Disclosure of Invention
The invention aims to provide a hydrogen distribution prediction method and a hydrogen distribution prediction device for an oil refining production device, which couple the mathematical modeling of commercial process simulation software and necessary laboratory test analysis, combine the production practice of a refinery plant, associate with the main operation conditions of the device, and fully utilize the production operation data of the device to carry out model training so as to achieve the purposes of improving the accuracy and extrapolation of model calculation and optimizing the operation of the device.
In order to achieve the above object, according to a first aspect of the present invention, there is provided a hydrogen distribution prediction method for an oil refinery production apparatus, comprising the steps of: A. determining the device type, working condition and key operation parameters, and determining the raw material, product type and material parameter information; B. establishing a device model through process simulation software to obtain hydrogen content simulation calculation data of raw materials and products under different working conditions; C. sampling experiment analysis is carried out on raw materials and products under a limited set of working conditions, and hydrogen content experiment test data is obtained; D. fitting and correcting the experimental test data of the hydrogen content and the analog calculation data of the hydrogen content under a limited set of working conditions aiming at an oil-phase product in the product to obtain corrected hydrogen content data; E. aiming at oil phase products, carrying out regression fitting by using the corrected hydrogen content data, the material parameter information of the raw oil and key operation parameters to obtain a device hydrogen distribution prediction model as follows:
wherein, Ff,iFeeding the device with i flow rate, t/h; f. ofHf,iM% is the hydrogen content of feed stream i; fp,jThe flow rate of a product j of the device is t/h; f. ofHp,jM% is the hydrogen content of product stream j; t isvFeeding the device with volume average boiling point, K; ρ is the feed density, kg/m 3; s is the feed sulfur content, m%; n is a radical ofM% as feed nitrogen content; t is the reaction temperature of the device, K; p is the reaction pressure of the device, MPa; a isj、bj、cj、dj、ej、 A1,j、A2,j、B1,jAre model coefficients.
Further, in the above technical solution, the correction in step D specifically adopts a correction model as follows:
wherein f isH, practice ofM% for experimental determination of hydrogen content in the stream; i is a power exponent; f. ofH, simulationM% of the hydrogen content in the stream calculated for the simulation; a. theiB is a coefficient; n in the formula (4) is less than or equal to 6;
f obtained by analogue calculation under a finite set of operating conditionsH, simulationAnd experimentally determined fH, practice ofCalculation of AiAnd b, further obtaining a universal correction model aiming at the same device, and then calculating corrected hydrogen content data.
Further, in the above technical solution, the apparatus in step a includes an atmospheric and vacuum distillation apparatus, a continuous reforming apparatus, a catalytic cracking apparatus, a delayed coking apparatus, a solvent deasphalting apparatus, various hydrorefining apparatuses, various hydroupgrading apparatuses, and various hydrocracking apparatuses.
Further, in the above technical scheme, the working condition in the step a is a production condition corresponding to the device within a period of time when the types of the main crude oil are the same.
Further, in the above technical scheme, the key operating parameters in step a mainly include reaction temperature and pressure.
Further, in the above technical solution, the material parameter information in step a mainly includes: density, distillation range, S content, N content of the liquid phase material and molecular composition of the gas phase material.
Further, in the above technical solution, the flow simulation software in step B is Hysys or PetroSim software; the method also comprises the step of checking the device model established by the software.
Further, in the above technical solution, the sampling experiment analysis in the step C specifically includes: 1 to 10 groups of samples in the same time period are taken under each working condition; and analyzing the liquid phase material by adopting a mass spectrum or hydrogen element tester, and analyzing the gas phase material by adopting molecular composition.
Further, in the above technical scheme, the method of fitting the hydrogen content experimental test data and the hydrogen content analog calculation data under a limited set of working conditions in step D adopts a least square method; the fitted tool was Excel, Matlab or Origin.
Further, in the above technical solution, the formula (1) in the step E is a material balance formula, and the material balance is corrected by calculating the flow rate of the product j of the device and comparing the flow rate with the flow rate of the known feed i of the device.
Further, in the above technical solution, the formula (2) in the step E is a hydrogen balance formula, and the hydrogen balance is corrected by calculating the product hydrogen content and comparing with the known feed hydrogen content.
Further, in the above technical solution, the model coefficient in the formula (3) is calculated by regression fitting in the step E, thereby obtaining the hydrogen distribution prediction model of a general structure.
In order to achieve the above object, according to a second aspect of the present invention, there is provided a hydrogen distribution prediction apparatus for an oil refinery apparatus, comprising: the basic information preparation module is used for determining the device type, the working condition and the key operation parameters and determining the raw material, the product type and the material parameter information; the simulation calculation data acquisition module is used for establishing a device model through process simulation software to acquire hydrogen content simulation calculation data of raw materials and products under different working conditions; the experimental test data acquisition module is used for sampling experimental analysis on the raw materials and the products under a limited set of working conditions to obtain experimental test data of hydrogen content; the correction data acquisition module is used for fitting and correcting the hydrogen content experiment test data and the hydrogen content simulation calculation data under a limited set of working conditions aiming at the oil phase product in the product to obtain corrected hydrogen content data; and the hydrogen distribution prediction model acquisition module is used for carrying out regression fitting on the oil phase product by utilizing the corrected hydrogen content data, the material parameter information of the raw oil and the key operation parameters to obtain a device hydrogen distribution prediction model.
In order to achieve the above object, according to a third aspect of the present invention, there is provided a memory including an instruction set adapted to a processor for executing the steps of the method for predicting hydrogen distribution in a refinery apparatus as described above.
In order to achieve the above object, according to a fourth aspect of the present invention, there is provided a hydrogen distribution prediction apparatus for an oil refinery apparatus, comprising a bus, an input device, an output device, a processor, and a memory as described above; the bus is used for connecting the memory, the input device, the output device and the processor; the input device and the output device are used for realizing interaction with a user; the processor is configured to execute a set of instructions in the memory.
Compared with the prior art, the invention has the following beneficial effects:
1) according to the invention, the hydrogen content of the gas phase product and the liquefied gas is calculated according to the actual molecular composition; calculating the hydrogen content of the liquid-phase product by adopting a hydrogen distribution model, and performing related calculation only by knowing the properties of the raw materials of the device and the operating conditions; the laboratory measurement data is adopted to represent solid phase products or loss, and the hydrogen content of gas, liquid and solid products can be accurately predicted by combining the experimental and model calculation data;
2) according to the invention, the material balance judgment and correction and the hydrogen balance judgment and correction are added in the hydrogen distribution prediction model, so that the larger deviation caused by directly adopting real-time data of production operation and the unbalance amount of the device is effectively avoided, and the prediction accuracy is more effectively ensured;
3) the invention couples the mathematical modeling of the commercial process simulation software and the necessary laboratory test analysis, combines the production practice of the refinery, performs mathematical association with the conventional analysis items and the main operation conditions of the device, and fully utilizes the production operation data of the device to perform model training, thereby achieving the purposes of improving the accuracy and the extrapolation of model calculation and optimizing the operation of the device.
Other features and aspects of the present invention will become apparent from the following detailed description of exemplary embodiments, which proceeds with reference to the accompanying drawings.
Detailed Description
The following detailed description of the present invention is provided in conjunction with the accompanying drawings, but it should be understood that the scope of the present invention is not limited to the specific embodiments.
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be obtained by a person skilled in the art without any inventive step based on the embodiments of the present invention, are within the scope of the present invention. Throughout the specification and claims, unless explicitly stated otherwise, the word "comprise", or variations such as "comprises" or "comprising", will be understood to imply the inclusion of a stated element or component but not the exclusion of any other element or component.
The word "exemplary" is used exclusively herein to mean "serving as an example, embodiment, or illustration. Any embodiment described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other embodiments.
Furthermore, in the following detailed description, numerous specific details are set forth in order to provide a better understanding of the present invention. It will be understood by those skilled in the art that the present invention may be practiced without some of these specific details. In some instances, methods, means, elements well known to those skilled in the art have not been described in detail so as not to obscure the present invention.
Example 1
As shown in fig. 1, the method for predicting hydrogen distribution in an oil refinery production apparatus according to embodiment 1 of the present invention includes the following steps:
step S101, basic information preparation is performed, that is: determining the device type, working condition and key operation parameters, and determining the raw material, product type and material parameter information.
The device mainly refers to a main device in an oil refining process, and the device types comprise an atmospheric and vacuum device, a continuous reforming device, a catalytic cracking device, a delayed coking device, a solvent deasphalting device, various hydrofining devices, various hydro-upgrading devices, various hydrocracking devices and the like. The working condition mainly refers to the corresponding production condition of the device when the types of main crude oil processed by the refinery are the same within a period of time (for example, within one year).
Key operating parameters can be classified into the following categories: for the atmospheric and vacuum device, the temperature at the outlet of the atmospheric heating furnace, the drawing rate of the device and the like are mainly indicated; for continuous reformers, it is mainly the reforming reaction temperature, pressure, etc.; for a catalytic cracking unit, the reaction temperature, space velocity, residence time and the like are mainly referred to; for various hydrogenation devices, the reaction temperature, the hydrogen partial pressure and the like are mainly referred; for a delayed coker, the reaction temperature, pressure, recycle ratio, etc. are referred to primarily. The key operating parameters used in this embodiment are primarily reaction temperature and pressure.
The raw material and product types mainly mean that the device feeding comprises single feeding or multiple feeding, and the product types comprise one or more of dry gas, liquefied gas, gasoline, aviation kerosene, diesel oil, wax oil, residual oil and coke.
The material parameter information mainly comprises: density, distillation range, S content, N content, etc. of liquid phase material and molecular composition of gas phase material. The raw material and product information of devices such as atmospheric and vacuum, catalysis and coking are universal, namely oil phase materials relate to flow, relative density, distillation range, sulfur content and nitrogen content (except liquefied gases, liquefied gas fractions generally refer to molecular composition analysis data), gas phase materials relate to flow and molecular composition analysis data, and solid phase products relate to yield and hydrocarbon element content data. For example, the raw material of the atmospheric and vacuum distillation unit is crude oil or a mixed feed of several kinds of crude oil, the flow rate, relative density, distillation range, sulfur content and nitrogen content of the raw material need to be determined in this embodiment, and the product mainly comprises gas-phase products (including initial overhead gas, atmospheric overhead gas and reduced overhead gas, and flow rate and molecular composition need to be determined) and liquid-phase distillate oil (flow rate, relative density, distillation range, sulfur content and nitrogen content need to be determined). For another example, the feed to a delayed coking unit includes vacuum residuum, catalytic slurry oil, and the product includes dry gas, liquefied gas, coker gas-diesel, coker gas-oil, and coke, so that the balance of the unit materials, the relative density of the oil phase materials, the distillation range, the sulfur content, and the nitrogen content, the molecular composition of the gas phase materials, and the hydrocarbon composition of the solid phase materials need to be determined.
And S102, establishing a device model through process simulation software, and obtaining the hydrogen content simulation calculation data of the raw materials and the products under different working conditions. The flow simulation software can adopt software such as Hysys or PetroSim. Model investigation and checking are needed after a device model is established through simulation software, and the model investigation mainly refers to the fact that under different working conditions, the influence of changes of main operating parameters on product distribution and hydrogen content distribution is investigated through a model. Modeling of devices by simulation software is conventional in the art and will not be described in detail herein. After the device model is established and checked, the hydrogen content simulation calculation data can be obtained by using the model.
And step S103, carrying out sampling experiment analysis on the raw materials and the products under a limited set of working conditions to obtain hydrogen content experiment test data. The sampling mainly refers to sampling raw materials and products of each device when the refinery mainly processes oil, and 1-10 groups of samples in the same time period are taken in each working condition, preferably 2-3 groups of samples. The experimental analysis mainly comprises the following steps: the gas phase material is analyzed by molecular composition to further determine the hydrogen element content, the liquid phase material is analyzed by mass spectrometry, a hydrogen element analyzer and the like, and preferably the hydrogen element analyzer is used for determining the hydrogen element content. For the product, for an oil phase product, information such as hydrogen content, sulfur content, nitrogen content, density, distillation range and the like is determined by utilizing experimental analysis; for gas phase products and liquefied gas products, the molecular composition of the products is measured in a laboratory; for solid phase products, the laboratory measures the hydrocarbon content.
And step S104, fitting and correcting the hydrogen content experimental test data and the hydrogen content simulation calculation data under a limited set of working conditions aiming at the oil phase product in the product to obtain corrected hydrogen content data. The correction model specifically adopted is as follows:
wherein f isH, practice ofMeasuring the content of hydrogen element m% in the stream for experiment; i is a power exponent; f. ofH, simulationM% of the hydrogen content in the stream calculated for the simulation; a. theiB is a coefficient; n in the formula is less than or equal to 6; in the embodiment, f is obtained through simulation calculation under a finite set of working conditionsH, simulationAnd experimentally determined fH, practice ofCalculation of AiAnd b, further obtaining a universal correction model aiming at the same device, and then calculating corrected hydrogen content data.
In the step, a least square method can be adopted for fitting the hydrogen content experimental test data and the hydrogen content analog calculation data under a limited set of working conditions; the fitting tool may use Excel, Matlab or Origin.
And S105, performing regression fitting on the oil phase product in the step S104 by using the corrected hydrogen content data, the material parameter information of the raw material oil and the key operation parameters to obtain a device hydrogen distribution prediction model. The corrected hydrogen content data mainly refers to the hydrogen element content of the raw material and the product under different operating conditions through simulation calculation in step S102, and the actual hydrogen element content of the raw material and the product after correction is obtained through the correction model obtained in step S104. The device hydrogen distribution prediction model is concretely as follows:
this equation (1) is a material balance equation that can be corrected by calculating the plant product j flow and comparing it to the known plant feed i flow.
This equation (2) is a hydrogen balance equation that can be corrected by calculating the product hydrogen content and comparing it to the known feed hydrogen content.
Wherein, Ff,iFeeding the device with i flow rate, t/h; f. ofHf,iM% is the hydrogen content of feed stream i; fp,jThe flow rate of a product j of the device is t/h; f. ofHp,jM% is the hydrogen content of product stream j; t isvFeeding the device with volume average boiling point, K; ρ is the feed density, kg/m 3; s is the feed sulfur content, m%; n is the feed nitrogen content, m%; t is the reaction temperature of the device, K; p is the reaction pressure of the device, MPa; a isj、bj、cj、dj、ej、 A1,j、A2,j、B1,jAre model coefficients.
T in the hydrogen distribution prediction model of the devicevρ, S, N can be calculated by the following formula:
t10、t30、t50、t70、t90gas phase temperature of 10%, 30%, 50%, 70%, 90% of distillation of raw material mixed feed is measured at DEG C; omegaiMass fraction of feed i to the apparatus; s. theiMass fraction of S in feed i to the apparatus; n is a radical ofiThe mass fraction of N in i is fed to the apparatus.
Specifically, 20-50 groups of samples can be selected in the step, basic property data (namely distillation range, density, S content, N content, flow rate and the like) and temperature T and pressure P of the raw oil are obtained, and for oil phase products, the actual hydrogen content f of each product is calculated through a correction model in the step S104H, practice ofIn the step, the actual hydrogen content data of the oil phase product is used for carrying out data fitting with the basic property data, the temperature T and the pressure P of the raw oil, so as to obtain aj、bj、cj、dj、ej、A1,j、A2,j、B1,jThese model coefficients form a general structural hydrogen distribution prediction model, so that f on the left side of the equation can be calculated by equation (3)Hp,jAnd the hydrogen distribution can be accurately predicted. Here, it should be noted that: if the real-time data of production operation is directly adopted, the unbalance amount of the device can cause larger deviation, so the material balance judgment and correction of the formula (1) and the hydrogen balance judgment and correction of the formula (2) are added in the hydrogen distribution prediction model in the step. The detailed process of calculating the hydrogen distribution using the hydrogen distribution prediction model is shown in fig. 2.
In addition, it should be noted that: under a certain working condition, the final presentation form of the hydrogen distribution prediction model in the step is as follows: gas phase products and liquefied gases-hydrogen content is calculated according to actual molecular composition; the hydrogen content of the liquid-phase product, namely the hydrogen distribution model determined by the model coefficient obtained in the step S105, can be calculated only by knowing the properties of the raw materials of the device and the operating conditions; solid phase production or loss-as indicated by the laboratory test data of step S103. Thus, in this case, if the feed properties of a plant (including: flow, hydrogen content, density, distillation range, S content, N content), the main operating parameters of the plant (temperature T, pressure P), the product distribution (product type, individual product flow, density, distillation range, S content, N content) are known, the hydrogen content calculation for each product can be performed using the final presentation of the aforementioned hydrogen distribution prediction model. If a condition is changed (for example, a crude oil with a property changing greatly), the hydrogen distribution prediction needs to be performed by repeating step S102 and the subsequent steps of the present embodiment.
The following detailed description of the present invention is given by taking the development and application calculation of a hydrogen distribution model of a hydrocracking unit of 180 ten thousand tons/year as an example:
1) device grounding information
The device is designed to process straight-run wax oil raw materials, the products mainly comprise dry gas (all gas phase material flows), liquefied gas, light naphtha, heavy naphtha, aviation kerosene, diesel oil and tail oil, the flow of the device is the prior art, and the detailed description is omitted.
2) Device model establishment through process simulation software
By utilizing Hysys software, a device flow simulation model is established according to the characteristics of the device flow, the relative deviation between the simulation calculation result and the device operation data is less than +/-5%, and the simulation model can be considered to accurately simulate and calculate the device operation data under the working condition, which is shown in a table 2-1.
TABLE 2-1
3) Correction model for obtaining hydrogen content
Taking 5 groups of samples from light naphtha, heavy naphtha, aviation kerosene, diesel oil and tail oil respectively, obtaining hydrogen content data of each sample by utilizing two ways of laboratory measurement and model calculation in the step S102, and performing data fitting by utilizing' VS simulation calculation of hydrogen content through experimental measurement to obtain a product hydrogen content correction calculation model (namely the correction model in the step S104).
(a) Light naphtha
And (2) measuring and calculating the simulated calculated hydrogen content by measuring the hydrogen content experimentally to obtain a correction formula of the light naphtha, wherein the dependent variable y in the formula 1 represents the actual hydrogen content, and the independent variable x represents the simulated hydrogen content, and the correction formula is shown as formula 1. The hydrogen content data obtained by the simulation calculation and the experimentally determined hydrogen content data are shown in Table 3-1, and the relationship between the two in the calibration model can also be seen in FIG. 5.
y=44995333079040.0000x4-30318585199744.8000x3+7660932835747.3700 x2-860343448267.2070x +36232084454.7147 (formula 1)
TABLE 3-1
The same can be obtained:
(b) the heavy naphtha hydrogen content calculation correction formula:
y=12576597868544.0000x4-7149679555718.1600x3+1524197375759.5300x2-144415326118.7810 x +5131172210.3161 (formula 2)
(c) Calculating and correcting formula of hydrogen content of aviation kerosene:
y=-3301309448192.0000x4+1790133338523.6800x3-364012015045.4000x2+ 32897542988.8125 x-1114916645.6957 (formula 3)
(d) Calculating and correcting formula of hydrogen content of diesel oil:
y=-31467167023104.0000x4+17453938803957.0000x3-3630449924075.4300x2+ 335617706284.6860 x-11634841660.3959 (formula 4)
(e) The tail oil hydrogen content calculation correction formula:
y=287699009536.0000x4-164178380825.7870x3+35133765566.6956x2-3341571618.0162x +119181261.4740 (formula 5)
4) Obtaining a hydrogen distribution model
20 groups of raw material samples are selected, the hydrogen content of each product is calculated by using the model established in the step S102, and the actual hydrogen content is calculated according to the product correction model obtained in the step S104, as shown in the table 4-1.
Taking 20 groups of raw material samples
TABLE 4-1 raw material samples
The average boiling point temperatures of 20 groups of raw material samples were calculated, and as shown in Table 4-2, there was no reference to calculating the mixture density, the sulfur and nitrogen content, etc., since there was only one raw material.
TABLE 4-2 average boiling temperature
The data of each product, including gas phase, liquefied gas, and oil phase product, is calculated by using the model established in step S102, and mainly the properties of the oil phase product are calculated, taking the calculation process of light naphtha as an example, as shown in table 4-3.
Tables 4-3 light naphtha simulation data
The actual hydrogen content data of the light naphtha of the 20 groups of samples are obtained by calculation by using the light naphtha hydrogen content correction model (formula 1) obtained in the step S104, and are shown in the following tables 4-4:
TABLE 4-4 corrected hydrogen content data
Sample (I)
|
Actual hydrogen content
|
1
|
16.8439%
|
2
|
16.8521%
|
3
|
16.8461%
|
4
|
16.8475%
|
5
|
16.8471%
|
6
|
16.8556%
|
7
|
16.3551%
|
8
|
16.6893%
|
9
|
16.6496%
|
10
|
16.3551%
|
11
|
16.3521%
|
12
|
16.3887%
|
13
|
16.3582%
|
14
|
16.6176%
|
15
|
16.3887%
|
16
|
16.6893%
|
17
|
16.3582%
|
18
|
16.3689%
|
19
|
16.3551%
|
20
|
16.3597% |
The data are summarized in tables 4-5:
TABLE 4-5 data summarization
Using the data in tables 4-4 for raw oil properties (T)VRho, S, N), operating parameters (T, P) and light naphtha flow rate (data in tables 4-5), and fitting by using an excel data fitting formula to obtain the hydrogen distribution model coefficients of the light naphtha device as shown in tables 4-6.
TABLE 4-6 light naphtha Hydrogen distribution model coefficients
Coefficient of performance
|
Light naphtha
|
ej |
-0.736379877
|
aj |
3202.180424
|
bj |
725.633915
|
cj |
-0.00456456
|
dj |
-1.591942854
|
A1,j |
1.5719E-05
|
A2,j |
-0.003825067
|
B1,j |
0.062394384 |
The hydrogen distribution model coefficients of heavy naphtha, aviation kerosene, diesel oil and tail oil were obtained in the same manner, as shown in tables 4 to 7.
TABLE 4-7 summary of coefficients of hydrogen distribution model
5) Hydrogen componentApplication of cloth model
The operation condition of the device at a certain moment is shown in a table 5-1:
TABLE 5-1 apparatus Material balance
Entering a formula:
|
amount of feed, t/h
|
Straight-run wax oil
|
212.80
|
New hydrogen
|
5.57
|
Total up to
|
218.37
|
The method comprises the following steps:
|
throughput, t/h
|
Dry gas
|
9.09
|
Liquefied gas
|
6.11
|
Light naphtha
|
10.39
|
Heavy naphtha
|
43.92
|
Aviation kerosene
|
50.67
|
Diesel oil
|
27.50
|
Tail oil
|
70.58
|
Loss of power
|
0.11
|
Total up to
|
218.37 |
TABLE 5-2 Properties of stock oils
TABLE 5-3 operating temperature of the apparatus
Temperature, K
|
663.15
|
Pressure, MPa
|
15.273 |
TABLE 5-4 Dry gas composition
Composition/% (v)
|
|
Hydrogen gas
|
27.66
|
Methane
|
40.31
|
Ethane (III)
|
20.14
|
Propane
|
3.83
|
N-butane
|
0.46
|
Isobutane
|
0.04
|
More than five carbon atoms
|
0.04
|
Hydrogen sulfide
|
2.25
|
Air (a)
|
5.27
|
Total up to
|
100 |
TABLE 5-5 compositions of liquefied gases
Composition/% (body)
|
|
Hydrogen gas
|
|
Methane
|
|
Ethane (III)
|
|
Propane
|
35.79
|
N-butane
|
41.06
|
Isobutane
|
22.57
|
More than five carbon atoms
|
0.58
|
Total up to
|
100 |
The hydrogen distribution of the plant was calculated using the hydrogen distribution prediction model of the present invention (i.e., equation (3) in step S105, at which time the model coefficients are known), and as shown in tables 5-6, the relative deviation of the total hydrogen element content of the plant product compared to the feed was (31.8258-31.3701)/31.3701 was 1.45% < 5%, which satisfied the engineering calculation requirements.
Tables 5-6 calculation of device hydrogen balance
The method for predicting the hydrogen distribution of the oil refining production device disclosed by the invention couples mathematical modeling of commercial process simulation software and necessary laboratory test analysis, combines the production practice of a refinery, performs mathematical association with conventional analysis items and main operation conditions of the device, and fully utilizes the production operation data of the device to perform model training, so that the purposes of improving the accuracy and extrapolation of model calculation and optimizing the operation of the device are achieved. The judgment and correction of material balance and hydrogen balance are carried out in the calculation process of the hydrogen distribution prediction model, and the prediction accuracy is more effectively ensured.
Example 2
As shown in fig. 3, the hydrogen distribution prediction apparatus of the oil refinery production apparatus of the present embodiment includes: the system comprises a basic information preparation module 201, a simulation calculation data acquisition module 202, an experimental test data acquisition module 203, a correction data acquisition module 204 and a hydrogen distribution prediction model acquisition module 205. The basic information preparation module 201 is used for determining the device type, working condition and key operation parameters, and determining the raw material, product type and material parameter information; the simulation calculation data acquisition module 202 is used for establishing a device model through process simulation software to acquire hydrogen content simulation calculation data of raw materials and products under different working conditions; the experimental test data acquisition module 203 is used for sampling experimental analysis on raw materials and products under a limited set of working conditions to obtain experimental test data of hydrogen content; the correction data acquisition module 204 is used for fitting and correcting hydrogen content experimental test data and hydrogen content simulation calculation data under a limited set of working conditions aiming at an oil phase product in the product to obtain corrected hydrogen content data; the hydrogen distribution prediction model obtaining module 205 is configured to perform regression fitting on the oil-phase product by using the corrected hydrogen content data, the material parameter information of the raw oil, and the key operation parameter, so as to obtain a device hydrogen distribution prediction model.
Example 3
The present embodiment provides a memory, which may be a non-transitory (non-volatile) computer storage medium, and the computer storage medium stores computer executable instructions, which can execute the steps of the hydrogen distribution prediction method of the oil refinery production device in any of the above-mentioned method embodiments, and achieve the same technical effect.
Example 4
The embodiment provides a hydrogen distribution prediction device for an oil refining production device, which comprises a memory and a corresponding computer program product, wherein the computer program product comprises program instructions which, when executed by a computer, can make the computer execute the hydrogen distribution prediction method for the oil refining production device in the above aspects and achieve the same technical effects.
Fig. 4 is a schematic diagram of a hardware structure of the electronic device according to the embodiment, and as shown in fig. 4, the device includes one or more processors 610 and a memory 620. Take a processor 610 as an example. The apparatus may further include: an input device 630 and an output device 640.
The processor 610, the memory 620, the input device 630, and the output device 640 may be connected by a bus or other means, and are exemplified by a bus in fig. 3.
The memory 620, which is a non-transitory computer readable storage medium, may be used to store non-transitory software programs, non-transitory computer executable programs, and modules. The processor 610 executes various functional applications and data processing of the electronic device, i.e., the processing method of the above-described method embodiment, by executing the non-transitory software programs, instructions and modules stored in the memory 620.
The memory 620 may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data and the like. Additionally, the memory 620 may include high speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid state storage device. In some embodiments, the memory 620 may optionally include memory located remotely from the processor 610, which may be connected to the processing device via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The input device 630 may receive input numeric or character information and generate a signal input. The output device 640 may include a display device such as a display screen.
The one or more modules are stored in the memory 620 and, when executed by the one or more processors 610, perform: the invention relates to a hydrogen distribution prediction method based on an oil refining production device. The product can execute the method provided by the embodiment of the invention, and has corresponding functional modules and beneficial effects of the execution method. For technical details that are not described in detail in this embodiment, reference may be made to the method provided by the embodiment of the present invention.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.