Raytheon Technologies Corporation

Carrier Corporation

Hamilton Sundstrand Corporation

Vivek Venugopalan

Michael J Giering

Kishore K Reddy

David L Lincoln

Soumik Sarkar

Michael J Birnkrant

Marcin Piech

Peter R Harris

Hui Fang

Parag M Kshirsagar

Catherine Thibaud

Jie Xi

Beata I Wawrzyniak

Amit Surana

Jose-Rodrigo Castillo-Garza

Soumalya Sarkar

Madhusudana Shashanka

An example SPR detection system includes a first prism having a first surface adjacent to a first metal layer exposed to a sample gas, and a second prism having a second surface adjacent to a second metal layer exposed to a reference gas. At least one light source is configured to provide respective beams to the first and second surfaces, where each of the beams causes SPR of a respective one of the metal layers. At least one photodetector is configured to measure a reflection property of reflections of the respective beams from the metal layers during the SPR. A controller is configured to determine whether a target gas is present in the sample gas based on a known composition of the reference gas and at least one of an electrical property of the first and second metal layers during the SPR and the reflection property of the metal layers.

Surface plasmon resonance detection system

A method includes fusing multi-modal sensor data from a plurality of sensors having different modalities. At least one region of interest is detected in the multi-modal sensor data. One or more patches of interest are detected in the multi-modal sensor data based on detecting the at least one region of interest. A model that uses a deep convolutional neural network is applied to the one or more patches of interest. Post-processing of a result of applying the model is performed to produce a post-processing result for the one or more patches of interest. A perception indication of the post-processing result is output.

Multi-modal sensor data fusion for perception systems

A method includes converting time-series data from a plurality of prognostic and health monitoring (PHM) sensors into frequency domain data. One or more portions of the frequency domain data are labeled as indicative of one or more target modes to form labeled target data. A model including a deep neural network is applied to the labeled target data. A result of applying the model is classified as one or more discretized PHM training indicators associated with the one or more target modes. The one or more discretized PHM training indicators are output.

Sensor data fusion for prognostics and health monitoring

An example method of designing an electrical machine includes providing at least one goal and at least one design constraint for a desired electrical machine to a deep neural network that comprises a plurality of nodes representing a plurality of prior electrical machine designs, the plurality of nodes connected by weights, each weight representing a correlation strength between two nodes. A proposed design is generated from the deep neural network for an electrical machine based on the goal(s) and design constraint(s). A plurality of the weights are adjusted based on a reward that rates at least one aspect of the proposed design. The proposed design is modified using the deep neural network after the weight adjustment. The adjusting and modifying are iteratively repeated to generate subsequent iterations of the proposed design, each subsequent iteration based on the reward from a preceding iteration. A system for designing electrical machines is also disclosed.

Method and system for designing electrical machines using reinforcement learning

A system and method of detecting smoke including establishing a baseline measurement for each of at least three overlapping sensing volumes; comparing a measured reading within each of the at least three sensing volumes and the baseline measurements to determine whether the measured reading is within a sensing threshold, and annunciating a warning signal if the difference is outside the sensing threshold.

Smoke detection methodology

Data indicative of a plurality of observations of an environment are received at a control system. Machine learning using deep reinforcement learning is applied to determine an action based on the observations. The deep reinforcement learning applies a convolutional neural network or a deep auto encoder to the observations and applies a training set to locate one or more regions having a higher reward. The action is applied to the environment. A reward token indicative of alignment between the action and a desired result is received. A policy parameter of the control system is updated based on the reward token. The updated policy parameter is applied to determine a subsequent action responsive to a subsequent observation.

Control systems using deep reinforcement learning

A method includes detecting at least one region of interest in a frame of image data. One or more patches of interest are detected in the frame of image data based on detecting the at least one region of interest. A model including a deep convolutional neural network is applied to the one or more patches of interest. Post-processing of a result of applying the model is performed to produce a post-processing result for the one or more patches of interest. A visual indication of a classification of defects in a structure is output based on the result of the post-processing.

Growing community of inventors

Bridgewater, NJ, United States of America

Vivek Venugopalan