CN113325824A - Regulating valve abnormity identification method and system based on threshold monitoring - Google Patents
Regulating valve abnormity identification method and system based on threshold monitoring Download PDFInfo
- Publication number
- CN113325824A CN113325824A CN202110612633.8A CN202110612633A CN113325824A CN 113325824 A CN113325824 A CN 113325824A CN 202110612633 A CN202110612633 A CN 202110612633A CN 113325824 A CN113325824 A CN 113325824A
- Authority
- CN
- China
- Prior art keywords
- abnormal
- data
- time
- regulating valve
- valve opening
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B23/00—Testing or monitoring of control systems or parts thereof
- G05B23/02—Electric testing or monitoring
- G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
- G05B23/0208—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterized by the configuration of the monitoring system
- G05B23/0213—Modular or universal configuration of the monitoring system, e.g. monitoring system having modules that may be combined to build monitoring program; monitoring system that can be applied to legacy systems; adaptable monitoring system; using different communication protocols
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/20—Pc systems
- G05B2219/24—Pc safety
- G05B2219/24065—Real time diagnostics
Abstract
The invention relates to a regulating valve abnormity identification method and system based on threshold monitoring, belongs to the field of data analysis and pattern identification, and is used for automatic identification of abnormity and early fault finding in the operation process of a regulating valve. The invention comprises the following steps: s1, a data acquisition module acquires actual valve opening data in corresponding duration; s2, analyzing the actual valve opening data by a data analysis module, counting abnormal characteristic values of the regulating valve and forming an abnormal data file; and S3, the abnormal monitoring module analyzes the abnormal data file, displays the analysis result and forms an abnormal parameter report. The invention is convenient for the staff to check, and can find the information that the actual valve opening data is abnormal in the first time period in time, so as to be convenient for the subsequent maintenance.
Description
Technical Field
The invention relates to a regulating valve abnormity identification method and system based on threshold monitoring, belongs to the field of data analysis and pattern identification, and is used for automatic identification of abnormity and early fault finding in the operation process of a regulating valve.
Background
The regulating valve is an important control device in pipeline equipment in the energy and power industry, and the passing and blocking of a flowing medium in a pipeline can be controlled by giving different valve opening instructions to the regulating valve, so that the running conditions of other devices are directly influenced. If the regulating valve fails, unexpected downtime of the whole system can be caused, and serious economic loss is caused. Therefore, the method has higher practical significance for timely finding and then eliminating the fault of the regulating valve. Normally, the operating parameters of the regulating valve are maintained near the standard values to generate small fluctuation. If the operation parameters of the regulating valve deviate from the normal operation threshold range, the regulating valve is predicted to have certain faults, and a field engineer needs to be prompted to perform corresponding treatment according to actual conditions in time.
At present, with the development of intelligent sensing technology, engineers can conveniently obtain a large amount of operating parameter data of the regulating valve, but the following defects exist in the task of abnormal identification of the regulating valve: some early signs of faults of the regulating valve are not obvious, the fault reasons are various, the mechanism is relatively complex, and the problems are difficult to find early through manual monitoring and analysis of engineers; the corresponding automatic identification method is lacked in abnormal operation of the regulating valve, an engineer is required to manually analyze and calculate characteristic data in mass data, the work is complicated, the difficulty is high, and the data utilization rate is low; the threshold value of the normal operation range of the regulating valve is determined by engineers according to own experience, corresponding mathematical basis is lacked, and personnel individual difference is large.
The patent document with publication number CN110687885A discloses a fault diagnosis method and system for a regulating valve of a first-order constant value control system, which comprises the following steps: different types and different strength faults are set on line for the first-order constant value liquid level control system, and fault characteristic values are analyzed according to discrete data points; acquiring sensor detection data and regulating valve opening data of a normal and stable system on line to obtain a fault detection threshold value, and determining a fault detection algorithm; determining a fault estimation algorithm; establishing a fault qualitative model; example validation failure diagnostic methods and systems. The method has the advantages that faults of different types and intensities are judged and analyzed, different fault qualitative equations need to be set for calculation, the requirement for extracting the characteristics of different parameters is high, during data analysis, the faults of different types and different intensities need to be detected to extract fault characteristics, the complexity is high, and once a certain parameter is wrong, time and labor are wasted in the aspect of subsequent maintenance.
Disclosure of Invention
The invention aims to provide a regulating valve abnormity identification method and system based on threshold monitoring, belongs to the field of data analysis and pattern identification, and is used for automatic identification of abnormity and early fault finding in the operating process of a regulating valve.
In order to solve the above technical problem, the present application provides a method for identifying an abnormality of a regulating valve based on threshold monitoring, which is characterized by comprising:
s1, a data acquisition module acquires actual valve opening data in corresponding duration;
s2, analyzing the actual valve opening data by a data analysis module, counting abnormal characteristic values of the regulating valve and forming an abnormal data file;
and S3, the abnormal monitoring module analyzes the abnormal data file, displays the analysis result and forms an abnormal parameter report.
The data analysis module analyzes the actual valve opening data in the first period of time collected by the data collection module, calculates and judges whether the opening data is abnormal, correspondingly counts the abnormal valve opening data, counts related abnormal characteristic values to form an abnormal data file, wherein the abnormal characteristic values are data information of abnormality in the first period of time in the analysis process, and the abnormal characteristic values are formed into an abnormal data file. At the abnormity monitoring module, a worker can check related information, and an abnormal parameter report is formed by analyzing an abnormal data file formed by the data analysis module, so that the worker can check the abnormal information in time, and the abnormal information of the actual valve opening data in the first time period can be found out for subsequent maintenance. The method has simple process and is easy to realize.
Preferably, before step S1, the method further includes:
s0. obtaining historical valve opening data in the second time period from the data analysis module as a method training set, and calculating to obtain an abnormal threshold of the historical valve opening data in the second time period.
Preferably, in step S0, a unique time identifier, i.e. a time stamp, is added to each piece of historical valve opening data.
Preferably, the step S0 includes:
s01, calculating the maximum value and the minimum value of historical valve opening data in the second time period;
s02, setting time windows with certain time width and step length, sliding backwards according to the set time width and step length by the initial end of historical valve opening data, and calculating and recording the maximum value, the minimum value and the fluctuation amplitude of the historical valve opening data in each time window;
s03, counting the probability density of the fluctuation amplitude in each time window, drawing a distribution curve of the probability density of the fluctuation amplitude, and taking the abscissa value at the lowest position between normal fluctuation and abnormal fluctuation in the curve as an initial abnormal fluctuation threshold value of historical valve opening data;
and S04, drawing a fluctuation amplitude distribution box type graph, verifying whether the initial abnormal fluctuation threshold is proper, if so, determining the initial abnormal fluctuation threshold to be an abnormal threshold of historical valve opening data in a second time period, and if not, repeating the step S03.
Preferably, in step S04, if the initial abnormal fluctuation threshold is smaller than the minimum value of the valve fluctuation abnormal value and larger than the maximum value of the normal value of the valve opening, it is determined that the initial adjustment valve abnormal threshold is appropriate.
Preferably, the step S2 includes:
s21, transmitting actual valve opening data, setting a latest time window with a certain time width and step length, and sliding backwards from an initial end of the actual valve opening data according to the set time width and step length to judge whether the regulating valve opening data in the latest time window is abnormal or not;
s22, recording the maximum value, the minimum value, the fluctuation amplitude value, the opening mean value in the latest time window of abnormal opening data of the regulating valve and the starting time and the ending time of the latest time window, and marking the latest time window as a regulating valve operation abnormal window;
s25, counting the number of abnormal operating windows of the regulating valve and abnormal characteristic values including an abnormal maximum value, an abnormal minimum value, an abnormal mean value and an abnormal variance value of actual valve opening data in a first time period, and forming an abnormal data file.
Preferably, in step S21, the maximum value, the minimum value, and the fluctuation amplitude of the actual valve opening data in the latest time window are calculated, and if the fluctuation amplitude is larger than the abnormality threshold, it is determined that the adjustment valve opening data in the latest time window is abnormal.
Preferably, after step S22, the method further includes:
and S23, forming a combined time window by taking the middle time of the last time window as a starting point and taking the middle time of the current last time window as an ending point, calculating the maximum value, the minimum value and the fluctuation amplitude of the actual valve opening data in the combined time window, recording the maximum value, the minimum value, the fluctuation amplitude, the opening mean value of the actual valve opening data in the combined window and the starting time and the ending time of the combined time window if the fluctuation amplitude is greater than an abnormal threshold, and marking the combined window as an adjusting valve operation abnormal window.
Preferably, after step S23, the method further includes:
and S24, analyzing and checking whether all the abnormal operation windows of the regulating valves overlap or not, combining the two abnormal operations into one time if the starting time of the abnormal operation window of the current regulating valve is earlier than or equal to the ending time of the abnormal operation window of the previous regulating valve, modifying the ending time of the abnormal operation window of the previous regulating valve into the ending time of the abnormal operation window of the current regulating valve, and modifying the starting time of the abnormal operation window of the current regulating valve into the starting time of the abnormal operation window of the previous regulating valve.
The application also provides a regulating valve abnormity identification system based on threshold monitoring, and the regulating valve abnormity identification method based on threshold monitoring carries out regulating valve abnormity identification, and comprises the following steps:
the data acquisition module is used for acquiring actual valve opening data;
the data analysis module is connected with the data acquisition module and used for analyzing the actual valve opening data and forming an abnormal data file aiming at abnormal data;
and the abnormity monitoring module is connected with the data analysis module and used for analyzing the abnormal data file to form an abnormal parameter report.
The invention has the following technical effects:
1. and historical valve opening data in the second time period are obtained from the data analysis module, and the abnormal threshold of the historical valve opening data is calculated through analysis of the historical valve opening data and can be used as a basis for judging whether the actual valve opening data is normal or not. The abnormal threshold value is extracted by analyzing historical valve opening data, so that the method is suitable for the service condition of the valve, and the actual applicability is high.
2. And adding a unique time identifier for each historical valve opening data, analyzing according to the time progress, conveniently recording the process of each analysis, and conveniently analyzing and recording.
3. The abnormal threshold value of the historical valve opening data is determined by the fluctuation amplitude through analyzing the fluctuation amplitude of the historical valve opening data, the fluctuation normal frequency of the historical valve opening data is larger than the fluctuation normal frequency during the working period of the general valve, and the corresponding abnormal threshold value can be determined through the characteristic. When the abnormal threshold is calculated, sectional calculation statistics is carried out in a time window mode, data in each time window is independently judged, and finally the data in all the time windows are counted to find the abnormal threshold. The time window can realize that only data in the time window is analyzed, the influence of other data is eliminated, the data analysis is more accurate, the slidability of the time window is realized, the step length of each sliding is consistent with the width of the time window, the continuous analysis can be realized, and the repetition and omission are eliminated.
4. The minimum value of the valve fluctuation abnormal value and the maximum value of the normal value of the valve opening can be visually determined through the box type graph, the initial abnormal fluctuation threshold value is smaller than the minimum value of the valve fluctuation abnormal value and larger than the maximum value of the normal value of the valve opening, and the box type graph can be used as a basis for distinguishing whether the fluctuation amplitude of actual valve opening data is normal or not, and is convenient for determining the abnormal threshold value.
5. The actual valve opening data of the first time period is segmented in a time mode in the form of the latest time window, one time segment is analyzed, and the data of each time segment is analyzed independently, so that the analysis accuracy can be improved. And meanwhile, marking the latest time window with abnormal analysis, and finally counting the abnormal characteristic value of the actual valve opening data in the corresponding first time period and the number of the latest time windows with abnormal analysis, so that the abnormal position of the subsequent actual valve opening data can be checked, and the abnormal problem of the valve opening can be solved conveniently in the subsequent process.
6. The middle time of the last time window is used as a starting point, the middle time of the current last time window is used as an ending point to form a combined time window, and the actual valve opening data in the combined window is analyzed, so that the problem that fluctuation crosses over the two last time windows is avoided, and the problem of omission during analysis is prevented.
7. Whether all the abnormal operation windows of the regulating valves are overlapped or not is checked, the abnormal operation windows of the regulating valves with the overlapping are integrated into one window, repeated analysis and judgment can be prevented, the final statistical result is prevented from being influenced, and the accuracy of the statistical result is improved.
Drawings
Fig. 1 is a flow chart of a method for identifying an abnormality of a regulator valve.
FIG. 2 is a probability density plot of the amplitude of the fluctuations.
FIG. 3 is a boxplot of the amplitude of the undulations.
Fig. 4 is a statistical diagram of anomaly identification.
Detailed Description
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. Unless otherwise defined, all terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. It will be further understood that the conventional terms should be interpreted as having a meaning that is consistent with their meaning in the relevant art and this disclosure. The present disclosure is to be considered as an example of the invention and is not intended to limit the invention to the particular embodiments.
Example one
A regulating valve abnormity identification method based on threshold monitoring is characterized by comprising the following steps:
s1, a data acquisition module acquires actual valve opening data in a first time period;
s2, analyzing actual valve opening data by a data analysis module, counting abnormal characteristic values of the regulating valve and forming an abnormal data file;
and S3, the abnormal monitoring module analyzes the abnormal data file and forms an abnormal parameter report.
The embodiment is carried out based on the opening data of the regulating valve, whether the opening of the regulating valve exceeds the threshold range or not is judged by judging the opening of the regulating valve, if the opening exceeds the threshold range, the regulating valve is judged to be abnormal, if the opening does not exceed the threshold range, the regulating valve is judged to be normal, and then a parameter report checked by a card is formed for abnormal data and corresponding abnormal information, so that a worker can check the abnormal information in time, corresponding adjustment is carried out according to the abnormal information, and the working efficiency is improved. The threshold range refers to an opening interval of the regulating valve between the minimum value and the maximum value of the opening of the regulating valve, and if the opening is too small, the control quality is poor, and even the control is difficult; if the opening degree is too large, the margin is small, and when the load changes, the control cannot be performed, so that the opening degree data exceeding the threshold range and the information thereof are integrated into a parameter report in time by detecting whether the opening degree data of the regulating valve exceeds the threshold range, and the regulating valve is maintained in time subsequently.
Wherein, before step S1, the method further includes:
s0. obtaining historical valve opening data in the second time period from the data analysis module as a method training set, and calculating to obtain an abnormal threshold of the historical valve opening data in the second time period. By comparing the actual valve opening data of the first time period with the abnormal threshold of the second time period, if the corresponding characteristic value (in this embodiment, the corresponding characteristic value is the fluctuation amplitude) of the actual valve opening data of the first time period is greater than the abnormal threshold of the second time period, the actual valve opening data is considered to be abnormal.
When the abnormal threshold value of the second time period is determined, in step S0, a unique time identifier, i.e., a time stamp, is added to each piece of historical valve opening data.
Step S0 includes:
s01, calculating the maximum value and the minimum value of historical valve opening data in a second time period;
s02, setting time windows with certain time width and step length, sliding backwards according to the set time width and step length by the initial end of historical valve opening data, and calculating and recording the maximum value, the minimum value and the fluctuation amplitude of the historical valve opening data in each time window;
s03, counting the probability density of the fluctuation amplitude in each time window, drawing a distribution curve of the probability density of the fluctuation amplitude, and taking the abscissa value at the lowest position between normal fluctuation and abnormal fluctuation in the curve as an initial abnormal fluctuation threshold value of historical valve opening data;
and S04, drawing a fluctuation amplitude distribution box type graph, verifying whether the initial abnormal fluctuation threshold is proper, if so, determining the initial abnormal fluctuation threshold to be an abnormal threshold of historical valve opening data in a second time period, and if not, repeating the step S03.
The fluctuation amplitude value is the difference between the maximum value and the minimum value, the historical valve opening data is analyzed in detail by using a time window (namely a sliding window commonly used in data analysis), only a part of data in the time window is seen at a time, other data can be shielded, and further the data in the time window is analyzed more finely, meanwhile, due to the sliding of the time window, the analysis on the historical valve opening data in the second time period in a section can be realized, omission does not occur, and the accuracy of data analysis is improved. When the time window is set, the width and the step length of the time window are set to be the same, so that each time window moves to be connected with the previous time window, and the analysis result is prevented from being influenced by analyzing or omitting certain historical valve opening data for multiple times. The fluctuation amplitude of historical valve opening data in the time window is analyzed, so that the abnormal threshold value of the regulating valve can be determined conveniently. When the abnormal threshold is determined, the probability density of the fluctuation amplitude in each time window is counted, a probability density distribution curve of the fluctuation amplitude is drawn, as shown in fig. 2, the abscissa is the fluctuation amplitude distribution, the ordinate is the probability density of the amplitude distribution, the probability of the corresponding fluctuation amplitude can be visually checked, according to experience, the higher toggle amplitude probability is determined to be normal fluctuation, and the lower toggle amplitude probability is determined to be abnormal fluctuation, and in fig. 2, according to the conditions of the normal fluctuation and the abnormal fluctuation, the abscissa value 2.3 corresponding to the lowest fluctuation position between the normal fluctuation and the abnormal fluctuation is determined to be an initial abnormal fluctuation threshold of historical valve opening data.
After the initial abnormal fluctuation threshold value is determined, the fluctuation amplitude value distribution box type graph is drawn, the minimum value of the abnormal fluctuation of the valve and the maximum value of the maximum opening degree can be automatically calculated and recorded, as shown in fig. 3, the normal value of the fluctuation of the valve is arranged in the box type graph, the abnormal value of the fluctuation of the valve is arranged beyond the box type graph, the minimum value of the abnormal value of the fluctuation of the valve is arranged at the bottommost part in the box type graph, and the maximum value of the normal value of the opening degree of the valve is arranged at the topmost part in the box type graph. In step S04, if the initial abnormal fluctuation threshold is smaller than the minimum value of the valve fluctuation abnormal value and larger than the maximum value of the normal value of the valve opening, it is determined that the initial adjustment valve abnormal threshold is appropriate. And if the selected initial abnormal fluctuation threshold value is 2.3, is smaller than the minimum value of the valve fluctuation abnormal value and is larger than the maximum value of the normal value of the valve opening, the abnormal threshold value of which the selected 2.3 is historical valve opening data in the second time period is considered to be proper.
After the abnormal threshold value is calculated by analyzing the historical valve opening data in the second time period, judging the actual valve opening data in the first time period:
step S2 includes:
s21, transmitting actual valve opening data, setting a latest time window with a certain time width and step length, and sliding backwards from an initial end of the actual valve opening data according to the set time width and step length to judge whether the regulating valve opening data in the latest time window is abnormal or not;
s22, recording the maximum value, the minimum value, the fluctuation amplitude value, the opening mean value in the latest time window of abnormal opening data of the regulating valve and the starting time and the ending time of the latest time window, and marking the latest time window as a regulating valve operation abnormal window;
s25, counting the number of abnormal operating windows of the regulating valve and abnormal characteristic values including an abnormal maximum value, an abnormal minimum value, an abnormal mean value and an abnormal variance value of actual valve opening data in a first time period, and forming an abnormal data file.
In step S21, the actual valve opening data in the first time period, referred to as a latest time window, is also analyzed in detail by using the sliding window, and in step S21, the maximum value, the minimum value, and the fluctuation amplitude of the actual valve opening data in the latest time window are calculated, and if the fluctuation amplitude is greater than the abnormal threshold, it is determined that the regulating valve opening data in the latest time window is abnormal. After the latest time window is judged to be abnormal and marked as the abnormal operation window of the regulating valve, the method further comprises the following steps after step S22:
and S23, forming a combined time window by taking the middle time of the last time window as a starting point and taking the middle time of the current last time window as an ending point, calculating the maximum value, the minimum value and the fluctuation amplitude of the actual valve opening data in the combined time window, recording the maximum value, the minimum value, the fluctuation amplitude, the opening mean value of the actual valve opening data in the combined window and the starting time and the ending time of the combined time window if the fluctuation amplitude is greater than an abnormal threshold, and marking the combined window as an adjusting valve operation abnormal window. If the fluctuation of the actual valve opening data crosses 2 latest time windows at a time, the fluctuation is possibly ignored, so that a combined time window is formed by taking the middle time of the current latest time window as an end point, and the abnormal judgment is made on the fluctuation amplitude of the actual valve opening data in the combined time window, so that the fluctuation crossing of the actual valve opening data crossing 2 latest time windows is ensured to be identified and calculated.
The step S23 is followed by:
and S24, analyzing and checking whether all the abnormal operation windows of the regulating valves overlap or not, combining the two abnormal operations into one time if the starting time of the abnormal operation window of the current regulating valve is earlier than or equal to the ending time of the abnormal operation window of the previous regulating valve, modifying the ending time of the abnormal operation window of the previous regulating valve into the ending time of the abnormal operation window of the current regulating valve, and modifying the starting time of the abnormal operation window of the current regulating valve into the starting time of the abnormal operation window of the previous regulating valve. The problem that due to the fact that the combined window is calculated in the step S23, the abnormal operation windows of the multiple regulating valves are overlapped is solved, repeated calculation is prevented, and statistics of subsequent abnormal characteristic values is facilitated.
And finally, counting the number of abnormal operating windows of the regulating valve and abnormal characteristic values including an abnormal maximum value, an abnormal minimum value, an abnormal mean value and an abnormal variance value of actual valve opening data in a first time period, wherein the counting result is shown in fig. 4.
In this embodiment, the maximum value, the minimum value, the opening average value, and the like of the actual valve opening data may be used as a basis for abnormality determination, and the corresponding abnormality threshold may be calculated from the historical valve opening data and compared to determine the abnormality.
Example two
The embodiment further provides a regulating valve abnormality recognition system based on threshold monitoring, and the regulating valve abnormality recognition method based on threshold monitoring according to the first embodiment performs regulating valve abnormality recognition, including:
the data acquisition module is used for acquiring actual valve opening data;
the data analysis module is connected with the data acquisition module and used for analyzing actual valve opening data and forming an abnormal data file aiming at abnormal data;
and the abnormality monitoring module is connected with the data analysis module and used for analyzing the abnormal data file to form an abnormal parameter report.
The data acquisition module is responsible for receiving the valve opening instruction and the control valve opening that the host computer sent, gathers and returns the valve actual operating data of governing valve opening, valve inlet pressure, valve outlet flow etc.. In this embodiment, the data analysis module is used for carrying out abnormity judgment on actual valve opening data collected by the data collection module, counting abnormal corresponding data, and further forming an abnormal data file, and the abnormal data analysis file collected by the data analysis module cannot be displayed and checked, so that the abnormal data analysis file is sent to the abnormity monitoring module, the abnormity monitoring module is used for analyzing the abnormal data file, and further forming an abnormal parameter report on abnormal data, so that a worker can check the abnormal data, and the abnormity of the regulating valve can be found in time.
Although embodiments of the present invention have been described, various changes or modifications may be made by one of ordinary skill in the art within the scope of the appended claims.
Claims (10)
1. A regulating valve abnormity identification method based on threshold monitoring is characterized by comprising the following steps:
s1, a data acquisition module acquires actual valve opening data in a first time period;
s2, analyzing the actual valve opening data by a data analysis module, counting abnormal characteristic values of the regulating valve and forming an abnormal data file;
and S3, analyzing the abnormal data file by an abnormal monitoring module and forming an abnormal parameter report.
2. The method for identifying an abnormality of a regulating valve based on threshold monitoring as claimed in claim 1, wherein:
before the step S1, the method further includes:
s0. obtaining historical valve opening data in the second time period from the data analysis module as a method training set, and calculating to obtain an abnormal threshold of the historical valve opening data in the second time period.
3. The method for identifying an abnormality of a regulator valve based on threshold monitoring as set forth in claim 2, wherein:
in step S0, a unique time identifier, i.e., a time stamp, is added to each piece of historical valve opening data.
4. The method for identifying an abnormality of a regulator valve based on threshold monitoring as set forth in claim 2, wherein:
the step S0 includes:
s01, calculating the maximum value and the minimum value of historical valve opening data in the second time period;
s02, setting time windows with certain time width and step length, sliding backwards according to the set time width and step length by the initial end of historical valve opening data, and calculating and recording the maximum value, the minimum value and the fluctuation amplitude of the historical valve opening data in each time window;
s03, counting the probability density of the fluctuation amplitude in each time window, drawing a distribution curve of the probability density of the fluctuation amplitude, and taking the abscissa value at the lowest position between normal fluctuation and abnormal fluctuation in the curve as an initial abnormal fluctuation threshold value of historical valve opening data;
and S04, drawing a fluctuation amplitude distribution box type graph, verifying whether the initial abnormal fluctuation threshold is proper, if so, determining the initial abnormal fluctuation threshold to be an abnormal threshold of historical valve opening data in a second time period, and if not, repeating the step S03.
5. The method for identifying an abnormality of a regulating valve based on threshold monitoring as set forth in claim 4, wherein:
in step S04, if the initial abnormal fluctuation threshold is smaller than the minimum value of the valve fluctuation abnormal value and larger than the maximum value of the normal value of the valve opening, it is determined that the initial regulating valve abnormal threshold is appropriate.
6. The method for identifying an abnormality of a regulating valve based on threshold monitoring as set forth in claim 4, wherein:
the step S2 includes:
s21, transmitting actual valve opening data, setting a latest time window with a certain time width and step length, and sliding backwards from an initial end of the actual valve opening data according to the set time width and step length to judge whether the regulating valve opening data in the latest time window is abnormal or not;
s22, recording the maximum value, the minimum value, the fluctuation amplitude value, the opening mean value in the latest time window of abnormal opening data of the regulating valve and the starting time and the ending time of the latest time window, and marking the combined time window as a regulating valve operation abnormal window;
s25, counting the number of abnormal operating windows of the regulating valve and abnormal characteristic values including an abnormal maximum value, an abnormal minimum value, an abnormal mean value and an abnormal variance value of actual valve opening data in a first time period, and forming an abnormal data file.
7. The method for identifying an abnormality of a regulating valve based on threshold monitoring as claimed in claim 6, wherein:
in step S21, the maximum value, the minimum value, and the fluctuation amplitude of the actual valve opening data in the latest time window are calculated, and if the fluctuation amplitude is greater than the abnormal threshold, it is determined that the regulating valve opening data in the combined time window is abnormal.
8. The method for identifying an abnormality of a regulating valve based on threshold monitoring as claimed in claim 6, wherein:
the step S22 is followed by:
and S23, forming a combined time window by taking the middle time of the last time window as a starting point and taking the middle time of the current last time window as an ending point, calculating the maximum value, the minimum value and the fluctuation amplitude of the actual valve opening data in the combined time window, recording the maximum value, the minimum value, the fluctuation amplitude, the opening mean value of the actual valve opening data in the combined window and the starting time and the ending time of the combined time window if the fluctuation amplitude is greater than an abnormal threshold, and marking the combined window as an adjusting valve operation abnormal window.
9. The method for identifying an abnormality of a regulator valve based on threshold monitoring as set forth in claim 8, wherein:
the step S23 is followed by:
and S24, analyzing and checking whether all the abnormal operation windows of the regulating valves overlap or not, combining the two abnormal operations into one time if the starting time of the abnormal operation window of the current regulating valve is earlier than or equal to the ending time of the abnormal operation window of the previous regulating valve, modifying the ending time of the abnormal operation window of the previous regulating valve into the ending time of the abnormal operation window of the current regulating valve, and modifying the starting time of the abnormal operation window of the current regulating valve into the starting time of the abnormal operation window of the previous regulating valve.
10. A regulating valve abnormality identification system based on threshold monitoring, characterized in that regulating valve abnormality identification is performed based on the regulating valve abnormality identification method based on threshold monitoring of any one of claims 1 to 9, and includes:
the data acquisition module is used for acquiring actual valve opening data;
the data analysis module is connected with the data acquisition module and used for analyzing the actual valve opening data and forming an abnormal data file aiming at abnormal data;
and the abnormity monitoring module is connected with the data analysis module and used for analyzing the abnormal data file to form an abnormal parameter report.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110612633.8A CN113325824B (en) | 2021-06-02 | 2021-06-02 | Regulating valve abnormity identification method and system based on threshold monitoring |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110612633.8A CN113325824B (en) | 2021-06-02 | 2021-06-02 | Regulating valve abnormity identification method and system based on threshold monitoring |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113325824A true CN113325824A (en) | 2021-08-31 |
| CN113325824B CN113325824B (en) | 2022-10-25 |
Family
ID=77423219
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110612633.8A Active CN113325824B (en) | 2021-06-02 | 2021-06-02 | Regulating valve abnormity identification method and system based on threshold monitoring |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113325824B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116886453A (en) * | 2023-09-08 | 2023-10-13 | 湖北华中电力科技开发有限责任公司 | Network flow big data analysis method |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108138660A (en) * | 2015-09-25 | 2018-06-08 | 日产自动车株式会社 | Control valve device |
| JP2019003260A (en) * | 2017-06-12 | 2019-01-10 | 住友金属鉱山株式会社 | Opening abnormality detection device and opening abnormality detection method of control valve |
| CN109752178A (en) * | 2017-11-07 | 2019-05-14 | 阿自倍尔株式会社 | Valve maintenance assisting system and method |
| CN110347116A (en) * | 2019-07-17 | 2019-10-18 | 重庆大学 | A kind of conditions of machine tool monitoring system and monitoring method based on operation data stream |
| CN110414155A (en) * | 2019-07-31 | 2019-11-05 | 北京天泽智云科技有限公司 | A kind of detection of fan part temperature anomaly and alarm method with single measuring point |
| CN111143438A (en) * | 2019-12-30 | 2020-05-12 | 江苏安控鼎睿智能科技有限公司 | Workshop field data real-time monitoring and anomaly detection method based on stream processing |
| CN112162878A (en) * | 2020-09-30 | 2021-01-01 | 深圳前海微众银行股份有限公司 | Database fault discovery method and device, electronic equipment and storage medium |
| CN112215307A (en) * | 2020-11-19 | 2021-01-12 | 薛蕾 | Method for automatically detecting signal abnormality of seismic instrument by applying machine learning |
| CN112581719A (en) * | 2020-11-05 | 2021-03-30 | 清华大学 | Semiconductor packaging process early warning method and device based on time sequence generation countermeasure network |
-
2021
- 2021-06-02 CN CN202110612633.8A patent/CN113325824B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108138660A (en) * | 2015-09-25 | 2018-06-08 | 日产自动车株式会社 | Control valve device |
| JP2019003260A (en) * | 2017-06-12 | 2019-01-10 | 住友金属鉱山株式会社 | Opening abnormality detection device and opening abnormality detection method of control valve |
| CN109752178A (en) * | 2017-11-07 | 2019-05-14 | 阿自倍尔株式会社 | Valve maintenance assisting system and method |
| CN110347116A (en) * | 2019-07-17 | 2019-10-18 | 重庆大学 | A kind of conditions of machine tool monitoring system and monitoring method based on operation data stream |
| CN110414155A (en) * | 2019-07-31 | 2019-11-05 | 北京天泽智云科技有限公司 | A kind of detection of fan part temperature anomaly and alarm method with single measuring point |
| CN111143438A (en) * | 2019-12-30 | 2020-05-12 | 江苏安控鼎睿智能科技有限公司 | Workshop field data real-time monitoring and anomaly detection method based on stream processing |
| CN112162878A (en) * | 2020-09-30 | 2021-01-01 | 深圳前海微众银行股份有限公司 | Database fault discovery method and device, electronic equipment and storage medium |
| CN112581719A (en) * | 2020-11-05 | 2021-03-30 | 清华大学 | Semiconductor packaging process early warning method and device based on time sequence generation countermeasure network |
| CN112215307A (en) * | 2020-11-19 | 2021-01-12 | 薛蕾 | Method for automatically detecting signal abnormality of seismic instrument by applying machine learning |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116886453A (en) * | 2023-09-08 | 2023-10-13 | 湖北华中电力科技开发有限责任公司 | Network flow big data analysis method |
| CN116886453B (en) * | 2023-09-08 | 2023-11-24 | 湖北华中电力科技开发有限责任公司 | Network flow big data analysis method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113325824B (en) | 2022-10-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP1763754B1 (en) | Sensor fault diagnostics and prognostics using component model and time scale orthogonal expansions | |
| CN109186813A (en) | A kind of temperature sensor self-checking unit and method | |
| US10152879B2 (en) | Method, apparatus, and system for monitoring manufacturing equipment | |
| CN110008565A (en) | A kind of industrial process unusual service condition prediction technique based on operating parameter association analysis | |
| CN105116873B (en) | A kind of more automatic adjustment circuit evaluation diagnostic methods of thermal power plant | |
| Zhu et al. | Two-dimensional contribution map for fault identification [focus on education] | |
| CN113325824B (en) | Regulating valve abnormity identification method and system based on threshold monitoring | |
| CN115277464A (en) | Cloud network change flow anomaly detection method based on multi-dimensional time series analysis | |
| CN105676807A (en) | Optimization system and optimization method for refining device equipment integrity operation window | |
| CN112598144A (en) | CNN-LSTM burst fault early warning method based on correlation analysis | |
| CN117406026A (en) | Power distribution network fault detection method suitable for distributed power supply | |
| CN117060409A (en) | Automatic detection and analysis method and system for power line running state | |
| EP0907913B1 (en) | Automatic control loop monitoring and diagnostics | |
| CN115657631A (en) | Intelligent monitoring system for industrial control equipment operation field environment | |
| CN112380206B (en) | Diagnosis and repair method of traffic time sequence data | |
| CN107908156A (en) | Equipment point-detecting method | |
| CN114924543A (en) | Fault diagnosis and prediction method and device for regulating valve | |
| CN114021602A (en) | Method and system for processing data in point switch fault diagnosis model | |
| CN111367255A (en) | Performance evaluation test system and method for multi-variable control system | |
| CN115951619B (en) | Development machine remote intelligent control system based on artificial intelligence | |
| CN117150274B (en) | Quality detection method for press fitting of plug | |
| CN117196590B (en) | Intelligent maintenance efficiency evaluation system for operation and maintenance of communication equipment | |
| CN116757535B (en) | Intelligent management method and system for industrial application platform | |
| CN116838947B (en) | Fault diagnosis method for oxygen supply and saving system and oxygen supply and saving system | |
| CN117560300B (en) | Intelligent internet of things flow prediction and optimization system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |