CN110263988A - A kind of data run optimization method based on power plant desulphurization system - Google Patents

A kind of data run optimization method based on power plant desulphurization system Download PDF

Info

Publication number
CN110263988A
CN110263988A CN201910490848.XA CN201910490848A CN110263988A CN 110263988 A CN110263988 A CN 110263988A CN 201910490848 A CN201910490848 A CN 201910490848A CN 110263988 A CN110263988 A CN 110263988A
Authority
CN
China
Prior art keywords
data
desulphurization system
power plant
analysis
operating
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.)
Granted
Application number
CN201910490848.XA
Other languages
Chinese (zh)
Other versions
CN110263988B (en
Inventor
金保昇
孔志伟
孙和泰
孙栓柱
张友卫
周春蕾
李逗
朱洁雯
张勇
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Southeast University
Jiangsu Fangtian Power Technology Co Ltd
Original Assignee
Southeast University
Jiangsu Fangtian Power Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Southeast University, Jiangsu Fangtian Power Technology Co Ltd filed Critical Southeast University
Priority to CN201910490848.XA priority Critical patent/CN110263988B/en
Publication of CN110263988A publication Critical patent/CN110263988A/en
Application granted granted Critical
Publication of CN110263988B publication Critical patent/CN110263988B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION 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
    • G06Q10/00Administration; Management
    • G06Q10/04Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION 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
    • G06Q50/00Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
    • G06Q50/06Electricity, gas or water supply
    • YGENERAL 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
    • Y02TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02EREDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
    • Y02E40/00Technologies for an efficient electrical power generation, transmission or distribution
    • Y02E40/70Smart grids as climate change mitigation technology in the energy generation sector
    • YGENERAL 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
    • Y04INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
    • Y04SSYSTEMS 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
    • Y04S10/00Systems supporting electrical power generation, transmission or distribution
    • Y04S10/50Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications

Abstract

A kind of method the invention discloses power plant desulphurization system based on data-optimized operation this method comprises: obtaining the actual operating data in power station actual motion system certain period of time, and carries out pretreatment and regression analysis to the actual operating data;Different operating conditions are divided according to operating load, and carries out numerical simulation and obtains the flow field of desulphurization system entirety, temperature, SO under different operating conditions2Component distribution situation;The actual operating data described in coal fired power plant desulphurization system carries out big data analysis, obtains the optimum interval for determining operation data under operating condition;Big data optimizing result is practiced to the accuracy to examine optimizing result in analog result.The present invention first distinguishes operating condition before establishing neural network prediction model, this reduces data volume, and relationship is relatively unambiguous and simple between energy consumption, desulphurizing ratio output parameter and impact factor, advantageously ensures that precision.

Description

A kind of data run optimization method based on power plant desulphurization system
Technical field
The present invention relates to coal-burning boiler technical field of air pollution control, and in particular to a kind of based on power plant desulphurization system Data run optimization method.
Background technique
Currently, environmental pollution has become one of the main roadblock for hindering the high quality sustainable development of national economy health, And pollutant emission standard is continuously improved in keypoint treatment object of the coal fired power plant as environmental problem, country.To meet pollutant Discharge standard, coal fired power plant often take the countermeasure of abundant materials decontamination, and which results in the waste of resource to a certain extent.
Meanwhile in desulphurization system simultaneously be related to heat and mass, acid-base neutralization, moisture evaporation, drop coalescence be crushed etc. ask Topic, practical operation situation is complicated, although having many scholars using related software to desulfurization flow field in tower, temperature field, SO2Distribution The problems such as carried out detailed analog study, however based on a large amount of actual operating datas, combined with numerical simulation to de- It is to rarely have that sulphur system, which carries out network analysis,.
In addition, power station in many years operational process, after various operating conditions, stores the actual operating data of a large amount of preciousnesses. It can be not only the significant wastage to data resource, simultaneously there is no this valuable data resource is utilized in most power stations at present Also valuable network and physical space are occupied.
Under this situation, the progress of big data, intelligent Computation Technology provides new for the fine-grained management in power station Developing direction.Big data analysis technology is gradually more and more fire coals because of remarkable advantages such as its is accurate, speed is fast, visualizations Power plant's concern, research and application.Depth analysis is carried out using actual operating data of the big data technology to desulphurization system, it has also become One of coal fired power plant pollutant process, running Optimization, the important content improved efficiency.
Summary of the invention
Goal of the invention: the present invention is in view of the above-mentioned problems, provide one kind based on theory analysis, supplemented by numerical simulation It helps, provides the method for strategy by means of big data analysis for desulphurization system running optimizatin, be for solving previous desulphurization system Meet National Emission Standard and there are problems that the energy, the wasting of resources.
Technical solution: the present invention is based on pollutant control system theoretical model, with the simulation of desulphurization system practical flow field Mathematical model is built as core by auxiliary, using actual operating data.Three kinds of models cooperate with each other, complement each other.This method tool Body practices step
(1) actual operating data in power station actual motion system certain period of time is obtained, and to the actual motion number According to carry out pretreatment and its regression analysis;
(2) different operating conditions are divided according to operating load, carries out numerical simulation and obtains desulphurization system entirety under different operating conditions Flow field, temperature, SO2Component distribution situation;
(3) actual operating data described in coal fired power plant desulphurization system carries out big data analysis, specifically includes:
(31) regression analysis is carried out to fixed floor data: according to removal unit mass SO2Consumed currency is to pretreatment Data carry out recurrence calculating afterwards, and analyzing influence determines the factor of energy consumption difference under operating condition;
(32) it screens impact factor: analyzing and determine operation data the most key to energy consumption under operating condition, screening is wherein Meet the operation data of preset threshold as impact factor collection, the impact factor collection is obtained power station actual operating data Subset;
(33) it builds mathematical forecasting model: being input with the impact factor collection supplemental characteristic, constructed using neural network Mathematical forecasting model is exported using the part actual operating data amount obtained after the pretreatment as training data as Energy Consumption Evaluation Index;
(34) prediction model is audited: using power station with other actual operating data amounts under operating condition, in addition to training data Output prediction is carried out to same operating condition prediction model, suitable error line, the accuracy of judgment models are set, if audit is by entering step Suddenly (35), otherwise separate regression steps (33);
(35) it algorithm optimizing: is found using genetic algorithm and determines prediction model global optimum disaggregation or optimal under operating condition Section.
(4) data are analyzed into gained optimal solution set or optimum interval brings gained simulation model, audit optimal solution set, optimal into The correctness in section.
Further, comprising:
In the step (1), actual operating data includes: unit load, coal, FGD import tolerance, the outlet FGD tolerance, Sulfur content, temperature, speed, loop slurry flow, serum density, absorption tower slurries PH, absorption tower liquid level of slurry, supplement in desulfurizing tower Serum density, flow, oxidation fan component, temperature, power consumption and blender power consumption.
Further, comprising:
In the step (2), numerical simulation is specifically included:
(21) according to the practical structures and size of power station actual motion system equipment, being established using Gambit software includes pot Furnace burner hearth, horizontal flue, each decontamination apparatus and back-end ductwork total system three-dimensional physical model;
(22) using the heterogeneity condition of desulphurization system inlet as the entrance side of the total system three-dimensional physical model Boundary's condition, using Fluent software, simulation calculates the flow field of desulphurization system entirety, temperature, SO under different operating conditions2Component is distributed feelings Condition;
(23) by the numerical simulation result and actual operation parameters date comprision, modifying factor is introduced, audits institute The reliability of total system three-dimensional physical model and analog result is stated, if audit passes through, enters the big data analysis, otherwise, Re-start numerical simulation.
Further, comprising:
In the step (1), pretreatment includes: firstly, carrying out confidence level audit to obtained operation data, rejecting is wherein Unreasonable data;Secondly, supplementing missing data using weighting fill method;Finally, being gone to frequent supplemental characteristic is fluctuated It makes an uproar processing.
Further, comprising:
This method further include: numerical simulation is carried out to the final optimization pass parameter section in step (35), with the phase of optimal solution The input that parameter is numerical simulation is closed, judges whether big data analysis parameters obtained optimum interval can satisfy sulfur limitation effect, if Meet, then integrate parameter value section under different operating conditions, obtain final optimization pass parameter section, otherwise, replacement input parameter is again Carry out numerical simulation.
Further, comprising:
In the step (32), analyze determine the operation data the most key to energy consumption uses under operating condition method for Grey relation entropy analysis method specifically includes:
(321) data initialization;X0={ X0(i) | i=1,2 ..., m }, Xk={ Xk(i) | i=1,2 ..., m }, m table Show that sequence length, n indicate dimension.
X'0={ X0(i)/X0(1) | i=1,2 ..., m }, X'k={ Xk(i)/Xk(1) | i=1,2 ..., m }
(322) data are calculated and arranges differential matrix
Wherein, yij=| X0(j)-Xi(j)|
(323) two-stage lowest difference Y is soughtmin, two-stage maximum difference Ymax
ymin=min (min (Y)), ymax=max (max (Y))
(324) incidence matrix ζ is calculated
Wherein, ζij=(ymin+εymax)/(yij+εymax), i=1,2 ..., n;J=1,2 ..., m.0 < ε < 1, ε= 0.5;
(325) grey correlation matrix E is calculatedr:
Pi,jiji
Er(Xi)=H (Ri)/Hm,Hm=ln (m).
Further, comprising:
In the step (2), operating load divide the method that different operating conditions specifically use for using conventional method by accounting for volume Constant load ratio divide or is distinguished using clustering method according to data distribution.
The utility model has the advantages that compared with prior art, the present invention its remarkable advantage is: 1, the present invention is establishing neural network prediction Operating condition is distinguished first before model, data volume is smaller, and the relationship between output parameters and impact factor such as energy consumption, desulphurizing ratio It is relatively unambiguous and simple, so often centainly being screened to input parameter, it ensure that precision;2, operating condition of the invention differentiation makes It obtains parameter fluctuation obviously to weaken, data volume is obviously reduced, this will greatly reduce the complexity of data analysis, help to obtain spy Determine the stable solution and optimal solution under operating condition;3, the present invention is auxiliary with numerical simulation, using desulphurization system big data analysis as means The method of strategy is provided for desulphurization system running optimizatin, it is intended to be improved the efficiency of energy utilization of coal fired power plant desulphurization system, be reduced Pollutant removing cost, it is energy saving;4, the present invention builds determining operating condition mathematical forecasting model by big data analysis, and analysis is each Relationship between a operation data provides running optimizatin improvement strategy for desulphurization system, solves previous desulphurization system due to abundant Energy resources caused by materials utilize unreasonable problem, achieve the effect that Optimized Operation power station resource.
Detailed description of the invention
Fig. 1 is method flow diagram described in a wherein embodiment of the invention.
Specific embodiment
To make the objectives, technical solutions, and advantages of the present invention clearer, below in conjunction with the accompanying drawings and the specific embodiments The present invention will be described in detail.
This method of the present invention is analysis and research object with power station desulphurization system, by the simulation of Fluent software, big data point The method of analysis carries out profound analysis to the system power station actual operating data, can not only obtain power station can not provide but The data information of important in inhibiting, and mathematical forecasting model can be built and obtain model part, globally optimal solution, simultaneously It is auxiliary with theoretical model, triplicity provides running optimizatin improvement strategy for desulphurization system actual motion.
As shown in fig.1, the data run optimization method of the present invention based on power plant desulphurization system, specifically includes:
S1 data needed for) establishing coal fired power plant desulphurization system theoretical model and obtaining: according to power station physical device component and Specific configuration builds theoretical model, establishes its energy balance, conservation of matter theoretical model, is 1:1 with prototype size ratio.
To remove unit mass SO2Consumed currency is energy consumption evaluation indexes, and data needed for analysis project are simultaneously closed with power station Make, obtains electric power station system structural parameters and certain period of time operation data.The energy consumption evaluation indexes are defined by the formula.
Energy consumption=a × feed consumption+b × power consumption-c × output
In formula, output is mainly gypsum, a, b, and c represents the market unit price of three kinds of materials.
Acquired operation data should include but is not limited to following parameter: unit load, coal, FGD into (out) implication amount, Sulfur content, temperature, speed, loop slurry flow, serum density in desulfurizing tower, absorption tower slurries PH, absorption tower liquid level of slurry, supplement Serum density, flow, oxidation fan component, temperature, power consumption, blender power consumption.
S2 Preprocessing) is carried out to power station actual operating data: confidence level audit being carried out to obtained operation data, is picked Except wherein unreasonable data;Missing data is supplemented using weighting fill method;To fluctuate frequent supplemental characteristic (such as pressure) into Row denoising, denoising method can use SG filter method.
And different operating conditions are divided according to operating load, it is of the invention in one embodiment, tradition side can be used Method is divided in rated load ratio is accounted for, and such as 50%, the rated loads such as 70%;Clustering method can also be taken according to number It is distinguished according to distribution.
S3) to S2) pretreatment after data carry out regression analysis: with S1) described in energy consumption evaluation indexes and traditional index Desulphurizing ratio, calcium sulfur ratio are that target component carries out recurrence calculating to data.
It returns to calculate and can obtain desulfurization degree, the parameters such as calcium sulfur ratio.Due to desulphurization plant design capacity and actual motion mistake The factors such as the abundant materials of journey carry out desulfurization degree and are often higher than national minimum discharge requirement, and excessively high desulphurizing ratio has directly energy consumption The influence connect.Under the premise of meeting minimum discharge standard, the ratio that desulphurizing ratio can reduce is often S5) it is pre- in big data analysis Survey the required precision of model.
S4 significant parameter can not be provided comprehensively by) obtaining power station by simulation, in one of them of the invention In embodiment, specially desulphurization system practical flow field, temperature field, SO2Component distribution situation.
Numerical simulation is in S2) in carry out under classed load.Specific step is as follows for simulation:
(1) according to power station actual motion system equipment practical structures and size, being established using Gambit software includes boiler Burner hearth, horizontal flue, each decontamination apparatus and back-end ductwork total system three-dimensional physical model;
(2) the non-homogeneous of desulphurization system inlet is obtained in conjunction with power station related data by experiment and on-the-spot test means Property entrance boundary condition of the condition as computation model, including but not limited to VELOCITY DISTRIBUTION, Temperature Distribution, constituent concentration distribution. Using Fluent software, the flow field of desulphurization system whole (entrance, desulfurizing tower, outlet), temperature, SO under different operating conditions are obtained2Group Divide distribution situation;
(3) by analog result and power station actual operation parameters date comprision, modifying factor is introduced, audits built object Manage the reliability of model and analog result.Audit passes through, then enters and carry out big data analysis in next step, otherwise re-start S4);
S5 big data analysis) big data analysis: is carried out to coal fired power plant desulphurization system actual operating data.
For distinguishing operating condition, following steps are specifically included:
(51) regression analysis is carried out to fixed floor data: according to energy consumption evaluation indexes described in S1) to S2) after pretreatment Data carry out recurrence calculating, and based on theoretical model, preliminary analysis influences to determine the factor of energy consumption difference under operating condition.It is distinguishing Under the premise of operating condition, logical relation is simple, and data volume is smaller, therefore can be divided using multinomial logistic regression method energy consumption Analysis, using obtained operation data as independent variable, using energy consumption as dependent variable.
(52) it screens impact factor: utilizing correlation technique, the present embodiment uses grey relation entropy analysis method, analyzes and determines operating condition Under the operation data the most key to energy consumption, threshold values screening wherein several factors are set up, of the invention one of real It applies in example, threshold values selected by possibility is different under different operating conditions, and impact factor number is different, the shadow as next step mode input Factor set is rung, impact factor collection is the subset of obtained power station parameter set.
Grey relation entropy analysis method specifically includes:
(521) data initialization;X0={ X0(i) | i=1,2 ..., m }, Xk={ Xk(i) | i=1,2 ..., m }
X'0={ X0(i)/X0(1) | i=1,2 ..., m }, X'k={ Xk(i)/Xk(1) | i=1,2 ..., m }
(522) data are calculated and arranges differential matrix
Wherein, yij=| X0(j)-Xi(j)|
(523) two-stage lowest difference Y is soughtmin, two-stage maximum difference Ymax
ymin=min (min (Y)), ymax=max (max (Y))
(524) incidence matrix ζ is calculated
Wherein, ζij=(ymin+εymax)/(yij+εymax), i=1,2 ..., n;J=1,2 ..., m.0 < ε < 1, ε= 0.5;
(525) grey correlation matrix E is calculatedr:
Pi,jiji
Er(Xi)=H (Ri)/Hm,Hm=ln (m)
(53) mathematical forecasting model is built: based on impact factor collection supplemental characteristic, by neural network, vector machine etc. Method builds mathematical forecasting model.Mathematical forecasting model is input with impact factor collection parameter, with S2) it is real after data prediction Border operation data is training data, and in the present embodiment, the data volume for choosing 95% is training data, and residue 5% is pre- for auditing Model is surveyed, output is energy consumption evaluation indexes.Furthermore, it is possible to add the parameters such as desulphurizing ratio, calcium sulfur ratio as multi output model.Such as benefit Energy consumption, desulphurizing ratio dual factors output model are built with neural network, help to obtain the optimal solution set for meeting numerous parameters in this way, If not building, related optimizing result can be automatically deleted in the dummy run phase;
(54) prediction model is audited: using power station with model buildings data non-under operating condition (remaining 5% data) to same operating condition Prediction model carries out output prediction, and suitable error line, the accuracy of judgment models is arranged.If audit, which passes through, enters step (55), Otherwise separate regression steps (53).If repeatedly for built model not by audit, separate regression steps (52) check physical model and institute Need data whether gaps and omissions;
(55) it is found using appropriate algorithm and determines prediction model part and globally optimal solution under operating condition.The embodiment of the present invention In, using genetic algorithm or artificial bee colony algorithm, it may be assumed that on built prediction model basis, in conjunction with genetic algorithm or Artificial bee colony algorithm is found each using genetic algorithm or the obtained Key Influential Factors data of artificial bee colony algorithm as mode input A optimal value interval of parameter.To avoid separated data from impacting optimizing result, calcium sulfur ratio, desulphurizing ratio parameter can use Related threshold is set.
S6) in conjunction with theoretical model and the optimal value interval of gained in S1), judge whether gained optimizing solution meets theory about Beam determines system each Key Influential Factors optimum interval in the case where determining operating condition;
S7) to S6) obtained in optimum interval using Fluent software carry out numerical simulation, with the relevant parameter of optimal solution The correctness of big data analysis parameters obtained optimum interval is judged referring to the analog result of S4) for the input of numerical simulation, if Correctly, S8 is carried out), otherwise, return S6);
S8 parameter value section under different operating conditions) is integrated, obtains final optimization pass parameter section, on this basis, the present invention Embodiment, analyze dynamic relationship between optimum interval and each impact factor, in the embodiment of the present invention, utilize the side of regression analysis Method is using energy consumption as dependent variable, respectively to input the optimal value of factor under different operating conditions as independent variable;Utilize each parameter under different operating conditions Relationship builds neural network model between optimal value and load, so can further obtain divided in operating condition it is not yet existing The optimal value of each parameter of operating condition, obtains final optimization pass improvement strategy.
The present invention will be described in detail referring to the drawings implements.The implementation case carries out real under premised on this technology method It applies, gives detailed embodiment and operating process, but protection scope of the present invention is not limited only to following embodiments.
It should be understood by those skilled in the art that, embodiments herein can provide as method, system or computer program Product.Therefore, complete hardware embodiment, complete software embodiment or reality combining software and hardware aspects can be used in the application Apply the form of example.Moreover, it wherein includes the computer of computer usable program code that the application, which can be used in one or more, The computer program implemented in usable storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.) produces The form of product.
The application is referring to method, the process of equipment (system) and computer program product according to the embodiment of the present application Figure and/or block diagram describe.It should be understood that every one stream in flowchart and/or the block diagram can be realized by computer program instructions The combination of process and/or box in journey and/or box and flowchart and/or the block diagram.It can provide these computer programs Instruct the processor of general purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices to produce A raw machine, so that being generated by the instruction that computer or the processor of other programmable data processing devices execute for real The device for the function of being specified in present one or more flows of the flowchart and/or one or more blocks of the block diagram.
These computer program instructions, which may also be stored in, is able to guide computer or other programmable data processing devices with spy Determine in the computer-readable memory that mode works, so that it includes referring to that instruction stored in the computer readable memory, which generates, Enable the manufacture of device, the command device realize in one box of one or more flows of the flowchart and/or block diagram or The function of being specified in multiple boxes.
These computer program instructions also can be loaded onto a computer or other programmable data processing device, so that counting Series of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, thus in computer or The instruction executed on other programmable devices is provided for realizing in one or more flows of the flowchart and/or block diagram one The step of function of being specified in a box or multiple boxes.
Finally it should be noted that: the above embodiments are merely illustrative of the technical scheme of the present invention and are not intended to be limiting thereof, to the greatest extent Invention is explained in detail referring to above-described embodiment for pipe, it should be understood by those ordinary skilled in the art that: still It can be with modifications or equivalent substitutions are made to specific embodiments of the invention, and without departing from any of spirit and scope of the invention Modification or equivalent replacement, should all cover within the scope of the claims of the present invention.

Claims (7)

1. a kind of data run optimization method based on power plant desulphurization system, which is characterized in that this method comprises:
(1) obtain power station actual motion system certain period of time in actual operating data, and to the actual operating data into Row pretreatment and regression analysis;
(2) different operating conditions are divided according to operating load, numerical simulation obtains the flow field of desulphurization system entirety, temperature under different operating conditions Degree, SO2Component distribution situation;
(3) actual operating data described in coal fired power plant desulphurization system carries out big data analysis, obtains running number under determining operating condition According to optimum interval, specifically include:
(31) regression analysis is carried out to fixed floor data: according to removal unit mass SO2Consumed currency is to data after pretreatment Recurrence calculating is carried out, the factor of energy consumption difference under the analyzing influence operating condition;
(32) it screens impact factor: analyzing and determine operation data the most key to energy consumption under operating condition, selection wherein meets For the operation data of preset threshold as impact factor collection, the impact factor collection is the son of obtained power station actual operating data Collection;
(33) it builds mathematical forecasting model: being input with the impact factor collection supplemental characteristic, mathematics is constructed using neural network Prediction model is exported using the part actual operating data amount obtained after the pretreatment as training data as energy consumption evaluation indexes;
(34) audit prediction model: using power station under operating condition, other actual operating data amounts in addition to training data are to same Operating condition prediction model carries out output prediction, and suitable error line, the accuracy of judgment models is arranged, if audit is by entering step (35), otherwise separate regression steps (33);
(35) it algorithm optimizing: is found using genetic algorithm and determines the prediction model part and globally optimal solution under operating condition, obtained The optimal value interval of parameters.
(4) by data analysis optimizing result in conjunction with numerical simulation result, mould once again is carried out to optimizing result by analog result It is quasi-, judge whether it can reach default sulphur removal target.
2. the data run optimization method according to claim 1 based on power plant desulphurization system, which is characterized in that the step Suddenly in (1), actual operating data includes: unit load, and coal, FGD import tolerance, FGD export tolerance, sulfur content, temperature, speed Serum density, absorption tower slurries PH, absorption tower liquid level of slurry, supplement serum density, stream in degree, loop slurry flow, desulfurizing tower Amount, oxidation fan component, temperature, power consumption and blender power consumption.
3. the data run optimization method according to claim 1 based on power plant desulphurization system, which is characterized in that the step Suddenly in (2), numerical simulation is specifically included:
(21) according to the practical structures and size of power station actual motion system equipment, being established using Gambit software includes Boiler Furnace Thorax, horizontal flue, each decontamination apparatus and back-end ductwork total system three-dimensional physical model;
(22) using the heterogeneity condition of desulphurization system inlet as the entrance boundary item of the total system three-dimensional physical model Part, using Fluent software, simulation calculates the flow field of desulphurization system entirety, temperature, SO under different operating conditions2Component distribution situation;
(23) by the numerical simulation result and actual operation parameters date comprision, modifying factor is introduced, is audited described complete The reliability of system three-dimensional physical model and analog result enters the big data analysis, otherwise, again if audit passes through Carry out numerical simulation.
4. the data run optimization method according to claim 1 based on power plant desulphurization system, which is characterized in that the step Suddenly in (1), pretreatment includes: to reject wherein unreasonable data firstly, to the progress confidence level audit of obtained operation data;Its It is secondary, missing data is supplemented using weighting fill method;Finally, carrying out denoising to frequent supplemental characteristic is fluctuated.
5. the data run optimization method according to claim 1 based on power plant desulphurization system, which is characterized in that this method Further include: numerical simulation is carried out to the final optimization pass parameter section in step (35), using the relevant parameter of optimal solution set as numerical value The input of simulation judges whether big data analysis parameters obtained can satisfy SO referring to the analog result of the step (2)2's Removing requires, if can be to integrate parameter value section under different operating conditions, obtain final optimization pass parameter section, otherwise, replacement is joined Number re-starts numerical simulation.
6. the data run optimization method according to claim 1 based on power plant desulphurization system, which is characterized in that the step Suddenly in (32), the method that the operation data the most key to energy consumption uses under the determining operating condition of analysis is grey relation entropy analysis Method specifically includes:
(321) assume to be compared sequence are as follows: X0={ X0(i) | i=1,2 ..., m }, comparing sequence is Xk={ Xk(i) | i=1, 2 ..., m }, k=1,2 ... n, m indicate that sequence length, n indicate dimension;
Data initialization: X'0={ X0(i)/X0(1) | i=1,2 ..., m }, X 'k={ Xk(i)/Xk(1) | i=1,2 ..., m }
(322): calculating data and arrange differential matrix
Wherein, yij=| X0(j)-Xi(j)|
(323) two-stage lowest difference Y is soughtmin, two-stage maximum difference Ymax
ymin=min (min (Y)), ymax=max (max (Y))
(324) incidence matrix ζ is calculated
Wherein, ζij=(ymin+εymax)/(yij+εymax), i=1,2 ..., n;J=1,2 ..., m.0 < ε < 1, ε=0.5;
(325) grey correlation matrix E is calculatedr:
Pi,jiji
Er(Xi)=H (Ri)/Hm,Hm=ln (m).
7. the data run optimization method according to claim 1 based on power plant desulphurization system, which is characterized in that the step Suddenly in (2), operating load divides the method that different operating conditions specifically use to carry out using conventional method in rated load ratio is accounted for It divides or is distinguished using clustering method according to data distribution.
CN201910490848.XA 2019-06-06 2019-06-06 Data operation optimization method based on power plant desulfurization system Active CN110263988B (en)

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 true CN110263988A (en) 2019-09-20
CN110263988B 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)

Cited By (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109636001A (en) * 2018-11-13 2019-04-16 北京国电龙源环保工程有限公司 Desulfurization pulp feeding system pH value adjusting method, system and computer-readable medium 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
CN111077869A (en) * 2019-12-31 2020-04-28 国电九江发电有限公司 Optimization control method and system for big data intelligent control bag-type dust collector
CN111240282A (en) * 2019-12-31 2020-06-05 联想(北京)有限公司 Process optimization method, device, equipment and computer readable storage medium
CN111598308A (en) * 2020-04-24 2020-08-28 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
CN111754030A (en) * 2020-06-11 2020-10-09 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
CN112216351A (en) * 2020-09-23 2021-01-12 成都佳华物链云科技有限公司 Desulfurization optimization method and device, electronic equipment and storage medium
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
CN113361971A (en) * 2021-07-13 2021-09-07 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
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
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
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
WO2022210827A1 (en) * 2021-03-31 2022-10-06 三菱重工業株式会社 Control method for wet flue gas desulfurisation device, control device for wet flue gas desulfurisation device, remote monitoring system comprising said control device for wet flue gas desulfurisation device, information processing device, and information processing system

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102693451A (en) * 2012-06-14 2012-09-26 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
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
CN109711642A (en) * 2019-02-01 2019-05-03 江苏方天电力技术有限公司 Desulphurization system running optimizatin method and system based on big data

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102693451A (en) * 2012-06-14 2012-09-26 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
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
CN109711642A (en) * 2019-02-01 2019-05-03 江苏方天电力技术有限公司 Desulphurization system running optimizatin method and system based on big data

Cited By (19)

* Cited by examiner, † Cited by third party
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
CN109636001A (en) * 2018-11-13 2019-04-16 北京国电龙源环保工程有限公司 Desulfurization pulp feeding system pH value adjusting method, system and computer-readable medium 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
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
CN111077869A (en) * 2019-12-31 2020-04-28 国电九江发电有限公司 Optimization control method and system for big data intelligent control bag-type dust collector
CN111240282A (en) * 2019-12-31 2020-06-05 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
CN111598308A (en) * 2020-04-24 2020-08-28 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
CN111754030A (en) * 2020-06-11 2020-10-09 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
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
CN112216351A (en) * 2020-09-23 2021-01-12 成都佳华物链云科技有限公司 Desulfurization optimization method and device, electronic equipment and storage medium
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
WO2022210827A1 (en) * 2021-03-31 2022-10-06 三菱重工業株式会社 Control method for wet flue gas desulfurisation device, control device for wet flue gas desulfurisation device, remote monitoring system comprising said control device for wet flue gas desulfurisation device, 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
CN113361971A (en) * 2021-07-13 2021-09-07 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
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
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

Also Published As

Publication number Publication date
CN110263988B (en) 2023-06-30

Similar Documents

Publication Publication Date Title
CN110263988A (en) A kind of data run optimization method based on power plant desulphurization system
Lu et al. Integration of life cycle assessment and life cycle cost using building information modeling: A critical review
Liu et al. Big data-informed energy efficiency assessment of China industry sectors based on K-means clustering
CN101498459B (en) Modeling method for boiler combustion optimization
CN104798043B (en) A kind of data processing method and computer system
CN107169633A (en) A kind of gas line network, gas storage peak regulating plan integrated evaluating method
Xu et al. A bottom-up optimization model for long-term CO2 emissions reduction pathway in the cement industry: a case study of China
CN103617147A (en) Method for identifying mine water-inrush source
CN113094988A (en) Data-driven slurry circulating pump operation optimization method and system
Jakobsen et al. A standardized Approach to Multi-criteria Assessment of CCS Chains
CN109948869A (en) Desulphurization system SO based on orderly cluster discretization2Exit concentration prediction technique
CN104680012A (en) Calculating model for sintering and burdening
Luo et al. Towards the sustainable development of the regional phosphorus resources industry in China: A system dynamics approach
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
CN108304975A (en) A kind of data prediction system and method
CN100370453C (en) Rare-earth cascade extraction separation component content soft measuring method
CN104299045B (en) System and method for forecasting yield of concentrate in whole mineral dressing process
CN110489844A (en) One kind being suitable for the uneven large deformation grade prediction technique of soft rock tunnel
Wang et al. Multi-scenario simulation on the impact of China's electricity bidding policy based on complex networks model
Liang et al. MES-DEA modelling for analysing anti-industrial pollution efficiency and its application in Anhui province of China
CN106940836A (en) A kind of data analysing method and device
Xu et al. Sustainable development-oriented industrial restructuring modeling and analysis: a case study in Leshan
CN109711642A (en) Desulphurization system running optimizatin method and system based on big data
He et al. Long-term planning of wind and solar power considering the technology readiness level under China's decarbonization strategy
Lu et al. Research on synergistic development of urbanization and energy consumption

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