CN104181859A - Design method and device for improvement on numerically-controlled machine tool based on cognitive gains - Google Patents

Design method and device for improvement on numerically-controlled machine tool based on cognitive gains Download PDF

Info

Publication number
CN104181859A
CN104181859A CN201410409469.0A CN201410409469A CN104181859A CN 104181859 A CN104181859 A CN 104181859A CN 201410409469 A CN201410409469 A CN 201410409469A CN 104181859 A CN104181859 A CN 104181859A
Authority
CN
China
Prior art keywords
information
numerically
controlled machine
designing requirement
cognitive
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
CN201410409469.0A
Other languages
Chinese (zh)
Other versions
CN104181859B (en
Inventor
高一聪
冯毅雄
梁野
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.)
Zhejiang University ZJU
Original Assignee
Zhejiang University ZJU
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 Zhejiang University ZJU filed Critical Zhejiang University ZJU
Priority to CN201410409469.0A priority Critical patent/CN104181859B/en
Publication of CN104181859A publication Critical patent/CN104181859A/en
Application granted granted Critical
Publication of CN104181859B publication Critical patent/CN104181859B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Landscapes

  • Structures Of Non-Positive Displacement Pumps (AREA)
  • Numerical Control (AREA)

Abstract

The invention discloses a design method and device for the improvement on a numerically-controlled machine tool based on the cognitive gains. The design method for the improvement on the numerically-controlled machine tool based on the cognitive gains comprises the steps that the design requirement for the improvement on the numerically-controlled machine tool is input, an information unit contained in the design requirement for the improvement on the numerically-controlled machine tool is marked according to an information unit marking rule, and an information requirement needed for meeting the design requirement for the improvement is obtained; recording is completed according to a design task, a cognitive weight coefficient is constructed, the contribution of the information unit in the information requirement to meeting the design requirement is calculated, the cognitive gains of information in an information library are obtained, the information is ranked in a descending order according to the values of the cognitive gains, and the improvement on the numerically-controlled machine tool is completed by means of the recommended information. According to the design method and device for the improvement on the numerically-controlled machine tool based on the cognitive gains, highly-targeted and highly-accurate information is provided for meeting the design requirement for the improvement on the numerically-controlled machine tool, in this way, information searching time and information screening time can be greatly shortened, and highest-availability reference design information for the improvement on the numerically-controlled machine tool is obtained fast, conveniently and efficiently.

Description

A kind of numerically-controlled machine based on cognition gain improves method for designing and device
Technical field
The present invention's design relates to a kind of numerically-controlled machine and improves method for designing, and particularly a kind of numerically-controlled machine based on cognition gain improves method for designing and device.
Background technology
Numerically-controlled machine improves and designs is a complicated Innovative Design Process, need to various information support improve design, improves in design process and needs to search in time the design knowledge that acquisition is relevant, assists and improves design.Along with the continuous increase of information, it is more and more longer that numerically-controlled machine improves the information searching time that design spends in information management system, is even difficult to find meet the information of improving designing requirement.Also quantitatively accurate Calculation information, to realizing the help that improves designing requirement, causes effectively number of support controlled machine improvement design of information simultaneously.Therefore the numerically-controlled machine that, need to study a kind of convenient and efficient for cognition gain improves method for designing.
Summary of the invention
The object of the invention is to for the deficiencies in the prior art, provide a kind of numerically-controlled machine based on cognition gain to improve method for designing and device.Input numerically-controlled machine improves designing requirement, according to message unit marking convention, identifies numerically-controlled machine and improves the message unit that designing requirement comprises, and obtains to realize and improves the required information requirement of designing requirement; According to design objective, complete record, construct cognitive weight coefficient, in computing information demand, message unit is to realizing the contribution amount of improving designing requirement, and try to achieve the cognitive amount of gain of information in information bank, by cognitive gain value, by information descending sort, utilize the information of recommending to complete numerically-controlled machine and improve design.
The numerically-controlled machine that the present invention realizes based on cognition gain improves method for designing, comprises the following steps:
Step 1), according to the user's request of numerically-controlled machine and market study, determine and input the improvement designing requirement t of numerically-controlled machine 1, t 2..., t p..., t n, according to message unit marking convention, identify and improve the message unit u that designing requirement comprises 1, u 2..., u j..., u m;
Step 2) according to numerically-controlled machine, improve design objective and complete record, construct cognitive weight coefficient (ε 1, ε 2, ε 3);
Step 3) calculate and establish the contribution amount of message unit to realization improvement designing requirement in information requirement;
Step 4) computing information is to realizing the cognitive amount of gain of improving designing requirement;
The value of step 5) pressing cognitive amount of gain, by the descending sort of candidate designs knowledge, is utilized the information of recommending to complete numerically-controlled machine and is improved design.
Described step 2) be specially: the numerically-controlled machine improvement design objective completing records quantity and is less than 10, is defined as the improvement design objective of poor information, cognitive weight coefficient ε 1=0.4, ε 2=0.2, ε 3=0.4; The numerically-controlled machine improvement design objective completing records quantity and is greater than 10, is defined as informative improvement design objective, cognitive weight coefficient ε 1=0.2, ε 2=0.4, ε 3=0.4.
Described step 3) be specially: information is divided into two classes: " c 1, to realizing, improve designing requirement t phelpful " and " c 2, to realizing, improve designing requirement t pwithout helping ", computing information unit u jto realize improving designing requirement t pcontribution amount CIG (u j), wherein
The improvement design objective of poor information, (formula 1)
Informative improvement design objective, (formula 2)
IG ( u j ) = - Σ q = 1 2 P ( c q ) log P ( c q ) + P ( u j ) Σ q = 1 2 P ( c q | u j ) log P ( c q | u j ) + P ( u j ‾ ) Σ q = 1 2 P ( c q | u j ‾ ) log P ( c q | u j ‾ ) (formula 3)
Wherein, IG (u j) be message unit u jinformation gain, for message unit u jgain corrected parameter, δ is for comprising coefficient, for convergence factor, ζ is uniformity ratio.
Described step 4) be specially: calculate for improving designing requirement t pinformation requirement, information k icognitive yield value be information k ithe design objective t comprising pthe summation of contribution amount of message unit of information requirement,
Score ( k i , t p ) = Σ j = 1 m CIG ( u j ) * f ( k i , u j ) (formula 7)
Wherein, f (k i, u j) be function of state, information k iinclusion information unit u j, f (k i, u j)=1, otherwise f (k i, u j)=0.
According to information entropy axiom, the cognitive yield value of information, selects the information of cognitive yield value maximum to provide numerically-controlled machine to improve design as design reference.
Described computing information unit u jto realize improving designing requirement t pcontribution amount CIG (u j), be specially:
Comprise coefficient δ, if the improvement designing requirement quantity that contains message unit is more, the contribution amount that message unit improves designing requirement to realization is larger,
δ = f p ( u j ) / Σ j = 1 m Σ p = 1 N ( f q ( u j ) ) 2 (formula 4)
Convergence factor if the improvement designing requirement that contains message unit is gathered under same type, the contribution amount that message unit improves designing requirement to realization is larger,
(formula 5)
Uniformity ratio ζ, if the improvement designing requirement that contains message unit is evenly distributed in design objective set, the contribution amount that message unit improves designing requirement to realization is larger,
ζ = 1 - 1 N p - 1 Σ l = 1 N p ( f pl ( u j ) - 1 N p Σ l = 1 N p f pl ( u j ) ) 2 / 1 N p Σ l = 1 N p f pl ( u j ) (formula 6)
Numerically-controlled machine based on cognition gain improves a design apparatus, comprises memory module, mark module, computing module, pushing module;
Memory module, for storage information, message unit and message unit marking convention, and sends respectively mark module by information teller's marking convention;
Mark module, improves designing requirement for receiving message unit marking convention and numerically-controlled machine, and the message unit that numerically-controlled machine is improved to designing requirement carries out mark, obtains message unit, sends to computing module;
Computing module, for receiving the message unit of mark, the contribution amount of message unit to improvement designing requirement in computing information demand, and the cognitive amount of gain of computing information, send to display module by the descending sort according to cognition gain value of information;
Display module, for reception information and show information, as design reference, completes numerically-controlled machine and improves design.
Described computing module is specially: difference calculated gains corrected parameter , computing information unit u jto realize improving designing requirement t pcontribution amount CIG (u j), acquired information unit u jcognitive amount of gain; Select the information large class relevant to improving designing requirement, the cognitive yield value Score (k of computing information i, t p).
Described pushing module is specially: the information that front 5 information or the cognitive yield value of cognitive yield value descending sort are greater than to 1.0, and by the form demonstration message header of list.
The invention has the beneficial effects as follows, by calculating numerically-controlled machine, improve the contribution amount of message unit to realization improvement designing requirement in designing requirement, the cognition gain of acquired information, utilizes the cognition gain of information to represent that information realization improves effective help degree of designing requirement.Based on cognitive yield value, can generate information list targetedly according to specialized information structure, the information preference of existing improvement design, as improving design reference, effectively number of support controlled machine improves design.It is simply efficient that this numerically-controlled machine improves method for designing, can greatly reduce the time of the information of searching, and the most useful information that numerically-controlled machine improves designing requirement that realizes is provided, and the auxiliary high efficiency numerically-controlled machine that completes improves design.
Accompanying drawing explanation
Fig. 1 is the inventive method flow chart of steps;
Fig. 2 is apparatus of the present invention structural drawing.
Concrete implementation
Below in conjunction with the drawings and specific embodiments, the present invention will be further described.
Fig. 1 is that the corresponding a kind of numerically-controlled machine based on cognition gain of the present invention improves design flow diagram.
1), according to the user's request of numerically-controlled machine and market study, determine that certain model work of numerical control machine turret systems improves designing requirement: t 1, Overall Power Consumption reduces by 3%.
2) according to message unit marking convention, identify " t 1, Overall Power Consumption reduces by 3% " and the message unit that comprises, obtain to realize and improve the required information requirement U of designing requirement, its result is as shown in table 1.
3) according to numerically-controlled machine, improve design objective and complete record, be defined as informative improvement design objective, construct cognitive weight coefficient ε=[0.2,0.4,0.4].
4) computing information unit u jinformation benefit amount IG (u j), its result is as shown in table 2.
5) computing information unit u jgain corrected parameter , its result is as shown in table 3.
6) computing information unit u jto realize improving designing requirement " t 1, Overall Power Consumption reduces by 3% " contribution amount CIG (u j), its result is as shown in table 4.
7) in computing information storehouse with " t 1, Overall Power Consumption reduces by 3% " and relevant information k icognition gain Score (k i, t p), its result is as shown in table 5.
Table 1 " t 1, Overall Power Consumption reduces by 3% " and numerically-controlled machine improves the message unit that designing requirement comprises
Sequence number Message unit Sequence number Message unit
u 1 Turntable u 9 Gear train
u 2 Circular guideway u 10 Torque motor
u 3 Power consumption u 11 Lightweight material
u 4 Grinding force u 12 Numerically-controlled machine
u 5 Cutting force u 13 Reinforcing rib design
u 6 Power of motor and torque u 14 Improve design
u 7 Lubricated u 15 Performance evaluation
u 8 Low friction pair ? ?
The information gain value of table 2 message unit
Sequence number IG(u j) Sequence number IG(u j)
u 1 0.09633 u 9 0.06123
u 2 0.09781 u 10 0.09491
u 3 0.08089 u 11 0.09522
u 4 0.09890 u 12 0.07467
u 5 0.09733 u 13 0.07300
u 6 0.08967 u 14 0.07467
u 7 0.09633 u 15 0.08816
u 8 0.08428 ? ?
The gain corrected parameter of table 3 message unit
Table 4 message unit u jcognitive yield value
Sequence number CIG(u j) Sequence number CIG(u j)
u 1 0.02237 u 9 0.01514
u 2 0.02445 u 10 0.02096
u 3 0.02330 u 11 0.02382
u 4 0.02273 u 12 0.01680
u 5 0.02988 u 13 0.02403
u 6 0.02972 u 14 0.02564
u 7 0.03632 u 15 0.03424
u 8 0.02348 ? ?
Table 5 number of support controlled machine improves the information list of design
Sequence number Information Score(k i,t 1)
k 1 Hollow variable cross-section steel plates structural design 1.9394
k 2 The performance evaluation of PTFE teflon circular guideway soft strip material 1.6758
k 3 The laminating feasibility analysis of circular guideway 1.1528
k 4 The performance evaluation of high-strength light Steel material 1.1163
k 5 Straight drive torque motor improves design 1.0875
Fig. 2 is that the corresponding a kind of numerically-controlled machine based on cognition gain of the present invention improves design apparatus structural drawing.
Device comprises: memory module, for storage information, message unit and message unit marking convention, and sends respectively mark module by information teller's marking convention; Mark module, improves designing requirement for receiving message unit marking convention and numerically-controlled machine, and the message unit that numerically-controlled machine is improved to designing requirement carries out mark, obtains message unit, sends to computing module; Computing module, for receiving the message unit of mark, the contribution amount of message unit to improvement designing requirement in computing information demand, and the cognitive amount of gain of computing information, send to display module by the descending sort according to cognition gain value of information; Display module, for reception information and show information, as design reference, completes numerically-controlled machine and improves design.

Claims (9)

1. the numerically-controlled machine based on cognition gain improves method for designing, input numerically-controlled machine improves designing requirement, according to message unit marking convention, identify numerically-controlled machine and improve the message unit that designing requirement comprises, obtain to realize and improve the required information requirement of designing requirement; According to design objective, complete record, construct cognitive weight coefficient, in computing information demand, message unit is to realizing the contribution amount of improving designing requirement, and try to achieve the cognitive amount of gain of information in information bank, by cognitive gain value, by information descending sort, utilize the information of recommending to complete numerically-controlled machine and improve design.Specifically comprise the following steps:
Step 1), according to the user's request of numerically-controlled machine and market study, determine and input the improvement designing requirement t of numerically-controlled machine 1, t 2..., t p..., t n, according to message unit marking convention, identify and improve the message unit u that designing requirement comprises 1, u 2..., u j..., u m;
Step 2) according to numerically-controlled machine, improve design objective and complete record, construct cognitive weight coefficient (ε 1, ε 2, ε 3);
Step 3) calculate and establish the contribution amount of message unit to realization improvement designing requirement in information requirement;
Step 4) computing information is to realizing the cognitive amount of gain of improving designing requirement;
The value of step 5) pressing cognitive amount of gain, by the descending sort of candidate designs knowledge, is utilized the information of recommending to complete numerically-controlled machine and is improved design.
2. a kind of numerically-controlled machine based on cognition gain according to claim 1 improves method for designing, it is characterized in that, described step 2) be specially: the numerically-controlled machine improvement design objective completing records quantity and is less than 10, is defined as the improvement design objective of poor information, cognitive weight coefficient ε 1=0.4, ε 2=0.2, ε 3=0.4; The numerically-controlled machine improvement design objective completing records quantity and is greater than 10, is defined as informative improvement design objective, cognitive weight coefficient ε 1=0.2, ε 2=0.4, ε 3=0.4.
3. a kind of numerically-controlled machine based on cognition gain according to claim 1 improves method for designing, it is characterized in that described step 3) be specially: information is divided into two classes: " c 1, to realizing, improve designing requirement t phelpful " and " c 2, to realizing, improve designing requirement t pwithout helping ", computing information unit u jto realize improving designing requirement t pcontribution amount CIG (u j), wherein
The improvement design objective of poor information, (formula 1)
Informative improvement design objective, (formula 2)
IG ( u j ) = - Σ q = 1 2 P ( c q ) log P ( c q ) + P ( u j ) Σ q = 1 2 P ( c q | u j ) log P ( c q | u j ) + P ( u j ‾ ) Σ q = 1 2 P ( c q | u j ‾ ) log P ( c q | u j ‾ ) (formula 3)
Wherein, IG (u j) be message unit u jinformation gain, for message unit u jgain corrected parameter, δ is for comprising coefficient, for convergence factor, ζ is uniformity ratio.
4. a kind of numerically-controlled machine based on cognition gain according to claim 1 improves method for designing, it is characterized in that described step 4) be specially: calculate for improving designing requirement t pinformation requirement, information k icognitive yield value be information k ithe design objective t comprising pthe summation of contribution amount of message unit of information requirement,
Score ( k i , t p ) = Σ j = 1 m CIG ( u j ) * f ( k i , u j ) (formula 7)
Wherein, f (k i, u j) be function of state, information k iinclusion information unit u j, f (k i, u j)=1, otherwise f (k i, u j)=0.
5. a kind of numerically-controlled machine based on cognition gain according to claim 1 improves method for designing, it is characterized in that, according to information entropy axiom, the cognitive yield value of information, selects the information of cognitive yield value maximum to provide numerically-controlled machine to improve design as design reference.
6. computing information according to claim 3 unit u jto realize improving designing requirement t pcontribution amount CIG (u j), it is characterized in that:
Comprise coefficient δ, if the improvement designing requirement quantity that contains message unit is more, the contribution amount that message unit improves designing requirement to realization is larger,
δ = f p ( u j ) / Σ j = 1 m Σ p = 1 N ( f q ( u j ) ) 2 (formula 4)
Convergence factor if the improvement designing requirement that contains message unit is gathered under same type, the contribution amount that message unit improves designing requirement to realization is larger,
(formula 5)
Uniformity ratio ζ, if the improvement designing requirement that contains message unit is evenly distributed in design objective set, the contribution amount that message unit improves designing requirement to realization is larger,
ζ = 1 - 1 N p - 1 Σ l = 1 N p ( f pl ( u j ) - 1 N p Σ l = 1 N p f pl ( u j ) ) 2 / 1 N p Σ l = 1 N p f pl ( u j ) (formula 6).
7. the numerically-controlled machine based on cognition gain improves a design apparatus, it is characterized in that: comprise memory module, mark module, computing module, display module;
Described memory module, for storage information, message unit and message unit marking convention, and sends respectively mark module by information teller's marking convention;
Described mark module, improves designing requirement for receiving message unit marking convention and numerically-controlled machine, and the message unit that numerically-controlled machine is improved to designing requirement carries out mark, obtains message unit, sends to computing module;
Described computing module, for receiving the message unit of mark, the contribution amount of message unit to improvement designing requirement in computing information demand, and the cognitive amount of gain of computing information, send to display module by the descending sort according to cognition gain value of information;
Described display module, for reception information and show information, as design reference, completes numerically-controlled machine and improves design.
8. the numerically-controlled machine based on cognition gain improves a design apparatus, it is characterized in that: described computing module is specially: difference calculated gains corrected parameter , computing information unit u jto realize improving designing requirement t pcontribution amount CIG (u j), acquired information unit u jcognitive amount of gain; Select the information large class relevant to improving designing requirement, the cognitive yield value Score (k of computing information i, t p).
9. the numerically-controlled machine based on cognition gain improves design apparatus, it is characterized in that: described pushing module is specially: the information that front 5 information or the cognitive yield value of cognitive yield value descending sort are greater than to 1.0, by the form demonstration message header of list.
CN201410409469.0A 2014-08-20 2014-08-20 Design method and device for improvement on numerically-controlled machine tool based on cognitive gains Active CN104181859B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201410409469.0A CN104181859B (en) 2014-08-20 2014-08-20 Design method and device for improvement on numerically-controlled machine tool based on cognitive gains

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201410409469.0A CN104181859B (en) 2014-08-20 2014-08-20 Design method and device for improvement on numerically-controlled machine tool based on cognitive gains

Publications (2)

Publication Number Publication Date
CN104181859A true CN104181859A (en) 2014-12-03
CN104181859B CN104181859B (en) 2017-04-12

Family

ID=51962997

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201410409469.0A Active CN104181859B (en) 2014-08-20 2014-08-20 Design method and device for improvement on numerically-controlled machine tool based on cognitive gains

Country Status (1)

Country Link
CN (1) CN104181859B (en)

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4974191A (en) * 1987-07-31 1990-11-27 Syntellect Software Inc. Adaptive natural language computer interface system
CN101673368A (en) * 2009-09-28 2010-03-17 西安交通大学 Method for realizing numerical control machine tool based industrial product service system (mt-iPSS)
CN102780766A (en) * 2012-06-27 2012-11-14 浙江大学 Design service resource cross-domain construction method for cloud manufacturing
JP2013039862A (en) * 2011-08-12 2013-02-28 Denso Corp Torque estimation method and torque control device for vehicle compressor
CN103347051A (en) * 2013-06-14 2013-10-09 浙江大学 Method for sharing and calling numerically-controlled machine tool design resource cloud model
CN103810525A (en) * 2012-11-13 2014-05-21 中国科学院沈阳计算技术研究所有限公司 Knowledge model of numerical control system based on multi-agent technology and reasoning algorithm thereof

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4974191A (en) * 1987-07-31 1990-11-27 Syntellect Software Inc. Adaptive natural language computer interface system
CN101673368A (en) * 2009-09-28 2010-03-17 西安交通大学 Method for realizing numerical control machine tool based industrial product service system (mt-iPSS)
JP2013039862A (en) * 2011-08-12 2013-02-28 Denso Corp Torque estimation method and torque control device for vehicle compressor
CN102780766A (en) * 2012-06-27 2012-11-14 浙江大学 Design service resource cross-domain construction method for cloud manufacturing
CN103810525A (en) * 2012-11-13 2014-05-21 中国科学院沈阳计算技术研究所有限公司 Knowledge model of numerical control system based on multi-agent technology and reasoning algorithm thereof
CN103347051A (en) * 2013-06-14 2013-10-09 浙江大学 Method for sharing and calling numerically-controlled machine tool design resource cloud model

Also Published As

Publication number Publication date
CN104181859B (en) 2017-04-12

Similar Documents

Publication Publication Date Title
CN105488594A (en) Typhoon track forecast method
CN103901813A (en) Material cutting power and energy consumption obtaining and energy-saving control method in variable cutting rate process
CN102750336A (en) Resource individuation recommendation method based on user relevance
CN103559303A (en) Evaluation and selection method for data mining algorithm
CN106777328A (en) Question recommendation method and device for mobile terminal
Ghiasi et al. Sectoral systems of innovation: the case of robotics research activities
CN106141808A (en) A kind of change cutting-depth adjusting device and radial cutting parameter optimization process
CN103559373B (en) A kind of cold ring rolling process parameter optimizing method based on Fuzzy Grey association
CN103353865A (en) Barter electronic trading commodity recommendation method based on position
CN113408854B (en) Building full life cycle environment influence evaluation management method based on BIM technology
CN104181859A (en) Design method and device for improvement on numerically-controlled machine tool based on cognitive gains
CN103177160A (en) Airplane structural part automatic clamping method based on characteristics
CN105956318A (en) Improved splitting H-K clustering method-based wind power plant fleet division method
Windmark Performance-based costing as decision support for development of discrete part production: Linking performance, production costs and sustainability
CN111485868B (en) Development scheme-based reserve estimation method for coal bed gas field
CN106649431A (en) Method of displaying charts in data visualization
Choi et al. Modularization business case analysis tool: Learning from industry practices
Kim A Study of Optimal Design for Mg Armrest Frame by using Response Surface Method
CN103425891A (en) Decision algorithm for site selection of tailings dam
Pickering Systematic Quantitative Literature Review
Clark Some Further Theoretical Considerations (with Jan Weiss)
Li et al. Decomposition of energy-induced carbon emissions in the construction industry of China
Yadav et al. A review on value engineering techniques in Indian context
Remeň et al. THE CONCEPTION INDUSTRY 4.0 IN THE ENVIRONMENT OF WOOD PROCESSING COMPANIES IN SLOVAKIA
Tajanowskij et al. To substantiation of combine wheeled chassis for beet harvesting equipment

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant