A method for stability analysis of a combustion chamber of a gas turbine engine based on image sequence analysis belongs to the field of fault prediction and health management of aeroengine. Firstly, flow field data inside a combustion chamber of a gas turbine engine is acquired. Secondly, flow field images of the combustion chamber are preprocessed to respectively obtain a discrimination model data set and a prediction model data set. Then, a 3DWaveNet model is constructed as a generation network of a prediction model. A discrimination network of the module is constructed. The generation network and the discrimination network are combined to form the prediction model. Finally, a discrimination model is constructed according to the discrimination model data set; the training set in the discrimination model data set is used for training, and the test set is used for assessment.

Embodiments in accordance with the present disclosure include a meta-stable detergent based foam generating device of a turbine cleaning system includes a manifold configured to receive a liquid detergent and an expansion gas, a gas supply source configured to store the expansion gas, and one or more aerators fluidly coupled with, and between, the gas supply source and the manifold. Each aerator of the one or more aerators comprises an orifice through which the expansion gas enters the manifold, and wherein the orifice of each aerator is sized to enable generation of a meta-stable detergent based foam having bubbles with bubble diameters within a range of 10 microns (3.9×10.sup.−4 inches inches) and 5 millimeters (0.2 inches), having a half-life within a range of 5 minutes and 180 minutes, or a combination thereof.

A method is disclosed herein of detecting at least one frozen period in at least one sensor dataset associated with at least one sensor in a technical system. The method includes receiving the at least one sensor dataset in time series and computing run-lengths for the at least one sensor dataset, wherein each of the run-lengths is length of consecutive repetitions of a sensor value in the at least one sensor dataset. The method includes clustering the run-lengths into one of two clusters based on a run frequency, wherein the run frequency is a number of times the run-lengths are repeated in the at least one sensor dataset. Further, the method includes identifying a cluster from the two clusters with lower run frequency and detecting the at least one frozen period in the at least one sensor dataset based on the identified cluster.

A turbine blade or vane inspection apparatus comprising a controller, mounting for holding a turbine blade or vane, a source of illumination, and a camera. At least two of the source of illumination, the camera, and the mounting are moveable components. The controller is configured to control the moveable components to (a) position the turbine blade or vane mounted thereon relative to the illumination source so as to provide a contrast of illumination between a feature of the turbine blade or vane and an adjacent surface of the turbine blade or vane and (b), position the camera so that the optical axis of the camera is directed towards the feature. The controller is further configured to determine a dimension and/or shape of the feature based on an image obtained by the camera.

A method of analyzing layer thickness of a multilayer component is provided. The method includes: creating an opening having a predefined geometry partially into the multilayer component at a selected location on a surface of the multilayer component. The multilayer component includes a plurality of material layers including a substrate and a bond coat. The opening exposes each of the plurality of material layers including the substrate. Contrast of the exposed plurality of material layers can be increased. An image is created of the exposed layers in the opening using a digital microscope, and thickness of a bond coat, thickness of a depletion layer\ and/or thickness of an oxide layer is calculated from the image and based on the predefined geometry of the opening. Repairing the opening, allows the multilayer component to be used for an intended purpose after testing, e.g., re-installed and reused in a gas turbine.

A method for generating material test samples for conducting material tests of a legacy steam turbine rotor having an inter-blade region rotor surface, and an inlet region rotor surface adjoining the inter-blade region rotor surface. The method includes forming an annular ring of rotor material in the sample area and forming a material test sample from a portion of the annular ring. Also described is a legacy steam turbine rotor including an inter-blade region rotor surface, and an inlet region rotor surface adjoining the inter-blade region rotor surface. The steam turbine rotor having a groove formed therein, and wherein the groove is machined to enable removal of material from the steam turbine rotor to form samples configured to enable at least one of conducting material property tests and operating the improved legacy steam turbine rotor at an expanded thermal stress compared to the legacy steam turbine rotor.

Embodiments of the present disclosure include a method for controlling a power generation system, the method including: detecting a heat distribution across a component of a power generation system from a thermal output of the component, during operation of the power generation system; calculating a projected heat distribution across the component based on a library of modeling data for the power generation system; calculating whether a difference between the heat distribution and the projected heat distribution exceeds a thermal threshold; adjusting the power generation system in response to the difference exceeding the predetermined threshold, wherein the adjusting includes modifying an operating setting of the power generation system.

A phonic wheel having a body and a tooth is disclosed. An embodiment of the phonic wheel includes a body that is configured to rotate about a rotation axis. The tooth is attached to the body. The tooth has a first axial end relative to the rotation axis, a second axial end opposite the first axial end, and a mid portion extending between the first and second axial ends. The mid portion has a substantially axially uniform height from the body. The first axial end has a greater height from the body than the height of the mid portion.

A computer-implemented method comprising: controlling input of data quantifying damage received by a compressor of a gas turbine engine into a first machine learning algorithm; receiving data quantifying a first operating parameter of the compressor as an output of the first machine learning algorithm; and determining operability of the compressor by comparing the received data quantifying the first operating parameter of the compressor with a threshold.

A method and system for aligning a component within a turbine casing, and a related turbine casing. In a top-on position, a location of an optical target and another, vertically spaced optical target on the joint flange are measured. After removing at least the upper casing, the optical targets' locations are measured again, and the locations of a pair of reference points on an upper surface of the horizontal joint flange are measured. A prediction offset value is calculated for the component support position in the top-on position based on the locations. The prediction offset value may include a vertical adjustment based, in part, on a translation of a triangular spatial relationship of a number of the reference points and/or a tilt angle, a horizontal adjustment, and a horizontal joint flange surface distortion adjustment. Support position is adjusted by the prediction offset value to improve alignment.