초록 ▼

A system and method for monitoring an apparatus or process asset including partitioning an unpartitioned training data set into a plurality of training data subsets each having an operating mode associated thereto; creating a process model comprised of a plurality of process submodels each trained a

A system and method for monitoring an apparatus or process asset including partitioning an unpartitioned training data set into a plurality of training data subsets each having an operating mode associated thereto; creating a process model comprised of a plurality of process submodels each trained as a function of at least one of the training data subsets; acquiring a current set of observed signal data values from the asset; determining an operating mode of the asset for the current set of observed signal data values; selecting a process submodel from the process model as a function of the determined operating mode of the asset; calculating a current set of estimated signal data values from the selected process submodel for the determined operating mode; and outputting the calculated current set of estimated signal data values for providing asset surveillance and/or control.

대표청구항 ▼

A system and method for monitoring an apparatus or process asset including partitioning an unpartitioned training data set into a plurality of training data subsets each having an operating mode associated thereto; creating a process model comprised of a plurality of process submodels each trained a

A system and method for monitoring an apparatus or process asset including partitioning an unpartitioned training data set into a plurality of training data subsets each having an operating mode associated thereto; creating a process model comprised of a plurality of process submodels each trained as a function of at least one of the training data subsets; acquiring a current set of observed signal data values from the asset; determining an operating mode of the asset for the current set of observed signal data values; selecting a process submodel from the process model as a function of the determined operating mode of the asset; calculating a current set of estimated signal data values from the selected process submodel for the determined operating mode; and outputting the calculated current set of estimated signal data values for providing asset surveillance and/or control. 1. A method of making a judgment on emotional positivity or negativity of a person, comprising the steps of: obtaining asymmetry ratio between the brain waves of the left and right cerebral hemisphere measured in a given unit time by means of electrodes attached to the left and right side of the scalp; calculating asymmetry ratio versus time at each frequency of said measured brain waves if the time taken for measuring said brain waves exceeds a given time interval; calculating a slope of the asymmetry ratio of the previous step with time; and entering a sign of said slope into an artificial neural network to make a judgment on said emotional positivist or negativity. 2. A method as defined in claim 1, wherein the first step includes further steps of: measuring said brain waves from said electrodes; subjecting said brain waves to Fourier transformation; and obtaining said asymmetry ratio between the left and right brain waves based on the previous Fourier transformation. 3. A method as defined in claim 1, wherein the second step includes further steps of: performing the first step if the time taken for measuring said brain waves does not exceed said given time interval; and calculating asymmetry ratio versus time at each frequency of said measured brain waves if the time taken for measuring said brain waves exceeds a given time interval. 4. A method as defined in claim 2, wherein said electrodes are two respectively attached to the left and right sides of the scalp with the left side one positioned at F3 and the right side one at F4 according to 10-20 international electrode system. 5. A method as defined in one of the claims 1 to 4, wherein the third step includes further steps of: smoothing out said asymmetry ratio versus time; and calculating an increase and a decrease of the smoothed asymmetry ratio with time. 6. A method as defined in claim 5, wherein the step of smoothing out said asymmetry ratio is to reduce fluctuations for a short time little concerned with emotional response. 7. A method as defined in claim 5, wherein said an increase and a decrease is the slope of said asymmetry ratio with time or the positive or negative sign of said slope. 8. A computer storage medium for storing a computer program executed by a computer, wherein said computer program is composed of performing the functions of obtaining asymmetry ratio between the brain waves of the left and right cerebral hemisphere measured in a given unit time by means of electrodes attached to the left and right side of the scalp; calculating asymmetry ratio versus time at each frequency of said measured brain waves if the time taken for measuring said brain waves exceeds a given time interval; calculating an increase and a decrease of the asymmetry ratio of the previous step with time; and entering said an increase and a decrease into an artificial neural network to make a judgment on said emotional positivity or negativity.