Abstract: Disclosed herein are a system and method for trend prediction of signals in a time series using a Markov model. The method includes receiving a plurality of data series and input parameters, where the input parameters include a time step parameter, preprocessing the plurality of data series according to the input parameters, to form binned and classified data series, and processing the binned and classified data series. The processing includes initializing a Markov model for trend prediction, and training the Markov model for trend prediction of the binned and classified data series to form a trained Markov model. The method further includes deploying the trained Markov model for trend prediction, including outputting trend predictions. The method develops an architecture for the Markov model from the data series and the input parameters, and disposes the Markov model, having the architecture, for trend prediction.

Abstract: A luminous signaling device with a heat dissipation system is provided. The heat dissipation system is configured to set up a natural convection current flow to remove air heated by the LED emitter and enable cooler ambient air to flow towards the LED emitter. The signaling device includes a generally tubular element having a hollow inner cavity and a first slot through the tubular element. An LED emitter is operatively connected to the tubular element, with the LED emitter being operable to emit light in response to power. The signaling device includes an electronic driver circuit configured to provide an adjustable current to the LED emitter. Wires connecting the circuit and the LED emitter run through the first slot and the inner cavity of the tubular element.

Abstract: Anomaly prediction of battery parasitic load includes processing input data related to a state of charge for a battery and a durational factor utilizing a machine learning algorithm and generating a predicted start-up state of charge. Warnings are issued if the predicted start-up state of charge drops below a threshold level within an operational time.

Abstract: A system and method for determining events in a system or process, such as predicting fault events. The method includes providing data from the process, pre-processing data and converting the data to one or more temporal spike trains having spike amplitudes and a spike train length. The spike trains are provided to a dynamical neural network operating as a liquid state machine that includes a plurality of neurons that analyze the spike trains. The dynamical neural network is trained by known data to identify events in the spike train, where the dynamical neural network then analyzes new data to identify events. Signals from the dynamical neural network are then provided to a readout network that decodes the states and predicts the future events.

Abstract: A method is provided for determining when to provide a refueling notification to a driver of a vehicle. A refueling behavior is determined for refueling the vehicle. The refueling behavior is associated at least in part to an amount of fuel customarily remaining in the vehicle when the vehicle is customarily refueled. A remaining amount of fuel in the vehicle and a fuel economy of the vehicle are determined. A distance the vehicle will travel to a next driving destination is estimated. An amount of fuel that will be used to travel to the next driving destination is estimated based on the estimated distance the vehicle will travel to the next driving destination and the fuel economy. A determination is made whether the amount of fuel that will be remaining in the vehicle after the vehicle travels to the next driving destination is less than the amount of a fuel customarily remaining in the vehicle when the vehicle is refueled.

Abstract: Disclosed herein are a system, method and apparatus for reporting, making alerts and predicting fault codes generated by machines in a line. Historical fault code data is received and filtered according to particular criteria to generate filtered fault code data. Classification of the filtered fault code data into physical groups and into logical groups is followed by sorting the groups to produce fault trend data. Processing the fault trend data with a plurality of analyzers generates output including reports, alerts, and predictions of future fault code occurrences.

Abstract: A method is provided for managing information on a plant floor, and includes recording a definition file, such as an extended markup language (XML) schema, in a source device, and generating a plant floor event (PFE) message as a bit array or string array. The PFE message transfers from the source device to a host device or other appliance. The method then includes executing at least one action in response to the PFE message. A system is also provided for managing information on a plant floor, and includes a PLC that generates a PFE message as a bit or string array. The system includes an alarm database, and automatically propagates the PFE message upward from the PLC to a host device, such as a server, a database, or a display device, and automatically executes an action in response to the PFE message.

Abstract: A luminous signaling device with a heat dissipation system is provided. The heat dissipation system is configured to set up a natural convection current flow to remove air heated by the LED emitter and enable cooler ambient air to flow towards the LED emitter. The signaling device includes a generally tubular element having a hollow inner cavity and a first slot through the tubular element. An LED emitter is operatively connected to the tubular element, with the LED emitter being operable to emit light in response to power. The signaling device includes an electronic driver circuit configured to provide an adjustable current to the LED emitter. Wires connecting the circuit and the LED emitter run through the first slot and the inner cavity of the tubular element.

Abstract: A system and method for data analysis are disclosed. Data analysis may include a step of filtering the data to produce filtered data. The method may include processing a plurality of prediction algorithms to produce prediction values, the prediction values having associated historical and expected prediction confidence intervals. The method may also include evaluating performance of the prediction algorithms to generate performance indexes, the performance indexes having associated index confidence intervals. The method may also include generating relevance values of the prediction algorithms based on the performance indexes, and index confidence intervals. The method may further include applying the relevance values and prediction confidence intervals to determine how to combine prediction values, and applying multivariable data fusion to combine the prediction values.

Abstract: A system, method, and apparatus for signal characterization, estimation, and prediction comprising an integrated search algorithm that cooperatively optimizes several data mining sub-tasks, the integrated search algorithm including a machine learning model, and the method comprising processing the data for data embedding, data embedding the processed data for searching for patterns, extracting time and frequency patterns, and training the model to represent learned patterns for signal characterization, estimation, and prediction.

Abstract: A system and method for providing an integrated virtual and real emulation environment for a manufacturing process to provide component compatibility testing and system performance prediction. In one embodiment, a real manufacturing system includes one or more real components that are controlled by a programmable logic controller. The real component can be replaced with a virtual component to determine whether it is compatible in the process, where the programmable controller sends signals to and receive signals from the virtual component as if it were the real component. For system performance prediction, a virtual manufacturing process is provided that includes virtual components where the virtual process is controlled by a programmable logic control as if it were a real process to determine the performance of a real system using the virtual process.

Abstract: An integrated real and virtual manufacturing automation system that employs a programmable logic controller that controls part flow between a real machine in the real world part of the system and a virtual machine in the virtual world part of the system using virtually coupled sensors and actuators. A real world sensor senses the position of the real world machine and a real world actuator actuates the real world machine. Likewise, a virtual world sensor senses the position of the virtual world machine and a virtual world actuator actuates the virtual world machine. An interface device transfers signals between the virtual world part of the system and the real world part of the system, and an input/output device processes signals sent to the programmable logic controller and signals sent from the programmable logic controller.

Abstract: A system and method for integrating a real and virtual manufacturing automation system that provides a part flow between a virtual world part of the system including virtual world components and a real world part of the system including real world components. The system includes an interface device for transferring signals between the virtual world part of the system and the real world part of the system, a programmable logic controller for controlling the operation of the system and an input/output device that processes signals sent to the programmable logic controller and signals sent from the programmable logic controller. The programmable logic controller controls the operation of the system where sensors and actuators coupled between the virtual world part of the system and the real world part of the system are physically coupled.

Abstract: Anomaly prediction of battery parasitic load includes processing input data related to a state of charge for a battery and a durational factor utilizing a machine learning algorithm and generating a predicted start-up state of charge. Warnings are issued if the predicted start-up state of charge drops below a threshold level within an operational time.

Abstract: A modular display device includes a housing module having a plurality of open face compartments and a back wall having access openings therein registering with each of the open face compartments. A circuit board is mounted on the back wall of the housing module and carries a plurality of light-emitting diodes mounted thereon and being energizable by the circuit board to shine through the access openings and light up the compartment. A lens is provided for each of the compartments and attached to the housing module to close the open face compartment. Each lens has an alphanumeric or other message thereon which will be backlit by the light-emitting diodes so that information is displayed. A plurality of these housing modules are mounted together side by side in order to form a display board of scalable and customizable size depending upon the number of information messages to be displayed and signaled.

Abstract: A method and system of automatically curve fit data series to generate data signal characterization and prediction is disclosed. The method includes receiving input data including a plurality of data series and set of input parameters. The method also includes preprocessing the data series to generate preprocessed data according to a plurality of input parameters. The method further includes performing sorting and prioritization of the data series and curve fitting by a plurality of models and search and optimization algorithms on the smoothed or raw data series according to a plurality of input parameters to generate text and graphic output, and storing text and graphic output. The system includes modules for carrying out steps of the method.

Abstract: A system and method for data analysis are disclosed. Data analysis may include a step of filtering the data to produce filtered data. The method may include processing a plurality of prediction algorithms to produce prediction values, the prediction values having associated historical and expected prediction confidence intervals. The method may also include evaluating performance of the prediction algorithms to generate performance indexes, the performance indexes having associated index confidence intervals. The method may also include generating relevance values of the prediction algorithms based on the performance indexes, and index confidence intervals. The method may further include applying the relevance values and prediction confidence intervals to determine how to combine prediction values, and applying multivariable data fusion to combine the prediction values.

Abstract: A method for characterizing, detecting and predicting an event of interest, a target event, based on temporal patterns useful for predicting a probable occurrence of the target event is disclosed. Measurable events and their features are defined and quantized into event classes. Temporal series of the event classes are analyzed, and preliminary prediction rules established by analyzing temporal patterns of the event classes that precede an occurrence of the target event using a sliding time window. The quality of the preliminary prediction rules is evaluated and parameters thereof are optimized by using a defined fitness function, thereby defining finalized prediction rules. The finalized prediction rules are then made available for application on temporal series of the event classes to forecast a probable occurrence of the target event.

Abstract: Systems and methods for implementing hybrid, closed-loop control that generates control values for processes defined by a limited number of function evaluations and large amounts of process and measurement noise. The described control system is applied to a stencil printing process for applying solder paste to an electronic medium such as a printed circuit board or semiconductor wafer. The control system is defined by a hybrid approach. A first, coarse algorithm is used to rapidly produce the value of a stencil printer control value resulting in a solder paste deposit having a volume within predetermined acceptable limits. After the coarse algorithm no longer produces solder paste deposits closer to a desired volume, a second, more refined estimator is used to fine tune the process. An additional transitional algorithm may be added between the coarse algorithm and refined estimator.

Abstract: Systems and methods for implementing hybrid, closed-loop control that generates control values for processes defined by a limited number of function evaluations and large amounts of process and measurement noise. The described control system is applied to a stencil printing process for applying solder paste to an electronic medium such as a printed circuit board or semiconductor wafer. The control system is defined by a hybrid approach. A first, coarse algorithm is used to rapidly produce the value of a stencil printer control value resulting in a solder paste deposit having a volume within predetermined acceptable limits. After the coarse algorithm no longer produces solder paste deposits closer to a desired volume, a second, more refined estimator is used to fine tune the process. An additional transitional algorithm may be added between the coarse algorithm and refined estimator.