Abstract: A control systems and methods are presented for controlling a production system, in which a model-based planner includes a formulation, such as a SAT formulation representing possible actions in the production, with a solver being used to provide a solution to the formulation based at least partially on production and diagnostic goals and the current plant condition, and a translation component translates the solution into a plan for execution in the plant.

Abstract: A method and system for diagnosing a fault that includes a decision tree having a plurality of decision points wherein at least some of the plurality of decision points terminate in a resolution point representing a diagnosis for the fault. Also included is a plurality of queries each having at least a first response and a second response where each of the plurality of queries being associated with one of the plurality of decision points. The system also includes a knowledge base that includes a plurality of first images where each of the plurality of first images illustrate one of the first responses. A user interface is included for presenting the plurality of queries and the illustrative first images to a user. The user navigates the decision tree by responding to at least some of the plurality of queries by viewing the illustrative first images and basing a selection between the first response and the second response associated with said at least some of said queries on said illustrative first images.

Abstract: A system and method for implementing an indirect controller for a plant. A plant can be provided with both a direct controller and an indirect controller with a system model or a committee of system models. When the system model has sufficient integrity to satisfy the plant requirements, i.e., when the system model has been sufficiently trained, the indirect controller with the system model is automatically enabled to replace the direct controller. When the performance falls, the direct controller can automatically assume operation of the plant, preferably maintaining operation in a control region suitable for generating additional training data for the system model. Alternatively, the system model incorporates a committee of models. Various types of sources for errors in the committee of models can be detected and used to implement strategies to improve the quality of the committee.

Abstract: A system (830) and method (800) for diagnosing a malfunctioning machine. A fault event is selected (806) together with sequential operating parameter data (808) from a selectively focused time interval about the fault event for evaluation of a machine (810). The selectively focused time interval may include data occurring just before, just after, or spanning the fault event. Characterizing information such as slope, rate of change, and absolute sign of the data may be derived (809) from the operating parameter data over the selectively focused time interval and used in the diagnosis. The fault event and operating parameter data may be compared to existing cases in a case database (834). A set of rules (817) or candidate anomalies (841) may be executed over the operating parameter data to further improve the accuracy of the diagnosis.

Abstract: A diagnostic method and system for a technical installation establish the cause of a fault event. A reliable, flexible and simple possible way of diagnosing an installation is provided by placing state variables that characterize an operating state of the technical installation in a dependency tree and establishing a fault path in the dependency tree by linking change directions of diagnostic parameters contained in the dependency tree.

Abstract: A network-based diagnosis server for monitoring and diagnosing a system, the server being remote from the system it is observing, comprises a sensor for generating signals indicative of a characteristic of a component of the system, a network-interfaced sensor agent coupled to the sensor for receiving signals therefrom, a broker module coupled to the network for sending signals to and receiving signals from the sensor agent, a handler application connected to the broker module for transmitting signals to and receiving signals therefrom, a reasoner application in communication with the handler application for processing, and responding to signals received from the handler application, wherein the sensor agent, broker module, handler application, and reasoner applications operate simultaneously relative to each other, such that the present invention diagnosis server performs continuous monitoring and diagnosing of said components of the system in real time.

Abstract: An optimization system is provided utilizing a Bayesian neural network calculation of a derivative wherein an output is optimized with respect to an input utilizing a stochastical method that averages over many regression models. This is done such that constraints from first principal models are incorporated in terms of prior art distributions.

Abstract: The invention is directed to a system and a method for the configuration and/or parameterization of diagnostic devices for test objects. The system includes a first data object having a collection of technological test object parameters of the test object and its components, and a second data object having a collection of technological parameters of hardware components of the diagnostic device. The system further includes a first program object containing data sentences for the assignment of at least test object parameters and technological parameters of hardware components, and a second program object for processing the data sentences assigned in the first program object. Via the data and program objects, a knowledge base is created that results in a configuration mainly automatically controlled by the knowledge of the system and/or parameterization of the diagnostic device including the test structure and evaluation. In this manner, the cost of such preparations is significantly reduced.

Abstract: The invention relates to a configuration of interconnected arithmetic elements and to a method for the computer-aided determination of a second state of a system in a first state space from a first state of the system in the first state space. According to the invention, the first state is transformed into a third state of the system in a second state space. A fourth state of the system in the second state space is determined and a variation between the third state and the forth state is ascertained. The second state is determined by using said variation and the first state.

Abstract: A method for controlling a decisional process when pursuing an overall aim in a specific field of application, such as economic, technical, organisational or similar, which is automated by the placing in relation, according to rules and strategies predetermined in accordance with the overall aim of at least one knowledge object reflecting a point of view of the field of application and comprising an item of information interpreted as an alarm sign for the decisional process with other knowledge objects reflecting other points of view or other fonctional competencies of the same field of application or of other fields.

Abstract: The invention relates to a process of detecting check sequences in a situation recognition system, composed of a list of events and time constraints. For each check sequence, a sequence of events and intervals between possible dates of occurrence of each of these events is created in memory. The process manages an internal clock differing from universal time, representing the current date of the system, updates the sequences of events for each situation upon each occurrence of a new event. This causes an updating of the current date, an updating for each sequence of events memorized of the intervals between possible dates of occurrences, detection of all the sequences of events for which one of these intervals is empty, creation of new sequences of events integrating this new event, and a detection of complete sequences.