System and method for monitoring operation state of valve rod of valve based on Internet of Things

Abstract

The invention discloses a valve and valve rod operation state monitoring system and method based on the Internet of Things, and relates to the technical field of valve and valve rod monitoring, the system comprises an intelligent equipment maintenance management platform, a valve and valve rod data acquisition module, a data processing module, an intelligent analysis module and a control adjustment module; the valve rod data acquisition module acquires detection data; the data processing module extracts torque related characteristics in the monitoring data of the valve rod of the valve; the intelligent analysis module judges whether the valve rod torque is abnormal or not; the adjusting module is controlled to adjust the operation state of the valve rod of the valve; according to the method, the data acquisition interval duration capable of being dynamically adjusted is introduced, so that the problems that the abnormal condition detection is not timely and the accuracy is reduced due to the fact that the abnormal probability and frequency are gradually increased along with the gradual increase of the working duration of the valve rod of the valve are solved, and the timeliness of determining the abnormal condition is improved; and the probability that the valve is further damaged within the duration of the abnormal condition is reduced.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of valve stem monitoring, and particularly relates to a valve stem operation state monitoring system and method based on the Internet of Things. BACKGROUND

[0002] In industrial production, a valve is a very important control component, and the operation state of a valve stem directly affects the normal operation of equipment; the torque of the valve stem is a key parameter reflecting the operation state of the valve stem, and torque abnormalities can cause serious problems such as damage to the valve stem and leakage of the medium; the traditional valve stem monitoring method relies on manual inspection, and has problems such as low efficiency, slow response, and inability to timely detect torque abnormalities; although some existing monitoring systems can collect valve-related data, they cannot deeply analyze the root cause of torque abnormalities, cannot automatically adjust the valve operation strategy according to the cause, and usually use a fixed interval time length for data collection; such a data detection process can increase the risk of valve damage during the abnormality confirmation process after the abnormality occurs, and as the working time of the valve stem approaches the average service life of the workpiece, the probability and frequency of valve stem abnormalities increase; at this time, using the initial data collection interval time length, the efficiency and accuracy of abnormality monitoring are reduced. SUMMARY

[0003] The present application aims to provide a valve stem operation state monitoring system and method based on the Internet of Things to solve the problems in the prior art.

[0004] To achieve the above-mentioned purpose, the present application provides the following technical scheme: a valve stem operation state monitoring system based on the Internet of Things, the system comprising an intelligent equipment maintenance management platform, a valve stem data collection module, a data processing module, an intelligent analysis module, and a control adjustment module;

[0005] The data processing module and the intelligent analysis module are deployed in the intelligent equipment maintenance management platform to receive and store the monitoring data collected by the valve stem data collection module, and to process and analyze the collected data;

[0006] The valve stem data collection module monitors the operation state of the valve stem through a high-precision torque sensor, collects detection data, and transmits the collected monitoring data to the intelligent equipment maintenance management platform;

[0007] The data processing module is deployed in the intelligent equipment maintenance management platform, and is used to preprocess the collected monitoring data and extract torque-related features in the monitoring data of the valve stem;

[0008] The intelligent analysis module analyzes the running state of the valve stem according to the extracted torque-related features, judges whether the torque of the valve stem is abnormal, analyzes the cause of the abnormality, and generates an abnormality prompt and an abnormality alarm instruction;

[0009] The control adjustment module adjusts the running state of the valve stem according to the received abnormality prompt and abnormality alarm instruction.

[0010] Further, the valve stem data acquisition module monitors the running state of the valve stem by setting a high-precision torque sensor, collects monitoring data of the valve stem running platform, transmits the collected monitoring data to the intelligent equipment maintenance management platform through a wireless transmission mode, and stores the collected detection data in the intelligent equipment maintenance management platform without wiring, which reduces the installation difficulty in complex industrial environments, is especially suitable for the transformation of old equipment and occasions where wiring is not easy, and also reduces the influence of line faults on data transmission, ensuring that the monitoring data can be stably and timely transmitted to the platform.

[0011] Further, the intelligent equipment maintenance management platform is deployed with a data processing module and an intelligent analysis module; the intelligent equipment maintenance management platform is used to receive and store the torque feature data collected by the valve stem data acquisition module;

[0012] The data processing module includes a data preprocessing unit and a feature data extraction unit; the data preprocessing unit processes the collected monitoring data by an adaptive Kalman filtering algorithm, and processes the abnormal values that appear by an isolated forest algorithm; the feature data extraction unit is used to extract torque-related feature data in the monitoring data, the torque-related feature data including torque peak value, torque average value, torque fluctuation amplitude, torque change rate and torque continuous abnormal time; the intelligent analysis module includes an abnormality detection unit and an abnormality cause analysis unit; the abnormality detection unit judges whether the valve stem is abnormal by setting a threshold value for comparative analysis; the abnormality cause analysis unit is used to analyze the cause of the abnormality according to the type of the abnormality.

[0013] Further, the control adjustment module adjusts the running state parameters of the valve switch according to the analyzed abnormality type, and the adjustment process is realized by remotely controlling the valve actuator through the Internet of Things.

[0014] A valve stem running state monitoring method based on the Internet of Things, the method comprising the following steps:

[0015] S1, monitoring the running state of the valve stem by a high-precision torque sensor, collecting detection data, and transmitting the collected monitoring data to an intelligent equipment maintenance management platform;

[0016] S2. Preprocess the collected monitoring data and extract the torque-related features from the monitoring data of the valve stem;

[0017] S3. Based on the extracted torque-related features, perform intelligent analysis on the valve stem operating status, determine whether the valve stem torque is abnormal, analyze the cause of the abnormality, and generate abnormal prompts and abnormal alarm commands.

[0018] S4. Adjust the operating status of the valve stem according to the received abnormal prompts and abnormal alarm commands.

[0019] Furthermore, in step S1: when collecting monitoring data, a data collection period T is set, and m torque values ​​are collected. The collected torque values ​​are represented as {A1, A2, ..., A...} m}; Obtain the average lifespan of the valve stem from the database. The system records the working time d of the valve stem currently in operation; the interval between data collection in each data acquisition cycle is Δt.

[0020] Furthermore, in step S2: the collected monitoring data is filtered using an adaptive Kalman filter algorithm, and outliers in the collected data are processed using an isolated forest algorithm; the collected monitoring data is analyzed and processed to extract torque-related feature data, including peak torque and average torque. Torque fluctuation amplitude ω and torque change rate p; peak torque is represented by B, B = max{A1, A2, ..., A m}; Average torque The torque fluctuation range is calculated using the following formula:

[0021] ω=B-min{A1,A2,…,A m};

[0022] Where ω represents the fluctuation amplitude, and i represents the label of the collected torque value, i = 1, 2, ..., m; This represents the mean of m collected torque values; min{A1, A2, ..., A m} represents the minimum value among m torque values;

[0023] The torque change rate over a data acquisition cycle can be calculated using the following formula:

[0024]

[0025] Where, p j The torque change rate is represented within the data collection interval Δt; j represents the label of different torque change rates, j = 1, 2, ..., m-1.

[0026] Further, in step S3: By setting a threshold value for comparing and analyzing with the obtained torque eigenvalue, it is determined whether there is an abnormality in the valve stem; the threshold value for determining the abnormality of the torque peak is set as B max , and the threshold value for determining the abnormality of the torque average value is set as The threshold value of the torque fluctuation amplitude is set as ω0, and the threshold value of the torque change rate is set as p0; the obtained torque eigenvalue is compared and analyzed with the set threshold value, and the analysis results are as follows:

[0027] If B < B max , it indicates that the torque peak is normal, and it is judged that there is no abnormal situation;

[0028] If B ≥ B max , it indicates that the torque peak is abnormally high, and it is judged that there is an abnormally high friction or jamming in a local area during the operation of the valve stem, and an abnormal alarm y1 is generated;

[0029] If it indicates that the torque average value is normal, and it is judged that there is no abnormal situation;

[0030] If it indicates that the torque average value is abnormally high, and it is judged that the valve stem continuously bears an abnormally high load during the operation, and an abnormal prompt x1 is generated;

[0031] If ω < ω0, it indicates that the torque fluctuation amplitude is normal, and it is judged that there is no abnormal situation;

[0032] If ω0 ≤ ω, it indicates that the torque fluctuation amplitude is high, and it is judged that the running state of the valve stem is unstable, there is a low-risk abnormality, and an abnormal prompt x2 is generated;

[0033] If p j ≤ p0, it indicates that the torque change rate is normal, and it is judged that there is no abnormal situation;

[0034] If p j > p0, it indicates that the torque fluctuation amplitude is abnormally high, and it is judged that the valve stem torque changes violently in a short time, and an alarm instruction y2 is generated;

[0035] After detecting the abnormal prompt instruction, record the moment t1 when the abnormal prompt is detected, and in the next data monitoring period, analyze the extracted data to determine whether the abnormal situation has recovered, and record the abnormal duration Δt′. Set the abnormal duration threshold as nT. If it is detected that Δt′ ≥ nT and the abnormality has not recovered, then convert the abnormal prompt to an abnormal alarm y2; if it is detected that Δt′ < nT and the abnormality has recovered, then cancel the abnormal prompt.

[0036] Further, in step S3: When there is no abnormal situation, the interval duration of data collection is a dynamically changing value, and the average life of the valve components is obtained through the database The current valve operating time d is collected and recorded using data acquisition equipment. An initial data acquisition interval Δt0 is set when the valve stem begins operation, and Δt0 is directly used as the data acquisition interval during the first data acquisition cycle. From the second data monitoring cycle onwards, the data acquisition interval is dynamically adjusted, calculated using the following formula:

[0037]

[0038] Wherein, Δt0 represents the initial data acquisition interval set when the valve stem starts working; w represents the standard deviation of the collected torque values ​​in the previous data detection cycle; a data acquisition interval that can be dynamically adjusted according to the working time and torque fluctuation of the valve stem is introduced, which solves the problem of untimely detection and decreased accuracy of abnormal situations caused by the gradual increase in the probability and frequency of abnormalities as the working time of the valve stem gradually increases.

[0039] The standard deviation of the torque values ​​collected within a data acquisition period is calculated using the following formula:

[0040]

[0041] w represents the standard deviation of the torque values ​​collected in the previous data acquisition cycle;

[0042] After detecting an anomaly alert, the data acquisition interval in the subsequent data acquisition cycle is further adjusted to account for the anomaly. A unit fluctuation duration ΔT0 for anomalies is set. After detecting the number of anomaly alerts k, the data acquisition interval is adjusted in the subsequent data monitoring cycle, and the adjusted data acquisition interval is Δt. 异常状态 =Δt-kΔT0; and after the abnormal situation is recovered, the adjustment of the data acquisition interval for the abnormal situation is lifted; when an abnormal situation is detected, an additional adjustment of the abnormal situation fluctuation duration is added, which shortens the data acquisition cycle after the abnormal situation occurs, as well as shortens the duration of the abnormal situation, improves the timeliness of abnormal situation determination, and reduces the probability of further damage to the valve during the duration of the abnormal situation.

[0043] Furthermore, in step S4: the operating status of the valve stem is adjusted according to the generated abnormal prompt instructions and abnormal alarm instructions.

[0044] If an abnormality warning instruction x1 is received, the opening and closing speed of the abnormal valve stem will be reduced, and the lubrication intensity of the abnormal valve stem will be increased.

[0045] If an abnormality warning instruction x1 is received, the load on the valve stem of the abnormal valve will be reduced, and the lubrication intensity of the valve stem will be increased.

[0046] If an abnormal alarm command y1 is received, the control valve actuator will reduce the opening and closing amplitude and frequency of the abnormal valve, and after adding lubrication to the abnormal valve, it will further check whether the abnormal situation has disappeared. If the abnormal situation has disappeared, it will restore the normal operation state; if the abnormal situation has not disappeared, it will control the valve stem of the abnormal valve to stop running and wait for the staff to inspect and repair it.

[0047] If an abnormal alarm command y2 is received, the valve stem of the abnormal valve will be directly controlled to stop operation and wait for maintenance personnel.

[0048] Compared with the prior art, the beneficial effects of the present invention are:

[0049] This application utilizes high-precision sensors to collect data in real time, ensuring data accuracy and timeliness, and providing a reliable foundation for subsequent analysis. By extracting the torque characteristic value of the valve stem and performing intelligent analysis on the extracted characteristic value, it can efficiently and accurately determine whether there are any abnormalities in the valve stem. This solves the problems of low efficiency, slow response, and inability to detect torque anomalies in a timely manner by traditional manual judgment. Furthermore, it analyzes the cause of the anomaly based on the data type of the anomaly and generates corresponding anomaly prompts and alarm commands. Then, it adjusts the operating status of the valve stem according to the generated commands, thus overcoming the limitations of some existing monitoring systems that, while collecting valve-related data, cannot deeply analyze the causes of torque anomalies or automatically adjust valve operation based on the causes. The present application addresses the shortcomings of the previous strategy by introducing a dynamically adjustable data acquisition interval based on the working time and torque fluctuation of the valve stem. This solves the problem of untimely detection and decreased accuracy caused by the increasing probability and frequency of anomalies as the working time of the valve stem gradually increases. Furthermore, the dynamically adjustable data acquisition interval in this application adds an adjustment to the fluctuation time of the anomaly when it is detected, shortening the data acquisition cycle after the anomaly occurs and shortening the duration of the anomaly. This improves the timeliness of anomaly identification and reduces the probability of further valve damage during the duration of the anomaly. Attached Figure Description

[0050] Figure 1 This is a schematic diagram of the structural composition of a valve stem operation status monitoring system based on the Internet of Things according to the present invention. Detailed Implementation

[0051] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0052] like Figure 1 As shown, the present invention provides a technical solution: a valve stem operation status monitoring system based on the Internet of Things. The system includes an intelligent equipment maintenance management platform, a valve stem data acquisition module, a data processing module, an intelligent analysis module, and a control and adjustment module.

[0053] The intelligent equipment maintenance management platform is equipped with a data processing module and an intelligent analysis module to receive and store monitoring data collected by the valve stem data acquisition module, and to process and analyze the collected data.

[0054] The valve stem data acquisition module monitors the operating status of the valve stem through a high-precision torque sensor, collects the detection data, and transmits the collected monitoring data to the intelligent equipment maintenance management platform.

[0055] The data processing module is deployed in the intelligent equipment maintenance management platform to preprocess the collected monitoring data and extract torque-related features from the monitoring data of the valve stem.

[0056] The intelligent analysis module performs intelligent analysis on the valve stem operating status based on the extracted torque-related features, determines whether the valve stem torque is abnormal, analyzes the cause of the abnormality, and generates abnormal prompts and abnormal alarm commands.

[0057] The control adjustment module adjusts the operating status of the valve stem based on the received abnormal prompts and alarm commands.

[0058] The valve stem data acquisition module uses a high-precision torque sensor to monitor the operating status of the valve stem and collects monitoring data from the valve stem operating turntable. The collected monitoring data is then transmitted wirelessly to the intelligent equipment maintenance management platform, and the collected test data is stored in the intelligent equipment maintenance management platform.

[0059] The intelligent equipment maintenance management platform deploys a data processing module and an intelligent analysis module; the intelligent equipment maintenance management platform is used to receive and store torque characteristic data collected by the valve stem data acquisition module;

[0060] The data processing module includes a data preprocessing unit and a feature data extraction unit. The data preprocessing unit uses an adaptive Kalman filter algorithm to process the collected monitoring data and an isolated forest algorithm to handle outliers. The feature data extraction unit extracts torque-related feature data from the monitoring data, including torque peak value, torque mean value, torque fluctuation amplitude, torque change rate, and torque duration of anomalies. The intelligent analysis module includes an anomaly detection unit and an anomaly cause analysis unit. The anomaly detection unit uses threshold comparison analysis to determine whether the valve stem is abnormal. The anomaly cause analysis unit analyzes the causes of anomalies based on their types.

[0061] The control and adjustment module adjusts the operating parameters of the valve switch based on the types of anomalies analyzed. The adjustment process is achieved by remotely controlling the valve actuator through the Internet of Things.

[0062] A method for monitoring the operating status of valve stems based on the Internet of Things (IoT), the method comprising the following steps:

[0063] S1. Monitor the valve stem operating status through a high-precision torque sensor, collect the detection data, and transmit the collected monitoring data to the intelligent equipment maintenance management platform;

[0064] S2. Preprocess the collected monitoring data and extract the torque-related features from the monitoring data of the valve stem;

[0065] S3. Based on the extracted torque-related features, perform intelligent analysis on the valve stem operating status, determine whether the valve stem torque is abnormal, analyze the cause of the abnormality, and generate abnormal prompts and abnormal alarm commands.

[0066] S4. Adjust the operating status of the valve stem according to the received abnormal prompts and abnormal alarm commands.

[0067] In step S1: When collecting monitoring data, a data collection period T is set, and m torque values ​​are collected. The collected torque values ​​are represented as {A1, A2, ..., A...} m}; Obtain the average lifespan of the valve stem from the database. The system records the working time d of the valve stem currently in operation; the interval between data collection in each data acquisition cycle is Δt.

[0068] In step S2: The collected monitoring data is filtered using an adaptive Kalman filter algorithm, and outliers in the collected data are processed using an isolated forest algorithm; the collected monitoring data is analyzed and processed to extract torque-related feature data, including peak torque and mean torque. Torque fluctuation amplitude ω and torque change rate p; peak torque is represented by B, B = max{A1, A2, ..., A m}; Average torque The torque fluctuation range is calculated using the following formula:

[0069] ω=B-min{A1,A2,…,A m};

[0070] Where ω represents the fluctuation amplitude, and i represents the label of the collected torque value, i = 1, 2, ..., m; This represents the mean of m collected torque values; min{A1, A2, ..., A m} represents the minimum value among m torque values;

[0071] The torque change rate over a data acquisition cycle can be calculated using the following formula:

[0072]

[0073] Where, p j The torque change rate is represented within the data collection interval Δt; j represents the label of different torque change rates, j = 1, 2, ..., m-1.

[0074] In step S3: A threshold is set for comparison and analysis with the acquired torque characteristic value to determine whether the valve stem is abnormal; the threshold for determining whether the torque peak value is abnormal is set to B. max Set the threshold for judging abnormalities in the average torque as follows: The torque fluctuation amplitude threshold was set to ω0, and the torque change rate threshold was set to p0. The acquired torque characteristic values ​​were compared and analyzed with the set thresholds. The analysis results are as follows:

[0075] If B max This indicates that the peak torque is normal, and there is no abnormality.

[0076] If B≥B max This indicates that the peak torque is abnormally high, indicating that the valve stem is experiencing abnormally high friction or jamming in a local area during operation, and an abnormal alarm y1 is generated.

[0077] like This indicates that the average torque value is normal, and the situation is judged to be normal.

[0078] like This indicates that the average torque is abnormally high, indicating that the valve stem is continuously subjected to abnormally high loads during operation, and generates an abnormality warning x1.

[0079] If ω < ω0, it indicates that the torque fluctuation is normal and is judged to be without abnormality; ​

[0080] If ω0 ≤ ω, it indicates that the torque fluctuation amplitude is high, and it is judged that the operating state of the valve stem is unstable, there is a low - risk abnormality, and an abnormal prompt x2 is generated;

[0081] If p j ≤ p0, it indicates that the torque change rate is normal, and it is judged that there is no abnormal situation;

[0082] If p j > p0, it indicates that the torque fluctuation amplitude is extremely abnormal, and it is judged that the torque of the valve stem changes violently in a short time, and an alarm instruction y2 is generated;

[0083] After detecting the abnormal prompt instruction, record the moment t1 when the abnormal prompt is detected, and in the next data monitoring period, analyze the extracted data to judge whether the abnormal situation has recovered, and record the abnormal duration Δt′. Set the abnormal duration threshold as nT. If it is detected that Δt′ ≥ nT and the abnormality has not recovered, then convert the abnormal prompt into an abnormal alarm y2; if it is detected that Δt′ < nT and the abnormality has recovered, then cancel the abnormal prompt.

[0084] In step S3: When there is no abnormal situation, the interval duration for data collection is a dynamically changing value. Obtain the average life of the valve components of the valve through the database And collect and record the working duration d of the current valve components through the data collection device. Set the initial data collection interval duration Δt0 when the valve stem starts to work, and directly use Δt0 as the data collection interval duration in the first data collection cycle; starting from the second data monitoring cycle, the data collection interval duration is dynamically adjusted, and the interval duration for data collection is calculated according to the following formula:

[0085]

[0086] Among them, Δt0 represents the initial data collection interval duration set when the valve stem starts to work; w represents the standard deviation of the torque values collected in the previous data detection cycle;

[0087] Calculate the standard deviation of the torque values collected in one data collection cycle through the following formula:

[0088]

[0089] w represents the standard deviation of the torque values collected in the previous data collection cycle;

[0090] After detecting an anomaly alert, the data acquisition interval in the subsequent data acquisition cycle is further adjusted to account for the anomaly. A unit fluctuation duration ΔT0 for anomalies is set. After detecting the number of anomaly alerts k, the data acquisition interval is adjusted in the subsequent data monitoring cycle, and the adjusted data acquisition interval is Δt. 异常状态 =Δt-kΔT0; and after the abnormal situation is recovered, the adjustment of the data collection interval for the abnormal situation is lifted.

[0091] In step S4: The operating status of the valve stem is adjusted according to the generated abnormal prompt instructions and abnormal alarm instructions.

[0092] If an abnormality warning instruction x1 is received, the opening and closing speed of the abnormal valve stem will be reduced, and the lubrication intensity of the abnormal valve stem will be increased.

[0093] If an abnormality warning instruction x1 is received, the load on the valve stem of the abnormal valve will be reduced, and the lubrication intensity of the valve stem will be increased.

[0094] If an abnormal alarm command y1 is received, the control valve actuator will reduce the opening and closing amplitude and frequency of the abnormal valve, and after adding lubrication to the abnormal valve, it will further check whether the abnormal situation has disappeared. If the abnormal situation has disappeared, it will restore the normal operation state; if the abnormal situation has not disappeared, it will control the valve stem of the abnormal valve to stop running and wait for the staff to inspect and repair it.

[0095] If an abnormal alarm command y2 is received, the valve stem of the abnormal valve will be directly controlled to stop operation and wait for maintenance personnel.

[0096] Example 1: In step S1: When collecting monitoring data, a data collection period T = 10 minutes is set, and m = 5 torque values ​​are collected. The collected torque values ​​are represented as {A1 = 2800 N·m}.

[0097] m, A2=3000N˙m, A3=3200N˙m, A2=2600N˙m, A5=2600N˙m}; The average lifespan of the valve stem is obtained from the database. The system records the operating time of the valve stem for the current valve as d = 200 days; the interval between data collection in each data collection cycle is Δt.

[0098] In step S2: the acquired monitoring data is subjected to rate-shifting using an adaptive Kalman filter algorithm, and outliers in the acquired data are processed using an isolated forest algorithm; the acquired monitoring data is analyzed and processed to extract torque-related feature data, including peak torque and mean torque. Torque fluctuation amplitude ω and torque change rate p; peak torque is represented by B, B = max{A1, A2, ..., A m = 3200 N·m; Average torque ˙m; Calculate the torque fluctuation range using the following formula:

[0099] ω=B-min{A1,A2,…,A m};

[0100] Where ω represents the fluctuation amplitude, and i represents the label of the collected torque value, i = 1, 2, ..., m; This represents the mean of m collected torque values; min{A1, A2, ..., A m} represents the minimum value among m torque values; ω = 600 N·m;

[0101] The torque change rate over a data acquisition cycle can be calculated using the following formula:

[0102]

[0103] Where, p j The value represents the torque change rate within the data collection interval Δt; j represents the label of different torque change rates, j = 1, 2, 3, 4; p1 = 100 N·m / min; p2 = 100 N·m / min; p1 = 300 N·m / min; p1 = 0 N·m / min.

[0104] In step S3: A threshold is set for comparison and analysis with the acquired torque characteristic value to determine whether the valve stem is abnormal; the threshold for determining whether the torque peak value is abnormal is set to B. max Set the threshold for judging abnormalities in the average torque as follows: The torque fluctuation amplitude threshold was set to ω0 = 800 N·m, and the torque change rate threshold was set to p0 = 400 N·m / min. The obtained torque characteristic values ​​were compared and analyzed with the set thresholds. The analysis results are as follows:

[0105] B max This indicates that the peak torque is normal, and there is no abnormality.

[0106] This indicates that the average torque value is normal, and the situation is judged to be normal.

[0107] ω<ω0 indicates that the torque fluctuation is normal and is judged to be without abnormality;

[0108] p j ≤p0 indicates that the torque change rate is normal, and it is judged that there is no abnormality.

[0109] ​It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the invention can be implemented in other specific forms without departing from its spirit or essential characteristics. Therefore, the embodiments should be considered in all respects as exemplary and non-limiting, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be included within the present invention. No reference numerals in the claims should be construed as limiting the scope of the claims.

Claims

1. A valve stem operation status monitoring system based on the Internet of Things, characterized in that: The system includes an intelligent equipment maintenance management platform, a valve stem data acquisition module, a data processing module, an intelligent analysis module, and a control and adjustment module; The intelligent equipment maintenance management platform is equipped with a data processing module and an intelligent analysis module for receiving and storing monitoring data collected by the valve stem data acquisition module, and for processing and analyzing the collected data. The valve stem data acquisition module monitors the valve stem's operating status through a high-precision torque sensor, collects detection data, and transmits the collected monitoring data to the intelligent equipment maintenance management platform. The data processing module is deployed in the intelligent equipment maintenance management platform and is used to preprocess the collected monitoring data and extract torque-related features from the monitoring data of the valve stem. The intelligent analysis module performs intelligent analysis on the valve stem operating status based on the extracted torque-related features, determines whether the valve stem torque is abnormal, analyzes the cause of the abnormality, and generates abnormal prompts and abnormal alarm commands. The control adjustment module adjusts the operating status of the valve stem based on the received abnormal prompts and abnormal alarm commands.

2. The valve stem operation status monitoring system based on the Internet of Things according to claim 1, characterized in that: The valve stem data acquisition module uses a high-precision torque sensor to monitor the operating status of the valve stem and collects monitoring data from the valve stem operating turntable. The collected monitoring data is then transmitted wirelessly to the intelligent equipment maintenance management platform, and the collected detection data is stored in the intelligent equipment maintenance management platform.

3. The valve stem operation status monitoring system based on the Internet of Things according to claim 1, characterized in that: The intelligent equipment maintenance management platform is equipped with a data processing module and an intelligent analysis module; the intelligent equipment maintenance management platform is used to receive and store torque characteristic data collected by the valve stem data acquisition module; The data processing module includes a data preprocessing unit and a feature data extraction unit. The data preprocessing unit performs rate-wave analysis on the collected monitoring data using an adaptive Kalman filter algorithm and processes outliers using an isolated forest algorithm. The feature data extraction unit extracts torque-related feature data from the monitoring data, including torque peak value, torque mean value, torque fluctuation amplitude, torque change rate, and torque duration of anomalies. The intelligent analysis module includes an anomaly detection unit and an anomaly cause analysis unit. The anomaly detection unit determines whether an anomaly has occurred by setting thresholds and performing comparative analysis. The anomaly cause analysis unit analyzes the causes of anomalies based on their types.

4. The valve stem operation status monitoring system based on the Internet of Things according to claim 1, characterized in that: The control and adjustment module adjusts the operating status parameters of the valve switch according to the analyzed anomaly type. The adjustment process is realized by remotely controlling the valve actuator through the Internet of Things.

5. A method for monitoring the operating status of valve stems based on the Internet of Things, characterized in that: The method includes the following steps: S1. Monitor the valve stem operating status through a high-precision torque sensor, collect the detection data, and transmit the collected monitoring data to the intelligent equipment maintenance management platform; S2. Preprocess the collected monitoring data and extract the torque-related features from the monitoring data of the valve stem; S3. Based on the extracted torque-related features, conduct intelligent analysis on the operating state of the valve stem, determine whether there is an abnormality in the torque of the valve stem, analyze the reasons for the abnormality, and generate an abnormality prompt and an abnormality warning instruction. S4. Adjust the operating state of the valve stem according to the received abnormality prompt and abnormality warning instruction.

6. The valve stem operation status monitoring method based on the Internet of Things according to claim 5, characterized in that: In step S1: When collecting monitoring data, a data collection period T is set, and m torque values ​​are collected. The collected torque values ​​are represented as {A1, A2, ..., A...} m }; Obtain the average lifespan of the valve stem from the database. The system records the working time d of the valve stem currently in operation; the interval between data collection in each data acquisition cycle is Δt.

7. The valve stem operation status monitoring method based on the Internet of Things according to claim 6, characterized in that: In step S2: Filter the collected monitoring data through an adaptive Kalman filter algorithm, and use an isolation forest algorithm to process the outliers in the collected data. The collected monitoring data is analyzed and processed to extract torque-related feature data, including peak torque and average torque. Torque fluctuation amplitude ω and torque change rate p; peak torque is represented by B, B = max{A1, A2, ..., A m }; Average torque The torque fluctuation range is calculated using the following formula: ω=B-min{A1,A2,…,A m }; Where ω represents the fluctuation amplitude, and i represents the label of the collected torque value, i = 1, 2, ..., m; This represents the mean of m collected torque values; min{A1, A2, ..., A m } represents the minimum value among m torque values; Calculate the torque change rate within one data collection period according to the following formula: Where, p j The torque change rate is represented within the data collection interval Δt; j represents the label of different torque change rates, j = 1, 2, ..., m-1.

8. The valve stem operation status monitoring method based on the Internet of Things according to claim 7, characterized in that: In step S3: Set a threshold for comparison and analysis with the obtained torque characteristic value to determine whether there is an abnormality in the valve stem. Set the threshold for detecting abnormal peak torque to B. max Set the threshold for judging abnormalities in the average torque as follows: The torque fluctuation amplitude threshold was set to ω0, and the torque change rate threshold was set to p0. The acquired torque characteristic values ​​were compared and analyzed with the set thresholds. The analysis results are as follows: If B max This indicates that the peak torque is normal, and there is no abnormality.​ If B≥B max This indicates that the peak torque is abnormally high, indicating that the valve stem is experiencing abnormally high friction or jamming in a local area during operation, and an abnormal alarm y1 is generated. like This indicates that the average torque value is normal, and the situation is judged to be normal. like This indicates that the average torque is abnormally high, indicating that the valve stem is continuously subjected to abnormally high loads during operation, and generates an abnormality warning x1. If ω < ω0, it indicates that the torque fluctuation amplitude is normal, and it is judged as no abnormal situation. If ω0 ≤ ω, it indicates that the torque fluctuation amplitude is high, and it is judged that the operating state of the valve stem is unstable, there is a low-risk abnormality, and an abnormality prompt x2 is generated. If p j ≤p0 indicates that the torque change rate is normal, and it is judged that there is no abnormality. If p j >p0 indicates that the torque fluctuation is abnormally high, indicating that the valve stem torque has changed drastically in a short period of time, and an alarm command y2 is generated; After detecting the abnormality prompt instruction, record the moment t1 when the abnormality prompt is detected, and in the next data monitoring period, analyze the extracted data to determine whether the abnormal situation has recovered, and record the abnormal duration Δt′. Set the abnormal duration threshold as nT. If it is detected that Δt′ ≥ nT and the abnormality has not recovered, then convert the abnormality prompt into an abnormality warning y2; if it is detected that Δt′ < nT and the abnormality has recovered, then cancel the abnormality prompt.

9. A valve stem operation status monitoring method based on the Internet of Things according to claim 8, characterized in that: In step S3: Under normal circumstances, the data collection interval is a dynamically changing value, and the average lifespan of the valve is obtained from the database. The current valve operating time d is collected and recorded using data acquisition equipment. An initial data acquisition interval ΔT0 is set when the valve stem begins operation, and ΔT0 is directly used as the data acquisition interval during the first data acquisition cycle. From the second data monitoring cycle onwards, the data acquisition interval is dynamically adjusted, calculated using the following formula: Among them, Δt0 represents the initial data collection interval duration set at the start of the valve stem operation; w represents the standard deviation of the collected torque values in the previous data detection period. Calculate the standard deviation of the collected torque values within one data collection period through the following formula: w represents the standard deviation of the collected torque values in the previous data collection period. After detecting an anomaly alert, the data acquisition interval in the subsequent data acquisition cycle is further adjusted to account for the anomaly. An anomaly unit fluctuation duration ΔT0 is set. After detecting the number of anomaly alerts k, the data acquisition interval is adjusted in the subsequent data monitoring cycle, and the adjusted data acquisition interval is Δt. 异常状态 =Δt-kΔT0; and after the abnormal situation is recovered, the adjustment of the data collection interval for the abnormal situation is lifted.

10. A valve stem operation status monitoring method based on the Internet of Things according to claim 8, characterized in that: In step S4: Adjust the operating state of the valve stem according to the generated abnormality prompt instruction and abnormality warning instruction: If the abnormality prompt instruction x1 is received, reduce the opening and closing speed of the abnormal valve stem, and increase the lubrication intensity of the abnormal valve stem. If the abnormality prompt instruction x1 is received, reduce the load of the abnormal valve stem, and increase the lubrication intensity of the abnormal valve stem. If the abnormality warning instruction y1 is received, control the valve actuator to reduce the opening and closing amplitude and frequency of the abnormal valve, and after increasing the lubrication of the abnormal valve, further detect whether the abnormal situation disappears. If the abnormal situation disappears, then resume the normal operating state; if the abnormal situation does not disappear, then control the abnormal valve stem to stop operating and wait for the staff to repair. If the abnormality warning instruction y2 is received, directly control the abnormal valve stem to suspend operation and wait for the staff to repair.

Images