Method of Cluster Based Cross-Domain Knowledge Acquisition for Biologically Inspired Design

Biologically inspired design inspires inventions and new technologies in the field of engineering by mimicking functions, principles, and structures in the biological domain. To deal with the obstacles of cross-domain knowledge acquisition in the existing biologically inspired design process, functional semantic clustering based on functional feature semantic correlation and environmental constraint clustering composition based on environmental characteristic constraining adaptability are proposed. A knowledge cell clustering algorithm and the corresponding prototype system is developed. Finally, the effectiveness of the method is verified by the visual prosthetic device design.

Authors:

• Shen Jian
• Hu Jie
• Ma Jin
• Peng Ying Hong
• Fang Yi
• Liu Wen Hai

Keywords:

• Knowledge based engineering
• biologically inspired design
• knowledge cell
• knowledge clustering
• knowledge acquisition.

References:

[1] Nagel J. K. Systematic design of biologically-inspired engineering solutions (J). Dissertations & Theses - Gradworks, 2010.
[2] Wang Q, Gossweiler G R, Craig S L, et al. Cephalopod-inspired design of electro-mechano-chemically responsive elastomers for on-demand fluorescent patterning(J). Nature Communications, 2014, 5:4899.
[3] Bionics Ants. A project of Festo AG & Co. KG Corporate Design Ostfildern Germany (DB/OL). 2015, available from: www.festo.com/bionic.
[4] Zhang, D.Q., Chen, S., Pan, Z.S, et al. Kernel based fuzzy clustering incorporating spatial constraints for image segmentation(C). Machine Learning and Cybernetics. 2003 International Conference on. IEEE. 2003, 4: 2189-2192.
[5] Tinsley A, Midha P, Nagel R, et al. Exploring the use of functional models as a foundation for biomimetic conceptual design (J). American Society of Mechanical Engineers, 2007:79-92.
[6] AskNature, A project of the Biomimicry Institute (DB/OL). 2008-2016, available from: http://asknature.org.
[7] Chakrabarti, A. Supporting Analogical Transfer in Biologically Inspired Design (J). Biologically Inspired Design, 2014:201-220.
[8] Haberland M, Kim S. On extracting design principles from biology: I. Method-General answers to high-level design questions for bioinspired robots (J). Bioinspiration & Biomimetics, 2015, 10(1):016010.
[9] Goel A K, Vattam S, Wiltgen B, et al. Information-processing theories of biologically inspired design (M) //Biologically Inspired Design. Springer London, 2014: 127-152.
[10] Ma J, Hu J, Feng J F, et al. Constrained FBS knowledge cell model, representation, and applications for conceptual design (J). Archive Proceedings of the Institution of Mechanical Engineers Part C Journal of Mechanical Engineering Science 1989-1996 (vols 203-210), 2015, 230(11).
[11] Couzin-Frankel J. Second chapter (J). Science, 2016, 353(6303):983.
[12] Normann R A, Maynard E M, Rousche P J, et al. A neural interface for a cortical vision prosthesis (J). Vision Research, 1999, 39(15):2577-2587.
[13] Li M, Yan Y, Wu K, et al. Penetrative Optic Nerve-Based Visual Prosthesis Research(M)//Artificial Vision. Springer International Publishing, 2017: 165-176.