Fabrication optimization for composite parts
AssigneeThe Boeing Company
InventorsMichael Yee-Chih Wang, Jeffrey Lawrence Miller, Jonas Beuchert, Roger Erh Hsiang Chen
Life of this patent
Estimating the term…
Abstract
Systems and methods are provided for facilitating fabrication of a composite part. An illustrative method includes loading a Numerical Control (NC) program that directs layup of tows by a fiber placement machine to create a laminate for curing into a composite part, identifying tow information recited in the NC program, applying inputs based on the tow information to a neural network that has been trained with measurements describing tow placement within other laminates that have been laid-up, and reporting likelihood of a fabrication discrepancy that is out of tolerance, based on an output of the neural network.
Claims25
A method for facilitating fabrication of a composite part, the method comprising:
- loading a Numerical Control (NC) program that directs layup of tows by a fiber placement machine to create a laminate for curing into a composite part;
- extracting tow information recited in the NC program;
- applying inputs based on the tow information to a neural network that has been trained with tow information extracted from prior NC programs, and measurements describing out-of-tolerance discrepancies for other laminates that have been laid-up according to the prior NC programs;
- and
- reporting likelihood of a fabrication discrepancy that is out of tolerance, based on an output of the neural network for the NC program.
A non-transitory computer readable medium embodying programmed instructions which, when executed by a processor, are operable for performing a method for facilitating fabrication of a composite part, the method comprising:
- loading a Numerical Control (NC) program that directs layup of tows by a fiber placement machine to create a laminate for curing into a composite part;
- extracting tow information recited in the NC program;
- applying inputs based on the tow information to a neural network that has been trained with tow information extracted from prior NC programs, and measurements describing out-of-tolerance discrepancies for other laminates that have been laid-up according to the prior NC programs;
- and
- reporting likelihood of a fabrication discrepancy that is out of tolerance, based on an output of the neural network for the NC program.
An apparatus for facilitating fabrication of a composite part, the apparatus comprising:
- a memory storing a Numerical Control (NC) program that directs layup of tows by a fiber placement machine to create a laminate for curing into a composite part;
- and
- a controller that identifies tow information recited in the NC program, applies inputs based on the tow information to a neural network that has been trained with tow information extracted from prior NC programs, and measurements describing out-of-tolerance fabrication discrepancies within other laminates that have been laid-up according to the prior NC programs, and reports a likelihood of a fabrication discrepancy that is out of tolerance, based on an output of the neural network for the NC program.
A method for facilitating fabrication of a composite part, comprising:
- laying up a laminate with a fiber placement machine according to a first Numerical Control (NC) program;
- acquiring measurements of the laminate, the measurements indicating locations of out of tolerance conditions:
- training a neural network based upon tow information extracted from the first NC program and the measurements;
- analyzing a second NC program for laying up a new laminate, via the neural network;
- and
- generating a heat map indicating likelihoods of locations on the new laminate exhibiting an out of tolerance condition, based on output from the neural network.
A method for facilitating fabrication of a composite part, the method comprising:
- acquiring definitions that characterize out of tolerance conditions for a laminate;
- training a neural network based upon the definitions using tow information extracted from a first Numerical Control (NC) program, and measurements describing out-of-tolerance fabrication discrepancies within other laminates that have been laid-up according to the first NC program;
- operating the neural network to identify a first set of expected locations of out of tolerance conditions for a new laminate defined by a second NC program;
- altering the definitions;
- re-training the neural network based upon the altered definitions;
- operating the re-trained neural network to identify a second set of expected locations of out of tolerance conditions for the new laminate;
- and
- generating a report that compares the first set of expected locations to the second set of expected locations.
Dependencies are inferred from the claim text.