Sas Institute Inc.

Anya Mary McGuirk

Deovrat Vijay Kakde

Yuwei Liao

Byron Davis Biggs

Arin Chaudhuri

Haoyu Wang

Vincent L Deters

Sergiy Peredriy

Allen Joseph Langlois

A computing device accesses a machine learning model trained on training data of first bonding operations (e.g., a ball and/or stitch bond). The first bonding operations comprise operations to bond a first set of multiple wires to a first set of surfaces. The machine learning model is trained by supervised learning. The device receives input data indicating process data generated from measurements of second bonding operations. The second bonding operations comprise operations to bond a second set of multiple wires to a second set of surfaces. The device weights the input data according to the machine learning model. The device generates an anomaly predictor indicating a risk for an anomaly occurrence in the second bonding operations based on weighting the input data according to the machine learning model. The device outputs the anomaly predictor to control the second bonding operations.

Quality prediction using process data

A computing system determines if an event has occurred. A first window is defined that includes a subset of a plurality of observation vectors modeled as an output of an autoregressive causal system. A magnitude adjustment vector is computed from a mean computed for a matrix of magnitude values that includes a column for each window of a plurality of windows. The first window is stored in a next column of the matrix of magnitude values. Each cell of the matrix of magnitude values includes an estimated power spectrum value for a respective window and a respective frequency. A second matrix of magnitude values is updated using the magnitude adjustment vector. Each cell of the second matrix of magnitude values includes an adjusted power spectrum value for the respective window and the respective frequency. A peak is detected from the next column of the second matrix of magnitude values.

Data monitoring system

A computing system detects an event. (A) A frequency spectrum is computed using a Fourier transform. (B) (A) is repeated a predefined plurality of times with successive windows of observation vectors. Each window of the successive windows includes a subset of the observation vectors. The successive windows include successive subsets selected sequentially in time. (C) An average frequency spectrum is computed from the frequency spectrum computed the predefined plurality of times. (D) A plurality of segmented average frequency spectra is computed from the computed average frequency spectrum. Each segmented average frequency spectrum of the plurality of segmented average frequency spectra is computed for a frequency band of a plurality of predefined frequency bands. (E) When an event has occurred is determined based on the computed plurality of segmented average frequency spectra and a predefined threshold value.

Event monitoring system using frequency segments

A frequency spectrum is computed using a Fourier transform a predefined plurality of times with successive windows of observation vectors, wherein each window of the successive windows includes a subset of observation vectors, wherein the successive windows include successive subsets selected sequentially in time. An average frequency spectrum is computed. A plurality of segmented average frequency spectra is computed, wherein each segmented average frequency spectrum is computed for a frequency band of predefined frequency bands. A distance value is computed using a trained support vector data description model with the segmented average frequency spectra. When an event has occurred is determined based on a comparison between the distance value and a predefined threshold. A vector is computed from the segmented average frequency spectra using t-stochastic neighbor embedding. When an event has occurred based on the comparison, an event indicator is presented on a graph using the vector.

Visualization to support event monitoring system

A computing system detects an event. (A) A frequency spectrum of observation vectors is computed using a Fourier transform. Each observation vector includes a sensor value. (B) (A) is repeated a predefined plurality of times with successive windows of the observation vectors. Each window of the successive windows includes a subset of the observation vectors. The successive windows include successive subsets selected sequentially in time. (C) An average frequency spectrum is computed from the frequency spectrum computed the predefined plurality of times. (D) A predefined noise filter is applied to the average frequency spectrum to define a filtered frequency spectrum. (E) A distance value is computed between the filtered frequency spectrum and a predefined reference spectrum using a distance computation function. (F) When an event has occurred is determined based on a comparison between the computed distance value and a predefined distance threshold.

Event monitoring system

A computing device identifies outliers. Support vectors, Lagrange constants, a center threshold value, an upper control limit value, and a lower control limit value are received that define a normal operating condition of a system. The center threshold value, the upper control limit value, and the lower control limit value are computed from the vectors and the Lagrange constants. A first plurality of observation vectors is received for a predefined window length. A window threshold value and a window center vector are computed. A window distance value is computed between the window center vector and the support vectors. Based on comparisons between the computed values and the received values, the first plurality of observation vectors is identified as an outlier relative to the normal operating condition of the system. When the first plurality of observation vectors are identified as the outlier, an alert is output.

Growing community of inventors

Holly Springs, NC, United States of America

Anya Mary McGuirk