US-20260124681-A1 - QUALITY ASSURANCE OF AN ADDITIVELY MANUFACTURED PART

US20260124681A1US 20260124681 A1US20260124681 A1US 20260124681A1US-20260124681-A1

Abstract

Devices, systems, machine-readable media, and methods for quality assurance of an additively manufactured part are provided. A method includes receiving by a manufacturer, a proprietary additive manufacturing process parameter, a non-proprietary additive manufacturing process parameter, and sensor data indicative of a build condition of an additively manufactured part, the build condition indicative of an attribute of the additively manufactured part during the additive manufacturing process; identifying, based on the proprietary additive manufacturing process parameter, the non-proprietary additive manufacturing process parameter, and the sensor data, a defect of the additively manufactured part; filtering out the proprietary additive manufacturing process parameter, resulting in filtered information; generating, based on the filtered information, a quality assurance report of the additively manufactured part; providing the quality assurance report to a customer, the quality assurance report includes a description of the defect and location of the defect; and delivering, based on the defect passing a part acceptance criterion, the additively manufactured part.

Inventors

Matthew E. Lynch
Jeffrey A. Shubrooks
Travis L. Mayberry
Stuart Taylor

Assignees

RAYTHEON COMPANY

Dates

Publication Date: 20260507
Application Date: 20241105

Claims (20)

1 . A method for quality assurance of an additive manufacturing process, the method comprising: receiving, by a manufacturer, a proprietary additive manufacturing process parameter, a non-proprietary additive manufacturing process parameter, and sensor data indicative of a build condition of an additively manufactured part, the build condition indicative of an attribute of the additively manufactured part during the additive manufacturing process; identifying, based on the proprietary additive manufacturing process parameter, the non-proprietary additive manufacturing process parameter, and the sensor data, a defect of the additively manufactured part; filtering out the proprietary additive manufacturing process parameter, resulting in filtered information; generating, based on the filtered information, a quality assurance report of the additively manufactured part; providing the quality assurance report to a customer, the quality assurance report includes a description of the defect and location of the defect; and delivering, based on the defect passing a part acceptance criterion, the additively manufactured part.
2 . The method of claim 1 , wherein the proprietary additive manufacturing process parameter includes at least one of a scan vector parameter, a layer thickness, an energy source parameter, a powder bed parameter, a heat treatment parameter, or a post-processing parameter.
3 . The method of claim 2 , wherein the energy source parameter includes at least one of a laser power, a laser speed, a spot size, or a pulse duration.
4 . The method of claim 1 , wherein the non-proprietary additive manufacturing process parameter includes at least one of a chamber oxygen concentration, heat treatment profile, a build plate temperature, a process chamber temperature, a turbine pressure, or a turbine pressure ramp rate.
5 . The method of claim 1 , wherein the sensor data includes at least one of a photodiode measurement, an acoustic measurement, a transducer measurement, a temperature measurement, a near infrared (IR) camera data, a short-wave IR camera data, a long-wave IR data, or a visible camera data.
6 . The method of claim 1 , wherein identifying a defect includes identifying at least one of a temperature-induced defect, a spatter-induced defect, a swelling defect, a delamination defect, a geometric fidelity defect, an anisotropic defect, or an inclusion defect.
7 . The method of claim 1 , wherein identifying the defect includes using at least one of a numerical method, a machine learning trained model, or a physics-based model.
8 . The method of claim 7 , wherein the machine learning trained model includes at least one of a computer vision system, or a temperature-based system to predict metal grain and metal microstructure.
9 . The method of claim 7 , wherein the physics-based model includes at least one of a finite element analysis (FEA) model, a computational fluid dynamics (CFD) model, fatigue analysis, thermal analysis, or structural analysis.
10 . The method of claim 1 , wherein filtering out further includes filtering out sensor data.
11 . The method of claim 1 , wherein filtering out includes identifying and removing the proprietary additive manufacturing process parameter.
12 . The method of claim 1 , wherein the quality assurance report further includes at least one of a time series of the non-proprietary additive manufacturing process parameter, the non-proprietary additive manufacturing process parameter, a model of the additively manufactured part, or an acceptance recommendation.
13 . The method of claim 1 , wherein the part acceptance criterion includes at least one of a process history acceptance criterion, a simulation analysis acceptance criterion, or a geometry analysis acceptance criterion.
14 . The method of claim 1 , further comprising scrapping, based on the defect failing the part acceptance criterion, the additively manufactured part.
15 . A non-transitory machine-readable medium comprising instructions that when executed by a processor executes a process comprising: receiving, by a manufacturer, a proprietary additive manufacturing process parameter, a non-proprietary additive manufacturing process parameter, and sensor data indicative of a build condition of an additively manufactured part, the build condition indicative of an attribute of the additively manufactured part during the additive manufacturing process; identifying, based on the proprietary additive manufacturing process parameter, the non-proprietary additive manufacturing process parameter, and the sensor data, a defect of the additively manufactured part; filtering out the proprietary additive manufacturing process parameter, resulting in filtered information; generating, based on the filtered information, a quality assurance report of the additively manufactured part; providing the quality assurance report to a customer, the quality assurance report includes a description of the defect and location of the defect; and delivering, based on the defect passing a part acceptance criterion, the additively manufactured part.
16 . The non-transitory machine-readable medium of claim 15 , wherein filtering out further includes filtering out sensor data.
17 . The non-transitory machine-readable medium of claim 15 , wherein filtering out includes identifying and removing the proprietary additive manufacturing process parameter.
18 . A system comprising: a computer processor; and a computer memory coupled to the computer processor; wherein the computer processor and the computer memory are operable for: receiving, by a manufacturer, a proprietary additive manufacturing process parameter, a non-proprietary additive manufacturing process parameter, and sensor data indicative of a build condition of an additively manufactured part, the build condition indicative of an attribute of the additively manufactured part during the additive manufacturing process; identifying, based on the proprietary additive manufacturing process parameter, the non-proprietary additive manufacturing process parameter, and the sensor data, a defect of the additively manufactured part; filtering out the proprietary additive manufacturing process parameter, resulting in filtered information; generating, based on the filtered information, a quality assurance report of the additively manufactured part; providing the quality assurance report to a customer, the quality assurance report includes a description of the defect and location of the defect; and delivering, based on the defect passing a part acceptance criterion, the additively manufactured part.
19 . The system of claim 18 , wherein filtering out further includes filtering out sensor data.
20 . The system of claim 18 , wherein filtering out includes identifying and removing the proprietary additive manufacturing process parameter.

Description

TECHNICAL FIELD Embodiments discussed herein regard devices, systems, machine-readable media, and methods in the field of additive manufacturing. Embodiments regard quality assurance and quality control of additively manufactured parts. Embodiments identify the presence of defects in additively manufactured parts and evaluate these defects for part acceptance without divulging proprietary manufacturing or analysis processes. BACKGROUND Additive manufacturing is a manufacturing process that builds parts sequentially, layer by layer. This approach stands in contrast to subtractive manufacturing methods, in which parts are shaped by removing material from a larger block or piece. One advantage of additive manufacturing is it enables the production of intricate and complex parts that would be difficult or prohibitively expensive to create through subtractive manufacturing techniques. Additive manufacturing provides new possibilities for design and engineering options across various industries. One of the key advantages of additive manufacturing is its ability to significantly accelerate the product development cycle. Additive manufacturing allows for quick iteration and testing of parts. Additive manufacturing can reduce the time and cost associated with product development and refinement. Additive manufacturing is also particularly suited for high value, low volume components due to its efficiency and low minimum order quantity. BRIEF DESCRIPTION OF THE DRAWINGS FIG. 1 illustrates, by way of example, a diagram of a quality assurance system of an additively manufactured part. FIG. 2A illustrates, by way of example, a diagram of an embodiment of defect identification by an acoustic signal of the quality assurance system of FIG. 1. FIG. 2B illustrates, by way of example, a diagram of an embodiment of defect identification by a temperature map of the quality assurance system of FIG. 1. FIG. 2C illustrates, by way of example, a diagram of an embodiment of defect identification by a visual identification method of the quality assurance system of FIG. 1. FIG. 2D illustrates, by way of example, a diagram of an embodiment of determination of as-built contour by tracking melt pool geometry around the exterior of a specified geometry, with comparison to the nominal geometry, of the quality assurance system process of FIG. 1 FIG. 3 illustrates, by way of example, a diagram of an embodiment of defect identification by stacking multiple 2D images into a 3D reconstruction, of the quality assurance system of FIG. 1. FIG. 4A-4D illustrate, by way of examples, embodiments of a quality assurance report. FIG. 5 illustrates by way of example, a flow diagram of an embodiment of a method for defect detection by a quality assurance system. FIG. 6 illustrates, by way of example, a machine learning (ML) engine for training a ML model. FIG. 7 illustrates, by way of example, a block diagram of an embodiment of a machine in the example form of a computer system within which instructions, for causing the machine to perform any one or more of the methodologies discussed herein, may be executed. DETAILED DESCRIPTION The following description and the drawings sufficiently illustrate specific embodiments to enable those skilled in the art to practice them. Other embodiments may incorporate structural, logical, electrical, process, and other changes. Portions and features of some embodiments may be included in, or substituted for, those of other embodiments. Embodiments set forth in the claims encompass all available equivalents of those claims. Complex assemblies and builds often involve components from multiple part suppliers. Each supplier contributes individualized and specialized parts to the final product. For additively manufactured parts, each supplier can possess proprietary process information of how they produce these parts, which they prefer to keep confidential. The proprietary process can form part of their manufacturing capabilities that can contribute to their market positions. In some instances, proprietary process information can be designated as confidential, trade secrets, or the like. Manufacturers keep proprietary process information confidential to protect their competitive edge in the market. However, the quality of an individual additively manufactured part is of importance to the customers who rely on these parts in their builds. Additive manufacturing represents a shift from conventional manufacturing systems in terms of part consistency. While manufacturing processes like injection molding produce nearly identical parts due to their repetitive nature, additive manufacturing processes create each part individually. The difference can lead to part-to-part variations if process variables are not tightly controlled. The additively manufactured part can serve as a key or critical component in an application, making the structural integrity, absence of defects in the part, or types of defects in the part important consider