Cloud Computing-Based Valve Status Monitoring System

Abstract

The present invention relates to the technical field of remote monitoring, specifically a valve state monitoring system based on cloud computing. The system includes a state data acquisition module, a sealing performance attenuation analysis module, a mutation point identification module, a leakage anomaly detection module, and an anomaly trend warning module. In the present invention, by calculating the valve pressure change rate, the periodic flow change trend, the opening and closing torque increment, and the micro-pressure change rate per unit time, the attenuation trend of the sealing performance is quantitatively analyzed. Combining the instantaneous mutation amplitude of pressure and flow, the pressure offset before and after the mutation point, the flow recovery time, and the torque change, the types of mutation points are accurately distinguished. The pressure recovery rate, the pressure relief rate per unit time, and the non-zero flow mean value in the closed state after the occurrence of the mutation point are comprehensively analyzed. The leakage trend change rate and trend offset of the valve are synchronously calculated, and the change of the opening and closing torque is comprehensively analyzed to determine the growth rate of the leakage trend and dynamically evaluate the leakage risk level, enhancing the valve fault prevention ability.

Description

Technical Field

[0001] The present invention relates to the technical field of remote monitoring, and particularly to a valve status monitoring system based on cloud computing. Background Art

[0002] The technical field of remote monitoring includes equipment status monitoring, data acquisition, information transmission, and remote control based on network and computer technologies. The core content involves obtaining the operating status of a target object through sensors or detection devices and transmitting the information to a remote server or cloud for storage and analysis using data transmission protocols. It generally includes a data acquisition layer, a transmission layer, and an application layer. The data acquisition layer is responsible for obtaining real-time information of the monitored object, the transmission layer completes data transmission through wireless networks, wired networks, or a hybrid method, and the application layer is used for data processing, analysis, and visualization. It is widely used in industrial production, environmental monitoring, energy management, transportation, and other fields. By monitoring equipment or environmental parameters, real-time sharing of information and intelligent management are achieved.

[0003] Among them, a valve status monitoring system based on cloud computing refers to a system that uses cloud computing technology to remotely monitor the operating status of valves and manage data. The system collects the working parameters of valves through devices such as pressure sensors, flow meters, and temperature sensors and transmits the data to the cloud platform through wireless communication technology. In the cloud, data storage and computing technologies are used to classify and organize the collected information, and the status information of the valves is analyzed based on a rule engine. The system usually adopts a remote access protocol, enabling users to query the status data of valves in real time through a web page or a mobile terminal. In addition, the system also uses historical data storage technology to record the operation of valves for a long time for subsequent analysis and maintenance management.

[0004] In the current valve status monitoring process, only limited sensors are relied on to obtain basic working parameters, and a complete data set covering pressure, flow, opening and closing torque, and micro-pressure gradient has not been formed, resulting in a lack of overallness in status monitoring and making it difficult to accurately reflect the operating status. The evaluation of the sealing state is mainly based on the change of a single parameter, and the attenuation of the sealing performance cannot be quantitatively analyzed. It is easily affected by the environment, affecting the long-term monitoring effect of the sealing performance. The identification of mutation points relies on the fluctuation of a single parameter, lacking multi-dimensional cross-analysis, making it difficult to accurately classify the types of mutations and possibly leading to misjudgment or omission of key state changes. During the leakage anomaly detection process, the pressure recovery situation, pressure relief rate, and flow change under the closed state of the valve after the occurrence of mutation points are not comprehensively considered, resulting in the leakage determination result being easily affected by a single abnormal value and having a high false alarm rate. The trend analysis ability is insufficient, lacking a monitoring and warning mechanism for the development trend of leakage, making it difficult to identify potential risks in a timely manner, resulting in a lag in maintenance response and affecting the safety and reliability of valve operation. Summary of the Invention

[0005] The object of the present invention is to solve the deficiencies existing in the prior art, and a valve state monitoring system based on cloud computing is proposed.

[0006] To achieve the above object, the present invention adopts the following technical solutions: The valve state monitoring system based on cloud computing includes:

[0007] The state data acquisition module collects pressure, flow rate, opening and closing torque, and micro-pressure gradient data during the operation of the valve through sensors, records the change trend of the flow rate, detects the pressure difference before and after the valve, calculates the torque change during the opening and closing process, analyzes the micro-pressure gradient at the seal, and comprehensively generates a valve state monitoring data set;

[0008] The seal degradation analysis module reads the valve state monitoring data set, calculates the pressure change rate per unit time, analyzes the periodic flow rate change trend, calculates the opening and closing torque increment and the micro-pressure change rate, analyzes the degradation trend of the valve seal, and obtains the seal degradation analysis result;

[0009] The mutation point identification module detects the instantaneous mutation amplitude of the valve pressure and flow rate according to the seal degradation analysis result, calculates the pressure offset before and after the mutation point, analyzes the flow rate fluctuation and calculates the flow rate recovery time at the mutation point, synchronously calculates the torque increment after the mutation point, comprehensively judges the type of the mutation point, and generates the mutation point classification result;

[0010] The leakage anomaly detection module analyzes the valve pressure recovery rate after the mutation point occurs based on the mutation point classification result, calculates the pressure relief rate per unit time and the average non-zero flow rate of the valve in the closed state, judges the valve leakage state, and generates the leakage anomaly determination result.

[0011] As a further solution of the present invention, the valve state monitoring data set includes pressure data, flow rate data, opening and closing torque data, and micro-pressure gradient data; the seal degradation analysis result includes pressure change rate data, periodic flow rate change trend record, opening and closing torque increment, micro-pressure change rate, pressure change record in the sealed state, flow rate change record in the sealed state, torque change record in the sealed state, and micro-pressure change record in the sealed state; the mutation point classification result includes the instantaneous mutation amplitude of the valve pressure, the instantaneous mutation amplitude of the flow rate, the pressure offset before and after the mutation point, the analysis result of the flow rate fluctuation, the flow rate recovery time at the mutation point, the analysis result of the torque change, the torque increment after the mutation point, and the type of the mutation point; the leakage anomaly determination result includes the valve pressure recovery rate, the pressure gradient on both sides of the valve, the pressure relief rate per unit time, the average non-zero flow rate of the valve in the closed state, and the valve leakage state determination result.

[0012] As a further solution of the present invention, the state data acquisition module includes:

[0013] The sensing data acquisition sub-module acquires data from pressure sensors, flow sensors, torque sensors, and micro-pressure sensors, records the time-series data of pressure, flow rate, opening and closing torque, and micro-pressure gradient during the operation of the valve, analyzes the trend of the flow rate changing with time, obtains the change of the pressure difference before and after the valve with the flow rate fluctuation, calculates the instantaneous change rate corresponding to the time step, and generates the change rates of pressure, flow rate, torque, and micro-pressure.

[0014] The valve state calculation sub-module, based on the change rates of pressure, flow rate, torque, and micro-pressure, screens the instantaneous torque values at critical moments during the opening and closing process, calculates the gradient value of the torque changing with time, analyzes the interaction relationship between the torque change and pressure and flow rate, judges the pressure and flow rate states corresponding to the torque peak points, and obtains the gradient data of the opening and closing torque change.

[0015] The sealing characteristic analysis sub-module, according to the gradient data of the opening and closing torque change, analyzes the change trend of the micro-pressure gradient at the valve seal with time, analyzes the fluctuation characteristics of the micro-pressure gradient in the differential torque interval, calculates the correlation between the average value of the micro-pressure fluctuation at the seal and the torque change, determines the micro-pressure offset degree of the valve seal area, and comprehensively generates the valve state monitoring data set.

[0016] As a further solution of the present invention, the sealing performance attenuation analysis module includes:

[0017] The pressure change calculation sub-module reads the valve state monitoring data set, extracts the pressure data sequence within a unit time, calculates the pressure change rate of adjacent time steps, screens the data points with sudden changes in the pressure change rate, analyzes the periodic fluctuation amplitude of the change rate, and obtains the pressure change rate per unit time.

[0018] The flow rate trend analysis sub-module, according to the pressure change rate per unit time, screens the flow rate data corresponding to the time steps, calculates the average gradient of the flow rate change, judges the periodic characteristics of the flow rate trend, and counts the flow rate increment within the period to obtain the periodic flow rate change trend.

[0019] The seal state screening sub-module, based on the periodic flow rate change trend, screens the valve data in the sealed state, extracts the pressure, flow rate, torque, and micro-pressure values during the sealed state, calculates the torque increment within the sealed state, and analyzes the micro-pressure fluctuation condition when the valve is in the sealed state to obtain the sealed state change data.

[0020] The attenuation rate calculation sub-module, according to the sealed state change data, calculates the change rates of pressure, flow rate, torque, and micro-pressure during the valve sealed state time, extracts the correlation coefficient between the torque and the micro-pressure change, judges the trend direction of the sealing performance attenuation, and obtains the sealing performance attenuation analysis result.

[0021] As a further solution of the present invention, the mutation point identification module includes:

[0022] The pressure offset calculation sub-module reads the sealing attenuation analysis result, extracts the pressure data corresponding to the time steps before and after the mutation point, calculates the pressure difference before and after the mutation point, determines the direction of the pressure offset, screens the data with the pressure change at the mutation point exceeding the set change threshold, and obtains the pressure offset data at the mutation point;

[0023] The flow recovery calculation sub-module screens the flow data at the time of the mutation point according to the pressure offset data at the mutation point, analyzes the recovery process after the flow mutation, calculates the recovery time of the flow before and after the mutation point, and determines whether the flow recovery reaches the initial stable interval to obtain the flow recovery judgment result at the mutation point;

[0024] The mutation point classification judgment sub-module extracts the torque data after the mutation point based on the flow recovery judgment result at the mutation point, calculates the torque increment and determines the persistence of the torque mutation, combines the pressure offset amount and the flow recovery situation, analyzes the formation reason of the mutation point, and generates the mutation point classification result.

[0025] As a further solution of the present invention, the leakage anomaly detection module includes:

[0026] The pressure recovery calculation sub-module reads the mutation point classification result, extracts the valve pressure data after the mutation point occurs, counts the pressure recovery rate after the mutation point, screens the data with the pressure recovery rate lower than the set recovery threshold, calculates the stability coefficient of the pressure recovery trend, and obtains the pressure recovery analysis record at the mutation point;

[0027] The flow offset detection sub-module extracts the flow data on both sides of the valve after the mutation point according to the pressure recovery analysis record at the mutation point, screens the non-zero flow values in the closed state, calculates the flow offset amount per unit time, and determines the duration of the non-zero flow to obtain the flow offset amount in the closed state;

[0028] The leakage state judgment sub-module calculates the valve pressure relief rate based on the flow offset amount in the closed state, analyzes the relationship between the pressure relief rate and the flow offset, determines whether there is a leakage in the valve, and generates the leakage anomaly determination result.

[0029] As a further solution of the present invention, the stability coefficient of the pressure recovery trend is calculated using the formula:

[0030] ;

[0031] where, represents the stability coefficient of the pressure recovery trend, represents the total number of time steps, represents the time step at the moment of the pressure recovery rate data, represents the time step corresponding recovery time window value, represents the average pressure recovery rate within all time steps, represents the summation operation from time step 1 to time step of, represents the absolute value operation, represents the square root operation.

[0032] As a further aspect of the present invention, the system further includes an abnormal trend warning module;

[0033] The abnormal trend warning module calculates the change rate of the valve leakage trend within a continuous time window according to the leakage abnormality determination result, calculates the valve trend offset amount according to the change of the opening and closing torque, analyzes the growth rate of the valve leakage trend, determines the valve leakage risk level, and issues a valve leakage warning message;

[0034] The valve leakage warning message includes the change rate of the valve leakage trend, the valve trend offset amount, the growth rate of the valve leakage trend, and the valve leakage risk level.

[0035] As a further aspect of the present invention, the abnormal trend warning module includes:

[0036] The leakage trend calculation sub-module reads the leakage abnormality determination result, extracts the valve leakage rate data within a continuous time window, calculates the change value of the leakage rate per unit time, determines the increasing or decreasing trend of the leakage rate, and outputs the analysis result of the valve leakage trend change;

[0037] The valve offset amount calculation sub-module extracts the opening and closing torque data of the corresponding time window according to the valve leakage trend change analysis result, calculates the offset amplitude within the torque change interval, determines whether the torque offset changes with the leakage trend, marks the time period with abnormal torque change, and obtains the valve trend offset record;

[0038] The risk level assessment sub-module calculates the growth rate of the valve leakage trend based on the valve trend offset record, determines whether the valve leakage rate continues to rise, combines the change of the leakage trend, determines the valve leakage risk level, and generates a valve leakage warning message.

[0039] As a further aspect of the present invention, the growth rate of the leakage trend is calculated using the formula:

[0040] ;

[0041] for calculation, where represents the growth rate of the valve leakage trend, represents the total number of time steps, represents time step the valve leakage rate value at the moment of, represents time step Valve leakage rate value at a moment Represents a time step Timestamp at a moment Represents a time step Timestamp at a moment Represents the summation operation from time step 1 to time step The summation operation And Respectively represent the absolute values of the leakage rates at time steps And at a moment

[0042] Compared with the prior art, the advantages and positive effects of the present invention are as follows:

[0043] In the present invention, by comprehensively analyzing the flow rate change trend, the pressure difference before and after the valve, the torque change during the opening and closing process, and the micro-pressure gradient at the seal, the accurate reflection of the valve operation state is ensured. By calculating the pressure change rate per unit time, the periodic flow rate change trend, the opening and closing torque increment, and the micro-pressure change rate, and screening the key parameters in the sealed state, the attenuation trend of the sealing performance is quantitatively analyzed to avoid the deviation caused by single-parameter judgment. Combining the instantaneous mutation amplitudes of pressure and flow rate, the pressure offset before and after the mutation point, the flow rate recovery time, and the torque change, the types of mutation points are accurately distinguished to improve the accuracy of anomaly recognition. By comprehensively analyzing the pressure recovery rate, the pressure relief rate per unit time, and the non-zero flow rate mean value in the closed state after the mutation point occurs, the accurate judgment of leakage anomalies is realized, reducing the interference of environmental variables and improving the recognition reliability. By calculating the leakage trend change rate and trend offset of the valve, and comprehensively analyzing the change of the opening and closing torque, the growth rate of the leakage trend is determined, the leakage risk level is dynamically evaluated, early warning information is provided, and the fault prevention ability is enhanced. Overall, the quantitative analysis accuracy of the sealing performance attenuation trend is improved, the reliability of mutation point recognition is enhanced, the false judgment rate of leakage anomalies is reduced, and a forward-looking trend warning mechanism is provided to realize the active monitoring and accurate management of the valve operation state. Brief Description of the Drawings

[0044] Figure 1 is the system flow chart of the present invention;

[0045] Figure 2 is the system module diagram of the present invention;

[0046] Figure 3 is the flow chart of the state data acquisition module of the present invention;

[0047] Figure 4 is the flow chart of the sealing performance attenuation analysis module of the present invention;

[0048] Figure 5 is the flow chart of the mutation point recognition module of the present invention;

[0049] Figure 6 This is the flowchart of the leakage anomaly detection module of the present invention;

[0050] Figure 7 This is the flowchart of the anomaly trend warning module of the present invention. Specific embodiments

[0051] In order to make the objectives, technical solutions and advantages of the present invention clearer and more understandable, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0052] In the description of the present invention, it should be understood that the orientation or positional relationships indicated by the terms "length", "width", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc. are based on the orientation or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the present invention. In addition, in the description of the present invention, the meaning of "a plurality of" is two or more unless otherwise specifically defined.

[0053] Please refer to Figure 1 , the valve status monitoring system based on cloud computing includes:

[0054] The status data acquisition module collects pressure, flow rate, opening and closing torque, and micro-pressure gradient data during the operation of the valve through a pressure sensor, a flow sensor, a torque sensor, and a micro-pressure sensor, records the change trend of the flow rate, detects the pressure difference before and after the valve, calculates the torque change during the opening and closing process, analyzes the micro-pressure gradient at the sealing point, and comprehensively generates a valve status monitoring data set;

[0055] The sealing performance attenuation analysis module reads the valve status monitoring data set, calculates the pressure change rate per unit time, analyzes the change trend of the periodic flow rate, calculates the increment of the opening and closing torque and the micro-pressure change rate, screens the data of the pressure, flow rate, torque, and micro-pressure changes of the valve under the sealing state, analyzes the attenuation trend of the valve sealing performance, and obtains the sealing performance attenuation analysis result;

[0056] The mutation point identification module detects the instantaneous mutation amplitude of the valve pressure and flow rate according to the sealing performance attenuation analysis result, calculates the pressure offset before and after the mutation point, analyzes the flow rate fluctuation and calculates the flow rate recovery time at the mutation point, analyzes the torque change and calculates the torque increment after the mutation point, comprehensively judges the type of the mutation point, and generates the mutation point classification result;

[0057] Based on the mutation point classification results, the leakage anomaly detection module analyzes the valve pressure recovery rate after the occurrence of mutation points, detects the pressure gradient on both sides of the valve, calculates the pressure relief rate per unit time, calculates the average non-zero flow rate of the valve in the closed state through a flow sensor, judges the valve leakage state, and generates a leakage anomaly determination result;

[0058] According to the leakage anomaly determination result, the abnormal trend warning module calculates the change rate of the valve leakage trend within a continuous time window, calculates the valve trend offset according to the change of the opening and closing torque, analyzes the growth rate of the valve leakage trend, judges the valve leakage risk level, and issues a valve leakage warning message.

[0059] The valve state monitoring data set includes pressure data, flow data, opening and closing torque data, and micro-pressure gradient data; the sealing performance attenuation analysis results include pressure change rate data, periodic flow change trend records, opening and closing torque increments, micro-pressure change rates, pressure change records in the sealed state, flow change records in the sealed state, torque change records in the sealed state, and micro-pressure change records in the sealed state; the mutation point classification results include the instantaneous mutation amplitude of the valve pressure, the instantaneous mutation amplitude of the flow rate, the pressure offset before and after the mutation point, the analysis result of the flow rate fluctuation condition, the flow rate recovery time at the mutation point, the analysis result of the torque change condition, the torque increment after the mutation point, and the mutation point type; the leakage anomaly determination result includes the valve pressure recovery rate, the pressure gradient on both sides of the valve, the pressure relief rate per unit time, the average non-zero flow rate of the valve in the closed state, and the valve leakage state determination result; the valve leakage warning message includes the change rate of the valve leakage trend, the valve trend offset, the growth rate of the valve leakage trend, and the valve leakage risk level.

[0060] Please refer to Figure 2 and Figure 3 , the state data acquisition module includes:

[0061] The sensing data acquisition sub-module acquires data from pressure sensors, flow sensors, torque sensors, and micro-pressure sensors, records the time series data of pressure, flow rate, opening and closing torque, and micro-pressure gradient during the operation of the valve, analyzes the trend of the flow rate changing with time, obtains the change of the pressure difference before and after the valve with the flow rate fluctuation, calculates the instantaneous change rate corresponding to the time step, and generates the pressure, flow rate, torque, and micro-pressure change rates;

[0062] The sensing data acquisition sub-module collects data from pressure sensors, flow sensors, torque sensors, and micro-pressure sensors. It initializes and sets each type of sensor respectively, setting its sampling frequency and data storage format. The pressure sensor collects the pressure values before and after the valve and stores them in a data table indexed by time stamps. The flow sensor obtains real-time flow data and stores the flow values in matching with time. The torque sensor records the torque change values during the opening and closing process of the valve, with a sampling period set to 10 ms. The micro-pressure sensor detects the micro-pressure gradient in the valve sealing area and stores data for each sampling point based on the valve operation time axis, recording the time series data of pressure, flow, opening and closing torque, and micro-pressure gradient during valve operation. The data format is set as a quadruple (time, pressure, flow, torque, micro-pressure). For the trend of flow changing with time, the differential calculation method is used to calculate the difference between the flow values at two adjacent time points and calculate its change rate: , where is the flow at the current time , is the flow at the previous moment , is the sampling time interval, obtaining the change of the pressure difference before and after the valve with the flow fluctuation, and calculating the pressure difference before and after the valve: , where is the pressure at the front end of the valve is the pressure at the rear end of the valve. The data is stored in the pressure-flow matrix. For the instantaneous change rate corresponding to the time step, calculate and respectively to form a time series data group, and finally generate the change rates of pressure, flow, torque, and micro-pressure.

[0063] Based on the change rates of pressure, flow, torque, and micro-pressure, the valve state calculation sub-module screens the instantaneous torque values at critical moments during the opening and closing process, calculates the gradient value of the torque changing with time, analyzes the interaction relationship between the torque change and pressure and flow, and determines the pressure and flow states corresponding to the torque peak point to obtain the change gradient data of the opening and closing torque;

[0064] Based on the change rates of pressure, flow, torque, and micro-pressure, the valve state calculation sub-module divides the opening and closing process into time periods, sets the initial opening time point and the fully closed time point . According to the time interval , it sequentially screens the critical moments during the opening and closing process. For , calculate the instantaneous torque value . The values collected by the torque sensor are stored in a data table in chronological order, calculate the gradient value of the torque changing with time, set the gradient calculation window , and adopt the sliding window calculation method. Every Calculate the torque gradient for each time step: Analyze the interaction relationship between the resolved torque change and pressure and flow rate, construct a three-dimensional matrix of torque-pressure-flow rate, and set a torque threshold When is satisfied, extract the corresponding pressure and flow rate status, store the data in the interaction matrix, screen the pressure and flow rate status corresponding to the torque peak point, and determine the local maximum value, record and , form a time-torque-pressure-flow rate data group, and finally obtain the opening and closing torque change gradient data.

[0065] The seal characteristic analysis sub-module analyzes the change trend of the micro-pressure gradient at the valve seal over time according to the opening and closing torque change gradient data, analyzes the fluctuation characteristics of the micro-pressure gradient within the differential torque range, calculates the correlation between the average micro-pressure fluctuation at the seal and the torque change, determines the micro-pressure offset degree of the valve seal area, and comprehensively generates a valve status monitoring data set;

[0066] The seal characteristic analysis sub-module extracts the change of the micro-pressure gradient in the valve seal area according to the opening and closing torque change gradient data, sets the detection time period for the change of the micro-pressure gradient , performs differential calculation on the micro-pressure gradient within this time period, sets a fluctuation threshold , classifies into intervals, determines as the violently fluctuating interval, as the smoothly fluctuating interval, analyzes the fluctuation characteristics of the micro-pressure gradient within the differential torque range, extracts the micro-pressure gradient data for each torque interval, sets the torque segmentation interval , calculates the change range of the micro-pressure gradient within each torque interval, obtains the average value , calculates the correlation between the average micro-pressure fluctuation at the seal and the torque change, sets a correlation threshold , and calculates using the Pearson correlation coefficient: where is the torque value, is the micro-pressure gradient, and are the average values. When , it is determined that the micro-pressure gradient fluctuation is significantly affected by the torque change. Finally, the micro-pressure offset degree of the valve seal area is determined, and a valve status monitoring data set is comprehensively generated.

[0067] Please refer to Figure 2 and Figure 4 , the sealing performance attenuation analysis module includes:

[0068] The pressure change calculation sub-module reads the valve status monitoring data set, extracts the pressure data sequence within a unit time, calculates the pressure change rate of adjacent time steps, filters the data points with sudden changes in the pressure change rate, analyzes the periodic fluctuation amplitude of the change rate, and obtains the pressure change rate per unit time.

[0069] The pressure change calculation sub-module reads the valve status monitoring data set, obtains the pressure values at different time points from the database or storage file, establishes a data sequence with the time stamp as the index, calculates the pressure values of each adjacent time step to determine the pressure change rate, that is, subtracts the pressure value of the previous time point from the pressure value of the current time point, and then divides by the time interval between the two time points to obtain the rate of change of pressure over time. Filter the data points with sudden changes in the pressure change rate, set the mutation determination criteria, statistically analyze the pressure change rates within all time steps, calculate their mean and variance, determine the normal range of the pressure change rate, and set a threshold for determining mutation points. If the pressure change rate at a certain time point changes more than the set threshold compared with the previous and subsequent time points, then this time point is marked as a mutation point. Subsequently, analyze the periodic fluctuation amplitude of the change rate, extract the pressure change rate data within all time steps, calculate the average value of the pressure change rate over the entire operation cycle, and statistically analyze its fluctuation range. Determine whether the fluctuation range exceeds the preset standard interval. If the fluctuation range exceeds the set interval, it is considered that the pressure change has obvious periodic fluctuation characteristics. Finally, obtain the pressure change rate per unit time.

[0070] The flow trend analysis sub-module filters the flow data corresponding to the time steps according to the pressure change rate per unit time, calculates the average gradient of the flow change, judges the periodic characteristics of the flow trend, statistically analyzes the flow increment within the period, and obtains the periodic flow change trend.

[0071] The flow trend analysis sub-module extracts the flow data corresponding to the time steps from the filtered pressure mutation points according to the pressure change rate per unit time, analyzes the change trend of the flow at the time points, calculates the average gradient of the flow change, that is, within multiple time steps, gradually calculates the increment of the flow values between adjacent time points, and averages all the increment data to obtain the trend rate of the overall flow change. Judge the periodic characteristics of the flow trend. First, statistically analyze the flow values at all time points, calculate the average cycle length of the flow change, and statistically analyze the fluctuation range of the flow within the period. If the flow fluctuation range exceeds the set normal change threshold, it is determined that the flow trend has periodic characteristics. Subsequently, statistically analyze the flow increment within each period, calculate the difference between the maximum flow value and the minimum flow value within the period, and use this difference as a measure of the periodic flow change, so as to obtain the periodic flow change trend.

[0072] The sealed state screening sub-module screens the valve data in the sealed state based on the periodic flow change trend, extracts the pressure, flow, torque, and micro-pressure values during the sealed state, calculates the torque increment within the sealed state, analyzes the micro-pressure fluctuation situation when the valve is in the sealed state, and obtains the sealed state change data;

[0073] The sealed state screening sub-module screens the valve data in the sealed state based on the periodic flow change trend. During the time period when the flow fluctuation is small and tends to be stable, it extracts the pressure, flow, torque, and micro-pressure data within this time period, analyzes the change situation of the torque in the sealed state, calculates the torque increment during the sealed state, that is, within multiple time steps of this time period, gradually calculates the change of the torque value between adjacent time points, and statistically calculates the torque change amplitude during the entire sealed state period. Furthermore, it analyzes the micro-pressure fluctuation situation in the sealed state, extracts the micro-pressure value within this time period from the time series data, calculates the change rate of the micro-pressure, that is, the ratio of the increment of the micro-pressure data between adjacent time points to the time interval, and statistically calculates the mean and fluctuation range of the micro-pressure change rate within this time period, and finally obtains the sealed state change data.

[0074] The decay rate calculation sub-module calculates the change rates of the pressure, flow, torque, and micro-pressure within the valve sealed state time according to the sealed state change data, extracts the correlation coefficient between the torque and the micro-pressure change, judges the trend direction of the seal decay, and obtains the seal decay analysis result;

[0075] The decay rate calculation sub-module calculates the change rates of the pressure, flow, torque, and micro-pressure within the valve sealed state time according to the sealed state change data, sets a time window for detecting the decay trend. Within this time window, it calculates the pressure change rate, flow change rate, torque change rate, and micro-pressure change rate between adjacent time points respectively, obtains a series of change rate values within a series of time steps, and statistically analyzes them, extracts the correlation between the torque and the micro-pressure change, calculates their linear correlation degree by comparing the torque change values and micro-pressure change values of multiple time steps, and judges the relationship between the two. If the torque change rate and the micro-pressure change rate show the same change trend within multiple time steps, and their correlation gradually increases over time, it is considered that the seal decay trend is obvious, and finally the analysis result of the seal decay is obtained.

[0076] Please refer to Figure 2 and Figure 5 , the mutation point identification module includes:

[0077] The pressure offset calculation sub-module reads the seal decay analysis result, extracts the pressure data corresponding to the time steps before and after the mutation point, calculates the pressure difference before and after the mutation point, judges the direction of the pressure offset, screens the data where the pressure change at the mutation point exceeds the set change threshold, and obtains the mutation point pressure offset data;

[0078] The pressure offset calculation sub-module reads the sealing attenuation analysis results, extracts the pressure data corresponding to the time steps before and after the mutation point from the stored dataset, determines the time interval before and after the mutation point. Taking the mutation point as a reference, it extracts the pressure data of several time steps forward, calculates the average pressure value before the mutation point, and extracts the pressure data of several time steps backward, calculates the average pressure value after the mutation point. It performs a difference calculation on the average pressure values before and after the mutation point to obtain the pressure offset at the mutation point, and judges the direction of the pressure offset. If the pressure value after the mutation point is higher than the pressure value before the mutation point, it is determined that the pressure has increased; otherwise, it is determined that the pressure has decreased. It screens the data where the pressure change at the mutation point exceeds the set change threshold, sets the pressure change threshold, compares the pressure difference before and after the mutation point with the set threshold. If the pressure change amplitude exceeds the threshold range, the mutation point is retained; otherwise, the point is excluded. Finally, the pressure offset data at the mutation point is obtained.

[0079] The flow rate recovery calculation sub-module screens the flow rate data at the time of the mutation point according to the pressure offset data at the mutation point, analyzes the recovery process after the flow rate mutation, calculates the recovery time of the flow rate before and after the mutation point, and judges whether the flow rate recovery reaches the initial stable interval to obtain the flow rate recovery judgment result at the mutation point;

[0080] The flow rate recovery calculation sub-module screens the flow rate data at the time of the mutation point according to the pressure offset data at the mutation point, extracts the flow rate value corresponding to the time step of the mutation point from the dataset, and extracts the flow rate data within the time steps before and after the mutation point, calculates the flow rate change trend, analyzes the recovery process after the flow rate mutation, sets the recovery time calculation window, calculates the flow rate change rates within the time steps before and after the mutation point respectively, compares the change trends before and after the flow rate mutation. If the flow rate tends to be stable within a certain time after the mutation, it is determined that the flow rate recovery is completed, calculates the recovery time of the flow rate before and after the mutation point, counts the number of time steps required for the flow rate to reach the recovery stable state from the mutation point, judges whether the flow rate recovery reaches the initial stable interval, sets the flow rate recovery stable judgment threshold. If the change amplitude of the flow rate within a certain number of time steps is less than the threshold, it is considered that the flow rate has recovered to the initial stable state; otherwise, it is considered that it is still in the recovery process. Finally, the flow rate recovery judgment result at the mutation point is obtained.

[0081] The mutation point classification and judgment sub-module extracts the torque data after the mutation point based on the flow rate recovery judgment result at the mutation point, calculates the torque increment and judges the persistence of the torque mutation, combines the pressure offset and the flow rate recovery situation, analyzes the formation reason of the mutation point, and generates the mutation point classification result;

[0082] Based on the judgment result of the mutation point flow recovery, the mutation point classification judgment sub-module extracts the torque data after the mutation point, screens the torque values within several time steps after the mutation point time step from the stored dataset, calculates the torque increment, calculates the difference between the torque values before and after the mutation point, determines the torque change amplitude after the mutation point, judges the persistence of the torque mutation, sets the torque change persistence judgment standard, and statistically analyzes the torque change trend within multiple time steps after the mutation point. If the torque maintains the mutated state within a certain number of time steps, it is considered that the torque mutation persists; if the torque gradually returns to the pre-mutation level, it is considered that the torque change is an instantaneous mutation. Combining the pressure offset and the flow recovery situation, the formation reason of the mutation point is analyzed, the classification basis of the mutation point is established, and according to the pressure offset direction, the flow recovery trend, and the torque change mode, it is determined whether the mutation point belongs to the pressure fluctuation type, the flow disturbance type, or the torque impact type, and finally the mutation point classification result is generated.

[0083] Please refer to Figure 2 and Figure 6 , the leakage anomaly detection module includes:

[0084] The pressure recovery calculation sub-module reads the mutation point classification result, extracts the valve pressure data after the mutation point occurs, statistically analyzes the pressure recovery rate after the mutation point, screens the data with a pressure recovery rate lower than the set recovery threshold, calculates the stability coefficient of the pressure recovery trend, and obtains the mutation point pressure recovery analysis record;

[0085] The stability coefficient of the pressure recovery trend is calculated using the formula:

[0086] ;

[0087] For the calculation, where represents the stability coefficient of the pressure recovery trend, represents the total number of time steps, represents the time step at time represents the time step corresponding recovery time window value, represents the average pressure recovery rate within all time steps, represents the summation operation from time step 1 to time step ; represents the absolute value operation, represents the square root operation.

[0088] Pressure recovery rate ( ):

[0089] Time point 1 ( ): Pressure MPa;

[0090] Time point 2 ( ): Pressure MPa;

[0091] Time point 3 ( ): Pressure MPa;

[0092] Time point 4 ( ): Pressure MPa;

[0093] Calculate the pressure recovery rate for adjacent time steps according to the data:

[0094] MPa / h;

[0095] MPa / h;

[0096] MPa / h;

[0097] Recovery time window value ( ): Represents the time interval within each time step, in hours (h). In this example, assume the time interval for each time step is 1 hour, i.e., = = = 1 hour;

[0098] Mean pressure recovery rate ( ):

[0099] ;

[0100] Substitute the pressure recovery rate and recovery time window value calculated above:

[0101] ;

[0102] ;

[0103] Calculate the stability coefficient of the pressure recovery trend ( ):

[0104] Item 1:

[0105] ;

[0106] ;

[0107] Item 2:

[0108] ;

[0109] ;

[0110] Item 3:

[0111] ;

[0112] ;

[0113] Add up the above items and take the average value:

[0114] ;

[0115] ;

[0116] Take the square root:

[0117] ;

[0118] The results show that during the monitored time period of the valve, the fluctuation degree of the pressure recovery rate is 0.0469 MPa / h. The larger the value, the stronger the fluctuation of the pressure recovery process; the smaller the value, the more stable the pressure recovery process. Further, statistically analyze the variation range of the pressure recovery rate within multiple time steps, calculate the mean square deviation of the pressure recovery rate. If the mean square deviation is large, it indicates that the pressure recovery fluctuation is strong. If the mean square deviation is small, it indicates that the recovery process is stable. Finally, obtain the analysis record of the pressure recovery at the mutation point.

[0119] The flow offset detection sub-module extracts the flow data on both sides of the valve after the mutation point according to the analysis record of the pressure recovery at the mutation point, screens the non-zero flow values in the closed state, calculates the flow offset per unit time, determines the duration of the non-zero flow, and obtains the flow offset in the closed state;

[0120] The flow offset detection sub-module extracts the flow data on both sides of the valve after the mutation point according to the analysis record of the pressure recovery at the mutation point, extracts the inlet and outlet flow values at the mutation point time step and several subsequent time steps from the dataset, matches the valve opening information with the time stamp, screens the non-zero flow values in the closed state, checks whether there is a situation where the inlet and outlet flows are not zero in the closed state of the valve, and statistically analyzes the time distribution of these non-zero flow values, calculates the flow offset per unit time, calculates the difference between the inlet and outlet flows in each time step, and divides this value by the time interval to obtain the flow offset rate per unit time, determines the duration of the non-zero flow, statistically analyzes the duration of the non-zero flow in consecutive time steps, sets the flow duration determination threshold. If the duration of the non-zero flow exceeds this threshold, it is considered that the flow is abnormal. Finally, obtain the flow offset in the closed state.

[0121] The leakage state judgment sub-module calculates the pressure relief rate of the valve based on the flow offset in the closed state, analyzes the relationship between the pressure relief rate and the flow offset, determines whether there is a leakage in the valve, and generates a leakage abnormality determination result;

[0122] The leakage state judgment submodule calculates the valve pressure relief rate based on the closed state flow offset, extracts the pressure data in the time step after the mutation point from the data set, calculates the rate of change of the pressure values in adjacent time steps, and counts the average pressure change in the entire time period to measure the pressure relief rate, analyzes the relationship between the pressure relief rate and the flow offset, and calculates the correlation between the pressure relief rate and the flow offset rate in multiple time steps. If the two have a strong positive correlation, it indicates that the flow offset may be caused by pressure relief, and judges whether the valve has a leak. A leakage judgment threshold is set. If the correlation between the pressure relief rate and the flow offset rate exceeds the set value, and the flow offset duration exceeds a certain threshold, it is judged that the valve has a leak, and finally a leakage abnormality judgment result is generated.

[0123] See also Figure 2 and Figure 7 , the abnormal trend warning module includes:

[0124] The leakage trend calculation submodule reads the leakage anomaly judgment result, extracts the valve leakage rate data in the continuous time window, calculates the leakage rate change value per unit time, determines the leakage rate increase and decrease trend, and outputs the valve leakage trend change analysis result;

[0125] The leakage trend calculation submodule reads the leakage anomaly judgment result, extracts the valve leakage rate data in the continuous time window from the data set, filters the leakage rate values in a fixed time range with the timestamp as the index, and stores them as time series data, calculates the leakage rate change value per unit time, obtains the change amount from the leakage rate data of adjacent time steps, and divides the change amount by the time interval to obtain the leakage rate change rate, determines the leakage rate increase or decrease trend, and counts the leakage rate change rate data of all time steps, and calculates the mean and standard deviation of the change trend. If the mean is positive, it indicates that the leakage rate is increasing. If the mean is negative, it indicates that the leakage rate is decreasing. If the standard deviation is small, it indicates that the leakage trend is relatively stable. If the standard deviation is large, it indicates that the leakage rate changes more drastically. Finally, the valve leakage trend change analysis results are output.

[0126] The valve offset calculation submodule extracts the opening and closing torque data of the corresponding time window according to the valve leakage trend change analysis results, calculates the offset amplitude within the torque change interval, determines whether the torque offset changes with the leakage trend, marks the period of abnormal torque change, and obtains the valve trend offset record;

[0127] Based on the analysis result of the valve leakage trend change, the valve offset calculation sub-module extracts the opening and closing torque data corresponding to the leakage trend change time window from the dataset, matches the leakage rate time window with the time stamp, filters the torque values within the same time range, calculates the offset amplitude within the torque change interval, calculates the difference between the maximum torque value and the minimum torque value within the interval to obtain the maximum offset amplitude, determines whether the torque offset changes with the leakage trend, compares the torque offset with the change rate of the leakage rate, calculates their correlation. If the torque offset amplitude increases with the increase of the leakage rate, it is determined that the two are positively correlated. If the torque offset amplitude decreases with the increase of the leakage rate, it is determined that the two are negatively correlated. If there is no obvious pattern, it is determined that there is no direct association. Mark the time period with abnormal torque change, set the abnormal threshold of torque change, compare the torque change rate within the time step with the set threshold. If it exceeds the threshold range, this time step is marked as abnormal, and finally the valve trend offset record is obtained.

[0128] Based on the valve trend offset record, the risk level assessment sub-module calculates the growth rate of the valve leakage trend, determines whether the valve leakage rate continues to rise, combines the change situation of the leakage trend, determines the valve leakage risk level, and generates valve leakage warning information;

[0129] The growth rate of the leakage trend is calculated using the formula:

[0130] ;

[0131] where, represents the growth rate of the valve leakage trend, represents the total number of time steps, represents the time step at which the valve leakage rate value, represents the time step at which the valve leakage rate value, represents the time step at which the time stamp, represents the time step at which the time stamp, represents the summation operation from time step 1 to time step , and respectively represent the absolute values of the leakage rates at time steps and .

[0132] Valve leakage rate ( ):

[0133] Time point 1 ( ): Leakage rate m³ / h;

[0134] Time point 2 ( ): Leakage rate m³ / h;

[0135] Time point 3 ( ): Leakage rate m³ / h;

[0136] Time point 4 ( ): Leakage rate m³ / h;

[0137] Time stamp ( ): Recording time corresponding to the above leakage rate, unit: hour (h)

[0138] Calculate the growth rate for each time step:

[0139] Step 1 (from to ):

[0140] ;

[0141] ;

[0142] Step 2 (from to ):

[0143] ;

[0144] ;

[0145] Step 3 (from to ):

[0146] ;

[0147] ;

[0148] Calculate the average growth rate :

[0149] ;

[0150] ;

[0151] The results show that the valve leakage rate increases by approximately 0.1446 m³ / h per hour on average during the monitored time period. To further determine whether the valve leakage rate continues to rise, the growth rate of the leakage rate within the time step is statistically analyzed, and the mean value and range of variation of the growth rate are calculated. If the mean value is greater than zero and the growth rate remains positive in multiple consecutive time steps, it is determined that the leakage rate continues to rise. Combining the change of the leakage trend, a risk assessment level standard is set. According to the magnitude, duration, and fluctuation range of the growth rate of the leakage rate, the risk level is divided into multiple levels, and the corresponding risk level is calculated for each time step, and finally, the valve leakage warning information is generated.

[0152] The above is only the preferred embodiment of the present invention, and it does not limit the present invention in other forms. Any person skilled in the art may use the disclosed technical content to make changes or modifications into equivalent embodiments with equivalent changes and apply them to other fields. However, as long as it does not depart from the technical solution content of the present invention, any simple modification, equivalent change, and modification made to the above embodiments based on the technical essence of the present invention still belong to the protection scope of the technical solution of the present invention.

Claims

1. A valve status monitoring system based on cloud computing, characterized in that: The system includes: The status data acquisition module collects pressure, flow rate, opening and closing torque, and micro-pressure gradient data during the operation of the valve through sensors, records the trend of flow rate changes, detects the pressure difference before and after the valve, calculates the torque changes during the opening and closing process, analyzes the micro-pressure gradient at the seal, and comprehensively generates a valve status monitoring data set; The seal tightness attenuation analysis module reads the valve status monitoring data set, calculates the pressure change rate per unit time, analyzes the trend of periodic flow rate changes, calculates the increment of opening and closing torque and the micro-pressure change rate, analyzes the trend of valve seal tightness attenuation, and obtains the seal tightness attenuation analysis result; The mutation point identification module detects the instantaneous mutation amplitudes of the valve pressure and flow rate according to the seal tightness attenuation analysis result, calculates the pressure offset before and after the mutation point, analyzes the flow rate fluctuation and calculates the flow rate recovery time at the mutation point, synchronously calculates the torque increment after the mutation point, comprehensively judges the type of mutation point, and generates the mutation point classification result; The leakage anomaly detection module analyzes the valve pressure recovery rate after the occurrence of the mutation point based on the mutation point classification result, calculates the pressure relief rate per unit time and the average non-zero flow rate of the valve in the closed state, judges the valve leakage state, and generates the leakage anomaly determination result.

2. The valve state monitoring system based on cloud computing according to claim 1, characterized in that: The valve status monitoring data set includes pressure data, flow rate data, opening and closing torque data, and micro-pressure gradient data; the seal tightness attenuation analysis result includes pressure change rate data, record of periodic flow rate change trend, increment of opening and closing torque, micro-pressure change rate, record of pressure change in the sealed state, record of flow rate change in the sealed state, record of torque change in the sealed state, record of micro-pressure change in the sealed state; the mutation point classification result includes instantaneous mutation amplitude of valve pressure, instantaneous mutation amplitude of flow rate, pressure offset before and after the mutation point, analysis result of flow rate fluctuation, flow rate recovery time at the mutation point, analysis result of torque change situation, torque increment after the mutation point, type of mutation point; the leakage anomaly determination result includes valve pressure recovery rate, pressure gradient on both sides of the valve, pressure relief rate per unit time, average non-zero flow rate of the valve in the closed state, valve leakage state determination result.

3. The valve status monitoring system based on cloud computing according to claim 1, characterized in that: The status data acquisition module includes: The sensing data acquisition sub-module collects data from pressure sensors, flow rate sensors, torque sensors, and micro-pressure sensors, records the time series data of pressure, flow rate, opening and closing torque, and micro-pressure gradient during the operation of the valve, analyzes the trend of flow rate change over time, obtains the change of the pressure difference before and after the valve with the flow rate fluctuation, calculates the instantaneous change rate corresponding to the time step, and generates the pressure flow torque micro-pressure change rate; The valve status calculation sub-module selects the instantaneous torque values at the critical moments during the opening and closing process based on the pressure flow torque micro-pressure change rate, calculates the gradient value of the torque change over time, analyzes the interaction relationship between the torque change and pressure and flow rate, judges the pressure and flow rate states corresponding to the torque peak point, and obtains the opening and closing torque change gradient data; The seal characteristic analysis sub-module analyzes the variation trend of the micro-pressure gradient at the valve seal over time based on the change gradient data of the opening and closing torque, analyzes the fluctuation characteristics of the micro-pressure gradient within the differential torque range, calculates the correlation between the mean micro-pressure fluctuation at the seal and the torque change, determines the micro-pressure offset degree of the valve seal area, and comprehensively generates a valve state monitoring data set.

4. The valve status monitoring system based on cloud computing according to claim 1, characterized in that: The seal performance attenuation analysis module includes: The pressure change calculation sub-module reads the valve state monitoring data set, extracts the pressure data sequence per unit time, calculates the pressure change rate for adjacent time steps, filters the data points with sudden changes in the pressure change rate, analyzes the periodic fluctuation amplitude of the change rate, and obtains the pressure change rate per unit time. The flow trend analysis sub-module filters the flow data for the corresponding time steps based on the pressure change rate per unit time, calculates the average gradient of the flow change, determines the periodic characteristics of the flow trend, and statistically calculates the flow increment within the period to obtain the periodic flow change trend. The seal state screening sub-module filters the valve data in the sealed state based on the periodic flow change trend, extracts the pressure, flow, torque, and micro-pressure values during the sealed state, calculates the torque increment within the sealed state, analyzes the micro-pressure fluctuation condition when the valve is in the sealed state, and obtains the seal state change data. The attenuation rate calculation sub-module calculates the change rates of pressure, flow, torque, and micro-pressure during the valve seal state time based on the seal state change data, extracts the correlation coefficient between the torque and micro-pressure changes, determines the trend direction of the seal performance attenuation, and obtains the seal performance attenuation analysis result.

5. The valve state monitoring system based on cloud computing according to claim 1, characterized in that: The mutation point identification module includes: The pressure offset calculation sub-module reads the seal performance attenuation analysis result, extracts the pressure data corresponding to the time steps before and after the mutation point, calculates the pressure difference before and after the mutation point, determines the direction of the pressure offset, filters the data where the pressure change at the mutation point exceeds the set change threshold, and obtains the mutation point pressure offset data. The flow recovery calculation sub-module filters the flow data at the time of the mutation point based on the mutation point pressure offset data, analyzes the recovery process after the flow mutation, calculates the recovery time of the flow before and after the mutation point, and determines whether the flow recovery reaches the initial stable range to obtain the mutation point flow recovery judgment result. The mutation point classification judgment sub-module extracts the torque data after the mutation point based on the mutation point flow recovery judgment result, calculates the torque increment and determines the persistence of the torque mutation, combines the pressure offset amount and the flow recovery situation, analyzes the formation reason of the mutation point, and generates the mutation point classification result.

6. The valve state monitoring system based on cloud computing according to claim 1, characterized in that: The leakage anomaly detection module includes: The pressure recovery calculation sub-module reads the mutation point classification result, extracts the valve pressure data after the mutation point occurs, statistically calculates the pressure recovery rate after the mutation point, filters the data where the pressure recovery rate is lower than the set recovery threshold, calculates the stability coefficient of the pressure recovery trend, and obtains the mutation point pressure recovery analysis record. The flow offset detection sub-module extracts the flow data on both sides of the valve after the mutation point based on the mutation point pressure recovery analysis record, filters the non-zero flow values in the closed state, calculates the flow offset amount per unit time, and determines the duration of the non-zero flow to obtain the flow offset amount in the closed state. The leakage state judgment sub-module calculates the valve pressure relief rate based on the closed-state flow offset, analyzes the relationship between the pressure relief rate and the flow offset, determines whether there is a leakage in the valve, and generates a leakage anomaly determination result.

7. The valve status monitoring system based on cloud computing according to claim 6, characterized in that: The stability coefficient of the pressure recovery trend adopts the formula: ； Perform calculations, where, represents the stability coefficient of the pressure recovery trend, represents the total number of time steps, represents the time step pressure recovery rate data at the moment, represents the time step corresponding recovery time window value, represents the average value of the pressure recovery rate within all time steps, represents from time step 1 to time step summation operation, represents the absolute value operation, represents the square root operation.

8. The valve state monitoring system based on cloud computing according to claim 1, characterized in that: The system further includes an abnormal trend warning module; Based on the leakage anomaly determination result, the abnormal trend warning module calculates the change rate of the valve leakage trend within a continuous time window, calculates the valve trend offset according to the change in the opening and closing torque, analyzes the growth rate of the valve leakage trend, determines the valve leakage risk level, and issues a valve leakage warning message; The valve leakage warning message includes the change rate of the valve leakage trend, the valve trend offset, the growth rate of the valve leakage trend, and the valve leakage risk level.

9. The valve status monitoring system based on cloud computing according to claim 8, wherein: The abnormal trend warning module includes: The leakage trend calculation sub-module reads the leakage anomaly determination result, extracts the valve leakage rate data within a continuous time window, calculates the change value of the leakage rate per unit time, determines the increasing or decreasing trend of the leakage rate, and outputs the analysis result of the valve leakage trend change; The valve offset calculation sub-module extracts the opening and closing torque data of the corresponding time window according to the analysis result of the valve leakage trend change, calculates the offset amplitude within the torque change range, determines whether the torque offset changes with the leakage trend, marks the time period with abnormal torque change, and obtains the valve trend offset record; Based on the valve trend offset record, the risk level assessment sub-module calculates the growth rate of the valve leakage trend, determines whether the valve leakage rate continues to rise, combines the change of the leakage trend, determines the valve leakage risk level, and generates a valve leakage warning message.

10. The valve status monitoring system based on cloud computing according to claim 9, characterized in that: The growth rate of the leakage trend adopts the formula: ； Perform calculations, where represents the growth rate of the valve leakage trend, represents the total number of time steps, represents the time step the valve leakage rate value at time represents the time step the valve leakage rate value at time represents the time step the timestamp at time represents the time step the timestamp at time represents the summation operation from time step 1 to time step and and respectively represent the absolute values of the leakage rates at time steps and respectively.

Images