CN109978059B - Early warning method for tower flushing faults of primary distillation tower in crude oil distillation process - Google Patents
Early warning method for tower flushing faults of primary distillation tower in crude oil distillation process Download PDFInfo
- Publication number
- CN109978059B CN109978059B CN201910242422.2A CN201910242422A CN109978059B CN 109978059 B CN109978059 B CN 109978059B CN 201910242422 A CN201910242422 A CN 201910242422A CN 109978059 B CN109978059 B CN 109978059B
- Authority
- CN
- China
- Prior art keywords
- tower
- primary
- early warning
- flushing
- crude oil
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 54
- 238000004821 distillation Methods 0.000 title claims abstract description 46
- 238000011010 flushing procedure Methods 0.000 title claims abstract description 30
- 239000010779 crude oil Substances 0.000 title claims abstract description 20
- 238000012549 training Methods 0.000 claims abstract description 14
- 238000009499 grossing Methods 0.000 claims abstract description 8
- 238000009826 distribution Methods 0.000 claims abstract description 6
- 238000007781 pre-processing Methods 0.000 claims abstract description 5
- 230000003203 everyday effect Effects 0.000 claims abstract description 4
- 238000005096 rolling process Methods 0.000 claims abstract description 4
- 238000001914 filtration Methods 0.000 claims abstract description 3
- 238000010992 reflux Methods 0.000 claims description 20
- 239000011159 matrix material Substances 0.000 claims description 15
- 238000001514 detection method Methods 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 7
- 239000003921 oil Substances 0.000 claims description 7
- 238000001816 cooling Methods 0.000 claims description 5
- 238000000513 principal component analysis Methods 0.000 claims description 5
- 239000007788 liquid Substances 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 3
- 238000011156 evaluation Methods 0.000 abstract description 3
- 238000010606 normalization Methods 0.000 abstract description 2
- 238000004519 manufacturing process Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 3
- 239000012071 phase Substances 0.000 description 3
- 238000005194 fractionation Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000007670 refining Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 206010019233 Headaches Diseases 0.000 description 1
- 230000005856 abnormality Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 231100000869 headache Toxicity 0.000 description 1
- 239000007791 liquid phase Substances 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 230000000087 stabilizing effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000005292 vacuum distillation Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
- G06F18/2135—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on approximation criteria, e.g. principal component analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Abstract
The invention discloses a primary distillation tower flushing fault early warning method in a crude oil distillation process, which comprises the steps of firstly selecting variables related to flushing according to the working process of a primary distillation tower and the distribution condition of sensors; then selecting the current data before a plurality of days as a training set; preprocessing the training set including smoothing filtering and normalization, and analyzing principal component to obtain SPE and T 2 A control limit; finally, calculating SPE and T of each moment of data to be tested 2 And (5) combining the two indexes to perform early warning. And if the two indexes exceed the time limit threshold value at the same time, sending out fault early warning. The method aims at the primary tower flushing faults, automatically updates a model every day, models in a rolling way, and early warns by comprehensive evaluation indexes, so that false alarms can be reduced, and the method has important application value for discovering faults in advance and reducing losses.
Description
Technical Field
The invention relates to industrial process fault detection, in particular to a primary distillation tower flushing fault early warning method facing a crude oil distillation process based on data driving.
Background
Crude oil distillation is a key link of a refining enterprise, and a typical process flow comprises the following steps: primary distillation, atmospheric distillation and vacuum distillation. The primary distillation is the first process of the crude oil distillation process, and whether the crude oil is stable or not greatly influences the subsequent processing.
The column flushing is a common fault in the primary distillation process, namely the phenomenon that the gas phase flow is too large and the liquid phase is directly brought into an upper tray in the distillation process, so that the fractionation effect is poor or the fractionation is destroyed, and the follow-up process flow is seriously influenced. The tower flushing failure can be caused by the high water content, low density, excessive oil feeding amount and the like of crude oil. In recent years, with more and more crude oil types imported in China, the properties of the crude oil are difficult to grasp, and the failure of the primary distillation tower occurs. The enterprise needs a proper method to early warn the faults of the tower, so that the operation and the remedy are timely carried out, and the loss is reduced.
Compared with other fault detection methods based on mechanism models and the like, the fault detection method based on data driving has been developed rapidly in recent years. However, the existing method always analyzes all the measurable variables, so that fault detection is generally only possible, and accurate diagnosis of faults is difficult to realize. If the effective variable is selected for analysis aiming at the tower flushing fault, the fault can be accurately diagnosed, and the fault early warning accuracy can be improved.
In addition, principal Component Analysis (PCA) is widely used as a data analysis method for data-based fault detection, which uses only square prediction error SPE or Hotelling's T 2 Is easy to report by mistake, and the high false alarm rate is the most headache problem of enterprises.
Finally, the existing fault early warning method generally comprises the steps of once modeling and continuously forecasting after collecting data in the production process, and a constant model is adopted, so that false report or missing report is very easy to occur.
Disclosure of Invention
Aiming at the problems, the invention discloses a method for early warning of a primary distillation tower flushing fault in a crude oil distillation process, which can be used for carrying out rolling modeling on the primary distillation tower flushing fault and adopting comprehensive evaluation indexes to carry out fault early warning.
The method comprises the following steps:
(1) Analyzing the technological process and the sensor distribution condition of the primary distillation tower, and determining the initial variable range related to the tower flushing fault;
(2) Further screening in the initial variable range: if the variable is a controlled variable of the closed-loop control system, rejecting the controlled variable, and simultaneously selecting a manipulated variable of the closed-loop control system to enter a final variable range; if the variable open loop is not controlled, directly selecting to enter a final variable range;
(3) Selecting the previous t for the data to be measured obtained every day 1 Day data is used as a training set;
(4) Preprocessing the training set, including smoothing filtering and standardization;
(5) The principal component analysis is carried out on the pretreated sample, and the control limit of the square prediction error SPE and Hotelling' sT are calculated 2 A control limit of the statistics;
(6) Preprocessing the data to be detected, and calculating SPE and T at each moment 2 Statistics, the two indexes are combined to perform early warning.
In the present method, the variables are selected within the following ranges: the method comprises the steps of feeding pressure, feeding temperature, tower top pressure, tower top temperature, primary top cooling reflux quantity, primary top circulating reflux quantity, primary top oil gas aftercooler outlet temperature, primary top reflux tank pressure and primary top reflux tank liquid level.
In the method, t 1 The range of the value is 5-10 days, and the confirmed fault data is removed.
Preferably, the smoothing filter algorithm uses a Savitzky-Golay (S-G) convolution smoothing algorithm.
In the method, a sample matrix X (d) is reorganized according to the following formula, wherein d is a time lag factor:
in the method, the training data is standardized, and the data to be measured is standardized by using the mean value and the variance of the training set.
The beneficial effects are that:
(1) The method provided by the invention is aimed at a primary distillation tower collision accident, the related variables are selected for modeling in a targeted manner, and the time sequence of industrial process data is considered in the modeling process, so that the prediction result is more accurate.
(2) The method provided by the invention can integrate SPE and T 2 The two evaluation indexes reduce false alarms.
(3) The method provided by the invention can automatically update the model every day, roll calculation, effectively reduce false alarm and missing report, and has important application value for finding faults in advance, reducing loss and stabilizing production.
Drawings
FIG. 1 is a flow chart of an implementation of a method for early warning of a primary distillation column flushing failure in a crude oil distillation process
FIG. 2 is a schematic view of a process and instruments for a No. 5 primary tower of a refinery enterprise
FIG. 3 shows the result of fault warning for a refinery from 11 months 15 to 11 months 19 days
FIG. 4 shows the result of fault warning for a refinery from 11 months 28 to 12 months 5 days
Detailed description of the preferred embodiments
The following provides a detailed description of the computing process and specific operational flows, taken in conjunction with the accompanying drawings and specific examples, to further illustrate the invention. The present embodiment is implemented on the premise of the technical solution of the present invention, but the scope of the present invention is not limited to the following embodiments.
This case is exemplified by a refinery having multiple sets of crude distillation units, wherein the crude processing capacity of the No. 5 atmospheric and vacuum unit is 800 ten thousand tons/year. Because of the variety of crude oil processed, the enterprise has suffered from primary tower flushing accidents for many times. The effectiveness and implementation process of the method are described below by using the tower flushing accident which occurs recently by the device, and then the case of successfully early warning and avoiding the tower flushing by using the method is introduced. First, a tower flushing failure occurring in the primary tower at about 17 points on 11/18/2018 will be described.
The implementation flow of the present case is shown in fig. 1, and specific implementation steps are as follows:
(1) And analyzing the working process and the sensor distribution condition of the primary distillation tower, and determining the initial variable range related to the tower flushing fault. The process and the instrument of the No. 5 primary distillation tower of the enterprise are shown in fig. 2. The variables related to the tower flushing accident are as follows through process analysis: the method comprises the steps of feeding pressure (6), feeding temperature (10), overhead pressure (5), overhead temperatures (46 and 8), primary overhead cooling reflux quantity (2), primary overhead circulating reflux quantity (19), primary overhead oil gas aftercooler outlet temperature (47), primary overhead reflux tank pressure (4) and primary overhead reflux tank liquid level (56).
(2) Further screening in the initial variable range: wherein, the temperature (8) of the tower top is controllable through the primary top cooling reflux quantity (2); the pressure (4) of the primary top reflux tank is controllable through two valves; the primary topping reflux drum level (56) is controllable by the primary topping reflux volume. The 3 variables are effectively controlled in a Distributed Control System (DCS), and the variable change amplitude is small, so that the method has no beneficial effect on fault early warning basically, and can be removed in early warning modeling. In order to stabilize the 3 variables, the corresponding manipulated variable has larger variation amplitude, which is very beneficial to timely finding out the abnormality. Thus, the variables retained are: the method comprises the steps of feeding pressure (6), feeding temperature (10), overhead pressure (5), primary top cooling reflux quantity (2), primary top circulating reflux quantity (19) and primary top oil gas aftercooler outlet temperature (47).
(3) Selecting the previous t for the obtained data to be tested 1 The day data is modeled as a training set, where t 1 The training data corresponding to each day is shown in table 1, taking 5.
TABLE 1 data to be tested and training set ranges corresponding thereto
Data range to be measured | Training set data range |
… | … |
11 month 15 days | 11 months 10-11 months 14 days |
11 month and 16 days | 11 months 11-11 months 15 days |
11 month 17 day | 11 months 12 days-11 months 16 days |
11 month 18 day | 11 months 13-11 months 17 days |
11 month and 19 days | 11 months 14-11 months 18 days |
… | … |
(5) S-G smoothing is carried out on the training set and the data to be tested, wherein a window is taken as 11, and the order is 3.
(6) Calculating hysteresis factors, recombining sample matrix, and calculating SPE control limit and T 2 And (5) a control limit.
Taking a model of 11 months and 15 days as an example, taking data of 11 months and 10 days to 11 months and 14 days to form a sample matrix X. Starting from d=0, the sample matrix X (d) is recombined according to formula (2), normalized and then subjected toPCA analysis is carried out to respectively calculate the number of principal elements, the static relation coefficient r (d) and the new relation coefficient r new (d) The formulas are shown as (3) and (4), and the calculation process is shown as table 2. When d=2, the new relationship coefficient r new (2) And +.0, therefore, the hysteresis factor is taken to be 2, at which time the normalized sample matrix X (2) has also been obtained.
r(d)=m-k-r(d-1) (3)
Where m is the variable number and k is the principal element number.
TABLE 2 hysteresis factor calculation procedure
d takes on the value of | Variable number | Number of principal components | Coefficient of static closure | New relation number |
0 | 6 | 3 | 3 | 3 |
1 | 12 | 3 | 9 | 3 |
2 | 18 | 3 | 15 | 0 |
PCA analysis is carried out on the sample matrix X (2) to obtain a load matrix P and a characteristic value matrix lambda as follows:
let the detection level α=0.99, the SPE control limit calculated according to the formula (5) and the formula (6) be 3.0679, t 2 The control limit is 11.3578.
Wherein,λ j is the j-th eigenvalue, c, of the covariance matrix of sample matrix X α Is a standard normal deviation corresponding to the upper limit (1- α) ×100%.
Where n is the number of samples, k is the number of principal elements, and F (k, n-1, α) is the critical value of the F distribution upper limit α×100% where the degrees of freedom are k and n-1.
(7) Forming a data matrix X to be tested according to d=2 by using data of 11 months and 15 days test And enter itAfter normalization, SPE and T are calculated for each time according to equation (7) and equation (8) 2 Statistics.
SPE=x T (I-PP T )x (7)
Where P is the load matrix in m x k dimensions.
Where λ is a diagonal matrix composed of eigenvalues corresponding to the first k principal components.
Table 3 variable controlled condition values
Variable controlled conditions | Value taking |
Closed loop control | 1 |
Manual or open loop uncontrolled | 0 |
Rolling modeling prediction was performed for 11 months 15 to 11 months 19 days, and the results are shown in fig. 3. SPE and T 2 The time at which the statistics are simultaneously overrun is marked by the vertical line. It can be seen that the SPE statistics overrun starting from 16:04 on day 18 of 11 months. Before this, T 2 Statistics are overrun, because the feed temperature and feed pressure of the primary distillation tower are increased, the gas phase in the tower is increased, and the control system automatically increases the cold reflux quantity, so that T 2 Increasing; however, the relationship among the variables is unchanged and still works normally, so the SPE statistics are always normal, and no fault is necessarily generated. But is provided withThe method has the advantages that as the cold reflux quantity approaches the set upper limit, the further increase of the gas phase cannot be pressed, the final output result is that the tower flushing early warning is sent out, the time is advanced by 1 hour compared with the actual manual intervention time, and the method can successfully early warn the tower flushing fault of the primary distillation tower.
FIG. 4 shows the early warning results of the No. 5 primary tower of the oil refining enterprise from 11.28.5 to 12.5 days, and the SPE and T of the data to be measured from 22:36 of 11.28.5 2 The statistics are overrun at the same time, and the method sends out early warning through calculation. The enterprises immediately take manual intervention measures after receiving the early warning, so that accidents are successfully avoided and expanded, and the occurrence of primary tower flushing faults is effectively prevented.
Claims (7)
1. A method for early warning of a primary distillation tower flushing fault in a crude oil distillation process is characterized in that the method carries out primary distillation tower flushing fault early warning by selecting variables, rolling calculation and adopting comprehensive indexes aiming at the working process of a primary distillation tower in an oil refinery, and comprises the following steps:
(1) Analyzing the technological process and the sensor distribution condition of the primary distillation tower, and determining the initial variable range related to the tower flushing fault;
(2) Further screening in the initial variable range: if the variable is a controlled variable of the closed-loop control system, rejecting the controlled variable, and simultaneously selecting a manipulated variable of the closed-loop control system to enter a final variable range; if the variable open loop is not controlled, directly selecting to enter a final variable range;
(3) Selecting the previous t for the data to be measured obtained every day 1 Day data is used as a training set;
(4) Preprocessing the training set, including smoothing filtering and standardization;
(5) Principal component analysis is performed on the pretreated sample, and the control limit of the square prediction error SPE and Hotelling's T are calculated 2 A control limit of the statistics; the control limit calculation method of the square prediction error SPE comprises the following steps:
wherein: SPE (SPE) α For the control limit of the SPE,λ j is the j-th eigenvalue, c, of the covariance matrix of sample matrix X α Is a standard normal deviation corresponding to the upper limit (1-alpha) x 100%, alpha being the detection level;
Hotelling's T 2 the statistic control limit calculation method comprises the following steps:
wherein:is T 2 N is the number of samples, k is the number of principal elements, F (k, n-1, alpha) is a critical value of the F distribution upper limit alpha x 100% with degrees of freedom of k and n-1, and alpha is a detection level;
(6) Preprocessing the data to be detected, and calculating SPE and T at each moment 2 Statistics, the two indexes are combined to perform early warning.
2. The method for early warning of a tower flushing failure of a primary distillation tower in a crude oil distillation process according to claim 1, wherein the variables are selected from the following ranges: the method comprises the steps of feeding pressure, feeding temperature, tower top pressure, tower top temperature, primary top cooling reflux quantity, primary top circulating reflux quantity, primary top oil gas aftercooler outlet temperature, primary top reflux tank pressure and primary top reflux tank liquid level.
3. The method for early warning of a tower flushing failure of a primary distillation tower in a crude oil distillation process according to claim 1, wherein t is 1 The range of the value is 5-10 days, and the confirmed fault data is removed.
4. The method for early warning of a tower flushing failure of a primary distillation tower in a crude oil distillation process according to claim 1, wherein the smoothing filter algorithm uses a Savitzky-Golay convolution smoothing algorithm.
5. The method for early warning of a tower flushing failure of a primary distillation tower in a crude oil distillation process according to claim 1, wherein the data to be measured is normalized by using means and variances of training data.
6. The method for early warning of a primary distillation column failure in a crude oil distillation process according to claim 1, wherein the SPE statistics and T of the data to be measured are as follows 2 Statistics all exceed the upper limit while continuing t 2 And when the time is minute, giving out fault early warning.
7. The method for early warning of a tower flushing failure of a primary distillation tower in a crude oil distillation process as set forth in claim 6, wherein t is 2 Take 30 minutes.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910242422.2A CN109978059B (en) | 2019-03-28 | 2019-03-28 | Early warning method for tower flushing faults of primary distillation tower in crude oil distillation process |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910242422.2A CN109978059B (en) | 2019-03-28 | 2019-03-28 | Early warning method for tower flushing faults of primary distillation tower in crude oil distillation process |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109978059A CN109978059A (en) | 2019-07-05 |
CN109978059B true CN109978059B (en) | 2024-02-23 |
Family
ID=67081210
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910242422.2A Active CN109978059B (en) | 2019-03-28 | 2019-03-28 | Early warning method for tower flushing faults of primary distillation tower in crude oil distillation process |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109978059B (en) |
Families Citing this family (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111126671A (en) * | 2019-11-29 | 2020-05-08 | 南京富岛信息工程有限公司 | Early warning method for tower flushing fault of primary distillation tower in oil refining production |
CN111413949B (en) * | 2020-03-30 | 2023-12-01 | 南京富岛信息工程有限公司 | Method for reducing fault early warning false alarm rate of industrial process |
CN113205121B (en) * | 2021-04-18 | 2023-10-03 | 宁波大学科学技术学院 | Primary tower sampling data coarse difference discrimination method based on local characteristic anomaly factors |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6389335B1 (en) * | 1995-06-07 | 2002-05-14 | Aurora Flight Sciences Corporation | Fault tolerant automatic control system utilizing analytic redundancy |
CN102736616A (en) * | 2012-06-18 | 2012-10-17 | 北京控制工程研究所 | Dulmage-Mendelsohn (DM)-decomposition-based measuring point optimal configuration method for closed loop system |
WO2015025087A1 (en) * | 2013-08-22 | 2015-02-26 | L'air Liquide,Societe Anonyme Pour L'etude Et L'exploitation Des Procedes Georges Claude | Detection of faults when determining concentrations of chemical components in a distillation column |
CN107667320A (en) * | 2015-06-11 | 2018-02-06 | 费斯托股份有限两合公司 | For operating electrically or the method for fluidic actuator and motion controller for actuator |
CN107918381A (en) * | 2017-12-04 | 2018-04-17 | 大连大学 | A kind of class average core pivot method for diagnosing faults based on compound kernel function |
CN109062196A (en) * | 2018-10-31 | 2018-12-21 | 东北大学 | The blast furnace process monitoring of integrated PCA-ICA a kind of and method for diagnosing faults |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8412357B2 (en) * | 2010-05-10 | 2013-04-02 | Johnson Controls Technology Company | Process control systems and methods having learning features |
US9053291B2 (en) * | 2010-09-29 | 2015-06-09 | Northeastern University | Continuous annealing process fault detection method based on recursive kernel principal component analysis |
DE112016001831B4 (en) * | 2015-05-21 | 2019-09-19 | Kastanienbaum GmbH | Method and device for controlling an actuator-driven robot joint |
-
2019
- 2019-03-28 CN CN201910242422.2A patent/CN109978059B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6389335B1 (en) * | 1995-06-07 | 2002-05-14 | Aurora Flight Sciences Corporation | Fault tolerant automatic control system utilizing analytic redundancy |
CN102736616A (en) * | 2012-06-18 | 2012-10-17 | 北京控制工程研究所 | Dulmage-Mendelsohn (DM)-decomposition-based measuring point optimal configuration method for closed loop system |
WO2015025087A1 (en) * | 2013-08-22 | 2015-02-26 | L'air Liquide,Societe Anonyme Pour L'etude Et L'exploitation Des Procedes Georges Claude | Detection of faults when determining concentrations of chemical components in a distillation column |
CN107667320A (en) * | 2015-06-11 | 2018-02-06 | 费斯托股份有限两合公司 | For operating electrically or the method for fluidic actuator and motion controller for actuator |
CN107918381A (en) * | 2017-12-04 | 2018-04-17 | 大连大学 | A kind of class average core pivot method for diagnosing faults based on compound kernel function |
CN109062196A (en) * | 2018-10-31 | 2018-12-21 | 东北大学 | The blast furnace process monitoring of integrated PCA-ICA a kind of and method for diagnosing faults |
Non-Patent Citations (7)
Title |
---|
主元分析方法在火电厂锅炉过程故障检测中的应用;黄孝彬,刘吉臻,牛玉广;《动力工程》;20040815;第24卷(第04期);第542-547页 * |
原油蒸馏装置SDG故障诊断应用研究;卢秉南;中国优秀硕士学位论文全文数据库 信息科技辑;全文 * |
周东华等.《现代故障诊断与容错控制》.清华大学出版社,2000,第256页. * |
基于多变量预测控制技术的丙烯精馏塔控制系统;张泉;王从庆;;化学工业与工程技术(第06期);全文 * |
基于改进动态主元分析在半实物仿真系统中的研究;高强,常勇;《电子学报》;20170315;第45卷(第03期);第565-569页 * |
基于相对㶲矩阵的精馏塔控制结构选择;叶尧;周猛飞;蔡亦军;潘海天;;计算机与应用化学(第03期);全文 * |
数据驱动蒸馏塔的安全生产的研究;李毅,常勇;《计算机与应用化学》;20151028;第32卷(第10期);第1191-1196页 * |
Also Published As
Publication number | Publication date |
---|---|
CN109978059A (en) | 2019-07-05 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109978059B (en) | Early warning method for tower flushing faults of primary distillation tower in crude oil distillation process | |
CN111508216B (en) | Intelligent early warning method for dam safety monitoring data | |
EP2132605B1 (en) | Method and system of using inferential measurements for abnormal event detection in continuous industrial processes | |
US7349746B2 (en) | System and method for abnormal event detection in the operation of continuous industrial processes | |
CN104360677B (en) | Cigarette processing quality evaluation and diagnosis method | |
CN111949700A (en) | Intelligent safety guarantee real-time optimization method and system for petrochemical device | |
CN115994248B (en) | Data detection method and system for valve faults | |
WO2021114320A1 (en) | Wastewater treatment process fault monitoring method using oica-rnn fusion model | |
CN112066724A (en) | Roller kiln energy consumption abnormity detection method based on self-adaptive principal component analysis | |
CN111752147A (en) | Multi-working-condition process monitoring method with continuous learning capability and improved PCA (principal component analysis) | |
CN111413949B (en) | Method for reducing fault early warning false alarm rate of industrial process | |
CN104615123B (en) | K-nearest neighbor based sensor fault isolation method | |
CN112418682A (en) | Security assessment method fusing multi-source information | |
CN112631258B (en) | Fault early warning method for key indexes of industrial process | |
CN111338310B (en) | Industrial process steady-state working condition identification and classification method | |
CN111126671A (en) | Early warning method for tower flushing fault of primary distillation tower in oil refining production | |
CN116339275A (en) | Multi-scale process fault detection method based on full-structure dynamic autoregressive hidden variable model | |
CN115310561A (en) | Electromagnetic valve fault monitoring method based on integrated instant learning | |
RU2470352C1 (en) | Statistical process control method (versions) | |
CN111983994B (en) | V-PCA fault diagnosis method based on complex industrial chemical process | |
Zhou et al. | Study on Optimization of Data-Driven Anomaly Detection | |
CN112990682A (en) | Chemical device control parameter optimization method and system based on big data | |
CN111504944A (en) | Statistical monitoring method of citric acid fermentation liquefied clear liquid based on near infrared spectrum | |
CN110377007A (en) | Fault Diagnosis for Chemical Process method based on pivot analysis | |
CN114819743B (en) | Energy consumption diagnosis and analysis method for chemical enterprises |
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 |