CN106960100A - A kind of technological parameter inference method and its device - Google Patents
A kind of technological parameter inference method and its device Download PDFInfo
- Publication number
- CN106960100A CN106960100A CN201710192283.8A CN201710192283A CN106960100A CN 106960100 A CN106960100 A CN 106960100A CN 201710192283 A CN201710192283 A CN 201710192283A CN 106960100 A CN106960100 A CN 106960100A
- Authority
- CN
- China
- Prior art keywords
- values
- parameter
- input
- group
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/04—Inference or reasoning models
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/18—Manufacturability analysis or optimisation for manufacturability
Abstract
The invention discloses a kind of technological parameter inference method and its device, include the technological parameter of the input of reception；According to the data in the technological parameter screening parameter preset database of input, obtain the degree of closeness in parameter preset database with the technological parameter of input and be in the selection result of preset range, wherein, parameter preset database includes the multigroup technological parameter being obtained ahead of time and its corresponding treats reasoning parameter；Analyze each technological parameter according to the selection result and treat the relation between reasoning parameter, reasoning parameter is treated corresponding to the technological parameter inputted according to relation, treat that reasoning parameter is processed for follow-up foundation.The present invention can make inferences to the technological parameter of various scopes, applied widely, and amount of calculation is small, expend the time short.
Description
Technical field
The present invention relates to bent plate processing technique field, more particularly to a kind of technological parameter inference method and its device.
Background technology
Flame forming plate is that the complicated outside plate of hull that domestic and international each shipyard is generally used shapes technique.The technology is difficult
Degree is big, influence factor is more, operation skill difficulty is big, and by experienced workman, handwork is completed by rule of thumb, and efficiency is low, quality
It is unstable.
The automatic Reasoning Problems of flame forming plate technological parameter be according to bent plate process when technological parameter reasoning its need
Firing rate, so as to be processed operation (i.e. according to one parameter of multiple parameters reasoning), current method master to flame forming plate
To include finite element simulating and predicting method and BP network process Parameters Forecasting methods.Wherein, finite element modelling Forecasting Methodology passes through
The FEM model of flame forming plate is set up, firing rate is extrapolated according to analog result is counter, but the analysis process of this method is needed
Number is lost time, efficiency is low with the iterative calculation of ten thousand times, computationally intensive.BP network process Parameters Forecastings method needs to set up many
Layer BP network models, and network is trained using substantial amounts of experimental data, but this method lacks generalization ability, can only be directed to
The processing outside plate of special parameter carries out accurate Parameters Forecasting.
Therefore, how to provide a kind of widely applicable and small amount of calculation technological parameter inference method and its device is this area
The problem of technical staff needs to solve at present.
The content of the invention
It is an object of the invention to provide a kind of technological parameter inference method and its device, the technique of various scopes can be joined
Number makes inferences, applied widely, and amount of calculation is small, expends the time short.
In order to solve the above technical problems, the invention provides a kind of technological parameter inference method, including：
The technological parameter of the input of reception；
According to the data in the technological parameter screening parameter preset database of the input, the parameter preset data are obtained
Degree of closeness in storehouse with the technological parameter of the input is in the selection result of preset range, wherein, the parameter preset number
Include multigroup technological parameter for being obtained ahead of time according to storehouse and its corresponding treat reasoning parameter；
Each technological parameter is analyzed according to the selection result and the relation between reasoning parameter is treated, is obtained according to the relation
Reasoning parameter is treated to corresponding to the technological parameter of the input, treats that reasoning parameter is processed according to described in for follow-up.
Preferably, the technological parameter includes the thickness of slab Hp, the length L of flue, target receipts of the processing outside plate of flame forming plate
Contracting amount Δ B；It is described to treat reasoning parameter specially firing rate.
Preferably, the parameter preset database includes including one in the multi-group data being obtained ahead of time, data described in every group
Group Hp values, L values and Δ B values and the corresponding V values of the Hp values, L values, Δ B values；
Data in the technological parameter screening parameter preset database according to the input, obtain the parameter preset
Degree of closeness in database with the technological parameter of the input is in the selection result of preset range, according to the selection result
The relation between each technological parameter and firing rate is analyzed, is obtained according to the relation corresponding to the technological parameter of the input
The process of firing rate be specially：
The technological parameter of the input and the data in the parameter preset database are carried out into parameter to compare, it is determined that described
Or immediate N group data identical with the Hp values of input in parameter preset database；
Select L identical with the L values inputted from the N groups data or immediate N groups data, obtain N^2 group data；
Δ B values and some groups of data of Δ B identicals of input are selected to be tied as the screening from the N^2 groups data
Really, if in the absence of the Δ B identical data with the input, all regarding the N^2 groups data as the selection result；
The selection result is divided into several big group according to the difference of Hp values, by each described big group according to L values not
It is same to be divided into several groups；
According to the Δ B and V in each group, the empirical regression for drawing the Δ B and V that obtain each group is bent
On line, the empirical regression curve that each Δ B and V is obtained by curve interpolation method, the Δ B values corresponding of the input
One output quantity VBi；1≤i≤N1, N1 are group's sum；
According to the corresponding L values of the first output quantity VBi and the group of group each described, drafting obtains each described
In big group on L and VBi empirical regression curve, the empirical regression curve that each L and VBi are obtained by curve interpolation method
The corresponding second output quantity VLj of L values of the input；1≤j≤N2, N2 are big group sum；
According to big group each described of the second output quantity VLj and the big group of corresponding Hp value, drafting obtains Hp and VLj
Empirical regression curve, the Hp values of the input on the Hp and VLj empirical regression curve are obtained by curve interpolation method
Corresponding 3rd output quantity V3, the V3 are the firing rate corresponding to the technological parameter of the input.
Preferably, described parameter preset database includes 3 layers of relation database table, and each layer relation database table is two
The data form of row multiple row；The Hp values that the first row storage of first layer relation database table is obtained ahead of time, the second row deposits each Hp
It is worth the address pointer of corresponding next layer of relation database table；The L values that the first row storage is obtained ahead of time in second layer relation database table,
Second row deposits the address pointer of the corresponding next layer of relation database table of each L value；The first row is deposited in third layer relation database table
The Δ B values being obtained ahead of time are put, the second row relation database table deposits corresponding V values；
Data in the technological parameter screening parameter preset database according to the input, obtain the parameter preset
Degree of closeness in database with the technological parameter of the input is in the selection result of preset range, according to the selection result
The relation between each technological parameter and firing rate is analyzed, is obtained according to the relation corresponding to the technological parameter of the input
The process of firing rate be specially：
Since first layer relation database table, identical with the Hp values inputted or immediate N number of Hp values are obtained, and extract institute
State the address pointer of the corresponding second layer relation database table of N number of Hp values；
Whole L values that the address pointer of the second layer corresponding to the N number of Hp values is pointed to inquire about, and obtain and input
L values are identical or immediate N number of L values, and extract the address pointer of the corresponding third layer of N number of L values；
Whole Δ B values pointed by the address pointer of third layer corresponding to the N number of L values are inquired about, obtain with it is defeated
The Δ B identicals Δ B values entered and its corresponding V values, if there is no the Δ B identical Δ B values with the input, then obtain institute
State the whole Δ B values and its corresponding V values pointed by the corresponding address pointer of N number of L values；V values of acquisition and its corresponding one group
Δ B values, L values and Hp values are the selection result；
The selection result is divided into several big group according to the difference of Hp values, by each described big group according to L values not
It is same to be divided into several groups；
According to the Δ B and V in each group, the empirical regression for drawing the Δ B and V that obtain each group is bent
On line, the empirical regression curve that each Δ B and V is obtained by curve interpolation method, the Δ B values corresponding of the input
One output quantity VBi；1≤i≤N1, N1 are group's sum；
According to the corresponding L values of the first output quantity VBi and the group of group each described, drafting obtains each described
In big group on L and VBi empirical regression curve, the empirical regression curve that each L and VBi are obtained by curve interpolation method
The corresponding second output quantity VLj of L values of the input；1≤j≤N2, N2 are big group sum；
According to big group each described of the second output quantity VLj and the big group of corresponding Hp value, drafting obtains Hp and VLj
Empirical regression curve, the Hp values of the input on the Hp and VLj empirical regression curve are obtained by curve interpolation method
Corresponding 3rd output quantity V3, the V3 are the firing rate corresponding to the technological parameter of the input.
Preferably, N takes 4.
In order to solve the above technical problems, present invention also offers a kind of technological parameter reasoning device, including：
Receiver module, the technological parameter for the input of reception；
Screening module, for the data in the technological parameter screening parameter preset database according to the input, obtains institute
State the degree of closeness in parameter preset database with the technological parameter of the input and be in the selection result of preset range, wherein,
The parameter preset database includes the multigroup technological parameter being obtained ahead of time and its corresponding treats reasoning parameter；
Reasoning module, for analyzing each technological parameter according to the selection result and treating the relation between reasoning parameter,
Obtain treating reasoning parameter corresponding to the technological parameter of the input according to the relation, reasoning parameter is treated according to described in for follow-up
It is processed.
Preferably, the parameter preset database includes including one in the multi-group data being obtained ahead of time, data described in every group
Group technological parameter and it is corresponding treat reasoning parameter, the technological parameter includes the thickness of slab Hp values of the processing outside plate of flame forming plate, flame
The length L values in road, targeted shrinkage amount Δ B values, it is described to treat that reasoning parameter is firing rate V；The screening module is specifically included：
First comparing unit, for the data in the technological parameter of the input and the parameter preset database to be carried out
Parameter is compared, and determines identical with the Hp values of input in the parameter preset database or immediate N groups data；
Second comparing unit, for selecting L identical with the L values of input from the N groups data or immediate N groups number
According to obtaining N^2 group data；
3rd comparing unit, for selecting Δ B values and some groups of numbers of Δ B identicals of input from the N^2 groups data
According to as the selection result, if in the absence of the Δ B identical data with the input, the N^2 groups data are all made
For the selection result；
The reasoning module is specifically included：
Grouped element, will be each described big for the selection result to be divided into several big group according to the difference of Hp values
Group is divided into several groups according to the difference of L values；
First tracing analysis unit, for according to the Δ B and V in each group, drafting to obtain each group
Δ B and V empirical regression curve, on the empirical regression curve that each Δ B and V is obtained by curve interpolation method, institute
State the corresponding first output quantity VBi of Δ B values of input；1≤i≤N1, N1 are group's sum；
Second tracing analysis unit, for the first output quantity VBi according to group each described and group correspondence
L values, draw and obtain the empirical regression curve of L and VBi in each described big group, obtained by curve interpolation method described in each
L second output quantity VLjs corresponding with the L values of the input on VBi empirical regression curve；1≤j≤N2, N2 are big group sum；
3rd tracing analysis unit, for the second output quantity VLj according to big group each described and the big group of correspondence
Hp values, draw and obtain Hp and VLj empirical regression curve, the experience for obtaining the Hp and VLj by curve interpolation method is returned
Hp the values corresponding 3rd output quantity V3, the V3 for returning the input on curve are corresponding to the technological parameter of the input
Firing rate.
Preferably, described parameter preset database includes 3 layers of relation database table, and each layer relation database table is two
The data form of row multiple row；The Hp values that the first row storage of first layer relation database table is obtained ahead of time, the second row deposits each Hp
It is worth the address pointer of corresponding next layer of relation database table；The L values that the first row storage is obtained ahead of time in second layer relation database table,
Second row deposits the address pointer of the corresponding next layer of relation database table of each L value；The first row is deposited in third layer relation database table
The Δ B values being obtained ahead of time are put, the second row relation database table deposits corresponding V values；
The screening module is specifically included：
First comparing unit, the Hp values for since first layer relation database table, obtaining with inputting are identical or closest
N number of Hp values, and extract the address pointer of the corresponding second layer relation database table of N number of Hp values；
Second comparing unit, the whole L values progress pointed to for the address pointer to the corresponding second layer of the N number of Hp values
Inquiry, obtains or immediate N number of L value identical with the L values of input, and extracts the address of the corresponding third layer of N number of L values and refer to
Pin；
3rd comparing unit, for whole Δ B values pointed by the address pointer to the corresponding third layer of the N number of L values
Inquired about, the Δ B identicals Δ B values and its corresponding V values with inputting are obtained, if there is no the Δ B phases with the input
Same Δ B values, then obtain the whole Δ B values and its corresponding V values pointed by the corresponding address pointer of N number of L values；Obtain
V values and its corresponding one group of Δ B values, L values and Hp values are the selection result；
The reasoning module is specifically included：
Grouped element, will be each described big for the selection result to be divided into several big group according to the difference of Hp values
Group is divided into several groups according to the difference of L values；
First tracing analysis unit, according to the Δ B and V in each group, draws the Δ B for obtaining each group
With V empirical regression curve, on the empirical regression curve that each Δ B and V is obtained by curve interpolation method, the input
The corresponding first output quantity VBi of Δ B values；1≤i≤N1, N1 are group's sum；
Second tracing analysis unit, the first output quantity VBi and the corresponding L of the group according to group each described
Value, draws and obtains the empirical regression curve of L and VBi in each described big group, by curve interpolation method obtain each described L with
The corresponding second output quantity VLj of the L values of the input on VBi empirical regression curve；1≤j≤N2, N2 are big group sum；
3rd tracing analysis unit, according to big group each described of the second output quantity VLj and big group of corresponding Hp
Value, draws the empirical regression curve for obtaining Hp and VLj, and the empirical regression for obtaining the Hp and VLj by curve interpolation method is bent
Hp the values corresponding 3rd output quantity V3, the V3 of the input on line are the heating corresponding to the technological parameter of the input
Speed.
The invention provides a kind of technological parameter inference method and its device, after the technological parameter for receiving input, from default
The multigroup technological parameter being obtained ahead of time in parameter database and its corresponding technique ginseng for treating to filter out in reasoning parameter with input
The partial data that number is closer to, is then analyzed in this partial data, each technological parameter and the relation for treating reasoning parameter, Jin Ergen
According to the relation, reasoning parameter is treated corresponding to the technological parameter inputted.It can be seen that, the present invention does not limit technological parameter first
Parameter area, as long as the data in parameter preset database are enough, then the technological parameter under any scope can pass through above-mentioned side
Formula reasoning its it is corresponding treat reasoning parameter, it is applied widely；And the present invention amount of calculation depend on the selection result number with
And the type of technological parameter how much, iterations is few, and amount of calculation is small, so as to reduce the calculating time.
Brief description of the drawings
Technical scheme in order to illustrate more clearly the embodiments of the present invention, below will be to institute in prior art and embodiment
The accompanying drawing needed to use is briefly described, it should be apparent that, drawings in the following description are only some implementations of the present invention
Example, for those of ordinary skill in the art, on the premise of not paying creative work, can also be obtained according to these accompanying drawings
Obtain other accompanying drawings.
A kind of flow chart of the process for technological parameter inference method that Fig. 1 provides for the present invention；
The flow chart of the process for another technological parameter inference method that Fig. 2 provides for the present invention；
The flow chart of the process for another technological parameter inference method that Fig. 3 provides for the present invention；
Fig. 4 obtains the reasoning process schematic diagram of final firing rate for foundation the selection result in the present invention；
A kind of structural representation for technological parameter reasoning device that Fig. 5 provides for the present invention.
Embodiment
The core of the present invention is to provide a kind of technological parameter inference method and its device, and the technique of various scopes can be joined
Number makes inferences, applied widely, and amount of calculation is small, expends the time short.
To make the purpose, technical scheme and advantage of the embodiment of the present invention clearer, below in conjunction with the embodiment of the present invention
In accompanying drawing, the technical scheme in the embodiment of the present invention is clearly and completely described, it is clear that described embodiment is
A part of embodiment of the present invention, rather than whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art
The every other embodiment obtained under the premise of creative work is not made, belongs to the scope of protection of the invention.
It is shown in Figure 1 the invention provides a kind of technological parameter inference method, a kind of work that Fig. 1 provides for the present invention
The flow chart of the process of skill Parameter reasoning method；This method includes：
Step s101：The technological parameter of the input of reception；
Step s102：According to the data in the technological parameter screening parameter preset database of input, parameter preset number is obtained
The selection result of preset range is according to the degree of closeness in storehouse with the technological parameter of input, wherein, in parameter preset database
Including multigroup technological parameter for being obtained ahead of time and its corresponding treat reasoning parameter；
Data in parameter preset database are the data obtained beforehand through experiment or practical experience.
Step s103：Analyze each technological parameter according to the selection result and treat the relation between reasoning parameter, according to relation
Reasoning parameter is treated corresponding to the technological parameter inputted, treats that reasoning parameter carries out bent plate processing for follow-up foundation.
Preferably, technological parameter includes the thickness of slab Hp, the length L of flue, target receipts of the processing outside plate of flame forming plate
Contracting amount Δ B；Treat reasoning parameter specially firing rate.Certainly, above-mentioned steps of the invention can also be applied to other according to many
Individual technological parameter determines in a processing unit (plant) or scene for treating reasoning parameter that the present invention is not especially limited to this.
It is further known that, parameter preset database includes including one group of Hp in the multi-group data being obtained ahead of time, every group of data
Value, L values and Δ B values and the corresponding V values of Hp values, L values, Δ B values；
I.e. in the present embodiment, in parameter preset database in the form of data group data storage, every group of data comprising Hp,
L, the number of Δ B and V tetra-.
It is understood that, it is necessary to different V values under different Hp, L, Δ B, therefore for different groups of data, as long as its
Comprising Hp, L, have a difference in Δ B, then can obtain different V values.
It is shown in Figure 2, the flow chart of the process for another technological parameter inference method that Fig. 2 provides for the present invention；
Step s102, step s103 process is specially：
Step s201：The technological parameter of input and the data in parameter preset database are carried out into parameter to compare, it is determined that in advance
Or immediate N group data identical with the Hp values of input in setting parameter database；
Step s202：Select L identical with the L values inputted from N group data or immediate N groups data, obtain N^2 group numbers
According to；
Step s203：Δ B values and some groups of data of Δ B identicals of input are selected to be tied as screening from N^2 group data
Really, if in the absence of the Δ B identical data with input, all regarding N^2 groups data as the selection result；
Step s301：The selection result is divided into several big group according to the difference of Hp values, by each big group according to L values not
It is same to be divided into several groups；
Step s302：According to the Δ B and V in each group, the empirical regression for drawing the Δ B and V that obtain each group is bent
Line, is obtained on each Δ B and V empirical regression curve by curve interpolation method, corresponding first output quantity of Δ B values of input
VBi；1≤i≤N1, N1 are group's sum；
Wherein, the method for drawing empirical regression curve is to utilize nonlinear least square method.
Step s303：According to the corresponding L values of the first output quantity VBi of each group and group, drafting obtains each big
L and VBi empirical regression curve, obtains what is inputted on each L and VBi empirical regression curve by curve interpolation method in group
The corresponding second output quantity VLj of L values；1≤j≤N2, N2 are big group sum；
Step s304：Organize according to each big group second output quantity VLj and greatly corresponding Hp values, drafting obtain Hp with
VLj empirical regression curve, obtains Hp corresponding with the Hp values inputted on VLj empirical regression curve by curve interpolation method
3rd output quantity V3, V3 are the firing rate corresponding to the technological parameter of input.
In addition, being obtained by curve interpolation method on each Δ B and V empirical regression curve, the Δ B values of input are corresponding
It is to determine on the empirical regression curve on first output quantity VBi process nature, when Δ B is equal to the Δ B values of input,
Its corresponding V value, the V values are the first output quantity VBi.Other steps can similarly be obtained.
Wherein, in step s301, several big group can also be divided into according to the difference of L values, the difference according still further to Hp values will
Each big component is several groups；Specific that big group and group are divided according to the value of which technological parameter, the present invention does not make
It is specific to limit.Accordingly, it is to draw empirical regression song according to two variables in each group finally divided in step s302
Line, obtains the first output quantity, and the parameter of foundation is drawn experience and returned when then step s303 draws the first output quantity with dividing group
Return curve, the parameter of foundation is drawn when obtaining drawing the second output quantity in the second output quantity, final step s304 with dividing big group
Empirical regression curve, obtains final output value.
In addition, when the parameter type that technological parameter is included is 2 kinds or 4 kinds or other quantity, being carried out to the selection result
During packet, packet number of times will also be decreased or increased accordingly, and final group result needs the variable in the most group that guarantee is obtained
Only include V and a kind of parameter.For example, when technological parameter includes 4 kinds, it is assumed that the 4th kind of parameter is X, then according to the difference of L values
Also each group will be divided into several most groups according to Δ B difference, often now after each big component is several groups
Two variables included in Ge groups are X and V.Accordingly, when carrying out Drawing of Curve according to each group divided afterwards, it is also desirable to
It is carry out a stacking generation more.Certainly, the present invention do not limit the parameter type that technological parameter is included number.
In another embodiment, parameter preset database includes 3 layers of relation database table, and each layer relation database table is two rows
The data form of multiple row；The Hp values that the first row storage of first layer relation database table is obtained ahead of time, the second row deposits each Hp value
The address pointer of corresponding next layer of relation database table；The L values that the first row storage is obtained ahead of time in second layer relation database table, the
Two rows deposit the address pointer of the corresponding next layer of relation database table of each L value；The first row is deposited in third layer relation database table
The Δ B values being obtained ahead of time, the second row relation database table deposits corresponding V values；
Certainly, above numerical value puts only preferred scheme, can also be positioned over L values in first layer relation database table, respectively
The which type of technological parameter present invention is specifically placed in layer relation database table to be not especially limited.
Referring to shown in Fig. 3 and Fig. 4, Fig. 3 for the process of another technological parameter inference method of the invention provided flow
Figure.Fig. 4 obtains the reasoning process schematic diagram of final firing rate for foundation the selection result in the present invention；
Step s102, step s103 process is specially：
Step s401：Since first layer relation database table, identical with the Hp values inputted or immediate N number of Hp is obtained
Value, and extract the address pointer of the corresponding second layer relation database table of N number of Hp values；
Now, each Hp values generally correspond to multiple address pointers.
Step s402：Whole L values that the address pointer of the second layer corresponding to N number of Hp values is pointed to are inquired about, obtain and
The L values of input are identical or immediate N number of L values, and extract the address pointer of the corresponding third layer of N number of L values；
Step s403：Whole Δ B values pointed by the address pointer of third layer corresponding to N number of L values are inquired about, and are obtained
With the Δ B identicals Δ B values of input and its corresponding V values, if there is no the Δ B identical Δ B values with input, then N is obtained
Whole Δ B values and its corresponding V values pointed by the corresponding address pointer of individual L values；The V values of acquisition and its corresponding one group of Δ B
Value, L values and Hp values are the selection result；
It is understood that obtaining L values according to the corresponding address pointer of Hp values, Δ B is obtained further according to the pointer of the L values
Value, now the corresponding V values of Δ B values are the firing rate in the case that input is above-mentioned Hp values, L values and Δ B values.
Step s501：The selection result is divided into several big group according to the difference of Hp values, by each big group according to L values not
It is same to be divided into several groups；
Step s502：According to the Δ B and V in each group, the empirical regression for drawing the Δ B and V that obtain each group is bent
Line, is obtained on each Δ B and V empirical regression curve by curve interpolation method, corresponding first output quantity of Δ B values of input
VBi；1≤i≤N1, N1 are group's sum；
Step s503：According to the corresponding L values of the first output quantity VBi of each group and group, drafting obtains each big
L and VBi empirical regression curve, obtains what is inputted on each L and VBi empirical regression curve by curve interpolation method in group
The corresponding second output quantity VLj of L values；1≤j≤N2, N2 are big group sum；
Step s504：Organize according to each big group second output quantity VLj and greatly corresponding Hp values, drafting obtain Hp with
VLj empirical regression curve, obtains Hp corresponding with the Hp values inputted on VLj empirical regression curve by curve interpolation method
3rd output quantity V3, V3 are the firing rate corresponding to the technological parameter of input.
It should be noted that when the parameter type that technological parameter is included is 2 kinds or 4 kinds or other quantity, parameter preset
The number of plies of the relation database table included in database will also be decreased or increased accordingly.Also, carried out afterwards to the selection result
During packet, packet number of times will also be decreased or increased accordingly, and final group result needs the variable in the most group that guarantee is obtained
Only include V and a kind of parameter；For example, when technological parameter includes 4 kinds, it is assumed that the 4th kind of parameter is X, then according to the difference of L values
Also each group will be divided into several most groups according to Δ B difference, often now after each big component is several groups
Two variables included in Ge groups are X and V.
In addition, specifically dividing big group and group according to the value of which technological parameter, the present invention is not especially limited, point
Screening order of the order of group in screening process is determined.For example, Hp values are in first layer, are screened first during screening and meet bar
The Hp values of part, afterwards again according to Hp values screening L values, so when according to big group of Hp values division, L value divisions group；If first during screening
First screening meets the L values of condition, then divides big group, Hp value divisions group according to L values according to L values screening Hp values again afterwards.Work as work
When the parameter type included of skill parameter is increased or decreased, order of packets is determined also according to aforesaid way.
Wherein, N takes 4.It is understood that N value determine it is each in the quantity and the selection result of the selection result
Group data and the degree of closeness of the technological parameter of input, if N is excessive, after causing the step s103 obtained relations of analysis with
There is larger error between the relation of the technique factory parameter of input so that the firing rate accuracy that final reasoning is obtained is low, if N
It is too small, it can cause in the selection result that sample size is very few, also result in accuracy inadequate.Certainly, the present invention does not limit the specific of N
Value.
The invention provides a kind of technological parameter inference method, after the technological parameter for receiving input, from parameter preset data
The multigroup technological parameter and its corresponding technological parameter for treating to filter out with input in reasoning parameter being obtained ahead of time in storehouse are closer to
Partial data, then analyze in this partial data, each technological parameter and the relation for treating reasoning parameter, and then according to the pass
It is to treat reasoning parameter corresponding to the technological parameter inputted.It can be seen that, the present invention does not limit the parameter model of technological parameter first
Enclose, as long as the data in parameter preset database are enough, then the technological parameter under any scope can reasoning through the above way
Its is corresponding to treat reasoning parameter, applied widely；And the present invention amount of calculation depend on the selection result number and technique
How much is the type of parameter, and iterations is few, and amount of calculation is small, so as to reduce the calculating time.
It is shown in Figure 5 present invention also offers a kind of technological parameter reasoning device, one kind that Fig. 5 provides for the present invention
The structural representation of technological parameter reasoning device.The device includes：
Receiver module 1, the technological parameter for the input of reception；
Screening module 2, for the data in the technological parameter screening parameter preset database according to input, obtains default ginseng
The selection result of preset range is in number database with the degree of closeness of the technological parameter of input, wherein, parameter preset data
Storehouse includes the multigroup technological parameter being obtained ahead of time and its corresponding treats reasoning parameter；
Reasoning module 3, for analyzing each technological parameter according to the selection result and treating the relation between reasoning parameter, foundation
Reasoning parameter is treated corresponding to the technological parameter that relation is inputted, treats that reasoning parameter is processed for follow-up foundation.
Wherein, parameter preset database includes including one group of technological parameter in the multi-group data being obtained ahead of time, every group of data
And it is corresponding treat reasoning parameter, the technological parameter include the processing thickness of slab Hp values of outside plate of flame forming plate, the length L values of flue,
Targeted shrinkage amount Δ B values, it is firing rate V to treat reasoning parameter；Screening module 2 is specifically included：
First comparing unit, for the data in the technological parameter of input and parameter preset database to be carried out into parameter ratio
It is right, determine identical with the Hp values of input in parameter preset database or immediate N groups data；
Second comparing unit, for selecting L identical with the L values of input from N group data or immediate N groups data, is obtained
To N^2 group data；
3rd comparing unit, for selecting Δ B values and some groups of data of Δ B identicals of input to make from N^2 group data
For the selection result, if in the absence of the Δ B identical data with input, all regarding N^2 groups data as the selection result；
Reasoning module 3 is specifically included：
Grouped element, for the selection result to be divided into several big group according to the difference of Hp values, will each big group according to L values
Difference be divided into several groups；
First tracing analysis unit, for according to the Δ B and V in each group, drawing the Δ B and V for obtaining each group
Empirical regression curve, obtained by curve interpolation method on each Δ B and V empirical regression curve, the Δ B values of input correspondence
The first output quantity VBi；1≤i≤N1, N1 are group's sum；
Second tracing analysis unit, for according to the corresponding L values of the first output quantity VBi of each group and group, painting
The empirical regression curve of L and VBi in each big group is made, each L and VBi empirical regression are obtained by curve interpolation method
The corresponding second output quantity VLj of L values inputted on curve；1≤j≤N2, N2 are big group sum；
3rd tracing analysis unit, for organizing according to each big group second output quantity VLj and greatly corresponding Hp values, is painted
Hp and VLj empirical regression curve is made, obtains what is inputted on Hp and VLj empirical regression curve by curve interpolation method
Hp values corresponding 3rd output quantity V3, V3 are the firing rate corresponding to the technological parameter of input.
In another embodiment for flame forming plate, parameter preset database includes 3 layers of relation database table, each layer relation
Tables of data is the data form of two row multiple rows；The Hp values that the first row storage of first layer relation database table is obtained ahead of time, second
Row deposits the address pointer of the corresponding next layer of relation database table of each Hp value；The first row storage is pre- in second layer relation database table
The L values first obtained, the second row deposits the address pointer of the corresponding next layer of relation database table of each L value；Third layer relation data
The Δ B values that the first row storage is obtained ahead of time in table, the second row relation database table deposits corresponding V values；
Screening module 2 is specifically included：
First comparing unit, the Hp values for since first layer relation database table, obtaining with inputting are identical or closest
N number of Hp values, and extract the address pointer of the corresponding second layer relation database table of N number of Hp values；
Second comparing unit, whole L values for the address pointer sensing to the corresponding second layer of N number of Hp values are looked into
Ask, obtain identical with the L values inputted or immediate N number of L values, and extract the address pointer of the corresponding third layer of N number of L values；
3rd comparing unit, is carried out for whole Δ B values pointed by the address pointer to the corresponding third layer of N number of L values
Inquiry, obtains the Δ B identicals Δ B values and its corresponding V values with inputting, if there is no the Δ B identical Δs B with input
Value, then obtain the whole Δ B values and its corresponding V values pointed by the corresponding address pointer of N number of L values；V values of acquisition and its correspondingly
One group of Δ B value, L values and Hp values be the selection result；
Reasoning module 3 is specifically included：
Grouped element, for the selection result to be divided into several big group according to the difference of Hp values, will each big group according to L values
Difference be divided into several groups；
First tracing analysis unit, according to the Δ B and V in each group, draws the Δ B and V that obtain each group warp
Regression curve is tested, is obtained by curve interpolation method on each Δ B and V empirical regression curve, the Δ B values corresponding of input
One output quantity VBi；1≤i≤N1, N1 are group's sum；
Second tracing analysis unit, according to the corresponding L values of the first output quantity VBi of each group and group, draws
L and VBi empirical regression curve, each L and VBi empirical regression curve is obtained by curve interpolation method in each big group
The corresponding second output quantity VLj of L values of upper input；1≤j≤N2, N2 are big group sum；
3rd tracing analysis unit, organizes according to each big group second output quantity VLj and greatly corresponding Hp values, draws
To Hp and VLj empirical regression curve, the Hp values for obtaining inputting on Hp and VLj empirical regression curve by curve interpolation method
Corresponding 3rd output quantity V3, V3 are the firing rate corresponding to the technological parameter of input.
The invention provides a kind of technological parameter reasoning device, after the technological parameter for receiving input, from parameter preset data
The multigroup technological parameter and its corresponding technological parameter for treating to filter out with input in reasoning parameter being obtained ahead of time in storehouse are closer to
Partial data, then analyze in this partial data, each technological parameter and the relation for treating reasoning parameter, and then according to the pass
It is to treat reasoning parameter corresponding to the technological parameter inputted.It can be seen that, the present invention does not limit the parameter model of technological parameter first
Enclose, as long as the data in parameter preset database are enough, then the technological parameter under any scope can reasoning through the above way
Its is corresponding to treat reasoning parameter, applied widely；And the present invention amount of calculation depend on the selection result number and technique
How much is the type of parameter, and iterations is few, and amount of calculation is small, so as to reduce the calculating time.
The embodiment of each in this specification is described by the way of progressive, and what each embodiment was stressed is and other
Between the difference of embodiment, each embodiment identical similar portion mutually referring to.For device disclosed in embodiment
For, because it is corresponded to the method disclosed in Example, so description is fairly simple, related part is said referring to method part
It is bright.
It should also be noted that, in this manual, such as first and second or the like relational terms be used merely to by
One entity or operation make a distinction with another entity or operation, and not necessarily require or imply these entities or operation
Between there is any this actual relation or order.Moreover, term " comprising ", "comprising" or its any other variant meaning
Covering including for nonexcludability, so that process, method, article or equipment including a series of key elements not only include that
A little key elements, but also other key elements including being not expressly set out, or also include be this process, method, article or
The intrinsic key element of equipment.In the absence of more restrictions, the key element limited by sentence "including a ...", is not arranged
Except also there is other identical element in the process including the key element, method, article or equipment.
The foregoing description of the disclosed embodiments, enables professional and technical personnel in the field to realize or using the present invention.
A variety of modifications to these embodiments will be apparent for those skilled in the art, as defined herein
General Principle can be realized in other embodiments without departing from the spirit or scope of the present invention.Therefore, it is of the invention
The embodiments shown herein is not intended to be limited to, and is to fit to and principles disclosed herein and features of novelty phase one
The most wide scope caused.
Claims (8)
1. a kind of technological parameter inference method, it is characterised in that including：
The technological parameter of the input of reception；
According to the data in the technological parameter screening parameter preset database of the input, obtain in the parameter preset database
The selection result of preset range is in the degree of closeness of the technological parameter of the input, wherein, the parameter preset database
Include multigroup technological parameter for being obtained ahead of time and its corresponding treat reasoning parameter；
Each technological parameter is analyzed according to the selection result and the relation between reasoning parameter is treated, institute is obtained according to the relation
State and treat reasoning parameter corresponding to the technological parameter of input, treat that reasoning parameter is processed according to described in for follow-up.
2. according to the method described in claim 1, it is characterised in that the technological parameter includes the processing outside plate of flame forming plate
Thickness of slab Hp, the length L of flue, targeted shrinkage amount Δ B；It is described to treat reasoning parameter specially firing rate.
3. method according to claim 2, it is characterised in that the parameter preset database is multigroup including what is be obtained ahead of time
One group of Hp value, L values and Δ B values and the corresponding V values of the Hp values, L values, Δ B values are included in data, data described in every group；
Data in the technological parameter screening parameter preset database according to the input, obtain the parameter preset data
Degree of closeness in storehouse with the technological parameter of the input is in the selection result of preset range, according to the selection result analysis
Relation between each technological parameter and firing rate, adding corresponding to the technological parameter of the input is obtained according to the relation
The process of thermal velocity is specially：
The technological parameter of the input and the data in the parameter preset database are carried out into parameter to compare, determined described default
Or immediate N group data identical with the Hp values of input in parameter database；
Select L identical with the L values inputted from the N groups data or immediate N groups data, obtain N^2 group data；
Δ B values and some groups of data of Δ B identicals of input are selected from the N^2 groups data as the selection result, if
In the absence of the Δ B identical data with the input, then the N^2 groups data are all regard as the selection result；
The selection result is divided into several big group according to the difference of Hp values, by each big group of difference according to L values point
For several groups；
According to the Δ B and V in each group, the Δ B and V that obtain each group empirical regression curve are drawn, is led to
Cross curve interpolation method to obtain on each Δ B and V empirical regression curve, the Δ B values of the input are corresponding first defeated
Output VBi；1≤i≤N1, N1 are group's sum；
According to the corresponding L values of the first output quantity VBi and the group of group each described, drafting obtains each described big group
Interior L and VBi empirical regression curve, obtain described on each L and VBi empirical regression curve by curve interpolation method
The corresponding second output quantity VLj of L values of input；1≤j≤N2, N2 are big group sum；
According to big group each described of the second output quantity VLj and the big group of corresponding Hp value, the warp for obtaining Hp and VLj is drawn
Regression curve is tested, it is corresponding with the Hp values of the input on VLj empirical regression curve to obtain the Hp by curve interpolation method
The 3rd output quantity V3, the V3 is the firing rate corresponding to the technological parameter of the input.
4. method according to claim 3, it is characterised in that described parameter preset database includes 3 layers of relation data
Table, each layer relation database table is the data form of two row multiple rows；The first row storage of first layer relation database table is advance
The Hp values of acquisition, the second row deposits the address pointer of the corresponding next layer of relation database table of each Hp value；Second layer relation data
The L values that the first row storage is obtained ahead of time in table, the address that the second row deposits the corresponding next layer of relation database table of each L value refers to
Pin；The Δ B values that the first row storage is obtained ahead of time in third layer relation database table, the second row relation database table deposits corresponding V values；
Data in the technological parameter screening parameter preset database according to the input, obtain the parameter preset data
Degree of closeness in storehouse with the technological parameter of the input is in the selection result of preset range, according to the selection result analysis
Relation between each technological parameter and firing rate, adding corresponding to the technological parameter of the input is obtained according to the relation
The process of thermal velocity is specially：
Since first layer relation database table, identical with the Hp values inputted or immediate N number of Hp values are obtained, and extract the N
The address pointer of the corresponding second layer relation database table of individual Hp values；
Whole L values that the address pointer of the second layer corresponding to the N number of Hp values is pointed to are inquired about, and obtain the L values with inputting
Identical or immediate N number of L values, and extract the address pointer of the corresponding third layer of N number of L values；
Whole Δ B values pointed by the address pointer of third layer corresponding to the N number of L values are inquired about, and are obtained and input
Δ B identicals Δ B values and its corresponding V values, if there is no the Δ B identical Δ B values with the input, then obtain the N
Whole Δ B values and its corresponding V values pointed by the corresponding address pointer of individual L values；The V values of acquisition and its corresponding one group of Δ B
Value, L values and Hp values are the selection result；
The selection result is divided into several big group according to the difference of Hp values, by each big group of difference according to L values point
For several groups；
According to the Δ B and V in each group, the Δ B and V that obtain each group empirical regression curve are drawn, is led to
Cross curve interpolation method to obtain on each Δ B and V empirical regression curve, the Δ B values of the input are corresponding first defeated
Output VBi；1≤i≤N1, N1 are group's sum；
According to the corresponding L values of the first output quantity VBi and the group of group each described, drafting obtains each described big group
Interior L and VBi empirical regression curve, obtain described on each L and VBi empirical regression curve by curve interpolation method
The corresponding second output quantity VLj of L values of input；1≤j≤N2, N2 are big group sum；
According to big group each described of the second output quantity VLj and the big group of corresponding Hp value, the warp for obtaining Hp and VLj is drawn
Regression curve is tested, it is corresponding with the Hp values of the input on VLj empirical regression curve to obtain the Hp by curve interpolation method
The 3rd output quantity V3, the V3 is the firing rate corresponding to the technological parameter of the input.
5. the method according to claim 3 or 4, it is characterised in that N takes 4.
6. a kind of technological parameter reasoning device, it is characterised in that including：
Receiver module, the technological parameter for the input of reception；
Screening module, for the data in the technological parameter screening parameter preset database according to the input, obtains described pre-
Degree of closeness in setting parameter database with the technological parameter of the input is in the selection result of preset range, wherein, it is described
Parameter preset database includes the multigroup technological parameter being obtained ahead of time and its corresponding treats reasoning parameter；
Reasoning module, for analyzing each technological parameter according to the selection result and treating the relation between reasoning parameter, foundation
The relation obtains treating reasoning parameter corresponding to the technological parameter of the input, treats that reasoning parameter is carried out according to described in for follow-up
Processing.
7. device according to claim 6, it is characterised in that the parameter preset database is multigroup including what is be obtained ahead of time
In data, data described in every group comprising one group of technological parameter and it is corresponding treat reasoning parameter, it is curved that the technological parameter includes extreme misery
The thickness of slab Hp values of the processing outside plate of plate, the length L values of flue, targeted shrinkage amount Δ B values, it is described to treat that reasoning parameter is firing rate
V；The screening module is specifically included：
First comparing unit, for the data in the technological parameter of the input and the parameter preset database to be carried out into parameter
Compare, determine identical with the Hp values of input in the parameter preset database or immediate N groups data；
Second comparing unit, for selecting L identical with the L values of input from the N groups data or immediate N groups data, is obtained
To N^2 group data；
3rd comparing unit, for selecting Δ B values and some groups of data of Δ B identicals of input to make from the N^2 groups data
For the selection result, if in the absence of the Δ B identical data with the input, all regarding the N^2 groups data as institute
State the selection result；
The reasoning module is specifically included：
Grouped element, for the selection result to be divided into several big group according to the difference of Hp values, each described big group is pressed
Difference according to L values is divided into several groups；
First tracing analysis unit, for according to the Δ B and V in each group, drawing the Δ B for obtaining each group
With V empirical regression curve, on the empirical regression curve that each Δ B and V is obtained by curve interpolation method, the input
The corresponding first output quantity VBi of Δ B values；1≤i≤N1, N1 are group's sum；
Second tracing analysis unit, for the first output quantity VBi and the corresponding L of the group according to group each described
Value, draws and obtains the empirical regression curve of L and VBi in each described big group, by curve interpolation method obtain each described L with
The corresponding second output quantity VLj of the L values of the input on VBi empirical regression curve；1≤j≤N2, N2 are big group sum；
3rd tracing analysis unit, for the second output quantity VLj according to big group each the described and big group of corresponding Hp
Value, draws the empirical regression curve for obtaining Hp and VLj, and the empirical regression for obtaining the Hp and VLj by curve interpolation method is bent
Hp the values corresponding 3rd output quantity V3, the V3 of the input on line are the heating corresponding to the technological parameter of the input
Speed.
8. device according to claim 6, it is characterised in that described parameter preset database includes 3 layers of relation data
Table, each layer relation database table is the data form of two row multiple rows；The first row storage of first layer relation database table is advance
The Hp values of acquisition, the second row deposits the address pointer of the corresponding next layer of relation database table of each Hp value；Second layer relation data
The L values that the first row storage is obtained ahead of time in table, the address that the second row deposits the corresponding next layer of relation database table of each L value refers to
Pin；The Δ B values that the first row storage is obtained ahead of time in third layer relation database table, the second row relation database table deposits corresponding V values；
The screening module is specifically included：
First comparing unit, the Hp values for since first layer relation database table, obtaining with inputting are identical or immediate N number of
Hp values, and extract the address pointer of the corresponding second layer relation database table of N number of Hp values；
Second comparing unit, is looked into for whole L values that the address pointer to the corresponding second layer of the N number of Hp values is pointed to
Ask, obtain or immediate N number of L value identical with the L values of input, and extract the address of the corresponding third layer of N number of L values and refer to
Pin；
3rd comparing unit, is carried out for whole Δ B values pointed by the address pointer to the corresponding third layer of the N number of L values
Inquiry, obtains the Δ B identicals Δ B values and its corresponding V values with inputting, if there is no the Δ B identicals with the input
Δ B values, then obtain the whole Δ B values and its corresponding V values pointed by the corresponding address pointer of N number of L values；The V values of acquisition
And its corresponding one group of Δ B values, L values and Hp values are the selection result；
The reasoning module is specifically included：
Grouped element, for the selection result to be divided into several big group according to the difference of Hp values, each described big group is pressed
Difference according to L values is divided into several groups；
First tracing analysis unit, according to the Δ B and V in each group, draws the Δ B and V for obtaining each group
Empirical regression curve, on the empirical regression curve that each Δ B and V is obtained by curve interpolation method, the input
The corresponding first output quantity VBi of Δ B values；1≤i≤N1, N1 are group's sum；
Second tracing analysis unit, according to the corresponding L values of the first output quantity VBi and the group of group each described, is painted
The empirical regression curve of L and VBi in each described big group is made, each L and VBi are obtained by curve interpolation method
The corresponding second output quantity VLj of L values of the input on empirical regression curve；1≤j≤N2, N2 are big group sum；
3rd tracing analysis unit, according to big group each described of the second output quantity VLj and the big group of corresponding Hp value, is painted
Hp and VLj empirical regression curve is made, institute on the Hp and VLj empirical regression curve is obtained by curve interpolation method
Hp the values corresponding 3rd output quantity V3, the V3 for stating input are the firing rate corresponding to the technological parameter of the input.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710192283.8A CN106960100B (en) | 2017-03-28 | 2017-03-28 | Technological parameter reasoning method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710192283.8A CN106960100B (en) | 2017-03-28 | 2017-03-28 | Technological parameter reasoning method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106960100A true CN106960100A (en) | 2017-07-18 |
| CN106960100B CN106960100B (en) | 2021-01-26 |
Family
ID=59471523
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710192283.8A Active CN106960100B (en) | 2017-03-28 | 2017-03-28 | Technological parameter reasoning method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106960100B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102682139A (en) * | 2011-03-17 | 2012-09-19 | 齐亮 | Method for forming shell plate curve of ship body |
| KR101246065B1 (en) * | 2010-11-25 | 2013-03-26 | 삼성중공업 주식회사 | Determination system of heating shape and position for triangle heating and method thereof |
| CN104359415A (en) * | 2014-10-31 | 2015-02-18 | 广东工业大学 | Measuring method and system of angular deformation for line heating and cooling |
-
2017
- 2017-03-28 CN CN201710192283.8A patent/CN106960100B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101246065B1 (en) * | 2010-11-25 | 2013-03-26 | 삼성중공업 주식회사 | Determination system of heating shape and position for triangle heating and method thereof |
| CN102682139A (en) * | 2011-03-17 | 2012-09-19 | 齐亮 | Method for forming shell plate curve of ship body |
| CN104359415A (en) * | 2014-10-31 | 2015-02-18 | 广东工业大学 | Measuring method and system of angular deformation for line heating and cooling |
Non-Patent Citations (1)
| Title |
|---|
| 陈文雄: "《水火弯板加工参数预报系统研究》", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106960100B (en) | 2021-01-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104200087B (en) | For the parameter optimization of machine learning and the method and system of feature tuning | |
| CN104537415B (en) | A kind of non-linear process industry failure predication and recognition methodss based on compressed sensing and DROS ELM | |
| CN108920786B (en) | Section uncertainty analysis method based on Chebyshev polynomial fitting | |
| CN105786860A (en) | Data processing method and device in data modeling | |
| CN102129715A (en) | Generation method of quadrilateral grid of geometric model with any internal feature constraints | |
| CN107091911A (en) | A kind of water quality prediction of river method | |
| CN106547934B (en) | Profile control well selection method and device for conglomerate oil reservoir | |
| CN113130014B (en) | Rare earth extraction simulation method and system based on multi-branch neural network | |
| CN106875286A (en) | A kind of polymer flooding oil field overall process notes poly- parameter hierarchy optimization decision-making technique | |
| CN106327340A (en) | Method and device for detecting abnormal node set in financial network | |
| Tokarska | Neural model of the permeability features of woven fabrics | |
| CN110334406A (en) | It is a kind of consider the especially big value of wind speed the Maximum wind speed return period determine method and apparatus | |
| Goswami et al. | Comparative assessment of six automatic optimization techniques for calibration of a conceptual rainfall—runoff model | |
| CN112113146A (en) | Synchronous self-adaptive check method for roughness coefficient and node water demand of water supply pipe network pipeline | |
| CN111597753A (en) | Data depth change characteristic self-adaptive two-dimensional resistivity inversion method and system | |
| CN106292289B (en) | The mixing elite Stochastic search optimization method of process industry control loop object | |
| CN106960100A (en) | A kind of technological parameter inference method and its device | |
| CN109978017A (en) | Difficult specimen sample method and system | |
| CN109285219A (en) | A kind of grid type hydrological model grid calculation order encoding method based on DEM | |
| CN108183754A (en) | A kind of GSM base stations electromagnetic radiation Forecasting Methodology | |
| CN109209361B (en) | Method for predicting stratum parameters of fractured ultra-low permeability reservoir | |
| CN107357165A (en) | Method, fuzzy controller and the computer-readable storage medium of fuzzy control | |
| CN104731761B (en) | Gas distributing system emulation mode and device | |
| CN107220234A (en) | A kind of screening technique of electronics resume | |
| CN106767952A (en) | A kind of interference elimination method of inductive displacement transducer |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |