Exploiting safety constraints in fuzzy self-organising maps for safety critical applications

被引：0

作者：

Kurd, Z ^{[1
]}

Kelly, TP

Austin, J

机构：

[1] Univ York, Dept Comp Sci, High Integr Syst Engn Grp, York YO10 5DD, N Yorkshire, England

[2] Univ York, Dept Comp Sci, Adv Comp Architecture Grp, York YO10 5DD, N Yorkshire, England

来源：

INTELLIGENT DAA ENGINEERING AND AUTOMATED LEARNING IDEAL 2004, PROCEEDINGS | 2004年 / 3177卷

关键词：

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

This paper defines a constrained Artificial Neural Network (ANN) that can be employed for highly-dependable roles in safety critical applications. The derived model is based upon the Fuzzy Self-Organising Map (FSOM) and enables behaviour to be described qualitatively and quantitatively. By harnessing these desirable features, behaviour is bounded through incorporation of safety constraints-derived from safety requirements and hazard analysis. The constrained FSOM has been termed a 'Safety Critical Artificial Neural Network' (SCANN) and preserves valuable performance characteristics for nonlinear function approximation problems. The SCANN enables construction of compelling (product-based) safety arguments for mitigation and control of identified failure modes. Illustrations of potential benefits for real-world applications are also presented.

引用

页码：266 / 271

页数：6