CN108447737B - A kind of relay base quality optimization system based on simplex search - Google Patents
A kind of relay base quality optimization system based on simplex search Download PDFInfo
- Publication number
- CN108447737B CN108447737B CN201810481182.7A CN201810481182A CN108447737B CN 108447737 B CN108447737 B CN 108447737B CN 201810481182 A CN201810481182 A CN 201810481182A CN 108447737 B CN108447737 B CN 108447737B
- Authority
- CN
- China
- Prior art keywords
- optimization
- point
- combination
- module
- simplex
- 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.)
- Active
Links
Classifications
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01H—ELECTRIC SWITCHES; RELAYS; SELECTORS; EMERGENCY PROTECTIVE DEVICES
- H01H49/00—Apparatus or processes specially adapted to the manufacture of relays or parts thereof
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
- G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
- G05B13/04—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators
- G05B13/042—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators in which a parameter or coefficient is automatically adjusted to optimise the performance
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Manufacturing & Machinery (AREA)
- General Factory Administration (AREA)
Abstract
The relay base quality optimization system based on simplex search that the present invention relates to a kind of.The system is connected with injection moulding machine by data communication interface, including detection unit and host computer.Host computer includes quality optimization initial module, simplex search optimization module, preprocessing module, post-processing module and Optimization Progress evaluation module.Quality testing is carried out to injection moulding machine relay base produced by detection unit, detected value sends host computer to by data communication interface, assessment is carried out by optimality of the host computer to this group of parameter and provides the iterative process parameter combination of next step by simplex search optimization module, which is sent to injection moulding machine by the communication interface between host computer and injection moulding machine and carries out online experiment;Above process iteration carries out, until finding reasonable optimal procedure parameters combination.Present invention is implemented as originally small, saving optimization time and experiment consumings.
Description
Technical field
The present invention relates to relay fields, more particularly to a kind of relay base quality optimization based on simplex search
System.
Background technique
Relay is a kind of Automatic Control Components important, with isolation features, can be widely applied to remote control, leads to
All conglomeraties and the fields such as news, automatic control, automobile.Important component of the relay base as relay, quality pair
It is had a major impact in the quality of relay.Therefore, relay is manufactured in link, and the quality control of relay base is answered
Pay much attention to.And relay base mostly uses plastics forming, in forming process, molding technique parameter is for relay
Pedestal quality has a significant impact.Parameter setting is proper, can effectively improve the quality of relay base.Therefore, at relay bottom
During seat is manufactured, enterprise engineering teacher or operator need to be adjusted plastics forming parameter, full to find
The optimal procedure parameters of sufficient quality requirement combine.
During traditional relay base is manufactured, enterprise engineering teacher or operator mainly pass through two ways
Look for optimal procedure parameters combination.First way is trial and error procedure, and engineer or operator rely on to technical process
Solution and personal experience, are repeatedly adjusted relevant parameter, attempt, be eventually found one group of preferably parameter combination;This optimization
Process is very time-consuming, and examination gathers and needs a large number of experiments in the process, and raw material consuming is very high, depends critically upon engineer experience, and most
The result obtained afterwards is also difficult to ensure the optimality of technological parameter.The second way is empirical formula method, in view of the effect of trial and error procedure
Rate is low, optimum results are bad, and part relay manufacturing enterprise, which changes, provides ginseng by theory analysis and calculating by industry specialists
The empirical equations of number setting, rule of thumb formula provides technological parameter by engineer or operator;This method is easy, is easy to
Implement, but empirical equation is difficult to accurately provide, the optimal procedure parameters combination predicted does not ensure that optimality;And relay
There are many models for pedestal, and with the continuous variation in market and demand, empirical equation is also required to constantly carry out with pedestal model, material etc.
It updates.The determination of parameter setting formula depends critically upon industry specialists, and cost is also very high.
Summary of the invention
The present invention is at high cost for optimizing existing for relay base quality optimization, relies on expertise, is difficult to ensure most
The problems such as dominance, proposes a kind of relay base quality optimization system based on simplex search, and its object is to realize
Under conditions of reducing quality optimization cost as far as possible, it is quickly found out the optimal procedure parameters combination of relay base forming process,
To improve the quality and production efficiency of relay base.For this purpose, the specific technical solution that the present invention uses is as follows:
A kind of relay base quality optimization system based on simplex search, wherein the relay base is quality
Change system is connected with injection moulding machine by data communication interface, including detection unit and host computer, and the host computer includes matter
Amount optimization initial module, simplex search optimization module, preprocessing module, post-processing module and Optimization Progress evaluation module;It is logical
It crosses the quality optimization initial module and gives initial technological parameter combination and relative parameters setting, optimized by the simplex search
Module is provided to be combined to experimental process parameters, passes through institute after preprocessing module pretreatment after experimental process parameters combination
It states data communication interface and is sent to the injection moulding machine and modify the setting of its technological parameter, the injection moulding machine executes molding and makees
Industry, relay base obtained carry out quality testing by the detection unit, and detected value is sent to by data communication interface
The host computer is handled this group of combination of process parameters by the post-processing module, then assesses mould by the Optimization Progress
Block assesses the optimality of current Optimization Progress, and such as being optimal property requirement, then Optimization Progress terminates and exports optimal work
Skill parameter combination;It is such as not up to optimality requirement, then provides the iterative process of next step by the simplex search optimization module
Parameter combination;The mistake that above-mentioned simplex search optimization, pretreatment, operations for forming, quality testing, post-processing and Optimization Progress are assessed
Journey iteration carries out, until finding reasonable optimal procedure parameters combination.
Further, the initial technological parameter combination is expressed asN is technique to be optimized
Number of parameters,The initial value for indicating i-th of technological parameter determines optimization problem feasible zone according to the bound of each technological parameter,
Be expressed as D=X | (Xt)L≤Xt≤(Xt)H, t=1 ..., n }, wherein (Xt)L=inf (Xt) it is lower bound, (Xt)H=sup (Xt)
For the upper bound, and combine initial technological parameter according to formulaIt is upscaled to arrive [0,100] section,
Obtain primary iteration point X0;It includes: to the simplex search that the quality optimization initial module, which is configured relevant parameter,
The parameter { α, beta, gamma, δ } of optimization module carries out assignment, and sets simplex search iteration count value s=0, and simplex building is calculated
Sub- v=1 sets the parameter of the Optimization Progress evaluation module, final state coefficient initial value κ=0, lower threshold
κF, termination factor lower threshold ξΓ, slipping smoothness coefficient lambda, sliding termination coefficient η.
In a specific embodiment, parameter { α=1, β=0.5, γ=2, δ=0.5 }, lower threshold κF=3, it terminates
Factor lower threshold ξΓ=0.1, slipping smoothness coefficient lambda=1, sliding terminates coefficient η=1.
Further, specific step is as follows for the simplex search optimization module execution simplex search optimization:
A. initialization condition determines: if current v >=n+1, goes to step C, otherwise, going to step B, executes simplex structure
It builds;
B. initial simplex constructs: being based on initial pointInitial simplex is constructed using sequential perturbation method, if the perturbation factor
For τ (τ ∈ (5,50]), then: ifK=k+1, v=v+1,Otherwise,K=k+1, v=v+1,ek=[0 ..., 1 ... 0]T, wherein i-th of element
It is 1, other are 0;
C. simplex vertex is sorted: enabling Vs+1=Vs, Fs+1=Fs, s=s+1, by simplex's
Vertex is according to its corresponding mass detected valueSize be ranked up, wherein after sequenceIndicate matter
Detection values smallest point,Indicate quality testing value maximum point,Indicate that quality testing value time is a little bigger;The optimization system
In, quality testing value is smaller, indicates quality closer to optimization aim, quality is better;
D. it reflects: according toGenerate reflective operation pointWhereinEnable k
=k+1,IfIt goes to step E and executes expansive working, ifGo to step F
Shrinkage operation is executed, in the case of other, uses VrefInstead of Vn+1, YrefInstead ofGo to step C;
E. it expands: according toGenerate expansion pointK=k+1 is enabled, If Yexp≤Yref, useInstead ofC is gone to step, is otherwise usedInstead of C is gone to step again;
F. it shrinks: according to formulaGenerate constriction pointWhenWhen,Otherwise,K=k+1 is enabled,
After contraction, compares constriction point and shrink reference pointIfWithInstead of Turn step
Otherwise rapid C goes to step G and executes operation of collapsing, if v=2;
G. it collapses: executing operation of collapsingK=k+1, v=v+1 are enabled,As v >=n+
1, go to step C;Otherwise continue step G.
Further, the preprocessing process of the preprocessing module is by iterative process parameter combination according to formulaIt is reduced to practical iterative process parameter,
WhereinFor reduction after iterative process parameter combination,Each dimensional representation and formerCorresponding actual physics parameter,
IfThe pratical and feasible point of iterative process parameter combinationOtherwise, it chooses one and meets distance in feasible zoneThe nearest point of Euclidean distanceTo replaceAnd enable the pratical and feasible point of iterative process parameter combinationWherein,For sky
Between in certain point arriveEuclidean distance, Φ is the disaggregation for meeting minimum euclidean distance.
Further, the last handling process of the post-processing module is by pratical and feasible iterative process parameter according to formulaIt is upscaled to arrive [0,100],
In, optimization section be D=X | (Xt)L≤Xt≤(Xt)H, t=1 ..., n }, (Xt)L=inf (Xt)。
Further, specific step is as follows for the Optimization Progress evaluation module execution Optimization Progress assessment:
S1. generate or update opposite optimality sequence: a batch of iterative process parameter combination sequence is M before settingk-1=
{(X1,Y1),(X2,Y2),…(Xk-1,Yk-1), wherein XiFor pratical and feasible iterative process parameter combination, YiFor the technological parameter group
Quality testing value under closing, (Xi,Yi) constitute an iterative process parameter combination information collection;New iterative process parameter combination information
Collection is (Xk,Yk), after being updated iteration point sequence, form current iteration composite sequence Mk, then each combination of process parameters believed
Size of the breath collection based on iterative process parameter combination quality testing value is resequenced, and is formed one group and is incremented by by quality testing value
SequenceWhereinFor current iteration point combination of process parameters sequence
Quality testing is worth optimal iterative process parameter combination in column, and iterative process parameter combination information collection write-in is relatively optimal
Property sequenceThe wherein newly-increased point of current optimal sequenceAs
S2. generate or update smooth track: using n+1 as the calculating basis of sliding trace, λ is that slipping smoothness coefficient (takes
Integer 1,2 ...), sliding window size is then λ (n+1).The computation rule that sliding trace is formed is as follows:
Smooth, generation sliding trace is carried out to opposite optimality sequence using the computation rule
S3. it generates or updates and terminate track: in sliding traceOn the basis of, it is further sliding
Dynamic average computation obtains terminating trackIts computation rule is as follows:
Wherein, η is that sliding terminates coefficient;
S4. it generates or updates sequence of differences and termination factor: according to termination trackIt is poor to obtain it
Value sequence Δ YT, target value growth trend of the sequence characterization at different iterative process parameter combinations, sequence of differences Δ YTProduction
Raw rule is as follows:
The termination factor ξ of Optimization Progress can be calculated based on sequence of differences and termination track:
The mathematical sense of the factor is quality of the improvement of current iteration combination of process parameters point relative to current iteration point
The ratio of objective function reflects the relative progress of Optimization Progress, and ξ is bigger, indicates at current iteration combination of process parameters point
Improvement degree it is bigger;Otherwise, it means that improvement degree at this point is smaller, the lower threshold ξ of the factorΓ, designation system
Optimization is close to stagnate;
S5. Optimization Progress terminates judgement: as ξ < ξΓWhen condition meets, κ sets 1 by 0;Then, in successive iterations batch,
When iterative process parameter combination meets ξ < ξ againΓ, κ incremental 1;And as κ ≠ 0, in case of ξ > ξΓ, indicate Optimization Progress
Dead state is jumped out, κ is set 0 again;Only when κ is equal to its lower threshold κFWhen, it is believed that Optimization Progress meets termination condition, that is, changes
It is as follows for stop criterion condition:
(ξ < ξΓ) ∩ (κ=κF)。
Further, technological parameter include injection one section of pressure, injection two sections of pressure, injection switching point, dwell pressure and
Dwell time, the quality index of relay base quality are the weight of relay base, and detection unit is poidometer.
The present invention by adopting the above technical scheme, has the beneficial effect that
1, implementation cost is small, saves the optimization time and experiment expends;
2, expertise is not depended on, is easy to implement in workshop;
3, Optimizing Process Parameters combination can efficiently be provided under minimum optimization cost.
Detailed description of the invention
Fig. 1 is system structure diagram of the invention;
Fig. 2 is the system construction drawing of the host computer in Fig. 1;
Fig. 3 is the step schematic diagram of simplex search optimization;
Fig. 4 is the schematic diagram of initial simplex construction;
Fig. 5 is the step schematic diagram of Optimization Progress assessment.
Specific embodiment
To further illustrate that each embodiment, the present invention are provided with attached drawing.These attached drawings are that the invention discloses one of content
Point, mainly to illustrate embodiment, and the associated description of specification can be cooperated to explain the operation principles of embodiment.Cooperation ginseng
These contents are examined, those of ordinary skill in the art will be understood that other possible embodiments and advantages of the present invention.In figure
Component be not necessarily to scale, and similar component symbol is conventionally used to indicate similar component.
Now in conjunction with the drawings and specific embodiments, the present invention is further described.
Fig. 1 is the structure chart of the relay base quality optimization system proposed by the invention based on simplex search, should
System is collectively constituted by detection unit 1 and host computer 2, and system and injection moulding machine 3 (relay base molding equipment) pass through number
It is connected according to communication interface.Detection unit 1 can be configured according to the quality index of relay base quality to be detected.?
In the case that quality index is the weight of relay base, detection unit 1 is poidometer (electronic balance).Injection moulding machine 3 is
The prior art is not further described herein.Data communication interface can be RS232, RS485 or RJ45 etc..Fig. 2 is institute of the present invention
The system construction drawing of the host computer 2 of proposition.Host computer 2 comprises the following modules: quality optimization initial module 21, simplex search
Optimization module 22, preprocessing module 23, post-processing module 24 and Optimization Progress evaluation module 25.Operator or engineer pass through matter
Amount optimization initial module 21 gives initial technological parameter combination and relative parameters setting, is provided by simplex search optimization module 22
It is combined to experimental process parameters, passes through data communication interface after the pretreatment of preprocessing module 23 after experimental process parameters combination
It is sent to injection moulding machine 3 and modifies the setting of its technological parameter, injection moulding machine 3 executes injection molding operation, relay obtained
Device pedestal carries out quality testing by detection unit 1, and detected value sends host computer 2 to by data communication interface, after host computer
Processing module 24 handles this group of combination of process parameters, then by Optimization Progress evaluation module 25 to current Optimization Progress most
Dominance is assessed, such as being optimal property requirement, and Optimization Progress terminates and exports optimal procedure parameters combination;It is such as not up to optimal
Property require, then provide the iterative process parameter combination of next step by simplex search optimization module 22, above process iteration carries out,
Until finding reasonable optimal procedure parameters combination.
The relay base based on simplex search is described in detail referring to Fig. 1-5 and in conjunction with a specific embodiment
The specific steps of quality optimization system execution optimization process.
Step 1: initial technological parameter combination is expressed asN is technological parameter to be optimized
Number,Indicate the initial value of i-th of technological parameter.Optimization problem feasible zone is determined according to the bound of each technological parameter, is expressed as
D=X | (Xt)L≤Xt≤(Xt)H, t=1 ..., n }, wherein (Xt)L=inf (Xt) it is lower bound, (Xt)H=sup (Xt) it is the upper bound.
In order to ensure the process variables of dimension each in optimization process have unified scale, initial technological parameter combination is pressed
[0,100] section is arrived according to formula (1) is upscaled.Operator chooses note according to forming process and relay base qualitative character
Penetrate one section of pressure, two sections of pressure of injection, injection switching point position (injecting the percentage of one section of total injection stage of Zhan), pressure maintaining pressure
The technological parameter that power and dwell time etc. have a significant impact pedestal shaped article quality is as Optimal Parameters.If X1Indicate injection
One section of pressure (unit: bar), X2Indicate injection two sections of pressure (unit: bar), X3Indicate injection switching point position (no symbol hundred
Score, %), X4Indicate dwell pressure (unit: bar), X5It indicates dwell time (unit: second, s).It is given just by operator
Beginning combination of process parameters setting value X0=[50,55,50%, 40,15]T;By operator
The lower limit value and upper limit value for rule of thumb setting each technological parameter obtain the process parameter optimizing section of considered critical, injection one
The percentage of one section of total injection stage of Zhan (is injected in section pressure, two sections of pressure of injection, two times of injection, injection switching point position
Number), dwell pressure, the upper limit value of dwell time be denoted asIt is taken in the present embodiment: Xmax
=[120,120,60%, 90,150]T, lower limit value is denoted as:It is taken in the present embodiment:
Xmin=[40,40,20%, 30,1]T;It is 100 times that largest optimization the number of iterations, which is arranged, by operator;Call host computer quality
Optimize 21 typing above- mentioned information of initialization module, and presses formula (1) for X0=[50,55,50%, 40,15]TScale turns toAfter upscaled, the process variables of each dimension have unified scale, each
Process variable is all by upscaled in [0,100] section.Assignment is carried out to the parameter { α, beta, gamma, δ } of simplex search method, is taken
{ α=1, β=0.5, γ=2, δ=0.5 }, and simplex search iteration count value s=0 is set, simplex constructs operator v=1.
Optimization Progress evaluation module parameter is set simultaneously, final state coefficient initial value κ=0, lower threshold κ are setF=3,
Termination factor lower threshold ξΓ=0.1, slipping smoothness coefficient lambda=1, sliding terminates coefficient η=1.
Step 2: simplex search optimization module 22 receives the combination of process parameters after upscaledIt is searched according to simplex
Suo Fangfa search provides iterative process parameter combination new, after testing, upscaledEnable i=i+1.Such as Fig. 3 institute
Show, specific step is as follows for simplex search optimization:
A: it executes initialization and determines.If current v >=n+1, goes to step C;Otherwise, B is gone to step, simplex structure is executed
It builds.
B: initial simplex building is carried out.With initial pointBased on, successively each technique is joined using sequential perturbation method
Number perturbs to construct initial simplex V1.If the perturbation factor is τ=10, then the technological parameter that perturbs constructs initial simplex
Criterion is as follows, as shown in Figure 4: ifThenV=v+1, k=k+1;Otherwise,V=v+1, k=k+1.ek=[0 ..., 1 ... 0]T, wherein i-th of element is 1,
He is 0.
C: simplex vertex is ranked up.Enable Vs+1=Vs, Fs+1=Fs, s=s+1.By simplexVertex according to its corresponding mass detected valueSize be ranked up.Its
In, after sequenceIndicate smallest point,Indicate maximum point,Indicate secondary a little bigger;In the optimization system, quality testing value is got over
It is small, quality is indicated closer to optimization aim, and quality is better.
D: reflective operation is carried out.According toGenerate reflective operation pointWhereinK=k+1 is enabled,IfIt goes to step E and executes expansive working;
IfIt goes to step F and executes shrinkage operation;In the case of other, V is usedrefInstead of Vn+1, YrefInstead ofGo to step C.
E: expansive working is carried out.According toGenerate expansion pointK=k+1 is enabled,If Yexp≤Yref, useInstead ofGo to step C;Otherwise it usesGeneration
It replacesC is gone to step again.
F: shrinkage operation is carried out.According to formulaGenerate constriction pointWhenWhen,Otherwise,K=k+1 is enabled,
After contraction, compares constriction point and shrink reference pointIfWithInstead ofTurn step
Rapid C;Otherwise, it goes to step G and executes operation of collapsing, if v=2.
Step G: it collapses: executing operation of collapsingK=k+1, v=v+1 are enabled,Work as v
>=n+1, goes to step C;Otherwise continue step G.
Step 3: by by simplex search optimization module 22 provide it is upscaled after iterative process parameter combinationTransmission
To preprocessing module 23.Iterative process parameter combination after upscaledReality is reduced to by formula (2) by preprocessing module
Iterative process parameter.
Wherein,For the iterative process parameter combination after reduction;Each dimensional representation and formerCorresponding reality
Physical parameter.
IfIterative process parameter combination feasible pointOtherwise, it chooses one and meets distance in feasible zoneThe nearest point of Euclidean distanceTo replaceAnd enable new iterative process parameter combination feasible pointIt chooses
The rule of approximate feasible point is as follows:
Wherein,It is arrived for certain point in spaceEuclidean distance, Φ is to meet minimum euclidean distance
Disaggregation.
Step 4: by pratical and feasible iterative process parameter combination XiIt is transferred to injection moulding machine 3 by data communication interface,
Run parameter is modified, molding production process is executed after modification, obtains relay base product.Pedestal product is put into inspection
It surveys in element 1 and measures and (select pedestal weight as quality index in the present embodiment), measured value passes through data communication interface
It is sent to host computer 2.
Step 5: passing through the input of data communication interface acquisition testing element 1 (poidometer) by post-processing module 24, and right
Practical iterative process parameter combination progress is upscaled, and each process variable arrives [0,100] section by upscaled.Upscaled rule
Then press formula (3):
Wherein, optimization section be D=X | (Xt)L≤Xt≤(Xt)H, t=1 ..., n }, (Xt)L=inf (Xt), (Xt)H=
sup(Xt)。
Step 6: combination of process parameters and its inspection of corresponding quality during 25 optimization of collection of Optimization Progress evaluation module
Measurement information, and calculate to obtain opposite optimality sequence according to historical information, and according to the track characteristic of the sequence, to Optimization Progress into
Row assessment in real time identifies section state of stagnating according to assessment result in time, and control Optimization Progress terminates in due course, output optimum process ginseng
Array is closed.As shown in figure 5, its key step is as follows:
S1. generate or update opposite optimality sequence.If preceding a batch of iterative process parameter combination sequence is Mk-1=
{(X1,Y1),(X2,Y2),…(Xk-1,Yk-1), wherein XiFor pratical and feasible iterative process parameter combination, YiFor the technological parameter group
Quality testing value under closing, (Xi,Yi) constitute an iterative process parameter combination information collection.New iterative process parameter combination information
Collection is (Xk,Yk), after being updated iteration point sequence, form current iteration composite sequence Mk.Each combination of process parameters is believed again
Size of the breath collection based on iterative process parameter combination quality testing value is resequenced, and is formed one group and is incremented by by quality testing value
SequenceWhereinFor current iteration point combination of process parameters sequence
Quality testing is worth the iterative process parameter combination of optimal (by taking minimum problem as an example) in column.And by the iterative process parameter combination
Opposite optimality sequence is written in information collectionWherein current optimal sequence is newly-increased
PointAs
S2. generate or update smooth track.Using n+1 as the calculating basis of sliding trace, λ is that slipping smoothness coefficient (takes
Integer 1,2 ...), sliding window size is then λ (n+1).The computation rule that sliding trace is formed is as follows:
Smooth, generation sliding trace is carried out to opposite optimality sequence using the computation rule
S3. it generates or updates and terminate track.In sliding traceOn the basis of, it is further sliding
Dynamic average computation must terminate trackIts computation rule is as follows:
Wherein, η is that sliding terminates coefficient.
S4. generate or update sequence of differences and termination factor.According to termination trackIt can obtain
Obtain its sequence of differences Δ YT, target value growth trend of the sequence characterization at different iterative process parameter combinations.Sequence of differences
ΔYTGeneration rule it is as follows:
The termination factor ξ of Optimization Progress can be calculated based on sequence of differences and termination track:
The mathematical sense of the factor is quality of the improvement of current iteration combination of process parameters point relative to current iteration point
The ratio of objective function reflects the relative progress of Optimization Progress.ξ is bigger, indicates at current iteration combination of process parameters point
Improvement degree it is bigger;Otherwise, it means that improvement degree at this point is smaller.The lower threshold ξ of the factorΓ, designation system
Optimization is close to stagnate.
S5. Optimization Progress terminates judgement.As ξ < ξΓWhen condition meets, κ sets 1 by 0.Then, in successive iterations batch,
When iterative process parameter combination meets ξ < ξ againΓ, κ incremental 1;And as κ ≠ 0, in case of ξ > ξΓ, indicate Optimization Progress
Dead state is jumped out, κ is set 0 again.Only when κ is equal to its lower threshold κFWhen, it is believed that Optimization Progress meets termination condition.
Stopping criteria condition is as follows:
(ξ < ξΓ) ∩ (κ=κF)
Step 7: when Optimization Progress evaluation module determines that Optimization Progress terminates, i.e. (ξ < ξΓ) (κ=3) ∩ when, export it is excellent
Change Process flowchart Status Flag ψ=1, system exports optimal procedure parameters and combines (X*,Y*), optimization system is out of service;As not yet
Meet termination condition, then optimization system go to step 2 continuation iteration execution.
In the present embodiment, after 45 iteration are tested, optimization system proposed by the invention finds optimal procedure parameters
It combines as follows: X=[108.66,112.83,0.5497,72.27,122.06]T.Injecting one section of pressure is 108.66bar,
Injecting two sections of pressure is 112.83bar, and injection switching point is 54.97%, dwell pressure 72.27bar, and the dwell time is
122.06s。
Although specifically showing and describing the present invention in conjunction with preferred embodiment, those skilled in the art should be bright
It is white, it is not departing from the spirit and scope of the present invention defined by the appended claims, it in the form and details can be right
The present invention makes a variety of changes, and is protection scope of the present invention.
Claims (7)
1. a kind of relay base quality optimization system based on simplex search, it is characterised in that: the relay base matter
Amount optimization system is connected with injection moulding machine by data communication interface, including detection unit and host computer, the host computer packet
Include quality optimization initial module, simplex search optimization module, preprocessing module, post-processing module and Optimization Progress assessment mould
Block;Initial technological parameter combination and relative parameters setting are given by the quality optimization initial module, is searched by the simplex
Rope optimization module is provided to be combined to experimental process parameters, after experimental process parameters combination after preprocessing module pretreatment
The injection moulding machine is sent to by the data communication interface and modifies the setting of its technological parameter, and the injection moulding machine executes
Operations for forming, relay base obtained carry out quality testing by the detection unit, and detected value passes through data communication interface
It sends the host computer to, the combination of process parameters is handled by the post-processing module, then is commented by the Optimization Progress
Estimate module to assess the optimality of current Optimization Progress, such as being optimal property requirement, then Optimization Progress is terminated and exported most
Excellent combination of process parameters;It is such as not up to optimality requirement, then provides the iteration of next step by the simplex search optimization module
Combination of process parameters;Above-mentioned simplex search optimization, pretreatment, operations for forming, quality testing, post-processing and Optimization Progress assessment
Process iteration carry out, until finding the combination of reasonable optimal procedure parameters;Wherein, the Optimization Progress evaluation module executes excellent
Specific step is as follows for the assessment of change process:
S1. generate or update opposite optimality sequence: a batch of iterative process parameter combination sequence is M before settingk-1={ (X1,
Y1),(X2,Y2),…(Xk-1,Yk-1), wherein XiFor pratical and feasible iterative process parameter combination, YiFor under the combination of process parameters
Quality testing value, (Xi,Yi) constitute an iterative process parameter combination information collection;Newly iterative process parameter combination information collection is
(Xk,Yk), after being updated iteration point sequence, form current iteration composite sequence Mk, then by each combination of process parameters information collection
Size based on iterative process parameter combination quality testing value is resequenced, and one group of sequence being incremented by by quality testing value is formed
ColumnWhereinFor matter in current iteration point combination of process parameters sequence
The optimal iterative process parameter combination of detection values, and opposite optimality sequence is written into the iterative process parameter combination information collectionThe wherein newly-increased point of current optimal sequenceAs
S2. generate or update smooth track: using n+1 as the calculating basis of sliding trace, λ is the (round numbers of slipping smoothness coefficient
1,2 ...), sliding window size is then λ (n+1);The computation rule that sliding trace is formed is as follows:
Smooth, generation sliding trace is carried out to opposite optimality sequence using the computation rule
S3. it generates or updates and terminate track: in sliding traceOn the basis of, further sliding is flat
It is calculated and terminates trackIts computation rule is as follows:
Wherein, η is that sliding terminates coefficient;
S4. it generates or updates sequence of differences and termination factor: according to termination trackObtain its difference sequence
Column Δ YT, target value growth trend of the sequence characterization at different iterative process parameter combinations, sequence of differences Δ YTGeneration rule
It is then as follows:
The termination factor ξ of Optimization Progress can be calculated based on sequence of differences and termination track:
The mathematical sense of the factor is quality objective of the improvement of current iteration combination of process parameters point relative to current iteration point
The ratio of function reflects the relative progress of Optimization Progress, and ξ is bigger, indicates changing at current iteration combination of process parameters point
Process degree is bigger;Otherwise, it means that improvement degree at this point is smaller, the lower threshold ξ of the factorΓ, designation system optimization
Close to stagnation;
S5. Optimization Progress terminates judgement: as ξ < ξΓWhen condition meets, κ sets 1 by 0;Then, in successive iterations batch, work as iteration
Combination of process parameters meets ξ < ξ againΓ, κ incremental 1;And as κ ≠ 0, in case of ξ > ξΓ, indicate that Optimization Progress jumps out stagnation
κ is set 0 again by state;Only when κ is equal to its lower threshold κFWhen, it is believed that Optimization Progress meets termination condition, i.e. iteration ends are quasi-
Then condition is as follows:
(ξ<ξΓ) ∩ (κ=κF)。
2. the relay base quality optimization system based on simplex search as described in claim 1, it is characterised in that: described
Initial technological parameter combination is expressed asN is technological parameter number to be optimized,It indicates i-th
The initial value of technological parameter determines optimization problem feasible zone according to the bound of each technological parameter, be expressed as D=X | (Xt)L≤Xt
≤(Xt)H, t=1 ..., n }, wherein (Xt)L=inf (Xt) it is lower bound, (Xt)H=sup (Xt) it is the upper bound, and initial process is joined
Array is closed according to formulaIt is upscaled
To [0,100] section, primary iteration point is obtainedIt includes: pair that the quality optimization initial module, which is configured relevant parameter,
The parameter { α, beta, gamma, δ } of the simplex search optimization module carries out assignment, and sets simplex search iteration count value s=
0, simplex constructs operator v=1, sets to the parameter of the Optimization Progress evaluation module, and final state coefficient initial value κ=
0, lower threshold κF, termination factor lower threshold ξΓ, slipping smoothness coefficient lambda, sliding termination coefficient η.
3. the relay base quality optimization system based on simplex search as claimed in claim 2, it is characterised in that: specific
Ground, parameter { α=1, β=0.5, γ=2, δ=0.5 }, lower threshold κF=3, termination factor lower threshold ξΓ=0.1, sliding
Smoothing factor λ=1, sliding terminate coefficient η=1.
4. the relay base quality optimization system based on simplex search as claimed in claim 2, it is characterised in that: described
Simplex search optimization module executes simplex search optimization, and specific step is as follows:
A. initialization condition determines: if current v >=n+1, goes to step C, otherwise, going to step B, executes simplex building;
B. initial simplex constructs: being based on initial pointInitial simplex is constructed using sequential perturbation method, if the perturbation factor is τ (τ
∈ (5,50]), then: ifOtherwise,ek=[0 ..., 1 ... 0]T, wherein i-th
A element is 1, other are 0;
C. simplex vertex is sorted: enabling Vs+1=Vs, Fs+1=Fs, s=s+1, by simplexVertex root
According to its corresponding mass detected valueSize be ranked up, wherein V after sequence1 sIndicate smallest point,Indicate maximum point,Indicate secondary a little bigger;In the optimization system, quality testing value is smaller, indicates quality closer to optimization
Target, quality are better;
D. it reflects: according toGenerate reflective operation pointWhereinEnable k=k+
1,If Yref<F1 s, it goes to step E and executes expansive working, ifIt goes to step F and executes receipts
Contracting operation, in the case of other, uses VrefInstead of Vn+1, YrefInstead ofGo to step C;
E. it expands: according toGenerate expansion pointK=k+1 is enabled, Such as
Fruit Yexp≤Yref, useInstead of C is gone to step, is otherwise usedInstead of It goes to step again
C;
F. it shrinks: according to formulaGenerate constriction pointWhenWhen,Otherwise,K=k+1 is enabled,
After contraction, compares constriction point and shrink reference pointIfWithInstead of It goes to step
Otherwise C goes to step G and executes operation of collapsing, if v=2;
G. it collapses: executing operation of collapsingK=k+1, v=v+1 are enabled,As v >=n+1, turn
Step C;Otherwise continue step G.
5. the relay base quality optimization system based on simplex search as claimed in claim 4, it is characterised in that: described
The preprocessing process of preprocessing module is by iterative process parameter combination according to formulaIt is reduced to practical iterative process parameter,
WhereinFor reduction after iterative process parameter combination,Each dimensional representation and formerCorresponding actual physics parameter,
IfThe pratical and feasible point of iterative process parameter combinationOtherwise, it chooses one and meets distance in feasible zone
The nearest point of Euclidean distanceTo replaceAnd enable the pratical and feasible point of iterative process parameter combinationWherein,For sky
Between in certain point arriveEuclidean distance, Φ is the disaggregation for meeting minimum euclidean distance.
6. the relay base quality optimization system based on simplex search as claimed in claim 4, it is characterised in that: described
The last handling process of post-processing module is by pratical and feasible iterative process parameter according to formulaIt is upscaled to arrive [0,100],
In, optimization section be D=X | (Xt)L≤Xt≤(Xt)H, t=1 ..., n }, (Xt)L=inf (Xt)。
7. the relay base quality optimization system based on simplex search as described in claim 1, it is characterised in that: technique
Parameter includes one section of pressure of injection, two sections of pressure of injection, injection switching point, dwell pressure and dwell time, relay base matter
The quality index of amount is the weight of relay base, and detection unit is poidometer.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810481182.7A CN108447737B (en) | 2018-05-18 | 2018-05-18 | A kind of relay base quality optimization system based on simplex search |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810481182.7A CN108447737B (en) | 2018-05-18 | 2018-05-18 | A kind of relay base quality optimization system based on simplex search |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108447737A CN108447737A (en) | 2018-08-24 |
CN108447737B true CN108447737B (en) | 2019-06-14 |
Family
ID=63204783
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810481182.7A Active CN108447737B (en) | 2018-05-18 | 2018-05-18 | A kind of relay base quality optimization system based on simplex search |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108447737B (en) |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109739193A (en) * | 2019-01-08 | 2019-05-10 | 益模(东莞)智能科技有限公司 | A kind of operating interactive method of process route |
CN116382219B (en) * | 2023-05-16 | 2023-08-11 | 苏州海卓伺服驱动技术有限公司 | Motor production process optimization method and system based on online measurement technology |
Family Cites Families (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN201166788Y (en) * | 2008-02-25 | 2008-12-17 | 华南理工大学 | System for eliminating injection products defect of an injection machine |
CN102101352B (en) * | 2010-12-22 | 2013-08-07 | 浙江大学 | Model-free weight controlling method for injection molding product |
CN102079125B (en) * | 2010-12-22 | 2013-04-17 | 浙江大学 | Model-free control method for focal distance of injection molded plastic lens |
CN102773981B (en) * | 2012-07-16 | 2014-10-29 | 南京航空航天大学 | Implementation method of energy-saving and optimizing system of injection molding machine |
CN102909844B (en) * | 2012-10-23 | 2014-06-25 | 东南大学 | Production method for injection molding machine workpiece production line |
AT513481B1 (en) * | 2012-11-09 | 2014-05-15 | Engel Austria Gmbh | Simulation device and method |
CN104772878A (en) * | 2015-02-15 | 2015-07-15 | 浙江大学 | Product weight control method based on iteration modeling and optimization for injection molding process |
CN107718479A (en) * | 2017-11-15 | 2018-02-23 | 广汉市盛泰塑化科技有限公司 | Engineering plastics Injection Molding Processing Optimization system and optimization method |
-
2018
- 2018-05-18 CN CN201810481182.7A patent/CN108447737B/en active Active
Also Published As
Publication number | Publication date |
---|---|
CN108447737A (en) | 2018-08-24 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11403535B2 (en) | Model-based machine learning system | |
CN103927412B (en) | Instant learning debutanizing tower soft-measuring modeling method based on gauss hybrid models | |
CN106444428A (en) | Process simulation software based atmospheric and vacuum distillation unit optimization operation system and method | |
CN111652402B (en) | Intelligent optimization method for big data of optical fiber preform deposition process | |
WO2021036546A1 (en) | Near-infrared quantitative analysis model construction method based on biased estimation | |
CN108447737B (en) | A kind of relay base quality optimization system based on simplex search | |
CN111638707B (en) | Intermittent process fault monitoring method based on SOM clustering and MPCA | |
CN110263488B (en) | Industrial rubber compound Mooney viscosity soft measurement method based on integrated instant learning | |
CN107403196B (en) | Method for predicting concentration of butane at bottom of debutanizer by instant learning modeling based on spectral clustering analysis | |
CN113780420B (en) | GRU-GCN-based method for predicting concentration of dissolved gas in transformer oil | |
CN106094786A (en) | Industrial process flexible measurement method based on integrated-type independent entry regression model | |
CN106156434A (en) | Sliding window time difference Gaussian process regression modeling method based on the low and deep structure of local time | |
CN114239400A (en) | Multi-working-condition process self-adaptive soft measurement modeling method based on local double-weighted probability hidden variable regression model | |
CN102621953B (en) | Automatic online quality monitoring and prediction model updating method for rubber hardness | |
CN104772878A (en) | Product weight control method based on iteration modeling and optimization for injection molding process | |
CN104749954B (en) | Intelligent ash bin control system device based on IMC (Internal Model Control) strategy and control method | |
CN110378035A (en) | Hydrocracking soft measurement modeling method based on deep learning | |
CN108710289A (en) | A method of the relay base quality optimization based on modified SPSA | |
CN106569982A (en) | GPR online soft measurement method and system with singular point detection compensation function | |
CN110674883A (en) | Active learning method based on k nearest neighbor and probability selection | |
CN103439964B (en) | A kind of online updating system and method for OCSVM monitoring model | |
CN114186771B (en) | Mixed regularized random configuration network industrial process operation index estimation method | |
CN108345726A (en) | Input variable automatic selecting method based on mutual information and soft instrument error | |
CN114692986A (en) | Coking artificial intelligence coal blending system based on neural network model | |
Mun et al. | Design and analysis of optimal recipe prediction model based on deep learning for advanced composite material injection molding |
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 |