CN111443602A - Hidden Markov-based valve health degree estimation and life prediction method - Google Patents
Hidden Markov-based valve health degree estimation and life prediction method Download PDFInfo
- Publication number
- CN111443602A CN111443602A CN201910041532.2A CN201910041532A CN111443602A CN 111443602 A CN111443602 A CN 111443602A CN 201910041532 A CN201910041532 A CN 201910041532A CN 111443602 A CN111443602 A CN 111443602A
- Authority
- CN
- China
- Prior art keywords
- valve
- data
- health degree
- life prediction
- hidden markov
- 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
- G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
- G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
- G05B13/04—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators
- G05B13/042—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators in which a parameter or coefficient is automatically adjusted to optimise the performance
Abstract
The invention provides a hidden Markov-based valve health degree estimation and life prediction method, which relates to the field of electric power and comprises the following steps of 1: deploying a Probe Probe program on a data host of a control valve, and acquiring valve control instructions and relevant index data of valve feedback data; step 2: performing dimensionality reduction analysis on the multi-dimensional index data to determine a core index variable; and step 3: and constructing a valve health degree estimation and life prediction model by using a hidden Markov HMM transfer model, outputting valve health degree evaluation information, and predicting the residual life of the valve. The intelligent operation and maintenance capacity of the valve is improved, the accurate valve health degree evaluation and valve service life prediction results can provide important support data for making valve maintenance decisions, and faults can be effectively avoided by finding potential threats in time and taking appropriate maintenance measures, so that the safety, reliability and usability of the valve are improved.
Description
Technical Field
The invention relates to the field of electric power, in particular to a hidden Markov-based valve health degree estimation and life prediction method.
Background
The traditional valve operation and maintenance mode is that after a valve control system breaks down, maintenance personnel are informed to maintain, the valve operation and maintenance mode belongs to post maintenance, the valve health degree estimation function and the valve service life prediction function are not provided, after the valve control system breaks down, the system maintenance personnel spend a large amount of energy and time to inquire the reason of the failure, the physical labor is large, the normal operation of the system can be influenced, and the equipment maintenance is passive.
Disclosure of Invention
In view of the above drawbacks of the prior art, an object of the present invention is to provide a hidden markov-based method for estimating health degree of a valve and predicting life of the valve, which can improve intelligent operation and maintenance capability of the valve, provide important support data for making a maintenance decision of the valve by accurate estimation of the health degree of the valve and prediction of the life of the valve, and effectively avoid faults by timely discovering potential threats and taking appropriate maintenance measures, thereby improving safety, reliability and usability of the valve.
The invention provides a hidden Markov-based valve health degree estimation and life prediction method, which comprises the following steps:
step 1: deploying a Probe Probe program on a data host of a control valve, and acquiring related index data such as a valve control instruction, valve feedback data and the like;
step 2: performing dimensionality reduction analysis on the multi-dimensional index data to determine a core index variable;
and step 3: and constructing a valve health degree estimation and life prediction model by using a hidden Markov HMM transfer model, outputting valve health degree evaluation information, and predicting the residual life of the valve.
Further, the step 3 comprises the following specific steps:
step 3.1: data host timing acquisition data for nth second control valve
1 hour as one sub-time T, for HnThe division is carried out, and the division is carried out,
wherein x ismRepresenting the value of each feature dimension at time t, M represents the feature dimension,
step 3.2: calculating the mean value of each sub-time
Variance Stdm＝||{xm，t}-Avgm||2；
Step 3.3: counting the average value Avg in one daymVariance and variance Std ofmThe average value of (1) is used for measuring the stable state and the pressure condition of a data host for controlling the valve in one day;
step 3.4: average value Avg in one daymVariance and variance Std ofmForm an observation variable data set Et；
Step 3.5: configuration T ═ P (S)t|St-1) Will observe the variable data set EtInputting into a hidden Markov HMM transition model, calculating Ot+1Outputting the probability T ═ P (S) of the fault of the next dayt|St-1＝αOt+1TTf1:t)；
Step 3.6: evaluating the health degree of the valve according to the 7-day valve failure prediction probability valuet+1＝H(ft-6:t) And outputs L a life prediction based on the health assessmentt+1＝L(ht+1)。
Further, the characteristic dimension M is 8.
As described above, the hidden markov-based valve health estimation and life prediction method according to the present invention has the following advantages:
1. the method utilizes a hidden Markov HMM transfer model to construct a valve health degree estimation and life prediction model, and intelligently evaluates the valve health degree according to relevant index data such as valve control instructions, feedback data and the like.
2. The invention intelligently estimates the health degree of the valve according to the intelligent evaluation and intelligently predicts the service life of the valve by combining the historical observation data and the operation and maintenance record data of the long-term operation of the valve.
3. The invention meets the maintenance requirements of maintenance personnel on valve health assessment and valve service life prediction through GE Xinhua power station verification, and can be used for supporting intelligent operation and maintenance work of the valve.
Drawings
Fig. 1 is a flow chart illustrating a method for estimating the health of a valve and predicting the life of the valve according to an embodiment of the present invention.
Detailed Description
The embodiments of the present invention are described below with reference to specific embodiments, and other advantages and effects of the present invention will be easily understood by those skilled in the art from the disclosure of the present specification. The invention is capable of other and different embodiments and of being practiced or of being carried out in various ways, and its several details are capable of modification in various respects, all without departing from the spirit and scope of the present invention. It is to be noted that the features in the following embodiments and examples may be combined with each other without conflict.
It should be noted that the drawings provided in the following embodiments are only for illustrating the basic idea of the present invention, and the components related to the present invention are only shown in the drawings rather than drawn according to the number, shape and size of the components in actual implementation, and the type, quantity and proportion of the components in actual implementation may be changed freely, and the layout of the components may be more complicated.
As shown in fig. 1, the present invention provides a hidden markov-based valve health estimation and life prediction method, comprising the steps of:
step 1: deploying a Probe Probe program on a data host of a control valve, and acquiring related index data such as a valve control instruction, valve feedback data and the like;
wherein, the acquisition cycle of relevant indexes such as valve control instructions, valve feedback data and the like is 1 second;
step 2: performing dimensionality reduction analysis on the multi-dimensional index data to determine a core index variable;
wherein the index data includes:
date: a date;
time: time;
set: setting first-stage temperature reduction water on the B side of the superheater;
control: a control instruction of a first-stage desuperheating water regulating valve on the B side of the superheater;
location: the position of a first-stage desuperheating water regulating valve on the B side of the superheater;
tempA: the front steam temperature of a primary desuperheater on the B side of the superheater is 1;
tempB: the rear steam temperature of a primary desuperheater on the B side of the superheater is 1;
tempC: rear steam temperature 2 of primary desuperheater on B side of superheater
The core index variables include:
1, diffy: static deviation;
diffys: standard deviation of static deviation;
scope: adjusting the amplitude variation;
scopes: adjusting amplitude variation fluctuation;
5, pree: a fault precursor indicator;
scope: a relative amplitude change;
scopys: relative amplitude variation standard deviation;
intime: calculating the time required for reaching the standard when the instruction changes;
and step 3: constructing a valve health degree estimation and life prediction model by using a hidden Markov HMM transfer model, outputting valve health degree evaluation information, and predicting the residual life of the valve;
the method comprises the following specific steps:
step 3.1: data host timing acquisition data for nth second control valve
1 hour as one sub-time T, for HnThe division is carried out, and the division is carried out,
wherein x ismThe value of each characteristic dimension at time t is represented, M ═ 8 represents the characteristic dimension, i.e. the number of core index variables,
step 3.2: calculating the mean value of each sub-time
Variance Stdm＝||{xm，t}-Avgm||2；
Step 3.3: counting the average value Avg in one daymVariance and variance Std ofmThe average value of (1) is used for measuring the stable state and the pressure condition of a data host for controlling the valve in one day;
step 3.4: average value Avg in one daymVariance and variance Std ofmForm an observation variable data set Et；
Step 3.6: configuration T ═ P (S)t|St-1) Will observe the variable data set EtInputting into a hidden Markov HMM transition model, calculating Ot+1Outputting the probability T ═ P (S) of the fault of the next dayt|St-1＝αOt+1TTf1:t)；
Step 3.7: evaluating the health degree of the valve according to the 7-day valve failure prediction probability valuet+1＝H(ft-6:t) And outputs L a life prediction based on the health assessmentt+1＝L(ht+1)。
The intelligent operation and maintenance capacity of the valve is improved, the accurate valve health degree assessment and valve service life prediction results can provide important support data for making valve maintenance decisions, and faults can be effectively avoided by timely discovering potential threats and taking appropriate maintenance measures, so that the safety, reliability and usability of the valve are improved. Therefore, the invention effectively overcomes various defects in the prior art and has high industrial utilization value.
The foregoing embodiments are merely illustrative of the principles and utilities of the present invention and are not intended to limit the invention. Any person skilled in the art can modify or change the above-mentioned embodiments without departing from the spirit and scope of the present invention. Accordingly, it is intended that all equivalent modifications or changes which can be made by those skilled in the art without departing from the spirit and technical spirit of the present invention be covered by the claims of the present invention.
Claims (3)
1. A hidden markov based valve health estimation and life prediction method, the method comprising the steps of:
step 1: deploying a Probe Probe program on a data host of a control valve, and acquiring valve control instructions and relevant index data of valve feedback data;
step 2: performing dimensionality reduction analysis on the multi-dimensional index data to determine a core index variable;
and step 3: and constructing a valve health degree estimation and life prediction model by using a hidden Markov HMM transfer model, outputting valve health degree evaluation information, and predicting the residual life of the valve.
2. The method for estimating the health and predicting the life of a valve according to claim 1, wherein the step 3 comprises the following steps:
step 3.1: data host timing acquisition data for nth second control valve
1 hour as one sub-time T, for HnThe division is carried out, and the division is carried out,
wherein x ismRepresenting the value of each feature dimension at time t, M represents the feature dimension,
step 3.2: calculating the mean value of each sub-time
Variance Stdm＝||{xm，t}-Avgm||2；
Step 3.3: counting the average value Avg in one daymVariance and variance Std ofmThe average value of (1) is used for measuring the stable state and the pressure condition of a data host for controlling the valve in one day;
step 3.4: average value Avg in one daymVariance and variance Std ofmForm an observation variable data set Et；
Step 3.5: configuration T ═ P (S)t|St-1) Will observe the variable data set EtInputting into a hidden Markov HMM transition model, calculating Ot+1Outputting the probability T ═ P (S) of the fault of the next dayt|St-1＝αOt+1TTf1:t)；
Step 3.6: evaluating the health degree of the valve according to the 7-day valve failure prediction probability valuet+1＝H(ft-6:t) And outputs L a life prediction based on the health assessmentt+1＝L(ht+1)。
3. The valve health estimation and life prediction method of claim 2, wherein: the characteristic dimension M is 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910041532.2A CN111443602B (en) | 2019-01-16 | 2019-01-16 | Hidden Markov-based valve health degree estimation and life prediction method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910041532.2A CN111443602B (en) | 2019-01-16 | 2019-01-16 | Hidden Markov-based valve health degree estimation and life prediction method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111443602A true CN111443602A (en) | 2020-07-24 |
| CN111443602B CN111443602B (en) | 2022-09-16 |
Family
ID=71626813
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910041532.2A Active CN111443602B (en) | 2019-01-16 | 2019-01-16 | Hidden Markov-based valve health degree estimation and life prediction method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111443602B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113408221A (en) * | 2021-07-06 | 2021-09-17 | 太仓比泰科自动化设备有限公司 | Probe service life prediction method, system, device and storage medium |
| CN115290316A (en) * | 2022-09-30 | 2022-11-04 | 艾坦姆流体控制技术(山东)有限公司 | Fault diagnosis method for eccentric rotary valve |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2014178800A (en) * | 2013-03-14 | 2014-09-25 | Gifu Univ | Medical information processing device and program |
| CN104282347A (en) * | 2013-07-09 | 2015-01-14 | 黄志奇 | Wireless sound detection apparatus for nuclear-power-station valve leakage and compression transmission method |
| CN104504296A (en) * | 2015-01-16 | 2015-04-08 | 湖南科技大学 | Gaussian mixture hidden Markov model and regression analysis remaining life prediction method |
| WO2018081627A1 (en) * | 2016-10-29 | 2018-05-03 | Kelvin Inc. | Plunger lift state estimation and optimization using acoustic data |
-
2019
- 2019-01-16 CN CN201910041532.2A patent/CN111443602B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2014178800A (en) * | 2013-03-14 | 2014-09-25 | Gifu Univ | Medical information processing device and program |
| CN104282347A (en) * | 2013-07-09 | 2015-01-14 | 黄志奇 | Wireless sound detection apparatus for nuclear-power-station valve leakage and compression transmission method |
| CN104504296A (en) * | 2015-01-16 | 2015-04-08 | 湖南科技大学 | Gaussian mixture hidden Markov model and regression analysis remaining life prediction method |
| WO2018081627A1 (en) * | 2016-10-29 | 2018-05-03 | Kelvin Inc. | Plunger lift state estimation and optimization using acoustic data |
| US20180119692A1 (en) * | 2016-10-29 | 2018-05-03 | Kelvin, Inc. | Plunger lift state estimation and optimization using acoustic data |
Non-Patent Citations (1)
| Title |
|---|
| 刘邦欣: "电子系统PHM关键技术的研究", 《中国优秀博硕士学位论文全文数据库（硕士） 信息科技辑》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113408221A (en) * | 2021-07-06 | 2021-09-17 | 太仓比泰科自动化设备有限公司 | Probe service life prediction method, system, device and storage medium |
| CN115290316A (en) * | 2022-09-30 | 2022-11-04 | 艾坦姆流体控制技术(山东)有限公司 | Fault diagnosis method for eccentric rotary valve |
| CN115290316B (en) * | 2022-09-30 | 2022-12-27 | 艾坦姆流体控制技术(山东)有限公司 | Fault diagnosis method for eccentric rotary valve |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111443602B (en) | 2022-09-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP7069269B2 (en) | Semi-supervised methods and systems for deep anomaly detection for large industrial surveillance systems based on time series data using digital twin simulation data | |
| KR102153924B1 (en) | Model parameter value estimation apparatus and estimation method, program, recording medium recording the program, model parameter value estimation system | |
| US9196009B2 (en) | Systems and methods for detecting changes in energy usage in a building | |
| KR101096793B1 (en) | data collecting method for detection and on-time warning system of industrial process | |
| Yoon | Virtual sensing in intelligent buildings and digitalization | |
| CN109213127A (en) | A kind of HVAC system gradual failure diagnostic method based on deep learning | |
| CN111443602B (en) | Hidden Markov-based valve health degree estimation and life prediction method | |
| EP3904987B1 (en) | Control support apparatus, control support method, control support program, computer readable medium with control support program recorded thereon and control system | |
| EP3800323A1 (en) | Virtual flow meter method and system for monitoring flow of an oil well in an industrial environment | |
| CN109598052B (en) | Intelligent ammeter life cycle prediction method and device based on correlation coefficient analysis | |
| CN110334383A (en) | Gas turbine fault diagnosis expert system method based on GA and L-M Combinatorial Optimization | |
| CN115438726A (en) | Device life and fault type prediction method and system based on digital twin technology | |
| CN111445105A (en) | Power plant online performance diagnosis method and system based on target value analysis | |
| Yan et al. | Two-stage degradation assessment and prediction method for aircraft engine based on data fusion | |
| JPWO2017169875A1 (en) | Analysis device, analysis method, and program | |
| CN117171596B (en) | Online monitoring method and system for pressure transmitter | |
| EP3596560B1 (en) | Evaluation apparatus, evaluation system, and evaluation method | |
| US10429828B2 (en) | Plant simulation device and plant simulation method with first parameter adjustable at start and second parameter adjustable during operation of the plant | |
| US10928811B2 (en) | Method and system to model industrial assets using heterogenous data sources | |
| JP7451854B2 (en) | Methods, systems and computer program products for diagnosing energy consumption in industrial environments | |
| CN112052496A (en) | Operation method of high arch dam valley amplitude deformation influence factor analysis system based on VAR model | |
| EP4083723A1 (en) | Evaluation apparatus, evaluation method, evaluation program, and control apparatus | |
| US10394255B2 (en) | Diagnostic device and method for monitoring frictional behavior in a control loop | |
| Coble et al. | Identifying suitable degradation parameters for individual-based prognostics | |
| Wang et al. | Predictive maintenance and sensitivity analysis for equipment with multiple quality states |
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 | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: A hidden Markov based method for valve health estimation and life prediction Effective date of registration: 20230811 Granted publication date: 20220916 Pledgee: The Bank of Shanghai branch Caohejing Limited by Share Ltd. Pledgor: Shanghai Gala Information Technology Co.,Ltd. Registration number: Y2023310000458 |
|
| PE01 | Entry into force of the registration of the contract for pledge of patent right |