Hydroelectric power generation equipment remote monitoring system based on Internet of Things technology

Abstract

The invention discloses a hydroelectric power generation equipment remote monitoring system based on the Internet of Things technology. The system comprises a sensor node, a gateway station, a cloud server and the like, and the sensor node is composed of various sensors, a microcontroller unit and the like, collects data such as water level, flow and temperature, and transmits the data to the gateway station through a LoRa module; after processing, the gateway station uploads data to the cloud server through Wi-Fi, and can give an alarm through 4G in case of power failure; the cloud server is used for storing data. Data transmission supports LoRa wireless, Wi-Fi and polling and event-driven modes, and the analysis processing module adopts an ARIMA model and the like to carry out anomaly detection and trend prediction. The system can operate stably after being installed and debugged, the performance is ensured through daily maintenance and upgrading, the equipment reliability, the operation efficiency and the operation and maintenance management level are improved in practical application, and a high-efficiency intelligent solution is provided for hydroelectric power generation equipment monitoring.

Description

Technical Field

[0001] The present invention relates to the field of remote monitoring of hydropower generation equipment, and in particular to a remote monitoring system of hydropower generation equipment based on Internet of Things technology. Background Art

[0002] As energy demand continues to grow, hydropower, as a clean energy source, plays an important role in power supply. The stable operation of hydropower equipment is crucial to ensuring the reliability of power supply. Traditional monitoring methods for hydropower equipment have many limitations, such as limited monitoring range, incomplete data collection, poor real-time performance, and low intelligence.

[0003] In terms of data collection, previous sensor technologies may not be able to accurately measure key parameters such as water level, flow, temperature, etc., or the sensor’s stability and durability are insufficient, making it difficult to adapt to complex hydropower generation environments. Data transmission mostly relies on limited wired networks, which have high wiring costs and poor flexibility, and face many difficulties in the construction of hydropower stations in remote mountainous areas or complex terrain. At the same time, traditional monitoring systems have limited data analysis and processing capabilities, making it difficult to accurately predict the operating status of equipment and provide fault warnings. Measures can often only be taken after equipment failures occur, resulting in increased maintenance costs, reduced power generation efficiency, and even affecting the stable operation of the power system.

[0004] The rapid development of Internet of Things technology has brought new opportunities for monitoring hydropower equipment. Through the organic combination of sensors, communication technology and data processing, the Internet of Things can achieve comprehensive perception of the equipment's operating status, real-time data transmission and intelligent analysis, effectively overcome the shortcomings of traditional monitoring methods, and improve the operation management level and safety of hydropower equipment. Summary of the invention

[0005] The purpose of the present invention is to provide a remote monitoring system for hydropower equipment based on Internet of Things technology to solve the problems raised in the above background technology.

[0006] To achieve the above object, the present invention provides the following technical solution: a remote monitoring system for hydropower equipment based on Internet of Things technology, comprising:

[0007] Sensor node module:

[0008] It consists of a microcontroller unit, various types of sensors, a LoRa transceiver module, a display unit, and a battery power supply unit, and is used to collect the operating data of the hydropower equipment and transmit it to the gateway station;

[0009] The microcontroller unit uses a specific control chip to control the overall operation of the sensor node and send the data collected by the sensor to the gateway station through the LoRa transceiver module;

[0010] The various types of sensors include pressure sensors that measure water level, which work based on the principle of hydrostatic pressure; electromagnetic flow meters that measure flow, which operate based on the principle of electromagnetic induction; and thermistor sensors that measure temperature, which use the material's resistance to change with temperature to monitor;

[0011] The LoRa transceiver module works at a specific frequency to achieve long-distance data transmission; the display unit is used to display measurement data and node working status; the battery power supply unit ensures that the sensor node continues to work for a certain period of time when the power is off;

[0012] The sensor node has a specific operation control logic, reads data at a preset frequency, determines faults based on voltage thresholds, and performs corresponding data transmission operations;

[0013] Gateway module:

[0014] It consists of a control unit, a LoRa receiving unit, a WiFi communication unit, a 4G communication unit, a display unit and a power supply unit. It is responsible for receiving sensor node data and uploading it to the cloud server. It also has a power failure alarm function.

[0015] The control unit uses a specific kit to receive sensor node data through the LoRa receiving unit, and after processing, sends it to the cloud server via the WiFi communication unit;

[0016] When the 4G communication unit detects a power outage, it receives a trigger signal from the control unit and sends a text message alert to the user; the display unit is used to display relevant information; the power supply unit supplies power to each component of the gateway station, and the data is uploaded at specific time intervals during the experiment;

[0017] Cloud server module: The cloud server is used to store the operating data of hydropower equipment. Managers can access specific data channels through mobile terminals to achieve real-time monitoring of data.

[0018] Data transmission link module:

[0019] Establish a LoRa wireless transmission link between the sensor node and the gateway station to ensure stable data transmission over long distances;

[0020] Build a WiFi transmission channel between the gateway station and the cloud server to ensure efficient data upload;

[0021] Data transmission modes include polling and event-driven. In polling mode, the data acquisition device requests data from the sensor periodically. In event-driven mode, the sensor actively sends data to the data acquisition device when a specific event is triggered.

[0022] Data analysis and processing module:

[0023] Introducing data analysis algorithms based on specific time series analysis models to detect anomalies and predict trends in monitoring data;

[0024] This model transforms non-stationary data into stationary series through a specific difference method and then builds the model. The model formula is: (Where X t For time series data, is the autoregressive coefficient, θ i is the moving average coefficient, ε t is white noise);

[0025] The residual between the actual observed value and the model predicted value is calculated and compared with the preset threshold to determine whether the data is abnormal. The threshold is determined by statistical or machine learning methods based on actual conditions and experience.

[0026] Furthermore, the microcontroller unit also includes a data cache module, which is used to cache sensor measurement data within a certain period of time when the sensor data acquisition frequency is high or the network transmission is temporarily interrupted to ensure that the data will not be lost; the data cache module adopts a first-in-first-out FIFO data storage structure, and its cache capacity is dynamically adjusted according to the frequency of sensor data acquisition and the stability of network transmission. After the network returns to normal, the earliest collected data in the cache is transmitted first to ensure the timeliness and continuity of the data.

[0027] Furthermore, the pressure sensor is a high-precision ceramic capacitive pressure sensor with a measurement accuracy of up to ±0.1% FS. It has good stability and anti-interference ability and can accurately measure the water level in harsh hydropower generation environments. The ceramic capacitor sensitive element inside the sensor adopts a special packaging process to effectively prevent the intrusion of moisture and impurities, thereby extending the service life of the sensor. At the same time, the sensor is equipped with an automatic temperature compensation function, which can compensate in real time for the impact of ambient temperature changes on the measurement results, further improving the measurement accuracy.

[0028] Furthermore, the electrodes of the electromagnetic flowmeter are made of corrosion-resistant Hastelloy material, which can adapt to the measurement of water flows containing complex components such as silt, corrosive substances, etc.; the inner wall of its measuring tube is coated with a special anti-fouling coating to reduce the influence of impurities in the water flow on the measurement accuracy; in addition, the electromagnetic flowmeter has an adaptive flow rate range adjustment function, which can automatically optimize the measurement parameters according to the actual water flow velocity, ensuring accurate flow measurement under different flow rate conditions, and the measurement range is 0.01m3 / s-10m3 / s.

[0029] Furthermore, the thermistor sensor adopts a high-precision negative temperature coefficient thermistor, whose resistance temperature coefficient is between -4% / ℃ and -6% / ℃, and can respond to temperature changes quickly and accurately; the outside of the sensor is wrapped with a high thermal conductivity silicone protective cover, which can not only effectively protect the thermistor from external physical damage, but also ensure that heat is quickly transferred to the thermistor, thereby improving the response speed and accuracy of temperature measurement; at the same time, the sensor has a built-in temperature drift compensation circuit to correct the temperature measurement deviation caused by long-term operation in real time.

[0030] Furthermore, the LoRa transceiver module supports adaptive power adjustment function, which can automatically adjust the transmission power according to the distance between the sensor node and the gateway station, the signal strength and the environmental interference, thereby reducing power consumption while ensuring reliable communication; its transmission power adjustment range is 10dBm-20dBm, the spreading factor can be dynamically adjusted between 7-12, and the coding rate supports 4 / 5, 4 / 6, 4 / 7, 4 / 8 options to adapt to different communication environment requirements.

[0031] Furthermore, the 4G wireless module in the gateway station supports multi-band communication and can automatically switch between frequency bands such as GSM900, DCS1800, PCS1900, etc., ensuring that SMS alerts can be sent stably in different regions and network environments; the module has signal strength detection and automatic reconnection functions. When the signal strength is lower than the preset threshold or the communication is interrupted, it automatically searches and switches to a frequency band with a stronger signal for reconnection, ensuring that the alarm information is delivered to the user in a timely and accurate manner.

[0032] Furthermore, the ARIMA model in the data analysis and processing module adopts a rolling forecast update mechanism, and re-estimates and updates the model parameters using newly collected data at regular time intervals to adapt to the dynamic changes in the operating status of the hydropower equipment and improve the accuracy of trend prediction; the time interval for model update is dynamically set according to the stability of the equipment operation and the frequency of data changes, and the update interval is shortened when the equipment operating status changes rapidly, and vice versa.

[0033] Furthermore, the event-driven data transmission method in the data transmission link module supports custom event trigger conditions. Users can flexibly set the thresholds, abnormality types and other conditions for triggering sensor data transmission according to the specific operating requirements and safety standards of the hydropower equipment, thereby improving the system's monitoring sensitivity and response speed to specific faults and abnormal conditions.

[0034] Furthermore, the cloud server module has data backup and recovery functions, which can perform full or incremental backup of the stored hydropower equipment operating data on a regular basis every day, and store the backup data in redundant servers at other locations; when the main server fails or data is lost, the data can be quickly restored from the backup server to ensure the security and integrity of the data and the continuous and stable operation of the monitoring system.

[0035] Compared with the prior art, the present invention has the following beneficial effects:

[0036] Various types of high-precision sensors can accurately collect key data such as water level, flow, temperature, etc., and fully reflect the operating status of hydropower equipment. For example, high-precision ceramic capacitive pressure sensors and specially designed electromagnetic flowmeters, thermistor sensors, etc. can work stably in harsh environments, providing a reliable basis for subsequent data analysis and decision-making.

[0037] LoRa wireless transmission technology combined with adaptive power adjustment function ensures long-distance, low-power data transmission between sensor nodes and gateway stations, adapting to complex terrain and changing environments. The coordinated application of Wi-Fi and 4G communication technologies ensures stable data upload to the cloud server and timely sends alarms in emergency situations such as power outages. Polling and event-driven data transmission methods not only ensure the timeliness of data, but also can be flexibly adjusted according to actual conditions to reduce system resource consumption.

[0038] The data analysis and processing module based on the ARIMA model can accurately capture trends and anomalies in the data through a rolling forecast update mechanism, detect potential faults in advance, provide sufficient time for equipment maintenance, reduce maintenance costs, and improve power generation efficiency; and customize the setting of event trigger conditions.

[0039] The reasonable architecture design of the gateway station and sensor nodes enables it to adapt to the monitoring needs of hydropower equipment of different scales and complexities. The data backup and recovery function of the cloud server ensures data security, guarantees the continuous and stable operation of the system, facilitates the subsequent upgrade and expansion of the system, and reduces maintenance costs.

[0040] Managers can access data on the cloud server in real time through mobile devices, so they can promptly understand the operating status of the equipment, make scientific and reasonable operation adjustments and maintenance decisions based on data analysis results, and improve the overall management level and economic benefits of the hydropower station. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 It is a system flow chart of the present invention. DETAILED DESCRIPTION

[0042] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0043] See also Figure 1 ,The present invention provides a technical solution: a remote monitoring system for hydropower equipment based on the Internet of Things technology, which is mainly composed of sensor nodes, gateway stations, cloud servers and related data transmission links and data analysis and processing modules.

[0044] The microcontroller unit uses a high-performance, low-power Arduino Nano kit as the core control component of the sensor node. It is responsible for coordinating the data collection and processing of each sensor and the data interaction with the LoRa transceiver module. The data cache module is integrated in the microcontroller unit and adopts a first-in-first-out data storage structure. The cache capacity is initially set to store data collected within 10 minutes. In actual operation, the cache capacity is dynamically adjusted according to the sensor collection frequency and network transmission stability. For example, when the sensor collection frequency is increased to 2 times per second, the cache capacity is automatically increased to store data within 15 minutes; when the network transmission is frequently interrupted, the cache capacity is further increased to ensure that data will not be lost.

[0045] The pressure sensor uses a high-precision ceramic capacitive pressure sensor with a measurement accuracy of up to ±0.1% FS; the ceramic capacitor sensitive element inside the sensor uses a special packaging process, such as sealant packaging, to effectively prevent moisture and impurities from invading. During installation, the pressure sensor is installed at a suitable underwater depth at key locations such as the dam or water inlet of a hydropower station, and its stability is ensured by a dedicated fixed bracket. The bottom of the sensor is exposed to the water, and the water level is measured using the relationship between the static pressure of the liquid and the depth. The measurement principle is based on the formula P = ρgh (where P is pressure, ρ is liquid density, g is gravity acceleration, and h is depth). The sensor converts the measured pressure change into an electrical signal output. At the same time, the sensor is equipped with an automatic temperature compensation function, which monitors the ambient temperature in real time through a built-in temperature sensor, and uses a pre-stored temperature compensation algorithm to correct the measurement results to further improve the measurement accuracy.

[0046] The electromagnetic flowmeter uses a product whose electrode material is corrosion-resistant Hastelloy, and the inner wall of the measuring tube is coated with a polytetrafluoroethylene anti-fouling coating. The electromagnetic flowmeter is installed in the water pipeline of the hydropower station to ensure that it is perpendicular to the direction of the water flow and the water flow in the pipeline meets the requirements. The electromagnetic flowmeter works according to the Faraday electromagnetic induction principle. When water passes through the magnetic field, the conductor in the liquid generates an electromotive force in the direction perpendicular to the magnetic field and the flow of the liquid, and its magnitude is proportional to the flow rate. By measuring the magnitude of the induced current, the flow rate is calculated using the built-in signal processing circuit, and then the flow rate is calculated based on the cross-sectional area of ​​the pipeline. The electromagnetic flowmeter has an adaptive flow rate range adjustment function. The built-in flow rate sensor monitors the water flow rate in real time. When the flow rate exceeds the preset range, the measurement parameters are automatically adjusted to ensure that the flow rate can be accurately measured under different flow rate conditions. The measurement range is 0.01m3 / s-10m3 / s.

[0047] The thermistor sensor uses a high-precision negative temperature coefficient thermistor, and its resistance temperature coefficient is between -4% / ℃ and -6% / ℃. The sensor is wrapped with a high thermal conductivity silicone protective cover and installed near the key heating parts of the hydropower equipment, such as the stator and rotor of the generator, to ensure accurate monitoring of the temperature changes of the equipment. When working, a constant current source is connected to form a circuit. When the ambient temperature changes, the resistance value of the thermistor changes accordingly, causing the voltage value in the circuit to change. The high-precision analog-to-digital converter built into the sensor converts the voltage value into a digital signal, and then passes through the data processing algorithm in the microcontroller unit to deduce the ambient temperature based on the pre-calibrated resistance-temperature relationship curve. At the same time, the sensor has a built-in temperature drift compensation circuit, which automatically performs temperature calibration at regular intervals to correct the temperature measurement deviation caused by long-term work.

[0048] The LoRa transceiver module uses a product with an operating frequency of 433MHz and supports adaptive power adjustment. Its transmission power adjustment range is 10dBm-20dBm, the spreading factor can be dynamically adjusted between 7-12, and the coding rate supports multiple options of 4 / 5, 4 / 6, 4 / 7, and 4 / 8. When the distance between the sensor node and the gateway station is close, the signal strength is good, and the interference is small, the LoRa transceiver module automatically reduces the transmission power to 10dBm, and selects a smaller spreading factor of 7 and a higher coding rate of 4 / 5 to increase the data transmission rate; when the distance is far, the signal is weak or the interference is large, the module automatically increases the transmission power to 20dBm, increases the spreading factor to 12, and reduces the coding rate to 4 / 8, enhancing the signal's anti-interference ability and ensuring reliable data transmission.

[0049] The LCD display uses a 1602 LCD display module and is connected to the microcontroller unit via a data line. When the sensor node is working normally, the display screen displays the currently collected water level, flow, temperature and other data in real time, as well as the working status information of the sensor node, such as battery power, data transmission status, etc. When the system detects an abnormal situation, the display screen will highlight the abnormal information, such as "abnormal water level: too high" or "abnormal temperature: overheating", etc., to facilitate on-site operation and maintenance personnel to quickly understand the operating status of the equipment.

[0050] The battery charger provides charging function for the rechargeable battery of the sensor node. The rechargeable battery adopts high-performance lithium-ion battery with a capacity of 3.7V / 2200mAh. The battery charger has overcharge protection, over-discharge protection and short-circuit protection functions to ensure safe charging and discharging of the battery. Under normal power supply conditions, the battery charger charges the battery and powers the sensor node; when a power outage occurs, the battery automatically switches to power supply mode to continuously power the sensor node. By optimizing the power management algorithm, the sensor node can work continuously for more than 12 hours in the case of power outage. For example, when it is powered only by battery and the sensor collects data once per second, and the LoRa transceiver module transmits data every 5 minutes, the sensor node can work continuously for about 15 hours.

[0051] After the sensor node is started, the microcontroller unit first performs initialization operations, including setting sensor acquisition parameters, LoRa transceiver module parameters, data cache module parameters, etc. Then, the sensor data acquisition program is started at a preset frequency of once every 30 seconds.

[0052] After collecting data such as water level, flow rate, and temperature, the data first enters the data cache module for temporary storage. At the same time, the microcontroller unit judges the collected phase voltage value. If the phase voltage value is within the preset normal threshold range, the normal voltage range is 220V±10V, then continue to wait for the next collection; if the phase voltage value is lower or higher than the preset threshold, the control program immediately starts the re-check mechanism within 15 seconds.

[0053] The phase voltage value is collected again within 15 seconds and judged. If the phase voltage continues to exceed the threshold, the microcontroller unit packages all the data in the cache and sends the data to the gateway station through the LoRa transceiver module. After the transmission is completed, the data cache module is cleared to prepare for the next data collection. If the phase voltage returns to normal within 15 seconds, the data sending operation is canceled and the normal data collection and caching process continues.

[0054] The Arduino Nano kit acts as the core control unit in the gateway station, responsible for coordinating data interaction and workflow control between components such as the LoRa transceiver module, ESP32 Node MCU Wi-Fi module, 4G wireless module, and LCD display.

[0055] The 433MHz LoRa transceiver module matches the LoRa transceiver module in the sensor node to receive data from the sensor node. When receiving data, it parses and verifies the data according to the pre-set communication protocol to ensure the integrity and accuracy of the data. If the received data has errors or fails the verification, a retransmission request is immediately sent to the sensor node.

[0056] The ESP32NodeMCUWi-Fi module is used to realize data transmission between the gateway station and the cloud server. During initialization, configure the Wi-Fi connection parameters, such as SSID and password, and search and connect to the specified Wi-Fi network. After the connection is successful, a secure communication channel with the cloud server is established using the SSL / TLS encryption protocol. The received sensor data is packaged and processed according to the data format required by the cloud server, and then uploaded to the cloud server regularly through the Wi-Fi network. In the experiment, the data is uploaded every 5 minutes. During the data upload process, the network status is monitored in real time. If there is a network interruption or connection abnormality, it automatically tries to reconnect and resume data upload.

[0057] The 4G wireless module uses an industrial-grade module that supports multi-band communication, GSM900, DCS1800, PCS1900 and other frequency bands. When the gateway station is initialized, the 4G module is initialized and configured, including setting parameters such as APN, user name and password. The module has a signal strength detection function, which regularly detects the signal strength of the current frequency band and compares it with the preset threshold of -90dBm. When the signal strength is lower than the threshold, the frequency band search and switching program is started, and the signal is automatically switched to the frequency band with a stronger signal for communication. When the substation is detected to be out of power, ArduinoNano generates an external interrupt signal to the ESP32NodeMCU module, and the ESP32NodeMCU module executes the interrupt subroutine, calls the SMS sending function of the 4G wireless module, and sends an SMS alert to the pre-set user mobile phone number. The alarm information contains the time and location of the power outage and the possible cause of the fault.

[0058] The LCD display screen is used in the gateway station to display the system's operating status information, such as sensor node connection status, data transmission status, network signal strength, etc. At the same time, when an abnormal situation occurs in the system, the display screen will display detailed abnormal information to help operation and maintenance personnel quickly locate the problem.

[0059] The battery charger charges the backup battery in the gateway station to ensure that the gateway station can continue to work for a period of time when the external power supply is interrupted, maintaining the data transmission and alarm sending functions. The backup battery has a low battery detection function. When the battery power is less than 20%, the low battery warning message is displayed on the display screen, and a text message notification is sent to the operation and maintenance personnel to remind them to replace or charge in time.

[0060] After the gateway station is started, the ArduinoNano kit first initializes each module, including the LoRa transceiver module, Wi-Fi module, 4G module, etc., and establishes communication connections with the sensor nodes and cloud servers.

[0061] The LoRa transceiver module is in a listening state, waiting to receive data sent by the sensor node. Once the data is received, it is passed to the Arduino Nano for data processing. Data processing includes data unpacking, verification, format conversion and other operations, converting the sensor data into a data format suitable for Wi-Fi upload to the cloud server.

[0062] The processed data is uploaded to the cloud server through the ESP32NodeMCUWi-Fi module at preset time intervals. During the upload process, the upload status is monitored in real time. If the upload fails, the data is cached in the local storage and automatically re-uploaded after the network returns to normal.

[0063] At the same time, ArduinoNano continuously monitors the system status, including power status, network status, etc. When a power outage is detected, the 4G wireless module is immediately triggered to send a text message alert. During normal operation, the gateway station's own status information, such as device temperature, operating time, etc., is regularly sent to the cloud server so that managers can fully understand the system operation status.

[0064] The cloud server uses ThingSpeak cloud server, which has powerful data storage and processing capabilities. On the server side, an independent registration data channel is created for each hydropower equipment. The channel name is associated with the power station name or equipment number, which is convenient for managers to identify and manage. By setting up a strict user authority management mechanism, it is ensured that only authorized personnel can access and operate relevant data.

[0065] After the sensor nodes and gateway stations are installed, the LoRa wireless communication parameters are configured. According to the actual environment, the transmission power, spreading factor and coding rate of the LoRa transceiver module are initially set. In the hydropower station area with open terrain and less interference, the transmission power is set to 15dBm, the spreading factor is set to 9, and the coding rate is set to 4 / 6.

[0066] After establishing the communication connection, the sensor node and the gateway station will conduct communication tests regularly, including signal strength detection, data packet transmission success rate test, etc. According to the test results, the communication parameters are dynamically optimized using the adaptive power adjustment function of the LoRa transceiver module. For example, if the data packet transmission success rate is low, the system will automatically increase the transmission power or adjust the spread factor until a stable communication effect is achieved.

[0067] In order to improve the reliability of communication, a data retransmission and verification mechanism is used in the data transmission protocol. After the sensor node sends the data, it waits for the confirmation information from the gateway station. If the confirmation information is not received within the specified time, the sensor node automatically retransmits the data. After receiving the data, the gateway station performs data verification, such as checksum verification or cyclic redundancy check. If the verification fails, a retransmission request is sent to the sensor node.

[0068] When connecting to a Wi-Fi network, the gateway first searches for available Wi-Fi hotspots around it and selects the target Wi-Fi network to connect to based on the preset priority list. During the connection process, enter the correct SSID and password for identity authentication.

[0069] After establishing a Wi-Fi connection, the gateway station and the cloud server communicate data via TCP / IP protocol. Before data transmission, the data is encrypted to ensure data security during transmission. During data transmission, the network bandwidth and delay are monitored in real time. If network congestion or delay is too high, the data transmission rate is automatically adjusted or data caching and time-sharing transmission strategies are adopted to avoid data loss.

[0070] To ensure the integrity of the data, the cloud server rechecks and verifies the received data. If the data is found to be wrong or incomplete, a retransmission request is sent to the gateway station. At the same time, the cloud server records the log of each data transmission, including transmission time, data size, transmission results and other information, to facilitate subsequent query and analysis.

[0071] In the polling mode, the data acquisition device sends a request to the sensor at a preset time interval of 10 seconds to obtain the current sensor data. After receiving the request, the sensor immediately collects the data and returns it to the data acquisition device. This method can ensure the timeliness and integrity of the data, but it will increase the load and energy consumption of the system. To optimize the polling efficiency, the polling interval is dynamically adjusted according to the frequency of changes in sensor data. For example, for data that changes relatively slowly, such as water level and flow, the polling interval is appropriately extended by 30 seconds; for data that changes quickly, such as temperature, the polling interval is kept short at 10 seconds.

[0072] In the event-driven mode, the sensor monitors data changes in real time. When it is detected that the data exceeds the preset threshold, such as the water level exceeds the warning water level, the temperature exceeds the maximum temperature allowed by the device, etc., or an abnormality occurs, such as sensor failure, data transmission error, etc., or other preset conditions are triggered, such as specific operations such as device start and stop, the sensor immediately sends data to the data acquisition device. In order to realize the event-driven function, an intelligent judgment algorithm and trigger mechanism are built into the sensor. The sensor continuously collects data and compares it with the preset threshold. Once the trigger condition is met, the data sending program is immediately started. At the same time, in order to avoid false triggering, the trigger conditions are filtered and anti-shake processed. For example, when the water level data fluctuates multiple times in a short period of time and approaches the warning water level but does not actually exceed it, the event is not triggered to send data. The alarm data is only sent when the water level continues to exceed the warning water level for 1 minute.

[0073] When the system is initialized, historical water level, flow, temperature and other data for a certain period of one week are collected as training data for building the ARIMA model. First, the data is preprocessed, including data cleaning and data stationarity test. If the data is not stationary, it is converted into a stationary series through differential operation. For example, for water level data, if it is found that it has an obvious seasonal trend, first-order difference and seasonal difference processing are performed to make it meet the stationarity requirements of the ARIMA model.

[0074] According to the preprocessed data, the autocorrelation and partial autocorrelation of the data are analyzed using the autocorrelation function and partial autocorrelation function to determine the order (p, d, q) of the ARIMA model. For example, through analysis, it is found that the autocorrelation coefficient of the water level data is significantly not 0 at lag 1 and lag 2, and the partial autocorrelation coefficient is significantly not 0 at lag 1, and the data is stable after the first-order difference, so the order of the ARIMA model is preliminarily determined to be (1, 1, 1). Then, the maximum likelihood estimation method and other parameter estimation methods are used to estimate the autoregressive coefficients in the model. The moving average coefficient θ1 and constant term c and other parameters are used to construct a complete ARIMA model.

[0075] -During the operation of the monitoring system, the newly collected data is added to the model at regular intervals of 1 hour to update the model. The updating process includes recalculating the statistical characteristics of the data, the mean and variance, re-testing the data stability, re-determining the model order, and re-estimating the model parameters. By continuously updating the model, it can adapt to the dynamic changes in the operating status of the hydropower equipment and improve the accuracy of trend prediction.

[0076] The constructed ARIMA model is used to predict the real-time data collected by the sensor. For water level data, the water level change trend in the next 6 hours is predicted based on historical data and current data; for flow data, the flow change range in the dry season and flood season in different periods in the future is predicted; for temperature data, the temperature change of the equipment under different operating loads is predicted.

[0077] Calculate the residual between the actual observation value and the ARIMA model prediction value, that is, the prediction error. The residual calculation formula is (where e t is the residual, X t is the actual observed value, The residual is then compared with the preset threshold to determine whether there is an anomaly. The threshold is determined by combining statistical methods and experience. For example, for water level data, the mean and standard deviation are calculated based on the distribution of historical residual data, and the threshold is set to the mean plus 3 times the standard deviation. When the residual exceeds the threshold, it is determined to be an abnormal situation.

[0078] When an abnormality is detected, the system immediately marks and records the abnormal data, including the time when the abnormality occurred, the data type, the abnormal value, and the possible cause of the fault. At the same time, a detailed abnormal alarm SMS is sent to the management personnel through the 4G module of the gateway station. The SMS content contains a summary of the abnormal information and handling suggestions. On the monitoring platform, the abnormal data and related information are displayed in a highlighted manner, which is convenient for management personnel to quickly discover and handle.

[0079] In order to improve the accuracy and reliability of anomaly detection, a multi-model fusion method is used to make a comprehensive judgment on anomalies. In addition to the ARIMA model, other machine learning models such as support vector machines and neural networks are introduced for anomaly detection. Each model analyzes and predicts the data independently, and then the results of multiple models are combined through voting mechanisms or weighted averages. For example, when both the ARIMA model and the SVM model are judged as abnormal, and the neural network model is judged as normal, the comprehensive score is calculated according to the pre-set weights. If the comprehensive score exceeds the abnormal threshold, it is finally judged as abnormal. This multi-model fusion method can effectively reduce the misjudgment rate of a single model and improve the system's ability to detect complex abnormal situations.

[0080] Determine the installation location of the sensor node based on the layout and monitoring requirements of the hydropower equipment. For water level sensors, choose to install them at key measurement points in reservoirs or rivers, such as near dams, water inlets and outlets, to ensure that water level changes can be accurately measured. During installation, use a professional underwater mounting bracket to fix the sensor at a predetermined depth to ensure that the bottom of the sensor is in full contact with the water body, while avoiding damage to the sensor caused by water flow impact and entanglement of debris. The cables connecting the sensor and the data acquisition equipment are made of waterproof and corrosion-resistant materials, and are properly wired and fixed to prevent cable damage from affecting data transmission.

[0081] The flow sensor is installed on the straight section of the water pipeline to ensure that the water flow in the pipeline is smooth and fills the entire pipeline cross section. Before installation, clean and pre-treat the pipeline to remove impurities and dirt in the pipeline to ensure the cleanliness of the sensor measurement surface. Select a suitable sensor installation method according to the pipeline diameter, such as flange connection or threaded connection, and use a sealing gasket to ensure that there is no leakage at the connection. After installation, calibrate and debug the sensor, set the sensor's measurement parameters according to the actual parameters of the pipeline, and calibrate the sensor through a standard flow device to ensure that the measurement accuracy is within the allowable range.

[0082] Temperature sensors are installed at key heating parts of hydropower equipment, such as near generator stator windings, bearings, transformers, etc. Choose a suitable installation method, such as adhesive, bolt-on or plug-in, to ensure that the sensor is in close contact with the surface of the object being measured to improve the accuracy of temperature measurement. For large equipment, multiple temperature sensors may need to be installed to fully monitor the temperature distribution of the equipment. During the wiring process, pay attention to avoid contact between the sensor cable and high-temperature components to prevent cable aging and damage.

[0083] The gateway station is usually installed in the control room of the hydropower station or in a nearby communication room. Choose a well-ventilated, dry, and non-strong electromagnetic interference location. During installation, ensure that the gateway station equipment is firmly installed to avoid damage to the equipment due to vibration or collision. The LoRa antenna connecting the gateway station and the sensor node is installed at a higher position outdoors, and the antenna direction is adjusted to face the area where the sensor nodes are distributed to obtain the best signal reception effect. The antenna feeder uses a low-loss coaxial cable and ensures a reliable connection to prevent signal attenuation and interference.

[0084] Connect the WiFi module of the gateway station to the WiFi network inside the hydropower station to ensure that the network connection is stable and the bandwidth meets the data transmission requirements. If the WiFi signal coverage is insufficient or the signal quality is poor, consider adding a WiFi repeater or optimizing the WiFi network layout. Install the 4G wireless module and insert a valid SIM card to ensure that the module can be normally registered to the operator's network. During the installation process, arrange the 4G antenna reasonably to avoid interference with other antennas or devices.

[0085] After completing the hardware installation, power on the entire system to test whether the power supply of each device is normal and whether the device indicator light is correct. Then, conduct the LoRa communication test between the sensor node and the gateway station. Send test data at the sensor node end, and the gateway station receives and displays the data to check the accuracy and completeness of data transmission. By adjusting the parameters of the LoRa transceiver module, optimize the communication distance and signal quality, and ensure stable communication between the sensor node and the gateway station under different environmental conditions.

[0086] Test the WiFi connection and data upload function between the gateway station and the cloud server. Check whether the gateway station can successfully connect to the cloud server, upload test data, and correctly receive and store data on the cloud server. During the test, simulate abnormal conditions such as network interruption and signal interference to verify the system's automatic reconnection and data recovery functions. At the same time, check whether the data management functions of the cloud server, such as data query, statistical analysis, and report generation, are working properly.

[0087] Debug the data analysis and processing module, and use historical data and simulation data to train and test the ARIMA model and other related algorithms. Check the model's prediction accuracy and anomaly detection capabilities, adjust model parameters and algorithm settings based on test results, and optimize the system's data analysis performance. Verify by comparing with actual equipment operation data to ensure that the system can accurately identify changes in equipment operation status and detect potential faults in a timely manner.

Claims

1. A remote monitoring system for hydropower equipment based on Internet of Things technology, characterized in that: include: Sensor node module: It consists of a microcontroller unit, various types of sensors, a LoRa transceiver module, a display unit, and a battery power supply unit, and is used to collect the operating data of the hydropower equipment and transmit it to the gateway station; The microcontroller unit uses a specific control chip to control the overall operation of the sensor node and send the data collected by the sensor to the gateway station through the LoRa transceiver module; The various types of sensors include pressure sensors that measure water level, which work based on the principle of hydrostatic pressure; electromagnetic flow meters that measure flow, which operate based on the principle of electromagnetic induction; and thermistor sensors that measure temperature, which use the material's resistance to change with temperature to monitor; The LoRa transceiver module works at a specific frequency to achieve long-distance data transmission; the display unit is used to display measurement data and node working status; the battery power supply unit ensures that the sensor node continues to work for a certain period of time when the power is off; The sensor node has a specific operation control logic, reads data at a preset frequency, determines faults based on voltage thresholds, and performs corresponding data transmission operations; Gateway module: It consists of a control unit, a LoRa receiving unit, a WiFi communication unit, a 4G communication unit, a display unit and a power supply unit. It is responsible for receiving sensor node data and uploading it to the cloud server. It also has a power failure alarm function. The control unit uses a specific kit to receive sensor node data through the LoRa receiving unit, and after processing, sends it to the cloud server via the WiFi communication unit; When the 4G communication unit detects a power outage, it receives a trigger signal from the control unit and sends a text message alert to the user; The display unit is used to display relevant information; the power supply unit supplies power to each component of the gateway station, and the data is uploaded at specific time intervals during the experiment; Cloud server module: The cloud server is used to store the operating data of hydropower equipment. Managers can access specific data channels through mobile terminals to achieve real-time monitoring of data. Data transmission link module: Establish a LoRa wireless transmission link between the sensor node and the gateway station to ensure stable data transmission over long distances; Build a WiFi transmission channel between the gateway station and the cloud server to ensure efficient data upload; Data transmission modes include polling and event-driven. In polling mode, the data acquisition device requests data from the sensor periodically. In event-driven mode, the sensor actively sends data to the data acquisition device when a specific event is triggered. Data analysis and processing module: Introducing data analysis algorithms based on specific time series analysis models to detect anomalies and predict trends in monitoring data; This model transforms non-stationary data into stationary series through a specific difference method and then builds the model. The model formula is: (Where X t For time series data, is the autoregressive coefficient, θ i is the moving average coefficient, ε t is white noise); The residual between the actual observed value and the model predicted value is calculated and compared with the preset threshold to determine whether the data is abnormal. The threshold is determined by statistical or machine learning methods based on actual conditions and experience.

2. The remote monitoring system for hydropower equipment based on Internet of Things technology according to claim 1 is characterized in that: The microcontroller unit also includes a data cache module, which is used to cache sensor measurement data within a certain period of time when the sensor data collection frequency is high or the network transmission is temporarily interrupted to ensure that the data will not be lost; the data cache module adopts a first-in-first-out FIFO data storage structure, and its cache capacity is dynamically adjusted according to the frequency of sensor data collection and the stability of network transmission. After the network returns to normal, the earliest collected data in the cache is transmitted first to ensure the timeliness and continuity of the data.

3. The remote monitoring system for hydropower equipment based on Internet of Things technology according to claim 1 is characterized in that: The pressure sensor is a high-precision ceramic capacitive pressure sensor with a measurement accuracy of up to ±0.1% FS. It has good stability and anti-interference ability and can accurately measure the water level in harsh hydropower generation environments. The ceramic capacitor sensitive element inside the sensor adopts a special packaging process to effectively prevent the intrusion of moisture and impurities, thereby extending the service life of the sensor. At the same time, the sensor is equipped with an automatic temperature compensation function, which can compensate in real time for the impact of ambient temperature changes on the measurement results, further improving the measurement accuracy.

4. The remote monitoring system for hydropower equipment based on Internet of Things technology according to claim 1 is characterized in that: The electrodes of the electromagnetic flowmeter are made of corrosion-resistant Hastelloy material and can adapt to the measurement of water flows containing complex components such as silt, corrosive substances, etc.; the inner wall of the measuring tube is coated with a special anti-fouling coating to reduce the impact of impurities in the water flow on the measurement accuracy; in addition, the electromagnetic flowmeter has an adaptive flow rate range adjustment function, which can automatically optimize the measurement parameters according to the actual water flow rate to ensure accurate flow measurement under different flow rate conditions. The measurement range is 0.01m3 / s-10m3 / s.

5. The remote monitoring system for hydropower equipment based on Internet of Things technology according to claim 1 is characterized in that: The thermistor sensor adopts a high-precision negative temperature coefficient thermistor, whose resistance temperature coefficient is between -4% / ℃ and -6% / ℃, and can respond to temperature changes quickly and accurately; the sensor is wrapped with a high thermal conductivity silicone protective cover, which can effectively protect the thermistor from external physical damage and ensure that heat is quickly transferred to the thermistor, thereby improving the response speed and accuracy of temperature measurement; at the same time, the sensor has a built-in temperature drift compensation circuit to correct the temperature measurement deviation caused by long-term operation in real time.

6. The remote monitoring system for hydropower equipment based on Internet of Things technology according to claim 1 is characterized in that: The LoRa transceiver module supports adaptive power adjustment function, which can automatically adjust the transmission power according to the distance between the sensor node and the gateway station, signal strength and environmental interference, thereby reducing power consumption while ensuring reliable communication; its transmission power adjustment range is 10dBm-20dBm, the spreading factor can be dynamically adjusted between 7-12, and the coding rate supports 4 / 5, 4 / 6, 4 / 7, 4 / 8 options to adapt to different communication environment requirements.

7. The remote monitoring system for hydropower equipment based on Internet of Things technology according to claim 1 is characterized in that: The 4G wireless module in the gateway station supports multi-band communication and can automatically switch between frequency bands such as GSM900, DCS1800, PCS1900, etc., ensuring that SMS alerts can be sent stably in different regions and network environments; the module has signal strength detection and automatic reconnection functions. When the signal strength is lower than the preset threshold or the communication is interrupted, it automatically searches and switches to a frequency band with a stronger signal for reconnection, ensuring that the alarm information is delivered to the user in a timely and accurate manner.

8. The remote monitoring system for hydropower equipment based on Internet of Things technology according to claim 1 is characterized in that: The ARIMA model in the data analysis and processing module adopts a rolling forecast update mechanism, and re-estimates and updates the model parameters at regular intervals using newly collected data to adapt to the dynamic changes in the operating status of the hydropower equipment and improve the accuracy of trend prediction; The model update interval is dynamically set according to the stability of the equipment operation and the frequency of data changes. The update interval is shortened when the equipment operation status changes rapidly, and vice versa.

9. The remote monitoring system for hydropower equipment based on Internet of Things technology according to claim 1 is characterized in that: The event-driven data transmission mode in the data transmission link module supports customized event triggering conditions. Users can flexibly set the thresholds, abnormality types and other conditions for triggering the transmission of sensor data according to the specific operating requirements and safety standards of the hydropower equipment, thereby improving the system's monitoring sensitivity and response speed to specific faults and abnormal conditions.

10. The remote monitoring system for hydropower equipment based on Internet of Things technology according to claim 1 is characterized in that: The cloud server module has data backup and recovery functions, performs full or incremental backup of the stored hydropower equipment operation data on a regular basis every day, and stores the backup data in a redundant server at a different location; When the main server fails or data is lost, the data can be quickly restored from the backup server to ensure data security and integrity and guarantee the continuous and stable operation of the monitoring system.

Images