Adistes

 

Adistes

Active Diagnosis based on Semantic Web Technologies for Distributed Embedded Real-Time Systems (ADISTES)

 

 

Working on new solutions, combining embedded systems and smart algorithms in the context of industry 4.0

Active diagnosis aims at significantly improving system reliability by using diagnostic information at run-time for fault isolation and online error recovery. Active diagnosis for open embedded real-time systems (e.g., health management and medical systems) is an open research problem due to stringent real-time and reliability requirements in combination with constituent components that are unknown at design time.

The proposed project will extend semantic techniques, usually used in large-scale IT systems, for active diagnosis in open embedded real-time systems. We will develop modeling techniques for expressing diagnostic features, symptoms, faults and recovery actions. Methods for distributed knowledge management will establish relaxed consistency while ensuring real-time constraints. Real-time inference will be investigated based on the time-triggered scheduling of diagnostic queries. The goal of query transformations, semantic transformations and goal-oriented learning will be improved schedulability and reliability. The methods and algorithms will be prototypically implemented, as well as experimentally and analytically evaluated concerning reliability and timeliness.

Major contributions beyond the state-of-the-art include

• (1) modeling techniques for a diagnostic knowledge base,
• (2) time-triggered scheduling and optimizations of diagnostic queries for real-time inference
• (3) distributed knowledge base management with relaxed consistency, and
• (4) goal-oriented self-learning for active diagnosis in open embedded systems.

In order to jointly address these three challenges in a framework for active diagnosis, we bring together two research fields in the proposed project:

• (1) the area of fault-tolerant embedded systems and
• (2) the area of knowledge-based system and semantic web technologies.

The research idea of the proposed project is that reliable and predictable methods for active diagnosis can be developed based on rule-based inference and semantic web technology. In standard IT applications, semantic web services were successfully deployed to deal with highly dynamic and open systems (e.g., in the Internet), provide semantic information and capture relations and dependencies.

However, there is a significant research gap since at present semantic web services neither support the modeling of the relevant properties for active diagnosis nor offer inference with real-time guarantees or an adaptive, learning behavior.

We propose the development of a diagnostic ontology, for ODRE systems time-triggered scheduling of rule executions, dynamic knowledge management and self-learning techniques to address the open-world assumption, real-time and reliability requirements.

Contakt

Christian Weber, christian.weber{at}uni-siegen.de