Fabio Sartori

Case Based Reasoning and Production Process Design: The Case of P-Truck Curing

This paper describes P–Truck Curing, a Case Based Reasoning system supporting the design of the curing phase for truck tyre production. The design of this process provides a trade–off between an optimal curing degree, to avoid imperfections in the final product, and the reduction of costs, related to thermal energy employed in the curing. Expert curing process designers store information about past episodes and exploit it to define new ones, without starting from scratch. A CBR system is thus a suitable approach to model this problem solving method: case structure, similarity and adaptation functions and a general system overview will be described. This work has been developed in the context of the P–Truck project, whose goal is the development of an integrated Knowledge Management (KM) system to support the Business Unit Truck of Pirelli Tyres in the design and manufacture of truck tyres.

INDUSTRIAL MECHANICAL DESIGN: THE IDS CASE STUDY

This paper presents IDS, a knowledge based system to support experts in the design and manufacturing of complex mechanical objects. Although many sophisticated integrated environments have been developed and are currently adopted by enterprises in the design of mechanical parts and components, they can be extended to further support design activities. Artificial Intelligence techniques are particularly suitable to provide such tools with knowledge based facilities derived from skilled designers expertise. IDS (Intelligent Design System) is a set of integrated AI- based facilities interacting the CATIA CAD software environment to support the design of dies for car body manufacturing.

The role of knowledge artifacts in innovation management: the case of a chemical compound designer CoP

The paper describes how the experience we gained in the interaction with a community of professionals, the Compound Designer CoP (involved in tire production), led to the identification of the role Knowledge Artifacts can play in the definition of computational supports of innovation management in the specific domain of chemical formulation for rubber compounds. The paper reports on an experience gained in a project we are involved in and on the technology that has been designed to support knowledge and innovation management in the involved company.

Improving the effectiveness of monitoring and control systems exploiting knowledge-based approaches

This paper illustrates how the adoption of techniques typical of artificial intelligence (AI) could improve the performance of monitoring and control systems (MCSs). Traditional MCSs are designed according to a three-level architectural pattern in which intelligent devices are usually devoted to evaluate whether the data acquired by a set of sensors could be interpreted as anomalous or not. Possible mistakes in the evaluation process, due to faulty sensors or external factors, can cause the generation of undesirable false alarms. To solve this problem, the traditional three-tier architecture of MCSs has been extended with a fourth level, named the correlation level, where an intelligent module, usually a knowledge-based system, collects the local interpretations made by each evaluation device, building a global view of the monitored field. In this way, possible local mistakes are identified by the comparison with other local interpretations.

SUBSTITUTIONAL ADAPTATION IN CASE-BASED REASONING: A GENERAL FRAMEWORK APPLIED TO P-TRUCK CURING

Adaptation is one of the most problematic steps in the design and development of case-based reasoning (CBR) systems. In fact, it may require considerable domain knowledge and involve complex knowledge engineering tasks, whereas CBR is often adopted when available domain knowledge is not enough to build a problem solution given its description, and thus past experiences are considered and exploited. This paper introduces a general framework for substitutional adaptation, which only requires analogical domain knowledge, which is very similar to the one required to define a similarity function. The approach is formally introduced, and its applicability is discussed with reference to case structure and its variability. A case study focused on the adaptation of cases related to truck tire production processes is also presented.

Case---Based Support to Small---Medium Enterprises: The Symphony Project

This paper presents Symphony, an IMS (Intelligent Manufacturing System) developed in the context of an interregional project supported by the European Commission. Symphony was a three year project that aimed at the development of an integrated set of tools for management of enterprizes, in order facilitate the continuous creation, exploration and exploitation of business opportunities through strategic networking. In particular, Symphony is devoted to support human resource managers of Small---Medium Enterprises in their decision making process about the looking for newcomers and/or assigning people to jobs. About this topic, the paper focuses on SymMemory, a case---based module of the main system that has been developed to identify what features are necessary to evaluate a person, aggregate them into a suitable case---structure representing a person or job profile and comparing profiles according to a specific similarity algorithm.

A conceptual framework for monitoring and control system development

This paper illustrates a conceptual framework for the development of Monitoring and Control Systems (MCS), based on a four level agent-based architecture. Traditional MCS are designed according to a three–level architectural pattern, in which intelligent devices are usually devoted to evaluate if data acquired by a set of sensors could be interpreted as anomalous or not. Possible mistakes in the evaluation process, due to faulty sensors or external factors, can cause the generation of undesirable false alarms. To solve this problem, our framework introduces a fourth level to the traditional MCS architecture, named correlation level, where an intelligent module, usually a Knowledge–Based System, collects the local interpretations made by each evaluation device building a global view of the monitored field. In this way, possible local mistakes are identified by the comparison with other local interpretations. The framework has been adopted for the development of Automotive MCSs.

A Knowledge-based Approach to Crowd Classification

This paper illustrates a formal tool for knowledge representation and management in the crowding area, in order to improve on the sharing of knowledge, data and information produced by different models and simulation tools. The presented approach exploits knowledge-based methods for acquisition and representation phases.

From handicraft prototypes to limited serial productions: Exploiting knowledge artifacts to support the industrial design of high quality products

Abstract This paper presents a conceptual and computational framework to support experts in the design and manufacturing of high quality products. The framework is based on the development of specific knowledge artifacts characterized by tools for the management of functional, procedural, and experiential knowledge. As a case study, the GUITAR HERO project is presented. The project aims at building a knowledge-based system to support experts of a handicraft enterprise involved in the design and manufacturing of electric guitars characterized by an aluminum body. The domain of the project is extremely innovative, because electric guitars are typically manufactured with different kinds of wood rather than metals or other materials. To this aim, an ontological representation of the electric guitar has been implemented exploiting NavEditOW, a computational framework for the codification, navigation, and querying of ontologies over the Internet, based on the OWL language.

Intelligent alarm correlation

This paper introduces a formal model for the development of monitoring and control systems devoted to manage a defined class of traffic anomalies. Although a lot of sophisticated technologies have been developed over the last years, the proper detection and management of critical situations that can arise in traffic flow is still a problem. A possible solution to this problem is to provide systems for monitoring and control of traffic situation with a correlation function that creates a dynamic view of traffic situation over the space and time. In order to do this, a first order logic-based language has been developed and applied to the development of the alarm correlation module (MCA) within the context of the system for automatic monitoring of traffic (SAMOT).