James L. Dolce

On-line monitoring and diagnosis of powersystem operating conditions using artificial neural networks

An adaptive pattern recognition methodology for online monitoring and diagnosis of power system operating conditions has been developed. It is implemented on highly parallel distributed architectures of the functional-link-net (FLN) type. The flat structure of the FLN allows the tasks of unsupervised learning, supervised learning, and associative recall to be carried out without intervention in network and data structures. The proposed methodology is capable of processing large bodies of information gathered by the data acquisition system in real time. It enhances the performance of the energy management system and effectively reduces the operators response time. The real-time monitoring and diagnosis facility can quickly detect and identify abnormal operating conditions. The main features of the system are described.<<ETX>>

Real-time security monitoring of electric power systems using parallel associative memories

A methodology for the monitoring of power system security, developed with emphasis on the efficient processing of large amounts of data gathered through communication channels in real time, is presented. The approach is based on the adaptive pattern recognition concept and its implementation on parallel distributed computational architectures of artificial neural networks. Clusterwise continuous associative maps are established through data self-organization encompassing a variety of system operating regimes and topological configurations of the transmission network. Accurate and very fast information retrieval characterizes the real-time behavior of the distributed information processing system.<<ETX>>

Automated Electric Power Management and Control for Space Station Freedom

A comprehensive automation design is being developed for Space Station Freedoms electric power system. A joint effort between NASAs Office of Aeronautics and Space Technology and NASAs Office of Space Station Freedom, it strives to increase station productivity by applying expert systems and conventional algorithms to automate power system operation. An integrated approach to the power system command and control problem is defined and used to direct technology development in: diagnosis, security monitoring and analysis, battery management, and cooperative problem-solving for resource allocation. The prototype automated power system is developed using simulations and test-beds.

Automating Security Monitoring and Analysis for Space Station Freedom's Electric Power System

Operating a large, space power system requires classifying the systems status and analyzing its security. Conventional algorithms are used by terrestrial electric utilities, to provide such information to their dispatchers, but their application aboard Space Station Freedom will consume too much processing time. We present a new approach for monitoring and analysis using adaptive pattern recognition techniques. This approach yields an on-line security monitoring and analysis algorithm that is accurate and fast; and thus, it can free the Space Station Freedoms power control computers for other tasks.

Electric Power Scheduling--A Distributed Problem-Solving Approach

Space Station Freedoms power system, along with the spacecrafts other subsystems, needs to carefully conserve its resources and yet strive to maximize overall Station productivity. Due to Freedoms distributed design, each subsystem must work cooperatively within the Station community. There is a need for a scheduling too which will preserve this distributed structure, allow each subsystem the latitude to satisfy its own constraints, and preserve, individual value systems while maintaining Station-wide integrity. The value-driven free-market economic model is such a tool.

Neural-net based megawatt-frequency control

The design of a new adaptive control system is presented, and its performance in a computer simulation of the single-area megawatt-frequency control problem is demonstrated. The new design utilizes self-organization and predictive estimation capabilities of neural-net computing. Real-time adaptation is facilitated by the error-based online learning scheme implemented on a clusterwise segmented associative memory system. The use of the pattern recognition approach in power systems control is demonstrated. The role of feedback is emphasized in order to compensate for uncertainties and lack of information.<<ETX>>

Reducing the cognitive workload: Trouble managing power systems

The complexity of space-based systems makes monitoring them and diagnosing their faults taxing for human beings. Mission control operators are well-trained experts but they can not afford to have their attention diverted by extraneous information. During normal operating conditions monitoring the status of the components of a complex system alone is a big task. When a problem arises, immediate attention and quick resolution is mandatory. To aid humans in these endeavors we have developed an automated advisory system. Our advisory expert system, Trouble, incorporates the knowledge of the power system designers for Space Station Freedom. Trouble is designed to be a ground-based advisor for the mission controllers in the Control Center Complex at Johnson Space Center (JSC). It has been developed at NASA Lewis Research Center (LeRC) and tested in conjunction with prototype flight hardware contained in the Power Management and Distribution testbed and the Engineering Support Center, ESC, at LeRC. Our work will culminate with the adoption of these techniques by the mission controllers at JSC. This paper elucidates how we have captured power system failure knowledge, how we have built and tested our expert system, and what we believe are its potential uses.

An Expert System For Simulating Electric Loads Aboard Space Station Freedom

Space Station Freedom will provide an infrastructure for space experimentation. This environment will feature regulated access to any resources required by an experiment. Automated systems are being developed to manage the electric power so that researchers can have the flexibility to modify their experiment plan for contingencies or for new opportunities. To define these flexible power management characteristics for Space Station Freedom, a simulation is required that captures the dynamic nature of space experimentation; namely, an investigator is allowed to restructure his experiment and to modify its execution. This changes the energy demands for the investigators range of options. An expert system competent in the domain of cryogenic fluid management experimentation was developed. It will be used to help design and test automated power scheduling software for Freedoms electric power system. The expert system allows experiment planning and experiment simulation. The former evaluates experimental alternatives and offers advice on the details of the experiments design. The latter provides a real-time simulation of the experiment replete with appropriate resource consumption.

Space Station power system autonomy demonstration

The Office of Aeronautics and Space Technology has selected the Space Station Electrical Power System as one of the systems that will participate in the Systems Autonomy Demonstration Project(SADP) 1990 Power/Thermal Demonstration. The purpose of this demonstration is the autonomous operation of two major Space Station systems through the application of cooperating knowledge-based systems technology. Lewis Research Center(LeRC) and Marshall Space Flight Center(MSFC) will first jointly develop an autonomous power system using existing Space Station testbed facilities at each center. The subsequent 1990 power-thermal demonstrationwill then involve the cooperative operation of the LeRC/MSFC power system with the Johnson Space Center(JSC)s thermal control and DMS/OMS testbed facilities. The testbeds and expert systems at each of the NASA centers will be interconnected via communication links. The appropriate knowledge-based technology will be developed for each testbed and applied to problems requiring inter-system cooperation. Primary emphasis will be focused on failure detection and classification, system reconfiguration, planning and scheduling of electrical power resources and integration of knowledge-based and conventional control system software into the design and operation of Space Station testbeds.