CN108226093B - Automatic model parameter selection and correction method for atmospheric and vacuum device - Google Patents
Automatic model parameter selection and correction method for atmospheric and vacuum device Download PDFInfo
- Publication number
- CN108226093B CN108226093B CN201810026959.0A CN201810026959A CN108226093B CN 108226093 B CN108226093 B CN 108226093B CN 201810026959 A CN201810026959 A CN 201810026959A CN 108226093 B CN108226093 B CN 108226093B
- Authority
- CN
- China
- Prior art keywords
- crude oil
- model parameters
- atmospheric
- newly processed
- model
- 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 32
- 238000012937 correction Methods 0.000 title claims abstract description 10
- 239000010779 crude oil Substances 0.000 claims abstract description 113
- 238000012545 processing Methods 0.000 claims abstract description 26
- 238000004088 simulation Methods 0.000 claims abstract description 14
- 238000005292 vacuum distillation Methods 0.000 claims abstract description 14
- 238000002835 absorbance Methods 0.000 claims description 10
- 230000003595 spectral effect Effects 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 5
- 238000011156 evaluation Methods 0.000 claims description 5
- 238000002329 infrared spectrum Methods 0.000 claims description 5
- 238000001228 spectrum Methods 0.000 claims description 5
- 150000001875 compounds Chemical class 0.000 claims description 2
- 230000006837 decompression Effects 0.000 claims description 2
- 238000012163 sequencing technique Methods 0.000 claims description 2
- 238000005259 measurement Methods 0.000 claims 1
- 238000012847 principal component analysis method Methods 0.000 claims 1
- 238000005457 optimization Methods 0.000 abstract description 8
- 230000008901 benefit Effects 0.000 abstract description 5
- 238000007670 refining Methods 0.000 abstract description 4
- 238000000513 principal component analysis Methods 0.000 abstract description 3
- 238000012216 screening Methods 0.000 abstract description 3
- 238000012423 maintenance Methods 0.000 abstract description 2
- 238000000605 extraction Methods 0.000 description 4
- 238000010992 reflux Methods 0.000 description 3
- IJGRMHOSHXDMSA-UHFFFAOYSA-N Atomic nitrogen Chemical compound N#N IJGRMHOSHXDMSA-UHFFFAOYSA-N 0.000 description 2
- 238000007664 blowing Methods 0.000 description 2
- 230000001186 cumulative effect Effects 0.000 description 2
- 239000003921 oil Substances 0.000 description 2
- ASNHGEVAWNWCRQ-UHFFFAOYSA-N 4-(hydroxymethyl)oxolane-2,3,4-triol Chemical compound OCC1(O)COC(O)C1O ASNHGEVAWNWCRQ-UHFFFAOYSA-N 0.000 description 1
- 241000183024 Populus tremula Species 0.000 description 1
- NINIDFKCEFEMDL-UHFFFAOYSA-N Sulfur Chemical compound [S] NINIDFKCEFEMDL-UHFFFAOYSA-N 0.000 description 1
- 239000002253 acid Substances 0.000 description 1
- 239000008186 active pharmaceutical agent Substances 0.000 description 1
- 238000002156 mixing Methods 0.000 description 1
- 238000012821 model calculation Methods 0.000 description 1
- 229910052757 nitrogen Inorganic materials 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 229910052717 sulfur Inorganic materials 0.000 description 1
- 239000011593 sulfur Substances 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
- G01N21/31—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry
- G01N21/35—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light
- G01N21/359—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light using near infrared light
Abstract
The invention discloses an atmospheric and vacuum distillation unit model parameter automatic selection and correction method, which is based on a crude oil historical processing database, and comprises the steps of firstly, performing principal component analysis on crude oil data, and preliminarily screening out a plurality of similar samples of newly processed crude oil; then, matching of newly processed crude oil is completed from similar samples based on the weighted Euclidean distance, and parameters of the model are automatically selected according to the historical processing scheme of the matched crude oil; and finally, performing device simulation and comparing with the measured value, judging whether the selected model parameters are suitable for the current working condition, and if not, correcting the model parameters. The method not only improves the speed of determining the model parameters, but also reduces the workload of manual maintenance. The accurate device model provides a basis for subsequent optimization, and has important application value for improving the economic benefit of the refining enterprise.
Description
Technical Field
The invention relates to the technical field of device simulation in the field of petrochemical industry, in particular to a method for automatically selecting parameters for a model of an atmospheric and vacuum device and correcting the parameters.
Background
The atmospheric and vacuum distillation device is a faucet device of an oil refining enterprise, and the operation optimization of the atmospheric and vacuum distillation device has great influence on the overall benefit of the enterprise. Before operation optimization, enterprises usually simulate the device through process simulation software such as Aspen Plus, Petro-SIM and the like so as to obtain an accurate model and perform operation optimization. Therefore, the accurate model is an important prerequisite for atmospheric and vacuum optimization.
The device parameters represented by the tower plate efficiency characterize the separation performance of the atmospheric and vacuum device, and directly influence the quality of products and the accuracy of model calculation. The tray efficiency is closely related to the crude oil property, and parameters such as the tray efficiency and the like are often required to be reset after the atmospheric and vacuum distillation unit is replaced with different crude oils. In addition, even if the same crude oil is processed, tray efficiency changes due to changes in operating time and the like, and model parameters need to be appropriately adjusted.
Therefore, how to efficiently and accurately determine the model parameters of the atmospheric and vacuum distillation unit realizes the optimized operation of the unit and has great significance for improving the benefits of the refining and chemical enterprises.
Disclosure of Invention
Aiming at the problems, the invention establishes a method for automatically selecting and correcting model parameters of an atmospheric and vacuum distillation unit based on a crude oil historical processing database, and adopts the following technical scheme:
the invention is based on a crude oil historical processing database, automatically selects model parameters for newly processed crude oil, and corrects the model parameters according to the simulation result and the measured value of the device, and comprises the following steps:
the method includes the steps that an enterprise crude oil historical processing database is established, and crude oil rapid evaluation data, near infrared spectrum data and historical processing schemes are included;
secondly, searching m approximate samples of the newly processed crude oil based on the crude oil rapid evaluation data and the near infrared spectrum data;
selecting matched crude oil of the newly processed crude oil from the approximate sample, and automatically selecting model parameters for the newly processed crude oil according to the historical processing scheme of the matched crude oil;
fourthly, simulating an atmospheric and vacuum device according to the model parameters, judging whether the selected model parameters are suitable for the current working condition, if so, storing the model parameters and the corresponding working condition into a crude oil historical processing database and turning to the step (7), and if not, turning to the step (5);
correcting the model parameters based on the measured values;
storing the corrected model parameters and the corresponding working conditions into a crude oil historical processing database;
and completing the configuration of the parameters of the model of the night-time decompression device.
The method adopts principal component analysis to perform dimensionality reduction on spectral data of crude oil in a crude oil historical processing library and newly processed crude oil, selects the first n principal components with the cumulative contribution rate exceeding 85%, respectively calculates Euclidean distances between the newly processed crude oil and crude oil samples in the database, sorts the Euclidean distances from small to large, selects the first m samples as similar samples of the newly processed crude oil, and adopts the following formula for calculation:
in the formula (d)0pThe Euclidean distance between the newly processed crude oil and the crude oil p in the reservoir; x is the number of0qDenotes the qth principal component score, x, of the freshly processed crude oilpq(ii) a qth principal score representing crude p in the pool; q is the number of principal components, q is 1, 2.
The method comprises the steps of respectively calculating weighted Euclidean distances between m similar samples and newly processed crude oil based on the spectrum data after dimensionality reduction, selecting the similar crude oil with the minimum distance as the matched crude oil of the newly processed crude oil, and calculating by adopting the following formula:
in the formula (I), the compound is shown in the specification,
the spectral distance between the newly processed crude oil and the jth similar crude oil is taken as the spectral distance; qiRepresenting the absorbance weight of the crude oil at a characteristic wavenumber i; a. the0iRepresenting the absorbance of the freshly processed crude oil at a characteristic wavenumber i; a. thejiRepresents the absorbance of the j-th similar crude oil at a characteristic wavenumber i, j being 1, 2. k is a constant used to amplify the calculation results for comparison.
The method compares the simulation result with the measured value, if the deviation is in the allowable range, the selected model parameter is suitable for the current working condition, otherwise, the parameter of the model of the atmospheric and vacuum device is corrected.
The method uses the least square sum of the deviation square of the measured value and the analog value as a target, and calculates the correction value of the parameter by adopting a least square method.
Preferably, in the method for screening similar crude oils based on Euclidean distance, the number m of the similar crude oils of the newly processed crude oil is generally determined as 5.
Has the advantages that:
the method is based on the crude oil historical processing database, and completes automatic selection and correction of the model parameters of the atmospheric and vacuum distillation unit according to the properties of the newly processed crude oil and instrument data. The method not only improves the speed of determining the model parameters, but also reduces the workload of manual maintenance. The accurate device model provides a basis for subsequent optimization, and has important application value for improving the economic benefit of the refining enterprise.
Drawings
FIG. 1 is a flow chart of an implementation of a method for automatically selecting and correcting model parameters of an atmospheric and vacuum device.
Detailed description of the preferred embodiment
The following detailed computing process and specific operation flow are given in conjunction with the accompanying drawings and specific examples to further explain the present 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.
In this case, the atmospheric tower in a 5# atmospheric pressure reduction device of a certain refinery is taken as an example to complete automatic selection and correction of model parameters of the atmospheric tower device, and the number of tower plates of the atmospheric tower is 56. The implementation flow is shown in fig. 1, and the specific implementation steps are as follows:
establishing a historical processing database of crude oil
The historical processing database of crude oil of the refinery is stored with historical crude oil data which are frequently refined, and comprises crude oil property data, spectrum data and historical crude oil processing schemes which are obtained by a crude oil rapid evaluation method. Besides a few single crude oil processing schemes, other crude oil mixing modes are basically adopted. The variety and main property data of crude oil normally refined by the No. 5 atmospheric and vacuum distillation unit are shown in the table 1:
TABLE 15 # atmospheric and vacuum unit atmospheric crude oil property data
| Serial number | Oil seed name | Density of | API | Sulfur content | Acid value | Nitrogen content |
| 1 | Kowitt | 865.2 | 31.3 | 2.52 | 0.09 | 0.12 |
| 2 | Barken | 806.9 | 42.96 | 0.11 | 0.33 | 0.06 |
| 3 | Maya | 921.5 | 21.4 | 3.41 | 0.18 | 0.46 |
| 5 | Soxhlet | 933.7 | 19.4 | 3.56 | 0.53 | 0.31 |
| 6 | Sapino | 894.5 | 26 | 0.76 | 0.95 | 0.26 |
| 7 | Oruit (R) form | 900.8 | 24.9 | 1.13 | 0.14 | 0.31 |
| 8 | South pascal | 741.9 | 58 | 0.28 | 0.07 | 0 |
| 9 | Yigan (Chinese character of 'yi gan') | 874.4 | 29.59 | 1.9 | 0.15 | 0.28 |
| 10 | Jenno | 887 | 27.32 | 0.36 | 0.54 | 0.37 |
| 11 | Saiba | 868.4 | 30.7 | 0.46 | 0.8 | 0.15 |
| 12 | Wushan mountain | 875.5 | 29.39 | 0.29 | 1.27 | 0.21 |
| 13 | Sitexas light | 820 | 40.2 | 0.29 | 0.09 | 0.08 |
In addition, the historical processing scheme of the 5# atmospheric and vacuum device is shown in table 2:
TABLE 25 # atmospheric and vacuum unit historical crude oil processing scheme
Screening of crude oil in a two-stage manner
Taking newly processed crude oil of 5, 8 and 2017 as an example, firstly, performing principal component analysis on near infrared spectrum data of the crude oil and historical processed crude oil, adopting a traditional method such as MATLAB and the like, finding that the cumulative contribution rate of the first 3 principal components exceeds 85%, selecting the first 3 principal components of the crude oil and the newly processed crude oil spectrum data in a library, calculating the Euclidean distance between the crude oil in the library and the current newly processed crude oil spectrum data, sequencing the distances from small to large, and selecting the first 5 principal components as similar samples of the newly processed crude oil (namely, the m value is 5).
Table 3 lists the numbers of 5 similarly processed crudes.
Table 3 list of similarly processed crude oils
| BC05 | BC07 | BC14 | BC17 | BC23 |
Matching of crude oil and determination of model parameters
Since different characteristic wavenumbers differ in the degree of importance to reflect crude oil properties, absorbance is given different weights at certain wavenumber intervals. Table 4 lists the absorbance weights in the weighted euclidean distance method of this case.
TABLE 4 Absorbance weights for different wavenumber ranges
| Wave number range | Absorbance weight |
| 4000～4200 | 0.005 |
| 4200～4440 | 0.003 |
| 4440～4800 | 0.008 |
The weighted euclidean distance calculation is of a small magnitude and is therefore multiplied by a constant k, where k is 1.0 x 10, to amplify it for comparison4. The spectral distances of the similar crude oils from the freshly processed crude oils were calculated one by one and the results are shown in table 5.
TABLE 5 similar crude oil numbering and distances
| Crude oil numbering | Distance between two adjacent plates |
| BC14 | 5.54 |
| BC23 | 5.90 |
| BC05 | 6.41 |
| BC07 | 7.04 |
| BC17 | 8.35 |
As can be seen from Table 5, the historical processed crude oil with the number BC14 has the highest similarity with the current newly processed crude oil, and the crude oil with the number BC14 consists of a mixed crude oil of two crude oils of Yimu and Nanpa, and the proportion is 95%: 5 percent. Based on the crude's historical processing scheme, table 6 lists the tray efficiency parameters for the newly processed crude.
TABLE 6 column plate efficiency parameters for freshly processed crude oil
| Number of plates | 1 | 2～4 | 5～18 | 19～21 | 22～32 | 33～34 | 35～42 | 43～51 | 52～56 |
| Murphree efficiency | 1 | 0.55 | 0.8 | 0.5 | 0.75 | 0.45 | 0.7 | 0.65 | 0.9 |
Wherein the 1 st tray is a condenser and the tray efficiency is set to 1.
Device simulation and parameter verification
The model parameters are input into the atmospheric tower model for simulation, and table 7 details the upper and lower limit ranges of the control index of the atmospheric tower device, the device simulation value, the measured value of the field instrument, and the deviation between the simulation value and the measured value.
Comparison of simulated 75/8/th day with measured
| Serial number | Name of item | Unit of | Lower limit of the range | Upper limit of the range | Analog value | Measured value | Deviation of |
| 1 | Atmospheric overhead temperature | ℃ | 126 | 149 | 144.8 | 145.5 | -0.7 |
| 2 | Constant line flow | t/h | 110 | 180 | 172.3 | 169.5 | 2.8 |
| 3 | Normal three-wire flow | t/h | 100 | 150 | 116.9 | 119.6 | -2.7 |
| 4 | Flow rate of constant top reflux | t/h | 48 | 141 | 105.5 | 103.2 | 2.3 |
| 5 | Blowing amount at bottom of atmospheric tower | t/h | 8.5 | 13.8 | 9.8 | 9.5 | 0.3 |
| 6 | Normal line draw off temperature | ℃ | 150 | 225 | 200.8 | 199.8 | 1.0 |
| 7 | Normal second line extraction temperature | ℃ | 160 | 280 | 261.2 | 260.0 | 1.2 |
| 8 | Temperature of normal temperature of wire | ℃ | 250 | 330 | 322.5 | 321.4 | 1.1 |
As can be seen from Table 7, the simulation value is within the constraint range of the control index, the temperature parameter deviation is less than 2 ℃, the flow deviation is less than 3t/h, the precision requirement of the device simulation is completely met, and the model can be used for operation optimization. And at this time, completing the configuration of the model parameters of the atmospheric tower.
Operation and parameter correction of device fifth
As described above, the model parameters of the atmospheric and vacuum distillation apparatus, which are represented by the tray efficiency, are closely related to the properties of crude oil, but the tray efficiency is also affected by other factors such as the operation time of the apparatus. Taking the processing condition of the device in 2017, 11 and 18 days as an example, the crude oil processed in the same day is completely the same as that processed in 5 and 8 days, and after simulation is carried out by adopting model parameters in a historical library, a relevant result comparison is given in table 8.
Comparison of Table 811 simulated 18-month-day values with actual measured values
| Serial number | Name of item | Unit of | Lower limit of the range | Upper limit of the range | Analog value | Measured value | Deviation of |
| 1 | Atmospheric overhead temperature | ℃ | 126 | 149 | 147.8 | 148.8 | -1.0 |
| 2 | Constant line flow | t/h | 110 | 180 | 172.3 | 167.2 | 5.1 |
| 3 | Normal three-wire flow | t/h | 100 | 150 | 131.9 | 140.4 | -8.5 |
| 4 | Flow rate of constant top reflux | t/h | 48 | 141 | 105.5 | 102.3 | 3.2 |
| 5 | Blowing amount at bottom of atmospheric tower | t/h | 8.5 | 13.8 | 9.8 | 9.5 | 0.3 |
| 6 | Normal line draw off temperature | ℃ | 150 | 225 | 200.8 | 197.8 | 3.0 |
| 7 | Normal second line extraction temperature | ℃ | 160 | 280 | 261.2 | 257.9 | 3.3 |
| 8 | Temperature of normal temperature of wire | ℃ | 250 | 330 | 322.5 | 320.6 | 1.9 |
As can be seen from Table 8, the error between the normal first line extraction temperature and the normal second line extraction temperature exceeds 2 ℃, and the deviation between the normal first line flow, the normal third line flow and the normal top reflux flow exceeds 3 t/h. The deviation between the measured value and the analog value of the main parameters of the atmospheric tower is considered to be large, and the tower plate efficiency needs to be corrected.
And (3) adjusting the tower plate efficiency by adopting a traditional least square method based on an MATLAB platform and taking the minimum deviation square sum of the measured value and the analog value as a target. The adjusted tray efficiencies are shown in Table 9.
TABLE 9 column plate efficiency after adjustment
| Number of plates | 1 | 2～4 | 5～18 | 19～21 | 22～32 | 33～34 | 35～42 | 43～51 | 52～56 |
| Murphree efficiency | 1 | 0.55 | 0.75 | 0.45 | 0.7 | 0.4 | 0.65 | 0.6 | 0.9 |
After the parameters are corrected, the deviation between the main parameter value and the measured value of the 5# atmospheric tower device simulation is returned to the allowable range again, and the deviation can be used for subsequent optimization of the device.
Claims (6)
1. An atmospheric and vacuum distillation unit model parameter automatic selection and correction method is characterized in that model parameters are automatically selected for newly processed crude oil based on a crude oil historical processing database, and the model parameters are corrected according to a device simulation result and an actual measurement value, and the method comprises the following steps:
the method includes the steps that an enterprise crude oil historical processing database is established, and crude oil rapid evaluation data, near infrared spectrum data and historical processing schemes are included;
secondly, searching m approximate samples of the newly processed crude oil based on the crude oil rapid evaluation data and the near infrared spectrum data;
selecting the matched crude oil of the newly processed crude oil from the approximate sample, and taking the model parameter of the historical processing scheme of the matched crude oil as the model parameter of the newly processed crude oil;
fourthly, simulating an atmospheric and vacuum device of the newly processed crude oil according to the model parameters, judging whether the selected model parameters are suitable for the current working condition, if so, storing the model parameters and the corresponding working condition into a crude oil historical processing database and turning to (7), otherwise, turning to (5);
correcting the model parameters based on the measured values;
storing the corrected model parameters and the corresponding working conditions into a crude oil historical processing database;
and completing the configuration of the parameters of the model of the night-time decompression device.
2. The method for automatically selecting and correcting the model parameters of the atmospheric and vacuum distillation unit as claimed in claim 1, wherein in the step (2), the spectral data of the crude oil in the crude oil historical processing library and the newly processed crude oil are subjected to dimensionality reduction by a principal component analysis method: selecting the first n main components with the accumulated contribution rate exceeding 85%, respectively calculating Euclidean distances between newly processed crude oil and crude oil samples in a database, sequencing the newly processed crude oil and the crude oil samples from small to large, selecting the first m samples as similar samples of the newly processed crude oil, and calculating by adopting the following formula:
in the formula (I), the compound is shown in the specification,
the Euclidean distance between the newly processed crude oil and the crude oil p in the reservoir;
denotes the qth principal component score, x, of the freshly processed crude oilpq(ii) a qth principal score representing crude p in the pool; q is the number of principal components, q is 1, 2.
3. The method for automatically selecting and correcting model parameters of an atmospheric and vacuum distillation unit as claimed in claim 2, wherein the weighted Euclidean distances between m similar samples and the newly processed crude oil are calculated respectively based on the spectrum data after dimensionality reduction, the similar crude oil with the smallest distance is selected as the matching crude oil of the newly processed crude oil, and the calculation is performed by adopting the following formula:
of formula (II) to'0jThe spectral distance between the newly processed crude oil and the jth similar crude oil is taken as the spectral distance; qiRepresenting the absorbance weight of the crude oil at a characteristic wavenumber i; a. the0iRepresenting the absorbance of the freshly processed crude oil at a characteristic wavenumber i; a. thejiRepresents the absorbance of the j-th similar crude oil at a characteristic wavenumber i, j being 1, 2. k is a constant used to amplify the calculation results for comparison.
4. The method for automatically selecting and correcting the model parameters of the atmospheric and vacuum relief device according to claim 1, wherein the step (4) is a method for verifying whether the selected model parameters are suitable for the current working condition: and comparing the simulation result with the measured value, if the deviation is within the allowable range, the selected model parameter is suitable for the current working condition, and otherwise, correcting the parameter of the model of the atmospheric and vacuum device.
5. The method for automatically selecting and correcting the model parameters of the atmospheric and vacuum distillation unit as claimed in claim 1, wherein the parameter correction method in step (5) comprises the following steps: and calculating the correction value of the parameter by adopting a least square method by taking the minimum deviation square sum of the measured value and the analog value as a target.
6. The method for automatically selecting and correcting model parameters of an atmospheric and vacuum distillation unit as claimed in claim 1, wherein the determination of the number m of similar crude oils is screened, and the value m is selected to be 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810026959.0A CN108226093B (en) | 2018-01-11 | 2018-01-11 | Automatic model parameter selection and correction method for atmospheric and vacuum device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810026959.0A CN108226093B (en) | 2018-01-11 | 2018-01-11 | Automatic model parameter selection and correction method for atmospheric and vacuum device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108226093A CN108226093A (en) | 2018-06-29 |
| CN108226093B true CN108226093B (en) | 2021-05-28 |
Family
ID=62640906
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810026959.0A Active CN108226093B (en) | 2018-01-11 | 2018-01-11 | Automatic model parameter selection and correction method for atmospheric and vacuum device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108226093B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109781967A (en) * | 2019-03-20 | 2019-05-21 | 杭州辛孚能源科技有限公司 | A kind of crude oil cutting calculations analysis method |
| CN112686430B (en) * | 2020-12-16 | 2024-02-23 | 南京富岛信息工程有限公司 | Method for improving accuracy of product yield model of refining enterprise device |
| CN112947325B (en) * | 2021-01-28 | 2022-11-08 | 南京富岛信息工程有限公司 | Storage tank dynamic scheduling method for crude oil blending |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103364364A (en) * | 2013-07-01 | 2013-10-23 | 南京富岛信息工程有限公司 | Crude oil property rapid detection method based on recombination prediction technology |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP4693225B2 (en) * | 2000-11-06 | 2011-06-01 | 株式会社東芝 | Manufacturing line automatic quality control method and apparatus, storage medium, and automatic quality control program |
| US20120298553A1 (en) * | 2011-05-27 | 2012-11-29 | Lyondell Chemical Company | Predicting petroleum coke morphology from feedstock properties |
| CN102520705B (en) * | 2011-12-31 | 2014-11-26 | 中国石油天然气股份有限公司 | Refining production process optimal analysis method and system |
| CN103150452B (en) * | 2013-03-26 | 2016-02-24 | 上海优华系统集成技术有限公司 | A kind of Atmospheric vacuum reference energy consumption computing method based on process simulation software |
| CN105717067B (en) * | 2016-05-03 | 2019-01-04 | 哈尔滨珍宝制药有限公司 | The automatic control system and method that Radix Notoginseng is quantitatively extracted |
| CN106770015B (en) * | 2017-01-10 | 2020-12-15 | 南京富岛信息工程有限公司 | Oil product property detection method based on principal component analysis similarity discrimination |
-
2018
- 2018-01-11 CN CN201810026959.0A patent/CN108226093B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103364364A (en) * | 2013-07-01 | 2013-10-23 | 南京富岛信息工程有限公司 | Crude oil property rapid detection method based on recombination prediction technology |
Non-Patent Citations (2)
| Title |
|---|
| 原油蒸馏装置的在线模拟、修正与优化;侯凯锋 等;《石油炼制与化工》;19991031;第30卷(第10期);第31页左栏 4、模型参数修正 * |
| 模糊聚类分析在依原油特性归类中的应用;王景芳;《石油炼制》;19911231(第6期);摘要，第41页前言，第43页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108226093A (en) | 2018-06-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108226093B (en) | Automatic model parameter selection and correction method for atmospheric and vacuum device | |
| AU2005277244B2 (en) | Refinery crude unit performance monitoring using advanced analytic techniques for raw material quality prediction | |
| CN104990894B (en) | A kind of gasoline property detection method based on weighting absorbance and similar sample | |
| CN106644983B (en) | Spectral wavelength selection method based on PLS-VIP-ACO algorithm | |
| CN106408423A (en) | Method and system for risk assessment and method for constructing system for risk assessment | |
| CN103886168A (en) | Multi-channel analysis method and device based on analytic hierarchy process | |
| CN109324014B (en) | Self-adaptive near-infrared rapid prediction method for crude oil properties | |
| CN102799772A (en) | Air quality forecast oriented sample optimization method | |
| CN101201331B (en) | Soft measuring method for on-line determining petroleum naphtha quality index on top of primary tower | |
| CN101169387B (en) | Soft sensing method for on-line determination of atmospheric tower top naphtha quality index | |
| CN106770015A (en) | A kind of oil property detection method based on the similar differentiation of principal component analysis | |
| CN110751213B (en) | Method for identifying and supplementing abnormal wind speed data of wind measuring tower | |
| CN105138824B (en) | A kind of crude data bearing calibration towards atmospheric and vacuum distillation unit optimization | |
| CN113420500B (en) | Intelligent atmospheric and vacuum system | |
| CN111892939B (en) | Crude oil distillation cutting method, system, equipment and storage medium | |
| CN112686430B (en) | Method for improving accuracy of product yield model of refining enterprise device | |
| CN111494988B (en) | Deep learning-based crude oil storage tank water cutting method and equipment | |
| CN108985336A (en) | A kind of fruit quality classification method based on multi-layer SVM | |
| CN111044482B (en) | Crude oil blending method | |
| CN109724938B (en) | Method for predicting properties of lubricating oil base oil by near infrared spectrum | |
| CN110619176A (en) | Aviation kerosene flash point prediction method based on DBN-RLSSVM | |
| CN110648023A (en) | Method for establishing data prediction model based on quadratic exponential smoothing improved GM (1,1) | |
| CN105574345B (en) | Oil property data correcting method | |
| CN113723015A (en) | Catalytic cracking unit optimization method based on mechanism model and big data technology | |
| CN105866062A (en) | Temperature correction method for gasoline near-infrared spectrum |
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 |