Grant: Discovery Grants Program - Individual
École Polytechnique de Montréal
$24,000.00
Intelligent Automated Modular Design Synthesis of Mechatronic Systems
FY 2018-19
Summary
Mechatronics design integrates several engineering disciplines in one system and plays an increasingly important role in both research and industry. In a mechatronic system, multi-domain components stem from mechanical, electronics and control engineering to form a special integration and a functional interaction in one product. The integration required among the multi-domain components makes it difficult for engineers to understand the design task as a whole, and this inherent complexity puts great strain on their creativity as they constantly need to develop new and improved products. Existing Computer Aided Design (CAD) solutions can help them to a certain extent; but they remain passive tools relying mainly on their own knowledge. Therefore, more intelligent and dynamic CAD support is highly desirable and to this end, Artificial Intelligence can help achieve this through design automation. *The MAIN objective of this research program is to develop automated solutions based on artificial evolution to support mechatronics engineers in their design task. However, a major drawback lies in the fact that automatically generated solutions, while valid, are generally very complex and cumbersome and end up not being considered as usable design alternatives by engineers. *The HYPOTHESIS underlying this research program is that simpler/more modular artificially evolved design candidates will be used by engineers as valid design alternatives. The added modularity would allow designers to shuffle between and re-use subsystems for increased design flexibility and product functionality.*The FIRST axis of research in this program will provide optimized artificial evolution solutions that offer engineers new, simpler and usable design alternatives, and in order to mitigate models' complexity levels, modularity principles will be integrated in the evolution. We will embed modularity as a full part of the artificial evolution of new design candidates trough the definition of new mechatronics-related modularity indexes. Additionally, Mechatronic systems models will be automatically generated using a building-block modular approach. The automated design support solutions will be using evolutionary computing techniques inspired from nature such as genetic programming and genetic algorithms in order to synthesis new mechatronic systems that meet design specifications subject to various constraints. *Moreover, to reduce the design space to feasible solutions only, the developed evolutionary design solution will be constrained by an intelligent decision support system. This will allow the engineers to get more design alternatives in faster times. The constraining of the design candidates' domain and the optimization of the artificial evolution performances represents the SECOND axis of this research program.*Finally, the THIRD axis of this research program deals with validation. To this end, two relevant real-word examples will be investigated, in terms of Micro-Electro-Mechanical systems and a robotic arm manipulator. *Our proposed approach offers excellent perceptive of success because it extends the spectrum of solutions for design engineers by offering new alternatives of mechatronic designs that are both feasible and simple enough to understand, use and re-use.
Program
Discovery Grants Program - Individual
Recipient
Location
Quebec, Canada
Recipient Type
Academia
Type
Grant
Source
NSERC's Awards Data
As published
Application id
RGPIN-2014-06289
Name nom
Achiche, Sofiane
Department département
Génie mécanique
Organization id
64
Institution établissement
École Polytechnique de Montréal
Province en
Québec
Province fr
Québec
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2018
Competition year année de concours
2014
Award amount
24000
Program id
RGPIN
Program name en
Discovery Grants Program - Individual
Program name fr
Programme de subventions à la découverte - individuelles
Group en
Discovery grants programs
Group fr
Programmes de subventions à la découverte
Committee code
1512
Committee name en
Mechanical Engineering
Committee name fr
Génie mécanique
Area of application code
1206
Area of application group en
Advancement of knowledge
Area of application group fr
Avancement des connaissances
Area of application en
Engineering
Area of application fr
Génie
Research subject code
1701
Research subject group en
Design and manufacturing
Research subject group fr
Conception et fabrication
Research subject en
Engineering design
Research subject fr
Conception technique
Partie
5
Nb partie
5
Application title
Intelligent Automated Modular Design Synthesis of Mechatronic Systems
Keyword
NSERC
Application summary
Mechatronics design integrates several engineering disciplines in one system and plays an increasingly important role in both research and industry. In a mechatronic system, multi-domain components stem from mechanical, electronics and control engineering to form a special integration and a functional interaction in one product. The integration required among the multi-domain components makes it difficult for engineers to understand the design task as a whole, and this inherent complexity puts great strain on their creativity as they constantly need to develop new and improved products. Existing Computer Aided Design (CAD) solutions can help them to a certain extent; but they remain passive tools relying mainly on their own knowledge. Therefore, more intelligent and dynamic CAD support is highly desirable and to this end, Artificial Intelligence can help achieve this through design automation. *The MAIN objective of this research program is to develop automated solutions based on artificial evolution to support mechatronics engineers in their design task. However, a major drawback lies in the fact that automatically generated solutions, while valid, are generally very complex and cumbersome and end up not being considered as usable design alternatives by engineers. *The HYPOTHESIS underlying this research program is that simpler/more modular artificially evolved design candidates will be used by engineers as valid design alternatives. The added modularity would allow designers to shuffle between and re-use subsystems for increased design flexibility and product functionality.*The FIRST axis of research in this program will provide optimized artificial evolution solutions that offer engineers new, simpler and usable design alternatives, and in order to mitigate models' complexity levels, modularity principles will be integrated in the evolution. We will embed modularity as a full part of the artificial evolution of new design candidates trough the definition of new mechatronics-related modularity indexes. Additionally, Mechatronic systems models will be automatically generated using a building-block modular approach. The automated design support solutions will be using evolutionary computing techniques inspired from nature such as genetic programming and genetic algorithms in order to synthesis new mechatronic systems that meet design specifications subject to various constraints. *Moreover, to reduce the design space to feasible solutions only, the developed evolutionary design solution will be constrained by an intelligent decision support system. This will allow the engineers to get more design alternatives in faster times. The constraining of the design candidates' domain and the optimization of the artificial evolution performances represents the SECOND axis of this research program.*Finally, the THIRD axis of this research program deals with validation. To this end, two relevant real-word examples will be investigated, in terms of Micro-Electro-Mechanical systems and a robotic arm manipulator. *Our proposed approach offers excellent perceptive of success because it extends the spectrum of solutions for design engineers by offering new alternatives of mechatronic designs that are both feasible and simple enough to understand, use and re-use.