Abstract: Embodiments of the present disclosure generally relate to aircraft engines and, more particularly, to detecting defects in aircraft engines using visual neuromorphic sensors. In some embodiments, an event associated with a portion of an aircraft engine may be identified based on a change on a visual data characteristic from a visual neuromorphic sensor. In response to identifying the event associated with the portion of the aircraft engine, synchronous data from a synchronous data collection sensor coupled to the aircraft engine may be retrieved for a predetermined period of time, and a defect associated with the aircraft engine detected based on the identified event and the synchronous data. Other embodiments may be disclosed or claimed.

Abstract: Systems and methods are provided for performing image processing. An exemplary method includes: receiving neuromorphic camera data from at least one neuromorphic camera; producing, using the neuromorphic camera data, a plurality of unaligned event data, where the unaligned event data are unaligned in time; aligning the unaligned event data in time producing aligned event data; generating, using a model and the aligned event data, a plurality of aligned event volumes; and aggregating the aligned event volumes to produce an image.

Abstract: Embodiments of the present disclosure generally relate to aircraft engines and, more particularly to data acquisition for aircraft engines using neuromorphic sensors. In some embodiments, an event associated with the aircraft engine may be identified based on a change in a data characteristic measured from a neuromorphic sensor and, in response to identifying the event associated with the aircraft engine, at least one other sensor coupled to the aircraft engine may be activated. Other embodiments may be disclosed or claimed.

Abstract: Embodiments of the present disclosure generally relate to aircraft engines and, more particularly to data acquisition for aircraft engines using thermal neuromorphic sensors. In some embodiments, an event associated with the aircraft engine may be identified based on a change in a thermal data characteristic measured from a thermal neuromorphic sensor. In response to identifying the event associated with the aircraft engine, one or more other sensors coupled to the aircraft engine may be activated and data received from the activated sensors stored in memory. Other embodiments may be disclosed or claimed.

Abstract: Embodiments of the present disclosure generally relate to aircraft engines and, more particularly, to detecting material failures associated with aircraft engines using neuromorphic sensors. In some embodiments, an event associated with a material failure in the portion of an aircraft engine is identified based on a change in a data characteristic from a neuromorphic sensor. In response to identifying the event associated with the material failure of the aircraft engine, at least one other sensor coupled to the aircraft engine is activated, where the activated sensor(s) is configured to collect data associated with the aircraft engine synchronously. Other embodiments may be disclosed or claimed.

Abstract: Embodiments of the present disclosure generally relate to aircraft engines and, more particularly, to aircraft engine inlet monitoring using neuromorphic sensors. In some embodiments, an event associated with debris in the inlet of an aircraft engine may be identified based on a change in a visual data characteristic from a visual neuromorphic sensor. In response to identifying the event, one or more other neuromorphic sensors coupled to the aircraft may be activated. Other embodiments may be disclosed or claimed.

Abstract: The present disclosure provides for the generation of microstructural images of components (e.g., titanium alloys) using machine learning frameworks. More particularly, the present disclosure provides for the generation of microstructural images of components (e.g., titanium alloys) as a function of heat treatment conditions using conditional generative adversarial networks. The present disclosure advantageously provides ways to accelerate component designs (e.g., titanium alloy designs) by developing generative models which can produce synthetic yet realistic microstructures conditioned on heat treatment conditions.

Abstract: A laser powder bed fusion (LPBF) system includes a build plate, a build station piston configured to adjust the height of the build plate as a part is built on top of the build plate, and a powder chamber configured to contain loose build powder, wherein the powder chamber surrounds the build plate. The LPBF system also includes a laser system configured to direct a laser beam onto the loose build powder to form a melt pool, which forms a layer of the part as the melt pool solidifies. As each layer of the part is formed, the build station piston lowers the build plate and part by a predetermined distance corresponding to a desired thickness of a next layer of the part.

Abstract: A neuromorphic foreign object debris (FOD) detection system includes a FOD processing system and a neuromorphic sensor. The FOD processing system includes a FOD controller including a trained artificial intelligence machine learning (AIML) model representing an area of interest. The neuromorphic sensor has a field of view (FOV) containing the area of interest and is configured to output pixel data in response to FOD appearing in the FOV. The FOD controller detects the FOD is present in the area of interest in response to receiving the pixel data, and generates an alert signal indicating the presence of the FOD.

Abstract: Systems and methods are provided for performing image processing. An exemplary method includes: receiving neuromorphic camera data from at least one neuromorphic camera; producing, using the neuromorphic camera data, a plurality of unaligned event data, where the unaligned event data are unaligned in time; aligning the unaligned event data in time producing aligned event data; generating, using a model and the aligned event data, a plurality of aligned event volumes; and aggregating the aligned event volumes to produce an image.

Abstract: Embodiments regard implementing operations that provide a virtual sensor. A method includes receiving, from a neuromorphic sensor, a time series of delta images, receiving auxiliary data indicating (i) an orientation, location, direction, or speed of the neuromorphic sensor, or (ii) metadata of the neuromorphic sensor, the auxiliary data associated with about a same time as the time series of images, operating, based on an image of the time series of delta images and auxiliary data of the auxiliary data associated with the image as occurring at about a same time, a first machine learning (ML) model resulting in a low-resolution image, and operating, based on the low-resolution image, a second ML model resulting in a high-resolution image, the high-resolution image of a type different than that produced by the neuromorphic sensor.

Abstract: A wearable device includes neuromorphic event cameras. A processor receives data streams from the event cameras and makes application specific predictions/determinations. The event cameras may be outward facing to make determinations about the environment or a specific task, inward facing to monitor the state of the user, or both. The processor may be configured as a trained neural network to receive the data streams and produce output based on predefined sets of training data. Sensors other than event cameras may supply data to the processor and neural network, including other cameras via a feature recognition process.

Abstract: Systems and methods for implementing neuromorphic sensor technology in aircraft cabin environments including smart devices to improve and/or expand the use and functionality of the smart devices. In some embodiments, neuromorphic sensors and smart devices are communicatively coupled to a controller operative to analyze object movements and instruct smart devices to operate according to preprogrammed instructions. Non-limiting examples include detecting passenger movements in passenger seating areas and lavatories associated with smart devices, detecting movements of smart devices configured to traverse aircraft aisles, etc. The neuromorphic sensors are incapable of capturing visually recognizable passenger identities and therefore satisfy privacy concerns.

Abstract: 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.

Abstract: A method of monitoring a conveyance apparatus within a conveyance system including: detecting a vibratory signature at a primary location during a commissioning phase using a primary sensing apparatus located at the primary location; detecting a vibratory signature at a secondary location during the commissioning phase using a secondary sensing apparatus located at the secondary location; determining a transfer algorithm in response to the vibratory signature at the primary location during the commissioning phase and the vibratory signature at the secondary location during the commissioning phase; detecting a vibratory signature at the primary location during a normal operation phase using the primary sensing apparatus located at the primary location; and converting the vibratory signature at the primary location during the normal operation phase to a vibratory signature at the secondary location during the normal operation phase using the transfer algorithm.

Abstract: According to an embodiment of the present disclosure, a method of training a machine learning model is provided. Input data is received from at least one remote device. A classifier is evaluated by determining a classification accuracy of the input data. A training data matrix of the input data is applied to a selected context autoencoder of a knowledge bank of autoencoders including at least one context autoencoder and the training data matrix is determined to be out of context for the selected autoencoder. The training data matrix is applied to each other context autoencoder of the at least one autoencoder and the training data matrix is determined to be out of context for each other context autoencoder. A new context autoencoder is constructed.

Abstract: 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.

Abstract: A method for searching video includes receiving a video query, the video query including a first video query term identifying a first foreground object, a second video query term identifying a second foreground object, and a third video query term identifying a spatiotemporal relationship; searching the video in response to the video query for the first foreground object and the second foreground object within the spatiotemporal relationship; and generating a search result in response to the searching.

Abstract: 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.

Abstract: 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.