Marc Le Goc

SACHEM, a Real-Time Intelligent Diagnosis System Based on the Discrete Event Paradigm

SACHEM is an extensive large-scale, real-time, knowledge-based system designed to monitor and diagnose complex dynamic processes such as blast furnaces. This article aims at illustrating the way the paradigm of discrete events allowed the design of SACHEM as a recursive abstraction process of discrete events. This recursive abstraction process is the basis of a “perception-based” approach of diagnosis. A first formalization of this kind of diagnosis is proposed and illustrated with the example of the perception of a “scaffolding” phenomenon. Some considerations about blast furnaces, SACHEM, and its development are also provided to argue the operational flavor of a“perception-based”approach for diagnosis.

Resident's activity at different abstraction levels: Proposition of a general theoretical framework

One of the major issues of monitoring activities in smart environments is the building of activity models from sensors timed data. This paper proposes a general theoretical approach to this aim that provides operational results as it is illustrated with the prototypical home of the GerHome project. This proposal is based on the use of a Knowledge Engineering methodology and a Machine Learning process that are both funded on a general theory of dynamic process modeling, the Timed Observation Theory.

Operationalization of the Blending and the Levels of Abstraction Theories with the Timed Observations Theory.

ion, Knowledge Engineering. Abstract: Providing a meaning to observations coming from humans (interviews) or machines (data sets) is a necessity to Providing a meaning to observations coming from humans (interviews) or machines (data sets) is a necessity to build adequate analysis and efficient models that can be used to take a decision in a given domain. Fauconnier and Turner demonstrates in 1998 the cognitive power of their Blending Theory where the blending of multiple conceptual networks is presented as a general-purpose, fundamental, indispensable cognitive operation to this aim. On the other hand, Floridi proposed in 2008 a theory of levels of abstraction as a fundamental epistemological method of conceptual analysis that can also be used to this aim. Both theories complete together but both lack of mathematical foundations to build an operational data and knowledge modeling method that helps and guides the Analysts and the Modeling Engineers. In this theoretical paper, we introduce the mathematical framework, based on the Timed Observations Theory, designed to build a method of abstraction merging together the Blending Theory and the Levels of Abstraction Theory. Up to our knowledge, this is the first mathematical theory allowing the operationalization of the Blending Theory and the Levels of Abstraction Theory. All over the paper, the mathematical framework is illustrated on an oral exchange between three persons observing a vehicle. We show that this framework allows to build a rational meaning of this exchange under the form of a superposition of three abstraction levels.

Building a Functionnal Model from a Sequence of Alarms: The Example of APACHE

Abstract This paper aims at showing for a real case the results obtained with the stochastic approach to the analysis of a sequence of alarms produced by the Apache system, a Sachem-like system that is dedicated to monitoring, diagnosing and controlling the zinc baths used by the Arcelor Group. Sachem is the Arcelors generic extensive large-scale real time knowledge based system designed to monitor, diagnose and control processes. The paper shows how the knowledge of the behavior of a continuous process can be formalized in terms of relations between discrete events that are deduced from a sequence of Apaches alarms by the mean ofa stochastic approach. The stochastic approach is based on the representation of a sequence of alarms under the dual form of a homogeneous Markov chain and its corresponding superposition of Poisson processes. The paper shows how a functional model can be derived from a behavioral model produced according to the stochastic approach.

Towards a Discrete Event Formalization of Sachem's Perception Based Monitoring

Abstract This paper aims at introducing the basis of the formalization of the Sachem perception based monitoring and diagnosis approach. Sachem is an extensive large-scale real time knowledge based system designed to monitor and diagnose blast furnaces. In this paper, Sachem is considered as a monitoring cognitive agent that analyzes a continuous dynamic process in order to generate discrete events (alarms) that inform about unsatisfactory process states occurences. The paper shows how the knowledge about the behavior of a continuous process can be formalized in terms of relation between discrete events so that a recursive recognition process of signatures can be used in order to design monitoring cognitive agents. The paper concludes on the main property of the discrete event representation of continuous process, the compactness.

Multimodel-Based Diagnosis of Hydraulic Dams

AbstractA dam diagnosis method based on a multimodel approach is proposed, and structural, functional, behavioral, and perception models are defined. The modeling process treats a dam as a connecte...