Abstract: A method includes training a model to identify anomalous portions of a test component using training images and labels that indicate anomalous portions of training components within the training images. The method also includes compressing a source image of the test component to generate a first input image having a first resolution and making a first determination of whether the first input image indicates that the test component is anomalous. The method also includes making a second determination, for each section of a second input image, of whether the section indicates that the test component is anomalous. The second input image has a second resolution that is greater than the first resolution. The method also includes providing an indication of whether the first input image indicates that the test component is anomalous and providing an indication of whether the second input image indicates that the test component is anomalous.

Abstract: A vehicle includes a first system, a first sensor, a second sensor, and a processor. The first sensor is configured to generate first sensor data indicative of an operational status of the first system. The second sensor is configured to generate second sensor data associated with an adaptive performance metric adjustment criterion. The processor is configured to, in response to determining that the second sensor data satisfies the adaptive performance metric adjustment criterion, determine, based on the second sensor data, an adaptive performance metric to be compared to the first sensor data to identify anomalous behavior of the first system. The processor is further configured to compare the first sensor data to the adaptive performance metric and to generate a maintenance alert in response to determining that the first sensor data fails to satisfy the adaptive performance metric.

Abstract: A vehicle includes a first system, a first sensor, a second sensor, and a processor. The first sensor is configured to generate first sensor data indicative of an operational status of the first system. The second sensor is configured to generate second sensor data associated with an adaptive performance metric adjustment criterion. The processor is configured to, in response to determining that the second sensor data satisfies the adaptive performance metric adjustment criterion, determine, based on the second sensor data, an adaptive performance metric to be compared to the first sensor data to identify anomalous behavior of the first system. The processor is further configured to compare the first sensor data to the adaptive performance metric and to generate a maintenance alert in response to determining that the first sensor data fails to satisfy the adaptive performance metric.

Abstract: A computer-implemented method, environmental control system (ECS) for an aircraft, and system are provided. Air temperatures at the inlet and outlet of a ram air duct for an ECS are measured. Also, air temperatures at outlets from one or more heat exchangers arranged in the ram air duct are measured. The temperatures are typically measured when the aircraft is on the ground and when aircraft engines supplying air to the ECS are operating at idle. Shortly thereafter, the heat exchangers are manually inspected to determine a level of actual fouling (e.g., dirt, dust, or other debris accumulated on heat exchanger surfaces). A supervised machine learning or other statistical analysis is performed on the measured temperatures and associated actual fouling levels to develop a model that predicts an amount of heat exchanger fouling, based on the temperature measurements. An alert can be output if the predicted fouling exceeds a fouling threshold.

Abstract: A method to provide prognosis and diagnosis of environmental control system maintenance.

Abstract: A computer-implemented method, environmental control system (ECS) for an aircraft, and system are provided. Air temperatures at the inlet and outlet of a ram air duct for an ECS are measured. Also, air temperatures at outlets from one or more heat exchangers arranged in the ram air duct are measured. The temperatures are typically measured when the aircraft is on the ground and when aircraft engines supplying air to the ECS are operating at idle. Shortly thereafter, the heat exchangers are manually inspected to determine a level of actual fouling (e.g., dirt, dust, or other debris accumulated on heat exchanger surfaces). A supervised machine learning or other statistical analysis is performed on the measured temperatures and associated actual fouling levels to develop a model that predicts an amount of heat exchanger fouling, based on the temperature measurements. An alert can be output if the predicted fouling exceeds a fouling threshold.

Abstract: A computer-implemented method, environmental control system, and aircraft are provided. Environmental operating conditions data for a heat exchanger is received. Measured values from sensors measuring parameters of the heat exchanger are also received. An operating model for the heat exchanger based on the received environmental operating conditions is retrieved from a first data structure. The retrieved model includes estimated values for the sensors. A difference between the estimated values and the measured values is calculated. The calculated differences are compared to at least one threshold value. Upon the differences exceeding the at least one threshold value, the calculated differences are compared to abnormal operation models in an abnormal operation library data structure. Upon the calculated difference matching an abnormal operation model in the abnormal operation library data structure, outputting an abnormal operation identity associated with the abnormal operation model.

Abstract: A system and method for transmitting an information signal through a radio-frequency opaque barrier are disclosed. A transmitter is positioned on a first side of the barrier and a re-transmitter is positioned on a second side of the barrier. The transmitter includes a controller that modulates a received information signal with a carrier signal and forwards the modulated information signal to a vibration generator which converts the received electrical signal to a corresponding vibration signal. The re-transmitter includes an accelerometer that detects vibration signals and produces a corresponding electrical signal and a controller coupled to the accelerometer which receives the electrical signal from the accelerometer and demodulates the information signal included within the electrical signal received from the accelerometer.

Abstract: A method to provide prognosis and diagnosis of environmental control system maintenance.

Abstract: A particular method includes receiving a conflict notice from a first airfield computing agent associated with a first airfield at a first aircraft computing agent associated with a first aircraft. The conflict notice indicates that the first aircraft is associated with a first conflict of the first airfield. The method also includes identifying, based on parameters associated with the first aircraft, one or more actions associated with the first aircraft to address the first conflict.

Abstract: A computer-based method for generating multi-generational relationships within a relational model. The method includes applying, with a processing device, a filter to parent node data and child node data in the relational model, the relational model stored in a computer memory, adding filtered data to a database within a computer memory via instructions executed by the processing device, the filtered data including relational model data that passed through the filter, and applying, through instructions executed by the processing device, a parent node selection process to every child node in the filtered data that is associated with a parent node record not conforming to the filter.