Deformation monitoring system and method for dam body surface

Abstract

The invention discloses a dam body surface deformation monitoring system and method, relates to the technical field of remote monitoring, and mainly solves the problems of poor environmental adaptability, low data processing capability and poor system monitoring efficiency of a monitoring system. The deformation monitoring system for the dam body surface comprises an operation and maintenance management platform, and a sensor network module, an Internet of Things communication module, a data analysis module and an intelligent regulation and control module which are connected with the operation and maintenance management platform, the system adapts to extreme weather and complex working conditions through a sensor network, and the environment adaptability of the system is improved; system data are analyzed through the dynamic analysis algorithm, and the data processing and analysis capability is improved; through the adaptive regulation and control algorithm, the monitoring efficiency of the monitoring system is improved.

Description

Technical Field

[0001] The present invention relates to the field of remote monitoring technology, and in particular to a deformation monitoring system and method for a dam body surface. Background Art

[0002] As an important water conservancy facility, the safety and stability of the dam are directly related to the safety of the downstream area and the utilization efficiency of water resources. Therefore, it is crucial to continuously monitor the health status of the dam structure. However, the accuracy and reliability of the sensors in the existing monitoring system will be affected under extreme weather or complex working conditions. It is necessary to improve the sensor design to improve the sensor's ability to adapt to the environment; the existing monitoring system has limited system data processing capabilities, and when faced with a large amount of data, there will be delays, affecting the timeliness and effectiveness of monitoring; the current monitoring system is difficult to adapt to the monitoring needs of large-scale and complex terrain, and the flexibility and adaptability of the monitoring system need to be improved; when the system data detects anomalies, the system cannot adjust the monitoring strategy in time, and the monitoring efficiency needs to be improved.

[0003] Therefore, the present invention provides a deformation monitoring system and method for the dam surface, which applies a sensor network to adapt to extreme weather and complex working conditions; analyzes system data through the dynamic analysis algorithm to improve data processing and analysis capabilities; and improves the monitoring efficiency of the monitoring system through the adaptive control algorithm. Summary of the invention

[0004] The purpose of the present invention is to solve the problems of poor system environmental adaptability, low data processing capability and poor system monitoring efficiency in the prior art, and to propose a deformation monitoring system and method for the dam surface.

[0005] In order to achieve the above object, the present invention adopts the following technical solutions:

[0006] A deformation monitoring system for a dam surface comprises an operation and maintenance management platform and a sensor network module, an Internet of Things communication module, a data analysis module and an intelligent control module connected to the operation and maintenance management platform, characterized in that:

[0007] The operation and maintenance management platform provides a user interface to facilitate operators to interactively access the system, view data and perform tasks;

[0008] The sensor network module is used to collect physical data and environmental data of the dam body;

[0009] The Internet of Things communication module is used to transmit the data information collected by the monitoring system;

[0010] The data analysis module is used to process and analyze the received sensor data;

[0011] The intelligent control module is used to adjust system monitoring parameters and sensor configuration;

[0012] The output end of the operation and maintenance management platform is electrically connected to the input ends of the sensor network module, the Internet of Things communication module, the data analysis module, the early warning report module and the intelligent control module respectively; the output end of the sensor network module is electrically connected to the input end of the Internet of Things communication module; the output end of the Internet of Things communication module is electrically connected to the input end of the data analysis module; the output end of the data analysis module is electrically connected to the input end of the intelligent control module.

[0013] As a further description of the above technical solution, the operation and maintenance management platform includes a server, a user interface, a database and an integration interface. The server uses an Intel Xeon processor to run requests from the system front end; the user interface sends the user-input instructions to the server through hypertext markup language HTML and scripting language ASP.NET, and displays the server's response to the user; the database uses the database management system MySQL to store, retrieve and manage monitoring system data; the integration interface uses RESTful API to realize data exchange and integration between the operation and maintenance management platform and other systems.

[0014] As a further description of the above technical solution, the sensor network module includes a power supply unit, a data acquisition sensor, a sensor node and a gateway unit. The power supply unit uses a solar panel to provide power supply for the sensor network; the data acquisition sensor includes a displacement sensor, a tilt sensor, a crack sensor, a strain sensor, a temperature sensor, a rainfall sensor and a wind sensor; the sensor node uses an STM32 microcontroller as a core unit to preprocess the electrical signal collected by the data acquisition sensor; the gateway unit aggregates the sensor node data and transmits the preprocessed data through a WIFI communication interface. The output end of the power supply unit is respectively connected to the input ends of the data acquisition sensor, the sensor node and the gateway unit, the output end of the data acquisition sensor is connected to the input end of the sensor node, and the output end of the sensor node is connected to the input end of the gateway unit.

[0015] As a further description of the above technical solution, the displacement sensor adopts a linear variable differential transformer to monitor the displacement change of the dam body; the tilt sensor adopts a gyroscope to detect the tilt angle of the dam body; the crack sensor adopts a fiber Bragg grating to detect the expansion of cracks on the surface of the dam body; the strain sensor adopts a resistance strain gauge to measure the strain of the dam body material; the temperature sensor adopts a thermistor to monitor the temperature changes of the dam body and the surrounding environment; the rainfall sensor adopts a tipping bucket rain gauge to measure the rainfall around the dam body within a fixed time; the wind sensor adopts a cup anemometer to monitor the wind speed and wind direction of the environment around the dam body.

[0016] As a further description of the above technical solution, the Internet of Things communication module includes a wireless communication unit, a security encryption unit and a network optimization unit. The wireless communication unit adopts the narrowband Internet of Things NB-IoT to realize the transmission of data between the various modules of the monitoring system; the security encryption unit establishes a secure connection through the TLS / SSL protocol to verify the identity of the communicating parties; the network optimization unit enhances network coverage through self-organizing networking and multi-hop routing to optimize the efficiency and quality of data transmission.

[0017] As a further description of the above technical solution, the data analysis module includes a data fusion unit, a data analysis unit, an early warning reporting unit and a data visualization unit. The data fusion unit adopts Kalman filtering to integrate data from multiple sensors; the data analysis unit analyzes the integrated data through a dynamic analysis algorithm to identify and predict the deformation development of the dam body; the early warning reporting unit makes early warning judgments by comparing real-time data and analysis results, and notifies operators through text messages and emails; the data visualization unit displays the monitoring data and analysis results in the form of charts and maps to intuitively understand the deformation conditions and trends of the dam body surface, the output end of the data fusion unit is connected to the input end of the data analysis unit, the output end of the data analysis unit is connected to the input end of the early warning reporting unit, and the output end of the early warning reporting unit is connected to the input end of the data visualization unit.

[0018] As a further description of the above technical solution, the implementation steps of the dynamic analysis algorithm are:

[0019] 1) Extract features from the integrated dam data according to the time characteristics, clean the data, remove noise and outliers, and extract complete data features;

[0020] 2) Divide the extracted feature data into different data sets, including training set, validation set and test set;

[0021] 3) Input the training set data into the LSTM model for model data training to capture the dynamic characteristics of dam deformation and find the optimal model parameters through grid search;

[0022] 4) Use the validation set to validate the model and use the model evaluation function to evaluate the performance of the model. The formula of the model evaluation function is:

[0023]

[0024] In formula (1), P i represents the model evaluation function, ξ represents the standard data value of the dam body, i represents the order of data comparison, represents the i-th data order of the validation set, ω represents the evaluation factor of the evaluation function, represents the function evaluation coefficient;

[0025] 5) Use the test set to make preliminary predictions for the LSTM model, test the accuracy of the model, and adjust the model parameters based on the verification results;

[0026] 6) The real-time monitoring data is input into the LSTM model, and the model outputs the deformation trend prediction, including the deformation amount and deformation rate.

[0027] As a further description of the above technical solution, the intelligent control module includes an anomaly detection unit, an adaptive control unit, and an intelligent response unit. The anomaly detection unit detects real-time monitoring data through machine learning to identify abnormal data; the adaptive control unit automatically adjusts the parameters and frequency of the monitoring system through an adaptive control algorithm; the intelligent response unit integrates abnormal data and a rule engine to automatically trigger a maintenance process to adapt to the impact of changes in the monitoring environment.

[0028] As a further description of the above technical solution, the implementation steps of the adaptive control algorithm are:

[0029] a) Collect real-time data from the dam monitoring system, including displacement, tilt, stress and humidity indicators. The parameter set is T is the displacement data set of the dam body at time n, Y is the tilt data set of the dam body at time n, U is the stress data set of the dam body at time n, I is the humidity data set of the dam body at time n, 0≤n≤24 and record the initial parameters and frequency of the monitoring system;

[0030] b) Analyze the collected data according to the One-Class SVM machine learning model, and evaluate the impact of abnormal data on monitoring accuracy according to the detection function, the formula expression of the detection function is:

[0031]

[0032] In formula (2), Z (n) represents the detection function, n represents the time when data is collected, represents the detection factor of the detection function, represents the detection coefficient of the detection function, T n represents the displacement data of the dam at time n, Y n represents the dam body tilt data at time n, U n represents the stress data of the dam body at time n, I n Represents the dam body humidity data at time n;

[0033] c) Increase the data collection frequency and adjust the sensitivity of the sensor accordingly based on the abnormal trends detected;

[0034] d) Applying the adjusted parameters to the monitoring system, continuously monitoring the adjusted operating effect, and outputting the adjustment result through an output function, wherein the formula of the output function is:

[0035]

[0036] In formula (3), O i represents the output function, i represents the number of monitoring data points, K represents the evaluation comparison standard value, γ represents the function evaluation factor, β n Indicates the system monitoring result at time n, where n represents the system monitoring time, 0≤n≤24, Represents the output function coefficient value;

[0037] e) Output control results and status reports of the monitoring system to provide decision support for managers.

[0038] As a further description of the above technical solution, the steps of the deformation monitoring method for the dam surface are as follows:

[0039] i. Operators access the monitoring system through the user interface of the operation and maintenance management platform and retrieve and manage data through the database of the MySQL database management system;

[0040] ii. Install the data acquisition sensor on the surface of the dam body, and set the power supply unit and the sensor node, the sensor node collects the physical data and environmental data of the dam body, and pre-processes these data, and transmits the pre-processed data through the WIFI communication interface through the gateway unit;

[0041] iii. Using narrowband Internet of Things NB-IoTUU wireless communication to receive the pre-processed data, and processing and analyzing the received sensor data through the dynamic analysis algorithm;

[0042] iv. Identify and predict the deformation development of the dam body through the data analysis module, make early warning judgments based on real-time data and analysis results, and notify operators through SMS and email;

[0043] v. After receiving the alarm, it identifies the abnormal data, adjusts the parameters and frequency of the monitoring system according to the analysis results and real-time data, and automatically triggers the maintenance process to adapt to the changes in the monitoring environment.

[0044] Compared with the prior art, the present invention provides a deformation monitoring system and method for a dam surface, which has the following beneficial effects.

[0045] 1. The present invention uses a sensor network to improve the monitoring accuracy of the monitoring system under extreme weather and complex working conditions.

[0046] 2. The present invention adopts the dynamic analysis algorithm to analyze system data to improve data processing and analysis capabilities.

[0047] 3. The present invention adopts the adaptive control algorithm to improve the monitoring efficiency of the monitoring system.

[0048] Other advantages, objectives and features of the present invention will be described in part in the following description; and in part, will be apparent to those skilled in the art based on an examination of the following; or, may be taught from the practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to understand and grasp the technical solution more intuitively and clearly, when describing the embodiments of the present invention or the prior art, drawings are often used to supplement and illustrate. It should be noted that the drawings are only one way of expressing the embodiments of the present invention or the prior art. In fact, the technical solution can also have other implementation methods and changes, which all fall within the protection scope of the present invention. Therefore, technicians can design other drawings as needed to implement the technical solution of the present invention, among which,

[0050] Figure 1 It is a schematic diagram of the overall structure of the present invention.

[0051] Figure 2 It is a structural schematic diagram of the operation and maintenance management platform of the present invention.

[0052] Figure 3 It is a schematic diagram of the structure of the sensor network module of the present invention.

[0053] Figure 4 It is a structural schematic diagram of the data analysis module of the present invention.

[0054] Figure 5 It is a structural schematic diagram of the intelligent control module of the present invention.

[0055] Figure 6 The figure is a schematic diagram of the process steps for implementing the present invention. DETAILED DESCRIPTION

[0056] The following will clearly and completely describe the technical solutions in the embodiments of this invention through the accompanying drawings in the embodiments of this invention. Obviously, the described embodiments are only part of the embodiments of this invention, not all of the embodiments. At the same time, the description of well-known structures and technologies is omitted in the following description to avoid unnecessary confusion of the concepts of the present invention.

[0057] like Figure 1-Figure 6 As shown, a deformation monitoring system for a dam surface includes an operation and maintenance management platform and a sensor network module, an Internet of Things communication module, a data analysis module and an intelligent control module connected to the operation and maintenance management platform;

[0058] The operation and maintenance management platform provides a user interface to facilitate operators to interactively access the system, view data and perform tasks;

[0059] The sensor network module is used to collect physical data and environmental data of the dam body;

[0060] The Internet of Things communication module is used to transmit the data information collected by the monitoring system;

[0061] The data analysis module is used to process and analyze the received sensor data;

[0062] The intelligent control module is used to adjust system monitoring parameters and sensor configuration;

[0063] The output end of the operation and maintenance management platform is electrically connected to the input ends of the sensor network module, the Internet of Things communication module, the data analysis module, the early warning report module and the intelligent control module respectively; the output end of the sensor network module is electrically connected to the input end of the Internet of Things communication module; the output end of the Internet of Things communication module is electrically connected to the input end of the data analysis module; the output end of the data analysis module is electrically connected to the input end of the intelligent control module.

[0064] In the above embodiment, the operation and maintenance management platform includes a server, a user interface, a database and an integration interface. The server uses an Intel Xeon processor to run requests from the system front end; the user interface sends the user-input instructions to the server through hypertext markup language HTML and scripting language ASP.NET, and displays the server's response to the user; the database uses the database management system MySQL to store, retrieve and manage monitoring system data; the integration interface uses RESTful API to realize data exchange and integration between the operation and maintenance management platform and other systems.

[0065] In a specific embodiment, the core architecture of the operation and maintenance management platform is composed of a high-performance server, an intuitive user interface, a powerful database system and a flexible integrated interface to achieve seamless operation and maintenance and efficient system management. The server is equipped with a high-end processor of the Intel Xeon series, which ensures the rapid response and processing capability of the massive requests from the front-end system. It can not only withstand the test of high concurrency, but also ensure the accuracy and timeliness of data processing, providing a solid hardware foundation for the efficient operation of the entire platform. The user interface uses the hypertext markup language HTML and the ASP.NET scripting language to build an intuitive and highly interactive operation interface. Users can easily enter instructions through this interface, and these instructions are then converted into signals that can be recognized by the server to achieve accurate communication and execution of instructions. The response results of the server are also displayed to the user in a clear and easy-to-understand form through this interface, ensuring the two-way efficient flow of information. The database management system selects the industry-leading MySQL to store, retrieve and manage the massive data generated during the operation and maintenance process. MySQL provides reliable data support for the platform with its excellent performance, stability and security. The integrated interface realizes the seamless connection between the operation and maintenance management platform and the external system through the RESTful API. This design not only simplifies the data exchange process, but also greatly improves the flexibility and efficiency of data integration.

[0066] In the above embodiment, the sensor network module includes a power supply unit, a data acquisition sensor, a sensor node and a gateway unit. The power supply unit uses a solar panel to provide power supply for the sensor network; the data acquisition sensor includes a displacement sensor, a tilt sensor, a crack sensor, a strain sensor, a temperature sensor, a rainfall sensor and a wind sensor; the sensor node uses an STM32 microcontroller as a core unit to pre-process the electrical signal collected by the data acquisition sensor; the gateway unit aggregates the sensor node data and transmits the pre-processed data through a WIFI communication interface. The output end of the power supply unit is respectively connected to the input ends of the data acquisition sensor, the sensor node and the gateway unit, the output end of the data acquisition sensor is connected to the input end of the sensor node, and the output end of the sensor node is connected to the input end of the gateway unit.

[0067] In a specific embodiment, the sensor network module demonstrates its capabilities in the field of data acquisition and environmental monitoring. The power supply unit adopts environmentally friendly and efficient solar panels, which not only provides a continuous supply of electricity for the entire sensor network, but also reflects the important position of green energy in modern scientific and technological applications. The use of solar panels not only reduces the dependence on traditional electricity, but also reduces the operating cost of the system and improves the sustainability of the system. The data acquisition sensor includes a displacement sensor, a tilt sensor, a crack sensor, a strain sensor, a temperature sensor, a rainfall sensor and a wind sensor, covering the full range of perception of environmental changes. These sensors can monitor the slight changes in the environment in real time, whether it is the slight displacement of the surface, the tilt angle of the structure, or the slight expansion of the crack, the slight change of strain, or the slight fluctuation of temperature, the precise measurement of rainfall and the real-time monitoring of wind power, can be accurately captured, providing detailed basic data for data analysis. The sensor node adopts a high-performance STM32 microcontroller as the core unit. This core unit is responsible for preprocessing the collected electrical signals, including signal amplification, filtering and digitization, to ensure the accuracy and reliability of the data. Through this link, the original analog signal is converted into a digital signal for analysis, providing a solid foundation for subsequent data transmission and analysis. The gateway unit is responsible for gathering data from various sensor nodes and efficiently transmitting the pre-processed data to the data processing center through the WIFI communication interface, which not only ensures the safe transmission of data, but also realizes real-time sharing of data, providing timely and accurate information support for decision makers, and enhancing the system's response speed and decision-making ability.

[0068] In the above embodiments, the displacement sensor uses a linear variable differential transformer to monitor the displacement change of the dam body; the tilt sensor uses a gyroscope to detect the tilt angle of the dam body; the crack sensor uses a fiber Bragg grating to detect the expansion of cracks on the surface of the dam body; the strain sensor uses a resistance strain gauge to measure the strain of the dam body material; the temperature sensor uses a thermistor to monitor the temperature changes of the dam body and the surrounding environment; the rainfall sensor uses a tipping bucket rain gauge to measure the rainfall around the dam body within a fixed time; the wind sensor uses a cup anemometer to monitor the wind speed and wind direction of the environment around the dam body.

[0069] In a specific embodiment, in order to comprehensively monitor the safety status of the dam, a series of high-precision and high-performance sensors are used to form an all-round monitoring network to ensure the accuracy and reliability of the data. The core of the displacement sensor is a linear variable differential transformer, which can capture the tiny displacement changes of the dam body with micron-level accuracy. Whether it is the overall displacement or local deformation of the dam body, it can be accurately recorded, providing key data for evaluating the stability of the dam; the tilt sensor uses advanced gyroscope technology to monitor the tilt angle of the dam body in real time. This sensor is not only highly accurate, but also has good stability. It can work stably for a long time, ensuring the continuity and reliability of the monitoring data. The crack sensor uses a fiber Bragg grating, which can detect the expansion of cracks on the surface of the dam. The fiber Bragg grating has extremely high sensitivity and can monitor the subtle changes of the cracks in real time, providing strong support for predicting the development trend of the cracks. The strain sensor uses a resistance strain gauge. This sensor can accurately measure the strain of the dam material. Whether it is tension or compression, it can be accurately captured. The data of the strain sensor is an important basis for evaluating the health status of the dam structure. The temperature sensor uses a thermal resistor to monitor the temperature changes of the dam body and the surrounding environment in real time, which is crucial for evaluating the thermal stress and thermal deformation of the dam. The accurate acquisition of temperature data helps to predict and prevent structural damage caused by temperature changes. The rainfall sensor uses a tipping bucket rain gauge to accurately measure the rainfall around the dam body within a fixed time. This sensor can not only provide real-time rainfall data, but also record historical rainfall, providing data support for analyzing the impact of rainfall on dam safety. The wind sensor uses a cup anemometer to ensure that the dam can remain stable under extreme weather conditions. Wind data is crucial for evaluating the dam's wind resistance and wind load impact. The comprehensive application of this series of sensors can not only monitor the safety status of the dam in real time, but also provide a scientific basis for the long-term maintenance and management of the dam, ensure the safe operation of the dam, and protect downstream areas from flood threats.

[0070] In the above embodiment, the Internet of Things communication module includes a wireless communication unit, a security encryption unit and a network optimization unit. The wireless communication unit adopts the narrowband Internet of Things NB-IoT to realize the transmission of data between the various modules of the monitoring system; the security encryption unit establishes a secure connection through the TLS / SSL protocol to verify the identity of the communicating parties; the network optimization unit enhances network coverage through self-organizing networking and multi-hop routing to optimize the efficiency and quality of data transmission.

[0071] In a specific embodiment, the design and implementation of the Internet of Things communication module not only reflects the cutting-edge nature of the technology, but also carries the heavy responsibility of connecting everything, ensuring information security and improving network performance. The wireless communication unit adopts narrowband Internet of Things NB-IoT technology, which is a wireless communication standard designed for low-power and wide-coverage scenarios. It can ensure efficient and stable transmission of data between modules in the monitoring system. With its low power consumption characteristics, NB-IoT technology enables monitoring equipment to be able to operate without frequent battery replacement for a long time, greatly reducing maintenance costs. At the same time, its wide coverage capability ensures that data can be accurately transmitted even in remote or complex environments, providing a solid foundation for Internet of Things applications. The security encryption unit builds an indestructible security line for data transmission by implementing the transport layer security TLS / secure socket layer SSL protocol. Through the two-way identity authentication mechanism, the legitimacy of the communicating parties is ensured, and eavesdropping, tampering and counterfeiting of data during transmission are effectively prevented. The TLS / SSL protocol uses advanced encryption algorithms to encrypt the data in transmission. Even if the data is intercepted, it cannot be interpreted by a third party, thereby ensuring the integrity and confidentiality of the data. The network optimization unit significantly enhances the network coverage and data transmission efficiency through Ad-hoc and multi-hop routing technologies. Ad-hoc technology allows devices to automatically form a network without fixed infrastructure, greatly enhancing the flexibility and adaptability of the IoT system. Multi-hop routing allows data to be transmitted between multiple devices, which not only expands the effective transmission distance, but also optimizes the data transmission path through a multi-path selection mechanism, thereby improving the efficiency and quality of data transmission.

[0072] In the above embodiment, the data analysis module includes a data fusion unit, a data analysis unit, an early warning reporting unit and a data visualization unit. The data fusion unit uses Kalman filtering to integrate data from multiple sensors; the data analysis unit analyzes the integrated data through a dynamic analysis algorithm to identify and predict the deformation development of the dam body; the early warning reporting unit makes an early warning judgment by comparing real-time data and analysis results, and notifies the operator through text messages and emails; the data visualization unit displays the monitoring data and analysis results in the form of charts and maps to intuitively understand the deformation conditions and trends of the dam body surface, the output end of the data fusion unit is connected to the input end of the data analysis unit, the output end of the data analysis unit is connected to the input end of the early warning reporting unit, and the output end of the early warning reporting unit is connected to the input end of the data visualization unit.

[0073] In a specific embodiment, the data analysis module constructs a comprehensive and accurate monitoring system to ensure real-time and efficient monitoring of the health status of the dam body. The data fusion unit plays the role of the "commander" of information integration. It uses the Kalman filter algorithm to accurately filter out effective signals from the complex data collected by multiple sensors, realizes efficient data fusion, and instantly connects the originally isolated data points into a clear image, laying a solid foundation for subsequent analysis. The data analysis unit uses a dynamic analysis algorithm to deeply mine the fused data, and identifies subtle signs of dam body deformation from the data. The development trend of deformation is judged by the prediction model, which not only improves the accuracy of monitoring, but also provides a scientific basis for preventing potential risks. The early warning reporting unit compares the data analysis results with the preset threshold in real time. Once an abnormality is found, the early warning mechanism is immediately activated, and the alarm information is quickly transmitted to the operator through SMS and email, etc., to ensure that a response is made in the first time and the possible losses are minimized. The data visualization unit intuitively displays the complex monitoring data and analysis results in the form of charts and maps, so that the deformation situation and trend of the dam body surface are clear at a glance. It not only simplifies the data interpretation process, but also makes the monitoring results vivid and intuitive, providing decision makers with a clear and intuitive reference.

[0074] In the above embodiment, the implementation steps of the dynamic analysis algorithm are:

[0075] 1) Extract features from the integrated dam data according to the time characteristics, clean the data, remove noise and outliers, and extract complete data features;

[0076] 2) Divide the extracted feature data into different data sets, including training set, validation set and test set;

[0077] 3) Input the training set data into the LSTM model for model data training to capture the dynamic characteristics of dam deformation and find the optimal model parameters through grid search;

[0078] 4) Use the validation set to validate the model and use the model evaluation function to evaluate the performance of the model. The formula of the model evaluation function is:

[0079]

[0080] In formula (1), P i represents the model evaluation function, ξ represents the standard data value of the dam body, i represents the order of data comparison, represents the i-th data order of the validation set, ω represents the evaluation factor of the evaluation function, represents the function evaluation coefficient;

[0081] 5) Use the test set to make preliminary predictions for the LSTM model, test the accuracy of the model, and adjust the model parameters based on the verification results;

[0082] 6) The real-time monitoring data is input into the LSTM model, and the model outputs the deformation trend prediction, including the deformation amount and deformation rate.

[0083] In a specific embodiment, the main function of the dynamic analysis algorithm is to predict the deformation trend of the dam body. It analyzes historical monitoring data, identifies and learns the time series characteristics of the dam body deformation, and then can predict the possible deformation amount and deformation rate in the future, providing data support and early warning information for the safety monitoring and maintenance of the dam body. The main problem solved by the dynamic analysis algorithm is to provide early warning of possible abnormal deformation of the dam body to buy time for taking preventive measures; based on the prediction results, optimize the dam body maintenance and repair plan to reduce unnecessary maintenance costs; provide accurate prediction information to assist managers in making more scientific decisions. In the model evaluation function, according to the dam body standard data value ξ, the evaluation function evaluation factor ω and the function evaluation coefficient For the i-th data in the validation set Evaluation is performed to verify the reliability of the data. The implementation of the algorithm is carried out through the following steps: data preprocessing: cleaning and feature extraction to ensure data quality; data set division: divide the data into training set, validation set and test set; model training: use the LSTM model to learn time series features on the training set; parameter optimization: optimize model parameters through grid search and other methods; model evaluation and tuning: evaluate the model on the validation set and test set, and adjust the model according to the results; real-time prediction: input real-time monitoring data into the model to predict deformation trends. The data analysis comparison between the dynamic analysis algorithm and the traditional data analysis algorithm is shown in Table 1:

[0084] Table 1 Comparison of dynamic analysis algorithm and traditional algorithm analysis

[0085]

[0086] In summary, the accuracy and efficiency of the dynamic analysis algorithm in data analysis are higher than those of the traditional algorithm. Therefore, it can be seen that the dynamic analysis algorithm is the best choice for the present invention.

[0087] In the above embodiment, the intelligent control module includes an anomaly detection unit, an adaptive control unit, and an intelligent response unit. The anomaly detection unit detects real-time monitoring data through machine learning and identifies abnormal data; the adaptive control unit automatically adjusts the parameters and frequency of the monitoring system through an adaptive control algorithm; the intelligent response unit integrates abnormal data and the rule engine to automatically trigger the maintenance process to adapt to the impact of changes in the monitoring environment.

[0088] In a specific embodiment, the intelligent control module constructs a highly intelligent monitoring and control system. The abnormal detection unit uses advanced machine learning algorithms to conduct in-depth analysis of real-time monitoring data, and can quickly identify abnormal signals hidden in a large amount of data to ensure that any subtle fluctuations are not hidden. The adaptive control unit automatically adjusts the parameters and frequency of the monitoring system through an adaptive control algorithm. It can intelligently optimize the data acquisition strategy according to environmental changes to achieve a dynamic balance between monitoring accuracy and efficiency. The intelligent response unit combines abnormal data with the rule engine to automatically trigger the maintenance process. When the abnormal detection unit captures an abnormal signal, the intelligent response unit starts immediately, accurately locates the problem according to the preset rules, and automatically triggers the corresponding maintenance process, such as equipment restart, parameter adjustment, etc., to ensure that the impact of changes in the monitoring environment on the system is minimized. This process is highly automated, reducing the need for manual intervention and greatly improving the response speed and maintenance efficiency of the system.

[0089] In the above embodiment, the implementation steps of the adaptive control algorithm are:

[0090] a) Collect real-time data from the dam monitoring system, including displacement, tilt, stress and humidity indicators. The parameter set is T is the displacement data set of the dam body at time n, Y is the tilt data set of the dam body at time n, U is the stress data set of the dam body at time n, I is the humidity data set of the dam body at time n, 0≤n≤24 and record the initial parameters and frequency of the monitoring system;

[0091] b) Analyze the collected data according to the One-Class SVM machine learning model, and evaluate the impact of abnormal data on monitoring accuracy according to the detection function, the formula expression of the detection function is:

[0092]

[0093] In formula (2), Z (n) represents the detection function, n represents the time when data is collected, represents the detection factor of the detection function, represents the detection coefficient of the detection function, T n represents the displacement data of the dam at time n, Y n represents the dam body tilt data at time n, U n represents the stress data of the dam body at time n, I n Represents the dam body humidity data at time n;

[0094] c) Increase the data collection frequency and adjust the sensitivity of the sensor accordingly based on the abnormal trends detected;

[0095] d) Applying the adjusted parameters to the monitoring system, continuously monitoring the adjusted operating effect, and outputting the adjustment result through an output function, wherein the formula of the output function is:

[0096]

[0097] In formula (3), O i represents the output function, i represents the number of monitoring data points, K represents the evaluation comparison standard value, γ represents the function evaluation factor, β n Indicates the system monitoring result at time n, where n represents the system monitoring time, 0≤n≤24, Represents the output function coefficient value;

[0098] e) Output control results and status reports of the monitoring system to provide decision support for managers.

[0099] In a specific embodiment, the role of the adaptive control algorithm is to dynamically adjust the parameters of the dam monitoring system to improve monitoring efficiency and accuracy. It automatically adjusts the data collection frequency and sensor sensitivity by analyzing data in real time to ensure that the monitoring system can provide more accurate and timely data when abnormal situations occur. The main problems solved by this algorithm include: Improving monitoring efficiency: In response to abnormal situations, by adaptively adjusting the data collection frequency and sensor sensitivity, unnecessary data collection is avoided while ensuring that key information is not missed; Accuracy enhancement: By automatically identifying abnormal trends and adjusting monitoring parameters, the accuracy of monitoring data is improved, and false alarms or omissions caused by improper settings of the monitoring system are reduced; Resource optimization: Rationally allocate sensor resources to reduce energy consumption and data processing burden. Detection coefficient based on the detection function and the detection factor of the detection function For the dam body tilt data Y at time n n , dam body stress data U at time n n, dam body humidity data at time n and dam body displacement data at time n n Perform data detection to evaluate the impact of abnormal data on monitoring accuracy; based on the evaluation comparison standard value K, function evaluation factor γ and output function coefficient value The monitoring result of the system at time n is β n The results are output, and the comparison between the adaptive control algorithm and the traditional algorithm is shown in Table 2:

[0100] Table 2 Comparison between adaptive control algorithm and traditional algorithm

[0101]

[0102] In summary, the adaptive control algorithm is superior to the traditional algorithm in terms of control efficiency after verification by multiple sets of experimental data. It can be seen that the adaptive control algorithm is the best choice for this article.

[0103] In the above embodiment, the deformation monitoring method for the dam surface comprises the following steps:

[0104] i. Operators access the monitoring system through the user interface of the operation and maintenance management platform and retrieve and manage data through the database of the MySQL database management system;

[0105] ii. Install the data acquisition sensor on the surface of the dam body, and set the power supply unit and the sensor node, the sensor node collects the physical data and environmental data of the dam body, and pre-processes these data, and transmits the pre-processed data through the WIFI communication interface through the gateway unit;

[0106] iii. Using narrowband Internet of Things NB-IoTUU wireless communication to receive the pre-processed data, and processing and analyzing the received sensor data through the dynamic analysis algorithm;

[0107] iv. Identify and predict the deformation development of the dam body through the data analysis module, make early warning judgments based on real-time data and analysis results, and notify operators through SMS and email;

[0108] v. After receiving the alarm, it identifies the abnormal data, adjusts the parameters and frequency of the monitoring system according to the analysis results and real-time data, and automatically triggers the maintenance process to adapt to changes in the monitoring environment.

[0109] In a specific embodiment, a deformation monitoring method for the surface of a dam is provided, and its steps are delicate and efficient, ensuring real-time and accurate monitoring of the health status of the dam body. The specific steps are as follows: First, professional operators seamlessly access the monitoring system through the intuitive user interface of the operation and maintenance management platform. Using the advanced MySQL database management system, operators can efficiently retrieve and manage massive historical and real-time data, ensure the accuracy and integrity of the data, and lay a solid foundation for subsequent analysis. Then, high-precision data acquisition sensors are carefully installed at key positions on the surface of the dam body. At the same time, stable power supply units and intelligent sensor nodes are set up, which not only collect physical parameters of the dam body, such as stress and displacement, but also monitor environmental data, such as temperature and humidity. The sensor node performs preliminary processing on the collected data, and transmits the pre-processed data to the central processing system safely and efficiently through the gateway unit and with the help of the WIFI communication interface. Then, the narrowband Internet of Things NB-IoT technology is introduced to realize wireless reception of pre-processed data. This technology significantly enhances the stability and range of data transmission and ensures the timeliness of data. Through the integrated dynamic analysis algorithm, the system deeply processes and analyzes the sensor data, accurately identifies small changes in the data, and provides a scientific basis for the subsequent early warning mechanism. Furthermore, the data analysis module uses advanced algorithms to identify and predict the deformation development of the dam body. Combining real-time data with historical analysis results, the system can intelligently judge potential risks. Once an abnormality is found, it immediately notifies the operator via SMS and email to ensure timely and accurate early warning. Finally, after receiving the alarm, the system automatically identifies abnormal data, and based on the analysis results and real-time data, intelligently adjusts the parameters and monitoring frequency of the monitoring system to adapt to environmental changes. At the same time, the system can automatically trigger maintenance processes, such as dispatching drones for aerial inspections, or adjusting sensor deployment to ensure comprehensive coverage and efficient operation of the monitoring network.

[0110] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

[0111] In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art can combine and combine different embodiments or examples described in this specification and the features of different embodiments or examples without contradiction.

[0112] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.

Claims

1. A deformation monitoring system for a dam surface, comprising an operation and maintenance management platform and a sensor network module, an Internet of Things communication module, a data analysis module and an intelligent control module connected to the operation and maintenance management platform, characterized in that: The operation and maintenance management platform provides a user interface to facilitate operators to interactively access the system, view data and perform tasks; The sensor network module is used to collect physical data and environmental data of the dam body; The Internet of Things communication module is used to transmit the data information collected by the monitoring system; The data analysis module is used to process and analyze the received sensor data; The intelligent control module is used to adjust system monitoring parameters and sensor configuration; The output end of the operation and maintenance management platform is electrically connected to the input ends of the sensor network module, the Internet of Things communication module, the data analysis module, the early warning report module and the intelligent control module respectively; the output end of the sensor network module is electrically connected to the input end of the Internet of Things communication module; the output end of the Internet of Things communication module is electrically connected to the input end of the data analysis module; the output end of the data analysis module is electrically connected to the input end of the intelligent control module.

2. A deformation monitoring system for a dam surface according to claim 1, characterized in that: The operation and maintenance management platform includes a server, a user interface, a database and an integrated interface. The server uses an Intel Xeon processor to run requests from the system front end; the user interface sends the user-input instructions to the server through hypertext markup language HTML and scripting language ASP.NET, and displays the server's response to the user; the database uses the database management system MySQL to store, retrieve and manage monitoring system data; the integrated interface uses RESTful API to realize data exchange and integration between the operation and maintenance management platform and other systems.

3. A deformation monitoring system for a dam surface according to claim 1, characterized in that: The sensor network module includes a power supply unit, a data acquisition sensor, a sensor node and a gateway unit. The power supply unit uses a solar panel to provide power supply for the sensor network; the data acquisition sensor includes a displacement sensor, a tilt sensor, a crack sensor, a strain sensor, a temperature sensor, a rainfall sensor and a wind sensor; the sensor node uses an STM32 microcontroller as a core unit to pre-process the electrical signals collected by the data acquisition sensor; The gateway unit aggregates the sensor node data and transmits the preprocessed data through the WIFI communication interface. The output end of the power supply unit is respectively connected to the input ends of the data acquisition sensor, the sensor node and the gateway unit. The output end of the data acquisition sensor is connected to the input end of the sensor node, and the output end of the sensor node is connected to the input end of the gateway unit.

4. A deformation monitoring system for a dam surface according to claim 3, characterized in that: The displacement sensor uses a linear variable differential transformer to monitor the displacement change of the dam body; the tilt sensor uses a gyroscope to detect the tilt angle of the dam body; the crack sensor uses a fiber Bragg grating to detect the expansion of cracks on the surface of the dam body; the strain sensor uses a resistance strain gauge to measure the strain of the dam body material; the temperature sensor uses a thermistor to monitor the temperature changes of the dam body and the surrounding environment; the rainfall sensor uses a tipping bucket rain gauge to measure the rainfall around the dam body within a fixed time; the wind sensor uses a cup anemometer to monitor the wind speed and wind direction of the environment around the dam body.

5. A deformation monitoring system for a dam surface according to claim 1, characterized in that: The Internet of Things communication module includes a wireless communication unit, a security encryption unit and a network optimization unit. The wireless communication unit uses the narrowband Internet of Things NB-IoT to realize the transmission of data between the various modules of the monitoring system; the security encryption unit establishes a secure connection through the TLS / SSL protocol to verify the identities of the communicating parties; the network optimization unit enhances network coverage through self-organizing networking and multi-hop routing to optimize the efficiency and quality of data transmission.

6. A deformation monitoring system for a dam surface according to claim 1, characterized in that: The data analysis module includes a data fusion unit, a data analysis unit, an early warning reporting unit and a data visualization unit. The data fusion unit uses Kalman filtering to integrate data from multiple sensors; the data analysis unit analyzes the integrated data through a dynamic analysis algorithm to identify and predict the deformation development of the dam body; the early warning reporting unit makes early warning judgments by comparing real-time data and analysis results, and notifies operators through text messages and emails; The data visualization unit displays the monitoring data and analysis results in the form of charts and maps to intuitively understand the deformation conditions and trends of the dam surface. The output end of the data fusion unit is connected to the input end of the data analysis unit, the output end of the data analysis unit is connected to the input end of the early warning reporting unit, and the output end of the early warning reporting unit is connected to the input end of the data visualization unit.

7. A deformation monitoring system for a dam surface according to claim 6, characterized in that: The implementation steps of the dynamic analysis algorithm are: 1) Extract features from the integrated dam data according to the time characteristics, clean the data, remove noise and outliers, and extract complete data features; 2) Divide the extracted feature data into different data sets, including training set, validation set and test set; 3) Input the training set data into the LSTM model for model data training to capture the dynamic characteristics of dam deformation and find the optimal model parameters through grid search; 4) Use the validation set to validate the model and use the model evaluation function to evaluate the performance of the model. The formula of the model evaluation function is: In formula (1), P i represents the model evaluation function, ξ represents the standard data value of the dam body, i represents the order of data comparison, represents the i-th data order of the validation set, ω represents the evaluation factor of the evaluation function, represents the function evaluation coefficient; 5) Use the test set to make preliminary predictions for the LSTM model, test the accuracy of the model, and adjust the model parameters based on the verification results; 6) The real-time monitoring data is input into the LSTM model, and the model outputs the deformation trend prediction, including the deformation amount and deformation rate.

8. A deformation monitoring system for a dam surface according to claim 1, characterized in that: The intelligent control module includes an anomaly detection unit, an adaptive control unit, and an intelligent response unit. The anomaly detection unit detects real-time monitoring data through machine learning and identifies abnormal data; the adaptive control unit automatically adjusts the parameters and frequency of the monitoring system through an adaptive control algorithm; the intelligent response unit integrates abnormal data and the rule engine to automatically trigger the maintenance process to adapt to the impact caused by changes in the monitoring environment.

9. A deformation monitoring system for a dam surface according to claim 8, characterized in that: The implementation steps of the adaptive control algorithm are: a) Collect real-time data from the dam monitoring system, including displacement, tilt, stress and humidity indicators. The parameter set is T is the displacement data set of the dam body at time n, Y is the tilt data set of the dam body at time n, U is the stress data set of the dam body at time n, I is the humidity data set of the dam body at time n, 0≤n≤24 and record the initial parameters and frequency of the monitoring system; b) Analyze the collected data according to the One-Class SVM machine learning model, and evaluate the impact of abnormal data on monitoring accuracy according to the detection function, the formula expression of the detection function is: In formula (2), Z (n) represents the detection function, n represents the time when data is collected, represents the detection factor of the detection function, represents the detection coefficient of the detection function, T n represents the displacement data of the dam at time n, Y n represents the dam body tilt data at time n, U n represents the stress data of the dam body at time n, I n Represents the dam body humidity data at time n; c) Increase the data collection frequency and adjust the sensitivity of the sensor accordingly based on the abnormal trends detected; d) Applying the adjusted parameters to the monitoring system, continuously monitoring the adjusted operating effect, and outputting the adjustment result through an output function, wherein the formula of the output function is: In formula (3), O i represents the output function, i represents the number of monitoring data points, K represents the evaluation comparison standard value, γ represents the function evaluation factor, β n Indicates the system monitoring result at time n, where n represents the system monitoring time, 0≤n≤24, Represents the output function coefficient value; e) Output control results and status reports of the monitoring system to provide decision support for managers.

10. A deformation monitoring system for a dam surface according to any one of claims 1 to 9, characterized in that: The deformation monitoring method for the dam surface comprises the following steps: i. Operators access the monitoring system through the user interface of the operation and maintenance management platform and retrieve and manage data through the database of the MySQL database management system; ii. Install the data acquisition sensor on the surface of the dam body, and set the power supply unit and the sensor node, the sensor node collects the physical data and environmental data of the dam body, and pre-processes these data, and transmits the pre-processed data through the WIFI communication interface through the gateway unit; iii. Using narrowband Internet of Things NB-IoTUU wireless communication to receive the pre-processed data, and processing and analyzing the received sensor data through the dynamic analysis algorithm; iv. Identify and predict the deformation development of the dam body through the data analysis module, make early warning judgments based on real-time data and analysis results, and notify operators through SMS and email; After receiving the alarm, the abnormal data is identified, and the parameters and frequency of the monitoring system are adjusted according to the analysis results and real-time data, automatically triggering the maintenance process to adapt to changes in the monitoring environment.

Images