An intelligent monitoring and early warning method and system for cofferdam construction process

Abstract

The present invention discloses an intelligent monitoring and early warning method and system for the cofferdam construction process, which belongs to the field of intelligent monitoring. The early warning method includes collecting historical hydrological and geological data, constructing a hydrological-geological database and marking risk factors, and determining the risk type and safety threshold of hydrology and geology. Then, the key monitoring parameters are determined according to the cofferdam type, and a unique ID is assigned to the sensor, and the sensor data is integrated into the network transmission node. After the data is transmitted to the data processing center, it is decompressed and compared with the hydrological-geological data, and the sensor data weight coefficient is calculated. Based on these data, a cofferdam construction early warning model is constructed, and the early warning conditions are screened step by step by weight coefficients and risk factors to form construction early warning evaluation parameters. Finally, the construction process is combined with real-time data for risk identification and probability early warning to improve construction safety. The present invention improves the accuracy of construction risk prediction by constructing an accurate cofferdam construction early warning model.

Description

Technical Field

[0001] The present invention relates to the field of intelligent monitoring, and in particular to an intelligent monitoring and early warning method and system for a cofferdam construction process. Background Art

[0002] Cofferdam construction is a critical part of the bridge construction process, especially in the construction of bridges across rivers, rivers, and seas. Cofferdam construction must not only ensure the safety and stability of the bridge foundation, but also deal with complex hydrological, geological and other environmental factors. However, the existing cofferdam construction monitoring methods still have some shortcomings, which affect the safety and stability of the construction process.

[0003] In the existing technology, the real-time and accuracy of cofferdam construction monitoring data is still a problem. Although modern technology can monitor hydrological, geological and other environmental parameters in real time through sensors, due to the complexity of the on-site environment and the limitations of sensor layout, it is often impossible to fully cover all key risk points in the cofferdam construction area. In addition, some sensors may be disturbed by harsh environmental conditions (such as water flow, sediment, temperature fluctuations, etc.), resulting in data deviation, which affects the accuracy of risk assessment. Secondly, the data processing and analysis capabilities are limited. Although some systems can collect a large amount of data, they often lack sufficiently powerful data processing capabilities and intelligent analysis tools. Existing monitoring systems often rely on manual analysis or simple algorithm processing, making it difficult to achieve real-time and comprehensive risk prediction of complex and changeable construction site environments. Especially when faced with a large amount of heterogeneous data (such as water level, soil settlement, meteorological changes, etc.), data integration and comparative analysis still have certain difficulties, making it difficult to efficiently and accurately identify potential construction risks. In addition, the response of the existing cofferdam construction early warning mechanism is not sensitive and intelligent enough. When risks occur, the existing cofferdam construction monitoring system often takes a certain amount of time to identify and respond, which may result in insufficient time to take effective emergency measures when danger occurs. Moreover, most of the existing early warning mechanisms are based on fixed threshold settings and lack dynamic adjustment and adaptive capabilities. They are unable to flexibly adjust early warning strategies according to different construction stages or environmental conditions, and may result in false alarms or missed alarms.

[0004] Therefore, although the cofferdam construction monitoring technology has been continuously improving, there are still problems such as incomplete data collection, insufficient analysis accuracy, and delayed early warning response. These shortcomings limit its application effect in complex construction environments, and it is urgent to improve its monitoring capabilities and risk warning levels through the improvement of intelligent and automated technologies. Summary of the invention

[0005] One of the purposes of the present invention is to provide an intelligent monitoring and early warning method for the cofferdam construction process to solve the problems of insufficient analysis accuracy and delayed early warning response in the prior art.

[0006] The present invention is implemented through the following technical scheme: an intelligent monitoring and early warning method for the cofferdam construction process, comprising the following steps: S100, collecting historical hydrological data and geological data of the construction site, constructing a hydrological-geological database, and cleaning and marking the data in the hydrological-geological database to obtain risk factors in the cofferdam construction process; marking the hydrological and geological risk types and safety standard thresholds in the hydrological-geological database according to the risk factors, and sending the risk factors to the network transmission node set at the construction site; S200, determining the key parameters to be monitored according to the specific type of the cofferdam, the key parameters including water level and flow rate, sedimentation and displacement, stress and deformation, turbidity, vibration and noise, and environmental meteorology; selecting corresponding sensors to collect data according to the key parameters; and assigning unique IDs to the sensors when arranging the sensors, so that the sensors include source information in the data while uploading the data, which is convenient for the subsequent organization and query of the data; dividing the types of sensors, integrating the same type of sensors into a convergence node, and the same type of sensors Multiple sensors correspond to one aggregation node to avoid each individual sensor being directly connected to the background system. The data collected by multiple sensors of the same type are uniformly uploaded to the corresponding aggregation node, and all these aggregation nodes are integrated to form a network transmission node set. The network transmission node set collects the data sent by the aggregation node, pre-processes the received data, and compresses the pre-processed data and sends it to the data processing center; S300, the data processing center builds a sensor database according to the type of sensor. After receiving the compressed data sent by the network transmission node set, the data center first decompresses the data, and then stores it in the sensor database according to the type of data. The data in the sensor database is compared with the data in the hydrological-geological database to obtain the weight coefficients of different sensor data. Based on the weight coefficients and risk factors of the different sensor data, a step-by-step screening mechanism for cofferdam construction warning conditions is constructed, and the screened construction warning evaluation parameters are quantitatively superimposed to obtain a cofferdam construction warning model. The general formula of the cofferdam construction warning model is:

[0007] y=α0+α1x1 +α2x2+α3x3……+α i x i +λ, where y is the construction warning evaluation parameter, x1 is the first hydrological-geological risk factor for construction warning; x2 is the second hydrological-geological risk factor for construction warning; x i is the i-th hydrological-geological risk factor for construction warning; α0 is the weight coefficient of the first type of sensor data, α1 is the weight coefficient of the second type of sensor data, α2 is the weight coefficient of the third type of sensor data, and α iis the weight coefficient of the i+1th class sensor data, and λ is the random error parameter; S400, based on the constructed cofferdam construction early warning model, real-time risk identification is performed on the cofferdam construction process in combination with the data in the sensor database, and finally the probability of risk occurrence of the risk characterization parameter model is obtained, and an early warning is issued based on the probability of risk occurrence.

[0008] Furthermore, the intelligent monitoring and early warning method also includes collecting environmental and ecological data, constructing an ecological environment database, marking the corresponding ecological environment pollution standard thresholds, comparing the data sent by the network transmission node set with the data in the ecological environment database, and judging the impact of the cofferdam construction process on the ecological environment based on the marked ecological environment pollution standard thresholds.

[0009] Furthermore, the cleaning mark includes the following sub-steps: S110, according to the specific type of cofferdam, the corresponding construction requirements are obtained, and the influence relationship of hydrological-geological structure on cofferdam construction is summarized in combination with the data in the hydrological-geological database, and the main control factors of the influence relationship are obtained, and a comprehensive evaluation index system for cofferdam construction conditions is established according to the influence relationship and the main control factors; S120, according to the comprehensive evaluation index system for cofferdam construction conditions, different weights are assigned according to the size of the influence, different hydrological-geological characteristics are divided into different echelon combinations according to their influence on the cofferdam construction conditions, and the total risk value of each echelon combination is calculated.

[0010] Furthermore, different echelon combinations are divided and the total risk value of each echelon combination is calculated, including: marking the influence of different hydrological factors and geological factors in the database on the cofferdam construction conditions according to the data in the hydrological-geological database, obtaining the influencing factors, and assigning corresponding weights to the influencing factors; and dividing the different hydrological and geological combinations into multiple echelons according to the influence of each hydrological and geological feature on the cofferdam construction and the assigned weight.

[0011] Furthermore, the division into multiple echelons includes the following division steps: S121, determining the impact level of the influencing factor according to the distribution of data in the hydrological-geological database, and dividing it into three impact levels, namely high impact, medium impact and low impact; S122, constructing a echelon combination according to the impact level, and classifying the influencing factors of different weights into three echelons, namely high-risk echelon, medium-risk echelon and low-risk echelon; S123, calculating the total risk value of each echelon combination according to the weights assigned to the influencing factors.

[0012] Furthermore, the preprocessing includes, S210, checking whether there are duplicate records in the data according to the sensor ID, deleting the duplicate data, and using Kalman filtering to filter out irrelevant noise and interference signals in the data; S220, using the standard deviation algorithm for the data of different aggregation nodes to determine whether the sent data conforms to the normal distribution, judging the data beyond the normal range as an outlier, and eliminating the identified outliers; S230, then screening the data according to the risk factors and key monitored parameters to obtain the preprocessed data.

[0013] Furthermore, the sensors include water level sensors, flow rate sensors, temperature and humidity sensors, displacement meters, pressure sensors, and strain gauges, among which the water level sensor is used to monitor the difference between internal and external water levels to prevent seepage and sudden floods; the pressure sensor is used to measure the pressure on the cofferdam structure and evaluate the stress condition of the structure; the strain gauge is used to monitor the strain change of the cofferdam material to prevent structural damage; the displacement sensor is used to detect the displacement and settlement of the cofferdam to prevent foundation instability; the inclination sensor is used to monitor the inclination of the cofferdam to prevent the risk of overturning; the environmental sensor is used to understand the environmental impact including temperature, humidity, rainfall, wind speed, etc.; sensors are deployed at various key positions of the cofferdam to comprehensively monitor the condition of the cofferdam.

[0014] Another aspect of the present invention provides an intelligent monitoring and early warning system for a cofferdam construction process, a database construction unit, a sensor unit, a data processing unit and an early warning model unit.

[0015] Among them, the database construction unit is configured to collect historical hydrological data and geological data of the construction site, construct a hydrological-geological database, and clean and mark the data in the hydrological-geological database to obtain risk factors in the cofferdam construction process, and mark the hydrological and geological risk types and safety standard thresholds in the hydrological-geological database according to the risk factors, and send the risk factors to the sensor unit at the same time; the sensor unit is connected to the database construction unit and is configured to determine the key parameters that need to be monitored according to the specific type of the cofferdam. The key parameters include water level and flow rate, sedimentation and displacement, stress and deformation, turbidity, vibration and noise, and environmental meteorology. According to the key parameters, corresponding sensors are selected to collect data, and unique IDs are assigned to sensors when arranging sensors, so that the sensors include source information in the data while uploading data, which is convenient for subsequent data organization and query, and the types of sensors are divided, and sensors of the same type are integrated into a convergence node. Multiple sensors of the same type correspond to one convergence node to avoid each individual sensor. The sensors are directly connected to the background system, and the data collected by multiple sensors of the same type are uniformly uploaded to the corresponding aggregation nodes. All these aggregation nodes are integrated to form a network transmission node set. The network transmission node set collects the data sent by the aggregation node, pre-processes the received data, and compresses the pre-processed data and sends it to the data processing unit; the data processing unit is connected to the sensor unit and the database construction unit and is configured as follows: the data processing center builds a sensor database according to the type of sensor. After receiving the compressed data sent by the network transmission node set, the data center first decompresses the data, and then stores it in the sensor database according to the type of data, compares the data in the sensor database with the data in the hydrological-geological database, and obtains the weight coefficients of different sensor data. Based on the weight coefficients and risk factors of the different sensor data, a step-by-step screening mechanism for cofferdam construction early warning conditions is constructed, and the screened construction early warning evaluation parameters are quantitatively superimposed to obtain a cofferdam construction early warning model. The general formula of the cofferdam construction early warning model is:

[0016] y=α0+α1x1 +α2x2+α3x3……+α i x i +λ, where y is the construction warning evaluation parameter, x1 is the first hydrological-geological risk factor for construction warning; x2 is the second hydrological-geological risk factor for construction warning; x i is the i-th hydrological-geological risk factor for construction warning; α0 is the weight coefficient of the first type of sensor data, α1 is the weight coefficient of the second type of sensor data, α2 is the weight coefficient of the third type of sensor data, and α iis the weight coefficient of the i+1th class sensor data, and λ is the random error parameter; the early warning model unit is connected to the data processing unit and is configured to perform real-time risk identification on the cofferdam construction process according to the constructed cofferdam construction early warning model combined with the data in the sensor database, and finally obtain the probability of risk occurrence of the risk characterization parameter model, and issue an early warning based on the probability of risk occurrence.

[0017] Furthermore, the intelligent monitoring and early warning system also includes an environmental monitoring unit, which is configured to collect environmental and ecological data, build an ecological environment database, mark the corresponding ecological environment pollution standard thresholds, compare the data sent by the network transmission node set with the data in the ecological environment database, and judge the impact of the cofferdam construction process on the ecological environment based on the marked ecological environment pollution standard thresholds.

[0018] Compared with the prior art, the present invention has the following advantages and beneficial effects:

[0019] 1. The present invention constructs a hydrological-geological database and collects historical hydrological data and geological data of the construction site, so that the early warning system can fully understand the historical environmental conditions of the construction site, providing a solid foundation for risk assessment. At the same time, by incorporating multiple key parameters such as environmental meteorology, turbidity, vibration and noise into the monitoring range, the entire system can achieve multi-dimensional monitoring to more comprehensively assess the safety risks of the construction site and provide more detailed construction risk warnings.

[0020] 2. The present invention integrates sensor data and performs preprocessing through aggregation nodes, thereby reducing the burden on the background system, compressing and transmitting data at the same time, improving the operating efficiency of the system, and after receiving the preprocessed data, the data center calculates the weight coefficient by comparing it with the historical data in the hydrological-geological database, providing accurate input for subsequent risk analysis. At the same time, the accuracy and traceability of data collection are ensured through the precise arrangement of sensors and the allocation of unique IDs.

[0021] 3. The present invention constructs an accurate early warning model for cofferdam construction by combining hydrological-geological factors and real-time monitoring data. The model adopts a step-by-step screening mechanism and a quantitative superposition method, and can dynamically adjust the early warning standard according to different sensor data weights and risk factors, thereby improving the accuracy of risk prediction and the flexibility of response. And by comparing sensor data with the early warning model, the probability of risk occurrence in the construction process is timely evaluated. According to the changes in risk probability, the system can provide real-time early warnings, provide the construction party with a basis for preventive measures or emergency response, and reduce the impact of sudden risks on construction safety. At the same time, in the cofferdam construction early warning model, the weight coefficient and threshold can be dynamically adjusted according to changes in the actual construction environment, which provides greater flexibility and adaptability for dealing with risks in different construction stages and under different environmental conditions.

[0022] 4. The present invention avoids each sensor from connecting to the background system separately by aggregating sensors of the same type, reduces the system load, and makes data collection and transmission more efficient. This resource integration method improves the stability of the overall system and the data processing capability. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The drawings described herein are used to provide a further understanding of the embodiments of the present invention, constitute a part of this application, and do not constitute a limitation of the embodiments of the present invention. In the drawings:

[0024] Figure 1 This is a flow chart of the method provided in Example 1 of the present invention.

[0025] Figure 2 A schematic diagram of the system structure provided in Example 2 of the present invention. DETAILED DESCRIPTION

[0026] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.

[0027] Embodiment 1:

[0028] An intelligent monitoring and early warning method for the cofferdam construction process monitors the environment, collects and analyzes real-time data from sensors, conducts targeted monitoring, and promptly feedbacks abnormal conditions and issues early warnings to avoid the impact of external environmental changes on the cofferdam. This ensures the safety of the cofferdam construction process, the stability of the cofferdam structure, and timely detects risks such as settlement, tilt, and deformation. Figure 1 The flowchart of the intelligent monitoring and early warning method disclosed in this embodiment is shown. It can be seen from the figure that this embodiment is implemented through the following steps:

[0029] Step 1: First, collect the past hydrological and geological data of the construction site and build a hydrological-geological database for subsequent comparative analysis. Collect environmental and ecological data and build an ecological environment database for subsequent ecological environment monitoring. After the hydrological-geological database and ecological environment database are built, clean and mark the data in the database to obtain the risk factors in the cofferdam construction process, and mark the hydrological and geological risk types and safety standard thresholds in the hydrological-geological database based on the obtained risk factors. For the ecological environment database, mark the corresponding ecological environment pollution standard threshold. At the same time, send the obtained risk factors to the network transmission node set at the construction site for preliminary comparison.

[0030] It should be noted that in this step, the risk factors are actually derived from a comprehensive analysis of various hydrological and geological characteristics, identifying which factors have the greatest impact on cofferdam construction (such as groundwater level, soil properties, rock stability, etc.), and these factors can be regarded as "risk factors".

[0031] Specifically, cleaning and marking the data in the database includes:

[0032] Firstly, according to the specific type of construction cofferdam and the specific construction requirements, the characteristics of the hydrological-geological database of the cofferdam construction area were compared and analyzed, the influence of hydrological-geological structure on cofferdam construction and its main controlling factors were summarized, and a comprehensive evaluation index system for cofferdam construction conditions was established.

[0033] According to the comprehensive evaluation index system of cofferdam construction conditions, different weights are assigned according to the size of the impact, and different hydrological and geological characteristics are divided into different echelon combination parameters according to their impact on the cofferdam construction conditions.

[0034] Specifically, it includes: according to the hydrological factors (for example, precipitation, river flow, water level fluctuation, groundwater level, etc.) and geological factors (for example, soil type, soil density, permeability, geological structure such as faults, groundwater flow path, rock layer thickness, etc.) in the hydrological-geological database, finding out the influence of different characteristics of hydrological factors and geological factors on the cofferdam construction conditions, and giving corresponding weights.

[0035] Then, according to the influence degree and weight of each hydrological-geological feature on cofferdam construction, different combinations of these features can be divided into multiple levels. The purpose of the level division is to classify the influence scope and influence size of each factor to clarify which combinations are higher risk and which are lower risk.

[0036] Specifically, the division of the tiered combination parameters can generally be divided into the following steps:

[0037] 1) Determine the impact level of the influencing factors based on the distribution of data in the hydrological-geological database. For example, in this embodiment, they can be divided into three impact levels, namely: High impact (major risk): hydrological or geological features that are crucial to cofferdam construction, their changes have a very large impact on construction and may even lead to construction failure. For example, unstable geological structures in some areas or drastic changes in water levels may cause serious problems such as cofferdam collapse. Medium impact (medium risk): Although some factors will not directly lead to the failure of cofferdam construction, they may increase construction risks, increase construction costs or extend construction time. For example, medium permeability soil layers may affect the stability of construction to a certain extent, but may not necessarily cause catastrophic consequences. Low impact (low risk): factors with less impact, changes in these factors will not significantly change the stability or safety of the construction process, but may still have some impact on the details of the construction. For example, slight changes in precipitation or changes in soil types.

[0038] 2) Construct a tiered combination based on the impact level. Generally, factors with greater impact should be classified into the high-risk tier, while factors with less impact should be classified into the low-risk tier. For example, in this embodiment, three tiered combinations are included:

[0039] High-risk tier (significant impact combination): The combination contains multiple high-impact factors, such as areas with drastic water level changes and unstable geological conditions, which may cause instability in cofferdam construction. Medium-risk tier (medium-impact combination): The combination includes some medium-impact factors, such as medium precipitation, normal geological conditions, etc., which may cause some interference to the construction of the cofferdam or increase the difficulty of construction, but will not immediately lead to failure. Low-risk tier (minor impact combination): The combination contains low-impact factors, such as stable soil layers and a lower range of water level changes, which usually will not have a significant impact on construction.

[0040] For example, one can assume the following influencing factors: precipitation (low, medium, high); water level fluctuation (low, medium, high); soil permeability (low, medium, high); and ground stability (stable, unstable).

[0041] Then the combinations of different levels may be:

[0042] High-risk levels: high precipitation + high water level fluctuations + unstable strata; high precipitation + high water level fluctuations + high permeability soil + unstable strata.

[0043] Medium risk level: medium precipitation + medium water level fluctuation + stable stratum; high precipitation + medium water level fluctuation + stable stratum; high precipitation + high permeability soil layer + stable stratum.

[0044] Low-risk tier: low precipitation + low water level fluctuation + stable stratum; low precipitation + stable water level + low permeability soil stratum.

[0045] 3) For each tier combination, the total risk value of each combination can be calculated based on the weights previously assigned to the hydrological and geological factors. For example, if the weight of water level fluctuation in a high-risk combination is 0.4, the weight of soil permeability is 0.3, and the weight of precipitation is 0.3, the total risk value of the combination can be calculated by weighted summation. Factors with higher weights contribute more to the total risk value.

[0046] It should be noted that the above-mentioned steps of echelon division are to mark and divide different influencing factors according to the degree of influence of hydrological and geological characteristics on cofferdam construction. These influencing factors will be given different weights according to the impact on construction safety (for example, a higher weight may be given when the groundwater level changes greatly). Finally, by calculating each risk factor and weighted combination, a "total risk value" is finally obtained as the manifestation of the risk factor. The risk value of each echelon combination is obtained by weighted and calculated, and these echelon combinations can be regarded as the manifestation of different risk factors. In other words, the risk factors mentioned in this embodiment are not a simple single data, but a set of characteristic factors obtained by analyzing and processing hydrological and geological data. They are given different weights according to the degree of influence, and a "total risk value" is calculated through a comprehensive evaluation index system and risk echelon division. The final results of these risk factors can be used as the basis for monitoring and early warning during the construction process.

[0047] Step 2: Determine the parameters that need to be monitored based on the type of cofferdam (selection of monitoring parameters). Specifically, during the cofferdam construction process, the key parameters that may affect the construction safety include: water level and flow rate monitoring. Changes in water level may affect the stability of the cofferdam, and flow rate may affect soil loss and cofferdam deformation during the construction process.

[0048] Settlement and displacement monitoring prevents uneven settlement or tilting by monitoring the settlement and horizontal displacement of the cofferdam.

[0049] Stress and deformation monitoring can be used to monitor whether the cofferdam structure has stress concentration or excessive deformation.

[0050] Turbidity monitoring monitors the turbidity of water bodies. Changes in water quality may indicate leakage or structural problems in the cofferdam or the existence of environmental pollution problems.

[0051] Vibration and noise monitoring: monitor the vibration condition of the cofferdam, especially during the construction process, the foundation vibration may cause the instability of the cofferdam.

[0052] Environmental meteorological monitoring, such as changes in precipitation, wind speed, temperature, etc., especially in extreme weather conditions, may affect the construction safety of the cofferdam.

[0053] It should be noted that the selection of monitoring parameters can be based on the size, depth, flow rate, geological conditions, etc. of the water area of ​​the specific construction site, and the selection of appropriate cofferdam types (for example, caisson cofferdam, steel cofferdam, steel sheet pile cofferdam, etc.), thereby determining the final monitoring parameters.

[0054] Step 3: After determining the parameters that need to be monitored, select appropriate sensors to collect various types of data. Sensor types can be water level sensors, flow rate sensors, temperature and humidity sensors, displacement meters, pressure sensors, strain gauges, etc. At the same time, assign unique IDs to the sensors when arranging them, and include source information in the data when uploading it, so as to facilitate subsequent data organization and query.

[0055] Among them, water level sensors are used to monitor the difference between internal and external water levels to prevent seepage and sudden floods. Pressure sensors are used to measure the pressure on the cofferdam structure and evaluate the stress of the structure. Strain gauges are used to monitor the strain changes of cofferdam materials to prevent structural damage. Displacement sensors are used to detect the displacement and settlement of the cofferdam to prevent foundation instability. Inclination sensors are used to monitor the inclination of the cofferdam to prevent the risk of overturning. Environmental sensors are used to understand environmental impacts including temperature, humidity, rainfall, wind speed, etc. Sensors are deployed at various key locations of the cofferdam to comprehensively monitor the condition of the cofferdam.

[0056] In this embodiment, through the arrangement of sensors, various data of the cofferdam will be collected and transmitted in real time. When arranging sensors, it is necessary to ensure that key locations (such as the inside and outside of the cofferdam, settlement points, support points, etc.) are covered, and the coverage of the sensors is as comprehensive as possible. At the same time, a unique ID is assigned to each sensor, which facilitates subsequent data tracking, storage and query. In addition, the sensor ID can help the system accurately identify the data source when receiving data, distinguish the data information of different sensors, and avoid confusion.

[0057] In this embodiment, by dividing the types of sensors, sensors of the same type are integrated into a sink node. Multiple sensors of the same type correspond to one sink node, so that each individual sensor is prevented from being directly connected to the background system, thereby reducing the complexity of data transmission and the burden on the system. The setting of the sink node can not only improve the efficiency of data transmission, but also reduce the system error caused by transmission interruption, equipment failure and other problems.

[0058] The data collected by multiple sensors of the same type are uniformly uploaded to the corresponding aggregation node. All these aggregation nodes are integrated into a network transmission node set. All the aggregation nodes are finally gathered through the network transmission node and the data is uniformly processed. The network transmission node set is responsible for managing, storing and analyzing various types of data received.

[0059] The network transmission node set can pre-process the data uploaded by the aggregation node, thereby ensuring the quality and accuracy of the data when it is sent to the background monitoring and early warning system.

[0060] Specifically, the preprocessing of data sent by all sink nodes includes:

[0061] Check whether there are duplicate records in the data according to the sensor ID, delete the duplicate data, and use Kalman filtering to filter out irrelevant noise and interference signals in the data. In actual use, irrelevant noise and interference signals may exist in the sensor data. Kalman filtering can improve the accuracy and credibility of the data.

[0062] Then, the standard deviation algorithm is used to determine whether the data sent by different aggregation nodes conforms to the normal distribution. Data outside the normal range is an outlier, and the identified outliers are removed. The purpose of this step is that outliers may be caused by sensor failure, external interference, or extreme weather. By removing outliers, those observations that deviate significantly from the normal range can be excluded.

[0063] The sensor data is then screened based on risk factors and key monitored parameters, and the screened data is sent to the data processing center.

[0064] Step 4: After receiving the compressed data from the network transmission node set, the data processing center first decompresses it. The decompressed data will be classified and stored according to the source, type and structure of the data based on the sensor ID. For example, the type of data (such as water level, flow rate, sedimentation, stress, etc.) can be determined based on the sensor ID and stored in the sensor database in different categories. In this embodiment, the sensor database adopts a time series database, which is suitable for processing large-scale sensor data and can efficiently support queries by timestamp.

[0065] The data in the sensor database is compared with the corresponding hydrological and geological features in the hydrological-geological database through the sensor ID to identify the hydrological and geological features related to the construction (such as groundwater level, soil bearing capacity, etc.). The comparison results can help identify the differences between the current environmental conditions and historical data, and provide a reference for subsequent risk assessment. In this embodiment, Euclidean distance or cosine similarity is used to quantify the similarity between sensor data and historical hydrogeological data. Then, the relationship between hydrological-geological data and construction conditions is analyzed through a regression model to determine whether the current construction environment is in a dangerous area.

[0066] Based on the identified hydrological and geological features related to the construction, the weight coefficient of each sensor data is calculated. The weight coefficient reflects the contribution or influence of the sensor data on the safety of the cofferdam construction.

[0067] Specifically, the data of each sensor is first analyzed, and combined with the influence of hydrological and geological characteristics, which sensors are critical to the safety of construction are identified. The influencing factors can be obtained through regression analysis of historical construction data. Then a weight coefficient is assigned to each sensor through the principal component analysis algorithm. The size of the weight coefficient reflects the role of the sensor data in monitoring hydrological and geological risks during the construction process. For example, for a water level monitoring sensor, if the data of the sensor is closely related to the stability of the cofferdam construction, a larger weight (for example, 0.4) is given. For environmental meteorological monitoring sensors, if they have little impact on construction, a smaller weight (for example, 0.1) may be given.

[0068] Finally, based on the weight coefficient and risk factor of the data in the sensor database, a step-by-step screening mechanism for the early warning conditions of cofferdam construction is constructed. The screened construction early warning evaluation parameters are quantitatively superimposed to obtain the cofferdam construction early warning model. The general formula of the cofferdam construction early warning model is:

[0069] y=α0+α1x1 +α2x2+α3x3……+α i x i +λ,

[0070] Among them, y is the construction early warning evaluation parameter, x1 is the first hydrological-geological risk factor of construction early warning; x2 is the second hydrological-geological risk factor of construction early warning; x i is the i-th hydrological-geological risk factor for construction warning; α0 is the weight coefficient of the first type of sensor data, α1 is the weight coefficient of the second type of sensor data, α2 is the weight coefficient of the third type of sensor data, and α i is the weight coefficient of the i+1th class sensor data, and λ is the random error parameter.

[0071] According to the constructed cofferdam construction early warning model, real-time risk identification is performed on the cofferdam construction process in combination with the data in the sensor database, and finally the probability of risk occurrence of the risk characterization parameter model is obtained, and an early warning is issued according to the probability of risk occurrence.

[0072] Step 5: After receiving the data sent by the network transmission node set, the data processing center compares it with the data in the hydrological-geological database, and combines the risk factors to conduct real-time risk identification of the cofferdam construction process, and finally obtains the probability of risk occurrence of the risk characterization parameter model, and issues an early warning based on the probability of risk occurrence.

[0073] At the same time, the data sent by the network transmission node set can be compared with the data in the ecological environment database, and the impact of the cofferdam construction process on the ecological environment can be judged based on the marked ecological environment pollution standard threshold.

[0074] Embodiment 2:

[0075] Figure 2 The system block diagram of this embodiment is shown. Figure 2 It can be seen that the system of this embodiment includes a database construction unit, a sensor unit, a data processing unit, a warning model unit and an environment monitoring unit.

[0076] Among them, the database construction unit is configured to collect historical hydrological data and geological data of the construction site, construct a hydrological-geological database, and clean and mark the data in the hydrological-geological database to obtain risk factors in the cofferdam construction process, and mark the hydrological and geological risk types and safety standard thresholds in the hydrological-geological database according to the risk factors, and send the risk factors to the sensor unit at the same time.

[0077] The sensor unit is connected to the database construction unit and is configured to determine the key parameters that need to be monitored according to the specific type of the cofferdam, the key parameters including water level and flow rate, sedimentation and displacement, stress and deformation, turbidity, vibration and noise, and environmental meteorology, select corresponding sensors to collect data according to the key parameters, and assign unique IDs to sensors when arranging sensors, so that the sensors can include source information in the data while uploading data, which is convenient for subsequent data organization and query, divide the types of sensors, integrate the same type of sensors into a convergence node, and multiple sensors of the same type correspond to one convergence node to avoid each individual sensor being directly connected to the background system. The data collected by multiple sensors of the same type are uniformly uploaded to the corresponding convergence node, and all these convergence nodes are integrated into a network transmission node set, which collects the data sent by the convergence node, pre-processes the received data, and compresses the pre-processed data and sends it to the data processing unit.

[0078] The data processing unit is connected with the sensor unit and the database construction unit and is configured as follows: the data processing center constructs a sensor database according to the type of sensor; after receiving the compressed data sent by the network transmission node set, the data center first decompresses the data, and then stores it in the sensor database according to the type of data; the data in the sensor database is compared with the data in the hydrological-geological database to obtain the weight coefficients of different sensor data; a step-by-step screening mechanism for cofferdam construction early warning conditions is constructed based on the weight coefficients and risk factors of the different sensor data; the screened construction early warning evaluation parameters are quantitatively superimposed to obtain a cofferdam construction early warning model; the general formula of the cofferdam construction early warning model is:

[0079] y=α0+α1x1 +α2x2+α3x3……+α i x i +λ,

[0080] Among them, y is the construction early warning evaluation parameter, x1 is the first hydrological-geological risk factor of construction early warning; x2 is the second hydrological-geological risk factor of construction early warning; x i is the i-th hydrological-geological risk factor for construction warning; α0 is the weight coefficient of the first type of sensor data, α1 is the weight coefficient of the second type of sensor data, α2 is the weight coefficient of the third type of sensor data, and α i is the weight coefficient of the i+1th class sensor data, and λ is the random error parameter.

[0081] The early warning model unit is connected to the data processing unit and is configured to perform real-time risk identification on the cofferdam construction process based on the constructed cofferdam construction early warning model in combination with the data in the sensor database, and finally obtain the probability of risk occurrence of the risk characterization parameter model, and issue an early warning based on the probability of risk occurrence.

[0082] The environmental monitoring unit is configured to collect environmental and ecological data, build an ecological environment database, mark the corresponding ecological environment pollution standard thresholds, compare the data sent by the sensor unit with the data in the ecological environment database, and judge the impact of the cofferdam construction process on the ecological environment based on the marked ecological environment pollution standard thresholds.

[0083] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. An intelligent monitoring and early warning method for the cofferdam construction process, characterized in that: The intelligent monitoring and early warning method comprises: S100, collecting historical hydrological data and geological data of the construction site, constructing a hydrological-geological database, and cleaning and marking the data in the hydrological-geological database to obtain risk factors in the cofferdam construction process, According to the risk factors, the risk types and safety standard thresholds of hydrology and geology are marked in the hydrology-geology database, and the risk factors are sent to a set of network transmission nodes at the construction site; S200, determining the key parameters that need to be monitored according to the specific type of the cofferdam, wherein the key parameters include water level and flow velocity, sedimentation and displacement, stress and deformation, turbidity, vibration and noise, and environmental weather. According to the key parameters, corresponding sensors are selected to collect data, and unique IDs are assigned to sensors when they are arranged, so that the sensors can include source information in the data while uploading data, which is convenient for subsequent data organization and query. Classify the types of sensors, integrate sensors of the same type into one aggregation node, and multiple sensors of the same type correspond to one aggregation node to avoid each individual sensor being directly connected to the background system. The data collected by multiple sensors of the same type are uniformly uploaded to the corresponding aggregation node, and all these aggregation nodes are integrated into a network transmission node set. The network transmission node set collects the data sent by the aggregation node, pre-processes the received data, and compresses the pre-processed data and sends it to the data processing center; S300, the data processing center builds a sensor database according to the types of sensors. After receiving the compressed data sent by the network transmission node set, the data center first decompresses the data and then stores it in the sensor database according to the type of data. The data in the sensor database are compared with the data in the hydrological-geological database to obtain the weight coefficients of different sensor data. Based on the weight coefficients and risk factors of the different sensor data, a step-by-step screening mechanism for cofferdam construction early warning conditions is constructed. The screened construction early warning evaluation parameters are quantitatively superimposed to obtain a cofferdam construction early warning model. The general formula of the cofferdam construction early warning model is: y=α0+α1x1 +α2x2+α3x3……+α i x i +λ, Among them, y is the construction early warning evaluation parameter, x1 is the first hydrological-geological risk factor of construction early warning; x2 is the second hydrological-geological risk factor of construction early warning; x i is the i-th hydrological-geological risk factor for construction warning; α0 is the weight coefficient of the first type of sensor data, α1 is the weight coefficient of the second type of sensor data, α2 is the weight coefficient of the third type of sensor data, and α i is the weight coefficient of the i+1th class sensor data, and λ is the random error parameter; S400, based on the constructed early warning model for cofferdam construction, real-time risk identification is performed on the cofferdam construction process in combination with the data in the sensor database, and finally the probability of risk occurrence of the risk characterization parameter model is obtained, and an early warning is issued according to the probability of risk occurrence.

2. The intelligent monitoring and early warning method for the cofferdam construction process according to claim 1 is characterized in that: The intelligent monitoring and early warning method also includes collecting environmental and ecological data, constructing an ecological environment database, marking the corresponding ecological environment pollution standard thresholds, comparing the data sent by the network transmission node set with the data in the ecological environment database, and judging the impact of the cofferdam construction process on the ecological environment based on the marked ecological environment pollution standard thresholds.

3. The intelligent monitoring and early warning method for the cofferdam construction process according to claim 1 is characterized in that: The cleaning mark comprises the following sub-steps: S110, obtaining corresponding construction requirements according to the specific type of cofferdam, combining the data in the hydrological-geological database, summarizing the influence relationship of hydrological-geological structure on cofferdam construction, and obtaining the main control factors of the influence relationship, and establishing a comprehensive evaluation index system for cofferdam construction conditions according to the influence relationship and the main control factors; S120. According to the comprehensive evaluation index system for cofferdam construction conditions, different weights are assigned according to the magnitude of the impact, different hydrological and geological characteristics are divided into different tier combinations according to their impact on the cofferdam construction conditions, and the total risk value of each tier combination is calculated.

4. The intelligent monitoring and early warning method for the cofferdam construction process according to claim 3 is characterized in that: The method of dividing different tier combinations and calculating the total risk value of each tier combination includes: According to the data in the hydrological-geological database, mark the influence of different hydrological factors and geological factors in the database on the cofferdam construction conditions, obtain the influencing factors, and assign corresponding weights to the influencing factors; According to the influence degree of each hydrological and geological feature on the cofferdam construction and the assigned weight, the different combinations of hydrology and geology are divided into multiple levels.

5. The intelligent monitoring and early warning method for the cofferdam construction process according to claim 4 is characterized in that: The division into multiple levels includes the following division steps: S121, determining the impact level of the impact factor according to the distribution of data in the hydrological-geological database, and dividing it into three impact levels, namely high impact, medium impact and low impact; S122. Constructing a tiered combination according to the impact level, and classifying the impact factors with different weights into three tiers, namely, a high-risk tier, a medium-risk tier, and a low-risk tier; S123. Calculate the total risk value of each tier combination based on the weights assigned to the influencing factors.

6. The intelligent monitoring and early warning method for the cofferdam construction process according to claim 1 is characterized in that: The pretreatment includes: S210, checking whether there are duplicate records in the data according to the sensor ID, deleting the duplicate data, and using Kalman filtering to filter out irrelevant noise and interference signals in the data; S220, using the standard deviation algorithm for the data of different sink nodes to determine whether the sent data conforms to the normal distribution, determining the data beyond the normal range as an outlier, and removing the identified outliers; S230, then screen the data according to the risk factors and key monitored parameters to obtain pre-processed data.

7. An intelligent monitoring and early warning system for the cofferdam construction process, characterized in that: The intelligent monitoring and early warning system includes a database construction unit, a sensor unit, a data processing unit and an early warning model unit, wherein: The database construction unit is configured to collect historical hydrological data and geological data of the construction site, construct a hydrological-geological database, clean and mark the data in the hydrological-geological database, and obtain risk factors in the cofferdam construction process. Marking the risk types and safety standard thresholds of hydrology and geology in the hydrology-geology database according to the risk factors, and sending the risk factors to the sensor unit; The sensor unit is connected to the database building unit and is configured to determine the key parameters that need to be monitored according to the specific type of the cofferdam, and the key parameters include water level and flow rate, sedimentation and displacement, stress and deformation, turbidity, vibration and noise, and environmental meteorology. According to the key parameters, corresponding sensors are selected to collect data, and unique IDs are assigned to sensors when they are arranged, so that the sensors can include source information in the data while uploading data, which is convenient for subsequent data organization and query. Classify the types of sensors, integrate sensors of the same type into one aggregation node, and multiple sensors of the same type correspond to one aggregation node to avoid each individual sensor being directly connected to the background system. The data collected by multiple sensors of the same type are uniformly uploaded to the corresponding aggregation node, and all these aggregation nodes are integrated into a network transmission node set. The network transmission node set collects the data sent by the aggregation node, pre-processes the received data, and compresses the pre-processed data and sends it to the data processing unit; The data processing unit is connected to the sensor unit and the database construction unit and is configured such that the data processing center constructs a sensor database according to the type of sensor. After receiving the compressed data sent by the network transmission node set, the data center first decompresses the data and then stores it in the sensor database according to the type of data. The data in the sensor database are compared with the data in the hydrological-geological database to obtain the weight coefficients of different sensor data. Based on the weight coefficients and risk factors of the different sensor data, a step-by-step screening mechanism for cofferdam construction early warning conditions is constructed. The screened construction early warning evaluation parameters are quantitatively superimposed to obtain a cofferdam construction early warning model. The general formula of the cofferdam construction early warning model is: y=α0+α1x1 +α2x2+α3x3……+α i x i +λ, Among them, y is the construction early warning evaluation parameter, x1 is the first hydrological-geological risk factor of construction early warning; x2 is the second hydrological-geological risk factor of construction early warning; x i is the i-th hydrological-geological risk factor for construction warning; α0 is the weight coefficient of the first type of sensor data, α1 is the weight coefficient of the second type of sensor data, α2 is the weight coefficient of the third type of sensor data, and α i is the weight coefficient of the i+1th class sensor data, and λ is the random error parameter; The early warning model unit is connected to the data processing unit and is configured to perform real-time risk identification on the cofferdam construction process based on the constructed cofferdam construction early warning model in combination with the data in the sensor database, and finally obtain the probability of risk occurrence of the risk characterization parameter model, and issue an early warning based on the probability of risk occurrence.

8. The intelligent monitoring and early warning system for the cofferdam construction process according to claim 7 is characterized in that: The intelligent monitoring and early warning system also includes an environmental monitoring unit, which is configured to collect environmental and ecological data, build an ecological environment database, mark the corresponding ecological environment pollution standard thresholds, compare the data sent by the sensor unit with the data in the ecological environment database, and judge the impact of the cofferdam construction process on the ecological environment based on the marked ecological environment pollution standard thresholds.

Images