CN110263988B - Data operation optimization method based on power plant desulfurization system - Google Patents
Data operation optimization method based on power plant desulfurization system Download PDFInfo
- Publication number
- CN110263988B CN110263988B CN201910490848.XA CN201910490848A CN110263988B CN 110263988 B CN110263988 B CN 110263988B CN 201910490848 A CN201910490848 A CN 201910490848A CN 110263988 B CN110263988 B CN 110263988B
- Authority
- CN
- China
- Prior art keywords
- data
- actual operation
- desulfurization system
- operation data
- power plant
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
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
- G06Q10/04—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
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E40/00—Technologies for an efficient electrical power generation, transmission or distribution
- Y02E40/70—Smart grids as climate change mitigation technology in the energy generation sector
-
- 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
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Abstract
The invention discloses a desulfurization method based on a power plantA method for optimizing data operation of a system, the method comprising: acquiring actual operation data of an actual operation system of a power station within a certain time period, and preprocessing and regression analysis are carried out on the actual operation data; dividing different working conditions according to the operation load, and performing numerical simulation to obtain the flow field, the temperature and the SO of the whole desulfurization system under different working conditions 2 Component distribution; carrying out big data analysis on the actual operation data of the desulfurization system of the coal-fired power plant to obtain an optimal interval of the operation data under a determined working condition; and practicing the big data optimizing result in the simulation result to check the accuracy of the optimizing result. The invention firstly distinguishes working conditions before building the neural network prediction model, which reduces data quantity, and the relation between the output parameters of energy consumption and sulfur removal rate and the influence factors is relatively clear and simple, thereby being beneficial to ensuring precision.
Description
Technical Field
The invention relates to the technical field of air pollution control of coal-fired boilers, in particular to a data operation optimization method based on a power plant desulfurization system.
Background
At present, environmental pollution has become one of main road blocking tigers which obstruct the economic health and high-quality sustainable development of the country, and the coal-fired power station is taken as a key treatment object of environmental problems, so that the country continuously improves the pollutant emission standard. In order to meet pollutant emission standards, coal-fired power plants often take measures for removing pollutants by using sufficient materials, which causes waste of resources to a certain extent.
Meanwhile, the desulfurization system simultaneously involves the problems of heat and mass transfer, acid-base neutralization, water evaporation, liquid drop coalescence, crushing and the like, and the actual operation condition is complex, although a plurality of students adopt related software to realize the functions of flow field, temperature field and SO in the desulfurization tower 2 The problems of distribution and the like are subjected to detailed simulation research, but on the basis of a large amount of actual operation data, the system analysis of the desulfurization system by combining numerical simulation is quite available.
In addition, during many years of operation of the power station, a large amount of precious actual operation data is stored through various working conditions. Most power stations can not utilize the precious data resources, so that the precious data resources are wasted greatly, and precious network and physical space are occupied.
Under the circumstance, the development progress of big data and intelligent computing technology provides a new development direction for the fine management of the power station. Big data analysis technology is gradually focused, researched and applied to more and more coal-fired power plants due to the remarkable advantages of accuracy, high speed, visualization and the like. The deep analysis of the actual operation data of the desulfurization system by utilizing the big data technology has become one of important contents of pollutant treatment of the coal-fired power plant, system operation optimization and efficiency improvement.
Disclosure of Invention
The invention aims to: the invention aims at the problems, provides a method for providing a strategy for the operation optimization of a desulfurization system by taking theoretical analysis as a basis and numerical simulation as an auxiliary and taking big data analysis as a means, and aims to solve the problems of energy and resource waste of the prior desulfurization system for meeting the national pollutant emission standard.
The technical scheme is as follows: the invention is based on a theoretical model of a pollutant control system, takes the actual flow field simulation of a desulfurization system as an assistance and takes a mathematical model built by actual operation data as a core. The three models cooperate with each other and complement each other. The method comprises the following specific practical steps:
(1) Acquiring actual operation data of an actual operation system of a power station within a certain time period, and preprocessing the actual operation data and carrying out regression analysis on the actual operation data;
(2) Dividing different working conditions according to the operation load, and performing numerical simulation to obtain the flow field, temperature and SO of the whole desulfurization system under different working conditions 2 Component distribution;
(3) Big data analysis is carried out on the actual operation data of the desulfurization system of the coal-fired power plant, and the method specifically comprises the following steps:
(31) Regression analysis is performed on the fixed working condition data: according to removal of SO per unit mass 2 Carrying out regression calculation on the preprocessed data by the consumed currency, and analyzing factors influencing the energy consumption difference under the determined working condition;
(32) Screening influence factors: analyzing and determining operation data which are most critical to the influence of energy consumption under the working condition, and screening the operation data which accord with a preset threshold value as an influence factor set, wherein the influence factor set is a subset of the obtained actual operation data of the power station;
(33) Building a mathematical prediction model: taking the parameter data of the influence factor set as input, adopting a neural network to construct a mathematical prediction model, taking part of actual operation data quantity obtained after pretreatment as training data, and outputting as an energy consumption evaluation index;
(34) Auditing and predicting model: outputting and predicting the prediction model under the same working condition of the power station by using other actual operation data except training data, setting a proper error line, judging the accuracy of the model, and if the verification is passed, entering a step (35), otherwise, returning to the step (33);
(35) And (3) algorithm optimizing: and searching the global optimal solution set or the optimal interval of the prediction model under the determined working condition by utilizing a genetic algorithm.
(4) And (3) bringing the optimal solution set or the optimal interval obtained by data analysis into the obtained simulation model, and checking the correctness of the optimal solution set and the optimal interval.
Further, the method comprises the steps of:
in the step (1), the actual operation data includes: unit load, coal type, FGD inlet gas quantity, FGD outlet gas quantity, sulfur quantity, temperature, speed, circulating slurry flow, slurry density in a desulfurizing tower, absorption tower slurry PH, absorption tower slurry liquid level, supplemental slurry density, flow, oxidation fan component, power consumption and stirrer power consumption.
Further, the method comprises the steps of:
in the step (2), the numerical simulation specifically includes:
(21) According to the actual structure and the actual size of the actual operation system equipment of the power station, adopting Gambit software to establish a full-system three-dimensional physical model comprising a boiler furnace, a horizontal flue, each decontamination device and a tail flue;
(22) Taking non-uniformity conditions at the inlet of the desulfurization system as inlet boundary conditions of the full-system three-dimensional physical model, and using Fluent software to simulate and calculate the flow field, temperature and SO of the whole desulfurization system under different working conditions 2 Component distribution;
(23) And comparing and analyzing the numerical simulation result with actual operation parameter data, introducing a correction factor, checking the reliability of the full-system three-dimensional physical model and the simulation result, and if the checking is passed, entering the big data analysis, otherwise, carrying out numerical simulation again.
Further, the method comprises the steps of:
in the step (1), the pretreatment includes: firstly, performing reliability audit on the obtained operation data, and removing unreasonable data; secondly, supplementing missing data by adopting a weighted filling method; and finally, denoising the parameter data with frequent fluctuation.
Further, the method comprises the steps of:
the method further comprises the steps of: and (3) carrying out numerical simulation on the final optimized parameter interval in the step (35), taking the relevant parameters of the optimal solution as input of the numerical simulation, judging whether the parameter optimal interval obtained by big data analysis can meet the sulfur removal effect, if so, integrating the parameter value intervals under different working conditions to obtain the final optimized parameter interval, otherwise, replacing the input parameters and carrying out numerical simulation again.
Further, the method comprises the steps of:
in the step (32), a method adopted for analyzing and determining operation data which is most critical to the influence of energy consumption under the working condition is an ash correlation entropy analysis method, and the method specifically comprises the following steps:
(321) Initializing data; x is X 0 ＝{X 0 (i)|i＝1,2,...,m},X k ＝{X k (i) I=1, 2,..m }, m represents the sequence length and n represents the dimension.
X' 0 ＝{X 0 (i)/X 0 (1)|i＝1,2,...,m},X' k ＝{X k (i)/X k (1)|i＝1,2,...,m}
(322) Calculating a data column level difference matrix
(323) Find two-stage minimum difference Y min Two-stage maximum difference Y max
y min ＝min(min(Y))，y max ＝max(max(Y))
(324) Calculating an association matrix ζ
Wherein ζ ij ＝(y min +εy max )/(y ij +εy max ),i＝1,2,...,n；j＝1,2,...,m.0＜ε＜1，ε＝0.5；
(325) Calculating gray correlation matrix E r ：
P i,j ＝ζ ij /ζ i
E r (X i )＝H(R i )/H m ,H m ＝ln(m)。
Further, the method comprises the steps of:
in the step (2), the method specifically adopted for dividing the running load into different working conditions is to divide the running load into the different working conditions according to the rated load proportion by adopting a traditional method or to divide the running load into different working conditions according to data distribution by adopting a clustering analysis method.
The beneficial effects are that: compared with the prior art, the invention has the remarkable advantages that: 1. the invention firstly distinguishes working conditions before building the neural network prediction model, has smaller data volume, and has relatively clear and simple relation between output parameters such as energy consumption, sulfur removal rate and the like and influence factors, so that input parameters are always screened to a certain extent, and the precision is ensured; 2. the working condition distinction of the invention obviously weakens the parameter fluctuation and obviously reduces the data volume, which greatly reduces the complexity of data analysis and is beneficial to obtaining stable solution and optimal solution under specific working conditions; 3. the invention relates to a method for providing a strategy for operation optimization of a desulfurization system by taking numerical simulation as an aid and taking analysis of big data of the desulfurization system as a means, which aims to improve the energy utilization efficiency of the desulfurization system of a coal-fired power plant, reduce the pollutant removal cost and save energy; 4. according to the invention, a mathematical prediction model for determining the working condition is built, the relation among all operation data is analyzed through big data analysis, an operation optimization and improvement strategy is provided for the desulfurization system, the problem of unreasonable energy resource utilization caused by full materials in the conventional desulfurization system is solved, and the effect of optimizing and scheduling power station resources is achieved.
Drawings
FIG. 1 is a flow chart of a method according to one embodiment of the invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in detail with reference to the accompanying drawings and specific embodiments.
According to the method, a power station desulfurization system is taken as an analysis research object, actual operation data of the power station of the system is analyzed in a deep level by means of a Fluent software simulation and big data analysis method, data information which cannot be provided by the power station but has important significance can be obtained, a mathematical prediction model can be built, a model local and global optimal solution can be obtained, and meanwhile, a theoretical model is taken as an auxiliary, and an operation optimization and improvement strategy is provided for the actual operation of the desulfurization system by combining the three.
Referring to fig. 1, the data operation optimization method based on the power plant desulfurization system specifically includes:
s1) establishing a theoretical model of a desulfurization system of the coal-fired power plant and obtaining required data: and building a theoretical model according to the actual equipment assembly and the specific structure of the power station, and building an energy balance and material conservation theoretical model of the power station, wherein the size ratio of the energy balance to the prototype is 1:1.
To remove SO of unit mass 2 The consumed currency is an energy consumption evaluation index, and the data required by the project are analyzed and cooperated with the power station to obtain the system structural parameters of the power station and the operation data in a certain period of time. The energy consumption evaluation index is defined by the following formula.
Energy consumption = a x consumption + b x consumption-c x output
In the formula, the produced product is mainly gypsum, and a, b and c represent market unit price of three materials.
The acquired operational data should include, but is not limited to, the following parameters: unit load, coal type, FGD inlet (outlet) gas quantity, sulfur quantity, temperature, speed, circulating slurry flow, slurry density in a desulfurizing tower, slurry PH of an absorption tower, slurry liquid level of the absorption tower, supplementing slurry density, flow, oxidation fan component, power consumption and stirrer power consumption.
S2) preprocessing and analyzing actual operation data of the power station: performing reliability audit on the obtained operation data, and eliminating unreasonable data in the operation data; supplementing the missing data by adopting a weighted filling method; and denoising the parameter data (such as pressure) with frequent fluctuation, wherein the denoising method can adopt an SG filtering method.
And divide different working conditions according to the running load, in one embodiment of the invention, can adopt the traditional method to divide according to the proportion of rated load, such as rated load of 50%, 70%; the data distribution can also be differentiated by adopting a cluster analysis method.
S3) carrying out regression analysis on the data after the pretreatment of S2): and (3) carrying out regression calculation on the data by taking the energy consumption evaluation index and the traditional index sulfur removal rate in the S1) and taking the calcium-sulfur ratio as a target parameter.
The parameters such as desulfurization rate, calcium-sulfur ratio and the like can be obtained through regression calculation. Due to factors such as design margin of desulfurization equipment and sufficient materials in the actual running process, the desulfurization rate is always higher than the national ultra-low emission requirement, and the too high desulfurization rate has direct influence on energy consumption. On the premise of meeting the ultra-low emission standard, the rate at which the sulfur removal rate can be reduced is often S5) the accuracy requirement of the prediction model in the big data analysis.
S4) obtaining parameters which are not fully provided by the power station but are significant through simulation, wherein in one embodiment of the invention, the parameters are specifically the actual flow field, the temperature field and the SO of the desulfurization system 2 Component distribution.
Numerical simulation is performed under the classification load in S2). The simulation comprises the following specific steps:
(1) According to the actual structure and the actual size of the actual operation system equipment of the power station, adopting Gambit software to establish a full-system three-dimensional physical model comprising a boiler furnace, a horizontal flue, each decontamination device and a tail flue;
(2) Non-uniformity conditions at the inlet of the desulfurization system are obtained as inlet boundary conditions of a calculation model by combining power station related data through experimental and field test means, including but not limited to speed distribution, temperature distribution and component concentration distribution. The flow field, the temperature and the SO of the whole desulfurization system (inlet, desulfurization tower and outlet) under different working conditions are obtained by utilizing Fluent software 2 Component distribution;
(3) And comparing and analyzing the simulation result with the actual operation parameter data of the power station, introducing a correction factor, and checking the reliability of the constructed physical model and the simulation result. If the verification is passed, the next step of big data analysis is carried out, otherwise S4 is carried out again;
s5) big data analysis: and carrying out big data analysis on actual operation data of the desulfurization system of the coal-fired power plant.
Taking the distinguishing working condition as an example, the method specifically comprises the following steps:
(51) Regression analysis is performed on the fixed working condition data: and (3) carrying out regression calculation on the data after the pretreatment in the step (S2) according to the energy consumption evaluation index in the step (S1), and primarily analyzing factors influencing the energy consumption difference under the determined working condition based on a theoretical model. On the premise of distinguishing working conditions, the logic relationship is simple, the data size is small, so that the energy consumption can be analyzed by adopting a multi-factor regression analysis method, the obtained operation data is taken as an independent variable, and the energy consumption is taken as a dependent variable.
(52) Screening influence factors: by using a correlation method, the embodiment adopts an ash correlation entropy analysis method to analyze and determine operation data which is most critical to the influence of energy consumption under the working condition, and sets up a threshold value to screen a plurality of factors.
The ash correlation entropy analysis method specifically comprises the following steps:
(521) Initializing data; x is X 0 ＝{X 0 (i)|i＝1,2,...,m},X k ＝{X k (i)|i＝1,2,...,m}
X' 0 ＝{X 0 (i)/X 0 (1)|i＝1,2,...,m},X' k ＝{X k (i)/X k (1)|i＝1,2,...,m}
(522) Calculating a data column level difference matrix
(523) Find two-stage minimum difference Y min Two-stage maximum difference Y max
y min ＝min(min(Y)),y max ＝max(max(Y))
(524) Calculating an association matrix ζ
Wherein ζ ij ＝(y min +εy max )/(y ij +εy max ),i＝1,2,...,n；j＝1,2,...,m.0＜ε＜1，ε＝0.5；
(525) Calculating gray correlation matrix E r ：
P i,j ＝ζ ij /ζ i
E r (X i )＝H(R i )/H m ,H m ＝ln(m)
(53) Building a mathematical prediction model: based on the parameter data of the influence factor set, a mathematical prediction model is built by means of a neural network, a vector machine and the like. The mathematical prediction model takes the parameters of the influence factor set as input, takes the actual operation data after the data preprocessing of S2) as training data, in this embodiment, 95% of the data quantity is selected as training data, the remaining 5% is used for auditing the prediction model, and the output is an energy consumption evaluation index. In addition, parameters such as sulfur removal rate, calcium-sulfur ratio and the like can be added as a multi-output model. If the neural network is used for building an energy consumption and sulfur removal rate dual-factor output model, the optimal solution set meeting a plurality of parameters is favorably obtained, and if the neural network is not built, related optimizing results are automatically deleted in a simulation stage;
(54) Auditing and predicting model: and outputting and predicting the prediction model under the same working condition by using non-model building data (remaining 5% data) of the power station under the same working condition, setting a proper error line, and judging the accuracy of the model. If the audit passes, step (55) is entered, otherwise step (53) is reverted to. If none of the multiple built models passes the audit, returning to the step (52) to check whether the physical model and the required data are missing;
(55) And searching and determining the local and global optimal solutions of the prediction model under the working condition by utilizing a proper algorithm. In the embodiment of the invention, a genetic algorithm or an artificial bee colony algorithm is adopted, namely: on the basis of constructing the prediction model, combining a genetic algorithm or an artificial bee colony algorithm, taking key influence factor data obtained by the genetic algorithm or the artificial bee colony algorithm as model input, and searching an optimal value interval of each parameter. In order to avoid the influence of discrete value points on the optimizing result, the related threshold value can be set by utilizing the parameters of the calcium-sulfur ratio and the sulfur removal rate.
S6) judging whether the obtained optimizing solution meets theoretical constraint or not by combining the theoretical model in the S1) and the obtained optimal value interval, and determining an optimal interval of each key influence factor of the system under a determined working condition;
s7) carrying out numerical simulation on the optimal section obtained in the S6) by using Fluent software, taking the relevant parameters of the optimal solution as input of the numerical simulation, referring to the simulation result of the S4), judging the correctness of the parameter optimal section obtained by big data analysis, if so, carrying out the S8), otherwise, returning to the S6);
s8) integrating parameter value intervals under different working conditions to obtain a final optimized parameter interval, and analyzing the dynamic relation between the optimal interval and each influence factor according to the embodiment of the invention, wherein in the embodiment of the invention, the energy consumption is taken as a dependent variable by using a regression analysis method, and the optimal value of each input factor under different working conditions is taken as an independent variable; and building a neural network model by utilizing the relation between the optimal values of all parameters and the load under different working conditions, so that the optimal values of all parameters of the working conditions which do not exist in the divided working conditions can be further obtained, and a final optimization and improvement strategy is obtained.
The practice of the invention will be described in detail below with reference to the drawings. The present embodiment is implemented on the premise of the present technical method, and detailed embodiments and operation procedures are given, but the scope of protection of the present invention is not limited to the following examples.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Finally, it should be noted that: the above embodiments are only for illustrating the technical aspects of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the above embodiments, it should be understood by those of ordinary skill in the art that: modifications and equivalents may be made to the specific embodiments of the invention without departing from the spirit and scope of the invention, which is intended to be covered by the claims.
Claims (6)
1. A data operation optimization method based on a power plant desulfurization system, which is characterized by comprising the following steps:
(1) Acquiring actual operation data of an actual operation system of a power station within a certain time period, and preprocessing and regression analysis are carried out on the actual operation data;
(2) Dividing different working conditions according to the operation load, and obtaining the flow field, the temperature and the SO of the whole desulfurization system under different working conditions through numerical simulation 2 Component distribution;
in the step (2), the numerical simulation specifically includes:
(21) According to the actual structure and the actual size of the actual operation system equipment of the power station, adopting Gambit software to establish a full-system three-dimensional physical model comprising a boiler furnace, a horizontal flue, each decontamination device and a tail flue;
(22) Taking non-uniformity conditions at the inlet of the desulfurization system as inlet boundary conditions of the full-system three-dimensional physical model, and using Fluent software to simulate and calculate the flow field, temperature and SO of the whole desulfurization system under different working conditions 2 Component distribution;
(23) Comparing and analyzing the numerical simulation result with actual operation parameter data, introducing a correction factor, checking the reliability of the full-system three-dimensional physical model and the simulation result, if the checking is passed, entering into big data analysis, otherwise, carrying out numerical simulation again;
(3) Big data analysis is carried out on the actual operation data of the desulfurization system of the coal-fired power plant, so as to obtain an optimal interval of the operation data under a determined working condition, and the method specifically comprises the following steps:
(31) Regression analysis is performed on the fixed working condition data: according to removal of SO per unit mass 2 Carrying out regression calculation on the preprocessed data by the consumed currency, and analyzing factors influencing the energy consumption difference under the working condition;
(32) Screening influence factors: analyzing and determining operation data which are most critical to the influence of energy consumption under the working condition, and selecting the operation data which accord with a preset threshold value as an influence factor set, wherein the influence factor set is a subset of the obtained actual operation data of the power station;
(33) Building a mathematical prediction model: taking the parameter data of the influence factor set as input, adopting a neural network to construct a mathematical prediction model, taking part of actual operation data quantity obtained after pretreatment as training data, and outputting as an energy consumption evaluation index;
(34) Auditing and predicting model: outputting and predicting the prediction model under the same working condition of the power station by using other actual operation data except training data, setting a proper error line, judging the accuracy of the model, and if the verification is passed, entering a step (35), otherwise, returning to the step (33);
(35) And (3) algorithm optimizing: searching the local and global optimal solutions of the prediction model under the determined working condition by utilizing a genetic algorithm to obtain the optimal value interval of each parameter;
(4) And carrying out numerical simulation on the optimal value interval obtained by data analysis, checking the correctness of the optimal value interval, and judging whether the optimal value interval can reach a preset sulfur removal target or not.
2. The method for optimizing data operation based on a desulfurization system of a power plant according to claim 1, wherein in the step (1), the actual operation data includes: unit load, coal type, FGD inlet gas quantity, FGD outlet gas quantity, sulfur quantity, temperature, speed, circulating slurry flow, slurry density in a desulfurizing tower, absorption tower slurry PH, absorption tower slurry liquid level, supplemental slurry density, flow, oxidation fan component, power consumption and stirrer power consumption.
3. The power plant desulfurization system-based data operation optimization method according to claim 1, wherein in the step (1), the preprocessing includes: firstly, performing reliability audit on the obtained operation data, and removing unreasonable data; secondly, supplementing missing data by adopting a weighted filling method; and finally, denoising the parameter data with frequent fluctuation.
4. The power plant desulfurization system-based data operation optimization method according to claim 1, further comprising: performing numerical simulation on the optimal value interval in the step (35), taking the related parameters of the optimal solution set as input of the numerical simulation, and referring to the simulation result of the step (2), judging whether the parameters obtained by big data analysis can meet SO (SO) 2 If so, integrating parameter value intervals under different working conditions to obtain a final optimized parameter interval, otherwise, replacing the parameters and carrying out numerical simulation again.
5. The method for optimizing data operation based on a desulfurization system of a power plant according to claim 1, wherein in the step (32), the method adopted to analyze the operation data most critical to the influence of energy consumption under the determined working conditions is an ash correlation entropy analysis method, and specifically comprises:
(321) Assume that the compared sequences are: x is X 0 ＝{X 0 (i) I=1, 2,..m }, the comparison sequence is X k ＝{X k (i) I=1, 2,..m }, k=1, 2, … n, m represents the sequence length, n represents the dimension;
data initialization: x'. 0 ＝{X 0 (i)/X 0 (1)|i＝1,2,...,m}，X’ k ＝{X k (i)/X k (1)|i＝1,2,...,m}
(322) Calculating a data column level difference matrix
(323) Find two-stage minimum difference Y min Two-stage maximum difference Y max
y min ＝min(min(Y)),y max ＝max(max(Y))
(324) Calculating an association matrix ζ
Wherein ζ ij ＝(y min +εy max )/(y ij +εy max ),i＝1,2,...,n；j＝1,2,...,m，0＜ε＜1，ε＝0.5；
(325) Calculating gray correlation matrix E r ：
P i,j ＝ζ ij /ζ i
E r (X i )＝H(R i )/H m ,H m ＝ln(m)。
6. The method for optimizing data operation based on a desulfurization system of a power plant according to claim 1, wherein in the step (2), the method specifically adopted for dividing different working conditions of the operation load is to divide according to the rated load ratio by adopting a traditional method or to divide according to the data distribution by adopting a cluster analysis method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910490848.XA CN110263988B (en) | 2019-06-06 | 2019-06-06 | Data operation optimization method based on power plant desulfurization system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910490848.XA CN110263988B (en) | 2019-06-06 | 2019-06-06 | Data operation optimization method based on power plant desulfurization system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110263988A CN110263988A (en) | 2019-09-20 |
| CN110263988B true CN110263988B (en) | 2023-06-30 |
Family
ID=67917008
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910490848.XA Active CN110263988B (en) | 2019-06-06 | 2019-06-06 | Data operation optimization method based on power plant desulfurization system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110263988B (en) |
Families Citing this family (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109636001B (en) * | 2018-11-13 | 2023-05-23 | 国能龙源环保有限公司 | Method, system and computer readable medium for adjusting pH value of desulfurization slurry supply system based on big data |
| CN110866997A (en) * | 2019-11-12 | 2020-03-06 | 中国计量大学 | Novel method for constructing running condition of electric automobile |
| CN111077869B (en) * | 2019-12-31 | 2023-04-28 | 国电九江发电有限公司 | Big data intelligent control bag-type dust collector optimization control method and system |
| CN111240282B (en) * | 2019-12-31 | 2021-12-24 | 联想(北京)有限公司 | Process optimization method, device, equipment and computer readable storage medium |
| CN111598308B (en) * | 2020-04-24 | 2022-03-29 | 大唐环境产业集团股份有限公司 | Method for solving combination optimization of slurry circulating pump based on regression and double PSO algorithm |
| CN111754030B (en) * | 2020-06-11 | 2022-04-12 | 浙江浙能技术研究院有限公司 | Thermal power generating unit power supply coal consumption optimization method based on HAC and RF-GA |
| CN112216351B (en) * | 2020-09-23 | 2024-02-13 | 成都佳华物链云科技有限公司 | Desulfurization optimization method and device, electronic equipment and storage medium |
| JP2022157305A (en) * | 2021-03-31 | 2022-10-14 | 三菱重工業株式会社 | Method for controlling wet flue gas desulfurization equipment, control device of wet flue gas desulfurization equipment, remote control system with the control device of wet flue gas desulfurization equipment, information processing device, and information processing system |
| CN113313325A (en) * | 2021-06-21 | 2021-08-27 | 西安热工研究院有限公司 | Desulfurization system operation optimization method, system, equipment and storage medium |
| CN113361971B (en) * | 2021-07-13 | 2023-04-07 | 浙江菲达环保科技股份有限公司 | Combined control method and system for gypsum dehydration and desulfurization wastewater |
| CN113469449A (en) * | 2021-07-13 | 2021-10-01 | 浙江菲达环保科技股份有限公司 | Optimizing control method and system for desulfurization system |
| CN113426264A (en) * | 2021-07-15 | 2021-09-24 | 国电环境保护研究院有限公司 | Intelligent operation control method and control platform for flue gas purification island |
| CN114413247A (en) * | 2022-01-14 | 2022-04-29 | 西安热工研究院有限公司 | Boiler combustion heating surface overtemperature monitoring and active inhibition system |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109711589A (en) * | 2019-02-01 | 2019-05-03 | 江苏方天电力技术有限公司 | A kind of SCR denitration system running optimizatin method and system based on big data |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102693451B (en) * | 2012-06-14 | 2014-11-19 | 东北电力大学 | Method for predicting ammonia process flue gas desulphurization efficiency based on multiple parameters |
| CN106650086A (en) * | 2016-12-20 | 2017-05-10 | 河南省电力勘测设计院 | Indirect air cooling system numerical simulation platform based on FLUENT software |
| CN109711642B (en) * | 2019-02-01 | 2022-06-07 | 江苏方天电力技术有限公司 | Big data-based desulfurization system operation optimization method and system |
-
2019
- 2019-06-06 CN CN201910490848.XA patent/CN110263988B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109711589A (en) * | 2019-02-01 | 2019-05-03 | 江苏方天电力技术有限公司 | A kind of SCR denitration system running optimizatin method and system based on big data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110263988A (en) | 2019-09-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110263988B (en) | Data operation optimization method based on power plant desulfurization system | |
| CN101498459B (en) | Modeling method for boiler combustion optimization | |
| CN111240282B (en) | Process optimization method, device, equipment and computer readable storage medium | |
| FR2947345B1 (en) | METHOD FOR MODIFYING FACIAL PROPORTIONS WHEN SETTING HISTORY OF A GEOLOGICAL MODEL | |
| CN113094988A (en) | Data-driven slurry circulating pump operation optimization method and system | |
| CN107506865A (en) | A kind of load forecasting method and system based on LSSVM optimizations | |
| CN104636834B (en) | A kind of improved joint probability plan model system optimization method | |
| CN106845767A (en) | A kind of industry development in science and technology power quantitative estimation method and assessment system | |
| CN105676814A (en) | SFLA-SVM-based digital water island online agent adding control method | |
| CN113554213A (en) | Natural gas demand prediction method, system, storage medium and equipment | |
| Zeng et al. | Dynamic simulation of urban water metabolism under water environmental carrying capacity restrictions | |
| CN105302724A (en) | Instant defect predicting method based on mixed effect removing | |
| CN103164631B (en) | A kind of intelligent coordinate expression gene analyser | |
| Yao et al. | Exploring the low-carbon transition pathway of China's construction industry under carbon-neutral target: A socio-technical system transition theory perspective | |
| CN106647259A (en) | Coking gas desulfurization and denitrification integrated equipment centralized management and control system | |
| CN109118093A (en) | A method of assessment carbon emission economic impact | |
| CN106022496A (en) | Raw material sintering burdening optimization method and system | |
| CN113449919A (en) | Power consumption prediction method and system based on feature and trend perception | |
| CN109212999B (en) | Intelligent generation method and system for digital satellite simulation working condition | |
| CN113485111B (en) | Optimizing control method and system for pulping system | |
| CN102360400B (en) | Method for designing automatic simulation calculation of flow state of large slow flow landscape water body in multi-scheme manner | |
| CN112228052B (en) | Shale and tight rock oil gas productivity prediction method, evaluation method and system | |
| CN114677052A (en) | Natural gas load fluctuation asymmetry analysis method and system based on TARCH model | |
| Juuso | Data-based development of hybrid models for biological wastewater treatment in pulp and paper industry | |
| CN114429258A (en) | Natural gas purification control method based on energy efficiency evaluation and online optimization platform |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |