Mitsubishi Denki Kabushiki Kaisha

Westinghouse Electric Corporation

Douglas A Bauman

Robert W Thompson, Jr

Simon Lowenfeld

Brian A Schultz

James A Neuner

Alan F Mandel

Thomas J Kenny

Kenneth M Eichler

Michal M Feilchenfeld

Hatsuhiko Naitoh

Kingsley F Graham

John R Smith

Timothy F Thompson

Sam S Palusamy

Lesley Greenberg

Elwyn L Cranford, Iii

Charles B Bond

William W Wassel

Theodore J Batt

Dhulipala M Rao

David G Theriault

Nobuyoshi Wada

Charles R Tuley, Jr

Thomas A Kozlosky

An artificial intelligence software shell for plant operation simulation includes a blackboard module including a database having objects representing plant elements and concepts. A rule-based knowledge source module and a case-based knowledge source module, in communication with the blackboard module, operate on specific predefined blackboard objects. A user interface module, in communication with the blackboard module, enables a user to view blackboard status information. A control module, in communication with the blackboard module and the knowledge source modules, receives input data and controls operation of the knowledge source modules in accordance with a predetermined knowledge source priority scheme.

Artificial intelligence software shell for plant operation simulation

An artificial intelligence software shell for plant operation simulation includes a blackboard module including a database having objects representing plant elements and concepts. A rule-based knowledge source module and a case-based knowledge source module, in communication with the blackboard module, operate on specific predefined blackboard objects. The case-based knowledge source module includes cases having past data points on a time scale. Present data is compared with the past data in the cases both on a time scale and on a magnitude scale for determining levels of closeness in time and magnitude. An input data module, in communication with the blackboard module, enables a user to input data to the shell. A control module, in communication with the knowledge source modules and the input data module, receives all input data and controls operation of the knowledge source modules in accordance with a predetermined knowledge source priority scheme.

Case-based knowledge source for artificial intelligence software shell

An artificial intelligence software shell for plant operation simulation includes a blackboard module including a database having objects representing plant elements and concepts. A rule-based knowledge source module and a case-based knowledge source module, in communication with the blackboard module, operate on specific predefined blackboard objects. An input data module, in communication with the blackboard module, enables a user to input data to the shell. A control module, in communication with the knowledge source modules and the input data module, receives all input data and controls operation of the knowledge source modules in accordance with a predetermined knowledge source interruptibility/priority scheme. The control module including an event detector module having a hash table defined by a chaining algorithm.

Interruptibility/priority control scheme for artificial intelligence

An artificial intelligence software shell for plant operation simulation includes a blackboard module including a database having objects representing plant elements and concepts. A rule-based knowledge source module or a case-based knowledge source module, in communication with the blackboard module, operate on specific predefined blackboard objects. An input data module, in communication with the blackboard module, enables a user to input data to the shell. A control module, in communication with the knowledge source modules and the input data module, receives all input data and controls operation of the knowledge source modules in accordance with a predetermined knowledge source priority scheme. The control module including an event detector module having a message evaluator that checks messages for syntax errors before searching a hash table structure in the event detector.

Control process for artificial intelligence software shell

An integrated information system is provided for a plant with interactive processes running in functional equipment subsets, such as a nuclear power generation plant. Sensors are operatively coupled to monitor processes and equipment in the plant, collecting sample data for assessing operational conditions and for predicting maintenance requirements based on loading of the equipment. One or more processors access the sample data and compares present conditions to diagnostic specifications, technical specifications and historical data stored in memory and indexed to equipment subsets and functional operating groups. The processor(s) generate prioritized reports to alert users to potential operational and/or maintenance problems. In addition to the prioritized reports, the processor accesses and outputs to the users reports of the diagnostic and technical specifications applicable to the process parameters exhibiting the potential problems. These specifications are provided in successive levels of detail and are cross referenced between related processes and related items of equipment. The information system integrates operations, maintenance, engineering and management interests in a common database of information via network-coupled data terminals.

Plant maintenance with predictive diagnostics

Numerous signal conditioning circuits on a plurality of printed circuit boards are calibrated remotely by a signal processing unit which sends coded signals to each board, either sequentially or in parallel, to connect either on-board or off-board test signals to one of the conditioning circuits in place of its field generated input. The processing unit utilizes the actual and expected responses of each conditioning circuit to low and high test signals to generate a gain and an offset which are applied to the conditioned field signal to provide a calibrated signal. The time constant for each conditioning circuit is also measured periodically, or upon a selected temperature change, for use in generating a minimum waiting period for obtaining valid data following transfers between the field generated signals and the test signals.

Method and apparatus for auto-calibration of signal conditioning

An inadvertent approach to criticality in a nuclear fueled electric power generating unit is detected and an alarm is generated through on-line monitoring of the neutron flux. The difficulties of accurately measuring the low levels of neutron flux in a subcritical reactor are overcome by the use of a microcomputer which continuously generates average flux count rate signals for incremental time periods from thousands of samples taken during each such period and which serially stores the average flux count rate signals for a preselected time interval. At the end of each incremental time period, the microcomputer compares the latest average flux count rate signal with the oldest, and preferably each of the intervening stored values, and if it exceeds any of them by at least a preselected multiplication factor, an alarm is generated. The interval and multiplication factor are chosen such that an alarm is generated early enough in the event to provide adequate time for an automatic system or the operator to take action which prevents the reactor from going critical yet minimizes the likelihood of a spurious response. As applied to a pressurized water reactor system, boron dilution events are detected in time that the chemical and volume control system can be isolated and the valves for the refueling water storage tank can be opened to inject highly borated water into the reactor coolant system to keep the reactor subcritical.

Method and apparatus for preventing inadvertent criticality in a nuclear

An elevator system having a plurality of elevator cars, and communication apparatus which includes a speech synthesizer for each car which provides audible, informative messages in its associted elevator car in response to its operation. Different messages may be simultaneously reproduced in the different elevator cars from a single vocabulary which is common to all messages and all elevator cars. A single central processing unit periodically replenishes the memory of each car's speech synthesizer before interruption can occur in the message due to lack of vocabulary information.

Elevator system with speech synthesizer for audible information

Growing community of inventors

Apollo, PA, United States of America

Douglas A Bauman