• Aucun résultat trouvé

Improvement of retrieval in Case-Based Reasoning for system design

N/A
N/A
Protected

Academic year: 2021

Partager "Improvement of retrieval in Case-Based Reasoning for system design"

Copied!
7
0
0

Texte intégral

(1)

HAL Id: hal-00975172

https://hal.archives-ouvertes.fr/hal-00975172

Submitted on 8 Apr 2014

HAL is a multi-disciplinary open access

archive for the deposit and dissemination of

sci-entific research documents, whether they are

pub-lished or not. The documents may come from

teaching and research institutions in France or

abroad, or from public or private research centers.

L’archive ouverte pluridisciplinaire HAL, est

destinée au dépôt et à la diffusion de documents

scientifiques de niveau recherche, publiés ou non,

émanant des établissements d’enseignement et de

recherche français ou étrangers, des laboratoires

publics ou privés.

Improvement of retrieval in Case-Based Reasoning for

system design

Thierry Coudert, Élise Vareilles, Laurent Geneste, Michel Aldanondo

To cite this version:

Thierry Coudert, Élise Vareilles, Laurent Geneste, Michel Aldanondo. Improvement of retrieval in

CaseBased Reasoning for system design. IEEE Industrial engineering and engineering management

-IEEM, Dec 2012, Hong Kong, China. pp. 1538-1542. �hal-00975172�

(2)

This is an author-deposited version published in:

http://oatao.univ-toulouse.fr/

Eprints ID: 8867

To cite this version:

Coudert, Thierry and Vareilles, Elise and Geneste, Laurent and

Aldanondo, Michel Improvement of retrieval in Case-Based Reasoning for

system design. (2012) In: IEEE Industrial engineering and engineering

management - IEEM, 10-13 Dec 2012, Hong Kong, China.

O

pen

A

rchive

T

oulouse

A

rchive

O

uverte (

OATAO

)

OATAO is an open access repository that collects the work of Toulouse researchers and

makes it freely available over the web where possible.

Any correspondence concerning this service should be sent to the repository

administrator:

staff-oatao@listes-diff.inp-toulouse.fr

(3)

! " # # $ ! % ! # & ! ' ! ( ! ) ! ! "#$ "%$ & ' ( ) * ) + ",$ "-$ . * "/$ "0$ "1$ "2$+ ( 3 4 ) 5 6 6 6 ( ' 7 5 ( 7 5 . 7 ) 8 "/$ 5 6 8 . 9 6 ) : ; 6 < . ! 6 ( 6 . ; => = ?@ A ; !B! ?= ?! A . . < ( 6 6 . < ' * c+ ? 8 C * c+ > . < * + > . > 9 ; # * + ! " ! " " " " # " ! $ # ; # ?9

*

#

6 ? D

%

6 @ A

#

6 = >

% #@AE @ AF E 6 ? 6 6 ; % A AF 6 ?=> 6 > 6 ; * G 6 ? D G 6 @ A G 6 = > G

(4)

. < H < > > ! ! * 8 + ( ! = ! #+ ' 6 ( ' + ( 6 + ( D + ( ( 6 6 8 ; % % %&&' % % ' ' % % ( ' ( " ( ( ) ( ) " ( ) % ' * ) * % ' %&&' + + % % % % ( ( , -; % ( 6 ( * +6 . ( D 6 ( ( < %+ ' ' + ! 6 + ! D 6 + ! D *; ,+ % ' % ' % ) ) " ) * ) . / % % %&&' % " ( ) ( . / + % % ) ) % ' % ; , ! > 6 6 *! + ( ( ! ! ! ' ! * ' ! II + ! ! D ! * ! D + > ( D * > ( D + 6 ! D < * > ! D + ? ! D * + ?J ?=? ! ?; E ?!!' ?A > ; ?! A ? E ?;? ? ?! ; . 6 ( E ' − ( * +6 − 6 ( ( > 9 9 @ 9 V V v1, v2, , vn 6 6 D Dv 1, Dv 2, , Dv n @ K V Xa x11, x12, , x1n , x21, x22, , x2n, , xp1, xp2, , xpn 98 8 @ Vvalue 6 . V : Vvalue X a 6 6 LM ' : Dv1 Dv2 Dv n 0, 1 ' ! #' LM K Ti 1, Ti Xa ! %' * K Xna Dv1 Dv2 Dv n Xa6 9 > 8 N # 8 9 ! . 6 ( 9 9

(5)

8 + . 9 9 ( . 9 9 6 8 ( * + 5 6 8 * RC cj +6 "O$ * ( #+ ; 6 s i m c1 ,c2 2 d e p t hS y s t e m cc o m d e p t hS y s t e m c1 d e p t hS y s t e m c2 *#+ ' depthSystem c ' * + 3 4 * + 6 cc o m' 8 ; 6 6 * RC RC 1C RC cj sim RC ,cj cj RC 8 ( C RC ck 0 . ( ! @ ?D?@ E=? E ?!!' ? ?D>@ ; E ! @ ! 6 ' ! *! + 6 > ) "#$ "%$6 * < + ( 6 * 9 + ( 6 ( = #6 ( > * + * + #+ ' * V + @ ! . ( VSol k value VSol k ! . ! ! . ( % Comp Solk, 1 if V VSol k and VSolk value Xa *%+ VSol k value if V V Solk and VSol k value Xa RC SoC if V VSolk < K 6 9 *#+ K 6 * +6 ' #+ E ' ( N C %+ ' ( # C ,+ ' ! * RCSoC + 6 . ( 9 ' ! . = * { 1, 2,..., M}+ ! = . . "#N$ * ( ,+ Comp Solk, i 1 M 1 M Comp Solk, i 1 *,+ * 1' 6 ' 9 + 6 6 ,+ ' 6 6

(6)

D >!? ! B #+ ' < ' ! # ! % ; # >)@? >!?&)>!? ? ! @ ' ! # ! ! P ! " D *VSol 1+ * + * + * + 9 D *VSol 1 value + # /NN #NN = 0N ! @ ' ! % ! P # " D *VSol 2+ * + * + * + = * + D *VSol 2 value + # -NN 1/ #/N = %+ $ ' 9 3%&

& & '((( &

& & " ,+ ' . * + >)@? ?E >@= ?@! Q 5 5? ) * $ ?E *; = 5? @ AB+ =

Aileron Lenght L , Width W , Weight Wg

= Aileron 900, 1000, 1100, 1200, 1300, 1400, 1500 , 45,50,55, 60,65, 70,75 , 25,50,75, 100, 125, 150, 175, 200, 250, 300, 350,400, 450, 500, 550 = Aileron 1: L 20 W , 2: W 25,50, 75,100,125 ( . @6 Q Q 1 2 * 6 + 16 2+ 3 4 3 * P #NNN+ 4 9 K#6 K%6 K, K ->)@? ?J ?=? ! ?E6 D> >)@?!6 => ! > ! > ! ( ' P 3 4 R * + dl 900, 1000, 1100, 1200, 1300, 1400, 1500 * + dw 45,50, 55,60,65, 70,75 Q * + dwg 25, 50,75,100, 125, 150,175, 200, 250, 300, 350, 400, 450, 500, 550 1:l 20 w Xa1 900,45 , 1000, 50 , 1100,55 , 1200, 60 , 1300,65 , 1400, 70 , 1500,75 2: w 30.00 , 100.00 Xa2 45,50, 55,60,65, 70,75 > R =

* + dmt Carbon Fiber , Metal

>

( & 3: mt Carbon Fiber Xa3 4: l 1000.00 Xa4 -+ # ' ; - 9 3! ! ; 4 3> 4 0&1 0&22 Aileron " ! " " " " 0&1 % 0&1 ! ; - ! 1 3 D >)@? D >@@ Q? > E ?;? ? & E@?! ; D>@ ?! # % , - / 0 1 2 O #N ON N #NNN ##NN #%NN #,NN #-NN #/NN #-NN #,NN #%NN -/ /N // 0N 0/ 1N 1/ 1/ 1/ 1/ 1Ti # # # # # # # N 2 N 1 N / # % ; = 3 Ti # N % 2 4 ' 2 Ti 1 Ti Xa2; 2 Ti 0 OtherwiseC 4 Ti 1 Ti Xa4; 4 Ti 0 Otherwise

(7)

/+ ' ! # ! % . 1 4 ! # ' 1 ! # *VSol 1 l ,wg ,mt ; V 1 l , w ;V 1 VSol1+ 6 ( %+6

Comp Sol1, 1 Aileron Single Slotted Flap 0.33 2 ! #' Comp Sol1, 2 0.33 3 ! # ' Comp Sol1, 3 3 metal 0.2 4 ! # #/NN ' Comp Sol1, 4 4 1500 0 > ' ! # ( *-+ 2 M 4 Comp Sol1, i 0 4 1 4 Comp Sol1, i 2 1 2 0.25 0.33² 0.33² 0.2² 0 0.253 *-+ ! % ' ) 1 ! % * Comp Sol2, 1 1 1400, 75 0.8+ . 1/ ! % 2 ' Comp Sol2, 2 2 75 1 . 3= 4 ! %

3 ' Comp Sol2, 3 3 Metal 0.2

. #-NN ! % 4 ' Comp Sol2, 4 4 1400 0 > ' ! % 9 * 2+ ( / Comp Sol2, i 0 4 1 4 Comp Sol2, i 2 1 2 0.25 0.8² 1² 0.2² 0²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

Références

Documents relatifs

S synthetase lourde, i1 augmente beaucoup 1 'activite de 1'enzyme particulaire qui persiste des heures apres 1a disparition de 1a gramicidine S synthetase

After defining two sets of criteria related to the task’s description and the context of images, that enable us to classify a task in order to know when and

Using generic agents and adequate case base structure associated with a dedicated recall algorithm, we improve retrieval performance under time pressure compared to classic CBR

To apply the CF approach to the a multi-agent system with CBR system nine agents are required: four monitoring and evaluation agents, each one responsible for one knowl- edge

Even before data is collected at the scene, the decision support system retrieves similar cases, which suggest extra caution in securing the location to avoid data loss via the

We propose a general architecture for an argumentation machine with focus on novel contributions to and conflu- ence of methods from Information Retrieval (IR) and

Kingdom, 3 University of Navarra, Department of Physiology and Nutrition, 31008 Pamplona, Spain, 4 Maastricht University, Department of Human Biology, 6200 MD Maastricht,

be adapted, starting from our local-in-time existence result, to obtain a global-in-time existence of solutions with non-standard boundary conditions involving the pressure.. To do