CN110334855A - Intelligence determines the prediction and optimization system and method for waste water water-coal-slurry preparation program - Google Patents
Intelligence determines the prediction and optimization system and method for waste water water-coal-slurry preparation program Download PDFInfo
- Publication number
- CN110334855A CN110334855A CN201910520229.0A CN201910520229A CN110334855A CN 110334855 A CN110334855 A CN 110334855A CN 201910520229 A CN201910520229 A CN 201910520229A CN 110334855 A CN110334855 A CN 110334855A
- Authority
- CN
- China
- Prior art keywords
- coal
- waste water
- slurry
- water
- data
- 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
Classifications
-
- C—CHEMISTRY; METALLURGY
- C10—PETROLEUM, GAS OR COKE INDUSTRIES; TECHNICAL GASES CONTAINING CARBON MONOXIDE; FUELS; LUBRICANTS; PEAT
- C10L—FUELS NOT OTHERWISE PROVIDED FOR; NATURAL GAS; SYNTHETIC NATURAL GAS OBTAINED BY PROCESSES NOT COVERED BY SUBCLASSES C10G, C10K; LIQUEFIED PETROLEUM GAS; ADDING MATERIALS TO FUELS OR FIRES TO REDUCE SMOKE OR UNDESIRABLE DEPOSITS OR TO FACILITATE SOOT REMOVAL; FIRELIGHTERS
- C10L1/00—Liquid carbonaceous fuels
- C10L1/32—Liquid carbonaceous fuels consisting of coal-oil suspensions or aqueous emulsions or oil emulsions
- C10L1/326—Coal-water suspensions
-
- 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
- G06N3/044—Recurrent networks, e.g. Hopfield 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
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- 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
- G06Q50/02—Agriculture; Fishing; Mining
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- General Health & Medical Sciences (AREA)
- Economics (AREA)
- Biomedical Technology (AREA)
- Tourism & Hospitality (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Marketing (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- General Business, Economics & Management (AREA)
- Oil, Petroleum & Natural Gas (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Organic Chemistry (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Chemical Kinetics & Catalysis (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- General Chemical & Material Sciences (AREA)
- Mining & Mineral Resources (AREA)
- Agronomy & Crop Science (AREA)
- Primary Health Care (AREA)
- Animal Husbandry (AREA)
- Marine Sciences & Fisheries (AREA)
Abstract
The present invention relates to waste water to prepare COAL-WATER SLURRY TECHNOLOGY, it is desirable to provide a kind of intelligent prediction and optimization system and method for determining waste water water-coal-slurry preparation program.The system includes water-coal-slurry slurry concentration prediction module and waste water proportion optimizing module;The former includes wastewater property Database Unit, coal and additive types selecting unit, data lead-out unit is slurried, for the type and scale prediction water-coal-slurry slurry concentration according to selected waste water, coal and additive.The latter includes waste water proportion optimizing unit, mix proportion scheme data lead-out unit, is up to the optimal mixing proportion that objective optimization determines all kinds of waste water with slurry concentration.The present invention realizes various waste water and blends the optimal path utilized, and the efficient of the various waste water of industries such as coal conversion, cleaning, low cost can be promoted to utilize.Optimal waste water mix proportion scheme can be selected to prepare waste water water-coal-slurry, improved benefit.The tedious steps for eliminating test method measurement water coal slurry concentration, reduce operating cost, shorten the operating time.
Description
Technical field
The present invention relates to waste water to prepare COAL-WATER SLURRY TECHNOLOGY, in particular to a kind of intelligent determining waste water water-coal-slurry preparation program
Prediction and optimization system and method.
Background technique
Coal resources in China reserves are larger, and coal occupies very high status in the energy resource structure in China.However coal is straight
It is lower to connect burning average utilization efficiency, causes the waste of energy resources.The application of coal conversion technology improves coal with development
Utilization efficiency, alleviate dependence of the energy market to petroleum resources, the attention by countries in the world.
However, the improvement of the waste water generated in coal conversion process is presented with the development and popularization and application of coal conversion technology
The situation of " two is high awkward ", i.e. wastewater discharge is big, and processing difficulty is big, and pollutant concentration is high, and treatment cost is high, often contains in waste water
Have a large amount of phenols, ammonia nitrogen, tar, cyanide, polycyclic aromatic hydrocarbon, oxygen-containing polycyclic and heterocyclic compound etc. it is a variety of it is difficult to degrade it is organic,
Poisonous and harmful substances, such as inappropriate processing, will cause environment seriously to pollute.Therefore, seek high treating effect, process stabilizing
Property it is stronger, the lower concentration organic wastewater disposal process for the treatment of cost be coal conversion Industry Innovation development only way.
Water-coal-slurry is a kind of novel low pollution oil-substituted fuel to grow up in oil crisis the 1970s, be by
60%~70% coal dust and 30%~40% water and a small amount of additive composition, it had both had the physical property of coal,
There is the flowing and stability as energy image-stone oil again.Production water-coal-slurry not only can use common cleaned industry water, moreover it is possible to
Using complicated component and it is difficult to the biochemical industrial wastewater disposed, can be realized while preparing the energy at easy, efficient waste
Reason and recycling.
Coal converts each type organic and oils for not only containing certain calorific value in waste water, also containing needed for water-coal-slurry preparation
Dispersing agent and stabilizer.Waste water preparation water-coal-slurry can simply and reliablely handle all types of industries waste water, save conventional slurrying water,
Realize waste water recycling even zero-emission.Waste water has certain promotion to the burning and gasification of water-coal-slurry simultaneously, and most of
Organic pollutant becomes CO2Or it is effectively synthesized gas ingredient, not only reduce environmental pollution, but also realize and turn waste into wealth.Therefore waste water
Slurrying is a kind of efficient and economical wastewater processing technology.
In waste water water-coal-slurry preparation process, the content of the components such as property of waste water such as ammonia nitrogen, COD can be to the characteristic of slurry
It produces bigger effect.It is that various waste water blending are handled and change of properties is larger in most cases and in practical application in industry,
So that the component of blending waste water is more complicated, difficulty is increased for the stable water-coal-slurry of processability.Currently, being directed to single waste water
The research of slurryability has certain achievement, but has not been reported for coal conversion industry various wastewater blending slurrying.Therefore, it grinds
The Optimization Prediction system that developing intellectual resourceization prepares waste water water-coal-slurry is studied carefully, by optimizing the configuration proportion of various waste water, the property prepared
The excellent waste water water-coal-slurry of energy is of great significance to improving water reuse efficiency and improving waste water water-coal-slurry performance.
Summary of the invention
The technical problem to be solved by the present invention is to overcome deficiency in the prior art, provide a kind of intelligent determining waste water
The prediction and optimization system and method for water-coal-slurry preparation program.
In order to solve the technical problem, solution of the invention is:
A kind of intelligent prediction and optimization system for determining waste water water-coal-slurry preparation program is provided, which includes water-coal-slurry
Slurry concentration prediction module and waste water match optimizing module;The former is used for the type according to selected waste water, coal and additive
And scale prediction water-coal-slurry slurry concentration, the latter is with the optimal Blend proportion that slurry concentration is up to that objective optimization determines all kinds of waste water
Example;Wherein,
The water-coal-slurry slurry concentration prediction module includes:
Wastewater property Database Unit, for storing the analysis data information of various waste water, including ammonia-nitrogen content, COD contain
Amount, BOD content, potassium content, sodium content, sulphates content, chloride content and total nitrogen content;
Coal and additive types selecting unit, for storing the type data information of coal and additive;
Slurry concentration predicting unit, it is dense using the type of waste water, coal and additive, the analysis data of waste water and water-coal-slurry
Test data is spent, the prediction of water-coal-slurry slurry concentration is realized based on BP neural network algorithm;
The waste water matches optimizing module
Waste water matches optimizing unit, for the type according to selected waste water, coal and additive, is up to slurry concentration
Objective optimization determines the optimal mixing proportion of all kinds of waste water, determines mix proportion scheme.
In the present invention, the water-coal-slurry slurry concentration prediction module further includes that data lead-out unit is slurried, for that will predict
Obtained water-coal-slurry slurry concentration export data;Export data are provided to waste water proportion optimizing unit (21) and carry out proportion optimizing
Operation, or it is directly output as the report of document or graphic form.
In the present invention, the waste water proportion optimizing module further includes mix proportion scheme data lead-out unit, for that will optimize
The report of mix proportion scheme export document or picture format afterwards.
Invention further provides realize the intelligent prediction for determining waste water water-coal-slurry preparation program using aforementioned system
With the method for optimization, comprising the following steps:
(1) it collects various for preparing the analysis data of the waste water of water-coal-slurry, building wastewater property database;It collects various
Coal and additive types information construct coal and additive types database;It collects enough waste water, coal and additive and prepares water coal
Test related data is slurried in slurry, the primary data as the training of BP neural network algorithm;
(2) training that BP neural network algorithm is carried out using primary data, by obtained by its prediction result and actual tests at
Concentration results are starched as further trained data, to improve forecasting accuracy;According to the kind of selected waste water, coal and additive
The prediction of class progress slurry concentration;
(3) variety classes waste water proportion possibility is enumerated using enumerative technique, and dense according to being slurried in step (2)
Prediction result is spent, selects the mix proportion scheme of highest slurry concentration as output scheme.
In the present invention, the step (2) is specifically included:
(2.1) to data prediction
Data are normalized before training neural network, are mapped to [0,1] or [- 1,1] section or smaller
Section;
(2.2) network struction
It is sequentially completed netinit, hidden layer output and output layer output, the calculating of error, the update of weight and biasing
Update, construct neural network;It is greater than the maximum times designed when error reaches default precision or learns number, then terminates to calculate
Method;Otherwise, next learning sample and corresponding output expectation are chosen, is learnt into next round;
(2.3) training
The waste water preparation water-coal-slurry data that experiment obtains are randomly divided into three groups, the 1st, 2,3 group is denoted as, accounts for total data respectively
70%, 15%, the 15% of amount;It is input to network using first group of data as training sample, wherein wastewater property parameter is as defeated
Enter parameter, waste water water-coal-slurry slurry concentration inputs neural network as output parameter, predicts water-coal-slurry slurry concentration;Initial power
Value and threshold value assign a certain range of random value, after trained, obtain satisfactory parameter;
(2.4) it verifies
Select the 2nd group of data as verifying sample, the setting period checks the validation error of network, under then entering by verifying
A cycle;Training error will be restrained with the increase of frequency of training and gradually, and then first dullness rises validation error after reducing;
(2.5) it tests
The network to meet the requirements after verified is tested with third group data;Wastewater property parameter is inputted, is calculated
Water-coal-slurry slurry concentration.
Compared with prior art, the present invention has the advantage that
(1) present invention selects on the basis of a large amount of waste water preparation water-coal-slurry mechanism Journal of Sex Research in laboratory to paste-forming properties shadow
Maximum waste component is rung, various waste water is realized and blends the optimal path utilized, the industries such as coal conversion can be promoted various useless
The efficient of water, cleaning, low cost utilize.
(2) it is various to realize waste water by the present invention, in the case where complicated component, optimal waste water can be selected with analogy
Case, the excellent waste water water-coal-slurry of processability are increased economic efficiency and environmental benefit.
(3) present invention uses BP neural network and intelligent allocation system prediction waste water water-coal-slurry slurry concentration, eliminates
Test method measures the tedious steps of water coal slurry concentration, and can science, accurately predict slurry concentration, reach rationally using useless
Water reduces operating cost, shortens the purpose of operating time.
Detailed description of the invention
Fig. 1 is the structural block diagram of the intelligent Optimization Prediction system for preparing waste water water-coal-slurry of the present invention.
In figure, 1 is water-coal-slurry slurry concentration prediction module, and 2 match optimizing module for waste water, and 11 be wastewater property database
Unit, 12 coals and additive types selecting unit, 13 slurry concentration predicting units, 14 is are slurried data lead-out unit, and 21 be useless
Water matches optimizing unit, and 22 be mix proportion scheme data lead-out unit.
Fig. 2 be the present invention with wastewater property data be input parameter, neural network knot of the slurry concentration as output parameter
Composition.
Specific embodiment
Firstly the need of explanation, it to be computer technology that the present invention relates to database technologys and neural network algorithm technology
In a kind of application of industrial big data field.During realization of the invention, answering for multiple software function modules can be related to
With.It is applicant's understanding that such as after reading over application documents, accurate understanding realization principle and goal of the invention of the invention,
In the case where existing well-known technique, the software programming technical ability that those skilled in the art can grasp completely with it realizes this
Invention.Aforementioned software functional module includes but is not limited to: water-coal-slurry slurry concentration prediction module, is given up at waste water proportion optimizing module
Aqueous nature Database Unit is slurried data lead-out unit, coal and additive types selecting unit, slurry concentration predicting unit, gives up
Water matches optimizing unit, mix proportion scheme data lead-out unit etc., category this scope that all the present patent application files refer to, applicant
It will not enumerate.
High concentrated organic wastewater component is sufficiently complex, and different waste water, and ingredient and concentration difference are very big, each in waste water
Kind ingredient and different concentration have different Influencing Mechanisms to the slurryability of water-coal-slurry, therefore, are prepared using waste water
Water-coal-slurry will such as ensure slurry concentration height, and water-coal-slurry performance is good, needs to carry out a large amount of basic research work.
Slurry concentration predicting unit prediction water-coal-slurry slurry concentration of the present invention is realized by BP neural network algorithm.Pass through industry
The a large amount of paste-forming properties in laboratory where boundary and applicant are studies have shown that under the premise of coal and additive types determine, waste water water
The slurry concentration of coal slurry is related with a variety of properties of waste water.Therefore, such as contained with the ammonia-nitrogen content of waste water, COD content, BOD content, potassium
Amount, sodium content, sulphates content, chloride content and total nitrogen content can predict water coal by BP neural network as parameter
Starch slurry concentration.
Through the invention waste water water-coal-slurry slurry concentration prediction to experiment obtain waste water preparation water-coal-slurry data into
The effective induction-arrangement of row, is trained and is predicted using BP neural network, and wastewater property data, coal data etc. are inputted number
Behind library, can user interface in the database select waste water, coal and additive by way of directly prediction water-coal-slurry at
Concentration is starched, the step of experiment is slurried is simplified, enterprise operation efficiency can be improved, reduces operating cost.
Waste water proportion optimizing part is then the slurry performance prediction that all proportion possibilities are carried out to selected various wastewater,
Select the mix proportion scheme output of highest slurry concentration.This method is succinctly intuitive, and result science is accurate.Selecting in the database needs
After the multiple waste water to be matched and selected coal and additive, mix proportion scheme can be directly calculated by user interface,
The utilization efficiency of wastewater treatment is improved on the basis of guaranteeing waste water water-coal-slurry performance.
The present invention is described in detail with specific embodiment below in conjunction with the accompanying drawings.Note that the following embodiments and the accompanying drawings is said
Bright only substantial illustration, the present invention is not intended to be applicable in it object or other purposes are defined, and the present invention and unlimited
Due to the following embodiments and the accompanying drawings.
As shown in Figure 1, the intelligent prediction for determining waste water water-coal-slurry preparation program includes: with optimization system
Water-coal-slurry slurry concentration prediction module 1: the module is according to selected waste water and ratio, coal and additive kind
Class predicts water-coal-slurry slurry concentration;
Waste water matches optimizing module 2: the module is up to that objective optimization determines that the optimal of all kinds of waste water is mixed with slurry concentration
Mixed ratio, determines mix proportion scheme.
Water-coal-slurry slurry concentration prediction module 1 includes:
Wastewater property Database Unit 11: the unit is used to store the data information of various waste water, the data information
Including ammonia-nitrogen content, COD content, BOD content, potassium content, sodium content, sulphates content, chloride content and total nitrogen content;
Coal and additive types selecting unit 12: the kind of selection coal and additive when the unit is predicted for slurry concentration
Class;
Slurry concentration predicting unit 13: the unit is selected according to wastewater property Database Unit 11 and coal and additive types
Unit 12 selectes waste water and ratio, coal and additive prediction water-coal-slurry slurry concentration;
Data lead-out unit 14 is slurried: the unit is slurried dense according to the waste water water-coal-slurry that slurry concentration predicting unit 13 is predicted
Degree export data, can export the report of document form or graphic form, and are supplied to waste water proportion optimizing unit 21 and are matched
It is operated than optimizing.
Slurry concentration predicting unit 13 predicts that water-coal-slurry slurry concentration is pre- using the intelligent optimization for preparing waste water water-coal-slurry
Examining system, and realized by BP neural network algorithm, the slurry concentration of waste water water-coal-slurry is related with a variety of properties of waste water.With waste water
Ammonia-nitrogen content, COD content, BOD content, potassium content, sodium content, sulphates content, chloride content and total nitrogen content conduct
Parameter predicts water-coal-slurry slurry concentration by BP neural network.
The waste water matches optimizing module 2
Waste water matches optimizing unit 21: the unit is used to set the optimal mixing proportion of various waste water, calls wastewater property
The data information of the various waste water of Database Unit 11, and combine the coal of coal and additive types selecting unit 12 and the number of additive
It is believed that breath, is up to the optimal mixing proportion that objective optimization determines all kinds of waste water with slurry concentration, determines mix proportion scheme;
Mix proportion scheme data lead-out unit 22: the unit matches matching for the determining all kinds of waste water of optimizing unit 21 according to waste water
Than the report that scheme exports document form or graphic form;
Waste water proportion optimizing unit 21 using enumerative technique by variety classes waste water proportion possibility enumerate, and call at
It starches concentration prediction unit 13 and carries out slurry concentration prediction, select highest slurry concentration mix proportion scheme for output scheme.
To sum up, the present invention is based on the intelligent Optimization Prediction systems for preparing waste water water-coal-slurry, are prediction with BP neural network
Algorithm can both predict the slurry concentration of selected waste water preparation water-coal-slurry or the type property according to live waste water, excellent
The proportion for changing variety classes waste water achievees the purpose that improve slurry concentration.
The training of BP neural network and prediction technique belong to the prior art, and application field is very extensive, but in various wastewater
Preferably there has been no utilizations for the formulation components of preparation water-coal-slurry and various waste water ratios.The example of detailed process is described as follows, related
The explanation of algorithmic procedure and formula is all made of the prior art, and those skilled in the art can be adjusted or mend according to actual needs
It fills, the present invention has not a particular requirement its content.
(1) data prediction
It needs to pre-process data before training neural network, the preprocessing means that the invention patent uses are normalizings
Change processing, maps the data into [0,1] or [- 1,1] section or smaller section.The output layer of this system neural network uses S
Shape excitation function, since the codomain of sigmoid function is limited in (0,1), i.e. the output of neural network can only be limited in (0,1), so
The output of training data need to normalize to [0,1] section.
Using simple, quickly normalization algorithm linear transformation algorithm is as follows:
Y=(x-min)/(max-min)
Wherein min is the minimum value of x, and max is the maximum value of x, and input vector x, the output vector after normalization is y.It is logical
Crossing above-mentioned formula can be by data normalization to [0,1] section.
(2) network struction
1) netinit
The node number of input layer is n, and the node number of hidden layer is l, and the node number of output layer is m.Input layer arrives
The weights omega of hidden layerij, the weight of hidden layer to output layer is ωjk, input layer to hidden layer is biased to aj, hidden layer is to defeated
Layer is biased to b outk.Learning rate is η, and excitation function is g (x).Wherein excitation function is that g (x) takes sigmoid function.Form are as follows:
2) hidden layer output and output layer output
The output of hidden layer are as follows:
The output of output layer are as follows:
3) calculating of error
Take error formula are as follows:
Wherein YkFor desired output.Remember Yk–Ok=ek, then E can be indicated are as follows:
In above formula, i=1 ... n, j=1 ... l, k=1 ... m.
4) update of weight
The more new formula of weight are as follows:
5) update biased
The more new formula of biasing are as follows:
6) algorithm terminates
Judge whether network error meets the requirements.It is greater than the maximum designed when error reaches default precision or learns number
Number then terminates algorithm.Otherwise, next learning sample and corresponding output expectation are chosen, is learnt into next round.
(3) training
The waste water preparation water-coal-slurry data that experiment obtains are randomly divided into three groups (being denoted as the 1st, 2,3 group), account for sum respectively
According to the 70% of amount, 15%, 15%, it is input to network using first group of data as training sample, wherein wastewater property parameter conduct
Parameter is inputted, waste water water-coal-slurry slurry concentration inputs neural network as output parameter, predicts water-coal-slurry slurry concentration.Initially
Weight and threshold value assign a certain range of random value, after trained, obtain satisfactory parameter.
(4) it verifies
Select the 2nd group of data as verifying sample, the setting period checks the validation error of network, under then entering by verifying
A cycle.General training error is gradually restrained with the increase of frequency of training, and validation error then it is first dull reduce after on
It rises.
(5) it tests
The network to meet the requirements after verified is tested with third group data.Wastewater property parameter is inputted, is calculated
Water-coal-slurry slurry concentration.
This example prepares ammonia synthesis process process as object using coal conversion, has invented a kind of intelligent preparation waste water water-coal-slurry
Optimization Prediction system.The system not only can directly predict the slurry performance for the single waste water that enterprises technique generates, and may be used also
To carry out intelligent optimization guidance to the various wastewater blending slurrying in enterprise and outside enterprise, optimal waste water mix proportion scheme system is provided
The waste water water-coal-slurry of standby high concentration.The system mainly includes the functions such as slurry concentration prediction and waste water proportion optimizing.
Slurry concentration prediction mainly includes following components:
1, wastewater property database is established
Wastewater property database is established, including the external waste water of the existing several waste water of enterprises and enterprise, data letter
Breath be ammonia-nitrogen content, COD content, BOD content, potassium content, sodium content, sulphates content, chloride content and total nitrogen content, such as
Shown in table 1, wastewater property data can be modified or created.
1 waste water data information of table
Note: gas washing wastewater, carbonization waste water, sulphur waste water are enterprises waste water, and external waste water is the external Industry Waste of enterprise
Water.
2, coal and the optional type of additive are determined
Coal is enterprise's Firing Shenhua Coal used at present, and additive includes a kind of common slurries additive agent sodium lignin sulfonate
With a kind of complex additive (sodium methylene bis-naphthalene sulfonate, formaldehyde condensate of sodium methylnaphthalene sulfonate and naphthalene for waste water exploitation
It is dispersing agent, and is prepared in 25%, 25% and 50% ratio), the additive amount of additive is 0.6% (dry pulverized coal).It can modify
Or newly-built coal and additive property data.
3, slurry concentration is predicted
Slurry concentration prediction is the core page of software, after wastewater property to database is manually entered, i.e., predictable
Its slurry concentration.When wastewater property changes, influence of certain waste water to water-coal-slurry slurryability can be individually predicted, it can also
Slurry concentration prediction is carried out to select the waste water of specific proportion, to play the role of determining waste water if appropriate for slurrying.Specifically
Embodiment is as shown in table 2.
2 slurry concentration of table predicts example
Note: gas washing wastewater, carbonization waste water, sulphur waste water are enterprises waste water, and external waste water is the external Industry Waste of enterprise
Water.
4, slurry concentration data export
Slurry concentration data export the main auxiliary enterprises internal information exchange in interface and retain, being slurried specific waste water
Concentration data exports as the report of document form or graphic form.
It includes following components that waste water, which matches optimizing:
It (1) is up to target with slurry concentration by multiple waste water in artificial selection wastewater property database, it is excellent
Change the optimal mixing proportion for determining all kinds of waste water, exports mix proportion scheme.When wastewater property changes, sought by waste water proportion
It is excellent that best waste water mix proportion scheme can be adjusted, guarantee the slurry performance of water-coal-slurry, maintains pulping process flow even running.Specifically
Embodiment is as shown in table 3.
(2) mix proportion scheme data export
Mix proportion scheme data export the main auxiliary enterprises information exchange in interface and retention, can be by the slurry concentration of specific waste water
Data export as the report of document form or graphic form.
The success of the system is developed and is put into operation, will so that enterprise wastewater prepares coal water slurry process parameter and is optimized,
Equipment operating efficiency improves, and the performance of waste water water-coal-slurry is secure, and wastewater treatment benefit is improved.The system can be widely popularized
It is applied in the technique of all kinds of coal conversion waste water preparation water-coal-slurry.
Above embodiment is only to enumerate, and does not indicate limiting the scope of the invention.These embodiments can also be with other
Various modes are implemented, and can be done in the range of not departing from technical thought of the invention it is various omit, displacement, change.
3 mix proportion scheme optimizing example of table
Note: gas washing wastewater, carbonization waste water, sulphur waste water are enterprises waste water, and external waste water is the external Industry Waste of enterprise
Water.
Claims (5)
1. a kind of intelligent prediction and optimization system for determining waste water water-coal-slurry preparation program, which is characterized in that the system includes
Water-coal-slurry slurry concentration prediction module (1) and waste water proportion optimizing module (2);The former be used for according to selected waste water, coal and
The type and scale prediction water-coal-slurry slurry concentration of additive, the latter are up to that objective optimization determines all kinds of waste water with slurry concentration
Optimal mixing proportion;Wherein,
The water-coal-slurry slurry concentration prediction module (1) includes:
Wastewater property Database Unit (11), for storing the analysis data information of various waste water, including ammonia-nitrogen content, COD contain
Amount, BOD content, potassium content, sodium content, sulphates content, chloride content and total nitrogen content;
Coal and additive types selecting unit (12), for storing the type data information of coal and additive;
Slurry concentration predicting unit (13), it is dense using the type of waste water, coal and additive, the analysis data of waste water and water-coal-slurry
Test data is spent, the prediction of water-coal-slurry slurry concentration is realized based on BP neural network algorithm;
The waste water matches optimizing module (2)
Waste water matches optimizing unit (21), for the type according to selected waste water, coal and additive, is up to slurry concentration
Objective optimization determines the optimal mixing proportion of all kinds of waste water, determines mix proportion scheme.
2. system according to claim 1, which is characterized in that the water-coal-slurry slurry concentration prediction module (1) further includes
Data lead-out unit (14) are slurried, the water-coal-slurry slurry concentration for that will predict to obtain exports data;Export data are provided to
Waste water proportion optimizing unit (21) carries out proportion optimizing operation, or is directly output as the report of document or graphic form.
3. system according to claim 1, which is characterized in that waste water proportion optimizing module (2) further includes proportion
Protocol lead-out unit (22), the report for mix proportion scheme export document or picture format after optimizing.
4. realizing the side of the intelligent prediction and optimization for determining waste water water-coal-slurry preparation program using system described in claim 1
Method, which comprises the following steps:
(1) it collects various for preparing the analysis data of the waste water of water-coal-slurry, building wastewater property database;Collect various coals and
Additive types information constructs coal and additive types database;It collects enough waste water, coal and additive and prepares water-coal-slurry
Test related data is slurried, the primary data as the training of BP neural network algorithm;
(2) training that BP neural network algorithm is carried out using primary data, it is dense by being slurried obtained by its prediction result and actual tests
Result is spent as further trained data, to improve forecasting accuracy;According to the type of selected waste water, coal and additive into
The prediction of row slurry concentration;
(3) variety classes waste water proportion possibility is enumerated using enumerative technique, and pre- according to the slurry concentration in step (2)
It surveys as a result, selecting the mix proportion scheme of highest slurry concentration as output scheme.
5. according to the method described in claim 4, it is characterized in that, the step (2) specifically includes:
(2.1) to data prediction
Data are normalized before training neural network, are mapped to [0,1] or [- 1,1] section or smaller section;
(2.2) network struction
Be sequentially completed netinit, hidden layer output and output layer output, the calculating of error, the update of weight and biasing more
Newly, neural network is constructed;It is greater than the maximum times designed when error reaches default precision or learns number, then terminates algorithm;
Otherwise, next learning sample and corresponding output expectation are chosen, is learnt into next round;
(2.3) training
The waste water preparation water-coal-slurry data that experiment obtains are randomly divided into three groups, the 1st, 2,3 group is denoted as, accounts for total amount of data respectively
70%, 15%, 15%;It is input to network using first group of data as training sample, wherein wastewater property parameter is as input ginseng
Number, waste water water-coal-slurry slurry concentration input neural network as output parameter, predict water-coal-slurry slurry concentration;Initial weight and
Threshold value assigns a certain range of random value, after trained, obtains satisfactory parameter;
(2.4) it verifies
Select the 2nd group of data as verifying sample, the setting period checks the validation error of network, by verifying then into next
Period;Training error will be restrained with the increase of frequency of training and gradually, and then first dullness rises validation error after reducing;
(2.5) it tests
The network to meet the requirements after verified is tested with third group data;Wastewater property parameter is inputted, water outlet coal is calculated
Starch slurry concentration.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910520229.0A CN110334855A (en) | 2019-06-17 | 2019-06-17 | Intelligence determines the prediction and optimization system and method for waste water water-coal-slurry preparation program |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910520229.0A CN110334855A (en) | 2019-06-17 | 2019-06-17 | Intelligence determines the prediction and optimization system and method for waste water water-coal-slurry preparation program |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110334855A true CN110334855A (en) | 2019-10-15 |
Family
ID=68141021
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910520229.0A Pending CN110334855A (en) | 2019-06-17 | 2019-06-17 | Intelligence determines the prediction and optimization system and method for waste water water-coal-slurry preparation program |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110334855A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112852512A (en) * | 2021-01-12 | 2021-05-28 | 中国矿业大学 | Method for preparing high-performance coal water slurry by quickly matching coal types |
CN115006881A (en) * | 2022-07-07 | 2022-09-06 | 晨星基因(北京)智能科技有限公司 | Plant component selection method capable of realizing accurate quantification |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107194026A (en) * | 2017-04-17 | 2017-09-22 | 中国大唐集团科学技术研究院有限公司火力发电技术研究所 | Absorption tower sweetening process modeling method based on Bayesian network |
CN107892964A (en) * | 2018-01-02 | 2018-04-10 | 浙江大学 | Application for the slurries additive agent of coal chemical industrial waste water slurrying and its in slurrying |
CN108975553A (en) * | 2018-08-03 | 2018-12-11 | 华电电力科学研究院有限公司 | A kind of thermal power plant's coal-contained wastewater processing coagulant charging quantity accuracy control method |
CN109022073A (en) * | 2018-08-10 | 2018-12-18 | 福州大学 | A kind of water-coal-slurry and preparation method thereof using phenol wastewater preparation |
CN109251773A (en) * | 2018-09-18 | 2019-01-22 | 西安三瑞实业有限公司 | A kind of coal and semicoke are the method that raw material composite waste prepares water-coal-slurry |
CN109810738A (en) * | 2019-03-05 | 2019-05-28 | 安徽理工大学 | Using the method for BDO waste water preparation water-coal-slurry |
-
2019
- 2019-06-17 CN CN201910520229.0A patent/CN110334855A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107194026A (en) * | 2017-04-17 | 2017-09-22 | 中国大唐集团科学技术研究院有限公司火力发电技术研究所 | Absorption tower sweetening process modeling method based on Bayesian network |
CN107892964A (en) * | 2018-01-02 | 2018-04-10 | 浙江大学 | Application for the slurries additive agent of coal chemical industrial waste water slurrying and its in slurrying |
CN108975553A (en) * | 2018-08-03 | 2018-12-11 | 华电电力科学研究院有限公司 | A kind of thermal power plant's coal-contained wastewater processing coagulant charging quantity accuracy control method |
CN109022073A (en) * | 2018-08-10 | 2018-12-18 | 福州大学 | A kind of water-coal-slurry and preparation method thereof using phenol wastewater preparation |
CN109251773A (en) * | 2018-09-18 | 2019-01-22 | 西安三瑞实业有限公司 | A kind of coal and semicoke are the method that raw material composite waste prepares water-coal-slurry |
CN109810738A (en) * | 2019-03-05 | 2019-05-28 | 安徽理工大学 | Using the method for BDO waste water preparation water-coal-slurry |
Non-Patent Citations (1)
Title |
---|
王金乾: "煤转化废弃物制备水煤浆成浆特性及优化配比专家系统的研究", 《中国优秀硕士学位论文全文数据库》 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112852512A (en) * | 2021-01-12 | 2021-05-28 | 中国矿业大学 | Method for preparing high-performance coal water slurry by quickly matching coal types |
CN115006881A (en) * | 2022-07-07 | 2022-09-06 | 晨星基因(北京)智能科技有限公司 | Plant component selection method capable of realizing accurate quantification |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Zhu et al. | The impact of cross-region industrial structure optimization on economy, carbon emissions and energy consumption: A case of the Yangtze River Delta | |
Wang et al. | Impact of China's economic growth and energy consumption structure on atmospheric pollutants: Based on a panel threshold model | |
Li et al. | A review of socio-technical energy transition (STET) models | |
Rabe et al. | State competition as a source driving climate change mitigation | |
Li et al. | Evaluation of the circular economy development level of Chinese chemical enterprises | |
Hall | Major OECD country industrial sector interfuel substitution estimates, 1960–1979 | |
CN110334855A (en) | Intelligence determines the prediction and optimization system and method for waste water water-coal-slurry preparation program | |
Liu et al. | Does green innovation suppress carbon emission intensity? New evidence from China | |
Xie et al. | Dynamic environmental efficiency analysis of China’s power generation enterprises: a game cross-Malmquist index approach | |
Jiang et al. | Which is the more important factor of carbon emission, coal consumption or industrial structure? | |
Steininger et al. | Exploiting the medium term biomass energy potentials in Austria: a comparison of costs and macroeconomic impact | |
Dantas | The evolution of the knowledge accumulation function in the formation of the Brazilian biofuels innovation system | |
Xia et al. | Coupling coordination degree between coal production reduction and CO2 emission reduction in coal industry | |
Xu et al. | Strategic diagnosis of China’s modern coal-to-chemical industry using an integrated SWOT-MCDM framework | |
Tong | The spatiotemporal evolution pattern and influential factor of regional carbon emission convergence in China | |
Deng et al. | On the nonlinear relationship between energy consumption and economic and social development: evidence from Henan Province, China | |
Jee et al. | Knowledge Spillovers between Clean and Dirty Technologies | |
CN110795815B (en) | Method for evaluating life cycle environmental influence during operation of boiler | |
CN113240343A (en) | Watershed water environment management performance evaluation method | |
Roussafi | Regional development trajectories of renewable energy: Evidence from French regions | |
Ju et al. | Environmental regulation, industrial agglomeration, and sustainable development in the Chinese textile industry | |
Li et al. | Paths to carbon neutrality in china’s chemical industry | |
Losacker | The diffusion of environmental innovations: a geographical perspective on lead markets and technology licensing in China | |
Wang et al. | Evaluation of clean coal technologies in China: Based on rough set theory | |
Lu | Energy consumption and pollution control from the perspective of industrial economic activity: An empirical study of China’s coastal provinces |
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 | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20191015 |
|
WD01 | Invention patent application deemed withdrawn after publication |