Abstract: An autonomous floor cleaning robot includes a transport drive and control system arranged for autonomous movement of the robot over a floor for performing cleaning operations. The robot chassis carries a first cleaning zone comprising cleaning elements arranged to suction loose particulates up from the cleaning surface and a second cleaning zone comprising cleaning elements arraigned to apply a cleaning fluid onto the surface and to thereafter collect the cleaning fluid up from the surface after it has been used to clean the surface. The robot chassis carries a supply of cleaning fluid and a waste container for storing waste materials collected up from the cleaning surface.

Abstract: Various amounts of information can be beneficial to different controllers configured upon an industrial control system. Information can be retained in a distributed directory such that controllers quickly learn information concerning other controllers. The distributed directory can be automatically constructed and populated with information from different controllers. When a module enters an industrial control system, information can automatically advertise to other units through use of the distributed directory.

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: Techniques for non-disruptive embedding of specialized elements are disclosed. In one aspect of the techniques, ontology is defined to specify an application domain. A program interface (API) is also provided for creating raw features by a developer. Thus a module is provided for at least one form of statistical analysis within the ontology. The module is configured automatically in a computing device with the API in response to a system consistent with the ontology, wherein the system has no substantial requirement for specialized knowledge of that form of statistical analysis, and the module has no substantial requirement for specialized knowledge of particular functions provided by the system.

Abstract: A system and method of controlling a sensor to sense one target from a plurality of targets includes predicting states of the targets. A set of probability distributions is generated. Each probability distribution in the set represents a setting or settings of at least one control parameter of the sensor. An expected information gain value for each control parameter in the set is calculated. The information gain value represents an expected quality of a measurement of one of the targets taken by the sensor if controlled according to the control parameter, based on the predicted state of the target. Updating the set of probability distributions takes place to identify the sensor control parameters that maximise the expected information gain value. The sensor is then controlled in accordance with the maximising control parameters.

Abstract: An electric power meter includes an embedded decomposition module that is configured to decompose a power meter signal into constituent loads to segregate and identify energy consumption associated with each individual energy consumption device within a plurality of energy consumption devices coupled to the power meter.

Abstract: A method, a computer-readable medium, and a system for tuning a cost function to control an operational plant are provided. A plurality of cost function parameters is selected. Predicted future states generated by the neural network model are selectively incorporated into the cost function, and an input weight is applied to a control input signal. A series of known signals are iteratively applied as control input inputs, and the cost output is calculated. A phase is taken of the control and plant outputs in response to each of the known signals and combined, thereby allowing effective combinations of the cost function parameters, the input weight, and the predicted future states to be identified.

Abstract: Operation of a multi-variable process involves multidimensional representation of the value (p1-p12) of the process variables (P1-P12) according to individual coordinate axes, and an operational envelope (UB,LB) derived from a group of sets of values for the process and quality variables (P1-P12,Q1-Q2) accumulated from multiple, earlier operations of the process, defines an operating zone for the process and quality variables of the process. If the current value (p7) of any process variable (P7) goes outside the envelope, an envelope (UO,LB) for a different, wider grouping of the stored data-sets is displayed at least for the quality variables (Q1-Q2). A series of nested envelopes to provide stepwise enlargement of the operating zone may be provided, but non-nested envelopes can be used where there is clustering of acceptable values of process variables of the stored data-sets. The changes to control variables to bring the values of dependent variables within a best operating range can be determined.

Abstract: Disclosed is process for producing polyethylene using a slurry loop reactor. The process includes using a mathematical model to predict a plurality of process control parameters based on the desired product properties and reactor characteristics and controlling the process using the predicted process control parameters. Also disclosed is a process controller programmed with the model and a method for optimizing the configuration of a loop reactor using the model.

Abstract: A method of controlling a process driven by a control signal for producing a corresponding output includes producing an error signal as a function of a state of the process and of a reference signal. A control signal is generated as a function of the error signal and of a parameter adjustment signal. The control signal is applied to the process. A derived signal representative of a quantity to be minimized is calculated by processing paired values of the state of the process and the control signal. A correction signal is calculated from a set of several different values of the control signal that minimizes the derived signal. The parameter adjustment signal is calculated by a neural network and fuzzy logic processor from the error signal and the correction signal. The correction signal is periodically calculated by a Quantum Genetic Search Algorithm that results from a merging of a genetic algorithm and a quantum search algorithm.

Abstract: A controller directs the operation of an air pollution control (APC) system having one or more controllable operating parameters and a defined operating limit representing a regulatory limit on an allowed amount of pollutant to be emitted by the APC system. An interface receives data representing a value of a regulatory credit available for emitting less of the pollutant than the regulatory limit on the allowed amount of pollutant. A control processor (i) determines a target set point for each of at least one of the one or more controllable operating parameters, which will maximize the regulatory credits earned, based on the received data and (ii) to directs control of each of the at least one controllable operating parameter based on the determined target set point for that parameter.

Abstract: A system and method for tuning a raw mix proportioning controller used in a cement plant. A fuzzy logic supervisory controller tracks the performance of a cement plant simulator to target set points for attaining a correct mix and composition of raw materials. A genetic algorithm adjusts the fuzzy logic supervisory controller's performance by adjusting its parameters in a sequential order of significance.

Abstract: The present invention provides a method of optimizing a painting process for applying a paint layer on an article. The method comprises defining a functional relationship paint processing parameters and a paint layer property (i.e., the average paint layer thickness) using a neural network. This functional relationship is then used in a paint optimization function that measures a combination of quality control parameters and efficiency parameters. Finally, the paint optimization function is optimized by adjusting the paint processing parameters utilizing the functional relationship formed by the neural network. The invention also provides a system that implements the methods of the invention.

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 neural network controller in parallel with a proportional-plus-integral (PI) feedback controller in a control system. At least one input port of the neural network for receiving an input signal representing a condition of a process is included. A first set of data is obtained that includes a plurality of output values of the neural network obtained during a training period thereof using a plurality of first inputs representing a plurality of conditions of the process. The process/plant condition signals generally define the process/plant, and may include one set-point as well as signals generated using measured systems variables/parameters. In operation, the neural network contributes to an output of the PI controller only upon detection of at least one triggering event, at which time a value of the first set of data corresponding with the condition deviation is added-in thus, contributing to the proportional-plus-integral feedback controller.

Abstract: In tuning a controller for a process in a feedback control system, a method is provided for bringing the system into asymmetric self-excited oscillations for measuring the frequency of the oscillations, average over the period value of the process output signal and average over the period control signal and tuning the controller in dependence of the measurements obtained. An element having a non-linear characteristic is introduced into the system in series with the process and set point signal is applied to excite asymmetric self-excited oscillations in the system. An algorithm and formulas are given for identification of the process model having the form of first order plus dead time transfer function. PI controller settings are given as a function of the dead time/time constant ratio. An apparatus for performing the method is disclosed.

Abstract: In a control method, the first controlled variable is made to coincide with a predetermined controlled variable set point. A relation variable representing the relationship between second controlled variables which are designated in advance from measured second controlled variables different from the first controlled variable so as to maintain a predetermined relationship is calculated. A control actuator is so controlled as to make the calculated relation variable coincide with a predetermined relation variable set point. The difference between the calculated relation variable and a relation variable set point corresponding to the calculated relation variable is calculated. The calculated difference is added to the measured first controlled variable. A manipulated variable is calculated by performing feedback control calculation so as to make the sum coincide with the controlled variable set point. The calculated manipulated variable is output to a corresponding control actuator.

Abstract: A method for determining an output value having a known relationship to an input value with a predicted value includes the step of first training a predictive model with at least one output for a given set of inputs that exist in a finite dataset. Data is then input to the predictive model that is within the set of given inputs. Thereafter, a prediction is made of an output from the predictive model that corresponds to the given input such that a predicted output value will be obtained which will have associated therewith the errors of the predictive model.

Abstract: The system and method disclosed herein allow a user to retrieve data from various process control loops and organize that data in dynamic manner to allow for multiple types of data analysis. A user may associate individual process control loops into groups and analyze the data and impact of select process control loops in those groups. Since the associations of process control loops into groups can be done dynamically, the user is able to easily reconfigure groups (i.e. add or remove process control loops) and redo the analysis. Another feature is the storage of both the data retrieved and the results of the analysis so that comparisons can be performed and reports can be generated.

Abstract: A system and method is provided for monitoring the operating condition of a pump by evaluating fault data encoded in the instantaneous current of the motor driving the pump. The data is converted to a frequency spectrum which is analyzed to create a fault signature having fault attributes relating to various fault conditions associated with the pump. The fault signature is then input to a neural network that operates in conjunction with a preprocessing and post processing module to perform decisions and output those decisions to a user interface. A stand alone module is also provided that includes an adaptive preprocessing module, a one-shot unsupervised neural network and a fuzzy based expert system to provide a decision making module that operates with limited human supervision.

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 present invention provides cavitation detection systems and methods employing a classifier for detecting, diagnosing and/or classifying cavitation in a pumping system. The classifier can be integral to tie cavitation detection system and/or operatively coupled to the cavitation system via a controller, diagnostic device and/or computer. Parameters such as flow, pressure and motor speed arc measured and/or estimated, and then provided to a classifier system Such systems include Bayesian, Fuzzy Set, nonlinear regression, neural networks and other training systems, for example The classifier system provides a signal indicative of the existence and extent of cavitation. An exemplary classification system is presented that delineates cavitation extent into one or more of the following categories: 0 (no cavitation), 1 (incipient cavitation), 2 (medium cavitation), 3 (fill cavitation) and 4 (surging cavitation).

Abstract: The present invention proposes a smart circuit device of a smoke exhauster for cooking. The smart circuit device of the present invention comprises a sensing circuit comprising a temperature sensor and a smoke sensor, a signal processing circuit of temperature sensor, a signal processing circuit of supersonic transducer, a microprocessor control circuit, an output and display circuit, a motor-driving circuit, and a power circuit. The temperature sensor is used to assist the smoke sensor (supersonic transducer). The present invention can detect the variations of the quantity of smoke and temperature in the cooking environment as input parameters to the microprocessor control circuit. The microprocessor control circuit will operate according to the fuzzy control theory to control the motor of the smoke exhauster to operate at a proper rotation speed so as to reduce noise, save energy, and achieve the object of automatic control.

Abstract: A method for analyzing and displaying process states of a technical plant includes enabling simultaneous, coherent assessment and display of relevant process variables of the plant by evaluating relevant process variables with regard to one another through the use of a neural analysis on the basis of self-organizing maps, by making a topology-producing projection of data of the relevant process variables onto a neural map. The current process courses are plotted as trajectories on the map. Evaluation in the sense of a diagnosis can be carried out either visually or in an automated manner.

Abstract: A method for building a model of a system includes first extracting data from a historical database (310). Once the data is extracted, a dataset is then created, which dataset involves the steps of preprocessing the data. This dataset is then utilized to build a model. The model is defined as a plurality of transforms which can be utilized to run an on-line model. This on-line model is interfaced with the historical database such that the variable names associated therewith can be downloaded to the historical database. This historical database can then be interfaced with a control system to either directly operate the plant or to provide an operator an interface to various predicted data about the plant. The building operation will create the transform list and then a configuration step is performed in order to configure the model to interface with the historical database. When the dataset was extracted, it is unknown whether the variables names are still valid.

Abstract: Power industry boiler tube failures are a major cause of utility forced outages in the United States, with approximately 41,000 tube failures occurring every year at a cost of $5 billion a year. Accordingly, early tube leak detection and isolation is highly desirable. Early detection allows scheduling of a repair rather than suffering a forced outage, and significantly increases the chance of preventing damage to adjacent tubes. The instant detection scheme starts with identification of boiler tube leak process variables which are divided into universal sensitive variables, local leak sensitive variables, group leak sensitive variables, and subgroup leak sensitive variables, and which may be automatically be obtained using a data driven approach and a leak sensitivity function. One embodiment uses artificial neural networks (ANN) to learn the map between appropriate leak sensitive variables and the leak behavior.

Abstract: A system and method for providing raw mix proportioning control in a cement plant with a fuzzy logic supervisory controller. A raw mix proportioning controller determines the correct mix and composition of raw materials to be transported to a mixer. The raw mix proportioning controller uses the fuzzy logic supervisory controller to determine the proper mix and composition of raw materials. The fuzzy logic supervisory controller takes targeted set points and the chemical composition of the raw material as inputs and generates the proportions of the raw material to be provided as an output for the next time step.

Abstract: A process control system determines optimal trajectories (input controls) using multiresolutional analysis of acquired data. In contrast to conventional control systems, the present control system does not use a predetermined mathematical model or algorithm to define the process in terms of a plurality of variables. Rather, the present system acquires system data and stores the data in a multiresolutional data structure. A knowledge base is created which can be searched at varying levels of resolution for determining optimal process trajectories. The continual addition of data to the data structure allows for continual top-down refinement of the determined trajectories and bottom-up improvement and updating of the system representation.

Abstract: A sequence of measured quantities is determined for a chemical reactor and a data generator generates a curve in normal coordinates from a respective predetermined normal form that describes a type of critical state. Each normal form is imaged onto the sequence of measured quantities by neural networks whereby a respective neural network is allocated to a data generator. The imaging is optimized by applying parameter optimization methods. The neural network that converges best through use of parameter optimization method describes the critical state that lies closest to the actual state of the chemical reactor.

Abstract: A device and a method use a decision-tree induction analysis to determine a web tension ratio range for which web breaks are less likely to occur within a printing system based on web tension data collected from a plurality of previous runs of the printing system. The device and method also measure two are more web tensions during operation of the printing system, calculate a web tension ratio and compare that calculated web tension ratio with the determined web tension ratio range. When the calculated web tension ratio falls outside of the determined web tension ratio range, the device and method alert a user to the fact that a condition leading to a web break is present and/or control the measured web tensions to drive the calculated web tension ratio to be within the determined web tension ratio range.

Abstract: A circuit for compensating variables in a measurement transmitter. Within the transmitter, a sensor senses a primary process variable such as differential pressure and a converter digitizes the sensed process variable. The sensor senses pressures within a span of pressures values. A memory inside the transmitter stores at least two membership functions, each membership function having a non-zero value over a predetermined region of the process variable span and a substantially zero value over the remainder of the span. The memory also stores a set of compensation formulas, each formula corresponding to a membership function. A selection circuit in the transmitter selects those membership functions which have a non-zero value at the digitized process variable and a correction circuit provides at least one correction value, each correction value calculated from a compensation formula corresponding to a selected membership function.

Abstract: In order to control an apparatus, such as a rolling mill, a control device may use a pre-set operation pattern to generate a pre-set command signal, which is then modified. That first modification may be part of a feedback loop in dependence on the variation of a variable operation device of the apparatus, on a plurality of pre-set signals may be combined by fuzzy logic. Then the relationship between the modified pre-set command signal and the variation of the variable operation device is investigated to generate a compensation signal which is used to modify further the pre-set command signal. In a feedback loop, that further modification may compensate for changes in the operating point of the loop, due to changes in the apparatus being controlled. In a fuzzy logic arrangement, the compensation signal may be a further control pattern developed by the control device itself, which is combined with the pre-set patterns by fuzzy logic. The control device may be in the form of a series of modules.

Abstract: The automated integrated input-output control system apparatus. A versatile industrial control apparatus that can be utilized as a modular unit or integrated into industrial machinery or tools to provide an apparatus and method for programmable control of industrial tools, industrial controls and manufacturing operation processes. The automated integrated input-output control system apparatus includes the following components: a control-power mechanism housing, a sensor, input attachment devices, output attachment device, and a control system.

Abstract: A tool, and the method of making the tool, for process system identification that is based on the general purpose learning capabilities of neural networks. The tool and method can be used for a wide variety of system identification problems with little or no analytic effort. A neural network is trained using a process model to approximate a function which relates process input and output data to process parameter values. Once trained, the network can be used as a system identification tool. In principle, this approach can be used for linear or nonlinear processes, for open or closed loop identification, and for identifying any or all process parameters.