CN114429258A - Natural gas purification control method based on energy efficiency evaluation and online optimization platform - Google Patents
Natural gas purification control method based on energy efficiency evaluation and online optimization platform Download PDFInfo
- Publication number
- CN114429258A CN114429258A CN202011186402.7A CN202011186402A CN114429258A CN 114429258 A CN114429258 A CN 114429258A CN 202011186402 A CN202011186402 A CN 202011186402A CN 114429258 A CN114429258 A CN 114429258A
- Authority
- CN
- China
- Prior art keywords
- natural gas
- gas purification
- energy consumption
- energy efficiency
- unit
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/80—Management or planning
- Y02P90/82—Energy audits or management systems therefor
Abstract
The invention relates to a natural gas purification control method based on energy efficiency evaluation and an online optimization platform, comprising the following steps of: acquiring current raw material natural gas parameters, and optimizing by an intelligent algorithm to obtain corresponding key operation parameters of the natural gas purification device when the energy efficiency condition is optimal under the raw material natural gas parameter condition; controlling the corresponding natural gas purification device according to the key operating parameters of the natural gas purification device; the intelligent algorithm can adopt a genetic algorithm to carry out iterative optimization; the optimal energy efficiency condition comprises three-level evaluation standards, and the evaluation standard value can be obtained by predicting after training the neural network model through historical data. The method can guide the control strategy of the natural gas purification device and the public engineering facilities, reduce the total energy consumption and material consumption in the natural gas purification process and reduce the production cost.
Description
Technical Field
The invention relates to a natural gas purification control method based on energy efficiency evaluation and an online optimization platform, and belongs to the technical field of natural gas exploitation and purification.
Background
Natural gas is used as high-quality clean energy, and the specific gravity of the natural gas in the energy consumption structure of China is steadily increased year by year. The purification device of the natural gas purification plant is used for purifying natural gas containing impurities into qualified natural gas and achieving the discharge standard of the whole process. However, the natural gas purification process consumes a large amount of energy, and particularly, the purification process of the natural gas with high sulfur content has great energy-saving potential.
The user's requirements and incoming gas conditions of natural gas purification plants often change, especially at the later stages of the production cycle, the operation of the purification plant deviates from the design conditions. The production process energy-saving measures are mainly used for adjusting and controlling running parameters of a part according to the load, the operation specification and the experience of a dispatcher on the natural gas purification device, the energy utilization maximization cannot be accurately controlled and realized, in order to prevent the situation that product gas does not reach the standard due to insufficient energy and material supply, an overfeeding mode is adopted for production, and the problem of serious energy waste exists.
At present, the energy consumption evaluation of the purification process on site mostly adopts extensive macroscopic energy consumption evaluation indexes, such as comprehensive energy consumption for treating ten thousand square raw material gases. However, the extensive long-period large-span energy consumption statistics is not favorable for mastering the operation condition and the energy consumption level of the purification device in the natural gas purification process, and is difficult to locate the weak link of energy consumption.
Except for the lack of a refined and scientific energy consumption evaluation mode. The difficulty of optimizing the energy consumption in the natural gas purification process is that the purification energy consumption is not only influenced by factors such as raw material gas flow, pressure and components, but also has a relationship with the operation conditions of each unit and key equipment of the purification device, and the key equipment has numerous related operation parameters and strong coupling relevance and has serious nonlinear influence on the system energy consumption. The relationship between the feed gas parameters and a plurality of key operation parameters of the equipment and the energy consumption (such as electricity consumption, fuel gas consumption) and material consumption (such as nitrogen, steam or fresh water consumption) of each equipment is complicated, different operation parameters of the purification equipment are presented under different key operation parameters of the purification equipment, the energy consumption and material consumption of different equipment are reduced, and the treatment capacity of raw natural gas in unit time and the yield of sulfur byproduct in the purification process are influenced. Therefore, it is difficult to achieve the overall process optimization by the conventional control means depending on the experience of the operator or the method of performing the adjustment control based on the feedback of the extensive energy consumption evaluation.
Disclosure of Invention
The invention aims to provide a natural gas purification control method based on energy efficiency evaluation and an online optimization platform, which are used for solving the problem that the whole natural gas purification process is high in energy consumption and difficult to further optimize.
In order to achieve the above object, the scheme of the invention comprises:
the invention discloses a natural gas purification control method based on energy efficiency evaluation, which comprises the following steps:
1) acquiring current raw material natural gas parameters, and optimizing by an intelligent algorithm B to obtain corresponding key operation parameters of the natural gas purification device when the energy efficiency condition is optimal under the raw material natural gas parameter condition;
the energy efficiency conditions comprise one or more of the ratio of total process energy consumption to the corresponding raw material natural gas treatment capacity, the ratio of total process energy consumption to the corresponding product economic value, the sum of unit energy consumption of each process unit of the purification device and the sum of unit energy consumption of each equipment of the purification device; the unit energy consumption of the process unit is the ratio of the energy consumption of the process unit to the flow of the corresponding input raw material or the flow of the corresponding output product, and the unit energy consumption of the equipment is the ratio of the energy consumption of the equipment to the flow of the corresponding treatment substance;
2) controlling the corresponding natural gas purification device according to the key operating parameters of the natural gas purification device;
the process of searching the optimal by the intelligent algorithm B in the step 1) comprises the following steps: firstly, initializing a population, wherein the population comprises key operating parameters of a natural gas purification device; then calculating population fitness, wherein the fitness is an energy efficiency condition, and the energy efficiency condition is calculated through a prediction model A; finally, changing the population and iterating for multiple times to finally select the key operation parameters of the natural gas purification device corresponding to the population with the optimal energy efficiency condition as an optimization result;
the prediction model A is a machine learning model and is obtained by training raw material natural gas parameters, key operating parameters of a natural gas purification device and historical data corresponding to energy efficiency conditions.
In the natural gas purification process, the energy requirement and the material requirement of each purification device are related to parameters such as flow, pressure and impurity content of the raw natural gas to be treated and are also related to a plurality of operation parameters of the purification devices, and the operation parameters of the purification devices are coupled with each other, so that the yield of the byproduct sulfur is determined. The invention firstly focuses on the whole purification process, purification units for realizing different process processes in the purification process or purification equipment for realizing specific functions to establish a more detailed and targeted energy consumption evaluation system, finds out the key operation parameter corresponding to the same raw material natural gas parameter in historical data under the condition of the lowest energy consumption in the purification process through an optimization algorithm according to different evaluation systems, and adjusts and controls each purification device according to the key operation parameter, thereby effectively reducing the total energy consumption in the natural gas purification process flow. The method breaks through the traditional natural gas purification plant, each purification series unit is controlled according to supply and demand, and fuel materials are supplied in excess according to experience. The energy consumption of the whole process of natural gas purification is reduced and optimized.
Further, the total energy consumption of the process is the sum of energy consumption and material consumption in the natural gas purification process; the energy consumption of the process unit is the sum of the energy consumption and the material consumption of the process unit in the natural gas purification process; the energy consumption of the equipment is the sum of the energy consumption and the material consumption of the equipment in the natural gas purification process.
Furthermore, the sum of the energy consumption and the material consumption is obtained by weighting and summing various consumed energy and substances according to respective energy conversion coefficients.
Further, the prediction model a is a neural network model.
Further, the intelligent algorithm B is a genetic algorithm.
The prediction model A can be any machine learning model, the machine learning model is trained through a large amount of historical data, and selected energy efficiency evaluation indexes under different feed gas parameters and key operation parameters of the purification device can be predicted based on the model.
The intelligent algorithm B can adopt an iterative optimization algorithm such as a genetic algorithm or a particle swarm algorithm.
Furthermore, each process unit of the purification device comprises a desulfurization and decarbonization unit, a dehydration unit, a sulfur recovery unit, a tail gas treatment unit and an acid water stripping unit.
And the purification units are distinguished according to the technological process of natural gas purification, and energy consumption evaluation and prediction are carried out by taking the purification units as units, so that the optimal comprehensive energy consumption in the process is favorably realized.
Furthermore, each device of the purification device comprises a desulfurization and decarburization pump unit, a desulfurization and decarburization reboiler, a cooler, a regeneration tower reboiler, a Claus fan, a waste heat boiler, a reaction feeding heater, a sulfur condenser, a burner, an incinerator, a tail gas treatment pump unit and a fan.
Energy consumption evaluation is carried out by taking equipment realizing different basic functions as a unit, the evaluation is more precise, the obtained key operating parameters of the natural gas purification device are more comprehensive, the control based on the key operating parameters is more thorough and sufficient, and the energy consumption optimization and adjustment are faster and more optimal.
Further, the raw natural gas parameters include raw natural gas flow, pressure, hydrogen sulfide content, and carbon dioxide content.
The invention discloses a natural gas purification online optimization platform based on energy efficiency evaluation, which comprises a control system, wherein the control system is connected with natural gas purification devices in a control mode so as to realize the adjustment of key operating parameters of the natural gas purification devices; the control system also executes instructions to realize the natural gas purification control method based on energy efficiency evaluation.
Drawings
FIG. 1 is a flow chart of the method of the present invention;
FIG. 2 is a flow diagram of a purification process of a high sulfur natural gas purification plant complex;
FIG. 3 is a schematic diagram of a model structure of a typical artificial neural network;
FIG. 4 is a diagram showing the comparison of the predicted result of the neural network prediction model A and the actual value of the historical data;
FIG. 5 is a diagram showing the relative error distribution of all sample prediction results of the neural network prediction model A;
FIG. 6 is a schematic flow chart of an iterative optimization algorithm B based on a genetic algorithm;
FIG. 7 is a schematic diagram showing the results of iterative calculation of feed natural gas at a flow rate of 100kNm3/h and a pressure of 7.80MPa using an optimization algorithm B;
FIG. 8 is a schematic diagram of unit energy consumption reference values at different raw gas treatment capacities;
FIG. 9 is a schematic diagram comparing the reference value of unit energy consumption with the actual unit energy consumption under different raw gas treatment capacities;
FIG. 10 is a schematic diagram of process energy consumption factors at different feed gas throughputs;
FIG. 11 is a schematic diagram of the natural gas purification online optimization platform of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings.
The method comprises the following steps:
according to the natural gas purification control method based on energy efficiency evaluation, three-level energy efficiency evaluation indexes related to the natural gas purification process are established according to the on-site natural gas purification process and device operation data, and the corresponding feed gas parameters and the key operation parameters of the purification equipment are determined. The method is shown in fig. 1, and specifically comprises the following steps:
1) firstly, establishing an energy efficiency evaluation index; the energy efficiency evaluation indexes are divided into three levels of energy efficiency evaluation indexes, namely a process level energy efficiency evaluation index, a unit level energy efficiency evaluation index and a device level energy efficiency evaluation index. Wherein, the process level energy efficiency evaluation indexes comprise process unit comprehensive energy consumption and product ten-thousand-yuan production value energy consumption; the unit-level energy efficiency evaluation index comprises unit energy consumption of the process units corresponding to the process units; the equipment level energy efficiency evaluation index comprises unit energy consumption of key equipment in each purification process. The unit comprehensive energy consumption of the process is the ratio of the total energy consumption of the process to the corresponding natural gas treatment amount of the raw material, the ten-thousand-yuan product value energy consumption of the product is the ratio of the total energy consumption of the process to the economic value of the corresponding product, the unit energy consumption of the process unit is the ratio of the energy consumption of the process unit to the corresponding input raw material flow or output product flow, and the unit energy consumption of the key equipment is the ratio of the energy consumption of the equipment to the corresponding treatment substance flow.
2) Establishing a prediction model A; based on historical data, a prediction model A of key operation parameters of different purification devices to the efficiency evaluation index under different fuel natural gas parameters (fuel gas parameters for short) is established. And screening out standard historical data to train the prediction model.
If the selected and established evaluation index is the comprehensive energy consumption of the process unit, obtaining key operation parameters of the historical purification device corresponding to different fuel gas parameters, total energy consumption, material consumption and natural gas treatment capacity of the corresponding process according to historical data; and calculating the unit comprehensive energy consumption of the process as a corresponding evaluation index according to the total energy consumption, the material consumption and the natural gas treatment amount of the process.
If the selected and established evaluation index is the product ten-thousand-yuan production value energy consumption, obtaining key operation parameters of the historical purification device corresponding to different fuel gas parameters, total energy consumption and material consumption of the corresponding process, the output purified natural gas (finished natural gas or commodity natural gas) and the output of the process sulfur according to historical data; and calculating the ten-thousand-yuan product value energy consumption of the product as a corresponding evaluation index according to the total process energy consumption, the material consumption, the produced natural gas of the commodity, the process sulfur yield, the current market price of the unit gas of the commodity and the market price of the sulfur.
If the selected and established evaluation index is the unit energy consumption of the process unit, obtaining key operation parameters of the historical purification device of each process unit, the input raw material flow or the output product flow of each process unit, and the energy consumption and the material consumption of the corresponding process unit under different fuel gas parameters according to historical data; and calculating the unit energy consumption of each process unit, and summing the unit energy consumption of each process unit to serve as a corresponding evaluation index.
If the selected and established evaluation index is the unit energy consumption of the key equipment, obtaining key operation parameters of the historical purification device of each key equipment, the flow of the treatment substance of each key equipment and the energy consumption and material consumption of the corresponding key equipment under different fuel gas parameters according to historical data; and calculating the unit energy consumption of the key equipment of each key equipment, and summing the unit energy consumption of each key equipment to serve as a corresponding evaluation index.
3) Establishing an optimization algorithm model B; establishing an optimization model of the raw material natural gas parameters and the key operation parameters of the purification process when the corresponding evaluation indexes are optimal based on the prediction model A; meanwhile, the energy consumption reference value corresponding to the energy efficiency evaluation index under different raw material gas parameters can be calculated, namely the calculated theoretical optimal energy consumption value under the corresponding raw material gas parameters, the energy-saving potential is reflected by the difference between the energy consumption reference value and the field actual value, and the operation level of the natural gas purification process can be effectively evaluated and the weak energy consumption link can be determined. And (4) when the energy efficiency evaluation index reference value is determined by the optimization algorithm model B, the obtained key operation parameters of the purification process can be used as the optimization guide values of the control parameters of the corresponding purification equipment (step 4).
4) Energy-saving control is carried out in the natural gas purification process; by adjusting and controlling the corresponding equipment, the control parameters of the corresponding equipment reach the key operation parameter guide value or the operation parameters of the corresponding equipment are close to the key operation parameter guide value, so that the purposes of saving energy, reducing consumption and optimizing energy consumption in the natural gas purification process are achieved.
The steps of the present invention are explained in more detail below with reference to examples.
The natural gas purification process selected in this embodiment is a typical high-sulfur natural gas purification process, and mainly includes five main units, i.e., MDEA desulfurization and decarbonization (acid gas removal), TEG dehydration, conventional Claus (Claus) sulfur recovery, hydrogen reduction tail gas treatment, and low-pressure acid water stripping.
Taking a certain high-sulfur natural gas purification plant as an example, the main process flow of the purification process of the purification plant is shown in fig. 2, which shows a process flow of a combined device with two purification series (I and II), and a prediction model a and an optimization algorithm B are both directed at a complete purification series. The purification process of the natural gas with high sulfur content comprises the following steps: removing hydrogen sulfide, partial organic sulfur, carbon dioxide and the like from raw natural gas by using MDEA lean amine liquid through a deacidification unit; the product gas meets the requirement after being dehydrated by a dehydration unit and is output by a long-distance pipeline network; acid gas generated by the deacidification gas unit enters a sulfur recovery unit, is mixed with air and enters a reaction furnace to react to recover sulfur element in the acid gas into liquid sulfur, industrial sulfur is produced by a sulfur forming unit, and reaction gas in the process generates medium-pressure saturated steam by a waste heat boiler; tail gas of the sulfur recovery unit is treated by a tail gas treatment unit, meets the environmental protection requirement and then is conveyed to a tail gas incinerator for incineration, and smoke is discharged through a chimney; acid water generated in the purification process is sent to an acid water stripping unit, the generated purified water is recycled, and acid gas generated by stripping is transmitted to a tail gas treatment unit for treatment.
1. And establishing energy efficiency evaluation indexes from the whole purification process to the main unit and then to the key equipment. The link mainly determines energy efficiency evaluation indexes of all levels.
(1) And (4) evaluating indexes of process level energy efficiency.
Unit energy consumption of the process or comprehensive energy consumption of the process:
the specific energy consumption of the process is the ratio of the total energy consumption of the process to the treatment capacity of the raw material gas, and the specific energy consumption of the process is expressed in terms of the unit energy consumption of the process
Identification in MJ/Nm3The calculation expression is:
wherein M isRaw material gasThe unit of the treatment capacity (or flow rate) of the raw material gas of the process is 104Nm3/t，EProcedureThe total energy consumption of the process is expressed in MJ/t, EProcedureThe energy consumption and material consumption in the process mainly comprise total power consumption, fuel gas consumption, fresh water consumption and the like, and are obtained by weighting and summing according to the national standard and respective energy conversion coefficients, and are calculated by the formula (2):
wherein E is1、E2、E3…ENAnd (4) unifying the dimension weighted and converted values for the various types of consumption.
Secondly, the product has ten thousand yuan production value and energy consumption:
the purification process can produce a byproduct, namely sulfur, while producing commodity natural gas, the index is defined from the product income angle and represents the ratio of the total energy consumption of the system to the economic value of the product, and the index is used for
Identification, the unit is MJ/ten thousand yuan of output value, and the calculation expression is as follows:
wherein M isPurified gasThe unit is 10 for the yield of clean natural gas in the process4Nm3/t，MSulfurThe unit of the sulfur yield in the process is ton/t, and a and b are market unit prices of commodity natural gas and sulfur, and the unit is ten thousand yuan/10 yuan respectively4Nm3Ten thousand yuan/ton.
③ energy consumption factor:
the energy consumption factor represents the ratio of the actual total energy consumption of the process to the corresponding reference energy consumption under a certain working condition, and the ratio is used as
And marking, namely dimensionless quantity, and calculating the expression as follows:
wherein E isDatumRepresenting a process baseline energy consumption value. The energy consumption factor reflects the difference between the actual total energy consumption of the process under a certain feed gas parameter and the minimum energy consumption of the process of the purifying equipment in the optimized operation under the key operation parameter obtained by the optimization algorithm, and the energy-saving potential of the process is directly reflected.
(2) And evaluating indexes of unit-level and equipment-level energy efficiency.
Unit level unit energy consumption:
for each main purification unit in the natural gas purification process, unit energy consumption can be used as a unit-level energy consumption evaluation index, and e is used hereinUIdentification in MJ/Nm3Or MJ/ton, the mathematical expression being:
wherein M isUnit cellRepresents the unit input feed flow or output product flow in units of 104Nm3T or ton/t, EUnit cellRepresents the corresponding energy consumption of the unit, and has the unit of MJ/t, EUnit cellThe energy consumption of various types of energy sources in the unit mainly comprises total power consumption, fuel gas consumption, fresh water consumption and the like, and is obtained by weighting and summing according to the national standard and respective energy conversion coefficients, and the energy consumption is calculated by a formula (6), wherein E1、E2、E3…ENAnd (4) unifying the dimension weighted and converted values for the various types of consumption.
Second equipment level unit energy consumption
For the main equipment in the unit, the unit energy consumption of the equipment can be used as the evaluation index of the equipment level energy consumption, and e is used hereinDIdentification in MJ/Nm3Or MJ/ton, the mathematical expression being:
wherein M isDeviceRepresenting the flow of the substance treated by the apparatus, EDeviceThe corresponding energy consumption of the equipment is represented by various energy consumption mainly comprising total power consumption, fuel gas consumption, fresh water consumption and the like, EDeviceWeighted and summed according to the respective energy conversion coefficients according to the national standard, calculated by the formula (8), wherein E1、E2、E3…ENAnd (4) unifying the dimension weighted and converted values for the various types of consumption.
Regarding the unit-level and equipment-level energy efficiency evaluation indexes, in combination with the examples, the desulfurization and decarburization unit is used for removing acidic components from the raw natural gas, and the unit and the internal main equipment energy efficiency evaluation indexes thereof are shown in table 1.
TABLE 1 evaluation index of desulfurization and decarburization Unit and energy efficiency of Main facility
The dehydration unit is used for dehydrating and dehumidifying the moisture in the purified gas so as to meet the dew point requirement of the pipeline natural gas, and the energy efficiency evaluation indexes of the unit and the internal equipment thereof are shown in table 2.
TABLE 2 evaluation index of dewatering Unit and Equipment energy efficiency
The sulfur recovery unit is used for recovering sulfur element in the acid gas, and specific energy efficiency evaluation indexes of the unit and main equipment in the unit are shown in table 3.
TABLE 3 evaluation index of sulfur recovery unit and equipment energy efficiency
The tail gas treatment device is used for further improving the sulfur recovery rate in the process and leading the discharged flue gas SO2When the standard is reached, the specific energy efficiency evaluation indexes of the units and the internal equipment of the units are shown in a table 4.
TABLE 4 Tail gas treatment Unit and Equipment energy efficiency evaluation index
The acid water stripping unit is used for stripping acid components in acid water generated in the process, and specific energy efficiency evaluation indexes of the device are shown in table 5.
TABLE 5 evaluation index of acid water stripping unit and equipment energy efficiency
2. And establishing a relation prediction model A between the key operation parameters and the correspondingly selected energy efficiency evaluation indexes by using a historical operation data training method, and predicting the energy efficiency evaluation index values under different working conditions.
(1) And determining key operation parameters and feed gas parameters influencing energy efficiency evaluation indexes.
Parameters influencing each level of energy efficiency evaluation indexes comprise uncontrollable raw material gas parameters, raw material gas flow, pressure, hydrogen sulfide content and carbon dioxide content, and key operation parameters of the purification equipment which can be adjusted and controlled on site. In the energy efficiency evaluation system, the key problem is to determine key operation parameters affecting the energy efficiency evaluation index, which are variable parameters in the evaluation system. And obtaining key operation parameters of all levels of evaluation indexes according to the working principle of the purification process and the field operation experience. The difficulty is to determine key operation parameters influencing process-level energy efficiency evaluation indexes. And table 6 shows key operation parameters corresponding to each level of energy efficiency evaluation indexes.
TABLE 6 energy efficiency indexes at different levels and key operating parameters thereof
The operation parameters can be obtained from the operation data of the natural gas purification plant and are used for operation energy efficiency evaluation.
(2) Based on historical data, an intelligent algorithm is adopted for machine learning to establish a prediction model A among raw material natural gas parameters, natural gas purification process key operation parameters and energy efficiency evaluation indexes.
Firstly, raw material gas parameters, key operation parameters and historical big data of original energy consumption and material consumption are collected, and corresponding historical big data of energy efficiency evaluation indexes are obtained through calculation.
Selecting a historical data collection interval, such as 1-3 months in 2019, collecting a feed gas parameter, a key operation parameter of each device at a corresponding time, and total energy consumption, material consumption and product yield data (the energy consumption, the material consumption and the product yield can be measured by using flow, such as MJ/h of energy consumption, ton per hour or cubic meter per hour of material consumption and product yield, and the like; or the output in unit time is used for measuring and the like), and the energy consumption, the material consumption, the intermediate substance processing capacity (including consumption and output) and other data of each device; and energy consumption, material consumption and intermediate substance treatment capacity data of each equipment can be only acquired, and the total energy consumption, material consumption and yield of the whole plant can be calculated based on the data of each equipment. The energy consumption and material consumption mainly comprise the consumption of electricity, fuel gas, supplied water and the like, and the product yield mainly comprises the yield of purified natural gas and sulfur. The historical data may be collected in a manner such that a set of corresponding data is collected at set time intervals. And calculating all levels of energy efficiency evaluation indexes according to the acquired data, or calculating one or more energy efficiency evaluation indexes according to selection. And forming the evaluation index historical big data by the energy efficiency evaluation index, the feed gas parameter and the key operation parameter at the corresponding time.
Secondly, establishing a relation prediction model A between the key operation parameters and the corresponding energy efficiency evaluation indexes by combining an intelligent algorithm according to the historical big data of the energy efficiency evaluation indexes.
And (3) eliminating shutdown and abnormal data (if any) in the historical data, and obtaining a prediction model A which takes key operation parameters as independent variables and energy efficiency evaluation indexes as dependent variables by adopting an artificial intelligence algorithm according to effective historical data (historical data of qualified natural gas produced after purification) of a single purification series. In the embodiment, the prediction model A is established by adopting an artificial neural network, which is a certain simplification, abstraction and simulation of a biological neural structure and is an empirical modeling tool. The method can learn complex input and output relations among data collected from specific problem domains, has good performance in accurate prediction and classification, and is widely used in multiple fields of engineering application at present. The multilayer perceptron artificial neural network is one of the most widely used neural networks in various fields of engineering problems, and comprises an input layer, a hidden layer and an output layer, wherein each layer is composed of neurons. The number of neurons in the input layer is equal to the number of input parameters, namely, the number of raw material gas parameters and key operation parameters; the number of neurons in the output layer is equal to the number of prediction targets, where the prediction targets are selected energy efficiency evaluation indices. The hidden layer can be composed of one or more layers, and the number of the layers and the number of the neurons of the hidden layer can be obtained through trial and error or by combining intelligent algorithm optimization.
FIG. 3 illustrates a typical fully-connected network architecture, where the model receives data input through input layer nodes/neurons, passes it to hidden layer nodes, and finally passes the information to output nodes. The neuron connects to any neuron in the next layer through a communication link associated with a connection Weight (synthetic Weight). Each neuron receives the output of the neurons in the previous layer and performs weighted summation with the connection weight, and the deviation is added on the basis to obtain the single output of the neuron through calculation of an activation function. To adapt to a particular data/problem, a corresponding artificial neural network model needs to be configured and trained, and the training process can be viewed as minimizing the error between the desired output and the actual output of the model. The training of the artificial neural network model is a process of introducing randomly selected samples with input data and expected output into the artificial neural network configuration model, determining the error between the expected output value and the actual output of the model, and minimizing the error by modifying/optimizing the connection weight and deviation of the neurons.
The model A is predicted by the artificial neural network, the input of the model is a raw material gas parameter and a key influence parameter, and the output of the model is all or selected part of energy efficiency evaluation indexes. Samples for establishing the model are historical operating data of 1-3 months in 2019, and a group of samples is extracted every hour in the production process and is used as effective historical data. Randomly dividing the obtained sample data into three types: the percentage of the test set is 70%, 15% and 15% respectively as a training set, a validation set and a test set.
Before inputting sample data into the neural network model for training, input data is normalized to the range of [ -1,1] using the minmax function in Matlab. The transfer function of the hidden layer is an S-shaped function 'tandig', the transfer function of the output layer is a linear function 'purelin', the training function of the network adopts a 'trainlm' function, and the function updates the weight and the deviation value based on a Levenberg-Marquardt algorithm. A model is established by adopting a single-layer hidden layer network, the number of neurons in the optimal hidden layer is found by using a trial-and-error method, the Mean Square Error (MSE) is adopted as a network performance function, and the correlation between expected data and actual network output is measured by a regression R value. As the initial values of the samples used for training the network, the network weight and the deviation are randomly selected and generated, and the neural networks with the same structure have different training results each time, each structure neural network is trained for 5 times, and the mean square error value is taken as the mean square error average value, the mean square error values calculated by the neural networks with different structures are different, the research finds that when the number of the neurons in the hidden layer is 18, the mean square error value and the correlation coefficient value of the test set are ideal, and therefore, the neural networks are selected for subsequent research.
In order to quantify the difference between the energy-carrying working medium consumption and the predicted result of the energy consumption and material consumption prediction model A and the actual value, the average relative deviation (AAD%) is defined and calculated by the following formula, wherein yi，xiAnd n represents the true value, the calculated value of the network model, and the number of samples, respectively.
FIG. 4 is a comparison graph of the predicted value of unit energy consumption of the process and the actual historical value under different conditions, i.e., different feed gas parameters and key operating parameters. FIG. 5 shows the relative error distribution of the predicted values, with an error rate within + -5% and good overall prediction accuracy.
3. And (3) establishing an optimization algorithm model B by using an iterative optimization method based on the relationship prediction model A among the feed gas parameters, the key operating parameters of the natural gas purification device and the corresponding energy efficiency evaluation indexes determined in the step (2).
And based on the established relation prediction model A among the feed gas parameters, the key operation parameters and the energy efficiency evaluation indexes, establishing an optimization algorithm model B among the feed gas parameters and the key operation parameters of the corresponding purification device when the energy efficiency evaluation indexes are optimal, and optimizing to obtain the optimal values of the energy efficiency evaluation indexes, namely the reference values with the lowest energy consumption, by changing the numerical values of the adjustable key operation parameters under each feed gas parameter value. And when the reference value is determined, the guide values of the corresponding adjustable key operating parameters are also determined, and the guide values can be used for guiding the field parameter adjusting work of the key operating parameters, so that the lowest energy consumption in the natural gas purification process is realized.
One or more energy efficiency evaluation indexes can be selected from the three-level evaluation indexes, after the energy efficiency evaluation indexes are selected, the corresponding concerned key operation parameters are also determined at the same time (determined according to the table 6 above), after the raw material gas parameters are obtained, the key operation parameter values corresponding to the optimal selected energy efficiency evaluation indexes are respectively calculated by optimizing through the optimization algorithm model B, the key operation parameter values corresponding to the optimal energy efficiency evaluation indexes are called key operation parameter guide values, and the optimal energy efficiency evaluation index values are also the energy efficiency evaluation index reference values corresponding to the lowest energy consumption indexes. Different energy efficiency evaluation indexes are correspondingly provided with the same key operation parameters, so that different key operation parameter guide values can be obtained for different key operation parameters when the different energy efficiency evaluation indexes are optimal, when the key operation parameter guide values are used for controlling and adjusting the operation of the natural gas purification device, one of the key operation parameter guide values can be selected according to actual conditions or field experience, or the average of the different key operation parameter guide values is calculated, or weights are set for the different energy efficiency evaluation indexes, and the key operation parameter guide values corresponding to the energy efficiency evaluation indexes are selected according to the weights and are used for controlling and adjusting the natural gas purification device.
Taking process unit energy consumption as an energy efficiency evaluation index as an example, an optimization relation between a feed gas parameter and a corresponding key operation parameter when the process unit energy consumption is the lowest (the energy efficiency evaluation index is optimal) is established, in the embodiment, an optimization algorithm model B is established by adopting a genetic algorithm, iterative adaptive optimization is carried out, and finally, process reference energy consumption and a key operation parameter for guidance (a key operation parameter guidance value) of a purification unit under different working conditions are found.
The genetic algorithm calculation process used in this example is shown in FIG. 6 for a technical roadmap. The basic elements of the genetic algorithm mainly comprise: chromosome coding, population initialization, individual fitness calculation, selection operation, crossover operation and mutation operation aiming at a specific problem to be solved. The genetic algorithm starts from an initial population, and finally converges to one or more individuals with the best fitness through multi-generation evolution, so that the optimal solution or the satisfactory solution of the problem is obtained.
Each individual in the population is an array, and corresponds to different key operation parameter variables and feed gas parameter variables, the individual fitness value is an energy efficiency evaluation index (in the embodiment, the energy consumption of a process unit) calculated by using the energy efficiency evaluation index prediction model A established in the step 2, the prediction model A is a fitness function, and the feed gas parameter does not participate in variation and serves as a constraint condition; calculating individual fitness through an optimization algorithm, comparing the individual fitness values one by one, and changing key operation parameters in individuals through cross variation until a fitness minimum value (energy consumption minimum value) is found, namely the key operation parameters of the purification device corresponding to the lowest process unit energy consumption under the feed gas parameters.
The initial population number, the iteration number, the cross probability and the mutation probability of the genetic algorithm designed in this embodiment are set to 300, 200, 0.5 and 0.05, respectively. With a raw natural gas throughput of 100kNm3The change curve of the optimal fitness value in the iterative calculation process of the genetic algorithm is shown in fig. 7, and it can be seen that when the iteration times reach 130 generations, the calculation result tends to converge and remain stable, and the output result after the iteration is finished is 100kNm of the device3The lowest value of the unit energy consumption of the process under the pressure of 7.80 MPa.
In fig. 8, black squares are obtained by performing optimization calculation on the optimal process unit energy consumption, i.e., the reference value of the process unit energy consumption, by using the optimization algorithm model B under different raw material gas treatment capacities (flow rates). In field engineering application, according to the calculation result of the optimization model, the relationship between the feed gas treatment capacity and the unit energy consumption reference value in the process can be fitted, and the fitting curve in the embodiment is shown in a curve in fig. 8. As can be seen from FIG. 8, as the treatment capacity of the raw material gas increases, the unit energy consumption reference value of the process also decreases, and the trend is in good agreement with the theory and practice of on-site operation.
4. And substituting the feed gas parameters actually operated on site into the optimization algorithm model B, calculating to obtain an energy efficiency evaluation index reference value, and determining a key operation parameter guide value corresponding to the energy efficiency evaluation index reference value.
In this embodiment, the process unit energy consumption is an energy efficiency evaluation index, the process unit energy consumption reference value under different field feed gas parameters is obtained by solving through the optimization algorithm model B, and the black squares in fig. 9 represent the actual purification process unit energy consumption values, which are all higher than the process unit energy consumption reference value (i.e., the reference unit consumption represented by the curve) under the same feed gas throughput (feed gas flow).
Along with the increase of the treatment capacity of the raw material gas, the difference between the actual value and the reference value of the field energy efficiency evaluation index is gradually reduced and is in good agreement with the field actual operation. The difference between the actual value and the reference value can also be used for analyzing that the process has greater energy-saving potential under the condition of low raw material gas treatment amount. Fig. 10 shows energy consumption factors under different raw material gas treatment amounts, and the actual operation condition operation level can be visually judged according to the energy efficiency index. Under actual working conditions, the difference value between the actual operation value of the key operation parameter and the guidance value of the key operation parameter calculated by the optimization algorithm model B is a field optimization space, and direct support is provided for optimization operation, namely, each purification device is correspondingly controlled according to the guidance value, each key operation parameter is adjusted towards the guidance value, and the comprehensive energy consumption in the natural gas purification process is effectively reduced.
The natural gas purification control method not only considers the influence of the difference of the feed gas parameters on the actual operation energy consumption level; the influence of key operation parameters on the actual operation energy consumption level under the same raw material gas parameters is also considered. Meanwhile, a plurality of energy efficiency evaluation indexes of three levels are provided, and the potential of natural gas energy consumption optimization is evaluated through the operation condition of field equipment and the reference value with the lowest energy consumption obtained through optimization. The method not only realizes scientific and visual evaluation of the operation level, the energy consumption change rule and the energy-saving space under different working conditions, but also provides an easy-to-implement operation parameter optimization guidance for the optimization operation of the purification process, and realizes the energy-saving operation of natural gas purification.
The platform embodiment is as follows:
the embodiment provides an energy efficiency evaluation-based natural gas purification online optimization platform, as shown in fig. 11, which includes a memory, a processor and an internal bus, wherein the processor and the memory are communicated with each other through the internal bus.
The processor can be a microprocessor MCU, a programmable logic device FPGA and other processing devices.
The memory can be various memories for storing information by using an electric energy mode, such as RAM, ROM and the like; various memories for storing information by magnetic energy, such as a hard disk, a floppy disk, a magnetic tape, a core memory, a bubble memory, a usb disk, etc.; various types of memory that store information optically, such as CDs, DVDs, etc., are used. Of course, there are other types of memory, such as quantum memory, graphene memory, and the like.
The processor can call logic instructions in the memory to realize a natural gas purification control method based on energy efficiency evaluation. The method is described in detail in the method embodiments, and is not described herein again.
Claims (9)
1. A natural gas purification control method based on energy efficiency evaluation is characterized by comprising the following steps:
1) acquiring current raw material natural gas parameters, and optimizing by an intelligent algorithm B to obtain corresponding key operation parameters of the natural gas purification device when the energy efficiency condition is optimal under the raw material natural gas parameter condition;
the energy efficiency conditions comprise one or more of the ratio of total process energy consumption to the corresponding raw material natural gas treatment capacity, the ratio of total process energy consumption to the corresponding product economic value, the sum of unit energy consumption of each process unit of the purification device and the sum of unit energy consumption of each equipment of the purification device; the unit energy consumption of the process unit is the ratio of the energy consumption of the process unit to the flow of the corresponding input raw material or the flow of the corresponding output product, and the unit energy consumption of the equipment is the ratio of the energy consumption of the equipment to the flow of the corresponding treatment substance;
2) controlling the corresponding natural gas purification device according to the key operating parameters of the natural gas purification device;
the process of searching the optimal by the intelligent algorithm B in the step 1) comprises the following steps: firstly, initializing a population, wherein the population comprises key operating parameters of a natural gas purification device; then calculating population fitness, wherein the fitness is an energy efficiency condition, and the energy efficiency condition is calculated through a prediction model A; finally, changing the population and iterating for multiple times to finally select the operation parameters of the natural gas purification device corresponding to the population with the optimal energy efficiency condition as an optimization result;
the prediction model A is a machine learning model and is obtained by training raw material natural gas parameters, key operating parameters of a natural gas purification device and historical data corresponding to energy efficiency conditions.
2. The natural gas purification control method based on energy efficiency evaluation according to claim 1, wherein the total process energy consumption is the sum of energy consumption and material consumption in the natural gas purification process; the energy consumption of the process unit is the sum of the energy consumption and the material consumption of the process unit in the natural gas purification process; the energy consumption of the equipment is the sum of the energy consumption and the material consumption of the equipment in the natural gas purification process.
3. The natural gas purification control method based on energy efficiency evaluation according to claim 2, characterized in that the sum of the energy consumption and the material consumption is obtained by weighting and summing various consumed energy sources and substances according to respective energy conversion coefficients.
4. The natural gas purification control method based on energy efficiency evaluation according to claim 1, characterized in that the prediction model A is a neural network model.
5. The natural gas purification control method based on energy efficiency evaluation according to claim 4, wherein the intelligent algorithm B is a genetic algorithm.
6. The natural gas purification control method based on energy efficiency evaluation according to claim 1, wherein each process unit of the purification device comprises a desulfurization and decarbonization unit, a dehydration unit, a sulfur recovery unit, a tail gas treatment unit and an acid water stripping unit.
7. The natural gas purification control method based on energy efficiency evaluation according to claim 1, wherein each of the purification devices comprises a desulfurization and decarburization pump unit, a desulfurization and decarburization reboiler, a cooler, a regeneration tower reboiler, a Claus fan, a waste heat boiler, a reaction feed heater, a sulfur condenser, a burner, an incinerator, a tail gas treatment pump unit, and a fan.
8. The natural gas purification control method based on energy efficiency evaluation according to claim 1, wherein the raw natural gas parameters include raw natural gas flow rate, pressure, hydrogen sulfide content, and carbon dioxide content.
9. The natural gas purification online optimization platform based on energy efficiency evaluation is characterized by comprising a control system, wherein the control system is connected with natural gas purification devices in a control mode to adjust key operation parameters of the natural gas purification devices; the control system further executes instructions to realize the natural gas purification control method based on energy efficiency evaluation according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011186402.7A CN114429258A (en) | 2020-10-29 | 2020-10-29 | Natural gas purification control method based on energy efficiency evaluation and online optimization platform |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011186402.7A CN114429258A (en) | 2020-10-29 | 2020-10-29 | Natural gas purification control method based on energy efficiency evaluation and online optimization platform |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114429258A true CN114429258A (en) | 2022-05-03 |
Family
ID=81310392
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011186402.7A Pending CN114429258A (en) | 2020-10-29 | 2020-10-29 | Natural gas purification control method based on energy efficiency evaluation and online optimization platform |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114429258A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116307131A (en) * | 2023-02-14 | 2023-06-23 | 北京市燃气集团有限责任公司 | System parameter determining method and device for natural gas recovery system |
-
2020
- 2020-10-29 CN CN202011186402.7A patent/CN114429258A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116307131A (en) * | 2023-02-14 | 2023-06-23 | 北京市燃气集团有限责任公司 | System parameter determining method and device for natural gas recovery system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2020088485A1 (en) | Intelligent multi-pollutant ultra-low emission system and global optimization method | |
| US9747544B2 (en) | Method and system for wastewater treatment based on dissolved oxygen control by fuzzy neural network | |
| CN110263988B (en) | Data operation optimization method based on power plant desulfurization system | |
| CN102693451B (en) | Method for predicting ammonia process flue gas desulphurization efficiency based on multiple parameters | |
| CN103744293B (en) | Wastewater treatment monitoring method and system based on fuzzy neural network | |
| CN104636600B (en) | High sulfur-containing natural gas purification Technology Modeling, optimization method based on extreme learning machine | |
| Wang et al. | Multi-objective optimization of synergic energy conservation and CO2 emission reduction in China's iron and steel industry under uncertainty | |
| CN114427684A (en) | Control method and control device for combustion furnace in natural gas purification process | |
| CN104656441B (en) | Gas purifying process modeling optimization method based on Unscented kalman neutral net | |
| CN109146121A (en) | The power predicating method stopped in the case of limited production based on PSO-BP model | |
| CN110263395A (en) | The power plant's denitration running optimizatin method and system analyzed based on numerical simulation and data | |
| CN105302973A (en) | MOEA/D algorithm based aluminum electrolysis production optimization method | |
| US20220365521A1 (en) | Virtual simulation manufacturing platform based on automatic control | |
| CN109473182A (en) | A kind of MBR film permeability rate intelligent detecting method based on deepness belief network | |
| CN104657586A (en) | Abnormal working condition detection-based high-sulfur natural gas purification process modeling optimization method | |
| Wang et al. | A full-view management method based on artificial neural networks for energy and material-savings in wastewater treatment plants | |
| CN113189881A (en) | Multi-objective optimization control method and system for sewage treatment | |
| CN111639820A (en) | Energy consumption parameter optimization method and system for cement kiln production | |
| CN114429258A (en) | Natural gas purification control method based on energy efficiency evaluation and online optimization platform | |
| CN106292296B (en) | Water island dosing On-Line Control Method and device based on GA SVM | |
| CN103488085A (en) | Multi-objective optimization control method of methyl alcohol four-tower rectification system | |
| CN114429236A (en) | Natural gas purification process control method | |
| CN101598927B (en) | Control system of soda carbonization technique based on neural network and control method thereof | |
| CN106769748B (en) | Intelligent detection system for water permeability of membrane bioreactor-MBR (Membrane bioreactor) | |
| CN105302976A (en) | Aluminum electrolysis production optimization method based on SPEA2 algorithm |
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 |