International Business Machines Corporation

Utopus Insights, Inc.

Other

Dung Tien Phan

Jinjun Xiong

Soumyadip Ghosh

Gary S Ditlow

Jayant R Kalagnanam

Lam Nguyen

Arun Kwangil Iyengar

Ramachandran Muralidhar

Robert J Baseman

Dhavalkumar C Patel

Chandrasekhara K Reddy

Pavankumar Murali

Nam H Nguyen

Xu Sun

Fateh Ali Tipu

Hongsheng Liu

Chai Wah Wu

Jeffrey Owen Kephart

Tsuyoshi Ide

David Shing-Ki Kung

Mayank Sharma

Haoran Zhu

Techniques for model evaluation and selection are provided. A plurality of models trained to generate predictions at each of a plurality of intervals is received, and a plurality of model ensembles, each specifying one or more of the plurality of models for each of the plurality of intervals, is generated. A test data set is received, where the test data set includes values for at least a first interval of the plurality of intervals and does not include values for at least a second interval of the plurality of intervals. A first model ensemble, of the plurality of model ensembles, is selected based on processing the test data set using each of the plurality of model ensembles.

Determining and selecting prediction models over multiple points in time using test data

A method for process control using predictive long short term memory includes obtaining historical post-process measurements taken on prior products of the manufacturing process; obtaining historical in-process measurements taken on prior workpieces during the manufacturing process; training a neural network to predict each of the historical post-process measurements, in response to the corresponding historical in-process measurements and preceding historical post-process measurements; obtaining present in-process measurements on a present workpiece during the manufacturing process; predicting a future post-process measurement for the present workpiece, by providing the present in-process measurements and the historical post-process measurements as inputs to the neural network; and adjusting at least one controllable variable of the manufacturing process in response to the prediction of the future post-process measurement.

Tool control using multistage LSTM for predicting on-wafer measurements

Techniques for generating model ensembles are provided. A plurality of models trained to generate predictions at each of a plurality of intervals is received. A respective prediction accuracy of each respective model of the plurality of models is determined for a first interval of the plurality of intervals by processing labeled evaluation data using the respective model. Additionally, a model ensemble specifying one or more of the plurality of models for each of the plurality of intervals is generated, comprising selecting, for the first interval, a first model of the plurality of models based on (i) the respective prediction accuracies and (ii) at least one non-error metric.

Determining and selecting prediction models over multiple points in time

A method of improving at least one of quality and yield of a physical process comprises: obtaining values, from respective performances of the physical process, for a plurality of variables associated with the physical process; determining at least one Gaussian mixture model (GMM) representing the values for the variables for the performances of the physical process; based at least in part on the at least one GMM, computing at least one anomaly score for at least one of the variables for at least one of the performances of the physical process; based on the at least one anomaly score, identifying the at least one of the performances of the physical process as an outlier; and, based at least in part on the outlier identification, modifying the at least one of the variables for one or more subsequent performances of the physical process.

Model management for non-stationary systems

In an approach to hyperparameter optimization, one or more computer processors express a hyperparameter tuning process of a model based on a type of model, one or more dimensions of a training dataset, associated loss function of the model, and associated computational constraints of the model, comprising: identifying a set of optimal hyper-rectangles based a calculated local variability and a calculated best function value; calculating a point as a representative for each identified potentially optimal hyper-rectangle by locally searching over the identified set of potentially optimal hyper-rectangles; dividing one or more hyper-rectangles in the identified set of optimal hyper-rectangles into a plurality of smaller hyper-rectangles based on each calculated point; and calculating one or more optimal hyperparameters utilizing a globally converged hyper-rectangle from the plurality of smaller hyper-rectangles. The one or more computer processors classify one or more unknown datapoints utilizing the model associated with tuned hyperparameters.

Tuning classification hyperparameters

An exemplary method includes solving on a computing system an optimal power flow formulation for a plurality of generators in a power system. The solving includes computing using multi-threaded parallelism a plurality of constraints for the formulation, computing using multi-threaded parallelism a plurality of Jacobian functions of the constraints, and computing using multi-threaded parallelism a Hessian of Lagrangian functions. The method further includes outputting results of the solving, wherein the results comprise values of generation levels for the plurality of generators. Apparatus and program products are also disclosed.

Parallel technique for computing problem functions in solving optimal power flow

Aspects of the invention include an optimal interpretable decision tree using integer linear programming techniques. A non-limiting example computer-implemented method includes receiving, using a processor, a plurality of data inputs from a process and selecting, using the processor, a data subset from the plurality of data inputs by solving linear programming to obtain a solution. The method builds and optimizes, using the processor, an optimal decision tree based on the data subset and alerts, using the processor, a user when a prediction of the optimal decision tree is greater than a threshold value.

Optimal interpretable decision trees using integer linear programming techniques

Aspects of the invention include implemented method includes selecting an optimization algorithm for the control system of a processing plant based on whether the control system is guided by a linear-based predictive model or a non-linear-based predictive model, in which a gradient is available. Calculating set-point variables using the optimization algorithm. Predicting an output based on the calculated set-point variables. Comparing an actual output at the processing plant to the predicted output. Suspending a physical process at the processing plant in response to the actual output being a threshold value apart from the predicted output.

Site-wide operations management optimization for manufacturing and processing control

A method for operating a power generating facility connected to a power distribution grid having an uncertain power generation condition includes predicting a probabilistic power flow forecast in a transmission line of the power distribution grid for a period of time, wherein the transmission line is electrically coupled to the power generating facility, predicting, using the probabilistic power flow forecast, a probability of congestion over the transmission line of the power distribution grid during the period of time, generating a mitigation plan, including a load adjustment on the transmission line, using the probability of congestion predicted over the transmission line and a thermal limit constraint of the transmission line, wherein the mitigation plan balances load adjustment and an overlimit line capacity on the transmission line, and controlling the power generating facility, using the mitigation plan, to achieve load modification and mitigate the probability of congestion predicted in the transmission line.

Congestion control in electric power system under load and uncertainty

A method for determining power output levels of a plurality of nodes in an electric power system includes receiving, at a first node of the plurality of nodes, voltage information and multipliers of all neighboring nodes of the first node within the electric power system, determining, by the first node, a local power generation and a local voltage using the voltage information and the multipliers of the neighboring nodes and distributing the local power generation and the local voltage to the neighboring nodes, determining, by the first node, an estimated voltage of each of the neighboring nodes and distributing the estimated voltage to each of the neighboring nodes, and updating, by the first node, a local multiplier using the voltage information received from the neighboring nodes and the estimated voltage of each of the neighboring nodes determined by the node.

Distributed control of electric power grids

A method for operating a power generating facility connected to a power distribution grid having an uncertain power generation condition includes predicting a probabilistic power flow forecast in a transmission line of the power distribution grid for a period of time, wherein the transmission line is electrically coupled to the power generating facility, predicting, using the probabilistic power flow forecast, a probability of congestion over the transmission line of the power distribution grid during the period of time, generating a mitigation plan, including a load adjustment on the transmission line, using the probability of congestion predicted over the transmission line and a thermal limit constraint of the transmission line, wherein the mitigation plan balances the load adjustment and an overlimit line capacity on the transmission line, and controlling the power generating facility, using the mitigation plan, to achieve the load modification and mitigate the probability of congestion predicted in the transmission line.

A method includes capturing multivariate time-series data comprising two or more data sets from a system captured over a past time period and a present time period, applying at least two sliding time windows to the multivariate time-series data in determining respective data matrices, computing an orthonormal matrix for each of the data matrices, wherein the orthonormal matrix is a signature of fluctuation patterns of a respective data matrix, computing a difference between at least two of the data sets in the past and the present time periods through the orthonormal matrices, and detecting a fault in at least one of the systems by comparing the difference to a threshold.

Change detection using directional statistics

A method includes determining whether transformer phases should be permuted. The method includes, responsive to a determination that the transformer phases should be permuted, permuting the transformer phases, based on historical aging information of transformer input phases, to cause transformer input phases with higher ages to be connected to transformer output phases with lower output loads and transformer input phases with lower ages to be connected to transformer output phases with higher output loads. Multiple apparatus and program products are also disclosed.

Growing community of inventors

Pleasantville, NY, United States of America

Dung Tien Phan