Fluid valve actuator monitoring and diagnosing system based on AI intelligence

Abstract

The invention relates to the technical field of fluid valve actuator equipment diagnosis, in particular to a fluid valve actuator monitoring and diagnosing system based on AI intelligence. According to the method, the target opening control instruction is generated through fluid medium characteristic data matching, and accurate regulation and control of the fluid valve are achieved; an opening degree change data set and a torque time sequence data set are captured in real time through a deployed sensor group, multi-dimensional dynamic fluctuation analysis is carried out, and intelligent recognition and screening of fluid valve abnormity are achieved; the medium temperature, the pipeline pressure and the medium flow velocity in the dynamic working condition parameters are substituted into a multiple regression linear model to generate reference torque and opening, and dynamic diagnosis of clamping stagnation abnormity is achieved by combining fusion calculation of a torque fluctuation coefficient and an opening deviation coefficient; through the correlation between the opening degree and the torque time sequence data and the traceability analysis of the current dynamic working condition parameters, the accurate positioning of the abnormal source is realized, and a systematic solution is provided for the state diagnosis and reliability evaluation of the fluid valve actuator.

Description

Technical Field

[0001] The present invention relates to the technical field of fluid valve actuator equipment diagnosis, and relates to a monitoring and diagnosis system for fluid valve actuators based on AI intelligence. Background Art

[0002] In many fields such as industrial production, energy transmission, and municipal engineering, fluid valves are widely used to control the flow rate, pressure, and flow direction of fluids. The stable operation of fluid valve actuators is crucial for the normal operation of the entire system. Once a fluid valve fails, such as jamming, it will not only affect the accuracy and efficiency of fluid control, but may also lead to production interruption, equipment damage, and even safety accidents. Therefore, accurate and timely monitoring and diagnosis of fluid valve actuators have important practical significance.

[0003] In the prior art, there are some related patents for diagnosing intermittent jamming of fluid valves. For example, a data processing system with the Chinese Patent Publication No. CN118043584A obtains input data including at least the time-series data of the valve opening degree of the main valve and the time-series data of the pressure on the output side of the solenoid valve of the driving fluid supplied and discharged from the solenoid valve to the driving device; and inputs the input data to a learned model that has learned the correlation between the input data and the output data including the time-series data of the acting torque acting on the valve stem corresponding to the input data, and infers the time-series data of the acting torque corresponding to the input data; at the same time, performs a specified process on the inferred time-series data of the acting torque, and determines whether there is an abnormality in at least one of the main valve and the driving device according to the result of the process.

[0004] However, the prior art has the following problems: 1. The operating state of the fluid valve is affected by various factors. In the prior art, it is difficult to comprehensively reflect the operating state of the actuator through a single torque data, and the dynamic influence of dynamic working conditions on the operation of the fluid valve is not fully considered. These changes will affect the normal operation of the fluid valve and the diagnostic results, resulting in serious interference of the diagnostic results by working condition fluctuations, and increasing the misjudgment probability of jamming faults.

[0005] 2. After the prior art determines that the fluid valve is abnormal, the traceability analysis of the abnormal source is not deep enough. It is difficult to accurately determine whether the fault is caused by lubricant failure, foreign object jamming, or mechanical transmission abnormality only based on torque data, which is not conducive to quickly taking targeted maintenance measures, prolonging the equipment downtime, and increasing the maintenance cost. Summary of the Invention

[0006] The present invention aims to provide a monitoring and diagnostic system for fluid valve actuators based on AI intelligence, so as to solve the problems existing in the monitoring and diagnosis of fluid valve actuators in the prior art, such as low diagnostic accuracy, poor adaptability to dynamic working conditions, and difficulty in tracing the source of anomalies, and to achieve more accurate and comprehensive monitoring and diagnosis of fluid valve actuators, improving the reliability and stability of equipment operation.

[0007] The technical solution adopted by the present invention to solve its technical problems is: a monitoring and diagnostic system for fluid valve actuators based on AI intelligence, including an execution instruction generation module, a multi-dimensional data monitoring module, an anomaly judgment module, a dynamic fault diagnosis module, and an anomaly source tracing module. Among them, the execution instruction generation module is connected to the multi-dimensional data monitoring module, the multi-dimensional data monitoring module is connected to the anomaly judgment module, the dynamic fault diagnosis module is respectively connected to the anomaly judgment module and the anomaly source tracing module, and the database is respectively connected to the execution instruction generation module and the dynamic fault diagnosis module.

[0008] The database is used to store the required opening degrees of fluid valves for different types of fluid media at different densities and viscosities, and to store the historical execution records of fluid valve actuators.

[0009] The execution instruction generation module is used to generate a target opening degree control instruction for the fluid valve according to the fluid medium characteristic data and send the instruction to the actuator.

[0010] The multi-dimensional data monitoring module is used to collect, in real time through a sensor group deployed in the fluid valve, the opening degree change data set and the torque time series data set of different fluid valves as time series response data.

[0011] The anomaly judgment module is used to extract the error between the starting change time and the steady state time of the opening degree from the opening degree change data set and judge whether there is an anomaly in the fluid valve according to the error between the starting change time and the steady state time of the opening degree.

[0012] The dynamic fault diagnosis module is used to perform dynamic deviation analysis on the time series response data of the abnormal fluid valve and the reference data affected by the preset dynamic working conditions, and screen out the stuck abnormal fluid valves according to the deviation results.

[0013] The anomaly source tracing module is used to perform tracing analysis by combining the time series response data of the stuck abnormal fluid valve and the current dynamic working condition parameters to generate an anomaly source diagnosis result.

[0014] Compared with the prior art, the present invention has the following beneficial effects:

[0015] (1) The present invention adopts multi-dimensional data acquisition and analysis means, comprehensively judges anomalies by combining the opening degree change data set and the torque time series data set of different fluid valves, solves the problem of diagnostic accuracy, reflects the operating state of the fluid valve actuator more comprehensively and accurately, improves the reliability of fault judgment, and ensures the stable operation of the equipment.

[0016] (2) The present invention fits the reference data for compensating the influence of dynamic working conditions based on a multiple regression linear equation, which is generated through normalization processing and associated compensation terms, effectively eliminating the interference of working condition parameters such as temperature, pressure, and flow rate on the diagnostic results and reducing the misjudgment probability of jamming faults.

[0017] (3) The present invention conducts dynamic deviation analysis on the time-sequence response data of the abnormal fluid valve and the reference data preset for the influence of dynamic working conditions, realizing refined diagnosis of the fluid valve under different working conditions, accurately screening out the jammed abnormal fluid valve, reducing the risk of diagnostic errors caused by changes in working conditions, and significantly improving the accuracy and reliability of diagnosis.

[0018] (4) The present invention combines the time-sequence response data of the jammed abnormal fluid valve and the current dynamic working condition parameters for traceability analysis to generate the diagnostic results of the abnormal source. Through timestamp alignment and analysis of the correspondence between the opening and torque, the fault source can be quickly located, providing clear guidance for optimizing the operation and maintenance measures of the fluid valve, thereby reducing the maintenance cost and downtime. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for describing the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention, and those of ordinary skill in the art can obtain other drawings without creative efforts based on these drawings.

[0020] Figure 1 It is a schematic diagram of the connection of the system modules of the present invention.

[0021] Figure 2 It is a schematic diagram of the judgment process for whether the fluid valve of the present invention is abnormal.

[0022] Figure 3 It is a schematic diagram of the determination steps for generating the diagnostic results of the abnormal source in the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0023] Various exemplary embodiments of the present invention will now be described in detail with reference to the drawings. It should be noted that: unless otherwise specifically stated, the relative arrangements, numerical expressions, and numerical values of the components and steps set forth in these embodiments do not limit the scope of the present invention. At the same time, it should be understood that, for the sake of convenience of description, the dimensions of the various parts shown in the drawings are not drawn in actual proportional relationships.

[0024] The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the invention, its application, or its use. Technologies, methods, and devices known to those of ordinary skill in the relevant art may not be discussed in detail, but where appropriate, the technologies, methods, and devices should be considered as part of the specification.

[0025] In all examples shown and discussed herein, any specific values should be construed as merely exemplary and not as limitations. Thus, other examples of exemplary embodiments may have different values.

[0026] The present invention provides a monitoring and diagnostic system for a fluid valve actuator based on AI intelligence. By matching fluid medium characteristic data, a target opening control instruction is generated to achieve precise regulation of the fluid valve. Through a deployed sensor group, a data set of opening changes and a data set of torque time series are captured in real time for multi-dimensional dynamic fluctuation analysis to achieve intelligent identification and screening of fluid valve anomalies. By substituting the medium temperature, pipeline pressure, and medium flow rate in the dynamic operating parameters into a multiple regression linear model to generate a reference torque and opening, and through the fusion calculation of the torque fluctuation coefficient and the opening deviation coefficient, dynamic diagnosis of jamming anomalies is achieved. Through the correlation relationship between the opening and torque time series data and the traceability analysis of the current dynamic operating parameters, precise positioning of the anomaly source is achieved. This solution breaks through the anomaly diagnosis bottleneck of traditional methods under dynamic operating condition interference and provides a systematic solution for the state diagnosis and reliability assessment of fluid valve actuators.

[0027] Please refer to Figure 1 As shown, the present invention provides a monitoring and diagnostic system for a fluid valve actuator based on AI intelligence, including an execution instruction generation module, a multi-dimensional data monitoring module, an anomaly judgment module, a dynamic fault diagnosis module, an anomaly source traceability module, and a database. The connection relationships between the modules are as follows: the execution instruction generation module is connected to the multi-dimensional data monitoring module, the multi-dimensional data monitoring module is connected to the anomaly judgment module, the dynamic fault diagnosis module is respectively connected to the anomaly judgment module and the anomaly source traceability module, and the database is respectively connected to the execution instruction generation module and the dynamic fault diagnosis module.

[0028] The database is used to store the required opening of the fluid valve for different types of fluid media at different densities and viscosities, and to store the historical execution records of the fluid valve actuator.

[0029] Among them, the required opening of the fluid valve for different types of fluid media at different densities and viscosities can be obtained through experimental testing methods. In a laboratory environment, for different types of fluid media (such as water, crude oil, alcohol, molten metal, etc.), by changing their densities and viscosities, at each density-viscosity combination, the fluid valve actuator is used to control the opening of the fluid valve, and the optimal required opening when the target flow rate or pressure is reached is measured. After multiple repeated experiments, data repeatability is ensured, and outliers are removed.

[0030] The execution instruction generation module is used to generate a target opening control instruction for the fluid valve according to the fluid medium characteristic data, and send the instruction to the actuator.

[0031] The method for generating the target opening control instruction of the fluid valve is as follows: according to the fluid type in the fluid medium characteristic data, retrieve the required opening of the fluid valve for the same type of fluid medium at different densities and viscosities from the database, match it with the fluid density and fluid viscosity in the fluid medium characteristic data to obtain the matched required opening, and generate a target opening control instruction for the fluid valve based on the required opening. Based on this required opening, generate a target opening control instruction for the fluid valve according to a specific instruction format, and send the instruction to the actuator through the communication interface to achieve precise control of the opening of the fluid valve.

[0032] The multi-dimensional data monitoring module is used to collect the opening change data set and torque time series data set of different fluid valves in real time through the sensor group deployed in the fluid valve as the time series response data. The sensor group includes a magnetic induction sensor and a strain gauge torque sensor.

[0033] The abnormality judgment module is used to extract the error between the starting change time and the steady state time of the opening from the opening change data set, and judge whether there is an abnormality in the fluid valve according to the error between the starting change time and the steady state time of the opening.

[0034] Please refer to Figure 2 As shown, it should be noted that judging whether there is an abnormality in the fluid valve specifically includes: extracting the starting time of the opening change and the stable time of the opening change from the opening change data set, and performing data dynamic fluctuation analysis on the starting time of the opening change of different fluid valves to obtain the time deviation fluctuation degree. The analysis method of the time deviation fluctuation degree is as follows: calculate the average starting time of the opening change for the starting time of the opening change of different fluid valves, and substitute the starting time of the opening change of different fluid valves and the average starting time of the opening change into the standard deviation calculation formula to obtain the time deviation fluctuation degree. By analyzing the fluctuation of the starting time of the opening change of different fluid valves, the stability of the fluid valve during operation can be judged. If the time deviation fluctuation degree is large, it means that the starting time of the opening change of the fluid valve is unstable and there may be a delay abnormality.

[0035] Starting time of opening change: refers to the time point corresponding to the start of the opening change in the opening change data set.

[0036] Stable time of opening change: refers to the time point corresponding to the opening reaching a stable state (no longer changing) in the opening change data set.

[0037] The difference between the stabilization time of the opening change of different fluid valves and the starting time of the opening change is analyzed with the standard duration for the corresponding fluid valve to reach the target opening, and the steady-state time error is obtained. The steady-state time error reflects the control accuracy of the fluid valve when reaching the target opening. A smaller steady-state time error indicates that the valve can reach and maintain the target opening more accurately. An increase in the steady-state time error may indicate potential faults in the fluid valve, such as wear of mechanical components, abnormal control signals, etc.

[0038] When the fluctuation degree of the time deviation exceeds the preset time deviation fluctuation threshold or the steady-state time error exceeds the preset time error threshold, it is determined that the fluid valve is abnormal.

[0039] The present invention uses multi-dimensional data acquisition and analysis means, comprehensively analyzes the opening change data set and the torque time series data set of different fluid valves for anomaly judgment, solves the problem of diagnostic accuracy, more comprehensively and accurately reflects the operating state of the fluid valve actuator, improves the reliability of fault judgment, and ensures the stable operation of the equipment.

[0040] The dynamic fault diagnosis module is used to perform dynamic deviation analysis on the time series response data of the abnormal fluid valve and the reference data affected by the preset dynamic working conditions, and screen the stuck abnormal fluid valve according to the deviation result.

[0041] It should be noted that the setting method of the reference data affected by the preset dynamic working conditions is as follows: The working condition parameters, torque time series data set and opening change data set of multiple execution records are retrieved from the historical execution records of the fluid valve actuator stored in the database. The torque average value of the torque time series data set and the opening stability value of the opening change data set are respectively subjected to multiple regression fitting with the medium temperature, pipeline pressure and medium flow rate in the working condition parameters to obtain the multiple regression linear equations of working condition parameter - torque and working condition parameter - opening. The opening stability value is the corresponding value when the opening in the opening change data set reaches the stable state.

[0042] The fitting process of the multiple regression linear equation is as follows: The torque average value, opening stability value, medium temperature, pipeline pressure and medium flow rate of multiple execution records are normalized. The normalized torque average value and opening stability value are respectively subjected to multiple linear regression equation fitting with the medium temperature, pipeline pressure and medium flow rate. If the multiple linear regression equation fitting is unsuccessful, the medium temperature, pipeline pressure and medium flow rate are subjected to correlation analysis to generate a correlation compensation term, and the multiple regression linear equations of working condition parameter - torque and working condition parameter - opening are obtained after refitting.

[0043] The normalization processing method can be the minimum - maximum normalization formula or the Z-score standardization formula , where is the normalized data. is the data that needs to be normalized, are the minimum and maximum values of the data that needs to be normalized, and are the mean and standard deviation of the data that needs to be normalized. Each parameter is processed separately. For example, the stable opening value is transformed to using min-max normalization, and the average torque, medium temperature, pipeline pressure, and medium flow rate are standardized using Z-score normalization.

[0044] In a specific embodiment, the average torque, medium temperature, pipeline pressure, and medium flow rate after normalization processing of multiple execution records are used for multiple linear regression equation fitting. The fitting equation is , are the average torque, medium temperature, pipeline pressure, and medium flow rate after normalization processing respectively, is the intercept, are the regression coefficients, is the regression coefficient corresponding to the medium temperature. When the temperature increases by 1°C, the change in torque caused by the decrease in viscosity may be negative, is the regression coefficient corresponding to the pipeline pressure. When the pressure increases by 1 MPa, the change in torque affected by the pressure difference driving effect is positive, is the regression coefficient corresponding to the medium flow rate. When the flow rate increases by 1 m / s, the change in torque dominated by inertial force may be positive.

[0045] If the solutions of are all unique solutions, the multiple linear regression equation fitting of the operating condition parameters - torque is successful.

[0046] If any one of the solutions of is not a unique solution, the multiple linear regression equation fitting of the operating condition parameters - torque is unsuccessful. The Pearson correlation coefficient analysis formula is used to perform pairwise correlation analysis on the medium temperature, pipeline pressure, and medium flow rate, and the correlation coefficients are output to determine the linear relationships of temperature - pressure, temperature - flow rate, and pressure - flow rate. The parameter ratios in the combinations with linear relationships are used to generate correlation compensation terms, and the multiple linear regression equation is refitted by combining the correlation compensation terms. is the regression coefficient corresponding to the correlation compensation term, is the correlation compensation term. There is one or more correlation compensation terms, is the error term, which covers all parts of the torque change not explained by temperature, pressure, flow rate, and correlation compensation terms, enabling the model to more realistically reflect the complexity of real data. Solve , the obtained results are fitted to generate a multiple linear regression equation of operating condition parameters - torque. Similarly, a multiple regression linear equation of operating condition parameters - opening is generated by fitting in the same way as above.

[0047] Further, taking the correlation analysis between the medium temperature and the pipeline pressure as an example, the medium temperature and the pipeline pressure of n execution records are obtained, and the correlation coefficient of temperature - pressure is analyzed through the Pearson correlation coefficient analysis formula. When the value of the correlation coefficient is , the linear relationship between temperature and pressure is positive linear correlation; when the value of the correlation coefficient is 0, the linear relationship between temperature and pressure is no linear relationship; when the value of the correlation coefficient is , the linear relationship between temperature and pressure is negative linear correlation.

[0048] The current dynamic operating condition parameters of the fluid valve are substituted into the multiple regression linear equation, and the reference torque and reference opening affected by the dynamic operating conditions of the fluid valve are output. Among them, the medium temperature, pipeline pressure and medium flow rate in the current dynamic operating condition parameters are measured by an infrared thermometer, a piezoelectric pressure sensor and an electromagnetic flowmeter respectively.

[0049] Based on the multiple regression linear equation, the present invention fits the reference data for compensating the influence of dynamic operating conditions, which is generated through normalization processing and correlation compensation terms, effectively eliminates the interference of operating condition parameters such as temperature, pressure and flow rate on the diagnosis result, and reduces the misjudgment probability of the jamming fault.

[0050] It should be noted that the screening method for the jammed abnormal fluid valve is as follows: the maximum torque, minimum torque and torque average value are screened from the torque time series data set in the time series response data of the abnormal fluid valve, and the torque fluctuation coefficient is calculated by combining with the reference torque.

[0051] The fusion calculation method of the torque fluctuation coefficient is as follows: the torque time series data set is divided into windows with a fixed duration, the corresponding torques of all windows are extracted, the maximum torque, minimum torque and torque average value are screened from them, the difference between the maximum torque and the minimum torque is ratioed with the reference torque to output the instantaneous fluctuation intensity, the absolute difference between the torque average value and the reference torque is ratioed with the reference torque to output the steady-state fluctuation intensity, and the adjacent feature matching is performed by combining the instantaneous fluctuation intensity and the steady-state fluctuation intensity to obtain the torque fluctuation coefficient.

[0052] Among them, weighted average is a mathematical means to achieve adjacent feature matching. The instantaneous fluctuation intensity measures the proportion of the absolute fluctuation range of torque within a time window to the reference torque. Under normal working conditions, the greater the instantaneous fluctuation intensity, the greater the torque fluctuation, indicating the existence of severe vibration or jamming; the steady-state fluctuation intensity quantifies the degree of deviation of the average torque from the reference value, reflecting long-term friction and wear or system drift. When the steady-state fluctuation intensity is greater, it indicates greater torque fluctuation, suggesting lubricant failure or mechanical structure deformation. To adapt to different working conditions, adaptive weight adjustment can be adopted. The weight factor of the instantaneous fluctuation intensity reflects the importance of the instantaneous peak-to-peak value. The weight factor of the instantaneous fluctuation intensity is obtained by dividing the instantaneous fluctuation intensity by the sum of the instantaneous fluctuation intensity and the steady-state fluctuation intensity. The weight factor of the steady-state fluctuation intensity reflects the importance of the mean deviation. The weight factor of the steady-state fluctuation intensity is the difference between 1 and the weight factor of the instantaneous fluctuation intensity.

[0053] According to the deviation between the opening degree at the end of the opening degree change data set and the reference opening degree, an opening degree deviation coefficient is generated. Among them, the opening degree deviation coefficient is expressed as the ratio of the deviation to the reference opening degree.

[0054] The torque fluctuation coefficient and the opening degree deviation coefficient are comprehensively statistically analyzed to output the comprehensive deviation of the abnormal fluid valve. The abnormal fluid valves with a comprehensive deviation greater than the set deviation threshold are screened out and regarded as jammed abnormal fluid valves. At the same time, the abnormal fluid valves with a comprehensive deviation less than or equal to the set deviation threshold are marked for reminder, alerting personnel to check the abnormal fluid valve, so as to be able to capture potential hidden dangers and prevent the escalation of faults.

[0055] The statistical formula for the comprehensive deviation of the abnormal fluid valve is , where are the torque fluctuation coefficient and the opening degree deviation coefficient respectively, are the weight coefficients of the torque fluctuation coefficient and the opening degree deviation coefficient respectively, which are assigned by expert experience. For example, if jamming is more sensitive to torque fluctuation, let , .

[0056] The present invention conducts dynamic deviation analysis on the time-series response data of the abnormal fluid valve and the reference data affected by the preset dynamic working conditions, realizes refined diagnosis of the fluid valve under different working conditions, accurately screens out jammed abnormal fluid valves, reduces the risk of diagnostic errors caused by changes in working conditions, and significantly improves the accuracy and reliability of diagnosis.

[0057] The abnormal source tracing module is used to conduct tracing analysis by combining the time-series response data of the jammed abnormal fluid valve and the current dynamic working condition parameters to generate an abnormal source diagnosis result.

[0058] Please refer to Figure 3As shown, it should be noted that the generation of the abnormal source diagnosis result includes: aligning the opening change data set and the torque time series data set of the stuck abnormal fluid valve through timestamps to obtain the opening change trend and the torque change trend at the same time series, obtaining the correlation between the opening and the torque based on the opening change trend and the torque change trend of the stuck abnormal fluid valve at all time series, and combining the current dynamic working condition parameters of the stuck abnormal fluid valve to conduct a traceability analysis to obtain the abnormal source diagnosis result.

[0059] Furthermore, the method for obtaining the correlation between the opening and the torque is as follows: if the opening change trend and the torque change trend of the stuck abnormal fluid valve are both upward trends at all time series, the correlation between the opening and the torque is a linear relationship; if the torque change trend of the stuck abnormal fluid valve is an upward trend while the opening change trend is a stable trend at any time series, the correlation between the opening and the torque is a non-linear relationship.

[0060] The judgment principle for the linear relationship between the opening and the torque is: increasing the opening requires overcoming continuously increasing frictional resistance. For example, insufficient lubrication or lubricant failure leads to an increase in uniform friction, so the torque requirement increases linearly with the opening.

[0061] The judgment principle for the non-linear relationship between the opening and the torque is: the valve movement suddenly encounters intermittent resistance, such as local jamming of foreign objects or abnormal mechanical transmission deformation, resulting in a sudden increase in torque while the opening remains stagnant, showing a non-linear mutation.

[0062] The specific process of the above-mentioned traceability analysis by combining the current dynamic working condition parameters of the stuck abnormal fluid valve is as follows: when the correlation between the opening and the torque of the stuck abnormal fluid valve is a linear relationship, extract the medium temperature in the current dynamic working condition parameters, compare the medium temperature with the applicable temperature range of the fluid valve lubricant, and judge whether the abnormal source of the stuck abnormal fluid valve is lubricant failure according to the comparison result.

[0063] The judgment basis for lubricant failure is that the medium temperature is not within the applicable temperature range of the fluid valve lubricant, which causes the lubricant to carbonize due to high temperature or solidify due to low temperature. The applicable temperature range of the fluid valve lubricant is determined through material characteristic tables or laboratory tests.

[0064] When the correlation between the opening and the torque of the stuck abnormal fluid valve is a non-linear relationship, extract the medium flow rate in the current dynamic working condition parameters of the stuck abnormal fluid valve, analyze the deviation degree between the medium flow rate and the reference flow rate of the fluid medium corresponding to the opening of the fluid valve at the current time series. When the deviation degree is greater than the set deviation degree threshold, it is diagnosed that the abnormal source of the fluid valve is foreign object jamming; otherwise, it is diagnosed that the abnormal source of the fluid valve is mechanical transmission abnormality.

[0065] The deviation degree analysis method is to compare the deviation between the medium flow rate and the reference flow rate of the fluid medium corresponding to the opening of the fluid valve at the current time sequence, and take the ratio of the obtained deviation result to the reference flow rate of the fluid medium corresponding to the opening of the fluid valve at the current time sequence as the deviation degree. The reference flow rate of the fluid medium corresponding to the opening of the fluid valve at the current time sequence is generated through the fluid medium flow rate - opening characteristic curve or numerical simulation.

[0066] The present invention combines the time sequence response data of the stuck abnormal fluid valve and the current dynamic working condition parameters for traceability analysis to generate an abnormal source diagnosis result. Through timestamp alignment and the analysis of the corresponding relationship between the opening and the torque, the fault source can be quickly located, providing clear guidance for optimizing the operation and maintenance measures of the fluid valve, thereby reducing the maintenance cost and downtime.

[0067] The above formulas are all dimensionless and take their numerical calculations. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0068] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product.

[0069] Those of ordinary skill in the art can realize that the modules and algorithm steps of each example described in combination with the embodiments disclosed in this article can be implemented by electronic hardware, or by a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this application.

[0070] In addition, in each embodiment of the present application, the functional modules can be integrated into a processing module, or each module can exist physically alone, or two or more modules can be integrated into one module.

[0071] The above is only the specific implementation manner of this application, but the protection scope of this application is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed in this application, and all should be covered within the protection scope of this application. Therefore, the protection scope of this application should be subject to the protection scope of the claims.

[0072] Finally, the above is only the preferred embodiment of the present invention and is not used to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A fluid valve actuator monitoring and diagnosis system based on AI intelligence, characterized in that: include: An execution instruction generation module is used to generate a fluid valve target opening control instruction according to the fluid medium characteristic data, and send the instruction to the actuator; A multi-dimensional data monitoring module, which is used to collect the opening change data set and torque time series data set of different fluid valves in real time through the sensor group deployed in the fluid valve as the time series response data; An abnormality judgment module is used to extract the opening start change time and the steady-state time error from the opening change data set, and judge whether the fluid valve has an abnormality according to the opening start change time and the steady-state time error; A dynamic fault diagnosis module is used to perform dynamic deviation analysis on the timing response data of abnormal fluid valves and reference data affected by preset dynamic working conditions, and screen the abnormally stuck fluid valves according to the deviation results; The abnormal source tracing module is used to combine the timing response data of the abnormally stuck fluid valve and the current dynamic operating parameters to perform tracing analysis and generate abnormal source diagnosis results.

2. The AI-based fluid valve actuator monitoring and diagnostic system according to claim 1 is characterized in that: The fluid valve target opening control instruction is generated in the following manner: According to the fluid type in the fluid medium characteristic data, the required fluid valve opening of the same type of fluid medium at different densities and viscosities is retrieved from the database, matched with the fluid density and fluid viscosity in the fluid medium characteristic data, and the matched required opening is obtained, and the fluid valve target opening control instruction is generated based on the required opening.

3. The AI-based fluid valve actuator monitoring and diagnostic system according to claim 1 is characterized in that: The determining whether the fluid valve is abnormal specifically includes: Extract the opening change start time and the opening change stabilization time from the opening change data set, perform data dynamic fluctuation analysis on the opening change start time of different fluid valves, and obtain the time deviation fluctuation; The difference between the opening change stabilization time and the opening change start time of different fluid valves and the standard time for the corresponding fluid valve to reach the target opening are analyzed to obtain the steady-state time error; When the time deviation fluctuation exceeds a preset time deviation fluctuation threshold or the steady-state time error exceeds a preset time error threshold, it is determined that the fluid valve is abnormal.

4. The AI-based fluid valve actuator monitoring and diagnostic system according to claim 3 is characterized in that: The analysis method of the time deviation fluctuation is: The average opening change starting time of different fluid valves is calculated by averaging, and the opening change starting time of different fluid valves and the average opening change starting time are substituted into the standard deviation calculation formula to obtain the time deviation fluctuation.

5. The AI-based fluid valve actuator monitoring and diagnostic system according to claim 1 is characterized in that: The reference data affected by the preset dynamic working condition is set in the following manner: The working parameters, torque time series data set and opening change data set of multiple execution records are retrieved from the historical execution records of the fluid valve actuator, and the torque average value of the torque time series data set and the opening stability value of the opening change data set are respectively subjected to multivariate regression fitting with the medium temperature, pipeline pressure and medium flow rate in the working parameters to obtain the multivariate regression linear equations of working parameter-torque and working parameter-opening; The current dynamic working condition parameters of the fluid valve are substituted into the multivariate regression linear equation, and the reference torque and reference opening of the fluid valve affected by the dynamic working condition are output.

6. The AI-based fluid valve actuator monitoring and diagnostic system according to claim 5 is characterized in that: The fitting process of the multivariate regression linear equation is: The torque average value, opening stability value, medium temperature, pipeline pressure and medium flow rate recorded in multiple executions are normalized, and the normalized torque average value and opening stability value are fitted with the medium temperature, pipeline pressure and medium flow rate respectively by multivariate linear regression equation. If the multivariate linear regression equation fitting is unsuccessful, the medium temperature, pipeline pressure and medium flow rate are correlated and analyzed to generate correlation compensation terms, and the multivariate regression linear equations of operating parameters-torque and operating parameters-opening are obtained after re-fitting.

7. The AI-based fluid valve actuator monitoring and diagnostic system according to claim 5 is characterized in that: The screening method of the abnormal stuck fluid valve is as follows: The maximum torque, the minimum torque and the torque mean are selected from the torque time series data set in the time series response data of the abnormal fluid valve, and the torque fluctuation coefficient is calculated by combining the fusion of the reference torque; Generate an opening deviation coefficient according to the deviation between the opening at the end of the opening change data set and the reference opening; The torque fluctuation coefficient and the opening deviation coefficient are comprehensively counted, and the comprehensive deviation of the abnormal fluid valve is output. The abnormal fluid valves with comprehensive deviation greater than the set deviation threshold are screened and regarded as stuck abnormal fluid valves.

8. The AI-based fluid valve actuator monitoring and diagnostic system according to claim 7 is characterized in that: The fusion calculation method of the torque fluctuation coefficient is: The torque time series data set is divided into windows of fixed length, and the torques corresponding to all windows are extracted. The maximum torque, minimum torque and torque mean are screened out. The difference between the maximum torque and the minimum torque is calculated by ratio with the reference torque to output the instantaneous fluctuation intensity. The absolute difference between the torque mean and the reference torque is calculated by ratio with the reference torque to output the steady-state fluctuation intensity. The torque fluctuation coefficient is obtained by combining the instantaneous fluctuation intensity and the steady-state fluctuation intensity for adjacent feature matching.

9. The AI-based fluid valve actuator monitoring and diagnostic system according to claim 1, characterized in that: Generating the abnormal source diagnosis result includes: The opening change data set and torque time series data set of the stuck abnormal fluid valve are aligned by timestamps to obtain the opening change trend and torque change trend at the same time series. The correlation between the opening and torque is obtained based on the opening change trend and torque change trend of the stuck abnormal fluid valve at all time series. The source tracing analysis is performed in combination with the current dynamic operating parameters of the stuck abnormal fluid valve to obtain the abnormal source diagnosis result.

10. The AI-based fluid valve actuator monitoring and diagnostic system according to claim 9, characterized in that: The specific process of tracing the source of the abnormal stuck fluid valve by combining the current dynamic working condition parameters is as follows: When the correlation between the opening degree and torque of the abnormally stuck fluid valve is a linear relationship, the medium temperature in the current dynamic working condition parameters is extracted, and the medium temperature is compared with the temperature range of the fluid valve lubricant, and it is determined whether the abnormal source of the abnormally stuck fluid valve is the failure of the lubricant according to the comparison result; When the correlation between the opening and torque of the stuck abnormal fluid valve is nonlinear, the medium flow rate is extracted from the current dynamic operating parameters of the stuck abnormal fluid valve, and the deviation degree of the medium flow rate and the fluid medium reference flow rate corresponding to the fluid valve opening at the current timing are analyzed. When the deviation degree is greater than the set deviation degree threshold, the abnormal source of the fluid valve is diagnosed as foreign body obstruction, otherwise, the abnormal source of the fluid valve is diagnosed as mechanical transmission abnormality.

Images