The nature of statistical learning theory
The nature of statistical learning theory
A Model-Based Approach to Self-Adaptive Software
IEEE Intelligent Systems
Requirements-driven design of autonomic application software
CASCON '06 Proceedings of the 2006 conference of the Center for Advanced Studies on Collaborative research
Dependable computing: concepts, limits, challenges
FTCS'95 Proceedings of the Twenty-Fifth international conference on Fault-tolerant computing
ICSEA '10 Proceedings of the 2010 Fifth International Conference on Software Engineering Advances
Industrial Control System Security
IHMSC '11 Proceedings of the 2011 Third International Conference on Intelligent Human-Machine Systems and Cybernetics - Volume 02
Impact of Adding Security to Safety-Critical Real-Time Systems: A Case Study
COMPSACW '11 Proceedings of the 2011 IEEE 35th Annual Computer Software and Applications Conference Workshops
Hi-index | 0.00 |
With the development of information technology and industrial automation, industrial control systems have become increasingly complicated which increases the difficulty to detect running errors. Errors usually lead to industry incidences, which in turn threaten civil property and even national economy. In this paper, we propose a novel safety mechanism based on data mining. Complex network analysis, data prediction, expert analysis and self-adaptive downgrade and upgrade techniques are also applied to solve safety problems in industrial control systems. To protect industrial control system, we define a safety protection status. The system can be switched into protection status by specific operations, which finally transfer the system back to safe status. Using data mining techniques, we propose a general safety mechanism which has four operations, including global safety, initiative safety, real-time safety, and self safety.