Search results

The purpose of this study is to automatically provide suggestions for predicting the likely status of a mechanical component is a key challenge in a wide variety of industrial domains.

Existing solutions based on ontological models have proven to be appropriate for fault diagnosis, but they fail when suggesting activities leading to a successful prognosis of mechanical components. The major reason is that fault prognosis is an activity that, unlike fault diagnosis, involves a lot of uncertainty and it is not always possible to envision a model for predicting possible faults.

This work proposes a solution based on massive text mining for automatically suggesting prognosis activities concerning mechanical components.

The great advantage of text mining is that makes possible to automatically analyze vast amounts of unstructured information to find corrective strategies that have been successfully exploited, and formally or informally documented, in the past in any part of the world.

A major problem of business process modelling languages that primarily express the flow of activities is the limited support for actor modelling provided by rigid swimlane concepts. Thus, the aim of this work is to present a general approach for actor modelling in business processes that supports different layers of abstraction, thereby increasing the expressiveness and avoiding inaccuracy and redundancy.

The proposed actor modelling approach supports task-based assignment of actors and roles based on deontic logic and speech act theory. The semantics of the approach is formally specified based on abstract state machines.

The new approach for actor modelling is more expressive and provides the possibility to reduce the structural complexity of the process flow as shown by a case study and a comparison of an ordinary business process modelling approach using swimlanes and the actor modelling approach based on the workflow resource patterns. In particular, the evaluation showed that important patterns such as separation of duties and retain familiar are only supported by the actor modelling approach.

The research is to some degree in the context of the business process model and notation as a representative of a business process modelling language using swimlanes.

Different gradations concerning the extent to which actor modelling is supported make the new approach outstanding for modelling activities, actors, and constraints in an expressive and legible way.