Valve intelligent operation control method and system based on Internet of Things

Abstract

The invention discloses a valve intelligent operation control method and system based on the Internet of Things, and relates to the technical field of electrical control equipment. In order to solve the problems that in a complex industrial environment, a communication link is possibly interfered, so that data transmission is unstable, self-adaptive adjustment of communication frequency cannot be realized to deal with changes of signal attenuation or channel occupation conditions, and deep fault diagnosis and predictive maintenance support of a valve are insufficient, the invention provides a valve fault diagnosis method and device. According to the method, the sensor network is constructed, valve operation and environment data are comprehensively and accurately collected, the adaptive frequency hopping technology ensures stable data transmission, key features are extracted, a time sequence feature curve graph is constructed, a valve state classification model is trained in combination with historical data, and the valve operation state is accurately judged. Fault types are accurately matched according to the fault knowledge base, the severity of the faults is determined, early warning and alarm are given out in time, and therefore the intelligent level and the operation efficiency of the valve system are further improved.

Description

Technical Field

[0001] The present invention relates to the technical field of electrical control equipment, and in particular to an intelligent operation control method and system for valves based on the Internet of Things. Background Art

[0002] Traditional valve control methods mainly rely on manual inspections and simple control logic, which makes it difficult to monitor the valve operation status in real time and comprehensively. The patent application with publication number CN102003563A discloses an intelligent valve electric actuator controller, which consists of a power conversion module, an AC asynchronous motor, a mechanical transmission device, a motor drive module and a control circuit. The mechanical transmission of the valve electric actuator is equipped with a torque switch to monitor the torque output to the valve, and a position sensor to detect the opening of the valve; it can also monitor the performance of the motor, as well as the phase sequence and phase loss of the power supply. The control circuit communicates with the remote through the bus communication board and the remote signal board, and completes the interactive function with the local operator through the remote control, buttons and LCD screen.

[0003] Although the above patent overcomes the problems of instability and low precision of the original control system based on analog circuits, in a complex industrial environment, the communication link may be interfered with, resulting in unstable data transmission. It fails to achieve adaptive adjustment of the communication frequency to cope with changes in signal attenuation or channel occupancy, and lacks support for in-depth fault diagnosis and predictive maintenance of valves. Summary of the invention

[0004] The purpose of the present invention is to provide a valve intelligent operation control method and system based on the Internet of Things, which, through sensor networks and data analysis technology, improves the communication stability, adaptability and fault diagnosis accuracy of the valve control system, thereby further improving the intelligence level and operation efficiency of the valve system to solve the problems raised in the above background technology.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] The intelligent operation control method of valves based on the Internet of Things includes:

[0007] Based on the sensor network, the monitoring data of valve operation is collected in real time, and the valve status is analyzed based on the collected real-time monitoring data to determine whether the valve operation is normal;

[0008] A corresponding valve control strategy is formulated according to the valve status analysis results, and the valve control instructions are matched based on the valve control strategy. The valve actuator receives the control instructions and performs corresponding actions. At the same time, the control strategy is optimized according to the feedback information of the valve actuator.

[0009] Furthermore, the sensor network specifically includes:

[0010] Install various sensors on the valve body and the valve deployment environment, and determine the installation location of each sensor based on the valve type, specification, operating environment characteristics and monitoring requirements;

[0011] After each sensor is deployed, it collects valve operation data and environmental data in real time according to the preset sampling frequency;

[0012] Each sensor converts the collected operation data and environmental data into digital signals and transmits them to the data aggregation node through adaptive frequency hopping technology;

[0013] The data quality of the operating data and environmental data collected by each sensor is monitored in real time at the data aggregation node to determine whether the operating data and environmental data are abnormal.

[0014] Furthermore, after the deployment of each sensor is completed, it also includes:

[0015] For each deployed sensor, determine a corresponding first range value according to the sensor type and measurement data characteristics;

[0016] According to the output value of each sensor at the first range value, combined with the range of each sensor and the value range of the normal operation condition of the valve, the second range value is determined for each sensor;

[0017] Based on the first sensor value and the second sensor value of each sensor, respectively calculate the adjustment compensation amount of each sensor to correct the measurement error of each sensor;

[0018] Combined with the calculated adjustment compensation amount of each sensor, the value measured by each sensor each time is automatically calibrated in real time.

[0019] Furthermore, the valve status is analyzed based on the collected real-time monitoring data, including:

[0020] Pre-process the operation data and environmental data transmitted to the data aggregation node after each sensor is automatically calibrated;

[0021] Extract key features of valve operation status from pre-processed operation data and environmental data, and obtain feature sets of valve monitoring data based on the extraction results;

[0022] Combined with the valve operation cycle and historical data, a time series characteristic curve diagram of each key feature is constructed based on the time series characteristics of each key feature in the feature set to determine the change trend of the key feature over time;

[0023] The known normal operation state and fault state data of the valve are used as training samples and input into the preset network model to obtain the valve state classification model;

[0024] The extracted feature set is input into the trained valve state classification model to obtain the classification result of the current state of the valve and determine whether the valve is operating normally.

[0025] Furthermore, judging whether the valve operation is normal also includes: based on the valve operation cycle and historical data, combined with the classification results of the valve's current state, predicting the valve's operating status trend and potential failure risks, and evaluating the valve's health status score and failure probability based on the prediction results. When the health status score is lower than the preset score or the failure probability exceeds the preset threshold, a fault warning is issued and the fault diagnosis process is started for diagnosis.

[0026] Furthermore, when it is determined that the valve is operating abnormally, the abnormal data of each sensor corresponding to the abnormal state of the valve is obtained, the abnormal combination pattern of the abnormal data of each sensor is analyzed, and the data is input into the fault knowledge base for matching the fault type, wherein the fault knowledge base is constructed based on the correlation between different fault types and key feature changes in historical data; according to the state classification result and the fault type, the severity of the valve fault is determined, and when the valve state is abnormal or the fault severity reaches a preset fault abnormality threshold, an alarm message is issued.

[0027] Furthermore, the valve actuator specifically includes:

[0028] Based on the IoT platform and the sensor network, a data interaction channel is built for data interaction. The valve actuator obtains control instructions based on the data interaction channel to achieve remote control of the valve.

[0029] During the execution process, the valve actuator monitors the operating status of the valve in real time, and at the same time, feeds back the valve operating status information and action execution results based on the data interaction channel.

[0030] Furthermore, if the valve actuator detects an abnormality during the execution process, it will immediately stop executing the control and re-acquire the control instructions to ensure that the valve can operate according to the expected control strategy, and store each instruction received, the execution result and its own operating status data.

[0031] The present invention provides another technical solution, a valve intelligent operation control system based on the Internet of Things, comprising:

[0032] A sensor network building module is configured to build a sensor network based on the installed sensors, collect the operation data and environmental data of the valve in real time based on the sensor network, and transmit the collected operation data and environmental data to the data aggregation node;

[0033] A state judgment module is configured to pre-process the operation data and environmental data transmitted by each sensor to the data aggregation node, extract key features of the valve operation state, and judge the current operation state of the valve;

[0034] A fault diagnosis module is configured to obtain abnormal data of each sensor corresponding to the abnormal state of the valve when it is determined that the valve is operating abnormally, analyze the abnormal combination mode of the abnormal data of each sensor, match and identify the fault type based on the fault knowledge base, determine the severity of the valve fault, and issue an alarm message;

[0035] The valve control module is configured to generate a corresponding valve control strategy according to the diagnosis result of the fault diagnosis module, match the valve control instruction based on the valve control strategy, and transmit it to the valve actuator to control the valve;

[0036] The display interaction module is configured to provide an operation interface, monitor the valve status in real time based on the operation interface, display the historical data and alarm information of the corresponding valve, and obtain the remote control valve operation instructions.

[0037] Furthermore, the sensor network building module also includes:

[0038] A real-time monitoring unit, configured to monitor in real time the signal quality of the frequency communication link between the sensor and the data aggregation node, and obtain the communication data volume within a preset unit period;

[0039] A frequency determination unit, configured to adjust a frequency selection strategy and select a corresponding communication frequency based on the amount of communication data within a preset unit period;

[0040] A frequency hopping unit is configured to send a frequency hopping instruction to a corresponding sensor according to the selected corresponding communication frequency, realize optimal frequency switching, and start data transmission;

[0041] The transmission quality monitoring unit is configured to set at least one backup frequency and perform real-time evaluation on each backup frequency based on the real-time monitoring unit. When the quality of the frequency communication link is lower than a preset threshold, it automatically switches to a backup frequency with qualified quality and re-establishes the communication link.

[0042] Compared with the prior art, the present invention has the following beneficial effects:

[0043] By building a sensor network, valve operation and environmental data are collected comprehensively and accurately. Adaptive frequency hopping technology ensures stable data transmission, real-time monitoring and dynamic adjustment of frequency, reduce interference and signal attenuation, and improve the communication stability, adaptability and fault diagnosis accuracy of the valve control system. Key features are extracted and a timing characteristic curve is constructed. The valve state classification model is trained in combination with historical data to accurately judge the valve operation state. The fault type is accurately matched according to the fault knowledge base, the severity of the fault is determined, and early warnings and alarms are issued in time, thereby further improving the intelligence level and operation efficiency of the valve system. It can also optimize strategies based on feedback and display interactive modules to facilitate operators to monitor and control valves, thereby improving the intelligence level and work efficiency of valve control. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 This is a flow chart of the valve intelligent operation control method based on the Internet of Things of the present invention;

[0045] Figure 2 This is a module diagram of the valve intelligent operation control system based on the Internet of Things of the present invention. DETAILED DESCRIPTION

[0046] 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.

[0047] To solve the technical problems that in complex industrial environments, communication links may be disturbed, resulting in unstable data transmission, failure to achieve adaptive adjustment of communication frequency to cope with changes in signal attenuation or channel occupancy, and insufficient support for in-depth fault diagnosis and predictive maintenance of valves, please refer to Figure 1 , this embodiment provides the following technical solutions:

[0048] The intelligent operation control method of valves based on the Internet of Things includes:

[0049] Based on the sensor network, the monitoring data of valve operation is collected in real time, and the valve status is analyzed based on the collected real-time monitoring data to determine whether the valve operation is normal;

[0050] A corresponding valve control strategy is formulated according to the valve status analysis results, and the valve control instructions are matched based on the valve control strategy. The valve actuator receives the control instructions and performs corresponding actions. At the same time, the control strategy is optimized according to the feedback information of the valve actuator.

[0051] In this embodiment, the sensor network specifically includes:

[0052] Install temperature sensors, pressure sensors, flow sensors, vibration sensors and other sensors on the valve body and valve deployment environment, and determine the installation location of each sensor based on the valve type, specification, operating environment characteristics and monitoring requirements;

[0053] After the deployment of each sensor is completed, each sensor collects the valve's operating data such as temperature, pressure, flow, vibration amplitude, and environmental data such as temperature and humidity in real time according to the preset sampling frequency;

[0054] Each sensor converts the collected operation data and environmental data into digital signals and transmits them to the data aggregation node through adaptive frequency hopping technology;

[0055] The data quality of the operating data and environmental data collected by each sensor is monitored in real time at the data aggregation node to determine whether the operating data and environmental data are abnormal. When the data collected by a sensor exceeds the normal range, it can be discovered and processed in time to avoid the impact of erroneous data on subsequent analysis and decision-making.

[0056] In this embodiment, for large industrial valves, temperature and pressure sensors are installed at key parts of the valve body, such as the inlet and outlet, near the valve core, etc., to accurately measure the temperature and pressure of the medium; vibration sensors are installed at the pipe connections of the valve to monitor the stability of the connection parts; in the surrounding environment of the valve, appropriate locations are selected to install ambient temperature and humidity sensors. Through professional installation processes and fixtures, the sensor is firmly installed and ensures good contact with the valve and the surrounding environment to avoid interference and looseness that affect the accuracy of data collection.

[0057] In this embodiment, the working status information of each sensor is collected regularly, and the working parameters or network topology of each sensor are automatically adjusted according to the battery power, communication signal strength, data transmission success rate, etc. At the same time, the sampling frequency and monitoring focus of each sensor are dynamically adjusted according to the changes in the valve operating conditions. This network self-optimization capability enables the sensor network to adapt to different working environments and operating conditions, maintain a stable operating state, and improve the performance and reliability of the entire network. For example, when the battery power of a sensor is too low, its sampling frequency is automatically reduced or the sensor is temporarily shut down to extend its service life; when the valve operating conditions change, the sampling frequency and monitoring focus of the sensor are adjusted to ensure that key data can be obtained in a timely manner.

[0058] In this embodiment, for valve temperature data, if the collected temperature value exceeds the upper and lower limits of the normal working temperature range, it is determined to be abnormal data; for pressure data, if there is a drastic change in a short period of time and exceeds the normal fluctuation range, it is also determined to be abnormal data. Once abnormal data is found, the data repair or marking mechanism is immediately started. For repairable abnormal data, such as erroneous data caused by instantaneous interference of the sensor, data interpolation or filtering algorithms are used to repair it; for abnormal data that cannot be repaired, it is marked and the abnormal information is recorded, and special processing or elimination is performed in the subsequent data analysis stage.

[0059] In this embodiment, after the deployment of each sensor is completed, the following steps are also included:

[0060] For each deployed sensor, determine the corresponding first range value based on the sensor type and measurement data characteristics. For example, for a pressure sensor, the first range value can be set to zero pressure (such as when the valve is completely closed and there is no medium pressure); for a temperature sensor, it can be set to the ambient reference temperature. Adjust the input value of each sensor to the corresponding first range value, trigger the sensor to perform a measurement operation, record the output value of each sensor at this time, and save it as the first sensor value;

[0061] According to the output value of each sensor at the first range value, combined with the range of each sensor and the value range of the normal working condition of the valve, the second range value is determined for each sensor; for example, for a flow sensor, a common flow value when the valve is working normally can be selected as the second range value, and the input value of each sensor is adjusted to the corresponding second range value (this can be achieved by simulating the normal working environment of the valve or adjusting relevant parameters), and the measurement is triggered again, and the output value of each sensor at this time is recorded and saved as the second sensor value;

[0062] Based on the first sensor value and the second sensor value of each sensor, the adjustment compensation amount of each sensor is calculated respectively to correct the measurement error of each sensor; for sensors with linear characteristics, a linear calculation method can be used to calculate the deviation compensation amount between the measured value and the actual value based on the principle of two points determining a straight line; for nonlinear sensors, polynomial fitting or other nonlinear algorithms can be used for calculation;

[0063] Combined with the calculated adjustment compensation amount of each sensor, the measured value of each sensor is automatically calibrated in real time, and the calibrated measurement value is used for subsequent valve operation status analysis and control decision-making to ensure the accuracy and reliability of the sensor output data.

[0064] In this embodiment, by determining the first and second range values ​​for each sensor and calculating the adjustment compensation amount accordingly, the measurement error of the sensor can be effectively corrected, and the accuracy of the sensor output data is greatly improved. The calibration process fully considers the actual operating conditions of the valve, and sets the range values ​​according to different sensor types and measurement data characteristics, so that the system can better adapt to the operation of the valve under various complex conditions. For example, for different types of valves under different openings, medium flows and pressures, the sensor can accurately measure, enhance the adaptability of the entire intelligent operation control system to diversified industrial scenarios, and can detect potential problems in valve operation in advance, reducing sudden failures caused by sensor errors covering up hidden faults. This helps to reasonably arrange maintenance plans, reduce equipment maintenance costs, improve production continuity, and avoid economic losses caused by valve failure shutdowns to industrial production.

[0065] In this embodiment, the valve status is analyzed based on the collected real-time monitoring data, specifically including:

[0066] Pre-process the operating data and environmental data transmitted to the data aggregation node after automatic calibration of each sensor, including redundant dimension reduction processing, etc., remove duplicate data and data with little impact on valve status analysis, and remove noise interference and outliers;

[0067] Extract key features of valve operation status from pre-processed operation data and environmental data, including temperature features, pressure features, flow change features, etc. For temperature data, extract features such as temperature change rate and standard deviation of temperature fluctuation; for pressure data, extract features such as peak value, valley value and average change amplitude of pressure; for vibration data, extract features such as vibration frequency and amplitude, and obtain feature set of valve monitoring data based on the extraction results;

[0068] Combined with the valve's operating cycle and historical data, a time series characteristic curve of each key feature is constructed based on the time series characteristics of each key feature in the feature set to determine the change trend of the key feature over time, for example, observing the dynamic change law of each key feature during the valve opening and closing process;

[0069] The model is trained using historical data, and the known normal operating state and fault state data of the valve are used as training samples and input into the preset network model to obtain a valve state classification model, so that it can accurately classify the valve state;

[0070] The extracted feature set is input into the trained valve state classification model to obtain the classification result of the current state of the valve and determine whether the valve is operating normally;

[0071] Based on the valve's operating cycle and historical data, combined with the classification results of the valve's current status, the valve's operating status trend and potential failure risks are predicted. The valve's health status score and failure probability are evaluated based on the prediction results. When the health status score is lower than the preset score or the failure probability exceeds the preset threshold, a fault warning is issued and the fault diagnosis process is started for diagnosis.

[0072] When it is determined that the valve is operating abnormally, the abnormal data of each sensor corresponding to the abnormal state of the valve is obtained, the abnormal combination pattern of each sensor abnormal data is analyzed, and the data is input into the fault knowledge base for matching the fault type, wherein the fault knowledge base is constructed based on the correlation between different fault types and key feature changes in historical data; for example, if the temperature sensor shows that the temperature is too high, and the pressure sensor shows abnormal pressure fluctuations, and the vibration sensor detects abnormal vibrations, it can be determined that the valve may have internal leakage or mechanical failure, and the operating state of the valve is comprehensively evaluated. According to the state classification results and fault type, the severity of the valve fault is determined. When the valve state is abnormal or the fault severity reaches the preset fault abnormality threshold, an alarm message is issued to notify relevant personnel to handle it. The early warning information may include the fault type, occurrence time, possible impact, etc.

[0073] In this embodiment, by extracting key features, the core information of valve operation can be accurately captured, and the actual operating status of the valve can be reflected. By inputting the extracted feature set into the model, it is possible to quickly and accurately determine whether the current operating status of the valve is normal. The valve's operating cycle, historical data and current status classification results are combined to predict the valve's operating status trend and potential failure risks, and evaluate the valve's health status score and failure probability. Potential problems can be discovered in advance, allowing operation and maintenance personnel to take preventive measures before a failure occurs, thereby reducing the risk of equipment damage and production interruptions. Through comprehensive analysis of multiple sensor data, it can be determined whether the valve has problems such as internal leakage or mechanical failure, providing maintenance personnel with a clear fault direction, allowing maintenance personnel to quickly understand the fault situation, take effective maintenance measures in a timely manner, and reduce the impact of the fault on production.

[0074] In this embodiment, the valve actuator specifically includes:

[0075] Based on the IoT platform and the sensor network, a data interaction channel is built for data interaction. The valve actuator obtains control instructions based on the data interaction channel to achieve remote control of the valve.

[0076] During the execution process, the valve actuator monitors the operating status of the valve in real time, such as the actual valve opening, the current and speed of the motor, etc. At the same time, the valve operating status information and the action execution results are fed back based on the data interaction channel;

[0077] If the valve actuator detects an abnormality during the execution process, it will immediately stop executing the control and re-acquire the control instruction to ensure that the valve can operate according to the expected control strategy, and store each instruction received, the execution result and its own operating status data.

[0078] In this embodiment, the valve actuator monitors the actual opening of the valve, the current and speed of the motor and other operating conditions in real time during the execution process, and feeds back this information through the data interaction channel. This allows operators to understand the working status of the valve in real time and comprehensively, and to detect potential problems in a timely manner. For example, an abnormal increase in the motor current may indicate that the valve is stuck. Through real-time feedback, measures can be taken in time to deal with it and avoid further expansion of the fault, which provides strong support for optimizing the control strategy. During the process of opening or closing the valve, if there is too much resistance and the motor is overloaded, the actuator can stop the operation in time to prevent the motor from burning. This abnormal handling mechanism makes the system more fault-tolerant and can quickly resume normal operation in the event of a short-term fault or interference, reducing the downtime caused by the fault and improving the continuity of production.

[0079] In order to better demonstrate the realization of the valve intelligent operation control method based on the Internet of Things, please refer to him 2. The present invention provides a valve intelligent operation control system based on the Internet of Things, including:

[0080] A sensor network building module is configured to build a sensor network based on the installed sensors, collect the operation data and environmental data of the valve in real time based on the sensor network, and transmit the collected operation data and environmental data to the data aggregation node;

[0081] A state judgment module is configured to pre-process the operation data and environmental data transmitted by each sensor to the data aggregation node, extract key features of the valve operation state, and judge the current operation state of the valve;

[0082] A fault diagnosis module is configured to obtain abnormal data of each sensor corresponding to the abnormal state of the valve when it is determined that the valve is operating abnormally, analyze the abnormal combination mode of the abnormal data of each sensor, match and identify the fault type based on the fault knowledge base, determine the severity of the valve fault, and issue an alarm message;

[0083] The valve control module is configured to generate a corresponding valve control strategy according to the diagnosis result of the fault diagnosis module, match the valve control instruction based on the valve control strategy, and transmit it to the valve actuator to control the valve;

[0084] The display interaction module is configured to provide an operation interface, monitor the valve status in real time based on the operation interface, display the historical data and alarm information of the corresponding valve, and obtain the remote control valve operation instructions.

[0085] In this embodiment, the sensor network construction module further includes:

[0086] A real-time monitoring unit is configured to monitor the signal quality of the frequency communication link between the sensor and the data aggregation node in real time, including signal strength, noise level, channel occupancy, etc., and obtain the communication data volume within a preset unit period;

[0087] A frequency determination unit, configured to adjust a frequency selection strategy and select a corresponding communication frequency based on the amount of communication data within a preset unit period;

[0088] A frequency hopping unit is configured to send a frequency hopping instruction to a corresponding sensor according to the selected corresponding communication frequency, realize optimal frequency switching, and start data transmission to ensure that all sensors communicate synchronously at the new frequency;

[0089] The transmission quality monitoring unit is configured to set at least one backup frequency and perform real-time evaluation on each backup frequency based on the real-time monitoring unit. When the quality of the frequency communication link is lower than a preset threshold, it automatically switches to a backup frequency with qualified quality and re-establishes the communication link.

[0090] In this embodiment, the sensor network construction module comprehensively collects valve operation data and environmental data, and can realize adaptive frequency hopping in the sensor network, monitor signal quality in real time, ensure the stable transmission of valve operation data and environmental data, and reduce communication failures caused by frequency interference or signal attenuation. The state judgment module accurately extracts key features of the valve operation state, combines historical data and operation cycles, and uses scientific methods to judge the current operation state of the valve, providing a basis for taking appropriate measures in a timely manner. The fault diagnosis module determines the severity of the fault and issues an alarm, so that the staff can understand the fault situation in time, arrange maintenance resources reasonably, and reduce the impact of the fault on production. The valve control module realizes precise control of the valve and maintains the stable operation of the production process. The display interaction module provides comprehensive information to managers, which helps them make scientific decisions, optimize valve operation management, and improve overall production efficiency.

[0091] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. The intelligent operation control method of valve based on Internet of Things is characterized by: include: Based on the sensor network, the monitoring data of valve operation is collected in real time, and the valve status is analyzed based on the collected real-time monitoring data to determine whether the valve operation is normal; A corresponding valve control strategy is formulated according to the valve status analysis results, and the valve control instructions are matched based on the valve control strategy. The valve actuator receives the control instructions and performs corresponding actions. At the same time, the control strategy is optimized according to the feedback information of the valve actuator.

2. The method for intelligent operation and control of valves based on the Internet of Things according to claim 1, characterized in that: The sensor network specifically includes: Install various sensors on the valve body and the valve deployment environment, and determine the installation location of each sensor based on the valve type, specification, operating environment characteristics and monitoring requirements; After each sensor is deployed, it collects valve operation data and environmental data in real time according to the preset sampling frequency; Each sensor converts the collected operation data and environmental data into digital signals and transmits them to the data aggregation node through adaptive frequency hopping technology; The data quality of the operating data and environmental data collected by each sensor is monitored in real time at the data aggregation node to determine whether the operating data and environmental data are abnormal.

3. The method for intelligent operation and control of valves based on the Internet of Things according to claim 2, characterized in that: After the deployment of each sensor is completed, it also includes: For each deployed sensor, determine a corresponding first range value according to the sensor type and measurement data characteristics; According to the output value of each sensor at the first range value, combined with the range of each sensor and the value range of the normal operation condition of the valve, the second range value is determined for each sensor; Based on the first sensor value and the second sensor value of each sensor, respectively calculate the adjustment compensation amount of each sensor to correct the measurement error of each sensor; Combined with the calculated adjustment compensation amount of each sensor, the value measured by each sensor each time is automatically calibrated in real time.

4. The method for intelligent operation and control of valves based on the Internet of Things as claimed in claim 3, characterized in that: Analyze valve status based on collected real-time monitoring data, including: Pre-process the operation data and environmental data transmitted to the data aggregation node after each sensor is automatically calibrated; Extract key features of valve operation status from pre-processed operation data and environmental data, and obtain feature sets of valve monitoring data based on the extraction results; Combined with the valve operation cycle and historical data, a time series characteristic curve diagram of each key feature is constructed based on the time series characteristics of each key feature in the feature set to determine the change trend of the key feature over time; The known normal operation state and fault state data of the valve are used as training samples and input into the preset network model to obtain the valve state classification model; The extracted feature set is input into the trained valve state classification model to obtain the classification result of the current state of the valve and determine whether the valve is operating normally.

5. The method for intelligent operation and control of valves based on the Internet of Things according to claim 4, characterized in that: Judging whether the valve is operating normally also includes: based on the valve's operating cycle and historical data, combined with the classification results of the valve's current status, predicting the valve's operating status trend and potential failure risks, and evaluating the valve's health status score and failure probability based on the prediction results. When the health status score is lower than the preset score or the failure probability exceeds the preset threshold, a fault warning is issued and the fault diagnosis process is started for diagnosis.

6. The method for intelligent operation and control of valves based on the Internet of Things according to claim 5, characterized in that: When it is determined that the valve is operating abnormally, the abnormal data of each sensor corresponding to the abnormal state of the valve is obtained, the abnormal combination pattern of each sensor abnormal data is analyzed, and the data is input into the fault knowledge base for matching the fault type, wherein the fault knowledge base is constructed based on the correlation between different fault types and key feature changes in historical data; the severity of the valve fault is determined according to the state classification result and the fault type, and an alarm message is issued when the valve state is abnormal or the fault severity reaches the preset fault abnormality threshold.

7. The method for intelligent operation and control of valves based on the Internet of Things according to claim 6, characterized in that: The valve actuator specifically comprises: Based on the IoT platform and the sensor network, a data interaction channel is built for data interaction. The valve actuator obtains control instructions based on the data interaction channel to achieve remote control of the valve. During the execution process, the valve actuator monitors the operating status of the valve in real time, and at the same time, feeds back the valve operating status information and action execution results based on the data interaction channel.

8. The method for intelligent operation and control of valves based on the Internet of Things according to claim 7, characterized in that: If the valve actuator detects an abnormality during the execution process, it will immediately stop executing the control and re-acquire the control instruction to ensure that the valve can operate according to the expected control strategy, and store each instruction received, the execution result and its own operating status data.

9. The valve intelligent operation control system based on the Internet of Things is applied in the valve intelligent operation control method based on the Internet of Things as claimed in claim 1, characterized in that: include: A sensor network building module is configured to build a sensor network based on the installed sensors, collect the operation data and environmental data of the valve in real time based on the sensor network, and transmit the collected operation data and environmental data to the data aggregation node; A state judgment module is configured to pre-process the operation data and environmental data transmitted by each sensor to the data aggregation node, extract key features of the valve operation state, and judge the current operation state of the valve; A fault diagnosis module is configured to obtain abnormal data of each sensor corresponding to the abnormal state of the valve when it is determined that the valve is operating abnormally, analyze the abnormal combination mode of the abnormal data of each sensor, match and identify the fault type based on the fault knowledge base, determine the severity of the valve fault, and issue an alarm message; The valve control module is configured to generate a corresponding valve control strategy according to the diagnosis result of the fault diagnosis module, match the valve control instruction based on the valve control strategy, and transmit it to the valve actuator to control the valve; The display interaction module is configured to provide an operation interface, monitor the valve status in real time based on the operation interface, display the historical data and alarm information of the corresponding valve, and obtain the remote control valve operation instructions.

10. The intelligent operation control system of a valve based on the Internet of Things according to claim 9, characterized in that: Sensor network building blocks also include: A real-time monitoring unit, configured to monitor in real time the signal quality of the frequency communication link between the sensor and the data aggregation node, and obtain the communication data volume within a preset unit period; A frequency determination unit, configured to adjust a frequency selection strategy and select a corresponding communication frequency based on the amount of communication data within a preset unit period; A frequency hopping unit is configured to send a frequency hopping instruction to a corresponding sensor according to the selected corresponding communication frequency, realize optimal frequency switching, and start data transmission; The transmission quality monitoring unit is configured to set at least one backup frequency and perform real-time evaluation on each backup frequency based on the real-time monitoring unit. When the quality of the frequency communication link is lower than a preset threshold, it automatically switches to a backup frequency with qualified quality and re-establishes the communication link.

Images