CN117470529A - Static friction fault detection method and system for valve of process control system - Google Patents
Static friction fault detection method and system for valve of process control system Download PDFInfo
- Publication number
- CN117470529A CN117470529A CN202310646547.8A CN202310646547A CN117470529A CN 117470529 A CN117470529 A CN 117470529A CN 202310646547 A CN202310646547 A CN 202310646547A CN 117470529 A CN117470529 A CN 117470529A
- Authority
- CN
- China
- Prior art keywords
- valve
- static friction
- index
- data
- control system
- 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.)
- Pending
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 70
- 230000003068 static effect Effects 0.000 title claims abstract description 64
- 238000004886 process control Methods 0.000 title claims abstract description 26
- 238000000034 method Methods 0.000 claims abstract description 52
- 238000004364 calculation method Methods 0.000 claims description 8
- 238000004458 analytical method Methods 0.000 claims description 5
- 238000000605 extraction Methods 0.000 claims description 5
- 238000007781 pre-processing Methods 0.000 claims description 4
- 238000010606 normalization Methods 0.000 claims description 2
- 230000010355 oscillation Effects 0.000 abstract description 8
- 239000011159 matrix material Substances 0.000 description 14
- 230000007774 longterm Effects 0.000 description 11
- 239000000284 extract Substances 0.000 description 5
- 230000001186 cumulative effect Effects 0.000 description 3
- 238000000354 decomposition reaction Methods 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000010361 irregular oscillation Effects 0.000 description 2
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical compound C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 description 2
- 238000012369 In process control Methods 0.000 description 1
- 238000005299 abrasion Methods 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- -1 construction Substances 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 239000012530 fluid Substances 0.000 description 1
- 238000010965 in-process control Methods 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000003345 natural gas Substances 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 239000003209 petroleum derivative Substances 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M13/00—Testing of machine parts
- G01M13/003—Machine valves
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention discloses a method and a system for detecting static friction faults of a valve of a process control system, comprising the following steps: acquiring controller output data and controlled process variable data of a valve; extracting slow features from the controller output data and the controlled process variable data; calculating the Hurst index of the slowest slow features in the slow features; determining a valve static friction detection index according to the Hurst index; judging whether the valve has static friction faults according to the static friction detection index of the valve, and obtaining a fault detection result. The noise robustness can be effectively enhanced, and meanwhile, the detection performance is improved, and particularly, the valve static friction-caused aperiodic random oscillation has good detection performance.
Description
Technical Field
The invention relates to the technical field of valve static friction fault detection, in particular to a method and a system for detecting valve static friction faults of a process control system.
Background
The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art.
Control valves are widely used in process control systems to regulate fluid flow, pressure, temperature, etc. in various industrial processes, such as petroleum and natural gas, construction, chemical, petrochemical, electrical, and water treatment processes. They are critical implementations of the production process to achieve precise control and to maintain product quality. However, one of the challenges in controlling the proper operation of a valve is the occurrence of static friction of the valve, which can lead to oscillations of the control loop, thereby reducing its control performance and product quality, and at the same time accelerating wear and aging of the valve and related equipment, causing system failures and even production safety accidents. According to investigation, 20% -30% of the control loop may oscillate due to valve stiction. Therefore, research on the valve static friction fault detection method has very important significance in improving the reliability, control performance and product quality of a process control system.
The inventor finds that the valve oscillation causes the process data to show oscillation, has obvious time sequence dynamic characteristics and nonlinear characteristics, so that long-term correlation information in the process data is obviously changed, the time sequence dynamic information and the long-term correlation information of the existing valve static friction detection technology are not fully utilized, and meanwhile, the existing technology has the defect of poor robustness to random noise in the data, so that the detection and identification accuracy rate of the valve static friction fault is low.
Disclosure of Invention
In order to solve the problems, the invention provides a method and a system for detecting the static friction fault of a valve of a process control system, and the detection precision of the static friction fault of the valve is improved.
In order to achieve the above purpose, the invention adopts the following technical scheme:
in a first aspect, a method for detecting a static friction failure of a valve of a process control system is provided, including:
acquiring controller output data and controlled process variable data of a valve;
extracting slow features from the controller output data and the controlled process variable data;
calculating the Hurst index of the slowest slow features in the slow features;
determining a valve static friction detection index according to the Hurst index;
judging whether the valve has static friction faults according to the static friction detection index of the valve, and obtaining a fault detection result.
In a second aspect, a process control system valve stiction fault detection system is provided, comprising:
the data acquisition module is used for acquiring the controller output data of the valve and the controlled process variable data;
the slow feature extraction module is used for extracting slow features from the output data of the controller and the controlled process variable data;
the Hurst index calculation module is used for calculating the Hurst index of the slowest characteristic in the slow characteristics;
the valve static friction detection index acquisition module is used for determining a valve static friction detection index according to the Hurst index;
the fault detection result acquisition module is used for judging whether the valve has static friction faults according to the static friction detection index of the valve to obtain a fault detection result.
In a third aspect, an electronic device is provided that includes a memory and a processor and computer instructions stored on the memory and running on the processor that, when executed by the processor, perform the steps described for a process control system valve stiction fault detection method.
In a fourth aspect, a computer readable storage medium is provided for storing computer instructions that, when executed by a processor, perform the steps of a method for detecting a valve stiction failure of a process control system.
Compared with the prior art, the invention has the beneficial effects that:
1. according to the invention, the slow characteristic of the acquired data is extracted, the time sequence dynamic characteristic of the acquired data is obtained, the long-term correlation information of the data can be acquired by calculating the Hurst index of the slowest characteristic, the valve static friction detection index is determined by using the Hurst index, and whether the valve has static friction fault or not is judged by using the valve static friction detection index, so that the detection precision of the valve static friction fault is improved, and particularly the detection performance of the valve static friction fault in the process of irregular oscillation of a control loop caused by static friction is improved.
2. When the slow features are extracted, the invention simultaneously eliminates the noise signals, and improves the robustness of the detection method to the noise signals.
Additional aspects of the invention will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the invention.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiments of the application and together with the description serve to explain the application and do not constitute an undue limitation to the application.
FIG. 1 is a flow chart of the method disclosed in example 1;
FIG. 2 is a schematic diagram of a typical control loop of a valve;
FIG. 3 is a flow chart of data acquisition and preprocessing disclosed in example 1;
FIG. 4 is a flow chart of SFA-based slow feature extraction and denoising disclosed in example 1;
Detailed Description
The invention will be further described with reference to the drawings and examples.
It should be noted that the following detailed description is illustrative and is intended to provide further explanation of the present application. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.
Example 1
Typical valve control loop configurations are shown in fig. 2, where the valve is controlled based on set point SP controller output (Controller Output, OP) data, and the sensor is used to obtain controlled process variable (Controlled Process Variable, PV) data after the valve is controlled.
When the valve has static friction fault, the OP data and the PV data in the loop are often caused to oscillate, so that the stability and the safety of a control system are affected, and the quality of products is reduced, the energy consumption and the equipment abrasion are increased. The static friction of the valve causes obvious dynamic change characteristics and nonlinear characteristics of data in a process loop, and the SFA method has dynamic characteristic extraction capability and denoising capability for time series data, and the Hurst index can calculate the long-term relativity of the time series data and is often used for nonlinear characteristic detection. Therefore, the embodiment provides a static friction fault detection method for a valve of a process control system, which is based on a double-layer ML method, and extracts dynamic characteristics and long-term correlation information in reconstructed spread data matrix data by combining an SFA and a Hurst index method. Wherein, the reconstruction and the dimension expansion based on the data are helpful to fully utilize the phase difference information and the oscillation information in the OP and the PV data; the SFA-based method can extract time sequence dynamic characteristic information with slow change in the reconstructed dimension expansion data; the long-term correlation information in the time sequence data can be calculated based on the Hurst index method so as to quantify the nonlinear characteristic of the data, thereby improving the accuracy and the sensitivity of the static friction fault detection of the valve.
As shown in fig. 1, the method for detecting static friction failure of a valve of a process control system disclosed in this embodiment includes:
s1: controller output data and controlled process variable data for the valve are obtained.
In a process control system, controller output data (OP data) and controlled process variable data (PV data) of a valve are obtained.
S2: slow features are extracted from the controller output data and the controlled process variable data.
The embodiment preprocesses the output data of the controller and the controlled process variable data to obtain preprocessed data; slow features are extracted from the preprocessed data.
As shown in fig. 3, the preprocessing includes normalization, data reconstruction, and dimension expansion.
And (3) performing standardization processing on the acquired OP data and PV data by adopting the formula (1).
Wherein x (k) is OP data and PV data acquired at time k,and σ are the mean and variance of data x (k), (k=1, …, N), respectively.
And carrying out data reconstruction on the normalized data by adopting a mode of carrying out difference on the normalized OP data and the PV data, and obtaining reconstructed data d (k).
d(k)＝v PV (k)-v OP (k)(2)
Wherein v is PV (k) And v OP (k) Respectively is standardizedProcessed PV data and OP data.
The reconstructed data D (k) is one-dimensional data, and the data expansion is carried out on the reconstructed data D (k) by using l hysteresis samples to obtain a data matrix D d (k) Is the data after pretreatment.
Where l is the number of hysteresis samples.
The slow feature analysis algorithm (SFA method) is adopted to extract slow features from the preprocessed data, as shown in fig. 4, and the specific process is as follows:
s21: for the preprocessed data D d (k) And (5) carrying out standardization processing to obtain a standardized matrix.
By using the formula (1) to the D d (k) Performing standardization processing to obtain a standardized matrix
S22: singular value decomposition (SingularValue Decomposition, SVD) is performed on the covariance matrix of the normalized matrix, and a spheroidization matrix Z is calculated.
S23: differential matrix to spheroidization matrixSingular value decomposition is performed, and an SFA conversion matrix W is obtained through calculation.
W＝PA -1/2 U T (7)
Wherein,z (k) and Z (k-1) are respectively a spheroidization matrix obtained by data calculation according to the k moment and a spheroidization matrix obtained by data calculation according to the k-1 moment.
S24: the SFA conversion matrix W and the normalized matrixMultiplication results in a slow feature s.
The oscillation signal caused by the valve stiction has a large autocorrelation, so that possible oscillations can be extracted in the form of slow characteristic information. In addition, some of the noise has zero lag autocorrelation, so that a large degree of noise removal can be achieved in this process.
S3: the Hurst index of the slowest of the slow features is calculated.
The SFA method only extracts single-lag time sequence dynamic characteristic information, and in order to further extract long-term correlation information, the slowest characteristic s extracted by Hurst index analysis is adopted 1 A long-term correlation of the slowest features is obtained to detect and analyze non-linear characteristics in the system.
The slow features extracted in the step S3 are arranged in sequence from slow to fast, wherein the slow features S with the slowest change 1 Is the slowest feature.
The Hurst index of the slowest characteristic in the slow characteristics is calculated by adopting a detrend fluctuation analysis (Detrended Fluctuation Analysis, DFA) method, the long-term correlation of the slowest characteristic is obtained, the long-term correlation is used for quantifying nonlinear characteristics, and the Hurst index calculating process comprises the following steps:
calculating the accumulated difference of the slowest characteristic to obtain an accumulated difference sequence;
performing window division on the accumulated difference sequence for a plurality of times, and for each division, calculating the root mean square value of the sequence under different windows, and calculating the logarithmic value of the window length and the logarithmic value of the root mean square value of the sequence under different windows;
and (3) performing linear fitting on the two values to obtain a slope of the linear fitting, namely a Hurst index.
Calculating the slowest feature s using (9) 1 The cumulative difference of (2) to obtain a cumulative difference sequence S (i).
For each division, the cumulative difference sequence is split into q non-overlapping windows of length n, and then a first order least squares line is fitted for each windowAnd calculates the variance +/under each window>
The root mean square value F (n) of the sequence under the different windows is calculated:
after that, log [ F (n) ] and log (n) are calculated.
The value of the window length n differs for each division.
And (3) performing linear fitting on the log [ F (n) ] and the log (n) obtained by calculation to obtain a slope of the linear fitting, namely the Hurst index He.
S4: and determining a valve static friction detection index according to the Hurst index.
Determining a valve static friction detection index according to the Hurst index and a static friction detection index model, wherein the static friction detection index model is as follows:
wherein, he is Hurst index; hs is the valve static friction detection index.
The Hs values range from 0 to 1, with values closer to 0 indicating higher long-term correlation in the time series, and strong non-linear characteristics in the time series data, which are indicative of valve stiction.
S5: judging whether the valve has static friction faults according to the static friction detection index of the valve, and obtaining a fault detection result.
And when the valve static friction detection index is smaller than the set threshold value, judging that the valve has static friction faults.
Preferably, the threshold is set to 0.5.
If Hs is less than 0.5, a valve sticking failure is indicated.
The method disclosed in the embodiment collects OP and PV data under the static friction fault of the valve and performs data preprocessing, uses SFA as a first layer machine learning to extract slowly-changing time sequence dynamic characteristics in the data, and performs Hurst index calculation s of a second layer on the slowest extracted characteristics 1 Finally, the valve static friction is detected, the anti-interference capability to noise is improved, the time sequence dynamic characteristics and the long-time correlation information of the whole time sequence data process are extracted, the valve static friction detection performance is improved, and especially the non-periodic random oscillation caused by the valve static friction can be accurately detected.
The embodiment discloses a method, which extracts time sequence dynamic characteristic information in OP-PV reconstruction data, eliminates noise signals, and improves the robustness of the detection method to the noise signals; according to the nonlinear characteristics of the valve during static friction, the correlation of the process data is obviously increased, the correlation of the process data is fully considered, the static friction detection precision of the valve is improved, and particularly the detection performance of the valve during irregular oscillation of a control loop caused by static friction is improved.
Example 2
In this embodiment, a process control system valve stiction fault detection system is disclosed comprising:
the data acquisition module is used for acquiring the controller output data of the valve and the controlled process variable data;
the slow feature extraction module is used for extracting slow features from the output data of the controller and the controlled process variable data;
the Hurst index calculation module is used for calculating the Hurst index of the slowest characteristic in the slow characteristics;
the valve static friction detection index acquisition module is used for determining a valve static friction detection index according to the Hurst index;
the fault detection result acquisition module is used for judging whether the valve has static friction faults according to the static friction detection index of the valve to obtain a fault detection result.
Example 3
In this embodiment, an electronic device is disclosed that includes a memory and a processor and computer instructions stored on the memory and running on the processor that, when executed by the processor, perform the steps of a method for detecting a valve stiction failure of a process control system disclosed in embodiment 1.
Example 4
In this embodiment, a computer readable storage medium is disclosed for storing computer instructions that, when executed by a processor, perform the steps of a method for detecting a valve stiction failure of a process control system disclosed in embodiment 1.
Finally, it should be noted that: the above embodiments are only for illustrating the technical aspects of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the above embodiments, it should be understood by those of ordinary skill in the art that: modifications and equivalents may be made to the specific embodiments of the invention without departing from the spirit and scope of the invention, which is intended to be covered by the claims.
Claims (10)
1. A method for detecting a static friction failure of a valve of a process control system, comprising:
acquiring controller output data and controlled process variable data of a valve;
extracting slow features from the controller output data and the controlled process variable data;
calculating the Hurst index of the slowest slow features in the slow features;
determining a valve static friction detection index according to the Hurst index;
judging whether the valve has static friction faults according to the static friction detection index of the valve, and obtaining a fault detection result.
2. The process control system valve stiction fault detection method according to claim 1, wherein the controller output data and the controlled process variable data are preprocessed to obtain preprocessed data;
slow features are extracted from the preprocessed data.
3. A process control system valve stiction fault detection method according to claim 2 wherein the pre-processing process comprises normalization, data reconstruction and dimension expansion.
4. A process control system valve stiction fault detection method according to claim 2 wherein slow features are extracted from the preprocessed data using a slow feature analysis algorithm.
5. A process control system valve stiction fault detection method according to claim 1 wherein the Hurst index of the slowest of the slow features is calculated using the DFA method.
6. The process control system valve stiction fault detection method according to claim 1, wherein the valve stiction detection index is determined according to a Hurst index and a stiction detection index model; wherein, the static friction detection index model is:
wherein, he is Hurst index; hs is the valve static friction detection index.
7. The process control system valve stiction fault detection method according to claim 1, wherein the valve is determined to have a stiction fault when the valve stiction detection index is less than a set threshold.
8. A process control system valve stiction fault detection system, comprising:
the data acquisition module is used for acquiring the controller output data of the valve and the controlled process variable data;
the slow feature extraction module is used for extracting slow features from the output data of the controller and the controlled process variable data;
the Hurst index calculation module is used for calculating the Hurst index of the slowest characteristic in the slow characteristics;
the valve static friction detection index acquisition module is used for determining a valve static friction detection index according to the Hurst index;
the fault detection result acquisition module is used for judging whether the valve has static friction faults according to the static friction detection index of the valve to obtain a fault detection result.
9. An electronic device comprising a memory and a processor and computer instructions stored on the memory and running on the processor, which when executed by the processor, perform the steps of a process control system valve stiction fault detection method according to any one of claims 1-7.
10. A computer readable storage medium storing computer instructions which, when executed by a processor, perform the steps of a process control system valve stiction fault detection method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310646547.8A CN117470529A (en) | 2023-05-31 | 2023-05-31 | Static friction fault detection method and system for valve of process control system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310646547.8A CN117470529A (en) | 2023-05-31 | 2023-05-31 | Static friction fault detection method and system for valve of process control system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117470529A true CN117470529A (en) | 2024-01-30 |
Family
ID=89622705
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310646547.8A Pending CN117470529A (en) | 2023-05-31 | 2023-05-31 | Static friction fault detection method and system for valve of process control system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117470529A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117519067A (en) * | 2023-10-20 | 2024-02-06 | 东北大学 | Multi-frame control performance evaluation method in continuous rolling process |
-
2023
- 2023-05-31 CN CN202310646547.8A patent/CN117470529A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117519067A (en) * | 2023-10-20 | 2024-02-06 | 东北大学 | Multi-frame control performance evaluation method in continuous rolling process |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Lindemann et al. | Anomaly detection in discrete manufacturing using self-learning approaches | |
| CN108052770B (en) | Long-span bridge girder performance early warning method considering time-varying effect | |
| CN111562108A (en) | Rolling bearing intelligent fault diagnosis method based on CNN and FCMC | |
| CN105259895A (en) | Method and monitoring system for detecting and separating micro fault in industrial process | |
| CN103103570B (en) | Based on the aluminium cell condition diagnostic method of pivot similarity measure | |
| CN117470529A (en) | Static friction fault detection method and system for valve of process control system | |
| CN114091525A (en) | Rolling bearing degradation trend prediction method | |
| CN111368428A (en) | Sensor precision reduction fault detection method based on monitoring second-order statistics | |
| CN109298633A (en) | Chemical production process fault monitoring method based on adaptive piecemeal Non-negative Matrix Factorization | |
| CN112395382A (en) | Ship abnormal track data detection method and device based on variational self-encoder | |
| CN112559598A (en) | Telemetry time series data abnormity detection method and system based on graph neural network | |
| CN116861313B (en) | Kalman filtering working condition identification method and system based on vibration energy trend | |
| CN115839763A (en) | Transformer vibration noise monitoring system | |
| CN118100446A (en) | Intelligent detection method for node running state of power system | |
| CN115030903A (en) | On-line diagnosis method for early fault of rolling bearing in centrifugal pump | |
| CN117807538A (en) | Fault detection method based on dynamic threshold and trend prediction | |
| CN111913463B (en) | State monitoring method for chemical volume control system of nuclear power plant | |
| Zhuang et al. | An autoregressive model-based degradation trend prognosis considering health indicators with multiscale attention information | |
| CN109840386B (en) | Damage identification method based on factor analysis | |
| CN116641941A (en) | Hydraulic system early fault dynamic detection method based on typical variable analysis | |
| CN115167364A (en) | Early fault detection method based on probability transformation and statistical characteristic analysis | |
| Lu et al. | Performance assessment of hydraulic servo system based on bi-step neural network and autoregressive model | |
| CN114200914A (en) | MW-OCCA-based quality-related early fault detection method | |
| Qu et al. | Incipient fault detection of chiller based on improved CVA | |
| CN114112390B (en) | Nonlinear complex system early fault diagnosis method |
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 |