CN113190792B - Ethylene cracking furnace running state monitoring method based on neighbor local abnormal factors - Google Patents
Ethylene cracking furnace running state monitoring method based on neighbor local abnormal factors Download PDFInfo
- Publication number
- CN113190792B CN113190792B CN202110440247.5A CN202110440247A CN113190792B CN 113190792 B CN113190792 B CN 113190792B CN 202110440247 A CN202110440247 A CN 202110440247A CN 113190792 B CN113190792 B CN 113190792B
- Authority
- CN
- China
- Prior art keywords
- cracking furnace
- ethylene cracking
- vector
- matrix
- data
- 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
- 238000005336 cracking Methods 0.000 title claims abstract description 71
- VGGSQFUCUMXWEO-UHFFFAOYSA-N Ethene Chemical compound C=C VGGSQFUCUMXWEO-UHFFFAOYSA-N 0.000 title claims abstract description 69
- 239000005977 Ethylene Substances 0.000 title claims abstract description 69
- 238000000034 method Methods 0.000 title claims abstract description 33
- 230000002159 abnormal effect Effects 0.000 title claims abstract description 23
- 238000012544 monitoring process Methods 0.000 title claims abstract description 16
- 239000011159 matrix material Substances 0.000 claims abstract description 35
- 238000005070 sampling Methods 0.000 claims abstract description 30
- 239000013598 vector Substances 0.000 claims description 61
- 238000010606 normalization Methods 0.000 claims description 5
- 238000005259 measurement Methods 0.000 claims description 4
- 230000005855 radiation Effects 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 3
- 239000012895 dilution Substances 0.000 claims description 3
- 238000010790 dilution Methods 0.000 claims description 3
- 238000007599 discharging Methods 0.000 claims 2
- 238000004458 analytical method Methods 0.000 abstract description 4
- 230000008859 change Effects 0.000 abstract description 4
- 239000007789 gas Substances 0.000 description 9
- 238000004519 manufacturing process Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 3
- 230000005856 abnormality Effects 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical compound C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 description 2
- 239000002994 raw material Substances 0.000 description 2
- 239000000243 solution Substances 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 239000006227 byproduct Substances 0.000 description 1
- 238000001311 chemical methods and process Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 239000010779 crude oil Substances 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- -1 ethylene, propylene Chemical group 0.000 description 1
- 230000002175 menstrual effect Effects 0.000 description 1
- 239000003345 natural gas Substances 0.000 description 1
- 238000011112 process operation Methods 0.000 description 1
- 239000000047 product Substances 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
-
- 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 an ethylene cracking furnace running state monitoring method based on neighbor local abnormal factors, which realizes real-time characteristic analysis on sampling data of an ethylene cracking furnace on the premise of considering unsteady running and time-varying characteristics of the ethylene cracking furnace, thereby effectively monitoring the running state of the ethylene cracking furnace. The method solves the unsteady state change problem of the ethylene cracking furnace sampling data by a technical means of constructing the neighbor local anomaly factors in real time, maximizes the difference between the online new sampling data and the neighbor reference data set in real time, and judges whether the new sampling data reflect the anomaly except for the ethylene cracking furnace. In addition, the method of the invention realizes the real-time update of the ethylene cracking furnace running state monitoring model by introducing the normal latest sample data into the normal data matrix in real time and deleting the oldest sample data.
Description
Technical Field
The invention relates to a monitoring method for the running state of a chemical process, in particular to a monitoring method for the running state of an ethylene cracking furnace based on a neighbor local anomaly factor.
Background
The ethylene cracking furnace is used for processing cracking gas and comprises a double radiation chamber, a single radiation chamber and a millisecond furnace. The ethylene cracking furnace is the core equipment of ethylene production equipment, and has the main functions of processing various raw materials such as natural gas, refinery gas, crude oil, naphtha and the like into cracking gas, providing the cracking gas for other ethylene equipment and finally processing the cracking gas into ethylene, propylene and various byproducts. The production capacity and the technology of the ethylene cracking furnace directly determine the production scale, the yield and the product quality of the whole set of ethylene equipment, so that the ethylene cracking furnace plays a role of a tap in the ethylene production equipment and even the whole set of petrochemical production.
It can be seen that the operation of the ethylene cracking furnace in the expected state (i.e., normal state) plays an important role in the whole ethylene production process, and real-time monitoring of the operation state of the ethylene cracking furnace is essential. However, conventional monitoring of ethylene-cracking furnace operating conditions is accomplished by monitoring changes in one or a few critical technical parameters. The key variable change can be monitored according to the single variable idea, whether a single technical parameter is in an allowable change range or not can be monitored in real time, and the running state of the ethylene cracking furnace can not be monitored in real time from the perspective of the whole system.
In addition, in actual operation, the state of the ethylene cracking furnace is influenced by fluctuation of raw material feeding, steam feeding and other factors, so that the operation of the ethylene cracking furnace is unstable. The data collected under this condition are all unsteady sample data. The conventional data driving method assumes gaussian distribution, which is not true in sample data of an ethylene cracking furnace. Thus, data-driven monitoring of the operating conditions of ethylene cracking furnaces is known to be a relatively troublesome problem. Unfortunately, at present, due to the promotion of industrial big data, a plurality of measuring instruments and a computer auxiliary system are installed on an ethylene cracking furnace object, so that sample data can be measured in real time at short intervals. This lays a substantial data foundation for implementing data-driven monitoring of the operating state of the ethylene cracking furnace.
In the case of a sufficient amount of sampled data from the ethylene-cracking furnace, the non-steady state nature of the process operation results in the Gaussian distribution assumption still not being established. However, it is contemplated that the abnormal operating conditions of the ethylene-cracking furnace are unknown, and any number or any variable of anomalies may be indicative of an abnormal operating condition of the ethylene-cracking furnace. Therefore, the characteristic analysis of the ethylene cracking furnace sample data is supposed to be performed on line in real time. In addition, the unsteady state of the sampled data can not be considered, the historical sample data of the ethylene cracking furnace can not be taken as a whole, and the sample data of the ethylene cracking furnace in the normal operation state can be updated in real time.
Disclosure of Invention
The main technical problems to be solved by the invention are as follows: on the premise of considering unsteady state operation and time-varying characteristics of the ethylene cracking furnace, real-time characteristic analysis is performed on sampling data of the ethylene cracking furnace in real time, so that the operation state of the ethylene cracking furnace is effectively monitored. Specifically, the method of the invention constructs the adjacent local abnormal factor for the online sampling data of the ethylene cracking furnace in real time, and monitors whether the operation state of the ethylene cracking furnace is abnormal by judging whether the abnormal factor exceeds the limit. Then, sample data in a normal running state is updated to a reference data set in real time, so that the self-adaptive updating characteristic of the model is ensured.
The technical scheme adopted by the method for solving the problems is as follows: an ethylene cracking furnace running state monitoring method based on neighbor local abnormal factors comprises the following steps.
Step (1): acquiring sample data x of n sampling moments of an ethylene cracking furnace in a normal operation state 1 ,x 2 ,…,x n And is composed into a data matrix X= [ X ] of n X m dimension 1 ,x 2 ,…,x n ] T The method comprises the steps of carrying out a first treatment on the surface of the Wherein the sample data x at the ith sampling time i ∈R 33×1 The 33 measurement data in (1) comprise in sequence the feed pressure of the radiation chamber of 6 furnace tubes, the feed flow of 6 furnace tubes, the dilution steam flow of 6 furnace tubes, the discharge temperature of 6 furnace tubes, the crossover temperature of 6 furnace tubes, the discharge average temperature of 1 ethylene cracking furnace, the furnace wall gas flow of 1 ethylene cracking furnace, and the bottom gas flow of 1 ethylene cracking furnace, i epsilon {1,2, …, n }, R 33×1 A 33 x 1-dimensional real vector is represented, R represents a real set, and the upper label T represents a matrix or a transpose of vectors.
Step (2): according to the formulaColumn vectors z in data matrix X, respectively 1 ,z 2 ,…,z 33 The process of standardization is carried out and the process of the method,thereby obtaining a normalized data matrix +.>Wherein z is k And->Respectively represent X and->Column vector of kth column, k ε {1,2, …,33}, μ k And delta k Respectively represent column vectors z k Average and standard deviation of all elements in (a).
Step (3): determining the normal upper limit value Q of the neighboring local abnormal factor according to the following steps (3.1) to (3.6) lim 。
Step (3.1): initializing i=1.
Step (3.2): setting upThen X is added again i Deleting the row vector of the ith row in the matrix to obtain a matrix X consisting of n-1 row vectors i ∈R (n-1)×33 The method comprises the steps of carrying out a first treatment on the surface of the Wherein R is (n-1)×33 Representing a real matrix of (n-1) x 33 dimensions.
Step (3.3): calculate X i Each row vector of (a) and (b) a row vector y i Distance between them, X again i Intermediate and y i N rows of vectors with minimum distance between them form neighbor reference matrixWherein R is N×33 Representing an N x 33-dimensional real matrix, y i Representation->Row vector of row i.
Step (3.4): solving generalized eigenvalue problemMaximum eigenvalue lambda of (1) i Corresponding feature vector alpha i Then, according to the formula->Updating feature vector alpha i 。
Step (3.5): according to the formulaCalculating neighbor local anomaly factor Q i Then judging whether the condition i is less than n; if yes, setting i=i+1, and returning to the step (3.2); if not, get Q 1 ,Q 2 ,…,Q n 。
Step (3.6): will Q 1 ,Q 2 ,…,Q n The maximum value in (a) is recorded as the normal upper limit value Q of the adjacent local abnormal factor lim 。
Step (4): at the latest sampling time t, sample data x of the ethylene cracking furnace is collected t ∈R 1×33 And according to the formulaFor x t Each element in the data vector is standardized to obtain an online data vector after the standardized processingWherein x is t (k) And->Respectively represent x t And->The k-th element of (a).
Step (5): calculation ofAre associated with the line data vector>Distance between them, will be->Middle and->N rows of vectors with minimum distance between them form a neighbor reference matrix +.>
Step (6): solving generalized eigenvalue problemMaximum eigenvalue lambda of (1) t Corresponding feature vector p t Then, according to the formula->Updating feature vector p t 。
Step (7): according to the formulaCalculating neighbor local anomaly factor Q of latest sampling time t t Then, judge whether or not the condition Q is satisfied t ≤Q lim The method comprises the steps of carrying out a first treatment on the surface of the If yes, executing the step (8); if not, executing the step (10).
Step (8): will be according to the following formulaRow vector y of middle and rear n-1 rows 2 ,y 3 ,…,y n And->After being combined into a matrix Y, the step (9) is executed.
In the above, y 2 ,y 3 ,…,y n Respectively representThe 2 nd to nth row vectors.
Step (9): according to the formulaFor column vectors in matrix Y, respectively>Performing normalization processing to obtain matrix +.>And then according to the formula->Andrespectively updating the average value mu 1 ,μ 2 ,…,μ 33 And standard deviation delta 1 ,δ 2 ,…,δ 33 After that, set->And returning to the step (4) to continuously monitor the running state of the ethylene cracking furnace at the latest sampling moment; wherein (1)>And ηk represents Y and +.>Column vector of the kth column, +.>And->Respectively represent column vector +.>Average and standard deviation of all elements in (a).
Step (10): returning to the step (4) to continuously monitor the running state of the ethylene cracking furnace at the latest sampling moment until the adjacent local abnormal factors at the continuous 6 latest sampling moments are obtained, and judging whether the 6 adjacent local abnormal factors are all larger than Q lim The method comprises the steps of carrying out a first treatment on the surface of the If yes, triggering an abnormal alarm; if not, the ethylene cracking furnace is in a normal running state, and the step (8) is executed.
In the implementation step, the problem of calculating similar generalized eigenvalues is involved in both the step (3.4) and the step (6). This generalized eigenvalue problem solution is actually the key core process of implementing the construction of neighbor local anomaly factors. Taking step (3.4) as an example, the so-called neighbor local feature factor is intended to pass through a feature vector α i To quantize the row vector y i Relative to a neighbor reference matrixIs a degree of abnormality of (a).
Simply put, it is the neighbor reference matrixMenstrual flow alpha i Minimum range of variation as possible after projective transformation and simultaneously enabling the row vector y i Menstrual flow alpha i The projective transformation is as maximum as possible. By referring to the basic idea of the discriminant analysis algorithm, an objective function as follows can be constructed:
without loss of generality, the denominator in the above objective function may be setThus, the above equation can be equivalently translated into a maximization problem with constraints as shown below:
the solution of the above formula (3) may use a classical langerhans multiplier method, i.e., a langerhans function L is constructed as shown below.
Then, solve for L relative to alpha i And setting it equal to 0 gives the following equation:
further, the generalized eigenvalue problem in the step (3.4) is converted into:if the generalized eigenvalue problem is respectively multiplied by +.>Then get +.>Thus lambda is i Equal to the maximization objective in the above formula (3), i.e. generalized eigenvalue problem +.>The maximum eigenvalue needs to be calculated.
By carrying out the steps described above, the advantages of the method according to the invention are described below.
The method solves the unsteady state change problem of the ethylene cracking furnace sampling data by constructing the technical means of the neighbor local anomaly factors, maximizes the difference between the online new sampling data and the neighbor reference data set in real time, and judges whether the new sampling data reflect the anomaly except for the ethylene cracking furnace. In addition, the method of the invention realizes the real-time update of the ethylene cracking furnace running state monitoring model by introducing the normal latest sample data into the normal data matrix in real time and deleting the oldest sample data.
Drawings
FIG. 1 is a schematic flow chart of the method of the present invention.
FIG. 2 is a schematic view of an ethylene cracking furnace.
Detailed Description
The invention will be described in detail below with reference to the drawings and the detailed description.
As shown in FIG. 1, the invention discloses an ethylene cracking furnace running state monitoring method based on a neighbor local anomaly factor. A specific embodiment of the method according to the invention will be described below in connection with a specific application example.
The ethylene cracking furnace shown in fig. 2 is a tap device for producing ethylene in a certain chemical industry in China, and the device comprises 6 furnace tubes, wherein 5 variables can be measured by each furnace tube, and the device specifically comprises: the radiant chamber feed pressure, feed flow, dilution steam flow, discharge temperature, and crossover temperature. Thus, there are 30 measurement variables for 6 furnace tubes. In addition, there are three measurable variables, specifically, furnace wall gas flow of the ethylene cracking furnace, bottom gas flow of the ethylene cracking furnace, and average temperature of the ethylene cracking furnace discharge. In summary, in this embodiment, 33 measurement data may be acquired at each sampling time, which constitutes a 33×1-dimensional sample data.
Step (1): acquiring sample data x of n sampling moments of an ethylene cracking furnace in a normal operation state 1 ,x 2 ,…,x n And records it as an n×m-dimensional data matrix x= [ X ] 1 ,x 2 ,…,x n ] T 。
Step (2): according to the formulaColumn vectors z in data matrix X, respectively 1 ,z 2 ,…,z 33 Performing normalization processing to obtain normalized data matrix>
Step (3): determining the normal upper limit value Q of the neighbor local abnormality factor according to the steps (3.1) to (3.6) lim 。
Step (4): at the latest sampling time t, sample data x of the ethylene cracking furnace is collected t ∈R 1×33 And according to the formulaFor x t Each element in the data vector is standardized to obtain an online data vector after the standardized processingWherein x is t (k) And->Respectively represent x t And->The k-th element of (a).
Step (5): calculation ofAre associated with the line data vector>Distance between them, will be->Middle and->Spacing ofThe N-row vector from the minimum constitutes a neighbor reference matrix +.>
In step (5), calculatingThe ith row vector y i And online data vector->Specific embodiments of the distance between them are: />
Step (6): solving generalized eigenvalue problemMaximum eigenvalue lambda of (1) t Corresponding feature vector p t Then, according to the formula->Updating feature vector p t 。
Step (7): according to the formulaCalculating neighbor local anomaly factor Q of latest sampling time t t Then, judge whether or not the condition Q is satisfied t ≤Q lim The method comprises the steps of carrying out a first treatment on the surface of the If yes, executing the step (8); if not, executing the step (10).
Step (8): will be according to formula (1)Row vector y of middle and rear n-1 rows 2 ,y 3 ,…,y n And->Is combined into a matrix Y 1 After that, execute againAnd (9) a step.
Step (9): according to the formulaRespectively to matrix Y 1 Column vector +.>Performing normalization processing to obtain matrix +.>And then according to the formula->Andrespectively updating the average value mu k And standard deviation delta k After that, set->And returning to the step (4) to continuously monitor the running state of the ethylene cracking furnace at the latest sampling moment.
Step (10): returning to the step (4) to continuously monitor the running state of the ethylene cracking furnace at the latest sampling moment until the adjacent local abnormal factors at the continuous 6 latest sampling moments are obtained, and judging whether the 6 adjacent local abnormal factors are all larger than Q lim The method comprises the steps of carrying out a first treatment on the surface of the If yes, triggering an abnormal alarm; if not, the ethylene cracking furnace is in a normal running state, and the step (8) is executed.
Claims (1)
1. The ethylene cracking furnace running state monitoring method based on the neighbor local abnormal factors is characterized by comprising the following steps of:
step (1): acquiring sample data x of n sampling moments of an ethylene cracking furnace in a normal operation state 1 ,x 2 ,…,x n And forms a data matrix X= [ X ] of n X m dimension 1 ,x 2 ,…,x n ] T The method comprises the steps of carrying out a first treatment on the surface of the Wherein the sample data x at the ith sampling time i ∈R 33×1 The 33 measurement data in (1) specifically comprises the feeding pressure of a radiation chamber of 6 furnace tubes, the feeding flow of 6 furnace tubes, the dilution steam flow of 6 furnace tubes, the discharging temperature of 6 furnace tubes, the intersection temperature of 6 furnace tubes, the discharging average temperature of 1 ethylene cracking furnace, the furnace wall gas flow of 1 ethylene cracking furnace and the bottom gas flow of 1 ethylene cracking furnace, i epsilon {1,2, …, n }, R 33×1 Representing a 33 x 1 dimensional real vector, R representing a real set, and the upper label T representing a matrix or a transpose of vectors;
step (2): according to the formulaColumn vectors z in data matrix X, respectively 1 ,z 2 ,…,z 33 Performing normalization processing to obtain normalized data matrix>Wherein z is k And->Respectively represent X and->Column vector of kth column, k ε {1,2, …,33}, μ k And delta k Respectively represent column vectors z k Average and standard deviation of all elements in (a);
step (3): determining the normal upper limit value Q of the neighboring local abnormal factor according to the following steps (3.1) to (3.6) lim ;
Step (3.1): initializing i=1;
step (3.2): setting upThen X is added again i Deleting the row vector of the ith row in the list, thereby obtaining a list of the ith rowMatrix X consisting of n-1 row vectors i ∈R (n-1)×33 The method comprises the steps of carrying out a first treatment on the surface of the Wherein R is (n-1)×33 A real number matrix of (n-1) ×33 dimensions;
step (3.3): calculate X i Each row vector of (a) and (b) a row vector y i Distance between them, X again i Intermediate and y i N rows of vectors with minimum distance between them form neighbor reference matrixWherein R is N×33 Representing an N x 33-dimensional real matrix, y i Representation->Row vectors of the ith row in (a);
step (3.4): solving generalized eigenvalue problemMaximum eigenvalue lambda of (1) i Corresponding feature vector alpha i Then, according to the formula->Updating feature vector alpha i ;
Step (3.5): according to the formulaCalculating neighbor local anomaly factor Q i Then judging whether the condition i is less than n; if yes, setting i=i+1, and returning to the step (3.2); if not, get Q 1 ,Q 2 ,…,Q n ;
Step (3.6): will Q 1 ,Q 2 ,…,Q n The maximum value in (a) is recorded as the normal upper limit value Q of the adjacent local abnormal factor lim ;
Step (4): at the latest sampling time t, sample data x of the ethylene cracking furnace is collected t ∈R 1×33 And according to the formulaFor x t Each element in the data vector is standardized to obtain an online data vector after the standardized processingWherein x is t (k) And->Respectively represent x t And->The kth element of (a);
step (5): calculation ofAre associated with the line data vector>Distance between them, will be->Middle and->N rows of vectors with minimum distance between them form a neighbor reference matrix +.>
Step (6): solving generalized eigenvalue problemMaximum eigenvalue lambda of (1) t Corresponding feature vector p t Then, according to the formula->Updating feature vector p t ;
Step (7): according to the formulaCalculating neighbor local anomaly factor Q of latest sampling time t t Then, judge whether or not the condition Q is satisfied t ≤Q lim The method comprises the steps of carrying out a first treatment on the surface of the If yes, executing the step (8); if not, executing the step (10);
step (8): will be according to the following formulaRow vector y of middle and rear n-1 rows 2 ,y 3 ,…,y n And->After being combined into a matrix Y, the step (9) is executed again;
in the above, y 2 ,y 3 ,…,y n Respectively representThe 2 nd to nth row vectors;
step (9): according to the formulaRespectively to matrix Y 1 Column vector +.>Performing normalization processing to obtain matrix +.>And then according to the formula->And->Respectively updating the average value mu 1 ,μ 2 ,…,μ 33 And standard deviation delta 1 ,δ 2 ,…,δ 33 After that, set->And returning to the step (4) to continuously monitor the running state of the ethylene cracking furnace at the latest sampling moment; wherein (1)>And eta k Respectively represent Y and->Column vector of the kth column, +.>And->Respectively represent column vector +.>Average and standard deviation of all elements in (a);
step (10): returning to the step (4) to continuously monitor the running state of the ethylene cracking furnace at the latest sampling moment until the adjacent local abnormal factors at the continuous 6 latest sampling moments are obtained, and judging whether the 6 adjacent local abnormal factors are all larger than Q lim The method comprises the steps of carrying out a first treatment on the surface of the If yes, triggering an abnormal alarm; if not, the ethylene cracking furnace is in a normal running state, and the step (8) is executed.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110440247.5A CN113190792B (en) | 2021-04-18 | 2021-04-18 | Ethylene cracking furnace running state monitoring method based on neighbor local abnormal factors |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110440247.5A CN113190792B (en) | 2021-04-18 | 2021-04-18 | Ethylene cracking furnace running state monitoring method based on neighbor local abnormal factors |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113190792A CN113190792A (en) | 2021-07-30 |
CN113190792B true CN113190792B (en) | 2023-10-24 |
Family
ID=76978113
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110440247.5A Active CN113190792B (en) | 2021-04-18 | 2021-04-18 | Ethylene cracking furnace running state monitoring method based on neighbor local abnormal factors |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113190792B (en) |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105518654A (en) * | 2013-08-23 | 2016-04-20 | 应用材料公司 | K-nearest neighbor-based method and system to provide multi-variate analysis on tool process data |
JP2016099863A (en) * | 2014-11-25 | 2016-05-30 | 日本電信電話株式会社 | Abnormal value detection device and operation method thereof |
CN110362608A (en) * | 2019-06-11 | 2019-10-22 | 广东工业大学 | Energy consumption method for detecting abnormality based on rain flow method and local outlier factor |
CN110865260A (en) * | 2019-11-29 | 2020-03-06 | 南京信息工程大学 | Method for monitoring and evaluating MOV actual state based on outlier detection |
CN111913460A (en) * | 2019-05-20 | 2020-11-10 | 宁波大学 | Fault monitoring method based on sequence correlation local preserving projection algorithm |
CN111914206A (en) * | 2019-05-20 | 2020-11-10 | 宁波大学 | Process monitoring method based on novel dynamic neighbor preserving embedding algorithm |
CN111914887A (en) * | 2020-06-13 | 2020-11-10 | 宁波大学 | Novel multi-mode chemical process abnormal state detection method |
-
2021
- 2021-04-18 CN CN202110440247.5A patent/CN113190792B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105518654A (en) * | 2013-08-23 | 2016-04-20 | 应用材料公司 | K-nearest neighbor-based method and system to provide multi-variate analysis on tool process data |
JP2016099863A (en) * | 2014-11-25 | 2016-05-30 | 日本電信電話株式会社 | Abnormal value detection device and operation method thereof |
CN111913460A (en) * | 2019-05-20 | 2020-11-10 | 宁波大学 | Fault monitoring method based on sequence correlation local preserving projection algorithm |
CN111914206A (en) * | 2019-05-20 | 2020-11-10 | 宁波大学 | Process monitoring method based on novel dynamic neighbor preserving embedding algorithm |
CN110362608A (en) * | 2019-06-11 | 2019-10-22 | 广东工业大学 | Energy consumption method for detecting abnormality based on rain flow method and local outlier factor |
CN110865260A (en) * | 2019-11-29 | 2020-03-06 | 南京信息工程大学 | Method for monitoring and evaluating MOV actual state based on outlier detection |
CN111914887A (en) * | 2020-06-13 | 2020-11-10 | 宁波大学 | Novel multi-mode chemical process abnormal state detection method |
Non-Patent Citations (5)
Title |
---|
Fault Detection and Identification Based on the Neighborhood Standardized Local Outlier Factor Method;Hehe Ma 等;Industrial & Engineering Chemistry Research;2389-2402 * |
基于k-近邻的多元时间序列局部异常检测;郭小芳;李锋;王卫东;;江苏科技大学学报(自然科学版);第26卷(第5期);505-508, 513 * |
基于偏离特征的离群点挖掘方法研究;尹新亮;中国优秀硕士学位论文全文数据库信息科技辑;I138-1119 * |
基于高维数据流的异常检测算法;余立苹 等;计算机工程;第44卷(第1期);51-55 * |
状态监测技术在裂解炉引风机故障诊断中的应用;吕志坚 等;中国设备工程;160-161 * |
Also Published As
Publication number | Publication date |
---|---|
CN113190792A (en) | 2021-07-30 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Kourti et al. | Process analysis, monitoring and diagnosis, using multivariate projection methods | |
Kourti et al. | Experiences with industrial applications of projection methods for multivariate statistical process control | |
US8010321B2 (en) | Metrics independent and recipe independent fault classes | |
Said et al. | Machine learning technique for data-driven fault detection of nonlinear processes | |
CN112036089A (en) | Coal mill fault early warning method based on DPC-MND and multivariate state estimation | |
CN108508865B (en) | A kind of fault detection method based on distributing OSC-PLS regression model | |
Martin et al. | Manufacturing performance enhancement through multivariate statistical process control | |
KR20120039160A (en) | Prediction and fault detection method and system for performance monitoring of plant instruments using principal component analysis, response surface method, fuzzy support vector regression and generalized likelihood ratio test | |
CN108469805A (en) | A kind of distributing dynamic process monitoring method based on dynamic optimal selection | |
MacGregor et al. | Analysis, monitoring and fault diagnosis of industrial processes using multivariate statistical projection methods | |
CN110942258B (en) | Performance-driven industrial process anomaly monitoring method | |
CN109858707B (en) | ABC-ANFIS-CTF-based intelligent coking diagnosis method for furnace tube of ethylene cracking furnace | |
CN113190792B (en) | Ethylene cracking furnace running state monitoring method based on neighbor local abnormal factors | |
CN109683594B (en) | Method for accurately identifying and positioning abnormal variable | |
Wise et al. | Process chemometrics | |
CN112149054B (en) | Construction and application of orthogonal neighborhood preserving embedding model based on time sequence expansion | |
CN110033175B (en) | Soft measurement method based on integrated multi-core partial least square regression model | |
CN113191614B (en) | Polypropylene product quality real-time monitoring method based on slow characteristic regression analysis | |
CN113253682B (en) | Nonlinear chemical process fault detection method | |
CN111914886B (en) | Nonlinear chemical process monitoring method based on online brief kernel learning | |
Deng et al. | Fault relevant variable selection for fault diagnosis | |
CN113191616B (en) | Polypropylene product quality abnormity detection method based on double-layer correlation characteristic analysis | |
JP2010141042A (en) | Control system, control method and control program for process treatment apparatus, and program recording medium | |
CN113205121B (en) | Primary tower sampling data coarse difference discrimination method based on local characteristic anomaly factors | |
CN111914210B (en) | Complex chemical process state monitoring method based on correlation characteristic analysis |
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 |