A method of optimizing probe placement in a turbomachine is disclosed which includes determining wavenumber (Wn) of N dominant wavelets generated by upstream and downstream stators and blade row interactions formed around an annulus, establishing a design matrix A utilized in developing flow properties around the annulus having a dimension of m×(2N+1), iteratively modifying probe positions placed around the annulus and determining a condition number of the design matrix A for each set of probe positions until a predetermined threshold is achieved for the condition number representing optimal probe position, wherein the condition number is defined as norm A.Math.norm A+, wherein A+ represents inverse of A for a square matrix and a Moore-Penrose pseudoinverse of A for a rectangular matrix.

Method for determining oscillation parameters of turbo-machine blades consists in that when the blade tip travels in front of a sensor, reading values of a single pulsed signal formed by the sensor are obtained in a number that is not lower than that of unknown parameters of a harmonic or polyharmonic oscillation of the blade, the origin of a single pulsed signal readings obtained for each blade being synchronized with the blade tip position relative to the sensor according to a given level of the single pulsed signal; then the values of the harmonic or polyharmonic oscillation parameters of the blade are calculated with the use of the obtained values of the single pulsed signal reading origins and of the value of the turbo-machine shaft revolution period.

There is described an oil contamination detection system and method. The system comprises a forward sensor package, a rearward sensor package, a catalytic chamber, and a computing device. The method comprises obtaining sensor measurements from the forward sensor package and the rearward sensor package, and detecting the presence of oil in the air flow from the sensor measurements.

A communication adapter of a gas turbine engine of an aircraft includes a communication interface configured to wirelessly communicate with an offboard system and to communicate with an engine control of the gas turbine engine. The communication adapter also includes a memory system and processing circuitry configured to check for a change of an identifier associated with the engine control, check for a loss of a plurality of remote dynamic data recording parameters from the engine control, and pass a request to update the remote dynamic data recording parameters from the offboard system through the communication adapter to the engine control based on detecting the change of the identifier. The processing circuitry is further configured to reload an existing configuration of the remote dynamic data recording parameters at the engine control based on determining that the loss of the remote dynamic data recording parameters has occurred.

A method of optimizing probe placement in a turbomachine is disclosed which includes establishing a design matrix A of size m×(2N+1) utilized in developing flow properties around an annulus of a turbomachine, where m represents the number of datapoints at different circumferential locations around the annulus, and N represents dominant wavelets generated by upstream and downstream stators and blade row interactions formed around an annulus, wherein m is greater or equal to 2N+1, and optimizing probe positioning by iteratively modifying probe positions placed around the annulus and for each iteration determining a condition number of the design matrix A for each set of probe positions until a predetermined threshold is achieved for the condition number representing an optimal probe layout.

The present invention belongs to the technical field of control of aero-engines, and proposes an adaptive boosting algorithm-based turbofan engine direct data-driven control method. First, a turbofan engine controller is designed based on the Least Squares Support Vector Machine (LSSVM) algorithm, and further, the weight of a training sample is changed by an adaptive boosting algorithm so as to construct a turbofan engine direct data-driven controller combining a plurality of basic learners into strong learners. Compared with the previous solution only adopting LS SVM, the present invention enhances the control precision, improves the generalization ability of the algorithm, and effectively solves the problem of sparsity of samples by the adaptive boosting method. By the adaptive boosting algorithm-based turbofan engine direct data-driven control method designed by the present invention.

The present invention belongs to the technical field of control of aero-engines, and proposes an adaptive boosting algorithm-based turbofan engine direct data-driven control method. First, a turbofan engine controller is designed based on the Least Squares Support Vector Machine (LSSVM) algorithm, and further, the weight of a training sample is changed by an adaptive boosting algorithm so as to construct a turbofan engine direct data-driven controller combining a plurality of basic learners into strong learners. Compared with the previous solution only adopting LS SVM, the present invention enhances the control precision, improves the generalization ability of the algorithm, and effectively solves the problem of sparsity of samples by the adaptive boosting method. By the adaptive boosting algorithm-based turbofan engine direct data-driven control method designed by the present invention.

A method for fault identification for a gas turbine engine includes receiving sensor data from at least one health monitoring sensor of a health monitoring system for a gas turbine engine; utilizing a pre-filter to filter the sensor data and obtain filtered data based on a plurality of signatures of fault conditions of the health monitoring system and the gas turbine engine; utilizing at least one transfer function to extract features from the filtered sensor data based on the plurality of signatures; utilizing a machine learning technique to analyze the extracted features, and determine whether any of the extracted features are indicative of a fault condition in the health monitoring system or the gas turbine engine; and based on the analysis indicating the presence of a fault condition, providing a fault detection notification. A health monitoring system for a gas turbine engine is also disclosed.

A method of optimizing probe placement in a turbomachine is disclosed which includes establishing a design matrix A of size m×(2N+1) utilized in developing flow properties around an annulus of a turbomachine, where m represents the number of datapoints at different circumferential locations around the annulus, and N represents dominant wavelets generated by upstream and downstream stators and blade row interactions formed around an annulus, wherein m is greater or equal to 2N+1, and optimizing probe positioning by iteratively modifying probe positions placed around the annulus and for each iteration determining a condition number of the design matrix A for each set of probe positions until a predetermined threshold is achieved for the condition number representing an optimal probe layout.

A method of optimizing probe placement in a turbomachine is disclosed which includes determining wavenumber (Wn) of N dominant wavelets generated by upstream and downstream stators and blade row interactions formed around an annulus, establishing a design matrix A utilized in developing flow properties around the annulus having a dimension of m×(2N+1), iteratively modifying probe positions placed around the annulus and determining a condition number of the design matrix A for each set of probe positions until a predetermined threshold is achieved for the condition number representing optimal probe position, wherein the condition number is defined as norm A.Math.norm A+, wherein A+ represents inverse of A for a square matrix and a Moore-Penrose pseudoinverse of A for a rectangular matrix.