CN108595518A - A kind of alumina producing evaporation process online data coordination approach and system - Google Patents
A kind of alumina producing evaporation process online data coordination approach and system Download PDFInfo
- Publication number
- CN108595518A CN108595518A CN201810251631.9A CN201810251631A CN108595518A CN 108595518 A CN108595518 A CN 108595518A CN 201810251631 A CN201810251631 A CN 201810251631A CN 108595518 A CN108595518 A CN 108595518A
- Authority
- CN
- China
- Prior art keywords
- data
- individual
- result
- coordination
- evaporation process
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Hardware Design (AREA)
- Evolutionary Computation (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Factory Administration (AREA)
Abstract
An embodiment of the present invention provides a kind of alumina producing evaporation process online data coordination approach and systems, including:Online data is inputted and presets multi-modal individual-layer data Coordination Model by the online data for obtaining each measurand in evaporation process;It includes multiple default single mode individual-layer data Coordination Models to preset multi-modal individual-layer data Coordination Model, and multiple default single mode individual-layer data Coordination Models are corresponding with multiple production mode of evaporation process;Obtain multiple first coordinations results that online data belongs to multiple probability of each production mode and online data obtains after the multiple default single mode individual-layer data Coordination Model processing, coordinate result according to multiple probability and corresponding the multiple first, the second of online data is obtained to coordinate as a result, realizing the data harmonization to online data.Method provided in an embodiment of the present invention considers the actual conditions that evaporation process runs on multiple production mode so that data harmonization result is more accurate.
Description
Technical field
The present embodiments relate to production process data processing technology fields, more particularly, to a kind of alumina producing
Evaporation process online data coordination approach and system.
Background technology
Alumina producing is a key areas of modern industrial production, and 70% aluminium oxide is given birth to by Bayer process in the world
Production, is made raw slurry, in high temperature and pressure item after bauxite and milk of lime, aqueous caustic and circulating mother liquor are ground by a certain percentage
Sodium aluminate solution is dissolved out through pre-desiliconizing under part, the works such as sodium aluminate solution passes through red-mud separation successively, kind point is decomposed, evaporation, roasting
Sequence produces aluminium oxide.Evaporation process is the critical process of aluminum oxide production process, by heat steam by seed precipitation solution and
The excessive moisture evaporation in filtrate is washed, high concentration circulating mother liquor is provided for dissolution process.It was evaporated in practical alumina producing
Cheng Zhong, process measurement data inevitably by error interference, makes measurement data deviate actual value, and is unsatisfactory for quality of material
Balance, heat balance relationship and some process constraints.In addition, the limitation of examined technology and economic condition, the important ginseng in part
Number can not obtain.Inaccurate measurement data determines the modeling for influencing alumina producing evaporation process, optimization, control even management
Plan is related to the economic and technical index of entire alumina producing.
Data harmonization is meeting mechanism balance about as a kind of data processing technique using the redundancy of measurement data
On the basis of beam and parametric boundary condition, measurement error is reduced, parameter is not surveyed in estimation.Currently, data coordinating method includes projection
Matrix method, iterative linearization method, weighted least-squares method, quasi- weighted least-squares method, the methods of based on principle of maximum entropy.But
Since the product demand of aluminium oxide actual production process is not fixed, when product demand fluctuates, pan feeding condition
It changes, operating parameter is caused to change.In addition, the change of product type and the variation of production decision, can cause to grasp
Make the adjustment of point.In this way, production process is run under multiple production mode, according to the data harmonization model of the single overall situation, meeting
Influence the accuracy of data harmonization result.Therefore, it is urgent to provide a kind of online datas suitable for alumina producing evaporation process
Coordination approach.
Invention content
An embodiment of the present invention provides a kind of aluminium oxide overcoming the above problem or solve the above problems at least partly
Produce evaporation process online data coordination approach and system.
On the one hand an embodiment of the present invention provides a kind of alumina producing evaporation process online data coordination approach, including:
The online data is inputted and presets multi-modal layering by the online data for obtaining each measurand in evaporation process
Data harmonization model;The default multi-modal individual-layer data Coordination Model includes that multiple default single mode individual-layer datas coordinate mould
Type, and multiple production mode of the multiple default single mode individual-layer data Coordination Model and evaporation process correspond;
It obtains the online data and belongs to each production mould probability of state and the online data through the multiple default list
Multiple first obtained after the processing of mode individual-layer data Coordination Model are coordinated as a result, according to multiple probability for getting and corresponding
The multiple first coordinates as a result, obtain the online data second coordinates result.
On the other hand an embodiment of the present invention provides a kind of alumina producing evaporation process online datas to coordinate system, described
System includes:
Data acquisition module, the online data for obtaining each measurand in evaporation process, by the online data
Multi-modal individual-layer data Coordination Model is preset in input;The default multi-modal individual-layer data Coordination Model includes multiple default single modes
State individual-layer data Coordination Model, and multiple production moulds of the multiple default single mode individual-layer data Coordination Model and evaporation process
State corresponds;
Data harmonization module belongs to each production mould probability of state and the online data for obtaining the online data
Obtained after the multiple default single mode individual-layer data Coordination Model processing multiple first are coordinated as a result, according to getting
Multiple probability and corresponding the multiple first are coordinated to coordinate as a result, i.e. realization pair as a result, obtaining the second of the online data
The data harmonization of online data described in evaporation process.
For the third aspect an embodiment of the present invention provides a kind of computer program product, the computer program product includes depositing
The computer program in non-transient computer readable storage medium is stored up, the computer program includes program instruction, when described
When program instruction is computer-executed, the computer is made to execute the above method.
An embodiment of the present invention provides a kind of non-transient computer readable storage medium, the non-transient calculating for fourth aspect
Machine readable storage medium storing program for executing stores computer instruction, and the computer instruction makes the computer execute the above method.
A kind of alumina producing evaporation process online data coordination approach provided in an embodiment of the present invention and system, pass through by
Multi-modal individual-layer data Coordination Model is preset in the online data input of each measurand, coordinates mould in default multi-modal individual-layer data
In type, the first coordination result that multiple default single mode individual-layer data Coordination Models obtain the processing of online data is obtained respectively
And online data belongs to each production mould probability of state, is obtained by multiple first coordination results and multiple corresponding Probabilistic Synthesis
Coordinate to second as a result, realizing the data slice to evaporation process online data.Method provided in an embodiment of the present invention considers
Evaporation process runs on the actual conditions of multiple production mode so that data harmonization result is compared with the data association using single overall situation
The method of mode transfer type is more accurate.
Description of the drawings
Fig. 1 is a kind of flow of alumina producing evaporation process online data coordination approach provided in an embodiment of the present invention
Figure;
Fig. 2 is the structural schematic diagram of single mode individual-layer data Coordination Model in the embodiment of the present invention;
Fig. 3 belongs to the probability schematic diagram of different modalities for each data sample in the example of the embodiment of the present invention;
Fig. 4 be the embodiment of the present invention example in each Modal Measured Data standard deviation and coordination data standard deviation comparison
Figure;
Fig. 5 be the embodiment of the present invention example under different modalities measurand relative standard deviation comparison diagram;
Fig. 6 be the embodiment of the present invention example in the coordination result standard deviation that obtains of single data harmonization model with it is multi-modal
The comparison diagram of the standard deviation for the result that data harmonization model obtains;
Fig. 7 be the embodiment of the present invention example in level Four flash vessel discharging flow measured value and coordination value comparison diagram;
Fig. 8 is the measured value of initial steam flow and the comparison diagram of coordination value in the example of the embodiment of the present invention;
Fig. 9 is that a kind of alumina producing evaporation process online data provided in an embodiment of the present invention coordinates system structure frame
Figure.
Specific implementation mode
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical solution in the embodiment of the present invention is explicitly described, it is clear that described embodiment is the present invention
A part of the embodiment, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art are not having
The every other embodiment obtained under the premise of creative work is made, shall fall within the protection scope of the present invention.
Fig. 1 is a kind of flow of alumina producing evaporation process online data coordination approach provided in an embodiment of the present invention
Figure, as shown in Figure 1, the method includes:
S1 obtains the online data of each measurand in evaporation process, and online data input is default multi-modal
Individual-layer data Coordination Model;The default multi-modal individual-layer data Coordination Model includes that multiple default single mode individual-layer datas are coordinated
Model, and multiple production mode of the multiple default single mode individual-layer data Coordination Model and evaporation process correspond;
S2 obtains the online data and belongs to each production mould probability of state and the online data through the multiple default
Multiple first obtained after the processing of single mode individual-layer data Coordination Model are coordinated as a result, according to the multiple probability and correspondence got
It is the multiple first coordinate as a result, obtain the online data second coordinate result.
Wherein, in step sl, since generally there are multiple production mode in evaporation process, so using default multi-modal
Individual-layer data Coordination Model carries out data harmonization to online data, and each production mode corresponds to a default single mode hierarchy number
According to Coordination Model.
In step s 2, when carrying out data harmonization to online data using default multi-modal individual-layer data Coordination Model,
For needing the online data of progress data harmonization, it can not determine which production mode it particularly belongs to, but can determine its category
In each production mould probability of state.
Specifically, the detailed process of data harmonization is carried out to online data using default multi-modal individual-layer data Coordination Model
For:Online data is inputted after presetting multi-modal individual-layer data Coordination Model, online data is corresponding more through multiple mode respectively
A default single mode individual-layer data Coordination Model processing, obtains multiple first and coordinates result.Due to that can not determine that online data has
Which mode body belongs to, and obtaining online data while obtaining the first coordination result belongs to each production mould probability of state,
I.e. each first, which coordinates result, corresponds to a probability.So coordinate result and multiple corresponding probability according to multiple first, it is comprehensive
One second is obtained to coordinate as a result, the second coordination result is online after default multi-modal individual-layer data Coordination Model processing
The final coordination result of data.
A kind of alumina producing evaporation process online data coordination approach provided in an embodiment of the present invention, by by each measurement
Multi-modal individual-layer data Coordination Model is preset in the online data input of variable, in presetting multi-modal individual-layer data Coordination Model,
Obtain respectively multiple default single mode individual-layer data Coordination Models to the processing of online data obtain first coordinate result and
Online data belongs to each production mould probability of state, and the is obtained coordinating results and multiple corresponding Probabilistic Synthesis by multiple first
Two coordinate as a result, realizing the data slice to evaporation process online data.Method provided in an embodiment of the present invention considers steaming
Process operation is sent out in the actual conditions of multiple production mode so that data harmonization result is compared with the data harmonization mould using the single overall situation
The method of type is more accurate.
Based on above-described embodiment, the method further includes:
The first history data set of each measurand in evaporation process is obtained, and is built according to first history data set
It is described to preset multi-modal individual-layer data Coordination Model.
It is specifically, described to preset multi-modal individual-layer data Coordination Model according to first history data set structure is described,
It specifically includes:
According to first history data set, evaporation process is divided into the multiple production mode;
Corresponding default single mode individual-layer data Coordination Model, the multiple production mode pair are built for each production mode
The multiple single mode individual-layer data Coordination Model answered constitutes the multi-modal individual-layer data Coordination Model.
Further, according to first history data set, evaporation process is divided into using gauss hybrid models described more
A production mode.
Specifically, the first history data set of measurand is expressed as X=[x1,x2,...,xm]∈Rn×m, n and m distinguish table
Show total sample number and variable dimension.Production mode is divided using gauss hybrid models, the number of wherein gauss component can
It is determined by the priori of production operation worker.Based on gauss hybrid models, the first history data set is divided into k second and is gone through
History data set, the second history data set divided are expressed asWherein k-th of mode pair
The sample set answered isIndicate i-th of sample in k-th of mould
All sample numbers in state, nkIndicate the number of samples under k-th of mode.In this way, evaporation process is divided by gauss hybrid models
At different modalities, corresponding second history data set of each mode also accordingly determines.
For example, 2880 groups of measurement data of certain 34 measurand of factory's quantity-produced is selected to do analysis of cases, i.e.,
One history data set is expressed as X=[x1,x2,...,x34]∈R2880×34.Production mode is drawn using gauss hybrid models
Point, 4 Gauss components are generated according to priori.Based on gauss hybrid models, the first history data set is divided into 4 kinds of mode
Corresponding second history data set, the second history data set divided are expressed asWherein
Corresponding second history data set of k-th of mode is Table
Show all sample numbers of i-th of sample in k-th of mode, nkIndicate the number of samples under k-th of mode.Each data sample category
It is as shown in Figure 2 in the probability graph of different modalities.
Further, the method further includes:
First history data set is divided into multiple second history data sets corresponding to each production mode;
Accordingly, described to build corresponding default single mode individual-layer data Coordination Model for each production mode, it is specific to wrap
It includes:
It is that corresponding production mode structure presets single mode individual-layer data Coordination Model according to each second history data set.
Specifically, consider that evaporation process does not survey number of the number more than equilibrium equation of variable, there are data redundancy deficiencies
The problem of, using individual-layer data Coordination Model, as shown in Figure 3.First, the data harmonization model of quality of material balance layer is established,
First into five effects and sextuple effect stock solution flow, original liquid concentration, go out four sudden strain of a muscle feed liquid flows, go out four sudden strain of a muscle feed concentrations and assist
It adjusts, each equipment discharging flow, discharge concentration, secondary steam flow amount is estimated;Then, by the coordination in quality of material balance layer
Value and estimated value are substituted into as given data in thermal balance layer, the data harmonization model of thermal balance layer are established, to drop temperature, two
Secondary stripping temperature, initial steam flow, initial steam temperature, condensate temperature, stoste temperature are coordinated, and are carried out to each heat gain from appliance and equipment
Estimation.Default single mode individual-layer data Coordination Model is expressed as:
In formula, f1And f2The object function of material mass balance layer and heat balance layer data Coordination Model is indicated respectively;X
=[x1,x2,...,xm] andThe measurement data and coordination data sample of m measurand are indicated respectively
Collection;WithThe measurement data and coordination data of ith measurement variable are indicated respectively
Sample set;WithJ-th of the measured value and coordination value of ith measurement variable are indicated respectively;σiIndicate ith measurement variable
Standard deviation;H indicates mechanism equality constraint;WithI-th of coordination variable is indicated respectively and is not surveyed under the variation of variable for q-th
Limit;WithThe variation upper limit for indicating i-th of coordination variable respectively and not surveying variable q-th;L indicates to wrap in material mass balance
The number of the measurand contained;M-l indicates the number for the measurand for including in thermal balance.
Specific object function and constraint equation are expressed as:
The object function of quality of material balance layer and thermal balance layer is defined as:
Make knowledge and gives numerical value.λ indicates weight, can be determined by empirical rule. Indicate coordination value.
Using the boundary condition of evaporation process quality of material balance, thermal balance and decision variable as the constraint of data harmonization model
Condition.One is as shown in table 1 to sextuple effect and one to the material balance of level Four flash vessel and thermal balance equality constraint.
Table 1
Feed liquid flow, temperature, concentration and steam flow, temperature boundary constraints are expressed as:
In formula,It indicates to measure
The variation lower limit of the coordination value of variable;Cjmin,Fjmin,Vlmin,QiminThe variation lower limit of the estimated value of variable is not surveyed in expression;Indicate the variation upper limit of the coordination value of measurand;
Cjmax,Fjmax,Vlmax,QimaxThe variation lower limit of the estimated value of variable is not surveyed in expression.
In fact, data harmonization problem can regard an optimization problem as.Data harmonization model is established for obtaining each measurement
The coordination data of variable, adoption status branching algorithm solve the individual-layer data Coordination Model, obtain so that becoming in each measurement
The coordination data of amount meets the coordination value of the measurement data of measurement error minimum in the case of process mechanism equilibrium equation.
Based on above-described embodiment, the default single mode individual-layer data Coordination Model is divided into mass balance layer and heat balance
Layer;
Accordingly, the online data is obtained to obtain after the multiple default single mode individual-layer data Coordination Model processing
It is multiple first coordinate as a result, specifically including:
The online data obtained third after mass balance layer processing is obtained to coordinate as a result, obtaining described the again
The first coordination result that three coordination results obtain after heat balance layer processing.
Further, the multiple probability and corresponding the multiple first that the basis is got are coordinated as a result, obtaining institute
State online data second is coordinated as a result, specifically including:
Coordinate result by the multiple first to be weighted to obtain the second coordination result;Wherein, each first
It is corresponding probability to coordinate weight of the result in the weighted calculation.
Specifically, mode vectors correlation is carried out to on-line measurement data, measurement data is belonged into each mould probability of state and different associations
Coordination value under mode transfer type is combined, and obtains the coordination data after mode vectors correlation.Concrete operations are:
Define one group of measured value of each measurand of evaporation processFor one group of on-line measurement
Data.Sample xnewBelong to k-th of mode probability be expressed as p (k | xnew), it is by Bayesian inference Rule Expression:
By on-line measurement data xnewCoordination value under k-th of modeWith measurement
Data belong to each mould probability of state and are combined, and obtain the data harmonization result after mode vectors correlation:
In formula,It is coordination result final after ith measurement variable point mode;p(k|xnew) it is that online data belongs to
K-th of mould probability of state;It is coordination value of the ith measurement variable under k-th of mode.
The embodiment of the present invention is further described below by an example, in formula,It is ith measurement variable
Final coordination result after point mode;p(k|xnew) it is that online data belongs to k-th of mould probability of state;It is ith measurement
Coordination value of the variable under k-th of mode.
Online data coordination is carried out to the measurement data under multi-modal working condition using the embodiment of the present invention, each mode is surveyed
It measures data and coordination data standard deviation compares as shown in figure 4, the standard deviation of the coordination result under four mode is than measured value
Standard deviation is small.In Fig. 4 (a), the coordination of discharging flow, initial steam flow is dodged into six effect stock solution flows, into five effect stock solution flows, four
Standard deviation does not reduce 9.22%, 1.09%, 7.01%, 12.89% compared with measurement standard difference.Three sons of other 4 (b) -4 (d)
The harmonized stndard difference of figure does not have different degrees of reduction, illustrates that the result fluctuation after coordinating is shallower.It measures and becomes under different modalities
Amount relative standard deviation compares as shown in figure 5, the relative standard deviation of 34 measurands is respectively less than zero, illustrates the standard deviation of coordination value
The standard deviation of relative measurement is small, and coordination value is closer to actual value.The coordination result and multimode that single data harmonization model obtains
The standard deviation for the result that state data harmonization model obtains compares as shown in fig. 6, using the association for dividing modal data Coordination Model to obtain
Adjust result standard deviation smaller than the coordination result standard deviation that single global data Coordination Model obtains.Pass through level Four flash vessel reactor effluent stream
Amount and initial steam flow measured value, divide mode coordination value and single global coordination value comparing result it is found that as Figure 7-8,
Divide mode coordination value waving interval narrow compared with measured value and single global coordination value section, the association for dividing modal data Coordination Model to obtain
It adjusts as a result, explanation divides the reconciliation precision of modal data Coordination Model high.
Fig. 9 is that a kind of alumina producing evaporation process online data provided in an embodiment of the present invention coordinates system structure frame
Figure, as shown in figure 9, the system comprises data acquisition modules 1 and data acquisition module 2.Wherein:
Data acquisition module 1 is used to obtain the online data of each measurand in evaporation process, by the online data
Multi-modal individual-layer data Coordination Model is preset in input;The default multi-modal individual-layer data Coordination Model includes multiple default single modes
State individual-layer data Coordination Model, and multiple production moulds of the multiple default single mode individual-layer data Coordination Model and evaporation process
State is corresponding.Data harmonization module 2 is used to obtain the online data and belongs to multiple probability of each production mode and described online
Multiple first coordinations that data obtain after the multiple default single mode individual-layer data Coordination Model processing are as a result, according to described
Multiple probability and corresponding the multiple first are coordinated to coordinate as a result, i.e. realization pair as a result, obtaining the second of the online data
The data harmonization of online data described in evaporation process.
Specifically, in the frequency assigning apparatus of the base station in the present embodiment the effect of each module and operating process with it is above-mentioned
Method class embodiment is one-to-one, and details are not described herein.
A kind of alumina producing evaporation process online data provided in an embodiment of the present invention coordinates system, by by each measurement
Multi-modal individual-layer data Coordination Model is preset in the online data input of variable, in presetting multi-modal individual-layer data Coordination Model,
Obtain respectively multiple default single mode individual-layer data Coordination Models to the processing of online data obtain first coordinate result and
Online data belongs to each production mould probability of state, and the is obtained coordinating results and multiple corresponding Probabilistic Synthesis by multiple first
Two coordinate as a result, realizing the data slice to evaporation process online data.Method provided in an embodiment of the present invention considers steaming
Process operation is sent out in the actual conditions of multiple production mode so that data harmonization result is compared with the data harmonization mould using the single overall situation
The method of type is more accurate.
The embodiment of the present invention discloses a kind of computer program product, and the computer program product is non-transient including being stored in
Computer program on computer readable storage medium, the computer program include program instruction, when described program instructs quilt
When computer executes, computer is able to carry out the method that above-mentioned each method embodiment is provided, such as including:Obtain evaporation process
In each measurand online data, by the online data input preset multi-modal individual-layer data Coordination Model;It is described pre-
If multi-modal individual-layer data Coordination Model includes multiple default single mode individual-layer data Coordination Models, and the multiple default single mode
Multiple production mode of state individual-layer data Coordination Model and evaporation process correspond;It obtains the online data and belongs to each life
Production mould probability of state and the online data obtain more after the multiple default single mode individual-layer data Coordination Model processing
A first coordinates as a result, being coordinated according to the multiple probability and corresponding the multiple first that get as a result, obtaining described online
The second of data coordinates result.
The embodiment of the present invention provides a kind of non-transient computer readable storage medium, the non-transient computer readable storage
Medium storing computer instructs, and the computer instruction makes the computer execute the side that above-mentioned each method embodiment is provided
Method, such as including:The online data for obtaining each measurand in evaporation process, online data input is default multi-modal
Individual-layer data Coordination Model;The default multi-modal individual-layer data Coordination Model includes that multiple default single mode individual-layer datas are coordinated
Model, and multiple production mode of the multiple default single mode individual-layer data Coordination Model and evaporation process correspond;It obtains
The online data is taken to belong to each production mould probability of state and the online data through the multiple default single mode hierarchy number
Multiple first obtained after being handled according to Coordination Model are coordinated as a result, according to multiple probability for getting and corresponding the multiple the
One coordinates as a result, obtain the online data second coordinates result.
One of ordinary skill in the art will appreciate that:Realize that all or part of step of above method embodiment can pass through
The relevant hardware of program instruction is completed, and program above-mentioned can be stored in a computer read/write memory medium, the program
When being executed, step including the steps of the foregoing method embodiments is executed;And storage medium above-mentioned includes:ROM, RAM, magnetic disc or light
The various media that can store program code such as disk.
Through the above description of the embodiments, those skilled in the art can be understood that each embodiment can
It is realized by the mode of software plus required general hardware platform, naturally it is also possible to pass through hardware.Based on this understanding, on
Stating technical solution, substantially the part that contributes to existing technology can be expressed in the form of software products in other words, should
Computer software product can store in a computer-readable storage medium, such as ROM/RAM, magnetic disc, CD, including several fingers
It enables and using so that a computer equipment (can be personal computer, server or the network equipment etc.) executes each implementation
Method described in certain parts of example or embodiment.
Finally it should be noted that:The above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations;Although
Present invention has been described in detail with reference to the aforementioned embodiments, it will be understood by those of ordinary skill in the art that:It still may be used
With technical scheme described in the above embodiments is modified or equivalent replacement of some of the technical features;
And these modifications or replacements, various embodiments of the present invention technical solution that it does not separate the essence of the corresponding technical solution spirit and
Range.
Claims (10)
1. a kind of alumina producing evaporation process online data coordination approach, which is characterized in that including:
The online data is inputted and presets multi-modal individual-layer data by the online data for obtaining each measurand in evaporation process
Coordination Model;The default multi-modal individual-layer data Coordination Model includes multiple default single mode individual-layer data Coordination Models, and
Multiple production mode of the multiple default single mode individual-layer data Coordination Model and evaporation process correspond;
It obtains the online data and belongs to each production mould probability of state and the online data through the multiple default single mode
Multiple first obtained after the processing of individual-layer data Coordination Model are coordinated as a result, according to multiple probability for getting and corresponding described
Multiple first coordinate as a result, obtain the online data second coordinates result.
2. method according to claim 1, which is characterized in that the method further includes:
The first history data set of each measurand in evaporation process is obtained, and according to described in first history data set structure
Preset multi-modal individual-layer data Coordination Model.
3. method according to claim 2, which is characterized in that described described default according to first history data set structure
Multi-modal individual-layer data Coordination Model, specifically includes:
According to first history data set, evaporation process is divided into the multiple production mode;
Corresponding default single mode individual-layer data Coordination Model is built for each production mode, the multiple production mode is corresponding
The multiple single mode individual-layer data Coordination Model constitutes the multi-modal individual-layer data Coordination Model.
4. method according to claim 3, which is characterized in that it is described according to first history data set, by evaporation process
It is divided into the multiple production mode, is specifically included:
According to first history data set, evaporation process is divided into the multiple production mode using gauss hybrid models.
5. method according to claim 3, which is characterized in that the method further includes:
First history data set is divided into multiple second history data sets corresponding to each production mode;
Accordingly, described to build corresponding default single mode individual-layer data Coordination Model for each production mode, it specifically includes:
It is that corresponding production mode structure presets single mode individual-layer data Coordination Model according to each second history data set.
6. method according to claim 1, which is characterized in that the default single mode individual-layer data Coordination Model is divided into quality
Balance layer and heat balance layer;
Accordingly, obtain the online data obtained after the multiple default single mode individual-layer data Coordination Model processing it is more
A first coordinates as a result, specifically including:
The third that the online data obtains after mass balance layer processing is obtained to coordinate as a result, obtaining the third association again
Adjust the first coordination result that result obtains after heat balance layer processing.
7. method according to claim 1, which is characterized in that multiple probability that the basis is got and corresponding described more
A first coordinates as a result, obtain the online data second is coordinated as a result, specifically including:
Coordinate result by the multiple first to be weighted to obtain the second coordination result;Wherein, each first coordinates
As a result the weight in the weighted calculation is corresponding probability.
8. a kind of alumina producing evaporation process online data coordinates system, which is characterized in that the system comprises:
Data acquisition module, the online data for obtaining each measurand in evaporation process, the online data is inputted
Preset multi-modal individual-layer data Coordination Model;The default multi-modal individual-layer data Coordination Model includes multiple default single modes point
Layer data Coordination Model, and multiple production mode one of the multiple default single mode individual-layer data Coordination Model and evaporation process
One corresponds to;
Data harmonization module belongs to each production mould probability of state and the online data through institute for obtaining the online data
Multiple first coordinations obtained after multiple default single mode individual-layer data Coordination Model processing are stated as a result, multiple according to what is got
Probability and corresponding the multiple first is coordinated as a result, obtain the online data second coordinates result.
9. a kind of computer program product, which is characterized in that the computer program product includes being stored in non-transient computer
Computer program on readable storage medium storing program for executing, the computer program include program instruction, when described program is instructed by computer
When execution, the computer is made to execute method as described in any one of claim 1 to 7.
10. a kind of non-transient computer readable storage medium, which is characterized in that the non-transient computer readable storage medium is deposited
Computer instruction is stored up, the computer instruction makes the computer execute method as described in any one of claim 1 to 7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810251631.9A CN108595518A (en) | 2018-03-26 | 2018-03-26 | A kind of alumina producing evaporation process online data coordination approach and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810251631.9A CN108595518A (en) | 2018-03-26 | 2018-03-26 | A kind of alumina producing evaporation process online data coordination approach and system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108595518A true CN108595518A (en) | 2018-09-28 |
Family
ID=63623624
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810251631.9A Pending CN108595518A (en) | 2018-03-26 | 2018-03-26 | A kind of alumina producing evaporation process online data coordination approach and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108595518A (en) |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105718532A (en) * | 2016-01-15 | 2016-06-29 | 北京大学 | Cross-media sequencing method based on multi-depth network structure |
CN105913078A (en) * | 2016-04-07 | 2016-08-31 | 江南大学 | Multi-mode soft measurement method for improving adaptive affine propagation clustering |
CN106199241A (en) * | 2016-06-24 | 2016-12-07 | 清华大学 | A kind of electric power station system Multiple faults diagnosis approach based on data harmonization and hypothesis testing |
CN107451101A (en) * | 2017-07-21 | 2017-12-08 | 江南大学 | It is a kind of to be layered integrated Gaussian process recurrence soft-measuring modeling method |
-
2018
- 2018-03-26 CN CN201810251631.9A patent/CN108595518A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105718532A (en) * | 2016-01-15 | 2016-06-29 | 北京大学 | Cross-media sequencing method based on multi-depth network structure |
CN105913078A (en) * | 2016-04-07 | 2016-08-31 | 江南大学 | Multi-mode soft measurement method for improving adaptive affine propagation clustering |
CN106199241A (en) * | 2016-06-24 | 2016-12-07 | 清华大学 | A kind of electric power station system Multiple faults diagnosis approach based on data harmonization and hypothesis testing |
CN107451101A (en) * | 2017-07-21 | 2017-12-08 | 江南大学 | It is a kind of to be layered integrated Gaussian process recurrence soft-measuring modeling method |
Non-Patent Citations (2)
Title |
---|
JIE YU 等: "Multimode Process Monitoring with Bayesian Inference-Based Finite Gaussian Mixture Models", 《AICHE JOURNAL》 * |
SEN XIE 等: "Data Reconciliation Strategy with Time Registration for the Evaporation Process in Alumina Production", 《WILEY ONLINE LIBRRARY》 * |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11874650B2 (en) | Industrial internet of things system for automatic control of production line manufacturing parameters and control methods thereof | |
KR102493658B1 (en) | Methods for labeling substrates based on process parameters | |
CN108469805A (en) | A kind of distributing dynamic process monitoring method based on dynamic optimal selection | |
CN102621953B (en) | Automatic online quality monitoring and prediction model updating method for rubber hardness | |
Wang et al. | A data-centric predictive control approach for nonlinear chemical processes | |
CN108664000A (en) | A kind of alumina producing evaporation process steady state detecting method for use and system | |
CN108595518A (en) | A kind of alumina producing evaporation process online data coordination approach and system | |
CN108388218B (en) | Correction self-adaptive batch process optimization method based on latent variable process migration model | |
CN114200840B (en) | Traditional Chinese medicine pharmaceutical process operation optimization method based on distributed model predictive control | |
CN110738403A (en) | data processing method, device and computer storage medium | |
KR102499412B1 (en) | Development of industrial process predictive model based on data characteristic and prediction method of industrial process data using same | |
CN113192034B (en) | Mixed dye solution concentration detection method based on counter-propagation neural network | |
CN113191614B (en) | Polypropylene product quality real-time monitoring method based on slow characteristic regression analysis | |
CN111914214B (en) | PTA production process soft measurement method based on reduced KPLS model | |
CN115018162A (en) | Method and system for predicting machining quality in industrial finish machining process in real time | |
CN109117495B (en) | Robust data coordination method, device and storage medium in alumina production evaporation process | |
CN113239187A (en) | Monitoring method based on multi-level industrial structure knowledge block division | |
CN114548417A (en) | Machine learning model training method and system based on data correction | |
CN111896038B (en) | Semiconductor process data correction method based on correlation entropy and shallow neural network | |
Hille et al. | Run-to-Run optimization of batch processes using set-based constraints | |
CN103198178A (en) | Soft measurement modeling method for PVC (polyvinyl chloride) polymerization process | |
CN116703245B (en) | System and method for monitoring and early warning of flow production process | |
CN116467911B (en) | Multi-working-condition information fusion-based evaporation process outlet solution concentration estimation method | |
CN111854822B (en) | Semiconductor process data correction method based on correlation entropy and deep neural network | |
CN108182341B (en) | A kind of method and device of the data pattern of recognition time sequence |
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 |
Application publication date: 20180928 |
|
RJ01 | Rejection of invention patent application after publication |