Stephen Duane Sanborn

Human performance and embedded intelligent technology in safety-critical systems

Information technology continues to evolve rapidly. We see this particularly in the evolution of embedded intelligent systems--knowledge-based systems deployed in larger hosts with real-time response requirements, which provide real-time advice, guidance, information, recommendations and explanations to their users. These systems have recently been deployed in safety-critical large-scale systems, where humans and technology are jointly responsible for executing tasks, monitoring operations, and providing system safety. Thus, human interaction with intelligent technology in safety-critical systems has important implications. Those interactions can enhance or reduce system efficiency, enhance or compromise safety, and augment or negate the other benefits that technology provides. In this paper, we focus on interactions between human operators and embedded intelligent systems. We first consider the role of technology in safety-critical systems, and discuss studies of the impact of technology on human operators in such systems. We then describe embedded intelligent systems, and studies of their impacts on human operators. To illustrate these points, we consider the case of embedded intelligent technology introduction in one such setting, and the results of an empirical investigation of the impact of the technology on human performance in that system. We conclude with a discussion of the implications of the study and of the importance of understanding the impact of embedded intelligent technology on human operators in safetycritical systems.

Evaluation of Embedded Intelligent Real‐time Systems*

Over the past two decades, questions have surfaced about the effectiveness and contribution of intelligent systems to decision makers in a variety of settings. This paper focuses on the evaluation challenges associated with intelligent real-time software systems that are embedded in larger host systems. With the proliferation of such systems in operational settings such as aerospace, medical, manufacturing, and transportation systems, increased attention to evaluations of such systems, and to resulting software safety, is warranted. This paper describes one such evaluation and proposes a set of evaluation criteria for embedded intelligent real-time systems (EIRTS). Implications of the evaluation and the evaluation criteria are discussed.

Remote Monitoring and Diagnostics System for GE Heavy Duty Gas Turbines

The paper describes GE’s Remote Monitoring and Diagnostic (RM&D) system, its operation, its unique features and our experiences in applying it to improve performance and availability of heavy-duty gas turbine fleet worldwide. A key success factor of the system is that it relies upon an effective combination of advanced computer automation complemented by technical experts who have an in-depth understanding of the power generation equipment to achieve its objectives.The RM&D system enables GE experts to remotely access operational data of power plants operating world wide, and exercise sophisticated algorithms, which can detect abnormal operating conditions. The experts, with ready access to the design information, operation and maintenance information and in-depth knowledge about the turbines, identify and track operational signatures, which may indicate potential problems. The real key is to be able to distinguish false indications from the ones that are true early indicators of potential problems. In this paper we describe a design approach for developing a successful RM&D system. We illustrate our approach through various examples of performance, vibration and combustion diagnostics scenarios.Copyright