Chronicle Recognition Research Articles

Distributed Monitoring Based on P-Time Petri Nets and Chronicle Recognition of the Tunisian Railway Network

This paper falls under the problems of the monitoring of a Discrete Event System (DES) with time constraints. Among the various techniques used for online and distributed monitoring, we are interested in the chronicle recognition. Chronicles are temporal patterns that represent the system’s possible evolutions. The proposed models are based on P-time Petri nets that are suitable to represent with accuracy and modularity the Tunisian railway network. These models are scalable and may be used to represent a large variety of railway networks. Then, monitoring is based on the generation of chronicles that are suitable to detect and isolate traffic incidents in a distributed setting. Consequently, the proposed approach is tractable for large networks. Finally, to demonstrate the effectiveness and accuracy of the approach, an application to the case study of the Tunisian railway network is outlined.

Distributed Chronicle for the fault diagnosis in Distributed Systems

The chronicle paradigm has been used to determine the faults in distributed systems, through the modelled of temporal relationships between observable events, which describe the patterns of the system behaviour. Normally, the diagnostic mechanisms based on chronicles are semi-centralised methods, based on the information from local diagnoses. These models have scalability problems when they are implemented in very large systems. This paper represents the system to be diagnosed as a distributed system composed of several components, and the behaviour of each component is described by its own subchronicles. A chronicle recognition module is assigned to each component, and each local diagnosis result (the recognition of a sub-chronicle) is sent (as an event) to the neighbouring components, so as it can be exploited during the recognition of other sub-chronicles. Additionally, this paper uses continuous query language (CQL), instead of the classic language to define chronicles, to give them more expressiveness.

Alarm management via temporal pattern learning

Industrial plant safety involves integrated management of all the factors that may cause accidents. Process alarm management can be formulated as a pattern recognition problem in which temporal patterns are used to characterize different typical situations, particularly at startup and shutdown stages. In this paper we propose a new approach of alarm management based on a diagnosis process. Assuming the alarms and the actions of the standard operating procedure as discrete events, the diagnosis step relies on situation recognition to provide the operators with relevant information on the failures inducing the alarm flows. The situation recognition is based on chronicle recognition where we propose to use the hybrid causal model of the system and simulations to generate the representative event sequences from which the chronicles are learned using the Heuristic Chronicle Discovery Algorithm Modified (HCDAM). An extension of this algorithm is presented in this article where the expertise knowledge is included as temporal restrictions which are a new input to HCDAM. An illustrative example in the field of petrochemical plants is presented.

Alarm management based on diagnosis

The transitions between operational modes (start up/shut down) in chemical processes generate alarm floods and cause critical alarm saturation. We propose in this paper an approach of alarm management based on a diagnosis process. This diagnosis step relies on situation recognition to provide to the operators relevant information on the failures inducing the alarms flows. The situation recognition is based on chronicle recognition where we propose to use the hybrid causal model of the system and the expertise to generate the pattern event sequences from which the chronicles will be extracted using the Heuristic Chronicle Discovery Algorithm Modified HCDAM. An illustrative example in the field of petrochemical plants is presented in the article.

Learning chronicles signing multiple scenario instances

Chronicle recognition is an efficient and robust method for fault diagnosis. The knowledge about the underlying system is gathered in a set of chronicles, then the occurrence of a fault is diagnosed by analyzing the flow of observations and matching this flow with a set of available chronicles. The chronicle approach is very efficient as it relies on the direct association of the symptom, which is in this case a complex temporal pattern, to a situation. Another advantage comes from the efficiency of recognition engines which make chronicles suitable for one-line operation. However, there is a real bottleneck for obtaining the chronicles. In this paper, we consider the problem of learning the chronicles. Because a given situation often results in several admissible event sequences, our contribution targets an extension to multiple event sequences of a chronicle discovery algorithm tailored for one single event sequence. The concepts and algorithms are illustrated with representative and easy to understand examples.

Timed Diagnosability Analysis Based on Chronicles

Automated chronicle recognition is an efficient and robust method for fault diagnosis in timed discrete-event systems (TDES). This paper addresses the problem of diagnosability of TDES with regards to such a diagnosis method. We propose a fully automated chain to a priori check whether faults can be identified with certainty based on a given set of chronicles. To deal with the time aspects inherent to the chronicles, we first propose an automated translation of chronicles into a set of Labeled Time Petri Nets with Priorities. The diagnosability analysis is then performed on the state class graph of these nets and consists in determining whether the recognition of a chronicle is exclusive or not.

Surveillance de compositions de web services. Deux approches distribuées à base de chroniques pour la surveillance et le diagnostic

The ability to create self healing software is a challenging task for research. This article describes an architecture dedicated to the monitoring and the diagnosis of web services. One of the main difficulties in this context is that faults may propagate from a service to another, which makes of diagnosis a crucial issue in order to react properly. Our main contribution is to extend the chronicle recognition approach to a distributed context such as choreographies of web services. Two cases are studied. In the first one, interactions between services are static and described a priori in WS-CDL; in the second one, the model of interactions is dynamic and built online.

Alarm Driven Monitoring Based on Chronicles

Chronicle recognition approaches are challenging techniques for alarm correlation and diagnostic when on-line efficiency is required. They rely on a set of patterns which represents the possible evolutions of the system and constitutes the chronicle base. The main positive point with these approaches is their high efficiency due to the symptom-to-fault knowledge they rely on. The counterpart is the difficulty of acquiring and updating this expertise-based knowledge.

Alarm driven supervision for telecommunication network: II - On-line chronicle recognition

Un systeme de supervision des reseaux de telecommunication est propose s’appuyant sur la reconnaissance en ligne et en temps reel de sequences temporelles d’alarmes appelees chroniques ou scenarios. Ces sequences peuvent etre creees par un expert ou generees par un systeme automatique comme celui presente dans l’article precedent (generation hors ligne de scenarios). Le systeme de reconnaissance de chroniques, expose dans cet article, accepte en entree un flot d’evenements dates; il reconnait des instances de chroniques au fur et a mesure de leur evolution et en sortie, il produit des evenements deduits ou declenche des actions. Ce systeme s’appuie essentiellement sur un raisonnement temporel, effectue des predictions d’evenements et maintient a jour les fenetres temporelles des evenements attendus par les chroniques en cours. Sa principale qualite est de reconnaitre efficacement et en ligne des schemas temporels d’evolution complexes. Ce systeme a ete utilise pour la surveillance d’ un systeme dynamique reel ainsi que pour la conception d’un superviseur experimental pour les reseaux de telecommunication.