Hydropower station dam foundation monitoring method and system based on Internet of Things

Abstract

The invention relates to the technical field of safety monitoring, in particular to a hydropower station dam foundation monitoring method and system based on the Internet of Things, and the method comprises the steps of equipment deployment, data acquisition and preprocessing, data transmission, data analysis and monitoring and early warning. Compared with the prior art that a single power supply module is adopted to provide continuous power supply for all sensors, so that high power supply energy consumption and insufficient system stability are possibly caused, the scheme adopts a graded power supply module design, and the first power supply module provides an uninterrupted stable power supply for a key sensor; the reliability and continuity of real-time data acquisition are ensured; the second power supply module provides an intermittent power supply for the non-key sensor, so that the data acquisition requirement is met, and the energy consumption is effectively reduced; meanwhile, the fault-tolerant capability of the whole system is further enhanced by the standby power supply module, and the graded power supply scheme not only optimizes the energy utilization and improves the system efficiency, but also remarkably enhances the reliability and durability of the hydropower station dam foundation monitoring system.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of safety monitoring, and particularly relates to a dam foundation monitoring method and system based on Internet of Things. BACKGROUND

[0002] In the traditional dam foundation monitoring system of a hydropower station, a single power module is usually used to provide continuous power supply for all sensors. However, this power supply method has obvious shortcomings.

[0003] Firstly, since all sensors rely on the same power module for power supply, when the power module fails, the power supply of all sensors will be affected, resulting in interruption of data collection, and further affecting the normal operation of the entire monitoring system. In addition, for some key sensors such as water level, water pressure and temperature sensors, they need to collect data in real time and continuously to ensure the safe operation of the hydropower station. If the power supply is unstable or interrupted, the accuracy and continuity of these data cannot be guaranteed.

[0004] Secondly, the traditional power supply method also has shortcomings in energy utilization. For some non-critical sensors such as humidity, speed and current voltage sensors, their data collection frequency may be relatively low, but they still need continuous power supply. This not only causes waste of energy, but also increases the energy consumption and operating cost of the system. SUMMARY

[0005] In order to overcome the problems raised in the above background art, the present application proposes a dam foundation monitoring method and system based on Internet of Things.

[0006] The technical solution of the present application is as follows: a dam foundation monitoring method based on Internet of Things, comprising the following steps: S11: device deployment, deploying intelligent sensors for real-time monitoring of water level changes, seepage conditions and displacement deformation of the dam foundation at key positions of the dam foundation of the hydropower station, including water level sensors, seepage pressure sensors and displacement sensors; S12: data collection and preprocessing, using the deployed intelligent sensors to collect real-time monitoring data of the dam foundation, and preprocessing the collected raw data; S13: data transmission, transmitting the preprocessed raw data to the Internet of Things cloud platform using wireless and wired networks; S14: data analysis, using cloud computing and big data technology to deeply analyze the preprocessed data and extract safety state information of the dam foundation; S15: monitoring and early warning, displaying the monitoring data of the dam foundation in real time on the Internet of Things cloud platform, and automatically triggering the early warning mechanism when the safety state of the dam foundation exceeds the preset threshold according to the data analysis results.

[0007] As preferred, when collecting various monitoring data of the dam foundation in real time by the deployed intelligent sensor and pre-processing the collected raw data, the following steps are included: S21: Data collection, collecting various monitoring data of the dam foundation in real time by the sensor, including water level, seepage pressure and displacement deformation; S22: Data cleaning, including removing outliers, removing duplicate values, handling missing values and removing noise in data; S23: Data formatting processing, including data type conversion, data standardization processing and data encoding processing, wherein the data type conversion is to convert the fields in the data set from one data type to a pre-set data type, the data standardization processing is to scale the numerical data in the data set to a pre-set range, and the data encoding is to convert text and category data into numerical data.

[0008] As preferred, when handling missing values in data, a filling strategy is selected according to the data type to fill the missing values in data, wherein the selectable filling strategy includes mean, median, mode and K-nearest neighbor algorithm, and when the proportion of missing values is lower than a set first threshold, the data containing missing values is directly deleted, and the first threshold is calculated by the following formula: ; Wherein, q is the first threshold, is the total amount of data collected, is the set required data amount, is the set data eligibility threshold, wherein The value of is related to the data type.

[0009] As preferred, when using cloud computing and big data technology to deeply analyze the data after pre-processing and extract the safety state information of the dam foundation, the following steps are included: S31: Model building, using a set data analysis algorithm to build a data analysis model, wherein the set data analysis algorithm includes classification algorithm, regression algorithm, clustering algorithm and dimensionality reduction algorithm; S32: Algorithm training, using pre-prepared labeled data to train the model, and evaluating the model by cross-validation; S33: Algorithm implementation, inputting the pre-processed data into the model for analysis, and using the model to extract the safety state information of the dam foundation; S34: Result verification, verifying the analysis result using actual observation data and expert experience, and optimizing the model according to the verification result; S35: Result interpretation, interpreting the analysis result to extract valuable information and insights.

[0010] A dam foundation monitoring system based on the Internet of Things, comprising: A data acquisition module for acquiring various state information of the hydropower unit and fixed measuring point information of the dam foundation; An Internet of Things module including a sensor network and a communication interface, for transmitting the data collected by the data acquisition module to the data processing module through Internet of Things technology; A data processing module for receiving the data collected by the data acquisition module and preprocessing and storing the data; A data transmission module for transmitting the data results of the data processing module to the Internet of Things cloud platform through an encrypted communication method; An Internet of Things cloud platform for receiving the data transmitted by the data transmission module and analyzing the data to obtain the state information of the dam foundation of the hydropower station.

[0011] Preferably, the data acquisition module comprises: A11: a water level sensor for real-time monitoring of the water level changes in the reservoir or in front of the dam of the hydropower station; A12: a water pressure sensor for measuring the water pressure in the dam foundation and the reservoir; A13: a temperature sensor for monitoring the temperature changes of the hydropower unit and the dam foundation; A14: a humidity sensor for real-time monitoring of the environmental humidity changes of the hydropower unit and the dam foundation; A15: a speed sensor for real-time monitoring of the speed indicators of the hydropower unit; A16: a current and voltage sensor for real-time monitoring of the current and voltage indicators of the hydropower unit.

[0012] Preferably, the data acquisition module is installed inside the dam foundation of the hydropower station, the data acquisition module is connected to the Internet of Things module through the Internet of Things, the Internet of Things module is installed inside the dam foundation of the hydropower station, the Internet of Things module is connected to the data processing module through a wired network, the data processing module is installed inside the dam foundation of the hydropower station, the data processing module is connected to the Internet of Things cloud platform through the data transmission module, and the data processing module transmits the data processing results to the Internet of Things cloud platform and stores the original data.

[0013] Preferably, it further comprises a power module, which comprises: A21: a first power module for providing uninterrupted stable power supply to the water level sensor, the water pressure sensor and the temperature sensor to realize real-time data acquisition of the water level sensor, the water pressure sensor and the temperature sensor; A22: a second power module, used for providing intermittent power supply for the humidity sensor, the rotation speed sensor and the current-voltage sensor, so as to realize intermittent data acquisition of the humidity sensor, the rotation speed sensor and the current-voltage sensor; A23: a backup power module, used for providing power supply for the water level sensor, the water pressure sensor, the temperature sensor, the humidity sensor, the rotation speed sensor and the current-voltage sensor when the first power module and the second power module fail.

[0014] Preferably, when the data processing module processes the data of the position sensor, the water pressure sensor, the temperature sensor, the humidity sensor, the rotation speed sensor and the current-voltage sensor, the data processing module comprises calibrating the sensors at a fixed time, wherein the principle formula for calibrating the sensors is: Y 校准= Y 原始+ Delta; Wherein, Y 校准 is a calibration value, Y 原始 is an original measurement value, and Delta is a predicted deviation value, and the specific value of Delta is predicted according to a machine learning model.

[0015] Preferably, when the data transmission module transmits the data results of the data processing module to the Internet of Things cloud platform by the method of encrypted communication, the data transmission module comprises the following steps: S41: first, the data results processed by the data processing module are encrypted by using a preset encryption algorithm; S42: signal strength detection is performed, if the signal strength is good, data transmission is performed, if the signal strength is poor, the signal strength detection is performed again after waiting for one minute; S43: if the signal transmission fails and the signal strength detection is performed three times, then the information sending is performed again after waiting for ten minutes; S44: if the data is still not successfully sent after the step S43 is performed three times, the data is marked as to-be-transmitted data.

[0016] The beneficial effects of the application are as follows: 1. Compared to existing technologies that use a single power module to continuously power all sensors, potentially leading to high power consumption and insufficient system stability, this solution innovatively adopts a hierarchical power module design: the first power module provides uninterrupted and stable power to critical sensors (water level, water pressure, temperature), ensuring the reliability and continuity of real-time data acquisition; the second power module provides intermittent power to non-critical sensors (humidity, rotational speed, current, voltage), satisfying data acquisition requirements while effectively reducing energy consumption; at the same time, the existence of a backup power module further enhances the fault tolerance and stability of the entire system. This hierarchical power supply scheme not only optimizes energy utilization and improves system efficiency but also significantly enhances the reliability and durability of the hydropower station dam foundation monitoring system. 2. Compared to existing technologies that directly transmit raw data to the cloud platform in real time, which may lead to high network load and low data transmission efficiency, this solution involves installing data acquisition modules, IoT modules, and data processing modules inside the hydropower station dam foundation. The data acquisition modules are connected to the IoT module via IoT, and the IoT module is connected to the data processing module via a wired network. The data processing module preprocesses the raw data, and the data transmission module efficiently and securely sends the processing results to the IoT cloud platform while storing the raw data locally. This solution not only reduces the network transmission load and the occupation of network resources, but also improves the stability and security of data transmission, while ensuring the integrity and traceability of the data. It provides more reliable technical support for real-time monitoring and data analysis of the hydropower station dam foundation. 3. Compared to existing technologies that use fixed calibration parameters to calibrate sensors, which may lead to inaccurate calibration due to environmental changes or sensor aging, this solution adopts a dynamic calibration method based on machine learning model prediction. This method calibrates the sensor periodically and uses a machine learning model to predict the possible deviation values ​​of the sensor, thereby calculating more accurate calibration values. This solution not only improves the accuracy and reliability of sensor data, but also adapts to the impact of environmental changes and sensor aging, effectively extending the service life of the sensor and providing more accurate data support for the monitoring of hydropower station dam foundations. Attached Figure Description

[0017] Figure 1 The diagram illustrates the workflow of the IoT-based hydropower station dam foundation monitoring method of the present invention. Figure 2 The diagram shown is a schematic representation of the construction of the IoT-based hydropower station dam foundation monitoring system of the present invention. Detailed Implementation

[0018] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0019] Referring to Figure 1 The present application provides an embodiment: a method for monitoring the dam foundation of a hydropower station based on the Internet of Things, comprising the following steps: S11: device deployment, deploying intelligent sensors for real-time monitoring of water level changes, seepage conditions and displacement deformation of the dam foundation at key positions of the dam foundation of the hydropower station, including water level sensors, seepage pressure sensors and displacement sensors; S12: data acquisition and preprocessing, using the deployed intelligent sensors to collect real-time monitoring data of the dam foundation, and preprocessing the collected raw data; S13: data transmission, using wireless and wired networks to transmit the raw data after preprocessing to the Internet of Things cloud platform; S14: data analysis, using cloud computing and big data technology to deeply analyze the data after preprocessing, and extracting the safety state information of the dam foundation; S15: monitoring and early warning, real-time display of the monitoring data of the dam foundation on the Internet of Things cloud platform, and automatic triggering of the early warning mechanism when the safety state of the dam foundation exceeds the preset threshold according to the data analysis results.

[0020] As described above, the present application realizes accurate grasp of the safety state of the dam foundation by real-time monitoring of key parameters of the dam foundation by intelligent sensors, combined with cloud computing and big data technology. This method not only improves the real-time and accuracy of monitoring, but also automatically triggers the early warning mechanism when the safety state of the dam foundation is abnormal, providing a strong guarantee for the safe operation of the hydropower station and effectively reducing the risk of dam foundation safety accidents.

[0021] As a preferred, when using the deployed intelligent sensors to collect real-time monitoring data of the dam foundation, and preprocessing the collected raw data, the following steps are included: S21: data acquisition, using sensors to collect real-time monitoring data of the dam foundation, including water level, seepage pressure and displacement deformation; S22: data cleaning, including removing outliers, removing duplicates, handling missing values and removing noise in the data; S23: data formatting processing, including data type conversion, data standardization processing and data encoding processing, wherein the data type conversion is to convert the fields in the data set from one data type to a pre-set data type, the data standardization processing is to scale the numerical data in the data set to a pre-set range, and the data encoding is to convert text and category data into numerical data.

[0022] As described above, the application effectively removes outliers, repeated values, missing values and noise by collecting key monitoring data of the dam foundation in real time and through strict data cleaning and formatting processing, ensuring the accuracy and consistency of the data. At the same time, data type conversion, standardization processing and coding processing and other steps further improve the usability and comparability of the data, providing a high-quality data basis for subsequent data analysis and monitoring and early warning, thereby enhancing the reliability and accuracy of the dam foundation monitoring system of the hydropower station.

[0023] As a preferred, in processing the missing values in the data, the missing values in the data are filled according to the data type selection filling strategy, wherein the selectable filling strategy includes mean, median, mode and K nearest neighbor algorithm, and when the proportion of missing values is lower than the set first threshold, the data containing missing values is directly deleted, and the first threshold is calculated by the following formula: ; Wherein, q is the first threshold, is the total amount of data collected, is the required data amount, is the set data qualified threshold, wherein, The value of is related to the data type.

[0024] As described above, the above technical solution of the application flexibly uses a plurality of filling strategies such as mean, median, mode and K nearest neighbor algorithm to fill the missing data in the optimal way when processing the missing values in the data, ensuring the integrity and continuity of the data. At the same time, by setting the first threshold and comprehensively calculating according to the total amount of data, the required data amount and the data qualified threshold, when the proportion of missing values is lower than the threshold, the data containing missing values is directly deleted, which not only avoids the error that may be introduced by excessive reliance on filling strategy, but also ensures the quality and effectiveness of the data set, providing more accurate data support for the dam foundation monitoring of the hydropower station.

[0025] As a preferred, when using cloud computing and big data technology to deeply analyze the data after preprocessing and extract the safety state information of the dam foundation, the following steps are included: S31: Model building, using the set data analysis algorithm to build a data analysis model, wherein the set data analysis algorithm includes classification algorithm, regression algorithm, clustering algorithm and dimension reduction algorithm; S32: Algorithm training, using the pre-prepared labeled data to train the model, and evaluating the model through cross-validation; S33: Algorithm implementation, inputting the preprocessed data into the model for analysis, and using the model to extract the safety state information of the dam foundation; S34: result verification, using actual observation data and expert experience to verify the analysis results, and optimizing the model according to the verification results; S35: result interpretation, interpreting the analysis results, and extracting valuable information and insights.

[0026] As described above, the present application realizes in-depth analysis of preprocessed data by constructing a data analysis model containing multiple algorithms such as classification, regression, clustering and dimensionality reduction, and training and cross-validation using pre-prepared labeled data, accurately extracts the safety state information of the dam foundation. At the same time, the actual observation data and expert experience are combined to verify and optimize the analysis results, ensuring the accuracy and reliability of the analysis results, providing strong support for accurate assessment of the safety state of the dam foundation, and extracting valuable information and insights through result interpretation, enhancing the scientificity and effectiveness of decision-making.

[0027] Please refer to Figure 2 The present application provides an embodiment: a water power station dam foundation monitoring system based on Internet of Things, comprising: A data acquisition module for acquiring various state information of the water power station unit and fixed measurement point information of the dam foundation; An Internet of Things module containing a sensor network and a communication interface, for sending the data collected by the data acquisition module to the data processing module through Internet of Things technology; A data processing module for receiving the data collected by the data acquisition module and preprocessing and storing the data; A data transmission module for transmitting the data results of the data processing module to the Internet of Things cloud platform through encrypted communication method; An Internet of Things cloud platform for receiving the data transmitted by the data transmission module and analyzing the data to obtain the state information of the water power station dam foundation.

[0028] As described above, the present application realizes real-time monitoring and accurate analysis of the state of the water power station unit and the dam foundation by integrating multiple module functions such as data acquisition, Internet of Things transmission, data processing, encrypted communication and cloud platform analysis, effectively improving the safety and reliability of the water power station operation, providing scientific data support for dam foundation maintenance and management, and reducing potential safety risks.

[0029] As a preferred, the data acquisition module comprises: A11: a water level sensor for real-time monitoring of the change of the water level of the water reservoir or the dam front of the water power station; A12: a water pressure sensor for measuring the water pressure in the dam foundation and the reservoir; A13: a temperature sensor for monitoring the temperature change of the water power station unit and the dam foundation; A14: a humidity sensor for monitoring the environmental humidity changes of the hydropower unit and the dam foundation in real time; A15: a rotating speed sensor for monitoring the rotating speed index of the hydropower unit in real time; A16: a current and voltage sensor for monitoring the current and voltage indexes of the hydropower unit in real time.

[0030] As described above, the application integrates various sensors such as water level, water pressure, temperature, humidity, rotating speed and current and voltage, comprehensively and in real time monitors the key operating parameters of the hydropower unit and the dam foundation, provides detailed and accurate data support for the safe operation and efficient management of the hydropower station, significantly improves the accuracy and response speed of the monitoring, and helps to discover and handle potential safety hazards in time.

[0031] As a preferred, the data acquisition module is installed in the interior of the dam foundation of the hydropower station, the data acquisition module is connected with the Internet of Things module through the Internet of Things, the Internet of Things module is installed in the interior of the dam foundation of the hydropower station, the Internet of Things module is connected with the data processing module through the wired network, the data processing module is installed in the interior of the dam foundation of the hydropower station, the data processing module is connected with the Internet of Things cloud platform through the data transmission module, and the data processing module sends the data processing result to the Internet of Things cloud platform and stores the original data.

[0032] As described above, the application solves the problem of high network occupation and low data transmission efficiency in the prior art that the original data is directly transmitted to the cloud platform in real time. The application installs the data acquisition module, the Internet of Things module and the data processing module in the interior of the dam foundation of the hydropower station, connects the data acquisition module with the Internet of Things module through the Internet of Things, connects the Internet of Things module with the data processing module through the wired network, and then pre-processes the original data by the data processing module, and efficiently and safely sends the processing result to the Internet of Things cloud platform through the data transmission module, and stores the original data locally. This scheme not only reduces the load of network transmission and reduces the occupation of network resources, but also improves the stability and safety of data transmission, and at the same time ensures the integrity and traceability of data, and provides more reliable technical support for real-time monitoring and data analysis of the dam foundation of the hydropower station.

[0033] As a preferred, the power module is further included, and the power module includes: A21: a first power module for providing uninterrupted stable power supply for the water level sensor, the water pressure sensor and the temperature sensor, realizing real-time data acquisition of the water level sensor, the water pressure sensor and the temperature sensor; A22: a second power module for providing intermittent power supply for the humidity sensor, the rotating speed sensor and the current and voltage sensor, realizing intermittent data acquisition of the humidity sensor, the rotating speed sensor and the current and voltage sensor; A23: a backup power module, used to provide power for the water level sensor, water pressure sensor, temperature sensor, humidity sensor, rotational speed sensor and current voltage sensor when the first power module and the second power module fail.

[0034] As described above, the present application, relative to the prior art, uses a single power module to provide continuous power for all sensors, which may cause high power consumption and insufficient system stability. The present application innovatively adopts a hierarchical power module design: the first power module provides uninterrupted stable power for the key sensors (water level, water pressure, temperature), ensuring the reliability and continuity of real-time data acquisition; the second power module provides intermittent power for the non-key sensors (humidity, rotational speed, current voltage), which meets the data acquisition requirements and effectively reduces the energy consumption; at the same time, the existence of the backup power module further enhances the fault tolerance and stability of the entire system. This hierarchical power supply scheme not only optimizes energy utilization and improves system efficiency, but also significantly enhances the reliability and durability of the dam foundation monitoring system of the hydropower station.

[0035] As a preferred embodiment, the data processing module, when processing the data of the position sensor, water pressure sensor, temperature sensor, humidity sensor, rotational speed sensor and current voltage sensor, includes calibrating the sensors at regular intervals, wherein the principle formula for calibrating the sensors is: Y 校准= Y 原始+ Δ; wherein Y 校准 is the calibration value, Y 原始 is the original measurement value, and Δ is the predicted deviation value, which is obtained by machine learning model prediction.

[0036] As described above, the present application, relative to the prior art, uses a fixed calibration parameter to calibrate the sensors, which may cause inaccurate calibration due to environmental changes or sensor aging. The present application adopts a dynamic calibration method based on machine learning model prediction. This method calibrates the sensors at regular intervals and uses a machine learning model to predict the possible deviation value of the sensor, thereby calculating a more accurate calibration value. This scheme not only improves the accuracy and reliability of sensor data, but also adapts to the effects of environmental changes and sensor aging, effectively extending the service life of the sensors and providing more accurate data support for the dam foundation monitoring of the hydropower station.

[0037] As a preferred embodiment, the data transmission module, when transmitting the data results of the data processing module to the Internet of Things cloud platform through an encrypted communication method, includes the following steps: S41: first, use a preset encryption algorithm to encrypt the data results processed by the data processing module; S42: signal strength detection is performed, if the signal strength is good, data transmission is performed, if the signal strength is poor, waiting for one minute, then signal strength detection is performed again; S43: if signal transmission fails and signal strength detection is performed three times, then waiting for ten minutes, information sending is performed again; S44: if data is not successfully sent after step S43 is performed three times, the data is marked as to-be-transmitted data.

[0038] As described above, the present application solves the problem of lack of encryption protection and retransmission mechanism in the data transmission process, which may lead to data leakage and transmission failure, compared with the prior art of directly transmitting data to the Internet of Things cloud platform. The present application adopts encryption communication and intelligent retransmission mechanism. Firstly, the present application uses a preset encryption algorithm to encrypt the data, ensuring the security of data transmission. Secondly, the signal strength detection mechanism is used to perform data transmission when the signal is good, avoiding transmission interruption. If the signal is not good or transmission fails, multiple retransmissions are performed according to the preset strategy until the data is successfully sent or marked as to-be-transmitted data. This scheme not only enhances the security of data transmission, but also significantly improves the reliability and stability of transmission, ensuring the timely and accurate uploading of the monitoring data of the dam foundation of the hydropower station.

[0039] The embodiments of the present application are described in detail above in combination with the drawings, but the present application is not limited to the above embodiments, and various changes can be made within the knowledge of those skilled in the art without departing from the purpose of the present application.

Claims

1. A method for monitoring the dam foundation of a hydropower station based on the Internet of Things; characterized in that: Comprise the following steps: S11: equipment deployment, in the key position of the dam foundation of the hydropower station, deploy intelligent sensors for real-time monitoring of water level change, seepage condition and displacement deformation of the dam foundation, including water level sensor, seepage pressure sensor and displacement sensor; S12: data acquisition and preprocessing, using the deployed intelligent sensor to collect the monitoring data of the dam foundation in real time, and preprocessing the collected raw data; S13: data transmission, using wireless network and wired network to transmit the raw data after preprocessing to the Internet of Things cloud platform; S14: data analysis, using cloud computing and big data technology, the data after preprocessing is analyzed in depth, and the safety state information of the dam foundation is extracted; S15: monitoring and early warning, on the Internet of Things cloud platform, real-time display of the monitoring data of the dam foundation, and according to the data analysis result, when the safety state of the dam foundation exceeds the preset threshold, the early warning mechanism is triggered automatically.

2. The method for monitoring the dam foundation of a hydropower station based on the Internet of Things according to claim 1, characterized in that: When using the deployed intelligent sensor to collect the monitoring data of the dam foundation in real time, and preprocessing the collected raw data, comprising the following steps: S21: data acquisition, using the sensor to collect the monitoring data of the dam foundation in real time, including water level, seepage pressure and displacement deformation; S22: data cleaning, including removing outliers, removing repeated values, processing missing values and removing noise in data; S23: data format processing, including data type conversion, data standardization processing and data encoding processing, wherein the data type conversion is to convert the fields in the data set from one data type to the preset data type, the data standardization processing is to scale the numerical data in the data set to the preset range, and the data encoding is to convert the text and category data into numerical data.

3. The method for monitoring the dam foundation of a hydropower station based on the Internet of Things according to claim 2, characterized in that: When processing the missing values in the data, according to the data type, the missing values in the data are filled by selecting the filling strategy, wherein the selectable filling strategy includes mean, median, mode and K nearest neighbor algorithm, and when the proportion of missing values is lower than the set first threshold, the data containing missing values is directly deleted, and the first threshold is calculated by the following formula: ; wherein q is a first threshold value, is the total amount of data collected, is the set required amount of data, is the set data eligibility threshold, wherein, the value of is related to the data type.

4. The method for monitoring the dam foundation of a hydropower station based on the Internet of Things according to claim 3, characterized in that: When using cloud computing and big data technology, the data after preprocessing is analyzed in depth, and the safety state information of the dam foundation is extracted, comprising the following steps: S31: model building, using the set data analysis algorithm to build the data analysis model, wherein the set data analysis algorithm includes classification algorithm, regression algorithm, clustering algorithm and dimension reduction algorithm; S32: algorithm training, using the pre-prepared labeled data to train the model, and evaluating the model by cross validation; S33: algorithm implementation, inputting the preprocessed data into the model for analysis, using the model to extract the safety state information of the dam foundation; S34: result verification, using actual observation data and expert experience to verify the analysis result, and optimizing the model according to the verification result; S35: result interpretation, interpreting the analysis result, extracting valuable information and insight.

5. The water power station dam foundation monitoring system based on the Internet of Things according to claim 4, characterized in that: Comprise: data acquisition module, for collecting various state information of the hydropower unit and fixed point information of the dam foundation; The Internet of Things module comprises a sensor network and a communication interface, and is used to send the data collected by the data collection module to the data processing module through the Internet of Things technology. The data processing module is used to receive the data collected by the data collection module, and to pre-process and store the data. The data transmission module is used to transmit the data results of the data processing module to the Internet of Things cloud platform through an encrypted communication method. The Internet of Things cloud platform is used to receive the data transmitted by the data transmission module, and to analyze the data to obtain the state information of the dam foundation of the hydropower station.

6. The water power station dam foundation monitoring system based on the Internet of Things according to claim 5, characterized in that: The data collection module comprises: A11: a water level sensor, which is used to monitor the change of the water level of the reservoir or the front of the dam of the hydropower station in real time; A12: a water pressure sensor, which is used to measure the water pressure in the dam foundation and the reservoir; A13: a temperature sensor, which is used to monitor the temperature change of the unit and the dam foundation of the hydropower station; A14: a humidity sensor, which is used to monitor the environmental humidity change of the unit and the dam foundation of the hydropower station in real time; A15: a speed sensor, which is used to monitor the speed index of the unit of the hydropower station in real time; A16: a current and voltage sensor, which is used to monitor the current and voltage indexes of the unit of the hydropower station in real time.

7. The water power station dam foundation monitoring system based on the Internet of Things according to claim 6, characterized in that: The data collection module is installed in the interior of the dam foundation of the hydropower station, the data collection module is connected with the Internet of Things module through the Internet of Things, the Internet of Things module is installed in the interior of the dam foundation of the hydropower station, the Internet of Things module is connected with the data processing module through a wired network, the data processing module is installed in the interior of the dam foundation of the hydropower station, the data processing module is connected with the Internet of Things cloud platform through the data transmission module, and the data processing module sends the data processing results to the Internet of Things cloud platform and stores the original data.

8. The water power station dam foundation monitoring system based on the Internet of Things according to claim 7, characterized in that: The power module comprises: A21: a first power module, which is used to provide uninterrupted stable power supply for the water level sensor, the water pressure sensor and the temperature sensor, and to realize the real-time data collection function of the water level sensor, the water pressure sensor and the temperature sensor; A22: a second power module, which is used to provide intermittent power supply for the humidity sensor, the speed sensor and the current and voltage sensor, and to realize the intermittent data collection of the humidity sensor, the speed sensor and the current and voltage sensor; A23: a backup power module, which is used to provide power supply for the water level sensor, the water pressure sensor, the temperature sensor, the humidity sensor, the speed sensor and the current and voltage sensor when the first power module and the second power module fail.

9. The water power station dam foundation monitoring system based on the Internet of Things according to claim 8, characterized in that: When the data processing module processes the data of the position sensor, the water pressure sensor, the temperature sensor, the humidity sensor, the speed sensor and the current and voltage sensor, the data processing module comprises calibrating the sensors at regular intervals, wherein the principle formula for calibrating the sensors is: Y 校准= Y 原始+ Δ; where Y 校准 is a calibration value, Y 原始 is an original measurement value, and Δ is a predicted deviation value, the specific value of Δ being predicted according to the machine learning model.

10. The water power station dam foundation monitoring system based on the Internet of Things according to claim 9, characterized in that: When the data transmission module transmits the data results of the data processing module to the Internet of Things cloud platform through an encrypted communication method, the data transmission module comprises the following steps: S41: first, the data results processed by the data processing module are encrypted by using a preset encryption algorithm; S42: signal strength detection is performed, if the signal strength is good, data transmission is performed, if the signal strength is poor, the signal strength detection is performed again after waiting for one minute; S43: If the signal transmission fails and the signal strength is detected three times, wait for ten minutes, and then re-perform the information sending; S44: If the data is still not successfully sent after three times of step S43, mark the data as to-be-transmitted data.

Images