Beidou system combining water level, osmotic pressure and displacement monitoring

Abstract

The invention relates to the technical field of monitoring, and discloses a Beidou system combining water level, osmotic pressure and displacement monitoring, and the system comprises a water level monitoring module which employs a high-precision radar water level gauge, measures the surface position of a water body according to an electromagnetic wave reflection signal, and eliminates the influence of climate factors; the osmotic pressure monitoring module is used for obtaining osmotic pressure data by measuring optical fiber reflection wavelength or resistance change by adopting a mode of combining an optical fiber grating sensor and an MEMS (Micro Electro Mechanical System) sensor; and the displacement monitoring module is combined with a high-precision GPS and Beidou positioning system and laser scanning and fiber grating technologies to monitor the displacement of the target area in real time. Through combination of water level, osmotic pressure and displacement monitoring data, comprehensive multi-dimensional monitoring is provided, data accuracy and reliability are improved, a Beidou positioning system is integrated, high-precision space matching of the monitoring data is ensured, and data timeliness and positioning accuracy are enhanced.

Description

Technical Field

[0001] The present invention relates to the technical field of monitoring, and specifically to a Beidou system combining water level, seepage pressure, and displacement monitoring. Background Art

[0002] With the continuous development of the engineering construction field, especially the increasing complexity and scale of infrastructure such as water conservancy, hydropower, and transportation, monitoring and safety management have become important means to ensure the stable operation of projects. Currently, for the safety monitoring of engineering facilities, common technical means include water level monitoring, seepage pressure monitoring, and displacement monitoring. These technologies rely on different types of sensors for data collection, use single or distributed monitoring systems, and combine traditional analysis methods for data processing and evaluation, which are widely used in the safety detection of structures such as dams, tunnels, and bridges. However, the existing technologies have certain limitations when facing diversified monitoring requirements, especially in aspects such as data fusion, positioning accuracy, and intelligent early warning, and there is still room for improvement.

[0003] The existing monitoring systems use a single sensor to monitor water level, seepage pressure, or displacement, lacking the collaborative work of multiple sensors, resulting in lower accuracy and reliability of monitoring results. In addition, traditional systems often rely on manual analysis and judgment after data collection, lacking an effective real-time early warning mechanism and being unable to make timely responses before potential risks occur. Although some systems attempt to combine positioning technologies, their accuracy and adaptability still need to be improved. Summary of the Invention

[0004] Aiming at the deficiencies of the existing technologies, the present invention provides a Beidou system combining water level, seepage pressure, and displacement monitoring, which solves the problems that a single monitoring method in the existing technologies cannot comprehensively and accurately evaluate the safety risks of engineering facilities and lacks a high-precision positioning and intelligent early warning mechanism.

[0005] To achieve the above purposes, the present invention is realized through the following technical solutions: A Beidou system combining water level, seepage pressure, and displacement monitoring, comprising: A water level monitoring module, using a high-precision radar water level gauge, capable of measuring the water surface position according to the electromagnetic wave reflection signal and eliminating the influence of climate factors; A seepage pressure monitoring module, adopting a combination of fiber Bragg grating sensors and MEMS sensors, and obtaining seepage pressure data by measuring the change in fiber reflection wavelength or resistance; A displacement monitoring module, combining high-precision GPS and Beidou positioning systems, as well as laser scanning and fiber Bragg grating technologies, to monitor the displacement of the target area in real time; A data collection and transmission module, transmitting the data of each monitoring module to the data processing center through wireless communication; The data processing and fusion module uses Kalman filtering and particle filtering algorithms to fuse and optimize water level, seepage pressure, and displacement data to improve data accuracy; The Beidou positioning module provides high-precision displacement positioning data through the Beidou satellite system; The intelligent early warning module performs real-time analysis and pattern recognition on data based on machine learning algorithms and automatically triggers an early warning when potential risks occur; The user interface and monitoring platform provide real-time visual display of water level, seepage pressure, and displacement data and the function of historical data retrieval.

[0006] Preferably, the radar water level gauge of the water level monitoring module uses frequency-modulated continuous-wave radar technology, which can accurately calculate the water level by measuring the frequency change of the electromagnetic wave reflection signal and eliminate the interference of environmental factors.

[0007] Preferably, the fiber Bragg grating sensor of the seepage pressure monitoring module is based on the Bragg grating principle, measures the seepage pressure through the wavelength change of the fiber reflected light, and the MEMS sensor responds to the seepage pressure change through the piezoelectric effect to provide high-precision seepage pressure data.

[0008] Preferably, in the data processing and fusion module, the Kalman filtering algorithm is used for real-time dynamic compensation and estimation of water level, seepage pressure, and displacement data, and the particle filtering algorithm is used to process non-linear and non-Gaussian data, thereby improving the accuracy and stability of data fusion. The Kalman filtering algorithm performs dynamic estimation through the following formula: where, is the state estimate, is the Kalman gain, is the observation value, is the observation matrix.

[0009] Preferably, the intelligent early warning module performs data pattern recognition through machine learning algorithms, uses supervised learning algorithms to train the monitoring data, and performs risk prediction and analysis based on real-time data. If the predicted risk exceeds the set threshold, the early warning mechanism is triggered.

[0010] Preferably, the laser scanning technology in the displacement monitoring module combines high-precision GPS and the Beidou positioning system, and uses the optical measurement principle to accurately calculate the displacement of the dam and levee structures with an accuracy reaching the millimeter level. The displacement calculation is carried out through the following formula: where, is the displacement, is the coordinate at the current moment, is the coordinate at the initial moment.

[0011] Preferably, the data acquisition and transmission module adopts wireless communication technologies, including but not limited to LoRa, ZigBee or 5G network, which can ensure the stability and real-time performance of large-scale and high-density data transmission.

[0012] Preferably, the data processing and fusion module uses multi-modal data fusion technology to combine multiple data sources of water level, seepage pressure and displacement sensors, and adopts weighted average or Bayesian estimation method for data fusion to further improve the overall accuracy and stability of the monitoring system. The data fusion formula is: Wherein, is the fused data result, is the weight of each data source, is the observation value provided by each sensor data source.

[0013] Preferably, the early warning trigger mechanism in the intelligent early warning module includes but not limited to threshold method, anomaly detection method and early warning method based on trend analysis, which can monitor in real time and early warn of potential risks of sudden hydrological disasters and dam deformation.

[0014] Preferably, the user interface and the monitoring platform provide real-time data display, historical data playback and risk early warning information through a visual graphic interface, and can generate data reports according to the monitoring data for users to refer to for decision-making.

[0015] The present invention provides a Beidou system combining water level, seepage pressure and displacement monitoring, which has the following beneficial effects: 1. By combining three types of monitoring data of water level, seepage pressure and displacement, the present invention can comprehensively monitor the safety status of engineering facilities. Through the collaborative work of multiple sensors, the system can simultaneously obtain multiple key parameters at different monitoring points and perform data fusion processing. This multi-dimensional monitoring method enables the system to provide more accurate and comprehensive evaluations in the face of complex environmental changes. Compared with traditional single monitoring methods, the present invention can more effectively identify potential risks and avoid missing some dangerous signals, thus improving the safety guarantee level of engineering facilities.

[0016] 2. By integrating the Beidou positioning system and combining high-precision position information for real-time data acquisition and processing, the present invention ensures that the data of each monitoring point can be accurately associated with specific geographical locations. This makes the monitoring data not only timely, but also accurately positioned in space, facilitating comparative analysis and comprehensive evaluation of the monitoring data at different locations. High-precision positioning and data matching can help engineering managers discover potential hazards in time and make corresponding adjustments, greatly improving the system's response ability to spatial distribution and abnormal changes.

[0017] 3. Through the intelligent warning module, by combining real-time monitoring data with historical data, and using a variety of intelligent algorithms for risk assessment, through setting appropriate warning thresholds and automated decision-making, the system can issue a warning in a timely manner when detecting potential danger signals, reminding relevant personnel to take emergency measures. The intelligent warning mechanism not only improves the automation level of the system, reduces the need for manual intervention, but also can take preventive measures before a disaster occurs to avoid or mitigate potential hazards, thereby enhancing the overall safety and risk resistance ability of the engineering project. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 It is the system architecture diagram of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0019] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the drawings in the specification of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without making creative efforts shall fall within the protection scope of the present invention.

[0020] Embodiment: Please refer to the attached Figure 1 The embodiment of the present invention provides a Beidou system combining water level, seepage pressure and displacement monitoring, including: A water level monitoring module, using a high-precision radar water level gauge, which can measure the position of the water surface according to the electromagnetic wave reflection signal and eliminate the influence of climate factors; In this embodiment, the water level monitoring module emits radar waves of a specific frequency and receives the electromagnetic wave signal reflected from the water surface, calculates the frequency difference of the reflected wave, and thus estimates the distance between the water surface and the radar sensor. Specifically, the radar sensor adopts frequency-modulated continuous wave (FMCW) technology, and through the frequency modulation of the electromagnetic wave, accurately measures the frequency difference between the reflected wave and the transmitted wave.

[0021] It should be noted that the basic formula of the FMCW radar principle is: Wherein, represents the distance from the water surface to the sensor, is the frequency difference between the received reflected wave and the transmitted wave, is the propagation speed of light in the air, and is the basic frequency emitted by the radar.

[0022] Specifically, by measuring the difference between the reflected wave frequency and the transmitted frequency in real time, the water level monitoring module can calculate the exact distance between the water surface and the radar sensor, thereby obtaining water level information. This measurement method can avoid the influence of environmental factors such as light, temperature, humidity, rain, and snow, and has significant advantages compared with traditional buoy type or pressure type water level gauges.

[0023] In the application of water level monitoring in reservoirs or dams, the FMCW radar water level gauge can monitor the water level changes in real time without contact, avoiding problems such as corrosion and wear caused by the direct contact of the water level gauge sensor with the water body. Due to its high precision and anti-interference ability, the FMCW radar water level gauge can effectively support large-scale water level monitoring systems.

[0024] The radar water level gauge described in this embodiment can be equipped with various types of sensors, such as temperature and humidity sensors, to further enhance the system's adaptability to environmental changes. For example, changes in temperature and humidity will affect the propagation speed of radar waves, thereby affecting the accuracy of water level measurement. Therefore, through additional environmental sensor monitoring, the system can perform real-time compensation and correction to further improve the measurement accuracy.

[0025] The operating frequency of the radar water level gauge can be adjusted according to the specific conditions of the water area. For example, lower frequency radar waves are used in shallow water areas to enhance the penetration ability; while in deep water areas, higher frequency radar waves can be used to improve the resolution. This flexible frequency adjustment mechanism enables the radar water level gauge to adapt to different water areas and application scenarios.

[0026] The water level monitoring module is not limited to the monitoring of large water bodies such as reservoirs and rivers, but can also be widely applied to scenarios such as urban drainage systems, ocean monitoring, and flood warning. For example, in urban drainage systems, the water level monitoring module can detect the water accumulation height in pipelines in real time. When the water accumulation reaches the set threshold, the system can automatically trigger the warning mechanism, thereby taking disaster prevention and mitigation measures in advance.

[0027] The installation of the radar water level gauge does not depend on the contact point of the water surface, making it highly flexible and reliable. When long-term monitoring or use in harsh environments is required, the radar water level gauge can maintain its stability and accuracy, avoiding errors caused by long-term immersion or sediment accumulation of traditional contact type water level gauges.

[0028] To further enhance the robustness of the system, various types of sensors can be integrated on the basis of the radar water level gauge. For example, combining the radar water level gauge with fiber optic sensors, laser sensors, etc. can not only provide water level information, but also detect parameters such as water flow velocity, temperature, and sediment thickness at the same time, thereby providing more auxiliary information for the system and supporting more accurate disaster warning and risk assessment.

[0029] Combining the measurement data of different sensors, the data processing and fusion module can optimize the water level information using the weighted average method or the Kalman filtering method, thereby reducing errors and improving the reliability of the system. Especially in complex environments, such as in the presence of strong winds or precipitation, the data fusion algorithm can significantly enhance the stability and accuracy of water level measurement.

[0030] In practical applications, the water level monitoring in some areas may be affected by large wind speeds and drastic climate changes, resulting in unstable measurement data of a single sensor. In such cases, through multi-sensor fusion, these external interferences can be effectively eliminated, thus ensuring the accuracy and reliability of the water level data.

[0031] To adapt to different requirements in different application scenarios, parameters such as the working frequency, measurement range, and accuracy requirements of the water level monitoring module can be adjusted according to the actual situation. For example, for small water bodies or local monitoring needs, the system can be configured with relatively compact sensors, while for large-scale hydrological monitoring, higher-precision sensors can be used, and through the cooperation of multiple sensors, a wider monitoring area can be covered.

[0032] The water level monitoring module can also be equipped with an automatic calibration function. By regularly self-calibrating, the accuracy of the measurement results can be ensured. Automatic calibration can be achieved by comparing the sensor with a known standard water level point, or by compensating for external factors using environmental sensors to further improve the measurement accuracy of the system.

[0033] In summary, the water level monitoring module in this embodiment adopts advanced FMCW radar technology. Through a high-precision frequency modulation measurement method, it can achieve high-precision monitoring of the water level and is not affected by environmental changes. In addition, the system can combine multiple sensor data for fusion and optimization, thereby further improving the measurement accuracy and reliability, and is widely used in water conservancy facilities, disaster warning and other fields. The seepage pressure monitoring module adopts a combination of fiber Bragg grating sensors and MEMS sensors, and obtains seepage pressure data by measuring the reflection wavelength of the optical fiber or the change in resistance. In this embodiment, the core technology of the seepage pressure monitoring module is based on the collaborative work of fiber Bragg grating sensors and MEMS sensors. The fiber Bragg grating sensor senses the change in pressure by detecting the wavelength change of the Bragg grating in the optical fiber, while the MEMS sensor measures the seepage pressure through the response of the micro-sensor to the piezoelectric effect. The combined use of the two sensors can achieve high-precision and real-time monitoring of the seepage pressure.

[0034] The fiber Bragg grating sensor utilizes the characteristic that the reflection light wavelength is linearly related to the pressure received by the sensor, and can accurately reflect the pressure change. The reflection light wavelength in the fiber Bragg grating changes with the pressure change. Therefore, the seepage pressure can be calculated through the wavelength shift.

[0035] It should be noted that the working principle of the fiber Bragg grating sensor is as follows: Among them, is the osmotic pressure, is the wavelength change of the fiber Bragg grating, is the initial wavelength of the optical fiber, is the sensitivity coefficient of the sensor. This formula indicates that the change in osmotic pressure will cause the wavelength of the fiber Bragg grating to change, and then the pressure value can be deduced by calculating the wavelength change.

[0036] In the dam monitoring, by arranging multiple fiber Bragg grating sensors in the soil at different depths, the change of osmotic pressure can be measured in real time, so as to judge the water flow state and possible leakage situation in the soil.

[0037] MEMS sensors can also be used for the detection of osmotic pressure. Based on the piezoelectric effect of micro sensors, MEMS sensors can cause the deformation of the sensor through the action of pressure, and then cause the change of resistance. By measuring the change of resistance, the osmotic pressure can be calculated.

[0038] MEMS sensors can be arranged at different positions in the soil, and the sensor signals can be transmitted to the data acquisition system through cables. Combining MEMS sensors with fiber Bragg grating sensors can provide more comprehensive and accurate seepage pressure data, enhancing the accuracy and reliability of monitoring.

[0039] The seepage pressure monitoring module can work for a long time in harsh environments, avoiding the damage or performance degradation of traditional sensors due to environmental changes, chemical corrosion and other problems. In special environments such as dams or tunnels, the real-time monitoring of osmotic pressure can effectively identify potential structural problems in advance.

[0040] This module has high adaptability and scalability. For different types of soils or structures, the configuration and quantity of fiber Bragg grating sensors and MEMS sensors can be adjusted according to specific monitoring requirements. For example, in areas with drastic water level changes, the system can enhance the accuracy of osmotic pressure monitoring by increasing the number of sensors and the measurement depth.

[0041] In order to improve the accuracy of osmotic pressure data, the seepage pressure monitoring module in this embodiment can also be equipped with temperature and humidity sensors to compensate for the influence of environmental factors such as temperature and humidity on the sensor performance. Since temperature changes will cause the shift of the fiber Bragg grating wavelength, therefore, by monitoring the temperature in real time and performing data compensation, the measurement accuracy can be further improved.

[0042] The wavelength change of the fiber Bragg grating sensor is affected not only by the pressure change but also by the temperature change. Therefore, in this embodiment, a temperature compensation technique is adopted. Combining the temperature data obtained by the temperature and humidity sensor, the osmotic pressure is corrected using the known relationship between temperature and wavelength change. The specific correction formula is: Where, is the osmotic pressure after temperature correction, is the osmotic pressure without temperature compensation, is the correction value of the osmotic pressure caused by the temperature change.

[0043] In tunnel construction monitoring, due to the possible influence of the underground temperature fluctuation on the sensor, the temperature compensation algorithm can effectively eliminate the interference of the temperature change on the measurement result of the osmotic pressure.

[0044] The data acquisition system of the osmotic pressure monitoring module can wirelessly transmit the data of the fiber Bragg grating sensor and the MEMS sensor to the cloud platform for processing and storage. This platform can perform real-time analysis on the collected data, judge the stability of the soil mass and issue early warnings in a timely manner. This function is of great significance for application scenarios such as disaster early warning and dam safety monitoring.

[0045] The sensors in the osmotic pressure monitoring module can select the installation location and depth according to the actual application requirements. For example, in the monitoring of the reservoir dam body, the sensors can be arranged at different depths along the dam body to comprehensively monitor the osmotic pressure at different levels inside the dam; while in tunnel monitoring, the sensors can be arranged on the tunnel wall and bottom to monitor the osmotic pressure of the soil around the tunnel.

[0046] Combining the high-precision measurement of the sensor and the data fusion algorithm, the osmotic pressure monitoring module can accurately capture the change of the osmotic pressure in the soil mass and provide timely alarms through the data processing and warning system to prevent the structure from becoming unstable or getting into danger.

[0047] In practical applications, the monitoring of the osmotic pressure can provide a scientific basis for the safety management of projects such as dams and reservoirs. When the osmotic pressure exceeds the set threshold, the system will trigger an early warning and transmit the information to the relevant personnel in a timely manner, providing decision-making support for the safety management of the structure.

[0048] In summary, the osmotic pressure monitoring module in this embodiment combines fiber Bragg grating sensors and MEMS sensor technologies. By measuring the osmotic pressure in the soil in real time, it can provide high-precision and real-time osmotic pressure data. In the monitoring of key facilities such as dams, reservoirs, and tunnels, the osmotic pressure monitoring module can promptly detect potential risks and prevent disasters from occurring, having broad application prospects. At the same time, through temperature and humidity compensation technologies, data fusion, and intelligent warning systems, the stability and accuracy of the system are further enhanced, meeting the monitoring requirements in complex environments. The displacement monitoring module combines high-precision GPS and Beidou positioning systems, as well as laser scanning and fiber Bragg grating technologies to monitor the displacement of the target area in real time; In this embodiment, the core technologies of the displacement monitoring module are based on the fiber optic interference principle and laser scanning technology. Fiber optic interference sensors can accurately measure the change in optical path caused by displacement changes by utilizing the interference effect of optical fibers, while laser scanning technology obtains the displacement information of the target in real time by emitting laser beams and measuring the return time. By combining the two technologies, the accuracy and reliability of displacement monitoring can be further improved.

[0049] The fiber optic interference sensor is based on the Mach-Zehnder interference principle. This principle indicates that when the light beam in the optical fiber changes the optical path due to displacement changes, the change in interference light intensity can reflect the magnitude of the displacement. In this embodiment, the fiber optic interference sensor obtains the displacement value of the target by measuring the change in interference light intensity and combining specific calculation formulas.

[0050] The measurement formula of the fiber optic interference sensor is as follows: where, represents the displacement change amount, is the optical wavelength, is the change amount of interference light intensity, is the initial light intensity. This formula illustrates the relationship between the change in the optical path of the optical fiber and the displacement. Thus, the specific displacement amount can be calculated.

[0051] In dam monitoring, by burying fiber optic sensors inside the dam structure, it is possible to monitor in real time whether the dam body has displacement. If the displacement exceeds the safety threshold, the system can immediately trigger an alarm to prevent potential disasters from occurring. Compared with traditional potentiometer sensors, fiber optic interference sensors have higher accuracy and electromagnetic interference resistance capabilities, and are suitable for long-term monitoring in harsh environments.

[0052] In some applications with high-precision requirements, the method of combining laser scanning technology with fiber optic interferometric sensors can be adopted to further improve the accuracy and reliability of monitoring. The laser scanner can accurately measure the distance and displacement of the target by emitting a laser beam and receiving the reflected signal. This technology can provide a larger range of displacement monitoring and is particularly suitable for the dynamic monitoring of large-scale structures or sites.

[0053] Laser scanning technology can obtain detailed displacement information on the target surface through multi-angle scanning and transmit this data to the data processing platform in real time. Through the comprehensive analysis of multi-point data, the system can effectively judge the displacement trend and generate a displacement change diagram to provide data support for engineering safety decision-making.

[0054] The displacement monitoring module can flexibly configure the number and layout of sensors according to the actual application requirements. For example, in dam monitoring, sensors can be arranged at different depths and positions of the dam body to comprehensively monitor the displacement of the dam body; in tunnel monitoring, the laser scanner can accurately judge the stability of the structure by scanning the displacement of the tunnel wall. This module can not only monitor static displacement but also capture dynamic displacement changes in real time to provide early warnings for sudden risks.

[0055] The working principle of the fiber optic interferometric displacement sensor has very strong adaptability to the environment. For example, it is not affected by electromagnetic interference and temperature changes, so it is particularly suitable for places with high requirements for the electromagnetic environment such as electrical equipment and communication systems. At the same time, laser scanning technology can perform high-precision measurements over a long distance, so it has great advantages for large-scale monitoring scenarios such as large bridges and tunnels.

[0056] To further improve the accuracy of displacement monitoring, the displacement monitoring module can compensate for environmental factors such as temperature, humidity, and pressure. Since temperature changes may affect the light speed of the optical fiber, thereby causing measurement errors, the system can install temperature sensors to monitor the environmental temperature in real time and correct the displacement data according to the temperature changes.

[0057] The displacement compensation caused by temperature changes can be achieved through the following formula: where, is the corrected displacement, is the uncorrected measured value, is the temperature expansion coefficient of the optical fiber, is the temperature change, is the initial optical path length. Through this formula, the displacement measurement error caused by temperature changes can be corrected, thereby improving the measurement accuracy.

[0058] In a high-temperature environment, the change in the optical path of the optical fiber may lead to displacement measurement errors. By real-time temperature monitoring and compensation, the errors can be effectively reduced and the accuracy of displacement data can be improved.

[0059] The displacement monitoring module can also adopt wireless transmission technology to transmit sensor data to the central data acquisition platform in real time. Through wireless transmission, the complexity brought by wiring can be avoided, and the installation and maintenance of the system can be simplified. This platform can process the collected data in real time and conduct prediction and trend analysis in combination with machine learning algorithms, so as to provide timely and effective decision-making support for the safety management of the project.

[0060] This module can be linked with other monitoring systems. For example, modules such as water level monitoring and seepage pressure monitoring can form an integrated monitoring system together with the displacement monitoring module to conduct comprehensive safety monitoring on structures such as dams and tunnels. Through data fusion and analysis among various modules, multi-dimensional monitoring and early warning can be achieved to ensure project safety.

[0061] The displacement monitoring module is not limited to the monitoring of static displacement, but can also capture the displacement changes of the structure under dynamic loads in real time. For example, under dynamic actions such as earthquakes and wind loads, the displacement monitoring module can quickly capture the displacement changes of the structure and provide immediate feedback, effectively improving the response ability of the system.

[0062] In summary, the displacement monitoring module in this embodiment combines fiber optic interferometry and laser scanning technology, and provides real-time and safe displacement monitoring for projects such as water conservancy, tunnels, and dams through high-precision displacement measurement. The system can further improve the monitoring accuracy and stability through technical means such as temperature compensation and data fusion. The displacement monitoring module is not only suitable for static monitoring, but can also effectively cope with dynamic changes and complex environments, and is widely used in fields such as disaster warning and safety monitoring, with important practical significance and application prospects. The data acquisition and transmission module transmits the data of each monitoring module to the data processing center through wireless communication; In this embodiment, the data acquisition and transmission module consists of multiple core components, including a sensor signal acquisition unit, a data processing unit, a wireless transmission unit, and a power management unit. Through the collaborative work of these modules, efficient and stable acquisition and transmission of various sensor data are realized.

[0063] The data acquisition unit is responsible for reading data from sensors such as water level, osmotic pressure, and displacement. For fiber Bragg grating sensors (FBG), MEMS sensors, laser scanning sensors, etc., the data acquisition unit obtains the raw data from the sensors through corresponding interface protocols (such as I2C, SPI, CAN, etc.). The acquisition unit uses a high-precision analog-to-digital converter (ADC) to digitize the analog signals output by the sensors and convert them into digital signals for subsequent analysis.

[0064] During the data acquisition process, for different types of sensors, the acquisition unit needs to adapt through different signal processing methods. For example, for fiber Bragg grating sensors, the acquisition unit will use a wavelength demodulation algorithm to extract the change in the reflected light wavelength in the optical fiber, thereby obtaining data on displacement, pressure, or temperature changes; for MEMS sensors, the osmotic pressure and other data will be obtained by precisely calculating the change in the resistance output by the sensors.

[0065] To further improve the accuracy and stability of data acquisition, the data acquisition unit can integrate digital filtering technology to reduce the interference of environmental noise on the acquired signals. By setting appropriate filter parameters, the acquisition unit can effectively remove high-frequency noise or periodic interference, thereby improving the accuracy and reliability of the data.

[0066] The data acquisition unit can also dynamically adjust the sampling frequency according to the acquisition time interval. For example, in a monitoring scenario where the osmotic pressure is relatively stable, the sampling frequency can be reduced to save the energy consumption of the system; while in the event of significant displacement or water level fluctuations, the sampling frequency can be appropriately increased to obtain more accurate real-time data.

[0067] For sensors for displacement monitoring, the data acquisition unit can regularly read the sensor data, calculate the corresponding displacement amount, and store the data in a predetermined format. The displacement data collected by the sensors will be based on the displacement amount and, combined with the spatial layout position of the sensors, calculate the overall displacement trend within the monitoring area.

[0068] The collected data not only includes the measured values of the sensors but also can include the status information of the sensors, such as fault information, signal strength, etc. These information helps to detect the operating status of the system and ensure the validity of the data.

[0069] The data transmission unit transmits the collected sensor data to the remote cloud platform in real time through a wireless communication module. In this embodiment, the wireless transmission unit uses low-power wide-area network (LPWAN) technologies such as LoRa, NB-IoT, or 5G technology, and selects a suitable communication method according to different application requirements and on-site environments.

[0070] The wireless transmission unit packages data through a network protocol stack (such as MQTT, CoAP, HTTP, etc.) and sends it to the central control system or cloud platform via a wireless network. This platform can perform real-time analysis and processing on the received data and trigger alarms or automatically adjust monitoring strategies according to the set thresholds.

[0071] To ensure the transmission quality and stability of data, the data transmission unit in this embodiment supports data encryption and redundant transmission mechanisms. For example, the AES encryption algorithm is used to encrypt the data during the transmission process to prevent the data from being tampered with or stolen during transmission. In addition, to avoid the failure of a single communication link affecting the stability of the entire system, the system can set up an alternative transmission link to achieve redundant transmission of data.

[0072] The data transmission module can also interact with the remote platform through two-way communication. Through two-way communication, the remote platform can not only receive sensor data but also send instructions to the device for remote configuration or adjustment. For example, when the system detects abnormal sensor data, the platform can send instructions to the data acquisition module to resample or adjust the sampling interval to ensure the accuracy of the data.

[0073] In a dam monitoring scenario, the data acquisition and transmission module can continuously obtain data on seepage pressure, displacement, and water level changes at various positions of the dam. Through wireless network transmission, this data is transmitted to the cloud platform in real time, and the cloud platform processes it according to the set risk warning mechanism. When the data exceeds the safety threshold, the system can automatically trigger an alarm and send a warning message to the staff.

[0074] The design of the data acquisition and transmission module has strong flexibility and scalability. For example, the system can increase or decrease the number of sensors according to on-site requirements, or expand the coverage of the system by adding more transmission nodes. The communication method of transmission can also be adjusted according to the actual situation to adapt to different types of engineering and environmental requirements.

[0075] To extend the working cycle of the data acquisition and transmission module, the system can also be equipped with an efficient energy management module, using solar energy or other renewable energy to power the device. In addition, the data acquisition and transmission module can also optimize power consumption management through intelligent scheduling technology, reduce the system energy consumption, and thus improve the overall energy use efficiency of the system.

[0076] The wireless communication method adopted by the data acquisition and transmission module can effectively adapt to the complex communication environment in different application scenarios. For example, in the monitoring of underground structures, there may be signal occlusion or weak signal areas. The data transmission unit can ensure stable data transmission even in a communication-limited environment through the optimization of network protocols and signal enhancement technologies.

[0077] In summary, the data acquisition and transmission module in this embodiment can achieve real-time and efficient transmission of sensor data such as water level, seepage pressure, and displacement through precise signal acquisition, flexible wireless communication technology, and an efficient energy management system, providing data support for the entire monitoring system. Through intelligent data processing and remote management, this module not only improves the stability and accuracy of data transmission but also effectively meets the requirements of complex environments and different application scenarios, and is widely applicable to various fields such as structural safety monitoring and disaster warning. The data processing and fusion module uses Kalman filtering and particle filtering algorithms to fuse and optimize water level, seepage pressure, and displacement data to improve data accuracy. In this embodiment, the core technology of the data processing and fusion module is based on data preprocessing, data fusion algorithms, and intelligent analysis models, and processes and comprehensively analyzes the data of multiple monitoring modules through an efficient computing platform. The implementation process of this module mainly includes the following steps: data cleaning and preprocessing, feature extraction and fusion, data analysis and judgment, and result output and visualization.

[0078] During the data acquisition process, the raw data collected by sensors often has problems such as noise, missing values, or outliers. To ensure the accuracy and reliability of the data, the data processing and fusion module first performs data cleaning and preprocessing. The data cleaning process includes removing invalid data, filling in missing values, smoothing noise signals, etc., and specific methods can use filtering algorithms, interpolation methods, or adaptive processing algorithms. For example, in the processing of water level data, if there are occasional abnormal fluctuations in the collected water level data, the system can correct the data through the median filtering algorithm to remove the interference of these outliers on the analysis results.

[0079] Common filtering algorithms used in the data cleaning process include low-pass filtering, high-pass filtering, and Kalman filtering. Kalman filtering is a filtering technology widely used in dynamic systems. By predicting and correcting the system state, it can effectively reduce system noise and improve the smoothness and accuracy of data. For the data of the water level monitoring module, Kalman filtering can compensate for external factors such as temperature and humidity during the processing to further enhance the reliability of the data.

[0080] In the data preprocessing stage, the module can also perform gain control on the collected signals through an adaptive algorithm to adapt to signal strength changes under different environmental conditions. For example, in a low-temperature environment, the sensor signal may be weak, and the system can adaptively increase the signal amplification factor to ensure the collectability and accuracy of the data.

[0081] After data preprocessing, the data processing and fusion module comprehensively processes the data from multiple sensors through feature extraction and fusion algorithms. This process extracts the feature information of different sensors, combines factors such as physical models and engineering experience, and fuses multi-dimensional monitoring data. Through data fusion technology, this module weights and fuses data such as water level, seepage pressure, and displacement to comprehensively evaluate the safety status of the monitored area.

[0082] When performing data fusion, methods such as weighted average method, principal component analysis (PCA), or Kalman filtering can be used to achieve the fusion of multi-source data. For example, the Kalman filter can not only fuse data from multiple sensors such as displacement and seepage pressure, but also take into account the noise characteristics between different data sources, reasonably adjust the weights, and obtain the optimal fusion result. The formula for data fusion is as follows: Among them, is the state estimate value at the current moment, is the state transition matrix, is the control matrix, is the control input, is the Kalman gain, is the measurement value, is the measurement matrix. This formula indicates that through the calculation of the Kalman gain, combined with the system model and observation data, the data of each sensor is fused.

[0083] In dam monitoring, the water level, seepage pressure, and displacement data come from different sensors. Through the data fusion module, the system can reasonably weight various types of data according to factors such as the accuracy of the sensors, the reliability and timeliness of the data, and comprehensively analyze the overall health status of the dam. For example, the combination of water level monitoring data and seepage pressure data can reveal the impact of reservoir water level changes on the seepage pressure of the dam, thereby more accurately evaluating the stability of the dam.

[0084] After data fusion, the data processing and fusion module will also use intelligent analysis algorithms to further analyze and predict the processed data. By establishing an analysis model based on machine learning, the system can model the relationships between different monitoring indicators, thereby predicting future monitoring trends. For example, using algorithms such as support vector machine (SVM), decision tree (DT), or neural network (NN), combined with historical monitoring data, the system can intelligently evaluate the health status of dams or other structures and even give early warnings of possible risks.

[0085] The intelligent analysis of the data processing and fusion module is not limited to traditional statistical analysis methods. It can also identify and predict complex data patterns through cutting-edge technologies such as deep learning. Through algorithms such as deep neural networks (DNN), the system can identify potential complex relationships in multi-dimensional monitoring data, thus achieving more accurate risk assessment. For example, in dam monitoring, the deep learning model can learn historical displacement, seepage pressure, and water level data to predict the safety state of the dam at a future moment and detect potential risk points in advance.

[0086] In practical applications, after data analysis by the data processing and fusion module, the system can not only provide real-time monitoring data but also generate visual reports to help engineering managers understand the monitoring results. The system can also generate safety level assessment reports based on the fusion results of different monitoring modules to provide decision-making support to managers. For example, when the comprehensive assessment of displacement data and seepage pressure data shows that there is a potential landslide risk in the dam, the system can immediately trigger an alarm and recommend corresponding reinforcement measures.

[0087] To further improve the real-time performance of data processing and analysis, the data processing and fusion module in this embodiment can also adopt a distributed computing architecture. In a distributed system, data processing tasks can be assigned to multiple nodes for parallel processing, reducing data processing latency and improving the overall processing capacity and response speed. For example, the data acquisition end, edge computing nodes, and cloud platform can work together to complete the real-time processing of large-scale data.

[0088] To improve the transparency and interpretability of data analysis, the analysis results of the present invention will be displayed through a visualization platform. The platform can display the processed data in the form of charts, curve graphs, heat maps, etc., enabling engineering personnel to clearly understand the health status of the monitoring object. For example, displacement monitoring data can be displayed through a real-time curve graph, and the water level change can be displayed through a heat map at different positions of the entire dam or reservoir to help managers detect problems in a timely manner.

[0089] In summary, the data processing and fusion module in this embodiment integrates and deeply analyzes the data from each monitoring module through efficient data preprocessing, fusion algorithms, and intelligent analysis models. The system can adopt flexible data fusion methods according to the actual situation of sensor data, combined with machine learning and deep learning technologies, to provide more accurate and intelligent decision-making support for engineering managers. These technologies not only improve the accuracy and real-time performance of the system but also enhance its adaptability in complex environments, and are widely applicable to various structural health monitoring and disaster warning systems. The Beidou positioning module provides high-precision displacement positioning data through the Beidou satellite system; In this embodiment, the Beidou positioning module includes a Beidou receiving unit, a position calculation unit, and a data output unit. The Beidou receiving unit is responsible for receiving positioning signals from the Beidou satellite system and transmitting the received signals to the position calculation unit. The position calculation unit processes the satellite signals through a series of calculation methods and algorithms to obtain the real-time coordinate information of the device, and finally transmits this information to the data output unit for further processing and application by the monitoring system.

[0090] The Beidou receiving unit uses a high-precision Beidou navigation receiver, which can receive signals in frequency bands such as L1 and L2 transmitted by the Beidou satellite system. In actual applications, the Beidou receiver performs precise positioning calculations based on the Doppler frequency shift, pseudorange information, etc. of the received satellite signals. Through the signals of at least four satellites, the receiving unit can calculate the three-dimensional position (longitude, latitude, altitude) of the device. The pseudorange measurement formula in this process is: where is the pseudorange, is the speed of light, is the satellite signal emission time, is the reception time, is the measurement error.

[0091] When transmitting data, the Beidou receiving unit performs differential processing on the received signals to improve the positioning accuracy. Differential positioning technology uses a fixed base station (reference station) to reduce errors such as atmospheric delay and multipath effects, thereby obtaining higher-precision positioning information. The differential signal can be transmitted to the user terminal through a ground station or the Internet.

[0092] To further improve the positioning accuracy, the Beidou positioning module can also perform combined positioning in conjunction with an inertial navigation system (INS). In the inertial navigation system, accelerometers and gyroscopes are used to measure the speed and rotation angle of the device in real time, thereby providing high-precision real-time position compensation in a short period of time. By combining inertial navigation with Beidou positioning, the problem of reduced positioning accuracy caused by satellite signal occlusion or weak signal areas can be effectively overcome.

[0093] The position calculation unit optimizes the positioning information through the least squares method or the Kalman filter algorithm based on the received satellite signals and differential data. Through the least squares method, the system can calculate the optimal device position from the observation data of multiple satellites. In addition, the Kalman filter algorithm can perform smoothing processing between multiple measurements to reduce the impact of instantaneous fluctuations on the positioning accuracy. The mathematical formula of the Kalman filter is: where is the state estimate at the current moment, is the Kalman gain, is the observed value at the current moment, is the observation matrix.

[0094] In water conservancy projects, when the Beidou positioning module is integrated into the reservoir dam body monitoring system, the positioning module can provide accurate dam body position coordinates, help the system monitor water level, seepage pressure and displacement data at different positions, and associate with geographical coordinates. By combining the positioning information with the monitoring data, accurate monitoring of each position of the dam body can be achieved, and then a comprehensive assessment of the dam body's health status can be carried out.

[0095] The high-precision positioning ability of the Beidou positioning module is not only of great significance to the data of a single monitoring point, but also can provide spatial correction for multi-point displacement monitoring. When the multi-point monitoring system is distributed at different geographical locations, the position data can help to perform unified coordinate transformation on the data from different monitoring positions, so as to obtain the overall spatial distribution.

[0096] The Beidou positioning module also supports the real-time kinematic positioning function and can update the position coordinates in real time when the device is moving. For example, in the monitoring of bridges or tunnels, the device may need to conduct regular inspections or position adjustments. At this time, the Beidou positioning module can provide the current position in real time and improve the accuracy of position update through differential positioning technology, so as to ensure the accuracy and timeliness of the monitoring data.

[0097] In order to adapt to different application scenarios, the Beidou positioning module can support different positioning accuracy settings. In an environment that requires extremely high positioning accuracy, such as the key monitoring points of a water conservancy dam, the high-precision mode can be enabled to use satellite signals of multiple frequencies and multiple constellations for positioning. In a relatively loose environment, such as ordinary roads or areas with relatively flat terrain, the single-frequency mode or low-precision positioning method can be adopted to reduce the system cost and power consumption.

[0098] In some remote areas or underground spaces and other scenarios where the reception of Beidou satellite signals is poor, the Beidou positioning module in this embodiment can be combined with other auxiliary positioning systems, such as Wi-Fi positioning or positioning technology based on ground base stations, for joint positioning, so as to ensure that the system can still provide relatively accurate position data in a signal-poor environment.

[0099] The Beidou positioning module not only has strong positioning ability, but also can work in coordination with other modules and play a greater role in the system. Through data fusion with monitoring modules such as water level, seepage pressure and displacement, the Beidou positioning module can provide accurate spatial coordinates for each monitoring point, which is of great significance for global monitoring, danger warning and later maintenance in complex engineering projects.

[0100] In summary, the Beidou positioning module in this embodiment can provide precise positioning services for the monitoring system through various means such as high-precision satellite reception technology, differential positioning technology, and inertial navigation technology. By combining with the data processing and analysis module, this positioning module can perform spatial matching with the monitoring data to ensure that the monitoring data of the system has sufficient spatial information and accuracy. The application of this technology can effectively improve the accuracy, real-time performance, and reliability of engineering monitoring, and is widely applicable to the monitoring and safety assessment of infrastructure such as dams, bridges, and tunnels. The intelligent early warning module performs real-time analysis and pattern recognition on the data based on machine learning algorithms, and automatically triggers an early warning when potential risks occur; In this embodiment, the intelligent early warning module includes a data receiving unit, a data processing unit, an early warning decision-making unit, and an early warning output unit. The data receiving unit receives data from the water level monitoring, seepage pressure monitoring, and displacement monitoring modules, and transfers these real-time data to the data processing unit. The data processing unit analyzes the received data, combines information such as historical data and environmental conditions, evaluates the safety status of the current monitoring point, and transfers it to the early warning decision-making unit. The early warning decision-making unit generates an early warning signal according to the set threshold and intelligent algorithm, and finally issues an early warning prompt through the early warning output unit.

[0101] The data processing unit first preprocesses various types of monitoring data received, including operations such as data denoising, interpolation processing, and outlier detection. The preprocessed data will be further compared with historical data to identify potential danger signals. In this process, common data analysis methods such as moving average and Kalman filter are used to remove noise and ensure the accuracy of the data.

[0102] The data processing unit also needs to handle the fusion problem of multi-source data. Especially in a multi-point monitoring environment, data from different monitoring points often have time delays and spatial differences. To improve the accuracy of data fusion, this embodiment adopts a fusion algorithm based on weighted average and least squares method, and obtains a unified safety assessment value by synthesizing multi-point data. This algorithm can be expressed as: where is the comprehensive safety assessment value, is the weight coefficient, is the data value of the

[0103] When making decisions, the early warning decision-making unit can adopt intelligent decision-making algorithms based on machine learning. By introducing training data sets and predefined risk patterns, the system can gradually learn and adjust the threshold settings. Commonly used algorithms include decision trees, support vector machines (SVMs), neural networks, etc. Specifically, the decision tree algorithm generates decision rules based on multiple input monitoring parameters to determine whether to trigger an early warning. For example, when the water level exceeds the set threshold and the seepage pressure reaches a dangerous value, the decision tree may trigger an early warning signal.

[0104] The early warning decision-making unit can combine physical models and statistical models for multi-level risk analysis. The physical model predicts the risk change trend of the monitoring point in a future period based on factors such as historical data and meteorological conditions. The statistical model predicts the probability of dangerous events occurring through statistical analysis of historical data. Combining the results of both can provide more reliable early warning information. For example, the physical model predicts that the water level may rise, while the statistical model gives the probability of a landslide occurring in this area. After comprehensive analysis, the system gives a comprehensive early warning.

[0105] In the monitoring application of a certain reservoir dam, the system can collect water level, seepage pressure, and displacement data in real time and comprehensively analyze these data through the intelligent early warning module. If the system finds that the water level at a certain monitoring point exceeds the set safety range and the displacement at this position is also within the abnormal range, the system will issue an early warning signal according to the preset risk assessment model, reminding the maintenance personnel to pay attention to this position and take corresponding emergency measures if necessary. The types of early warnings include but are not limited to: over-limit early warning, trend change early warning, emergency event early warning, etc.

[0106] The intelligent early warning module not only makes early warning judgments through real-time analysis of monitoring data but also can provide customized early warning strategies according to specific application scenarios. For example, for different types of projects (such as bridges, tunnels, reservoirs, etc.), the intelligent early warning module can make corresponding adjustments according to specific safety standards and risk assessment models to ensure the accuracy and pertinence of early warning information.

[0107] To improve the intelligence of the system, the intelligent early warning module can introduce an adaptive learning mechanism. For example, based on the changes in real-time data, the system can adaptively adjust the early warning threshold to make the early warning more sensitive and timely. Specifically, when the system detects that a certain monitoring point frequently triggers minor early warnings, the intelligent early warning module may analyze the normal change pattern of this point through algorithms and appropriately adjust the early warning threshold of this point to avoid over-early warning and resource waste.

[0108] The intelligent early warning module can also be linked with mobile terminals or alarm systems. When the early warning signal is triggered, the system can promptly convey the early warning information to engineering management personnel through various methods such as text messages, emails, and APP push. By combining multiple alarm means, it is ensured that the early warning information can be transmitted in a timely manner and rapid response measures can be taken.

[0109] In summary, the intelligent early warning module in this embodiment receives multi-source monitoring data, utilizes data processing, fusion, analysis, and intelligent algorithms to evaluate potential risks, and thus issues reasonable and timely early warning signals. By being linked with other modules of the monitoring system, it can effectively improve the safety guarantee ability of engineering facilities and reduce the risk of potential disasters. This technology is widely applicable to the fields of intelligent monitoring and risk management of infrastructure such as reservoirs, tunnels, and bridges, and has good application prospects. The user interface and the monitoring platform provide real-time visual display of water level, seepage pressure, and displacement data and the function of historical data backtracking.

[0110] Although the embodiments of the present invention have been shown and described, for those of ordinary skill in the art, it can be understood that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principle and spirit of the present invention. The scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A Beidou system combining water level, seepage pressure and displacement monitoring, characterized in that: include: The water level monitoring module uses a high-precision radar water level meter to measure the surface position of the water body based on the electromagnetic wave reflection signal and eliminate the influence of climate factors; The osmotic pressure monitoring module uses a combination of fiber grating sensors and MEMS sensors to obtain osmotic pressure data by measuring the optical fiber reflection wavelength or resistance change; The displacement monitoring module combines high-precision GPS and Beidou positioning systems, as well as laser scanning and fiber grating technology to monitor the displacement of the target area in real time; The data acquisition and transmission module transmits the data of each monitoring module to the data processing center through wireless communication; The data processing and fusion module uses Kalman filtering and particle filtering algorithms to fuse and optimize water level, seepage pressure and displacement data to improve data accuracy; Beidou positioning module, which provides high-precision displacement positioning data through the Beidou satellite system; Intelligent early warning module, which performs real-time data analysis and pattern recognition based on machine learning algorithms, and automatically triggers early warnings when potential risks occur; The user interface and monitoring platform provide real-time visualization of water level, seepage pressure, and displacement data, as well as historical data backtracking functions.

2. A Beidou system combining water level, seepage pressure and displacement monitoring according to claim 1, characterized in that: The radar water level meter of the water level monitoring module adopts frequency modulation continuous wave radar technology, and accurately calculates the water level by measuring the frequency change of the electromagnetic wave reflection signal, thereby eliminating the interference of environmental factors.

3. A Beidou system combining water level, seepage pressure and displacement monitoring according to claim 1, characterized in that: The fiber grating sensor of the osmotic pressure monitoring module is based on the Bragg grating principle and measures the osmotic pressure through the wavelength change of the light reflected by the optical fiber. The MEMS sensor responds to the osmotic pressure change through the piezoelectric effect and provides high-precision osmotic pressure data.

4. A Beidou system combining water level, seepage pressure and displacement monitoring according to claim 1, characterized in that: In the data processing and fusion module, the Kalman filter algorithm is used to perform real-time dynamic compensation and estimation of water level, seepage pressure and displacement data, and the particle filter algorithm is used to process nonlinear and non-Gaussian data, thereby improving the accuracy and stability of data fusion. The Kalman filter algorithm performs dynamic estimation through the following formula: in, is the state estimation, is the Kalman gain, is the observed value, is the observation matrix.

5. A Beidou system combining water level, seepage pressure and displacement monitoring according to claim 1, characterized in that: The intelligent early warning module uses machine learning algorithms to perform data pattern recognition, adopts supervised learning algorithms to train monitoring data, and performs risk prediction and analysis based on real-time data. If the predicted risk exceeds a set threshold, the early warning mechanism is triggered.

6. A Beidou system combining water level, seepage pressure and displacement monitoring according to claim 1, characterized in that: The laser scanning technology in the displacement monitoring module combines high-precision GPS and Beidou positioning systems, and uses optical measurement principles to accurately calculate the displacement of dam and embankment structures with millimeter-level accuracy. The displacement calculation is performed using the following formula: in, is the displacement, is the coordinate of the current moment, is the coordinate at the initial moment.

7. A Beidou system combining water level, seepage pressure and displacement monitoring according to claim 1, characterized in that: The data acquisition and transmission module adopts wireless communication technology, including but not limited to LoRa, ZigBee or 5G network, to ensure the stability and real-time performance of large-scale and high-density data transmission.

8. The Beidou system combining water level, seepage pressure and displacement monitoring according to claim 1, characterized in that: The data processing and fusion module uses multimodal data fusion technology, combines multiple data sources of water level, seepage pressure, and displacement sensors, and adopts weighted average or Bayesian estimation method to perform data fusion, further improving the overall accuracy and stability of the monitoring system. The data fusion formula is: in, is the fused data result, is the weight of each data source, Observation values ​​provided by each sensor data source.

9. A BeiDou system combining water level, seepage pressure and displacement monitoring according to claim 1, characterized in that: The warning triggering mechanism in the intelligent warning module includes but is not limited to a threshold method, an anomaly detection method and a warning method based on trend analysis, which monitors in real time and warns in advance the potential risks of sudden hydrological disasters and dam deformation.

10. A Beidou system combining water level, seepage pressure and displacement monitoring according to claim 1, characterized in that: The user interface and monitoring platform provide real-time data display, historical data playback and risk warning information through a visual graphical interface, and generate data reports based on monitoring data for users to refer to for decision-making.

Images