An official website of the United States government
Additive manufacturing (AM) has the potential to improve productivity especially processing time, cost and surface roughness. In similar lines, part separation for assembly-based design in additive manufacturing can help in improving productivity. This paper discusses an optimization technique for part separation in assembly based part design in additive manufacturing. The technique improves productivity by decreasing the processing time of printed parts, which is the sum of the build time and the assembly time. The technique uses optimal cutting planes for part separation that has distinct advantages compared to random cutting planes. The work discusses a Genetic Algorithm (GA) technique for part separation using planar cuts. The optimization technique provides the optimal number of parts for assembly and their corresponding build orientations for the minimum processing time. Three examples have been provided to demonstrate the application of the proposed method. Finally, the results from two examples are compared to the already established hill climbing optimization method for part separation.
more »
« less
This content will become publicly available on September 16, 2025
Genetic Algorithm-Based Data-Driven Process Selection System for Additive Manufacturing in Industry 4.0
Additive manufacturing (AM) has impacted the manufacturing of complex three-dimensional objects in multiple materials for a wide array of applications. However, additive manufacturing, as an upcoming field, lacks automated and specific design rules for different AM processes. Moreover, the selection of specific AM processes for different geometries requires expert knowledge, which is difficult to replicate. An automated and data-driven system is needed that can capture the AM expert knowledge base and apply it to 3D-printed parts to avoid manufacturability issues. This research aims to develop a data-driven system for AM process selection within the design for additive manufacturing (DFAM) framework for Industry 4.0. A Genetic and Evolutionary Feature Weighting technique was optimized using 3D CAD data as an input to identify the optimal AM technique based on several requirements and constraints. A two-stage model was developed wherein the stage 1 model displayed average accuracies of 70% and the stage 2 model showed higher average accuracies of up to 97.33% based on quantitative feature labeling and augmentation of the datasets. The steady-state genetic algorithm (SSGA) was determined to be the most effective algorithm after benchmarking against estimation of distribution algorithm (EDA) and particle swarm optimization (PSO) algorithms, respectively. The output of this system leads to the identification of optimal AM processes for manufacturing 3D objects. This paper presents an automated design for an additive manufacturing system that is accurate and can be extended to other 3D-printing processes.
more »
« less
- Award ID(s):
- 2434487
- PAR ID:
- 10560289
- Publisher / Repository:
- MDPI
- Date Published:
- Journal Name:
- Materials
- Volume:
- 17
- Issue:
- 18
- ISSN:
- 1996-1944
- Page Range / eLocation ID:
- 4544
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Additive Manufacturing (AM) provides the advantage of producing complex shapes that are not possible through traditional cutting processes. Along with this line, assembly-based part design in AM creates some opportunities for productivity improvement. This paper proposes an improved optimization algorithm for part separation (OAPS) in assembly-based part design in additive manufacturing. For a given object, previous studies often provide the optimal number of parts resulting from cutting processes and their corresponding orientation to obtain the minimum processing time. During part separation, the cutting plane direction to generate subparts for assembly was often selected randomly in previous studies. The current work addresses the use of random cutting planes for part separation and instead uses the hill climbing optimization technique to generate the cutting planes to separate the parts. The OAPS provides the optimal number of assemblies and the build orientation of the parts for the minimum processing time. Two examples are provided to demonstrate the application of OAPS algorithm.more » « less
-
Abstract Nature provides us with a large number of functional material systems consisting of hierarchical structures, where significant variations in dimensions are present. Such hierarchical structures are difficult to build by traditional manufacturing processes due to manufacturing limitations. Nowadays, three-dimensional (3D) objects with complex structures can be built by gradually accumulating in a layer-based additive manufacturing (AM); however, the hierarchical structure measured from macroscale to nanoscale sizes still raises significant challenges to the AM processes, whose manufacturing capability is intrinsically specified within a certain scope. It is desired to develop a multiscale AM process to narrow this gap between scales of feature in hierarchical structures. This research aims to investigate an integration approach to fabricating hierarchical objects that have macro-, micro-, and nano-scales features in an object. Firstly, the process setup and the integrated process of two-photon polymerization (TPP), immersed surface accumulation (ISA), and mask image projection-based stereolithography (MIP-SL) were introduced to address the multiscale fabrication challenge. Then, special hierarchical design and process planning toward integrating multiple printing processes are demonstrated. Lastly, we present two test cases built by our hierarchical printing method to validate the feasibility and efficiency of the proposed multiscale hierarchical printing approach. The results demonstrated the capability of the developed multiscale 3D printing process and showed its future potential in various novel applications, such as optics, microfluidics, cell culture, as well as interface technology.more » « less
-
Convolutional neural network (CNN), a type of deep learning algorithm, is a powerful tool for analyzing visual images. It has been actively investigated to monitor metal additive manufacturing (AM) processes for quality control and has been proven effective. However, typical CNN algorithms inherently have two issues when used in metal AM processes. First, in many cases, acquiring datasets with sufficient quantity and quality, as well as necessary information, is challenging because of technical difficulties and/or cost intensiveness. Second, determining a near-optimal CNN model takes considerable effort and is time-consuming. This is because the types and quality of datasets can be significantly different with respect to different AM processes and materials. The study proposes a novel concatenated ensemble learning method to obtain a flexible and robust algorithm for in-situ anomaly detection in wire + arc additive manufacturing (WAAM), a type of wire-based direct energy deposition (DED) process. For this, data, as well as machine learning models, were seamlessly integrated to overcome the limitations and difficulties in acquiring sufficient data and finding a near-optimal machine learning model. Using inexpensively obtainable and comprehensive datasets from the WAAM process, the proposed method was investigated and validated. In contrast to the one-dimensional and two-dimensional CNN models’ accuracies of 81.6 % and 88.6 %, respectively, the proposed concatenated ensemble model achieved an accuracy of 98 %.more » « less
-
Abstract Additive manufacturing (AM) is a rapidly growing technology within the industry and education sectors. Despite this, there lacks a comprehensive tool to guide AM-novices in evaluating the suitability of a given design for fabrication by the range of AM processes. Existing design for additive manufacturing (DfAM) evaluation tools tend to focus on only certain key process-dependent DfAM considerations. By contrast the purpose of this research is to propose a tool that guides a user to comprehensively evaluate their chosen design and educates the user on an appropriate DfAM strategy. The tool incorporates both opportunistic and restrictive elements, integrates the seven major AM processes and outputs an evaluative score and recommends processes and improvements for the input design. The paper presents a thorough framework for this evaluation tool and details the inclusion of features such as dual-DfAM consideration, process recommendations, and a weighting system for restrictive DfAM. The result is a detailed recommendation output that helps users to determine not only “can you print your design” but also “should you print your design” by combining several key research studies to build a comprehensive user design tool. This research demonstrates the potential of the framework through a series of case studies geometries. The preliminary framework presented in this paper establishes a foundation for future studies to refine the tool’s accuracy using more data and expert analysis.more » « less
