| | SLO | ENG | Cookies and privacy

Bigger font | Smaller font

Show document Help

Title:Zasnova inteligentnega sistema celovite obdelave podpornih informacij za razvoj novih aparatov
Authors:ID Ogrizek, Boštjan (Author)
ID Buchmeister, Borut (Mentor) More about this mentor... New window
ID Leber, Marjan (Comentor)
Files:.pdf DOK_Ogrizek_Bostjan_2017.pdf (6,24 MB)
MD5: 57A73BE175D1CCE5E14586C2DCB189C8
 
Language:Slovenian
Work type:Dissertation
Typology:2.08 - Doctoral Dissertation
Organization:FS - Faculty of Mechanical Engineering
Abstract:V industrijski praksi je vedno večja težnja po izboljšanju razvojnega procesa. Eden izmed razlogov je želja po končnem dobičku na izdelani aparat. Drug razlog je porast količine različnih razvojnih podjetij ter posledično tudi konkurence na globalnem trgu. Sam razvoj traja od prve ideje za nov izdelek pa vse do njegove ukinitve. V tem času poteka veliko aktivnosti, ki se izvajajo z željo po končnem uspehu izdelka na trgu. Vendar pa se, tako kot je to znano iz drugih panog, v obilici konkurence pogoji za uspeh zaostrijo. To pomeni, da v primeru podobnega napredka ter delovanja podjetij le ta celovito gledano ne morejo ustvariti večje konkurenčne prednosti na trgu. Če je v razvoj vloženih preveč resursov to pomeni, presežek investicije ter vpliv na končno ceno izdelka. V koliko je vloženih resursov premalo je lahko končni rezultat nepopoln izdelek, ki ga trg na dolgi rok zavrne. Tako je za optimalen razvoj izdelka potrebna optimalna pot, ki sočasno zmanjša resurse na optimalno raven prav tako pa zagotovi prepotrebno končno kvaliteto. V doktorski disertaciji smo zbrali podatke o različnih aparatih za pripravo napitkov za namene raziskovanja v področju snovanja inteligentnega podpornega sistema za razvoj aparatov. Iz zbranih podatkov smo nato izluščili predvidene pomembne karakteristike, ki smo jih nato zapisali v različne table za kasnejše delo. Zaradi samega tipa delovanja smo za kreiranje podpornega sistema uporabili metodologijo nevronskih mrež. S pomočjo le teh smo na podlagi podatkov iz obstoječe baze znanja kreirali podporne mehanizme, ki smo jih kasneje umestili v naš podporni sistem. Podporni sistem smo zastavili modulno, saj je bil že začetni namen možnost kasnejših enostavnih nadgradenj v primeru novih dognanj ter učenja iz lastnih primerov. Kreirane nevronske mreže so bile tekom razvoja sistema tudi testirane ter kvalitativno ovrednotene. Podporni sistem je bil kreiran s pomočjo implementacije šestih podpornih področij. Ta področja so bila izbrana iz različnih vej razvoja aparatov. Končni sistem je bil zasnovan z miselnostjo hitre pomoči ter enostavnostjo uporabe končnega odjemalca. Rezultati testiranja podpornega sistema so pokazali ustreznost metodologije za namen razvoja aparatov. Dokazali smo, da je mogoče razviti podporni sistem s pomočjo nevronskih mrež, ki pomaga pri obdelavi podpornih informacij. Prav tako pa smo s pomočjo rezultatov ponudili možnosti za dodatne raziskave ter razvoj v smeri inteligentnih sistemov za podporo tekom razvoja različnih izdelkov.
Keywords:razvoj izdelka, nevronske mreže, inteligentni sistem, podporne informacije
Place of publishing:Maribor
Publisher:[B. Ogrizek]
Year of publishing:2017
PID:20.500.12556/DKUM-65506 New window
UDC:004.89:658.512.2(043.3)
COBISS.SI-ID:20809494 New window
NUK URN:URN:SI:UM:DK:TZ6VYRAE
Publication date in DKUM:07.07.2017
Views:1638
Downloads:192
Metadata:XML DC-XML DC-RDF
Categories:KTFMB - FS
:
Copy citation
  
Average score:(0 votes)
Your score:Voting is allowed only for logged in users.
Share:Bookmark and Share



Hover the mouse pointer over a document title to show the abstract or click on the title to get all document metadata.

Secondary language

Language:English
Title:CONCEPT OF SUPPORTING INFORMATION INTELLIGENT SYSTEM FOR DEVELOPMENT OF NEW APPLIANCES
Abstract:There is increasing momentum in industrial practice to improve the development process itself. One of the key factors to do so is the desire for the profit made per appliance. The second reason is increase of the development oriented companies and with this also fierce competition in the global market. Development of the appliance lasts from the first idea about the product till the end of production. In between that time a lot of activities take place in order to achieve the success on the market. But because, as we know from the other fields, of more competition, the terms for success get stricter. This means that equally progressing companies can’t make a significant competitive advantage on the market. If there is too much resources applied in the development phase it later shows on the price of the product itself. If there is too less resources assigned to it it could happen the product is qualitatively not sufficient and therefore market rejects it. Therefore optimum development would be to minimize resources to the minimum necessary quantity with preserving quality of theend product. In the doctoral dissertation we gathered data from different appliances with the intention of research purposes to develop intelligent system for providing supporting information during development. Form the acquired data we filtered and picked the required details which we later arranged into fields for use in the later work. Because of the methodology characteristics itself, we used the methodology of neural networks for developing the supporting system. With the help of neural networks we were able to created supporting mechanisms which we later used in our supporting system. Supporting system was designed as modulous system with the intention of being able to easily upgrade it later based on new findings. Created neural networks were during development tested and qualitatively examined. Intelligent system was being made with the help of six supporting fields. Those fields were chosen from different phases of development. End system was being designed in regards of quick help and ease of use for the user. Results of testing of the support system proved the acceptability of the methodology to be used during the development of the appliances. We proved it is possible to develop the system with neural networks that helps with processing of the supporting information. With the help of result we also provided possibilities of further development in the direction of supporting systems and support during development of various products.
Keywords:Product development, neural networks, intelligent system, supporting information


Comments

Leave comment

You must log in to leave a comment.

Comments (0)
0 - 0 / 0
 
There are no comments!

Back
Logos of partners University of Maribor University of Ljubljana University of Primorska University of Nova Gorica