index to obtain water level prediction correction optimization data; Step S43: performing abnormal alarm monitoring and analysis on the water level prediction correction optimization data to obtain a water level abnormal alarm signal; Step S44: performing maintenance decision-making analysis on the water level prediction correction optimization data according to the water level abnormality alarm signal to obtain a water level abnormality maintenance decision plan; Step S45: Execute corresponding abnormal water level maintenance management operations according to the abnormal water level maintenance decision plan.
8. A track section water level prediction system based on BIM digital base, characterized in that: Used to execute the track section water level prediction method based on BIM digital base as claimed in claim 1, the track section water level prediction system based on BIM digital base includes: The digital base modeling module is used to obtain the geographic information data and environmental information data of the track section, and perform BIM fusion modeling on the geographic information data and environmental information data to obtain a BIM digital base model of the track section; The soil infiltration water level impact detection module is used to obtain meteorological information data of the track section; perform soil infiltration detection processing on the BIM digital base model of the track section according to the meteorological information data to obtain soil infiltration information data; perform water level impact assessment and analysis on the BIM digital base model of the track section according to the soil infiltration information data to obtain the soil infiltration water level impact factor; The track section water level prediction module is used to observe and analyze the ground point water level of the track section BIM digital base model to obtain the ground point water level horizontal displacement data and ground point water level settlement data; the track section BIM digital base model is used to perform water level prediction processing according to the ground point water level horizontal displacement data and ground point water level settlement data, so as to obtain the track section water level prediction data; The water level prediction abnormality maintenance module is used to correct and optimize the water level prediction process of the track section water level prediction data according to the soil infiltration water level influencing factor to obtain the water level prediction correction optimization data; perform abnormal maintenance decision-making analysis on the water level prediction correction optimization data to obtain the water level abnormality maintenance decision plan; and perform corresponding water level abnormality maintenance management operations according to the water level abnormality maintenance decision plan.
