Samir Padalkar

Real-time fault diagnostics

The intelligent process control system (IPCS), an integrated environment for developing complex process control and automation systems is discussed, focusing on its real-time fault diagnostics capability. IPCS has been used to build a supervisory monitoring and diagnostics system for a cogenerator plant. The requirements and problems specific to such systems are examined. The key concepts involved in fault modeling in IPCS are explicated. The IPCS reasoning technique is described in some detail. The IPCS tool kit is also described. IPCSs performance in the cogenerator plant application is reported.<<ETX>>

Model-based intelligent process control for cogenerator plants

Abstract This paper describes a new approach for the design and implementation of an intelligent monitoring and diagnostic system for a complex, practical system: a cogenerator plant. The methodology is based on multiple aspect modeling and model interpretation , which is used for instantiating a run-time system based on a graph-model of computation. Sensory input signals from the plant are processed and interpreted in the context of various models of the cogenerator system in real-time . The system demonstrated that the model-based approach has a significant impact not only on the functional performance of the control system, but dramatically reduces development time as well.

Model-embedded on-line problem solving environment for chemical engineering

The building of custom monitoring, control, simulation and diagnostics applications for complex chemical plants necessitates the integration of models into the problem solving process. This paper describes a system and its practical applications that supports this activity. It is based on the Multigraph Architecture, which is a generic framework for building these model-based systems. The paper discusses the modeling paradigms used, how the applications are generated, and some practical, existing applications.

Intelligent monitoring and diagnostics for plant automation

A approach is proposed for the design and implementation of an intelligent monitoring and diagnostic system for a cogenerator plant. The approach is based on multiple-aspect modeling and model interpretation: sensory input signals from the plant are processed and interpreted in the context of various models of the cogenerator system. Experiences obtained during the development and the field test of the system have proved that the approach is viable even in real-time applications and results in considerable improvement in software technology.<<ETX>>

Real-time fault diagnostics with multiple aspect models

A real-time fault diagnostics system that is applicable for diagnosing large-scale plants is described. It uses a multiple aspect model of the plant including the hierarchical process model, the hierarchical component model, and the hierarchical fault model (HFM). HFM represents the spatial and temporal aspects of faulty behavior in the form of a hierarchical fault propagation digraph. The reasoning algorithm is based on the structural and temporal constraint enforcement, and is migrated to lower levels of HFM hierarchy. It is able to guarantee response times, perform nonmonotonic and temporal reasoning, operate continuously, accept asynchronous data, generate requests, perform time and diagnostic resolution tradeoffs, and diagnose single and most multiple fault cases.<<ETX>>

Testing And Validation In Artificial Intelligence Programming

The paper describes a test and validation toolset developed for artificial intelligence programs. The basic premises of this method are: (1) knowledge bases have a strongly declarative character and represent mostly structural information about different domains, (2) the conditions for integrity, consistency and correctness can be transformed to structural properties of knowledge bases and (3) structural information and structural properties can be uniformly represented by graphs and checked by graph algorithms. The interactive test and validation environment have been implemented on a SUN workstation.

Programming Model For Coupled Intelligent Systems In Distributed Execution Environments

This paper discusses the requirements for integrating artificial intelligence (AI) techniques with traditional real-time computing in distributed computing environments, and describes an architecture and high-level programming model developed for this purpose. The Multigraph Architecture is a multilayered system, which includes a parallel computation model, the corresponding execution environment and various software tools. The components of the high-level programming model are tailored to the specific properties of the distri-buted computing system, and are centered around the concept of autonomous, communicating objects. The programming model consists of special object types that offer high-level support for the design of complex system components, such as procedural networks, or rule-based systems.

Model based Intelligent Process Monitoring and Real-Time Diagnosis

Abstract This paper describes a new approach to the design and implementation of an intelligent process monitoring and diagnosis system shell called IPCS (Intelligent Process Control System). A multiple aspect model consisting of a functional decomposition of the plant (Hierarchical Process Model: HPM) and a structural decomposition of the plant (Hierarchical Component Model: HCM) is the basic modeling technique. A Hierarchical Fault Model (HFM) is derived in the context of the HPM and HCM, and represents causal failure possibilities among components and functions in the form of a hierarchical fault propagation digraph. An edge of such a digraph is weighted with a fault propagation probability and a fault propagation time interval. Structural and temporal constraint enforcement on the HFM is the means of identifying fault source components. The model description, diagnostic algorithm and its programming environment are described in this paper. IPCS has undergone field tests and was in experimental use from May 1989 to July 1990.

MODEL BASED INTELLIGENT PROCESS MONITORING AND REAL-TIME DIAGNOSIS

This paper describes a new approach to the design and implementation of an intelligent process monitoring and diagnosis system shell called IPCS (Intelligent Process Control System). A multiple aspect model consisting of a functional decomposition of the plant (Hierarchical Process Model: HPM) and a structural decomposition of the plant (Hierarchical Component Model: HCM) is the basic modeling technique. A Hierarchical Fault Model (HFM) is derived in the context of the HPM and HCM, and represents causal failure possibilities among components and functions in the form of a hierarchical fault propagation digraph. An edge of such a digraph is weighted with a fault propagation probability and a fault propagation time interval. Structural and temporal constraint enforcement on the HFM is the means of identifying fault source components. The model description, diagnostic algorithm and its programming environment are described in this paper. IPCS has undergone field tests and was in experimental use from May 1989 to July 1990.