A method for controlling a combustion process in a gas turbine wherein a combustion chamber, a control device storing a calculation model of the combustion process, and an exhaust air measurement device are used. A permissible limit value for nitrogen oxides and for carbon monoxide as pollutants is set. The actual value of at least one of the two pollutants is measured continuously in the exhaust air. When a signal to reduce the power of the gas turbine to a lowest possible value is given, then a minimum fuel supply at which the limit values are complied with is calculated. The fuel supply is then reduced either until the calculated minimum fuel supply is reached or until the continuously measured proportion of the pollutant reaches the permissible limit value.

A burner arrangement has a plurality of mixing channels which extend parallel to the main axis of the burner arrangement and are arranged in at least two concentric circles, in which mixing channels fuel and discharge air from the compressor are mixed during the operation of the burner arrangement. The mixing channels are grouped together into fuel stages so as to produce an irregular staging in the peripheral direction of the burner arrangement.

Methods and systems for supply of fuel for a turbine-driven fracturing pump system used in hydraulic fracturing may be configured to identify when the supply pressure of primary fuel to a plurality of gas turbine engines of a plurality of hydraulic fracturing units falls below a set point, identify a gas turbine engine of the fleet of hydraulic fracturing units operating on primary fuel with highest amount of secondary fuel available, and to selectively transfer the gas turbine engine operating on primary fuel with the highest amount of secondary fuel from primary fuel operation to secondary fuel operation. Some methods and systems may be configured to transfer all gas turbine engines to secondary fuel operation and individually and/or sequentially restore operation to primary fuel operation and/or to manage primary fuel operation and/or secondary fuel operation for portions of the plurality of gas turbine engines.

In a method for operating a combustor of an embodiment, before ignition in the combustor, a mixed gas containing oxygen is circulated through the combustor as a circulating gas. Then, in an operating time from the time of ignition in the combustor to the time of a rated load of a turbine, from the time of ignition until reaching stable combustion conditions allowing stable combustion, a combustion gas in which a controller controls a flow rate of a fuel supplied from a fuel supply part and a flow rate of an oxidant supplied from an oxidant supply part to maintain the same oxygen concentration as an oxygen concentration in the mixed gas is circulated as the circulating gas.

A method for controlling a combustion apparatus having a combustion state in which a parameter related to the combustion state reflects a chaotic behavior is provided. The method includes the steps of measuring the parameter and determining a time series of the parameter, shifting the time series by a variable time delay for determining a time-shifted signal, and forming a difference between the time-shifted signal and the time series for determining a time dependent first signal, so that a norm of the difference is lowest. A time dependent second signal is determined, wherein determining the time dependent second signal includes at least one of using a frequency of a desired oscillating combustion state, and shifting the time series by a set time delay. The first signal and the second signal are combined to determine a control signal. The control signal is used to influence the combustion apparatus.

A method of identifying a fuel contained in a fuel tank of an aircraft and arranged to power a gas turbine engine of the aircraft is performed by processing circuitry of the aircraft and includes: obtaining at least one fuel characteristic of any fuel already present in the fuel tank prior to refuelling; determining at least one fuel characteristic of a fuel added to the fuel tank on refuelling; and calculating at least one fuel characteristic of the resultant fuel in the fuel tank after refuelling. The method may further controlling the propulsion system of the aircraft based on the calculated at least one fuel characteristic of the resultant fuel in the fuel tank after refuelling.

A fuel control device includes a combustion temperature estimation value calculation unit that calculates a temperature estimation value when a mixture of fuel and inflow air is burned using an atmospheric condition, an opening degree command value of a valve that controls the amount of air that is mixed with the fuel and burned, and an output prediction value calculated on the basis of a fuel control signal command value used for calculation of a total fuel flow rate flowing through a plurality of fuel supply systems, a fuel distribution command value calculation unit that calculates a fuel distribution command value indicating a distribution of fuel output from the fuel supply systems based on the temperature estimation value, and outputs the fuel distribution command value, and a valve opening degree calculation unit that calculates each valve opening degree of a fuel flow rate control valve of the fuel supply systems.

This disclosure relates to method and system for training of deep learning based time-series models based on self-supervised learning. The problem of missing data is taken care of by introducing missing-ness masks. The deep learning model for univariate and multivariate time series data is trained with the distorted input data using the self-supervised learning to reconstruct the masked input data. Herein, the one or more distortion techniques include quantization, insertion, deletion, and combination of the one or more such distortion techniques with random subsequence shuffling. Different distortion techniques in the form of reconstruction of masked input data are provided to solve. The deep learning model performs these different distortion techniques, which force the deep learning model to learn better features. It is to be noted that the system uses a lot of unlabeled data available cheaply as compared to the label or annotated data which is very hard to get.

A measurement system for a gas turbine engine is provided. The measurement system comprises a sensor assembly. The measurement system also includes multiple sensors coupled to the sensor assembly. The sensor assembly is configured to be removably inserted within a space defined by a circumferential track embedded within an inner diameter of a casing of the gas turbine engine without having to disassemble the casing.

Methods and systems for supply of fuel for a turbine-driven fracturing pump system used in hydraulic fracturing may be configured to identify when the supply pressure of primary fuel to a plurality of gas turbine engines of a plurality of hydraulic fracturing units falls below a set point, identify a gas turbine engine of the fleet of hydraulic fracturing units operating on primary fuel with highest amount of secondary fuel available, and to selectively transfer the gas turbine engine operating on primary fuel with the highest amount of secondary fuel from primary fuel operation to secondary fuel operation. Some methods and systems may be configured to transfer all gas turbine engines to secondary fuel operation and individually and/or sequentially restore operation to primary fuel operation and/or to manage primary fuel operation and/or secondary fuel operation for portions of the plurality of gas turbine engines.