Described herein are methods and systems to establish a pre-build relationship in a model that specifies a first parameter for a first feature of a structure and a second parameter for a second feature of the structure. In particular, a computing system may receive data specifying a pre-build relationship that defines a build value of the first parameter in terms of a post-build observed value of the second parameter. During production of the structure, the computing system may determine the post-build observed value of the second parameter and, based on the determined post-build observed value, may determine the build value of the first parameter in accordance with the pre-build relationship. After determining the build value, the computing system may then transmit, to a robotic system, an instruction associated with production of the first feature by the robotic system, with that instruction specifying the determined build value of the first parameter.

The invention relates to a method and to system for producing blades (1) of a machine interacting with a fluid, in particular a fluid-driven machine, in particular a wind turbine, comprising an examination device (19) for determining geometric deviations (A, B, C, D, E, F) from a target shape for one or more shaped blades (1), a device (21) for determining a deviation evaluation of one or more determined geometric deviations from the target shape for each blade with respect to the aerodynamic and/or mechanical consequences thereof, a device (23) for assigning one or more corrective measures (100, 101, 102), each including an expenditure evaluation (100, 101, 102), to one or more determined geometric deviations (A, B, C, D, E, F) from the target shape for each blade, and a linking device (24) for linking a deviation evaluation that was determined for one or more of the determined geometric deviations to the expenditure evaluation for one or more determined corrective measures and for determining the corrective measures to be carried out from the result of the linkage.

Described herein are methods and systems to establish a pre-build relationship in a model that specifies a first parameter for a first feature of a structure and a second parameter for a second feature of the structure. In particular, a computing system may receive data specifying a pre-build relationship that defines a build value of the first parameter in terms of a post-build observed value of the second parameter. During production of the structure, the computing system may determine the post-build observed value of the second parameter and, based on the determined post-build observed value, may determine the build value of the first parameter in accordance with the pre-build relationship. After determining the build value, the computing system may then transmit, to a robotic system, an instruction associated with production of the first feature by the robotic system, with that instruction specifying the determined build value of the first parameter.

This invention concerns improvements in the inspection, assessment and re-working of manufactured components such as nozzle guide vanes (NGVs) and blades, in particular by improving the comparison of the component with nominal data. Dimensional data of a physical component is obtained and used to create a virtual digitized model of the component which is aligned with a nominal CAD model of the component in a virtual space. The correspondence is assessed and used to adjust weightings of different regions of the digitized model to improve the alignment. This process is repeated within the digital space until either conformance is reached or it is determined that this is not possible.

A machining apparatus is provided with a machine learning device that performs machine learning. The machine learning device performs the machine learning by receiving the input of machining accuracy between a machining shape of a workpiece measured on-machine and design data on the workpiece and machining time of the workpiece measured by a measurement device. Based on a result of the machine learning, the machining apparatus changes machining conditions such that the machining accuracy increases and the machining time becomes as short as possible.

Described herein are methods and systems to establish a pre-build relationship in a model that specifies a first parameter for a first feature of a structure and a second parameter for a second feature of the structure. In particular, a computing system may receive data specifying a pre-build relationship that defines a build value of the first parameter in terms of a post-build observed value of the second parameter. During production of the structure, the computing system may determine the post-build observed value of the second parameter and, based on the determined post-build observed value, may determine the build value of the first parameter in accordance with the pre-build relationship. After determining the build value, the computing system may then transmit, to a robotic system, an instruction associated with production of the first feature by the robotic system, with that instruction specifying the determined build value of the first parameter.

A command value generator includes: a target path and tolerance range changing unit changing at least one of the target path and a range of tolerance based on the machining error; a response path calculation unit calculating a response error and a response path; a path comparison unit calculating an error between the response path and the target path and determining whether the calculated error falls within the range of tolerance; a temporary command path holding unit holding the target path as a temporary command path; and a command path correction unit correcting the temporary command path. The temporary command path is corrected based on the response error when determining the calculated error not to fall within the range of tolerance, and a corrected temporary command path is held in the temporary command path holding unit.

Producing a component having an in use gas washed surface includes: obtaining a reference component having a reference shape with an in use gas washed surface; setting one or more performance threshold for the reference shape, the threshold defining an acceptable performance for the reference shape; obtaining a manufactured component made to the reference shape; measuring the manufactured component and determining a displacement distribution indicative of the geometric deviation of the manufactured component from the reference shape; determining a performance sensitivity distribution for the reference component, the sensitivity distribution having a plurality of points, each point indicative of a performance factor for the reference component; combining the sensitivity distribution and displacement distribution to determine a performance prediction for the manufactured component; determining whether the performance prediction is within the performance threshold; accepting or rejecting the component for use if the predicted performance is within or outside the performance threshold, respectively.

A round hole machining method and a round-hole machining device in which machining can be accurately performed regardless of the wear of an edge tool. A non-round hole machining device includes: a machining load data acquisition section for obtaining machining load data corresponding to a machining load acting on the cutting edge of a cutting tool when boring a bore in a cylinder block; a machined shape prediction section for predicting a machined shape of the workpiece by utilizing the obtained machining load data and elastic deformation amounts at respective positions on the workpiece; and a motor control section for machining the workpiece so as to form an inverted shape, that is, a shape formed by inverting the predicted machined shape with respect to a target shape.

A machining apparatus is provided with a machine learning device that performs machine learning. The machine learning device performs the machine learning by receiving the input of machining accuracy between a machining shape of a workpiece measured on-machine and design data on the workpiece and machining time of the workpiece measured by a measurement device. Based on a result of the machine learning, the machining apparatus changes machining conditions such that the machining accuracy increases and the machining time becomes as short as possible.