CN110334840A - A kind of thermal power plant's coal yard field damage prediction technique based on neural network algorithm - Google Patents
A kind of thermal power plant's coal yard field damage prediction technique based on neural network algorithm Download PDFInfo
- Publication number
- CN110334840A CN110334840A CN201910302672.0A CN201910302672A CN110334840A CN 110334840 A CN110334840 A CN 110334840A CN 201910302672 A CN201910302672 A CN 201910302672A CN 110334840 A CN110334840 A CN 110334840A
- Authority
- CN
- China
- Prior art keywords
- loss
- dump
- coal
- coal yard
- neural network
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 239000003245 coal Substances 0.000 title claims abstract description 111
- 238000000034 method Methods 0.000 title claims abstract description 33
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 17
- 238000004422 calculation algorithm Methods 0.000 title claims abstract description 16
- 238000004364 calculation method Methods 0.000 claims abstract description 14
- 238000012512 characterization method Methods 0.000 claims abstract description 12
- 238000003062 neural network model Methods 0.000 claims abstract description 9
- 238000005259 measurement Methods 0.000 claims abstract description 3
- 230000001186 cumulative effect Effects 0.000 claims description 8
- 230000008569 process Effects 0.000 claims description 8
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 4
- 239000007921 spray Substances 0.000 claims description 3
- 238000004590 computer program Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 238000012545 processing Methods 0.000 description 6
- 239000000126 substance Substances 0.000 description 6
- 230000006866 deterioration Effects 0.000 description 5
- 238000012549 training Methods 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 4
- 239000000446 fuel Substances 0.000 description 4
- 238000004519 manufacturing process Methods 0.000 description 4
- 238000003860 storage Methods 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 3
- 238000002485 combustion reaction Methods 0.000 description 3
- 238000000151 deposition Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000007246 mechanism Effects 0.000 description 3
- 238000007254 oxidation reaction Methods 0.000 description 3
- 230000002269 spontaneous effect Effects 0.000 description 3
- 241001269238 Data Species 0.000 description 2
- 238000005094 computer simulation Methods 0.000 description 2
- 230000007423 decrease Effects 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000000284 resting effect Effects 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000033228 biological regulation Effects 0.000 description 1
- 229910052799 carbon Inorganic materials 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000001704 evaporation Methods 0.000 description 1
- 230000008020 evaporation Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 239000007789 gas Substances 0.000 description 1
- 229910052739 hydrogen Inorganic materials 0.000 description 1
- 239000001257 hydrogen Substances 0.000 description 1
- 125000004435 hydrogen atom Chemical class [H]* 0.000 description 1
- 238000012821 model calculation Methods 0.000 description 1
- 210000004218 nerve net Anatomy 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 230000008654 plant damage Effects 0.000 description 1
- 239000000047 product Substances 0.000 description 1
- 230000002787 reinforcement Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 230000005619 thermoelectricity Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 238000010977 unit operation Methods 0.000 description 1
- 230000004580 weight loss Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
- G01N33/22—Fuels; Explosives
- G01N33/222—Solid fuels, e.g. coal
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/042—Knowledge-based neural networks; Logical representations of neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Molecular Biology (AREA)
- Mathematical Physics (AREA)
- General Business, Economics & Management (AREA)
- Software Systems (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- Chemical & Material Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Food Science & Technology (AREA)
- Primary Health Care (AREA)
- Biochemistry (AREA)
- Analytical Chemistry (AREA)
- Public Health (AREA)
- Medicinal Chemistry (AREA)
- Immunology (AREA)
- Water Supply & Treatment (AREA)
- Pathology (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
Abstract
The invention discloses a kind of, and prediction technique is damaged in thermal power plant's coal yard field based on neural network algorithm, belongs to thermal power plant's coal yard field damage computing technique field.Method includes: S1, determines the parameter of the principal element for influencing coal yard loss and characterization loss;S2 will affect the current measurement value input neural network model of the principal element of coal yard damage for each dump, calculate the parameter value for obtaining characterization loss, S3, according to the loss objective data of each dump of parameter value calculation of the characterization loss of each dump;S4 calculates the loss objective for obtaining entire coal yard according to the loss objective data of each dump.The method of the present invention can Accurate Prediction go out the loss of entire coal yard.
Description
Technical field
Present invention relates particularly to a kind of, and prediction technique is damaged in thermal power plant's coal yard field based on neural network algorithm, belongs to thermal power plant
Damage computing technique field in coal yard field.
Background technique
Coal-fired cost accounts for the 2/3 of thermal power plant costs of production and operation.Therefore, the loss pair of coal-fired coal quality, heat
The economic benefit of power plant has an important influence.It is coal-fired during storage, due to by external environmental factor and self-characteristic
It influences, it may occur that a series of variations such as coal amount is lost, moisture increases, calorific value reduces, coal-fired spontaneous combustion.These variations all cause
An important factor for coal-fired coal quality, the loss of coal amount, also it is directly related to the benefits of production and management of thermal power plant.
Coal yard loss through standing is mainly made of physical deterioration and chemical wear two parts:
(1) physical deterioration refers to coal yard loss through standing caused by pure physical change, mainly includes windage loss, rain damage and moisture loss
(variation) etc., physical deterioration are characterized by coal-fired weight difference.
(2) chemical wear is the loss as caused by oxidation reaction during fire coal storage.Oxidation reaction is in coal
Oxidation reaction occurs at normal temperature for the elements such as carbon, hydrogen, and reacting combustible a part in generating process will be precipitated with gas procedure, together
When can also discharge heat, can also result in self-ignition of coal pile when serious.Above-mentioned chemical reaction will generate the calorific value decline for depositing coal simultaneously
And weight loss, chemical wear are characterized by coal-fired calorific value difference.
It is existing enter factory to the coal-fired quantity loss index entered between furnace be that coal yard deposits loss rate, calorific value loss objective is into factory
It is poor with as-fired coal calorific value.
In order to reduce coal-fired loss, power industry and enterprise, all go out corresponding regulation, depositing loss rate such as coal yard is 0.5%,
Enter factory and as-fired coal calorific value difference is 502kJ/kg (120kcal/kg), plays the role of to reinforcement fuel management larger.But in electricity
It is found in factory's production practices, they have certain limitation, show that depositing damage only considers factory and enter coal-fired loss between furnace
A part, and inconvenient directly survey calculation obtains.
The calculating of coal yard field damage is studied in major part power plant at present, factory is mainly entered extremely with the administration of Power Plant Fuel department
Enter defeated coal between furnace and stocking system is object, defining the statistics phase outputs and inputs heat, respectively from coal quantity balance, heat
Amount balance and comprehensive calorific value set out, overall to calculate entering factory and entering the coal quantity proportion of goods damageds between furnace, coal-fired heat for coal-fired loss
The proportion of goods damageds, rated coal consumption enter the indexs such as factory and as-fired coal Thermal Synthetic value difference, the comprehensive calorific value proportion of goods damageds, and as judgment criteria
Coal yard is lost and carries out net assessment calculating.Coal yard mass loss is by using the regular disk coal of disk coal instrument, in conjunction with sampling and coal quality
Industrial Analysis, calculate coal yard quality and thermal losses index.
Also there is part power plant based on thermal conduction study and mass transfer theory simultaneously, based on the mechanism model of coal yard loss, is added special
Family's empirical model calculates coal yard quality using the method for computer simulation emulation and heat calorific value is lost.
To enter factory to the defeated coal and stocking system entered between furnace as whole object, based on coal quantity balance, heat balance, always
The fire coal for entering factory and entering between furnace that body calculates coal-fired loss is lost.It is big that this method calculates global error, for each dump without
Method carries out statistics calculating, and the heap for being unfavorable for dump unloads management and burning scheduling uses.Overall calculation method this simultaneously is by disk
The coal period, sampling and Industrial Analysis time restriction, can not accomplish in minor time slice field damage indicator-specific statistics.
Possess significant limitation using computer Simulation calculation, be mainly manifested in due to coal yard itself complex environment,
Coal, heap such as unload, manage at the influence of factors, carry out needing to carry out coal yard before simulation calculating it is a large amount of assume and simplify, obtain
Be the computation model of idealization, while also needing to rely on expertise and computation model largely corrected, can not
It is accurate to calculate each index amount of complicated coal yard field damage under actual conditions, it can only be as one kind under small sample, standard laboratory atmosphere
Calculating means.
Therefore, the present invention is based on a large amount of historical datas generated in coal yard management operational process, neural network algorithm is used
It constructs field and damages prediction model, for predicting the physics and chemical wear amount of calculating coal yard, pass through the loss objective amount of quantum chemical method
Burning is changed for the fuel management of coal yard, fire coal and unit operation provides reference proposition.
Summary of the invention
It is an object of the invention to overcome deficiency in the prior art, a kind of thermoelectricity based on neural network algorithm is provided
Prediction technique is damaged in factory's coal yard field, complicated for solving existing power plant's coal yard field damage calculating process, and field damage index is not available formula
It is accurate to calculate, the technical issues of can only be predicted roughly by the special work experience of fuel.
In order to solve the above technical problems, the present invention provides a kind of, thermal power plant's coal yard field damage based on neural network algorithm is pre-
Survey method, characterized in that the following steps are included:
S1 determines the parameter of the principal element for influencing coal yard loss and characterization loss;
S2 will affect the current measurement value input neural network model of the principal element of coal yard damage for each dump,
Calculate the parameter value for obtaining characterization loss;
S3, according to the loss objective data of each dump of parameter value calculation of the characterization loss of each dump;
S4 calculates the loss objective for obtaining entire coal yard according to the loss objective data of each dump.
Further, the principal element for influencing coal yard loss includes pilling up time, air humidity, environment temperature, dump height
Degree, dump base diameter, dump heap density, the moisture as received coal of coal, the As-received volatile matter of coal, dump temperature field and shower water
Amount.
Further, dump temperature field includes apart from dump surface 0m measuring point mean temperature, apart from dump surface 1m measuring point
Mean temperature, apart from dump surface 2m measuring point mean temperature, apart from dump surface 3m measuring point mean temperature, apart from dump surface 4m
Measuring point mean temperature and apart from surface distance 5m measuring point mean temperature.
Further, the parameter for characterizing loss includes dump gross mass, dump calorific value and dump heat.
Further, loss objective includes mass loss, calorific value loss and thermal loss.
Further, the process for obtaining the loss objective of entire coal yard is calculated according to the loss objective data of each dump are as follows:
Mass loss is acquired using each dump mass loss is cumulative, and calorific value loss is acquired using each dump calorific value loss weighted average,
Thermal loss is acquired using each dump thermal loss is cumulative.
Compared with prior art, the beneficial effects obtained by the present invention are as follows being: the model is suitable for various coals respectively not
Loss calculation under same environment, different condition, different waiting times, building, training and the calculating of model are based entirely on discrete
Historical data is not directly affected by each factor of specific coal yard, can accurate calculating field more damage index;Model calculate with
Single dump is object, can calculate the loss objective of dump, and the loss objective of entire coal yard is based on dump and is counted again;Mould
Type dynamically, can regularly update Optimized model, can also pass through experimental data by using the data sample constantly generated
The endless integer of data sample is improved with expertise data.
Detailed description of the invention
Fig. 1 is the flow chart of the method for the present invention.
Specific embodiment
The invention will be further described below in conjunction with the accompanying drawings.Following embodiment is only used for clearly illustrating the present invention
Technical solution, and not intended to limit the protection scope of the present invention.
The present invention is based on a large amount of historical datas stored in power plant's coal yard management and operation, utilize neural network algorithm, structure
Build the prediction model of coal yard field damage index.The building of model is using dump as object, and the loss objective of entire coal yard is according to dump
Index carries out summarizing calculating.
As shown in Figure 1, a kind of thermal power plant's coal yard field damage prediction technique based on neural network algorithm of the invention, including with
Lower process:
Step S1 determines the parameter of the principal element for influencing coal yard loss and characterization loss.
According to the mechanism of coal yard loss (referred to as " field damage "), analysis and arrangement influences the factor of coal yard loss through standing:
(1) for physical deterioration, the characteristic of closing coal yard is considered, wherein the principal element for influencing evaporation mainly includes
Moisture as received coal (Mar), dump temperature (T) and the air of coal contact situation (bulk density ρ) and resting period (t) etc., also
Consider to spray bring moisture supplement (Ms), physical deterioration can (Δ m) be characterized with dump weight change.
(2) chemical wear caused by spontaneous combustion (quasi- spontaneous combustion) is paid particular attention in closing coal yard, wherein influencing chemistry damage
The principal element of consumption includes that moisture as received coal (Mar), dump temperature (T) and the air of coal contact situation (bulk density ρ), coal
As-received volatile matter (Var), away from surface distance (L), the decline of calorific value caused by shower water (Ms) and resting period (t) are changed
Learning loss can change that (Δ q) is characterized with calorific value.
In conclusion influence coal yard loss principal element having time parameter (pilling up time), (air is wet for environmental parameter
Degree, environment temperature), dump physical parameter (dump height, dump base diameter, dump heap density), coal Industrial Analysis parameter
(temperature T1 is (apart from the average temperature of dump surface 0m measuring point for (the As-received volatile matter of the moisture as received coal of coal, coal), dump temperature field
Degree), temperature T2 (apart from dump surface 1m measuring point mean temperature), temperature T3 (apart from dump surface 2m measuring point mean temperature), temperature
Spend T4 (apart from dump surface 3m measuring point mean temperature), temperature T5 (apart from dump surface 4m measuring point mean temperature), temperature T6 (away from
From surface distance 5m measuring point mean temperature)), water spray.Dump surface is indicated apart from surface 0m, and distance 1m indicates that thermometric bar hangs down
Directly in dump surface, vertical range between top temperature measuring point and dump surface, other similar when being inserted into dump.
The parameter of characterization loss includes dump gross mass, dump calorific value and dump heat.
Step S2 establishes neural network model, and input layer is the principal element for influencing coal yard loss, and output layer is characterization damage
The parameter of consumption.
Neural network model input/output argument is determined according to the above factor, as shown in table 1:
1 neural network input/output argument table of table
It according to model parameter table, is obtained from database and arranges historical data, by data cleansing and pretreatment (normalization
Processing), it obtains calculating desired sample data.
According to calculating model of neural networks, MATLAB training script is write, uses MATLAB training debugging model.Model instruction
After the completion of white silk, trained model is saved.
The numerical value for obtaining the current influence factor of thermal power plant's coal yard calls prediction model to be calculated, obtains using calculation procedure
Take the loss parameter of current coal yard.
Step S3 damages parameter according to the field of current coal yard and calculates each achievement data of field damage.
Field damage achievement data includes following three fields damage index:
(1) single dump mass loss Δ mi,j
Δmi,j=mi,j-mi,0
In formula, mi,jFor the dump quality at i dump j moment, kg;mi,0For the dump of 0 moment of i dump (starting pilling up time)
Quality, kg;J mark are as follows: to start pilling up time as the number of days of time started (current time-time started).
This value calculated result should be negative value, using the time as calculating scale, generally be subtracted initially with the value at current time
The value at moment, negative sign indicate loss, then can be considered error in data or mistake of statistics if it is positive value.
(2) calorific value of single dump loses Δ qi,j
In formula, Qi,jFor the dump total amount of heat at i dump j moment, kJ;Qi,0For the coal of 0 moment of i dump (starting pilling up time)
Heap total amount of heat, kJ;mi,jFor the dump quality at i dump j moment, kg.
(3) single dump thermal loss Mi,j(mark coal)
In formula, q0To mark coal calorific value, q0=29307kJ/kg (7000 kilocalories).Thermal loss is to fix the mark coal quality of calorific value
Amount is easier perception thermal loss size to identify in this way, this is also the calculation method of power plant's approval.
Step S4, calculates the loss objective of each dump, and the loss objective of entire coal yard is based on dump again and carries out statistics calculating.
Using single dump as unit of account, (each dump uses neural network model to carry out independent meter in entire coal yard
Calculate, but what all dumps used is all the same neural network model), quality and the calorific value costing bio disturbance of all dumps have been calculated
Cheng Hou, statistics calculates entire coal yard quality and calorific value loses, statistical calculation method are as follows: mass loss uses each dump mass loss
Cumulative to acquire, calorific value loss is acquired using each dump calorific value loss weighted average, and thermal loss uses each dump thermal loss
It is cumulative to acquire.
Calorific value loss by arithmetic mean of instantaneous value (cumulative after average) or cumulative cannot be calculated that (heat and quality can make
With accumulation calculating), it the use of weighted average is determined by its Physical Mechanism.
Step S5: neural network model optimization updates.
Update cycle and more new strategy is arranged in model, according to the model calculation, selects sample extraction strategy by user, certainly
Determine model training and deployment time point, periodically update computation model.
After computation model runs a period of time, neural network model model can be by utilizing the data generated during operation
New samples dynamically, regularly update Optimized model, can also improve data sample by experimental data and expertise data
Endless integer.
The purpose of the present invention mainly using having a large amount of historical data samples in discrete, database, is based on nerve net
Network algorithm, the prediction model of building coal yard field damage index.The model is suitable for various coals respectively in varying environment, different items
Loss calculation under part, different waiting time, building, training and the calculating of model based entirely on discrete historical data, not by
Specific each factor of coal yard directly affects, can accurate calculating field more damage index;It is pair that model, which is calculated with single dump,
As the loss objective of dump can be calculated, and the loss objective of entire coal yard is based on dump and is counted again;Model can pass through benefit
With the data sample constantly generated, dynamically, Optimized model is regularly updated, experimental data and expertise number can also be passed through
According to the endless integer for improving data sample.
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.
The above is only a preferred embodiment of the present invention, it is noted that for the ordinary skill people of the art
For member, without departing from the technical principles of the invention, several improvement and deformations can also be made, these improvement and deformations
Also it should be regarded as protection scope of the present invention.
Claims (6)
1. prediction technique is damaged in a kind of thermal power plant's coal yard field based on neural network algorithm, characterized in that the following steps are included:
S1 determines the parameter of the principal element for influencing coal yard loss and characterization loss;
S2 will affect the current measurement value input neural network model of the principal element of coal yard damage, calculate for each dump
Obtain the parameter value of characterization loss;
S3, according to the loss objective data of each dump of parameter value calculation of the characterization loss of each dump;
S4 calculates the loss objective for obtaining entire coal yard according to the loss objective data of each dump.
2. prediction technique, feature are damaged in a kind of thermal power plant's coal yard field based on neural network algorithm according to claim 1
It is that influence the principal element of coal yard loss include that pilling up time, air humidity, environment temperature, dump height, dump bottom are straight
Diameter, dump heap density, the moisture as received coal of coal, the As-received volatile matter of coal, dump temperature field and water spray.
3. prediction technique, feature are damaged in a kind of thermal power plant's coal yard field based on neural network algorithm according to claim 2
Be, dump temperature field include apart from dump surface 0m measuring point mean temperature, apart from dump surface 1m measuring point mean temperature, apart from coal
Heap surface 2m measuring point mean temperature, apart from dump surface 3m measuring point mean temperature, apart from dump surface 4m measuring point mean temperature and
Apart from surface distance 5m measuring point mean temperature.
4. prediction technique, feature are damaged in a kind of thermal power plant's coal yard field based on neural network algorithm according to claim 1
It is that characterize the parameter of loss include dump gross mass, dump calorific value and dump heat.
5. prediction technique, feature are damaged in a kind of thermal power plant's coal yard field based on neural network algorithm according to claim 4
It is that loss objective includes mass loss, calorific value loss and thermal loss.
6. prediction technique, feature are damaged in a kind of thermal power plant's coal yard field based on neural network algorithm according to claim 5
It is that the process for obtaining the loss objective of entire coal yard is calculated according to the loss objective data of each dump are as follows: mass loss uses each
Dump mass loss is cumulative to be acquired, and calorific value loss is acquired using each dump calorific value loss weighted average, and thermal loss uses each
Dump thermal loss is cumulative to be acquired.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910302672.0A CN110334840A (en) | 2019-04-16 | 2019-04-16 | A kind of thermal power plant's coal yard field damage prediction technique based on neural network algorithm |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910302672.0A CN110334840A (en) | 2019-04-16 | 2019-04-16 | A kind of thermal power plant's coal yard field damage prediction technique based on neural network algorithm |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110334840A true CN110334840A (en) | 2019-10-15 |
Family
ID=68139019
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910302672.0A Pending CN110334840A (en) | 2019-04-16 | 2019-04-16 | A kind of thermal power plant's coal yard field damage prediction technique based on neural network algorithm |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110334840A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111027257A (en) * | 2019-11-19 | 2020-04-17 | 中国矿业大学 | Method for predicting safe storage time of pulverized coal covered coal pile by using neural network |
CN111290357A (en) * | 2020-03-17 | 2020-06-16 | 山东创德软件技术有限公司 | Intelligent fuel management and control system based on Internet of things and big data |
CN112213228A (en) * | 2020-10-12 | 2021-01-12 | 华能海南发电股份有限公司海口电厂 | Dissipation rate testing system and method suitable for large coal-fired power station coal yard |
CN112508226A (en) * | 2020-10-29 | 2021-03-16 | 华能国际电力股份有限公司玉环电厂 | Thermal power plant coal yard loss prediction method and system |
CN113837607A (en) * | 2021-09-24 | 2021-12-24 | 浙江中烟工业有限责任公司 | Real-time analysis method and device for abnormal loss of related cut tobacco removed from cigarette packets |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103455901A (en) * | 2013-09-03 | 2013-12-18 | 华电电力科学研究院 | Coal-fired power plant coal yard refined management system and control method thereof |
CN105181744A (en) * | 2015-08-25 | 2015-12-23 | 清华大学 | Coal pile ignition period calculation method and coal yard spontaneous combustion preventing and monitoring system |
-
2019
- 2019-04-16 CN CN201910302672.0A patent/CN110334840A/en active Pending
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103455901A (en) * | 2013-09-03 | 2013-12-18 | 华电电力科学研究院 | Coal-fired power plant coal yard refined management system and control method thereof |
CN105181744A (en) * | 2015-08-25 | 2015-12-23 | 清华大学 | Coal pile ignition period calculation method and coal yard spontaneous combustion preventing and monitoring system |
Non-Patent Citations (2)
Title |
---|
王晓文: "基于支持向量机的火电厂燃煤优化控制", 《中国优秀硕士学位论文全文数据库 工程科技II辑》 * |
陈锋等: "火电厂燃煤损耗新指标研究与应用", 《华东电力》 * |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111027257A (en) * | 2019-11-19 | 2020-04-17 | 中国矿业大学 | Method for predicting safe storage time of pulverized coal covered coal pile by using neural network |
CN111027257B (en) * | 2019-11-19 | 2021-10-08 | 中国矿业大学 | Method for predicting safe storage time of pulverized coal covered coal pile by using neural network |
CN111290357A (en) * | 2020-03-17 | 2020-06-16 | 山东创德软件技术有限公司 | Intelligent fuel management and control system based on Internet of things and big data |
CN112213228A (en) * | 2020-10-12 | 2021-01-12 | 华能海南发电股份有限公司海口电厂 | Dissipation rate testing system and method suitable for large coal-fired power station coal yard |
CN112508226A (en) * | 2020-10-29 | 2021-03-16 | 华能国际电力股份有限公司玉环电厂 | Thermal power plant coal yard loss prediction method and system |
CN113837607A (en) * | 2021-09-24 | 2021-12-24 | 浙江中烟工业有限责任公司 | Real-time analysis method and device for abnormal loss of related cut tobacco removed from cigarette packets |
CN113837607B (en) * | 2021-09-24 | 2024-04-30 | 浙江中烟工业有限责任公司 | Real-time analysis method and device for loss abnormality of tobacco shreds related to package rejection |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110334840A (en) | A kind of thermal power plant's coal yard field damage prediction technique based on neural network algorithm | |
CN113723718A (en) | Energy carbon emission prediction method, device, equipment and medium | |
CN114722104B (en) | System and method for managing and operating enterprise carbon emission energy consumption data based on block chain | |
Zhang | Evaluating the method of total factor productivity growth and analysis of its influencing factors during the economic transitional period in China | |
CN105023061B (en) | Iron and steel enterprise's gas balance based on prediction model result dispatches system and method | |
Zhang et al. | The cost of low-carbon transition for China's coal-fired power plants: A quantile frontier approach | |
JP5501893B2 (en) | Plant operation evaluation system | |
JP6851275B2 (en) | LP gas consumption prediction device and LP gas consumption prediction method | |
CN105895175B (en) | A kind of method for demarcating nuclear reactor exit thermocouple | |
CN105303243A (en) | Blast furnace gas prediction balance scheduling system and method | |
CN110619409B (en) | Universal energy station scheduling method and device for self-adaptive disturbance quantum particle swarm | |
CN110137952A (en) | It is a kind of to realize source-lotus-storage coordinated operation Optimized model and method | |
CN110533247B (en) | Monthly power consumption prediction method adopting temperature data anomaly point compensation | |
Liu | FDI and employment by industry: A co-integration study | |
CN108932562A (en) | Integrated energy system comprehensive benefit assessment model method for building up | |
CN113887808A (en) | Carbon emission measuring and calculating method based on electric power big data | |
KR20220143920A (en) | The optimal calculation method of energy operating conditions in a steelworks, the optimal calculation apparatus of the energy operating conditions in a steelworks, and the operation method of a steelworks | |
Chen et al. | Uncertainty level of voltage in distribution network: an analysis model with elastic net and application in storage configuration | |
CN102136037A (en) | By-product gas generation predicting method for gray multi-factor MGM (modified Gompertz model) (1, n) model based on principal component analysis | |
Ibrahim et al. | Short-term individual household load forecasting framework using LSTM deep learning approach | |
CN105389637A (en) | Effective workday construction method for monthly electricity consumption prediction model | |
Quazza | Large scale control problems in electric power systems | |
CN115147136A (en) | Natural gas supply and demand difference determining method and device, computer equipment and storage medium | |
Meifeng et al. | Forecasting gas consumption based on a residual auto-regression model and kalman filtering algorithm | |
CN107066770A (en) | The commercial plant vapour system method for on-line optimization accelerated based on GPU |
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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191015 |