Method and device for controlling a machine in accordance with to multiple control objectives in which machine control is based on automated learning of subordinate control skills, wherein the device provides multiple subordinate control skills which are each assigned to a different one of the multiple control objectives, the device provides multiple learning processes that are reinforcement learning processes that are each assigned to a different one of the multiple control objectives and are configured to optimize the corresponding subordinate control skill based on input data received from the machine, and where the device is configured to determine a superordinate control skill based on the subordinate control skills and to control the machine based on the superordinate control skill.

The present disclosure relates to a system and a method for validating the validity of a sensor, in particular, validating the validity of a sensor using a control limit. The present disclosure provides a method for validating the validity of a sensor using a control limit, including inferring a posterior distribution of a parameter in a Bayesian technique using a prior distribution of the parameter of sensor data and historical data of the sensor, setting a target credible interval for the posterior distribution of the parameter and setting a control line of the sensor data using the set credible interval, and validating the validity of the sensor by monitoring whether the actual measurement data of the sensor deviates from the control line.

According to the present disclosure, it is possible to set the control limit based on the Bayesian inference and validate the validity of the sensor from the actual sensor data reliably using the control limit.

A rotating machine control device is provided with: an operating terminal for changing a parameter of the rotating machine; a clearance measuring device which measures the amount of clearance between a rotor and a casing; and a control device body. The control device body, in accordance with the amount of clearance measured by means of the clearance measuring device, determines an operating amount for the operating terminal so as to vary the rate of change in the parameter, and outputs the operating amount to the operating terminal.

A wash optimization system and related methods are provided that increase the efficiency and the effectiveness of engine washes. A system comprising at least one processor receives sensor data representing one or more measured parameters of a turbine engine and determines at least one performance parameter based on the sensor data. The at least one performance parameter represents one or more particulate values associated with the turbine engine. The system generates a health state for the turbine engine based on the at least one performance parameter and generates a wash identifier based on the health state of the turbine engine.

The invention relates to a device for monitoring the lifetime of at least one hydraulic apparatus of an aircraft that is subject to ventilations in hydraulic pressure during flight, comprising an interface for receiving measurement data which are representative of hydraulic pressure (P). The invention is characterised in that the device comprises a processing device, comprising a means for detecting a pressure (P) load (SOLL.sub.END) of a damaging nature, which load is defined by the fact that the pressure (P) comprises a pressure increase (ΔP.sub.AUG) that is greater than a predetermined damage threshold (S.sub.ΔP), followed by a pressure decrease (ΔP.sub.DIM) that is greater than the threshold (S.sub.ΔP), a means for calculating a pressure variation magnitude that is equal to the maximum increase (ΔP.sub.AUG) and the maximum decrease (ΔP.sub.DIM), a means for projecting the magnitude onto a decreasing curve or straight line of a damage model in order to determine the permissible number of loads corresponding to the magnitude, a means for calculating a potential damage ratio that is equal to a number of reference loads divided by the permissible number, a means for increasing a count of accumulated ratios by said ratio.

A repair method (72) for extending a service life of a power turbine disk (12) having corrosion damage, wherein the power turbine (14) includes stages (16, 18, 20, 22) and interstage gaps (26, 28, 30, 32). The method (72) includes conducting a first thermal analysis (74) of a baseline configuration of a baseline disk that does not have corrosion to determine a first steady state temperature distribution (44). A corrosion damaged disk (12) is then machined (76) to a depth suitable for repairing the corrosion to form a machined disk. A second thermal analysis (78) of the machined disk is conducted to determine a second steady state temperature distribution of the machined disk. A first predicted safe cyclic life (PSCL) (80) is then calculated for disk axisymmetric features (1-10) of the machined disk. A second PSCL (82) is also calculated for disk firtree features (70) of the machined disk. Further, the method (72) is qualified (84) to ensure that the quality of the machined disk is consistent with a new disk.

A method for qualifying a gas turbine engine component includes creating a first set of substantially identical gas turbine engine components via a uniform manufacturing procedure, determining a set of as-manufactured parameters of each gas turbine engine component in the first set, and determining a variance model of the first set. The variance model includes a representative parameter profile, which includes a plurality of component parameter profiles. The sum of each of the component parameter profiles is the representative parameter profile. The method also includes determining at least one predicted response models based at least in part on the variance model, identifying as-manufactured parameters of a second engine component, applying the as-manufactured parameters of the second engine component to the at least one predicted response models, thereby generating a predicted response output, and qualifying the second engine component for usage in at least one gas turbine engine corresponding to the at least one predicted response model.

A method for operating a turbine engine is provided. The method includes receiving operating data comprising at least an engine operation parameter, an environmental parameter, a location parameter, and a time parameter; operating the turbine engine based on a baseline ground operation schedule; generating an adjusted ground operation schedule based on the operating data and the baseline ground operation schedule, wherein generating the adjusted ground operation schedule is based on a machine learning algorithm; and operating the engine based on the adjusted ground operation schedule.

An inspection device is disclosed herein. In various embodiments, the inspection system device comprises: a support structure; a motor; a shaft operably coupled to the motor, the shaft extending from a first side of the support structure to a second side of the support structure, the shaft configured to couple to a bladed rotor; and a scanner moveably coupled to the support structure, the scanner configured to generate a three-dimensional model for the bladed rotor.

A method can comprise receiving, via the processor, one of a point cloud and a three-dimensional model for an inspected integrally bladed rotor (IBR) and a defect including a defect shape, a defect size, and a defect location; performing, via the processor, a simulation of a rotor module in a gas turbine engine, the rotor module including the inspected IBR with a potential repaired defect; determining, via the processor, the potential repaired defect would produce an estimated life less than a design life for the inspected IBR; determining, via the processor, the estimated life would exceed a remaining life threshold for the inspected IBR; and generating, via the processor, a repair process for the potential repaired defect.