Paolo Salvaneschi

Applying AI to structural safety monitoring and evaluation

Four decision-support systems: Mistral, Damsafe, Kaleidos, and Igor provide powerful AI-based tools for evaluating structural data. The paper considers how safety managers, engineers, and authorities are using the systems to handle safety problems in structures.

Embedding a Geographic Information System in a Decision Support System for Landslide Hazard Monitoring

In this paper we present an application that exploitsa geographic information system as a front-end of acomplex information system supporting the managementof landslide hazard in Valtellina, an alpine valley inNorthern Italy.A decision support system (EYDENET, operational sinceOctober 1996), incorporating a geographic informationsystem and a data interpreter based on artificialintelligence techniques, processes the readings of the250 most significant instruments of a monitoring netof about 1000 sensors installed on differentlandslides in several alpine valleys.Data gathered by extensometers, clinometers andpluviometers, to check both movements of rocks andclimatic conditions which could affect them, areprocessed by EYDENET, that provides on-lineinterpretation of data, helps the users analyse them,and generates natural language explanations and alarmmessages for the people responsible for theenvironmental management and the civil protection.

A causal modelling framework for the simulation and explanation of the behaviour of structures

An approach to the modelling of systems in civil engineering is presented. It allows the integration of quantitative relations in a qualitative causal framework which uses objects and Petri nets to represent the device and process ontologies. This approach supports the modelling and simulation of the behaviour of a physical system and causal explanations of it. The explanations are customisable depending on the needs of different users. The approach is shown by modelling the seismic behaviour of a masonry building, simulating it and generating causal explanations tailored for the needs of different users. An example application is presented through IGOR, a decision support system for seismic assessment of buildings and planning of precautionary operations.

Improved monitoring and surveillance through integration of artificial intelligence and information management systems

Describes the results of a project which aims to improve the capabilities of an information system (IS) which supports the management of dam safety. The improvement has been achieved through the incorporation of additional components developed using AI concepts and technologies. We describe the pre-existing IS (comprised of automatic monitoring systems, telemetry and databases), identify user requirements driving the evolution of the IS and explain how AI concepts and technologies may contribute. We describe the functions, the architecture and the AI techniques of two systems (MISTRAL and DAMSAFE) added to the IS. Moreover, we discuss the issue of integration of the AI components and the pre-existing system and we present the technology developed to support this process. Finally, we give the implementation status of the project (which has delivered components that have been operational since 1992) and some information about the user acceptance, development effort and applicability to other fields.<<ETX>>

Diagnosing Ancient Monuments with Expert Software

After the 1989 collapse of the Civic Tower of Pavia, Italy, the Italian government appointed a scientific committee to analyse the causes of the collapse and to check the state of other monuments i...

MI—an object oriented environment for integration of scientific applications

Scientific and engineering software is often produced by integration of existing software components of the size of a whole program. However, on the average, scientific software was not developed for reusability and is quite distant from the user model of the application problem; integration and retrofitting is as such a costly process. An architecture, methodology and several C++ class libraries for supporting integration are introduced. The architecture separates a software component layer, and an integration layer. The latter in based on the concept of software model, that is an abstraction of components and a representation of the system differing from its actual physical structure. The methodology is based on matching needs with existing models. The C++ class libraries are explained in some detail. The application to two major systems is analysed and the ideas behind seven other systems are briefly outlined. Some lessons learned are summarised in the conclusions.

21 – Integrating Databases, Data Communication, and Artificial Intelligence for Applications in Systems Monitoring and Safety Problems

Publisher Summary The integration of different information management technologies helps to deal with safety problems. Artificial intelligence techniques provide powerful tools for processing information stored in archives of safety-related data, such as measurements, documents, and test data. Internet technologies can be successfully coupled with these data processing tools to distribute data and knowledge among safety managers. This chapter describes a chain of software tools currently being used to face different aspects of safety management procedures in different fields of engineering. The main achievements of the joint application of these software techniques consist of the automatic support of those in charge of safety management, a performance that reduces the requests for expert intervention and the associated costs and delays, and increases the reliance upon the safety of the facility under examination.

Looking for analogues in structural safety management through connectionist associative memories

This paper describes the first successful achievements of an experimental application of connectionist hashed associative memories for realising analogical reasoning. The application field is the management of structural safety, where analogical reasoning is used to retrieve, given the qualitative description of the state of a structure, the closest-matching cases stored in a case base, which can help safety managers to interpret the current situation. This work extends the use of Greenes associative memories by proposing a complex data structure and a compositional algorithm which is able to access the case base through structured keywords.

Safety management of civil structures using knowledge based systems

With regard to the problems of safety of civil engineering structures, the technology of knowledge-based systems can provide new tools to manage the problem complexity and to assist safety experts and operators. The approach of the so called second-generation or deep-knowledge expert systems extends the idea of numerical modelling. It proposes the construction of software systems which implement complex models (with quantitative and qualitative attributes) and functions able to reason about the model structure and behaviour. These models and reasoning functions can support human activities like the fusion of information, diagnosis, explanation and forecasting. The aim of such systems is not to substitute the expert, but to extend the experts ability to deal quickly and efficiently with complex problems. In this paper, a family of knowledge-based systems is presented, whose members share the same conceptual reference framework to deal with seismic risk evaluation of masonry buildings and safety assessment of concrete dams.

Quality Measurement of Software Products: an Experience about a Large Automation System

We present our experience in measuring quality of a large automation system. Our approach was to start from the state of the art in quality models, to formalise the expression of quality requirements, to build a quality matrix, which relates quality requirements to each single functionality, to apply several pruning techniques to cut down the measurements to be taken. Our approach allowed us to manage the complexities involved in quality measuring of large systems: it is difficult to express quality requirements, measurement costs are high, users need something more specific than a single quality profile over a complete application. We discuss a specific real case, with some practical implications. We conclude quoting some possible extensions.