CN103064370A - Cooperating production method of multiple coaxial-cable shield machines - Google Patents

Cooperating production method of multiple coaxial-cable shield machines Download PDF

Info

Publication number
CN103064370A
CN103064370A CN2012105472832A CN201210547283A CN103064370A CN 103064370 A CN103064370 A CN 103064370A CN 2012105472832 A CN2012105472832 A CN 2012105472832A CN 201210547283 A CN201210547283 A CN 201210547283A CN 103064370 A CN103064370 A CN 103064370A
Authority
CN
China
Prior art keywords
production
coaxial cable
machine
cable sheathing
sheathing machine
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
Application number
CN2012105472832A
Other languages
Chinese (zh)
Other versions
CN103064370B (en
Inventor
王春林
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
HANGZHOU FUTONG ELECTRIC WIRE & CABLE CO., LTD.
Original Assignee
Futong Group Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Futong Group Co Ltd filed Critical Futong Group Co Ltd
Priority to CN201210547283.2A priority Critical patent/CN103064370B/en
Publication of CN103064370A publication Critical patent/CN103064370A/en
Application granted granted Critical
Publication of CN103064370B publication Critical patent/CN103064370B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]

Abstract

The invention relates to a cooperating production method of multiple coaxial-cable shield machines. At present actual production mainly depends on the experience of working staff. The cooperating production method of the multiple coaxial-cable shield machines collects production operation parameters and production quality indexes of each coaxial-cable shield machine under all producing material situations aiming to the producing units of the coaxial-cable shield machines, and sets up a database. Then modeling is carried out to each coaxial-cable shield machine by using multi-output support vector machine method, the models of the production quality and the production operation parameters of each coaxial-cable shield machine under each producing material are respectively set up, then each model of different producing material is combined into an integrated model of a single shield machine, and the integrated model of the single shield machine is mutually set up. Optimizations of productive tasks are carried out by using a particle swarm optimization algorithm. The cooperating production method of the multiple coaxial-cable shield machines uses a data mining technique and a parallel optimization algorithm to set up feature model, and carries out optimization to productive tasks of each model by combining optimizing algorithm, and achieves the purpose of producing by the optimal coaxial-cable shield machine under optimal productive task.

Description

A kind of many coaxial cable sheathing machines are worked in coordination with production method
Technical field
The invention belongs to the information and control technical field, relate to the collaborative production method of a kind of many coaxial cable sheathing machines.
Background technology
The delivery rate of coaxial cable sheathing machine, heart yearn speed, the production operations such as the temperature in process ginsengs has direct impact to production efficiency and the quality of concentric cable sheath.Each sheath machine (even model is identical) has its unique characteristic when producing, namely have different production operation parameters and the relation between production efficiency and quality.For total number of units be
Figure 2012105472832100002DEST_PATH_IMAGE002
(
Figure 2012105472832100002DEST_PATH_IMAGE004
) in the situation of platform, exist and how to dispose each sheath machine alternate and produce optimum problem, also be how under given production material and demand, the problem of finishing production task of full blast how.
Yet, obtain comparatively accurately the production operation parameter of every sheath machine and the relation between production efficiency and quality, and under certain production requirement, for every sheath machine prepares the production operation parameter, carrying out the distribution of total production task, is not an easy thing.At present, also there is not good solution.
Mainly be by staff's experience in the actual production, its target is also just kept production and is normally carried out, the concept of not distributing rationally, but so its integral production process also have very large room for promotion.
By data mining, the method for applied for machines study is excavated the relational model between each sheath machine production operation parameter and production efficiency and quality, again in conjunction with optimized algorithm to production task distribution to be optimized be very potential method.The method really being reached produce actual requirement, is the key of this technology, and main bugbear comprises how to improve prediction and the generalization ability of model, how to realize that the optimization of Prescribed Properties distributes.
Summary of the invention
Target of the present invention is to produce simultaneously for many coaxial cable sheathing machines to finish production task, proposes a kind of production task distribution method of optimization, and optimize the content has been taken into account efficient and product quality situation that each coaxial cable sheathing machine is produced.
The inventive method is by each coaxial cable sheathing machine production efficiency and product quality and with it corresponding production operation supplemental characteristic collection, production operation parameter and product quality to every coaxial cable sheathing machine, set up the model of based on data digging technology, and the means such as optimized algorithm of integrating parallel, established a kind of method of many coaxial cable sheathing machine production optimizations distribution production task, utilize the method can be effectively in total certain situation of production task, by optimizing the production task of distributing each sheath machine, enhance productivity and product quality.
Concrete steps of the present invention are:
Step (1). for the total number of units of coaxial cable sheathing machine be
Figure 693386DEST_PATH_IMAGE002
(
Figure 423576DEST_PATH_IMAGE004
) production unit of platform, gather respectively all and produce in material situations, each coaxial cable sheathing machine production operation parameter and the relevant sign concentric cable sheath production index of quality, building database; Coaxial cable sheathing machine production operation parameter is obtained by coaxial cable sheathing machine operation digital control system, or directly by the apparatus measures collection, different sheaths is produced material and separated image data, so that targetedly respectively modeling;
The data of described coaxial cable sheathing machine production operation parameter comprise: the production material of concentric cable sheath, delivery rate
Figure 2012105472832100002DEST_PATH_IMAGE006
, heart yearn passes sheath machine speed
Figure 2012105472832100002DEST_PATH_IMAGE008
, the production temperature
Figure 2012105472832100002DEST_PATH_IMAGE010
The data of the described sign concentric cable sheath production index of quality comprise: the anti-aging index of sheath
Figure 2012105472832100002DEST_PATH_IMAGE012
, unit length average bubble quantity
Figure 2012105472832100002DEST_PATH_IMAGE014
With the abrasion resistance index
Figure 2012105472832100002DEST_PATH_IMAGE016
, the method for its acquisition is mature technology;
Step (2). every coaxial cable sheathing machine is adopted the modeling of many output support vector machine methods, setting up respectively every kind of sheath produces under the material, model between the product quality of each coaxial cable sheathing machine and each production operation parameter, then every sheath is produced the difference of machine and produced the block mold that material model is combined as a separate unit sheath production machine, it is vertical to build together
Figure 452581DEST_PATH_IMAGE002
Individual separate unit sheath is produced the block mold of machine
Figure 2012105472832100002DEST_PATH_IMAGE018
Concrete modeling method is as follows:
The input parameter and the output parameter that are used for modeling sample are expressed as , wherein
Figure 2012105472832100002DEST_PATH_IMAGE022
Expression the
Figure 2012105472832100002DEST_PATH_IMAGE024
Group is as the coaxial cable sheathing machine production operation parameter of input data vector,
Figure 2012105472832100002DEST_PATH_IMAGE026
Expression the
Figure 97058DEST_PATH_IMAGE024
Group is as the index of the concentric cable sheath production quality of output parameter vector,
Figure 2012105472832100002DEST_PATH_IMAGE028
Be sample size; Take actual operating data as the basis, set up the product quality of each coaxial cable sheathing machine and the block mold that the separate unit sheath between each production operation parameter is produced machine;
Adopt the support vector machine method modeling, the support vector machine kernel function is elected radial basis function as
Figure 2012105472832100002DEST_PATH_IMAGE030
Parameter σ be radial basis function width, Be mapping function, establish required objective function and be:
Figure 2012105472832100002DEST_PATH_IMAGE034
, Be the vector value of model output,
Figure 2012105472832100002DEST_PATH_IMAGE038
Be the weight coefficient vector,
Figure 2012105472832100002DEST_PATH_IMAGE040
Be the intercept vector.Introduce relaxation factor ξ * i〉=0 and ξ i〉=0 and allow error of fitting ε, model passes through constraint condition
Figure 2012105472832100002DEST_PATH_IMAGE044
, minimize
Figure 2012105472832100002DEST_PATH_IMAGE046
Obtain;
Constant wherein C0 be penalty coefficient,
Figure 2012105472832100002DEST_PATH_IMAGE048
For prediction exceeds the quantity that allows error of fitting point,
Figure 2012105472832100002DEST_PATH_IMAGE050
This minimization problem is a convex quadratic programming problem, introduces Lagrangian function:
Figure 2012105472832100002DEST_PATH_IMAGE052
Wherein:
Figure 2012105472832100002DEST_PATH_IMAGE054
〉=0,
Figure 2012105472832100002DEST_PATH_IMAGE056
〉=0, be Lagrange's multiplier;
At the saddle point place, function L is about w, b, ξ i, ξ i *Minimal point, also be
Figure 2012105472832100002DEST_PATH_IMAGE058
Maximal point, minimization problem are converted into the maximization problems of asking its dual problem;
LagrangianL is about w at the saddle point place, b, ξ i, ξ i *Minimal point:
Figure 2012105472832100002DEST_PATH_IMAGE060
Can get the dual function of Lagrangian function:
Figure 2012105472832100002DEST_PATH_IMAGE062
At this moment,
Figure 2012105472832100002DEST_PATH_IMAGE066
According to Ku En-Plutarch (KKT) conditional theorem, have following formula to set up at saddle point:
Figure 2012105472832100002DEST_PATH_IMAGE068
Figure 2012105472832100002DEST_PATH_IMAGE070
By following formula as seen, α i α i * =0, α i With α i * Can not be non-zero simultaneously, can get:
Figure 2012105472832100002DEST_PATH_IMAGE072
Figure 101310DEST_PATH_IMAGE044
Can obtain vectorial b from following formula, obtain model;
Step (3). utilize particle swarm optimization algorithm, the product quality of integrating step (2) each coaxial cable sheathing machine of building and the separate unit sheath between each production operation parameter are produced the block mold of machine
Figure 736822DEST_PATH_IMAGE018
, carry out the optimization of each production task, concrete steps are as follows:
A. define the particle cluster algorithm initial population
Figure 2012105472832100002DEST_PATH_IMAGE074
Vector respectively tie up component, be respectively production operation parameter and the sheath production material category of each coaxial cable sheathing machine;
B. set search target and the iterations of particle cluster algorithm, the search target is the target setting of each coaxial cable sheathing machine production quality, this target setting can be the integration objective of production quality, it also can be single production QT Quality Target, also can be that multiple goal is optimized simultaneously, be determined by needs of production;
C. to produce the length need finish the concentric cable sheath be total unit interval production task the unit interval
Figure 2012105472832100002DEST_PATH_IMAGE076
, the production task sum of the highest unit interval of permission of each coaxial cable sheathing machine is the highest unit interval production task of permission of each coaxial cable sheathing machine
Figure 2012105472832100002DEST_PATH_IMAGE078
, ,
Figure 2012105472832100002DEST_PATH_IMAGE082
Be
Figure 247263DEST_PATH_IMAGE024
The highest unit interval production task of the permission of platform coaxial cable sheathing machine, when The time, establish
Figure 2012105472832100002DEST_PATH_IMAGE086
Be total unit interval production task of each coaxial cable sheathing machine that initialization is good,
Figure 2012105472832100002DEST_PATH_IMAGE088
, wherein
Figure 2012105472832100002DEST_PATH_IMAGE090
,
Figure 2012105472832100002DEST_PATH_IMAGE092
Be the initialization unit interval production task of each coaxial cable sheathing machine that initialization is good, when
Figure 2012105472832100002DEST_PATH_IMAGE094
The time,
Figure 2012105472832100002DEST_PATH_IMAGE096
,
Figure 2012105472832100002DEST_PATH_IMAGE098
Be The initialization production task of platform coaxial cable sheathing machine, the
Figure 131649DEST_PATH_IMAGE100
Each coaxial cable sheathing machine after the platform coaxial cable sheathing machine (
Figure 2012105472832100002DEST_PATH_IMAGE102
) production task is 0, otherwise Platform coaxial cable sheathing machine production task initialization interval is:
Figure 2012105472832100002DEST_PATH_IMAGE104
, produce initial the in this interval The production task of platform coaxial cable sheathing machine is individual;
According to above step initialization colony vector Wherein heart yearn speed is determined by the production task of distributing, situation or explained hereafter requirements set that other production operation parameters are produced machine according to actual concentric cable sheath, integrating step (2) model between each coaxial cable sheathing machine product quality and production operation parameter of building
Figure 347550DEST_PATH_IMAGE018
According to the production task of each coaxial cable sheathing machine in the initial population, obtain the optimization aim initial value of each coaxial cable sheathing machine under the initial population production task, then according to the search target of setting, carry out iterative computation with particle cluster algorithm, search Optimal Production task distribution condition;
D. when particle cluster algorithm is finished iterations or find set to require optimum, stop to calculate the colony's vector that obtains corresponding optimum, the production task that namely obtains each optimum coaxial cable sheathing machine is distributed.
The inventive method is for improving total production efficiency, and the quality that improves output aggregate is useful, but also has certain difficulty.To the distribution of each coaxial cable sheathing machine production task, according to personal experience or simple mean allocation, the production efficiency in this load distribution situation has much room for improvement fully in the production run of present reality.The inventive method specifically for the total number of units of coaxial cable sheathing machine is
Figure 933252DEST_PATH_IMAGE002
(
Figure 680540DEST_PATH_IMAGE004
) production unit of platform, gather respectively in each coaxial cable sheathing machine production run, product quality reaches corresponding with it production operation supplemental characteristic, utilize data mining technology and parallel optimization algorithm, product quality and production operation parametric relationship for every coaxial cable sheathing machine, set up characteristic model, in conjunction with the production task allocation optimized of optimizing algorithm to each coaxial cable sheathing machine, the target of under the production task of optimum, producing to reach optimum coaxial cable sheathing machine.
The inventive method both can on-line optimization also can offline optimization.
Embodiment
A kind of many coaxial cable sheathing machines are worked in coordination with production method, specifically may further comprise the steps:
(1) for the total number of units of coaxial cable sheathing machine is
Figure 984483DEST_PATH_IMAGE002
(
Figure 72656DEST_PATH_IMAGE004
) production unit of platform, gather respectively all and produce in material situations, in each coaxial cable sheathing machine production run, product quality and corresponding production operation parameter with it, building database; Concrete coaxial cable sheathing machine production operation parameter is obtained by coaxial cable sheathing machine operation digital control system, or directly by the apparatus measures collection, different sheaths is produced material will separate image data, so that targetedly respectively modeling.
Described coaxial cable sheathing machine production operation supplemental characteristic comprises: the production material of concentric cable sheath, delivery rate
Figure 716127DEST_PATH_IMAGE006
, heart yearn passes sheath machine speed
Figure 113610DEST_PATH_IMAGE008
, the production temperature
Figure 154116DEST_PATH_IMAGE010
The data of the index of described sign concentric cable sheath production quality comprise: the anti-aging index of sheath
Figure 295247DEST_PATH_IMAGE012
, unit length average bubble quantity
Figure 606274DEST_PATH_IMAGE014
With the abrasion resistance index
Figure 377921DEST_PATH_IMAGE016
, the method for its acquisition is mature technology;
(2) respectively every coaxial cable sheathing machine is adopted the modeling of many output support vector machine methods, setting up respectively every kind of sheath produces under the material, model between the product quality of each coaxial cable sheathing machine and each production operation parameter, then every sheath is produced the difference of machine and produced the block mold that material model is combined as a separate unit sheath production machine, it is vertical to build together
Figure 390876DEST_PATH_IMAGE002
Individual separate unit sheath is produced the block mold of machine Concrete modeling method is as follows:
The input parameter and the output parameter that are used for modeling sample are expressed as
Figure 999767DEST_PATH_IMAGE020
, wherein Expression the
Figure 193299DEST_PATH_IMAGE024
Group is as the coaxial cable sheathing machine production operation parameter of input data vector,
Figure 676233DEST_PATH_IMAGE026
Expression the
Figure 460387DEST_PATH_IMAGE024
Group is as the index of the concentric cable sheath production quality of output parameter vector, Be sample size, take actual operating data as the basis, set up the product quality of each coaxial cable sheathing machine and the block mold that the separate unit sheath between each production operation parameter is produced machine.
Adopt the support vector machine method modeling, the support vector machine kernel function is elected radial basis function as
Figure 561384DEST_PATH_IMAGE030
Parameter " σ " is the width of radial basis function,
Figure 785692DEST_PATH_IMAGE032
Be mapping function, establish required objective function and be:
Figure 660238DEST_PATH_IMAGE034
,
Figure 6906DEST_PATH_IMAGE036
Be the vector value of model output,
Figure 419433DEST_PATH_IMAGE038
Be the weight coefficient vector,
Figure 447432DEST_PATH_IMAGE040
Be the intercept vector.Introduce relaxation factor ξ * i〉=0 and ξ i〉=0 and allow error of fitting ε, model passes through constraint condition
Figure 958177DEST_PATH_IMAGE042
Figure 210167DEST_PATH_IMAGE044
, minimize
Figure 109990DEST_PATH_IMAGE046
Obtain;
Constant wherein C0 be penalty coefficient,
Figure 489150DEST_PATH_IMAGE048
Exceed the quantity that allows error of fitting point for prediction
Figure DEST_PATH_IMAGE106
Figure 853135DEST_PATH_IMAGE050
This minimization problem is a convex quadratic programming problem, introduces Lagrangian function:
Figure 213709DEST_PATH_IMAGE052
Wherein:
Figure 912412DEST_PATH_IMAGE054
〉=0,
Figure 282214DEST_PATH_IMAGE056
〉=0, be Lagrange's multiplier.
At the saddle point place, function L is about w, b, ξ i, ξ i *Minimal point, also be
Figure 235126DEST_PATH_IMAGE058
Maximal point, minimization problem are converted into the maximization problems of asking its dual problem.
LagrangianL is about w at the saddle point place, b, ξ i, ξ i *Minimal point:
Can get the dual function of Lagrangian function:
Figure 454066DEST_PATH_IMAGE062
At this moment,
Figure 689876DEST_PATH_IMAGE064
Figure 700557DEST_PATH_IMAGE066
According to Ku En-Plutarch (KKT) conditional theorem, have following formula to set up at saddle point:
Figure 76229DEST_PATH_IMAGE070
By following formula as seen, α i α i * =0, α i With α i * Can not be non-zero simultaneously, can get:
Figure 850150DEST_PATH_IMAGE072
Figure 528387DEST_PATH_IMAGE044
Can obtain vectorial b from following formula, obtain model.
(3) utilize particle swarm optimization algorithm, in conjunction with the product quality of above step (2) each coaxial cable sheathing machine of building and the block mold of the production of the separate unit sheath between each production operation parameter machine
Figure 667245DEST_PATH_IMAGE018
, carry out the optimization of each production task, concrete steps are as follows:
A. define the particle cluster algorithm initial population
Figure 250673DEST_PATH_IMAGE074
Vector respectively tie up component, be respectively production operation parameter and the sheath production material category of each coaxial cable sheathing machine;
B. set search target and the iterations of particle cluster algorithm, the search target is the target setting of each coaxial cable sheathing machine production quality, this target setting can be the integration objective of production quality, it also can be single production QT Quality Target, also can be that multiple goal is optimized simultaneously, be determined by needs of production;
C. according to total unit interval production task
Figure 562706DEST_PATH_IMAGE076
, namely the unit interval is produced the length that need finish the concentric cable sheath, and the highest unit interval production task of the permission of each coaxial cable sheathing machine
Figure 859564DEST_PATH_IMAGE078
, the production task sum of the highest unit interval of permission of each coaxial cable sheathing machine,
Figure 231639DEST_PATH_IMAGE080
,
Figure 302363DEST_PATH_IMAGE082
Be
Figure 168819DEST_PATH_IMAGE024
The highest unit interval production task of the permission of platform coaxial cable sheathing machine is set the Search Range of each coaxial cable sheathing machine unit interval production task, if
Figure DEST_PATH_IMAGE108
Then for the production task that need finish greater than allowing the highest production task, this production task can't be finished in the existing equipment situation.If
Figure DEST_PATH_IMAGE110
Then for the production task that need finish equals to allow the highest production task, this production task also can't be optimized, and each concentric cable machine is operated in the highest permission production task situation gets final product.Patent of the present invention is only right
Figure 70916DEST_PATH_IMAGE084
Situation applicable, establish Be total unit interval production task of each coaxial cable sheathing machine that initialization is good,
Figure 161461DEST_PATH_IMAGE088
, wherein
Figure 80875DEST_PATH_IMAGE090
,
Figure 775162DEST_PATH_IMAGE092
Be the initialization unit interval production task of each coaxial cable sheathing machine that initialization is good, when
Figure 239772DEST_PATH_IMAGE094
The time,
Figure 347406DEST_PATH_IMAGE096
,
Figure 742615DEST_PATH_IMAGE098
Be
Figure 602992DEST_PATH_IMAGE100
The initialization production task of platform coaxial cable sheathing machine, the
Figure 691034DEST_PATH_IMAGE100
Each coaxial cable sheathing machine after the platform coaxial cable sheathing machine (
Figure 20384DEST_PATH_IMAGE102
) production task is 0, otherwise
Figure 219285DEST_PATH_IMAGE024
Platform coaxial cable sheathing machine production task initialization interval is:
Figure 435633DEST_PATH_IMAGE104
, produce initial the in this interval
Figure 694576DEST_PATH_IMAGE100
The production task of platform coaxial cable sheathing machine is individual.According to above step initialization colony vector Wherein heart yearn speed is determined by the production task of distributing, situation or explained hereafter requirements set that other production operation parameters are produced machine according to actual concentric cable sheath, integrating step (2) model between each coaxial cable sheathing machine product quality and production operation parameter of building
Figure 248235DEST_PATH_IMAGE018
According to the production task of each coaxial cable sheathing machine in the initial population, obtain the optimization aim initial value of each coaxial cable sheathing machine under the initial population production task, the search target of then setting according to previous step, carry out iterative computation with particle cluster algorithm, search Optimal Production task distribution condition;
D. when particle cluster algorithm is finished iterations or find set to require optimum, stop to calculate the colony's vector that obtains corresponding optimum, the production task that namely obtains each optimum coaxial cable sheathing machine is distributed.

Claims (1)

1. coaxial cable sheathing machine more than a kind is worked in coordination with production method, it is characterized in that the concrete steps of the method are:
Step (1). for the total number of units of coaxial cable sheathing machine be
Figure 2012105472832100001DEST_PATH_IMAGE002
( ) production unit of platform, gather respectively all and produce in material situations, each coaxial cable sheathing machine production operation parameter and the relevant sign concentric cable sheath production index of quality, building database; Coaxial cable sheathing machine production operation parameter is obtained by coaxial cable sheathing machine operation digital control system, or directly by the apparatus measures collection, different sheaths is produced material and separated image data, so that targetedly respectively modeling;
The data of described coaxial cable sheathing machine production operation parameter comprise: the production material of concentric cable sheath, delivery rate
Figure DEST_PATH_IMAGE006
, heart yearn passes sheath machine speed
Figure DEST_PATH_IMAGE008
, the production temperature
Figure DEST_PATH_IMAGE010
The data of the described sign concentric cable sheath production index of quality comprise: the anti-aging index of sheath
Figure DEST_PATH_IMAGE012
, unit length average bubble quantity
Figure DEST_PATH_IMAGE014
With the abrasion resistance index
Step (2). every coaxial cable sheathing machine is adopted the modeling of many output support vector machine methods, setting up respectively every kind of sheath produces under the material, model between the product quality of each coaxial cable sheathing machine and each production operation parameter, then every sheath is produced the difference of machine and produced the block mold that material model is combined as a separate unit sheath production machine, it is vertical to build together
Figure 699293DEST_PATH_IMAGE002
Individual separate unit sheath is produced the block mold of machine
Figure DEST_PATH_IMAGE018
Concrete modeling method is as follows:
The input parameter and the output parameter that are used for modeling sample are expressed as
Figure DEST_PATH_IMAGE020
, wherein
Figure DEST_PATH_IMAGE022
Expression the
Figure DEST_PATH_IMAGE024
Group is as the coaxial cable sheathing machine production operation parameter of input data vector, Expression the
Figure 378405DEST_PATH_IMAGE024
Group is as the index of the concentric cable sheath production quality of output parameter vector,
Figure DEST_PATH_IMAGE028
Be sample size; Take actual operating data as the basis, set up the product quality of each coaxial cable sheathing machine and the block mold that the separate unit sheath between each production operation parameter is produced machine;
Adopt the support vector machine method modeling, the support vector machine kernel function is elected radial basis function as
Parameter σ be radial basis function width,
Figure DEST_PATH_IMAGE032
Be mapping function, establish required objective function and be:
Figure DEST_PATH_IMAGE034
,
Figure DEST_PATH_IMAGE036
Be the vector value of model output,
Figure DEST_PATH_IMAGE038
Be the weight coefficient vector,
Figure DEST_PATH_IMAGE040
Be the intercept vector; Introduce relaxation factor ξ * i〉=0 and ξ i〉=0 and allow error of fitting ε, model passes through constraint condition
Figure DEST_PATH_IMAGE042
Figure DEST_PATH_IMAGE044
, minimize Obtain; Constant wherein C0 be penalty coefficient,
Figure DEST_PATH_IMAGE048
For prediction exceeds the quantity that allows error of fitting point,
Figure DEST_PATH_IMAGE050
This minimization problem is a convex quadratic programming problem, introduces Lagrangian function:
Figure DEST_PATH_IMAGE052
Wherein:
Figure DEST_PATH_IMAGE054
〉=0,
Figure DEST_PATH_IMAGE056
〉=0, be Lagrange's multiplier;
At the saddle point place, function L is about w, b, ξ i, ξ i *Minimal point, also be
Figure DEST_PATH_IMAGE058
Maximal point, minimization problem are converted into the maximization problems of asking its dual problem;
LagrangianL is about w at the saddle point place, b, ξ i, ξ i *Minimal point:
Figure DEST_PATH_IMAGE060
Can get the dual function of Lagrangian function:
Figure DEST_PATH_IMAGE062
At this moment,
Figure DEST_PATH_IMAGE064
Figure DEST_PATH_IMAGE066
According to Ku En-Plutarch (KKT) conditional theorem, have following formula to set up at saddle point:
Figure DEST_PATH_IMAGE068
By following formula as seen, α i α i * =0, α i With α i * Can not be non-zero simultaneously, can get:
Figure 544332DEST_PATH_IMAGE044
Can obtain vectorial b from following formula, obtain model;
Step (3). utilize particle swarm optimization algorithm, the product quality of integrating step (2) each coaxial cable sheathing machine of building and the separate unit sheath between each production operation parameter are produced the block mold of machine
Figure 898084DEST_PATH_IMAGE018
, carry out the optimization of each production task, concrete steps are as follows:
A. define the particle cluster algorithm initial population Vector respectively tie up component, be respectively production operation parameter and the sheath production material category of each coaxial cable sheathing machine;
B. set search target and the iterations of particle cluster algorithm, the search target is the target setting of each coaxial cable sheathing machine production quality, this target setting can be the integration objective of production quality, it also can be single production QT Quality Target, also can be that multiple goal is optimized simultaneously, be determined by needs of production;
C. to produce the length need finish the concentric cable sheath be total unit interval production task the unit interval
Figure DEST_PATH_IMAGE076
, the production task sum of the highest unit interval of permission of each coaxial cable sheathing machine is the highest unit interval production task of permission of each coaxial cable sheathing machine ,
Figure DEST_PATH_IMAGE080
,
Figure DEST_PATH_IMAGE082
Be
Figure 977773DEST_PATH_IMAGE024
The highest unit interval production task of the permission of platform coaxial cable sheathing machine, when
Figure DEST_PATH_IMAGE084
The time, establish
Figure DEST_PATH_IMAGE086
Be total unit interval production task of each coaxial cable sheathing machine that initialization is good,
Figure DEST_PATH_IMAGE088
, wherein
Figure DEST_PATH_IMAGE090
,
Figure DEST_PATH_IMAGE092
Be the initialization unit interval production task of each coaxial cable sheathing machine that initialization is good, when
Figure DEST_PATH_IMAGE094
The time,
Figure DEST_PATH_IMAGE096
,
Figure DEST_PATH_IMAGE098
Be
Figure DEST_PATH_IMAGE100
The initialization production task of platform coaxial cable sheathing machine, the
Figure 437573DEST_PATH_IMAGE100
Each coaxial cable sheathing machine after the platform coaxial cable sheathing machine (
Figure DEST_PATH_IMAGE102
) production task is 0, otherwise
Figure 472220DEST_PATH_IMAGE024
Platform coaxial cable sheathing machine production task initialization interval is:
Figure DEST_PATH_IMAGE104
, produce initial the in this interval
Figure 613351DEST_PATH_IMAGE100
The production task of platform coaxial cable sheathing machine is individual;
According to above step initialization colony vector
Figure 924378DEST_PATH_IMAGE074
Wherein heart yearn speed is determined by the production task of distributing, situation or explained hereafter requirements set that other production operation parameters are produced machine according to actual concentric cable sheath, integrating step (2) model between each coaxial cable sheathing machine product quality and production operation parameter of building
Figure 430446DEST_PATH_IMAGE018
According to the production task of each coaxial cable sheathing machine in the initial population, obtain the optimization aim initial value of each coaxial cable sheathing machine under the initial population production task, then according to the search target of setting, carry out iterative computation with particle cluster algorithm, search Optimal Production task distribution condition;
D. when particle cluster algorithm is finished iterations or find set to require optimum, stop to calculate the colony's vector that obtains corresponding optimum, the production task that namely obtains each optimum coaxial cable sheathing machine is distributed.
CN201210547283.2A 2012-12-17 2012-12-17 Cooperating production method of multiple coaxial-cable shield machines Active CN103064370B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201210547283.2A CN103064370B (en) 2012-12-17 2012-12-17 Cooperating production method of multiple coaxial-cable shield machines

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201210547283.2A CN103064370B (en) 2012-12-17 2012-12-17 Cooperating production method of multiple coaxial-cable shield machines

Publications (2)

Publication Number Publication Date
CN103064370A true CN103064370A (en) 2013-04-24
CN103064370B CN103064370B (en) 2015-05-06

Family

ID=48107032

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201210547283.2A Active CN103064370B (en) 2012-12-17 2012-12-17 Cooperating production method of multiple coaxial-cable shield machines

Country Status (1)

Country Link
CN (1) CN103064370B (en)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2003046770A1 (en) * 2001-11-28 2003-06-05 Pavilion Technologies, Inc. System and method for historical database training of support vector machines
CN101498458A (en) * 2009-03-02 2009-08-05 杭州电子科技大学 Model updating method for on-line boiler combustion optimization
CN102222128A (en) * 2011-05-05 2011-10-19 杭州电子科技大学 Method for combustion optimization of waste plastics oil refining
CN102750424A (en) * 2012-07-16 2012-10-24 杭州电子科技大学 Method for optimizing combustion of biomass furnace
CN102799778A (en) * 2012-07-16 2012-11-28 杭州电子科技大学 Method for optimizing load distribution of boiler

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2003046770A1 (en) * 2001-11-28 2003-06-05 Pavilion Technologies, Inc. System and method for historical database training of support vector machines
CN101498458A (en) * 2009-03-02 2009-08-05 杭州电子科技大学 Model updating method for on-line boiler combustion optimization
CN102222128A (en) * 2011-05-05 2011-10-19 杭州电子科技大学 Method for combustion optimization of waste plastics oil refining
CN102750424A (en) * 2012-07-16 2012-10-24 杭州电子科技大学 Method for optimizing combustion of biomass furnace
CN102799778A (en) * 2012-07-16 2012-11-28 杭州电子科技大学 Method for optimizing load distribution of boiler

Also Published As

Publication number Publication date
CN103064370B (en) 2015-05-06

Similar Documents

Publication Publication Date Title
CN102799778B (en) A kind of optimization boiler load distribution method
CN104537503B (en) Data processing method and system
CN101833709A (en) Mixing intelligent optimizing method for semiconductor production line production plan
CN102222128B (en) Method for combustion optimization of waste plastics oil refining
CN103942375A (en) High-speed press sliding block dimension robust design method based on interval
CN108460548A (en) A kind of more Metal Open production-operational-plan methods based on improvement grey wolf algorithm
CN110059842A (en) A kind of foundry's production planning optimization method considering smelting furnace and sand mold size
CN105160433A (en) Assembly line multi-target modeling method, particle swarm algorithm and optimization scheduling method
CN103613272B (en) A kind of glass optical fiber wire-drawing equipment optimization production method
CN102981409B (en) Method for optimizing operation of coaxial cable sheathing machine
CN101685302B (en) Method for calculating cold rolling material by using computer program
CN103064370A (en) Cooperating production method of multiple coaxial-cable shield machines
CN102194057A (en) Method for updating model of waste plastic oil refining combustion optimization
CN102156405B (en) Sintered ore chemical component prediction and intelligent control system under small sample poor information
CN109559017A (en) Technical indicator boundary and its determination before Qinghai gas area gas well foam drainage gas recovery is implemented
CN103020455B (en) Multi-target model updating method for optimizing operation of coaxial cable sheath machine
CN112005679A (en) Water and fertilizer integrated distribution method for precision agriculture
CN104834986B (en) Tunnel construction progress dynamic control method based on the analysis of global overall sensitivity
CN108520087B (en) Robustness measurement and balance optimization design method for heterogeneous and multi-target performance of mechanical structure
CN106651011A (en) Particle swarm algorithm-based canal system optimization water distribution method
CN109409593A (en) For assisting the flow management method and system of hospital financial budget allocation decision
Tian et al. Decomposition algorithm for the scheduling of typical polyvinyl chloride production by calcium carbide method
CN103020447A (en) Modeling method for optimized operation of coaxial cable sheathing machine
CN105631548B (en) More small hydropower systems power output Uncertainty Analysis Method based on scenario analysis
CN112668187B (en) Decoration service configuration multi-objective optimization method considering service flow information

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
C14 Grant of patent or utility model
GR01 Patent grant
TR01 Transfer of patent right

Effective date of registration: 20180514

Address after: 311400 Zhejiang Hangzhou Fuyang District golden autumn Avenue Fortis Technology

Patentee after: HANGZHOU FUTONG ELECTRIC WIRE & CABLE CO., LTD.

Address before: 311499 Fuchun street, Fuyang, Hangzhou, Zhejiang, 18

Patentee before: Futong Group Co., Ltd.

TR01 Transfer of patent right