CN117454653A - Energy consumption optimization method for natural gas desulfurization device and electronic equipment - Google Patents
Energy consumption optimization method for natural gas desulfurization device and electronic equipment Download PDFInfo
- Publication number
- CN117454653A CN117454653A CN202311497108.1A CN202311497108A CN117454653A CN 117454653 A CN117454653 A CN 117454653A CN 202311497108 A CN202311497108 A CN 202311497108A CN 117454653 A CN117454653 A CN 117454653A
- Authority
- CN
- China
- Prior art keywords
- data
- energy consumption
- model
- natural gas
- optimization
- 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.)
- Pending
Links
- 238000005265 energy consumption Methods 0.000 title claims abstract description 140
- VNWKTOKETHGBQD-UHFFFAOYSA-N methane Chemical compound C VNWKTOKETHGBQD-UHFFFAOYSA-N 0.000 title claims abstract description 96
- 238000005457 optimization Methods 0.000 title claims abstract description 81
- 238000006477 desulfuration reaction Methods 0.000 title claims abstract description 69
- 230000023556 desulfurization Effects 0.000 title claims abstract description 69
- 238000000034 method Methods 0.000 title claims abstract description 63
- 239000003345 natural gas Substances 0.000 title claims abstract description 48
- 239000002904 solvent Substances 0.000 claims abstract description 67
- 230000008859 change Effects 0.000 claims abstract description 52
- 238000004088 simulation Methods 0.000 claims abstract description 46
- 238000013499 data model Methods 0.000 claims abstract description 35
- 239000000203 mixture Substances 0.000 claims abstract description 34
- 238000005187 foaming Methods 0.000 claims abstract description 31
- 238000012549 training Methods 0.000 claims abstract description 7
- 238000002474 experimental method Methods 0.000 claims description 55
- 238000010521 absorption reaction Methods 0.000 claims description 37
- 238000012360 testing method Methods 0.000 claims description 23
- 230000008569 process Effects 0.000 claims description 22
- 150000001412 amines Chemical class 0.000 claims description 16
- 238000004364 calculation method Methods 0.000 claims description 15
- 230000003009 desulfurizing effect Effects 0.000 claims description 15
- 229910052717 sulfur Inorganic materials 0.000 claims description 15
- 239000011593 sulfur Substances 0.000 claims description 15
- 238000004519 manufacturing process Methods 0.000 claims description 14
- 239000000463 material Substances 0.000 claims description 14
- 239000003795 chemical substances by application Substances 0.000 claims description 12
- 230000007246 mechanism Effects 0.000 claims description 11
- 238000004422 calculation algorithm Methods 0.000 claims description 10
- 230000002068 genetic effect Effects 0.000 claims description 9
- 238000013506 data mapping Methods 0.000 claims description 8
- 238000013507 mapping Methods 0.000 claims description 8
- 238000004445 quantitative analysis Methods 0.000 claims description 6
- 238000005516 engineering process Methods 0.000 claims description 4
- 230000001502 supplementing effect Effects 0.000 claims description 4
- 238000005481 NMR spectroscopy Methods 0.000 claims description 3
- 230000009467 reduction Effects 0.000 abstract description 14
- 238000011160 research Methods 0.000 abstract description 12
- 238000004134 energy conservation Methods 0.000 abstract description 8
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 abstract description 2
- 229910052799 carbon Inorganic materials 0.000 abstract description 2
- 239000000243 solution Substances 0.000 description 70
- 239000007789 gas Substances 0.000 description 34
- 239000007788 liquid Substances 0.000 description 13
- 239000000047 product Substances 0.000 description 9
- 238000003860 storage Methods 0.000 description 7
- PVXVWWANJIWJOO-UHFFFAOYSA-N 1-(1,3-benzodioxol-5-yl)-N-ethylpropan-2-amine Chemical compound CCNC(C)CC1=CC=C2OCOC2=C1 PVXVWWANJIWJOO-UHFFFAOYSA-N 0.000 description 5
- QMMZSJPSPRTHGB-UHFFFAOYSA-N MDEA Natural products CC(C)CCCCC=CCC=CC(O)=O QMMZSJPSPRTHGB-UHFFFAOYSA-N 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 5
- 230000006872 improvement Effects 0.000 description 5
- 230000001105 regulatory effect Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000000746 purification Methods 0.000 description 3
- CURLTUGMZLYLDI-UHFFFAOYSA-N Carbon dioxide Chemical compound O=C=O CURLTUGMZLYLDI-UHFFFAOYSA-N 0.000 description 2
- YNAVUWVOSKDBBP-UHFFFAOYSA-N Morpholine Chemical compound C1COCCN1 YNAVUWVOSKDBBP-UHFFFAOYSA-N 0.000 description 2
- NINIDFKCEFEMDL-UHFFFAOYSA-N Sulfur Chemical compound [S] NINIDFKCEFEMDL-UHFFFAOYSA-N 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000012937 correction Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000011835 investigation Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000005728 strengthening Methods 0.000 description 2
- 238000012546 transfer Methods 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 239000006096 absorbing agent Substances 0.000 description 1
- 239000002253 acid Substances 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000033228 biological regulation Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 229910002092 carbon dioxide Inorganic materials 0.000 description 1
- 239000001569 carbon dioxide Substances 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 239000000498 cooling water Substances 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 239000008151 electrolyte solution Substances 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 239000000446 fuel Substances 0.000 description 1
- 230000008303 genetic mechanism Effects 0.000 description 1
- 238000011065 in-situ storage Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000002156 mixing Methods 0.000 description 1
- 238000012821 model calculation Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000035772 mutation Effects 0.000 description 1
- 238000012803 optimization experiment Methods 0.000 description 1
- 125000001741 organic sulfur group Chemical group 0.000 description 1
- 230000000704 physical effect Effects 0.000 description 1
- 238000011112 process operation Methods 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
- 230000008929 regeneration Effects 0.000 description 1
- 238000011069 regeneration method Methods 0.000 description 1
- 230000002787 reinforcement Effects 0.000 description 1
- 238000010845 search algorithm Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Hardware Design (AREA)
- Evolutionary Computation (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Treating Waste Gases (AREA)
Abstract
The invention discloses an energy consumption optimization method of a natural gas desulfurization device and electronic equipment, belonging to the field of energy-saving and carbon reduction research, comprising the following steps: constructing an energy-consumption optimization model of data-model hybrid driving; training the energy-consumption optimization model of the data-model hybrid drive by combining historical operation data, the actual measured energy consumption data change rule, the influence rule of solvent composition change on solvent foaming performance and the full-flow simulation predicted energy consumption data change rule; and putting the trained energy consumption optimization model driven by the data-model mixture into practical industrial application to optimize the energy consumption of the natural gas desulfurization device. The dominant factors influencing the energy consumption of the device can be induced from the flow simulation and the industrial operation big data, so that the optimal scheme of energy conservation and consumption reduction of the device can be obtained.
Description
Technical Field
The invention relates to the field of energy-saving and carbon reduction research, in particular to an energy consumption optimization method of a natural gas desulfurization device and electronic equipment.
Background
The natural gas purification plant has the characteristics of large energy consumption load, stable energy consumption and long energy consumption time, explores the optimal solution for reducing the running energy consumption of the natural gas purification plant, is a precondition for realizing safe and stable clean energy consumption and energy consumption supply, is a powerful way for effectively improving the comprehensive utilization rate of natural gas and reducing the energy consumption cost of the purification plant, and is an effective attempt for excavating, upgrading and enhancing the quality in enterprises.
The research on energy saving and consumption reduction measures of natural gas purifying plants at home and abroad is mainly focused on three aspects of enterprise management, early design and technical transformation, and experimental research is carried out from a single factor.
The desulfurization device is equivalently built by using software and is subjected to preliminary simulation, only the influence of a single factor on the energy consumption of the desulfurization device can be obtained, the influence of multiple factor changes on the energy consumption cannot be simulated at the same time, and meanwhile, how to induce dominant factors influencing the energy consumption of the device from flow simulation and industrial operation big data, the optimal scheme of energy conservation and consumption reduction of the condensing device still faces great challenges.
Disclosure of Invention
The invention aims to overcome the defects of the prior art how to induce dominant factors influencing the energy consumption of a device from flow simulation and industrial operation big data, and an optimal scheme of energy conservation and consumption reduction of a condensing device is still faced with great challenges, and provides an energy consumption optimization method of a natural gas desulfurization device and electronic equipment.
In order to achieve the above object, the present invention provides the following technical solutions:
the energy consumption optimizing method of the natural gas desulfurizing device comprises the following steps:
s1: constructing an energy-consumption optimization model of data-model hybrid driving;
s2: training the energy-consumption optimization model of the data-model hybrid drive by combining historical operation data, the actual measured energy consumption data change rule, the influence rule of solvent composition change on solvent foaming performance and the full-flow simulation predicted energy consumption data change rule;
s3: and putting the trained energy consumption optimization model driven by the data-model mixture into practical industrial application to optimize the energy consumption of the natural gas desulfurization device.
By adopting the technical scheme, dominant factors influencing the energy consumption of the device can be induced from the flow simulation and the industrial operation big data, so that an optimal scheme for saving energy and reducing consumption of the device is obtained.
As a preferred embodiment of the present invention, before constructing the energy-consumption optimization model of the data-model mixture, the method further includes: and acquiring material flow and energy flow data, constructing a high-sulfur natural gas desulfurization unit simulation model, performing simulation calculation to obtain the energy consumption data change rule of full-flow simulation prediction, verifying the reliability of the high-sulfur natural gas desulfurization unit simulation model according to the energy consumption data change rule of full-flow simulation prediction and the actually measured energy consumption data change rule, and constructing a data-model hybrid driving energy consumption optimization model if the reliability is satisfied.
As a preferred scheme of the invention, the energy consumption data change rule obtained by performing simulation calculation and full-flow simulation prediction comprises the following steps:
step one: quantitatively analyzing the components of the desulfurizing agent by adopting a meteorological chromatograph-mass spectrometer, an infrared spectrometer and a nuclear magnetic resonance spectrometer to obtain a quantitative analysis result;
step two: supplementing the information of components and components lacking the physical components of the desulfurizing agent based on a database, and developing thermodynamic experiments or on-site production data regression calculation to perfect thermodynamic data;
step three: and combining the quantitative analysis result and the thermodynamic data after completion, and adopting simulation software to perform full-flow simulation on the high-sulfur natural gas desulfurization unit.
As a preferable scheme of the invention, the simulation software is HYSYS software and Aspenplus software.
As a preferable scheme of the invention, the actual measured energy consumption data change rule is based on an industrial device desulfurization process optimization experiment of the solvent by an on-site industrial device.
As a preferable scheme of the invention, firstly, a solvent foaming experiment is carried out based on a small experiment platform, so as to obtain the rule of influence of the change of the solvent composition on the solvent foaming performance, and then, the method is based on the solvent foaming experiment.
As a preferred embodiment of the present invention, the industrial device desulfurization process optimization experiment for the solvent based on the on-site industrial device based on the solvent foaming experiment includes: absorption tower plate number optimizing field test, solution circulation amount optimizing field test, lean solution entering absorption tower temperature optimizing field test, semi-rich amine solution entering absorption tower temperature optimizing field test, desulfurizing agent composition optimizing field test:
as a preferred embodiment of the present invention, the energy-consumption optimization model of the data-model hybrid driving in step S1 includes: an input layer, a hidden layer and an output layer which are connected in sequence;
the input layer is used for inputting decision parameters;
the hidden layer is used for constructing an initial mapping relation between decision parameters and sub-targets, and correcting the relation between the decision parameters and the sub-targets according to historical production data;
the output layer is used for outputting the optimization parameters.
As a preferred scheme of the present invention, the training of the energy consumption optimization model for the data-model hybrid driving by combining the historical operation data, the actual measured energy consumption data change rule, the influence rule of the solvent composition change on the solvent foaming performance, and the full-flow simulation predicted energy consumption data change rule in step S2 includes:
s21: constructing initial mapping relations between a plurality of decision parameters and a plurality of sub-targets, and correcting data mapping relations between the decision parameters and the sub-targets by using the historical operation data;
s22: according to the data mapping relation, simulation software is selected to simulate the decision parameter change in the desulfurization process and the conduction mechanism of material flow and energy flow;
s23: the data-model hybrid driven energy-consumption optimization model adopts a genetic algorithm to generate a feasible solution;
s24: according to the feasible solution, a data deconstructing technology is adopted to clarify the influence degree of each sub-target corresponding to each decision parameter when the decision parameters change within a feasible range, and the relative importance of the decision parameters is weighted.
In another aspect, an electronic device is disclosed that includes at least one processor, and a memory communicatively coupled to the at least one processor; the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the natural gas desulfurization apparatus energy consumption optimization method of any one of the above.
Compared with the prior art, the invention has the beneficial effects that: the dominant factors influencing the energy consumption of the device can be induced from the flow simulation and the industrial operation big data, so that the optimal scheme of energy conservation and consumption reduction of the device can be obtained.
Drawings
FIG. 1 is a flow chart of a method for optimizing energy consumption of a natural gas desulfurization apparatus according to embodiment 1 of the present invention;
FIG. 2 is a process flow diagram of a desulfurization absorber tower of a natural gas desulfurization apparatus energy consumption optimization method according to embodiment 3 of the present invention;
FIG. 3 is a block diagram of a data-model hybrid-driven energy-consumption optimization model of a natural gas desulfurization apparatus energy consumption optimization method according to embodiment 3 of the present invention;
FIG. 4 is a Pareto front search graph based on a novel "multi-objective collaborative strengthening operator" for a natural gas desulfurization apparatus energy consumption optimization method according to embodiment 3 of the present invention;
FIG. 5 is a Pareto front search graph of a multi-objective decision for a natural gas desulfurization apparatus energy consumption optimization method according to embodiment 3 of the present invention;
fig. 6 is a block diagram of an electronic device according to embodiment 4 of the present invention.
Detailed Description
The present invention will be described in further detail with reference to test examples and specific embodiments. It should not be construed that the scope of the above subject matter of the present invention is limited to the following embodiments, and all techniques realized based on the present invention are within the scope of the present invention.
Example 1
The energy consumption optimizing process of natural gas desulfurizing apparatus includes the following steps: .
S1: constructing an energy-consumption optimization model of data-model hybrid driving;
s2: training the energy-consumption optimization model of the data-model hybrid drive by combining historical operation data, the actual measured energy consumption data change rule, the influence rule of solvent composition change on solvent foaming performance and the full-flow simulation predicted energy consumption data change rule;
s3: and putting the trained energy consumption optimization model driven by the data-model mixture into practical industrial application to optimize the energy consumption of the natural gas desulfurization device.
The dominant factors influencing the energy consumption of the device can be induced from the flow simulation and the industrial operation big data, so that the optimal scheme of energy conservation and consumption reduction of the device can be obtained.
Example 2
This embodiment is a specific embodiment of embodiment 1;
before constructing the energy-usage optimization model of the data-model mixture, the method further comprises: and acquiring material flow and energy flow data, constructing a high-sulfur natural gas desulfurization unit simulation model, performing simulation calculation to obtain the energy consumption data change rule of full-flow simulation prediction, verifying the reliability of the high-sulfur natural gas desulfurization unit simulation model according to the energy consumption data change rule of full-flow simulation prediction and the actually measured energy consumption data change rule, and constructing a data-model hybrid driving energy consumption optimization model if the reliability is satisfied.
The energy consumption data change rule for full-flow simulation prediction obtained by simulation calculation comprises the following steps:
step one: quantitatively analyzing the components of the desulfurizing agent by adopting a meteorological chromatograph-mass spectrometer, an infrared spectrometer and a nuclear magnetic resonance spectrometer to obtain a quantitative analysis result;
step two: supplementing the information of components and components lacking the physical components of the desulfurizing agent based on a database, and developing thermodynamic experiments or on-site production data regression calculation to perfect thermodynamic data;
step three: and combining the quantitative analysis result and the thermodynamic data after completion, and adopting HYSYS software and AspenPlus software to perform full-flow simulation on the high-sulfur-content natural gas desulfurization unit.
The actual measurement energy consumption data change rule is that firstly, a solvent foaming experiment is carried out based on a small experiment platform to obtain an influence rule of solvent composition change on solvent foaming performance, and then, an industrial device desulfurization process optimization experiment is carried out on the solvent based on an on-site industrial device on the basis of the solvent foaming experiment.
The industrial device desulfurization process optimization experiment for the solvent based on the on-site industrial device based on the solvent foaming experiment comprises the following steps:
optimization of the number of absorption trays field test: firstly, recording energy consumption data of a device when lean solution is fed into an nth layer plate tower; switching the lean solution to the n-3 layer plate tower for feeding, maintaining for 3 days, and recording the energy consumption and the running stability data of the device; judging whether the product gas meets one type of gas index, if so, switching the lean solution to an n-m layer plate tower for feeding, maintaining for 3 days, recording the energy consumption and the running stability data of the device, and if the product gas still meets one type of gas index and the device runs stably, completing an absorption tower plate number optimization field test;
solution circulation amount optimization field test: maintaining the position of the lean solution inlet at the n-m layer tower plate, examining the influence of the lean solution and semi-rich amine solution circulation quantity on the energy consumption of the device, and firstly, maintaining the flow velocity of the semi-rich amine solution at xm 3 And (h) regulating the lean solution circulation quantity according to the gradual reduction trend, observing the steady operation condition of the desulfurization unit, maintaining for 7 days, and recording the energy consumption and the operation stability data of the device; judging whether the product gas can meet a gas index, if so, keeping the circulating flow rate of the lean solution to be ym 3 Per hour, pressAdjusting the semi-rich amine liquid circulation quantity according to the gradual reduction trend, examining the influence of the semi-rich amine liquid circulation quantity change on the energy consumption of the device, and recording the energy consumption and the running stability data of the device;
lean solution entering the absorption tower temperature optimization field test: maintaining the position of the lean solution inlet at the n-m layer plate tower, maintaining the solvent circulation amount at a better solution circulation amount obtained in a solution circulation amount optimization field test, namely meeting the minimum circulation amount required by production, and observing the influence of the lean solution temperature on the energy consumption of the device; setting the temperature of a lean solution absorption tower, sequentially keeping the device stably running at each temperature point for 3 days according to the sequence from the temperature to the bottom, respectively recording the energy consumption data of the device, and if the product gas meets the gas index requirement, and the device runs stably, entering the next temperature point for test until the load of a heat exchange system reaches the upper limit;
semi-rich amine liquid enters an absorption tower for temperature optimization field test: maintaining the position of the lean solution inlet at the n-m layer plate tower, maintaining the solvent circulation amount at the optimal solution circulation amount obtained in the solution circulation amount optimization field test, and examining the influence of the semi-rich amine solution temperature on the energy consumption of the device; setting the temperature of a semi-rich amine liquid absorption tower, sequentially keeping the device stably running at each temperature point for 3 days according to the sequence from the temperature to the bottom, respectively recording the energy consumption data of the device, and if the product gas meets the gas index requirement, and the device stably runs, entering the next temperature point for testing until the load of a heat exchange system reaches the upper limit;
desulfurizing agent composition optimization field test: based on the rule of influence of the change of the solvent composition on the solvent foaming performance, starting from an on-site solvent composition operation point, gradually adjusting the solvent composition within a range with good solvent foaming performance, adjusting the operation of a holding device for 7 days each time, recording energy consumption data of the device, judging whether product gas meets one type of gas index requirement after each test, judging whether the solvent foaming condition is good, and judging whether the operation of the device is stable, if so, continuously changing the solvent ratio to perform the next group of experiments, recording experimental data, and otherwise, stopping the test.
And combining flow simulation data and field experiment data, providing a new method for utilizing data-model hybrid driving, exploring the influence rule of each variable on the energy consumption of the device, and condensing the optimal solution for reducing the energy consumption of the device.
The training of the energy consumption optimization model of the data-model hybrid driving by combining historical operation data, the actual measured energy consumption data change rule, the influence rule of the solvent composition change on the solvent foaming performance and the full-flow simulation predicted energy consumption data change rule in the step S2 comprises the following steps:
s21: constructing initial mapping relations between a plurality of decision parameters and a plurality of sub-targets (solution circulation quantity, lean solution entering absorption tower temperature, energy saving, consumption reduction, synergy, solvent composition and absorption tower plate number), and correcting data mapping relations between the decision parameters and the sub-targets by using the historical operation data;
s22: according to the data mapping relation, HYSYS software is selected to simulate decision parameter change in the desulfurization process and a conduction mechanism of material flow and energy flow;
s23: the data-model hybrid driven energy-consumption optimization model adopts a genetic algorithm to generate a feasible solution;
s24: according to the feasible solution, a data deconstructing technology is adopted to clarify the influence degree of each sub-target corresponding to each decision parameter when the decision parameter changes within a feasible range, and the relative importance of the decision parameter is weighted, for example: both lean and semi-rich circulation are reduced by 5t/h, but the energy consumption of the plant is reduced to a different extent, so that in the process of reducing the energy consumption of the plant, each variable has a relatively important order, and which variable is adjusted most easily to obtain the desired result.
Example 3
This embodiment is a specific embodiment of embodiment 1;
firstly, determining that a research object is a high-sulfur natural gas desulfurization unit, counting production operation data, extracting material flow and energy flow information, wherein the material flow information comprises material flow data such as material flow, temperature and pressure, and energy flow data such as fuel, water and electricity. In combination with investigation of literature and field device variable space, analysis of key operating parameters affecting energy consumption of the device includes: the operation parameters of lean liquid circulation quantity, semi-rich liquid circulation quantity, regeneration tower reboiler steam consumption, circulating cooling water consumption, absorption tower tray number and the like.
Because the pressure and the acid gas composition of the natural gas with high sulfur content are obviously higher than those of the conventional natural gas, the desulfurization process is different from the conventional condition. Therefore, a thermodynamic model capable of describing the phase behavior of the high-sulfur natural gas desulfurization process needs to be studied with great importance, and the accuracy of model calculation is related to solving the problems of state equation, UDS electrolyte solution property calculation and the like.
On the one hand, the project is to analyze the molecular information of key material flows such as absorption solvent and the like by using a modern instrument analysis method to acquire the component molecular information and content of the key material flows. On the other hand, the project is to acquire the component and the component pair information of the missing physical component based on the physical database of the flow simulation software such as AspenHYSYS, PRO/II and the database such as NIST and DECHEMA, and to carry out thermodynamic experiments or on-site production data regression calculation to perfect and supplement thermodynamic models of the components.
The method aims at reducing the energy consumption of the device, and implements the experimental research of a small-sized experiment platform and a field industrial device of the high-sulfur natural gas desulfurization process, wherein the small-sized experiment platform focuses on observing the influence of solvent composition on the foaming condition of the solution, and the field desulfurization device experiment focuses on observing the law of the influence of variables such as solvent circulation quantity, lean solvent temperature, feeding position (tower plate number of an absorption tower), solvent composition and the like on the energy consumption of the device.
1. Solvent foaming experiment of small experiment platform
The UDS desulfurizing agent contains chemical substances such as MEA, DEA, morpholine and the like with certain concentration, has higher absorption efficiency on organic sulfur and carbon dioxide, and has poor solvent desulfurization selectivity, and the circulating amount of the solution is high, so that the energy consumption of the device is higher.
In order to cooperate with the desulfurization optimization experiment of the field industrial device, a small desulfurization experiment is carried out in advance before the solvent composition optimization field experiment so as to investigate the influence rule of the solvent composition change on the solvent foaming performance. And (3) blending the UDS pure solvent and the MDEA according to the mass ratio of 8:2,6:4,4:6,2:8 and 0:1, recording the foaming condition of the solvent in the wet purified gas, if the solvent has no obvious foaming condition, continuously changing the solvent ratio to carry out the next experiment, and recording experimental data.
2. In situ desulfurization device experiments
And (3) referring to the existing operating temperature, pressure and other conditions of the device, carrying out single-factor experimental study on key operating parameters in the process operation constraint range, and observing the influence rule of the change of each key parameter on the energy consumption of the device. Taking the desulfurization unit of the 4 th combined device as an example (the flow of the absorption tower is shown as figure 2), the influence rule of the optimization of the operation parameters of the absorption tower on the energy consumption of the device is examined. The specific research method is as follows:
(1) on-site experiment for optimizing number of absorption tower plates
Maintaining the lean solution circulation volume of the absorption tower at 180m < 3 >/h and the semi-rich amine solution circulation volume at 150m < 3 >/h. The semi-rich amine liquid is fed at the 7 th tray of the primary absorption tower. And when the lean liquid feeding positions of the second-stage absorption tower are respectively 22 th, 19 th and 17 th, the experiment is performed to investigate the change rule of the energy consumption of the device. Specifically, the method comprises the following three steps:
a. firstly, recording data such as energy consumption of a device when the lean solution is fed to a 22 nd column plate;
b. switching the lean solution to the 19 th tower plate for feeding, maintaining the operation condition for 3 days, and recording the data of the energy consumption of the device, the running stability of the device and the like;
c. if the commodity gas in the step b can reach a gas index, switching the lean solution to the 17 th column plate for feeding, and repeating the operation in the step b. If the product gas quality still meets the gas quality requirement, and the device runs stably, the experimental task of the influence of the tower plate number of the absorption tower on the energy consumption of the device is completed.
(2) Solution circulation amount optimization field experiment
Maintaining the position of the lean solution inlet as the lowest feeding position meeting the first-class gas quality requirement in the step (1), and examining the relation between the circulating quantity of the lean solution and the semi-rich solution and the energy consumption of the device. Specifically, the method comprises the following three steps:
a. maintaining the semi-rich amine solution 145m3/h, regulating the lean solution circulation amount according to the gradual decrease trend (3 m3/h decrease per day), observing the steady operation condition of the desulfurization unit, and recording the data such as the energy consumption of the device; when the operation is expired in 7 days, if the commodity gas still meets the gas index requirement, and the device operates stably, the semi-rich liquid circulation quantity is adjusted downwards, and the subsequent experiment is continued;
b. keeping the lean solution circulation amount at 149m3/h, and examining the influence of the semi-rich amine solution circulation amount change on the energy consumption of the device according to the trend of gradually reducing and adjusting the semi-rich amine solution circulation amount (reducing by 3m3/h every day), wherein the operation method is the same as that of the step a;
c. and under the condition of a slightly low absorption tower plate number, the influence of the change of lean liquid and semi-rich amine liquid in the qualified range of the product gas on the energy consumption of the device is examined according to the operation of the steps a and b.
(3) Lean solution entering absorption tower temperature optimization field experiment
Maintaining the position of the lean solution inlet as the lowest feeding position meeting the first-class gas quality requirement in the step (1), and under the condition that the solvent circulation amount is the optimal solution circulation amount obtained through the step 2 experiment, examining the experimental study of the influence of the lean solution temperature on the energy consumption of the device. The temperature of the lean solution entering the absorption tower is 36 ℃, 33 ℃ and 30 ℃ respectively, and under each working condition, the device is kept to stably operate for 3 days, and data such as energy consumption of the device are recorded. Specifically, the method comprises the following three steps:
a. setting the temperature of the lean solution entering the absorption tower to be 36 ℃, keeping stable operation for 3 days, recording data such as energy consumption of the device, and if the commodity gas meets the gas index requirement, and the device operates stably, reducing the temperature of the lean solution entering the absorption tower, and entering the next stage of research;
b. regulating the temperature of the lean solution entering the absorption tower to 33 ℃, keeping stable operation for 3 days, recording data such as energy consumption of the device, and if the commodity gas meets the gas index requirement, and the device operates stably, regulating the temperature of the lean solution entering the absorption tower, and entering the next stage of research;
c. and regulating the temperature of the lean solution entering the absorption tower to be 30 ℃, keeping stable operation for 3 days, recording data such as energy consumption of the device, and if the commodity gas meets the gas index requirement, and the device operates stably, ending the lean solution entering the tower temperature regulation experiment.
The temperature of the semi-rich amine liquid entering the absorption tower can be adjusted by referring to the temperature of the lean liquid entering the absorption tower, each temperature point is kept to run stably, if no abnormality exists, the next temperature point experiment is carried out until the load of the heat exchange system is close to the upper limit.
(4) Desulfurizing agent composition optimization field experiment
Based on the research results of the solvent foaming experiment of the small experiment platform, the desulfurizing agent composition optimization field experiment is developed. Starting from an on-site solvent composition operating point, gradually adjusting the solvent composition within a range with good solvent foaming performance, continuously operating the adjusting and maintaining device for 7 days each time, recording data such as energy consumption of the device, and if the commodity gas indexes all meet a gas quality requirement, the solvent foaming condition is good, the device is stable to operate, continuously changing the solvent ratio to perform the next group of experiments, and recording experimental data.
For example, the research result of the solvent foaming experiment shows that UDS: MDEA has no foaming phenomenon within the range of 0.6:0.4-0.2:0.8, then 5 experimental points are taken in the range to sequentially carry out field experiments, such as 0.6:0.4, 0.5:0.5, 0.4:0.6, 0.3:0.7 and 0.2:0.8, and firstly, UDS: MDEA is adjusted to be 0.6:0.4, and the continuous operation is kept for 7 days, so that the data such as energy consumption of a device and the like are recorded. If the commodity gas meets the gas index requirement of one type and the device runs stably, adjusting UDS by adding an MDEA solution, wherein the MDEA is 0.5:0.5, and carrying out the next group of experiments until all 5 groups of experiments are completed; and stopping the experiment if the operation of the device is unstable or the commodity gas index does not meet the requirement.
3. Verification and correction of flow simulation model
Comparing and analyzing all single factor experimental results of the field industrial device in the step (2) with the calculation results of the flow simulation model established in the step (1), verifying the reliability of the flow simulation model, and if the calculation results are consistent with the experimental results, indicating that the simulation model can effectively reproduce the actual production process of desulfurizing the natural gas with high sulfur content, and the model is reasonable and enters the next step; if the difference between the experimental result and the calculation result is larger, the simulation model is considered to be incapable of accurately reproducing the actual production process, and the simulation model needs to be optimized and improved. The key point is to improve from the following three aspects: (1) optimizing and perfecting a physical property model suitable for the desulfurization process of the high-sulfur natural gas, and supplementing model parameters by means of literature investigation, phase equilibrium experiments and the like; (2) further perfecting the key molecular information topological structure taking material flow as a main line and further accurately quantifying the solvent composition; (3) the efficiency of the correction tower plates is researched through the existing experiments, and the mass transfer rule and the heat transfer rule on each tower plate are clearly expressed.
4. The data-model hybrid driving-based high-sulfur natural gas desulfurization process is used for optimizing modeling and solving strategies.
The research content is oriented to optimization modeling of a plurality of targets such as energy conservation, consumption reduction, synergy and the like, and the energy consumption optimization modeling of data-model hybrid driving is performed by combining historical operation data, combined device field experiment data, desulfurization process mechanism model, flow simulation software simulation data and the like.
And searching a Pareto (Pareto) front edge solution set in a feasible domain by adopting a global searching strategy represented by a genetic algorithm, and outputting an optimal solution from the Pareto front edge solution set according to the sub-target interaction relation and the decision preference.
The data-model hybrid modeling is a modeling strategy combining a mechanism model and a data-based modeling method, and a desulfurization mechanism and a data sample are introduced into process modeling and system analysis, so that the desulfurization process is characterized from production experience to data analysis to mechanism rules. The modeling thought not only utilizes the mechanism law to reveal the deep connection between decision parameters and an optimization target, but also utilizes data driving to improve the optimizing efficiency of the modeling process. The multi-objective optimization modeling of the data-model hybrid drive not only solves the defect that the evolution rule of the complex process is difficult to accurately describe during mechanism modeling, but also reduces the problem that the data sample is too demanding in the data driving method, can reduce the difficulty of model construction and the dimension of a parameter space, improves the modeling precision and the modeling efficiency to the maximum extent, and strengthens the adaptability of the model.
As shown in fig. 3, the energy-consumption optimization model of the data-model hybrid drive includes: an input layer, a hidden layer and an output layer which are connected in sequence;
the input layer is used for inputting decision parameters;
the hidden layer is used for constructing an initial mapping relation between decision parameters and sub-targets, and correcting the relation between the decision parameters and the sub-targets according to historical production data;
the output layer is used for outputting the optimization parameters.
The modeling concept of the data-model hybrid drive is shown in fig. 3. According to field experimental data of the combined device, an initial mapping relation of solution circulation quantity (decision parameter 1), lean solution entering absorption tower temperature (decision parameter 2), energy conservation (sub-target 1), consumption reduction (sub-target 2), synergy (sub-target 3), solvent composition (decision parameter 3) and absorption tower plate number (decision parameter 4) is constructed; and correcting the data mapping relation between each decision parameter and each sub-target by using the historical production data.
According to the data mapping relation, a process model or a data driving model (such as an artificial neural network, a random forest and the like) which is built in HYSYS flow simulation software is reasonably selected, the transmission mechanism of decision parameter change in the desulfurization process and output information such as material flow, energy flow and the like is simulated,
the complex desulfurization process can be described by a mechanism model or replaced by a predictable machine learning model, parameters such as thermodynamics, dynamics and the like are allowed to be dynamically adjusted along with the change of decision parameters, and a sufficient feasible solution is generated through model operation and depends on an optimization algorithm and data resource limitation so as to meet the basic requirement of forming a Pareto front, thereby obtaining the representation value of each sub-target corresponding to different decision parameters when the different decision parameters change within a feasible range.
According to the feasible solution, data deconstructing technologies such as information Entropy (Entropy) and gray correlation degree (Greyrational analysis) are adopted, the influence degree of each decision parameter on each sub-target is clarified, and the relative importance of the decision parameters is weighted. On this basis, a novel multi-objective balanced strengthening operator is introduced into a classical genetic algorithm to solve, as shown in fig. 4. The genetic algorithm simulates natural selection and genetic mechanism to perform multi-objective optimization, and is a highly parallel, random, self-adaptive and efficient search algorithm with global optimization. Aiming at the characteristic that various decision parameters can be dynamically adjusted and mutually influenced in the desulfurization process, the decision parameter evolution direction is encoded by combining (real and simulated) data change trend. The generation method of the initial population is reasonably set, genetic operators (crossover and mutation) are designed, so that the technical improvement scheme after evolution meets the constraint, energy conservation and emission reduction sub-targets are respectively used as objective functions, and a pareto front solution set consisting of the sub-targets is obtained by utilizing a genetic algorithm.
Further utilizing a multidimensional space vector function to characterize and express a technical improvement scheme (namely decision parameters), describing absolute optimization degree of the technical improvement scheme on a multidimensional target by using a space vector model length, measuring relative development balance of the technical improvement scheme by using a space vector direction, utilizing a pareto front edge solution set as a reference plane, utilizing a space vector projection relation to realize integrated output of sub-target absolute optimization and relative balance, maximizing vector projection as an equivalent objective function of multi-target collaborative reinforcement, and utilizing computer coding to solve the optimal technical improvement scheme of the desulfurization process.
Based on the simulation model, key parameters are changed to perform simulation calculation, at least 104 data points are generated in the whole multidimensional variable space, and the experimental data in the step (3) are combined to form a solving and searching space of the multi-objective optimization model.
In the space, the values of indexes such as energy consumption of the device at each point are recorded, and the desulfurization process evolution modeling and the multi-objective decision analysis are carried out in a data-model hybrid driving mode. Firstly, device energy consumption optimization is implemented by using a Pareto front search method based on a multi-objective genetic robust optimization (MORE) algorithm. All decisions on the Pareto front were scored by expert scoring, and expert scoring was synthesized with a modified OWA algorithm. Next, as shown in fig. 5, a complex nonlinear mapping between each scheme on the Pareto front and the OWA comprehensive evaluation is applied to obtain a neural network comprehensive decision model based on expert scores. And finally, outputting each key variable value of the optimal decision to guide the optimization of the actual device, and adjusting each operation parameter step by step from the existing operation working condition of the device to the optimal decision direction in the actual production.
Example 4
As shown in fig. 6, an electronic device includes at least one processor, and a memory communicatively coupled to the at least one processor, and at least one input-output interface communicatively coupled to the at least one processor; the memory stores instructions executable by the at least one processor to enable the at least one processor to perform a method as described in the previous embodiments. The input/output interface may include a display, a keyboard, a mouse, and a USB interface for inputting and outputting data.
Those skilled in the art will appreciate that: all or part of the steps for implementing the above method embodiments may be implemented by hardware related to program instructions, and the foregoing program may be stored in a computer readable storage medium, where the program, when executed, performs steps including the above method embodiments; and the aforementioned storage medium includes: a removable storage device, a read only memory (ReadOnlyMemory, ROM), a magnetic or optical disk, or other various media capable of storing program code.
The above-described integrated units of the invention, when implemented in the form of software functional units and sold or used as stand-alone products, may also be stored in a computer-readable storage medium. Based on such understanding, the technical solutions of the embodiments of the present invention may be embodied in essence or a part contributing to the prior art in the form of a software product stored in a storage medium, including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in the embodiments of the present invention. And the aforementioned storage medium includes: various media capable of storing program codes, such as a removable storage device, a ROM, a magnetic disk, or an optical disk.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, and alternatives falling within the spirit and principles of the invention.
Claims (10)
1. The energy consumption optimizing method for the natural gas desulfurization device is characterized by comprising the following steps of:
s1: constructing an energy-consumption optimization model of data-model hybrid driving;
s2: training the energy-consumption optimization model of the data-model hybrid drive by combining historical operation data, the actual measured energy consumption data change rule, the influence rule of solvent composition change on solvent foaming performance and the full-flow simulation predicted energy consumption data change rule;
s3: and putting the trained energy consumption optimization model driven by the data-model mixture into practical industrial application to optimize the energy consumption of the natural gas desulfurization device.
2. The method for optimizing energy consumption of a natural gas desulfurization apparatus according to claim 2, further comprising, prior to constructing the energy consumption optimizing model of the data-model mixture: and acquiring material flow and energy flow data, constructing a high-sulfur natural gas desulfurization unit simulation model, performing simulation calculation to obtain the energy consumption data change rule of full-flow simulation prediction, verifying the reliability of the high-sulfur natural gas desulfurization unit simulation model according to the energy consumption data change rule of full-flow simulation prediction and the actually measured energy consumption data change rule, and constructing a data-model hybrid driving energy consumption optimization model if the reliability is satisfied.
3. The method for optimizing energy consumption of a natural gas desulfurization apparatus according to claim 2, wherein the performing simulation calculation to obtain the full-flow simulation predicted energy consumption data change rule comprises:
step one: quantitatively analyzing the components of the desulfurizing agent by adopting a meteorological chromatograph-mass spectrometer, an infrared spectrometer and a nuclear magnetic resonance spectrometer to obtain a quantitative analysis result;
step two: supplementing the information of components and components lacking the physical components of the desulfurizing agent based on a database, and developing thermodynamic experiments or on-site production data regression calculation to perfect thermodynamic data;
step three: and combining the quantitative analysis result and the thermodynamic data after completion, and adopting simulation software to perform full-flow simulation on the high-sulfur natural gas desulfurization unit.
4. The energy consumption optimization method for a natural gas desulfurization device according to claim 1, wherein the simulation software is HYSYS software and Aspenplus software.
5. The method for optimizing energy consumption of a natural gas desulfurization device according to claim 1, wherein the actual measured energy consumption data change rule is obtained by performing an industrial device desulfurization process optimization experiment on a solvent based on an on-site industrial device.
6. The method for optimizing energy consumption of a natural gas desulfurization apparatus according to claim 5, wherein the industrial apparatus desulfurization process optimization experiment comprises: firstly, performing a solvent foaming experiment based on a small experiment platform to obtain an influence rule of the change of the solvent composition on the solvent foaming performance, and then, based on the solvent foaming experiment.
7. The method for optimizing energy consumption of a natural gas desulfurization apparatus according to claim 6, wherein the industrial apparatus desulfurization process optimization experiment for the solvent based on the on-site industrial apparatus based on the solvent foaming experiment comprises: and (3) an absorption tower plate number optimization field test, a solution circulation amount optimization field test, a lean solution entering an absorption tower temperature optimization field test, a semi-rich amine solution entering an absorption tower temperature optimization field test and a desulfurizing agent composition optimization field test.
8. The method for optimizing energy consumption of a natural gas desulfurization apparatus according to claim 5, wherein the data-model hybrid-driven energy consumption optimization model in step S1 comprises: an input layer, a hidden layer and an output layer which are connected in sequence;
the input layer is used for inputting decision parameters;
the hidden layer is used for constructing an initial mapping relation between decision parameters and sub-targets, and correcting the relation between the decision parameters and the sub-targets according to historical production data;
the output layer is used for outputting the optimization parameters.
9. The method for optimizing energy consumption of a natural gas desulfurization apparatus according to claim 8, wherein the training of the data-model hybrid-driven energy optimization model in step S2 comprises:
s21: constructing initial mapping relations between a plurality of decision parameters and a plurality of sub-targets, and correcting data mapping relations between the decision parameters and the sub-targets by using the historical operation data;
s22: according to the data mapping relation, simulation software is selected to simulate the decision parameter change in the desulfurization process and the conduction mechanism of material flow and energy flow;
s23: the data-model hybrid driven energy-consumption optimization model adopts a genetic algorithm to generate a feasible solution;
s24: according to the feasible solution, a data deconstructing technology is adopted to clarify the influence degree of each sub-target corresponding to each decision parameter when the decision parameters change within a feasible range, and the relative importance of a plurality of decision parameters is weighted.
10. An electronic device comprising at least one processor, and a memory communicatively coupled to the at least one processor; the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the natural gas desulfurization apparatus energy consumption optimization method of any one of claims 1-9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311497108.1A CN117454653A (en) | 2023-11-10 | 2023-11-10 | Energy consumption optimization method for natural gas desulfurization device and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311497108.1A CN117454653A (en) | 2023-11-10 | 2023-11-10 | Energy consumption optimization method for natural gas desulfurization device and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117454653A true CN117454653A (en) | 2024-01-26 |
Family
ID=89592785
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311497108.1A Pending CN117454653A (en) | 2023-11-10 | 2023-11-10 | Energy consumption optimization method for natural gas desulfurization device and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117454653A (en) |
-
2023
- 2023-11-10 CN CN202311497108.1A patent/CN117454653A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Ding | A novel self-adapting intelligent grey model for forecasting China's natural-gas demand | |
| Ibragimov et al. | The national economy competitiveness: effect of macroeconomic stability, renewable energy on economic growth | |
| Shao et al. | Estimation, characteristics, and determinants of energy-related industrial CO2 emissions in Shanghai (China), 1994–2009 | |
| CN111142494B (en) | Intelligent control method and system for amine liquid regeneration device | |
| JP2023544067A (en) | Basal medium development method and system | |
| CN105930916A (en) | Parallel modular neural network-based byproduct gas real-time prediction method | |
| Petrović et al. | Impact of financial development on CO2 emissions: improved empirical results | |
| CN116244941A (en) | Park carbon emission accounting method | |
| Ye et al. | A nonlinear interactive grey multivariable model based on dynamic compensation for forecasting the economy-energy-environment system | |
| CN113409072A (en) | Empirical mode decomposition and distributed GRU neural network and price prediction method | |
| Hosseinpour et al. | Machine learning in absorption-based post-combustion carbon capture systems: A state-of-the-art review | |
| Wu et al. | Analysis of carbon emission drivers of secondary industries in Energy “Golden Triangle” area based on LMDI and two-dimensional decoupling model | |
| CN103150581A (en) | Method and device for optimizing boiler based on least square support vector machine (LSSVM) combustion model | |
| Liu et al. | The regulation path of coal consumption based on the total reduction index—a case study in Shandong Province, China | |
| CN117454653A (en) | Energy consumption optimization method for natural gas desulfurization device and electronic equipment | |
| CN116108963A (en) | Electric power carbon emission prediction method and equipment based on integrated learning module | |
| CN115201408A (en) | Method for predicting concentration of sulfur dioxide at desulfurization outlet under all working conditions | |
| Xu et al. | On simulation and optimization of one natural gas industry system under the rough environment | |
| CN114330485A (en) | Power grid investment capacity prediction method based on PLS-SVM-GA algorithm | |
| Tock et al. | Process design optimization strategy to develop energy and cost correlations of CO2 capture processes | |
| Tsai et al. | The exponential grey forecasting model for CO2 emissions in Taiwan | |
| Xu et al. | The research on a novel multivariate grey model and its application in carbon dioxide emissions prediction | |
| Aldinucci et al. | On parallelizing on-line statistics for stochastic biological simulations | |
| Tang et al. | Octane number prediction of blend gasoline based on improved particle swarm optimization | |
| CN117252438A (en) | Automatic evaluation method, computing equipment and storage medium for pollution control of enterprises |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |