Learning-based error modeling in FDM 3D printing process

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Paschalis Charalampous ◽  
Ioannis Kostavelis ◽  
Theodora Kontodina ◽  
Dimitrios Tzovaras
Keyword(s):  
Machine Learning ◽  
Computer Aided Design ◽  
Fused Deposition Modeling ◽  
Real Life ◽  
Deep Understanding ◽  
Error Modeling ◽  
Machine Learning Algorithms ◽  
Content Type ◽  
Fused Deposition ◽  
The Impact

Purpose Additive manufacturing (AM) technologies are gaining immense popularity in the manufacturing sector because of their undisputed ability to construct geometrically complex prototypes and functional parts. However, the reliability of AM processes in providing high-quality products remains an open and challenging task, as it necessitates a deep understanding of the impact of process-related parameters on certain characteristics of the manufactured part. The purpose of this study is to develop a novel method for process parameter selection in order to improve the dimensional accuracy of manufactured specimens via the fused deposition modeling (FDM) process and ensure the efficiency of the procedure. Design/methodology/approach The introduced methodology uses regression-based machine learning algorithms to predict the dimensional deviations between the nominal computer aided design (CAD) model and the produced physical part. To achieve this, a database with measurements of three-dimensional (3D) printed parts possessing primitive geometry was created for the formulation of the predictive models. Additionally, adjustments on the dimensions of the 3D model are also considered to compensate for the overall shape deviations and further improve the accuracy of the process. Findings The validity of the suggested strategy is evaluated in a real-life manufacturing scenario with a complex benchmark model and a freeform shape manufactured in different scaling factors, where various sets of printing conditions have been applied. The experimental results exhibited that the developed regressive models can be effectively used for printing conditions recommendation and compensation of the errors as well. Originality/value The present research paper is the first to apply machine learning-based regression models and compensation strategies to assess the quality of the FDM process.

scholarly journals The impact of process parameters on mechanical properties of parts fabricated in PLA with an open-source 3-D printer

2015 ◽  
Vol 21 (5) ◽  
pp. 604-617 ◽  
Author(s):  
Antonio Lanzotti ◽  
Marzio Grasso ◽  
Gabriele Staiano ◽  
Massimo Martorelli
Keyword(s):  
Mechanical Properties ◽  
Open Source ◽  
Process Parameters ◽  
Computer Aided Design ◽  
Fused Deposition Modeling ◽  
Testing Machine ◽  
Main Process ◽  
Content Type ◽  
Fused Deposition ◽  
The Impact

Purpose – This study aims to quantify the ultimate tensile strength and the nominal strain at break (ɛf) of printed parts made from polylactic acid (PLA) with a Replicating Rapid prototyper (Rep-Rap) 3D printer, by varying three important process parameters: layer thickness, infill orientation and the number of shell perimeters. Little information is currently available about mechanical properties of parts printed using open-source, low-cost 3D printers. Design/methodology/approach – A computer-aided design model of a tensile test specimen was created, conforming to the ASTM:D638. Experiments were designed, based on a central composite design. A set of 60 specimens, obtained from combinations of selected parameters, was printed on a Rep-Rap Prusa I3 in PLA. Testing was performed using a JJ Instruments – T5002-type tensile testing machine and the load was measured using a load cell of 1,100 N. Findings – This study investigated the main impact of each process parameter on mechanical properties and the effects of interactions. The use of a response surface methodology allowed the proposition of an empirical model which connects process parameters and mechanical properties. Even though results showed a high variability, additional ideas on how to understand the impact of process parameters are suggested in this paper. Originality/value – On the basis of experimental results, it is possible to obtain practical suggestions to set common process parameters in relation to mechanical properties. Experiments discussed in the present paper provide a variety of data and insight regarding the relationship among the main process parameters and the stiffness and strength of fused deposition modeling-printed parts made from PLA. In particular, this paper underlines the shortage in existing literature concerning the impact of process parameters on the elastic modulus and the strain to failure for the PLA. The experimental data produced show a good degree of compliance with analytical formulations and other data found in literature.

Effect of layer thickness on irreversible thermal expansion and interlayer strength in fused deposition modeling

2017 ◽  
Vol 23 (5) ◽  
pp. 943-953 ◽  
Author(s):  
Anthony A. D’Amico ◽  
Analise Debaie ◽  
Amy M. Peterson
Keyword(s):  
Mechanical Properties ◽  
Thermal Expansion ◽  
Flexural Strength ◽  
Layer Thickness ◽  
Fused Deposition Modeling ◽  
Thermal Strain ◽  
Content Type ◽  
Fused Deposition ◽  
Deposition Modeling ◽  
The Impact

Purpose The aim of this paper is to examine the impact of layer thickness on irreversible thermal expansion, residual stress and mechanical properties of additively manufactured parts. Design/methodology/approach Samples were printed at several layer thicknesses, and their irreversible thermal expansion, tensile strength and flexural strength were determined. Findings Irreversible thermal strain increases with decreasing layer thickness, up to 22 per cent strain. Tensile and flexural strengths exhibited a peak at a layer thickness of 200 μm although the maximum was not statistically significant at a 95 per cent confidence interval. Tensile strength was 54 to 97 per cent of reported values for injection molded acrylonitrile butadiene styrene (ABS) and 29 to 73 per cent of those reported for bulk ABS. Flexural strength was 18 to 41 per cent of reported flexural strength for bulk ABS. Practical implications The large irreversible thermal strain exhibited that corresponding residual stresses could lead to failure of additively manufactured parts over time. Additionally, the observed irreversible thermal strains could enable thermally responsive shape in additively manufactured parts. Variation in mechanical properties with layer thickness will also affect manufactured parts. Originality/value Tailorable irreversible thermal strain of this magnitude has not been previously reported for additively manufactured parts. This strain occurs in parts made with both high-end and consumer grade fused deposition modeling machines. Additionally, the impact of layer thickness on tensile and flexural properties of additively manufactured parts has received limited attention in the literature.

An explainable prediction framework for engineering problems: case studies in reinforced concrete members modeling

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Amirhessam Tahmassebi ◽  
Mehrtash Motamedi ◽  
Amir H. Alavi ◽  
Amir H. Gandomi
Keyword(s):  
Machine Learning ◽  
Case Studies ◽  
Failure Modes ◽  
Statistical Significance ◽  
Deep Understanding ◽  
Machine Learning Algorithms ◽  
Learning Models ◽  
Content Type ◽  
Engineering Problems ◽  
Machine Learning Models

PurposeEngineering design and operational decisions depend largely on deep understanding of applications that requires assumptions for simplification of the problems in order to find proper solutions. Cutting-edge machine learning algorithms can be used as one of the emerging tools to simplify this process. In this paper, we propose a novel scalable and interpretable machine learning framework to automate this process and fill the current gap.Design/methodology/approachThe essential principles of the proposed pipeline are mainly (1) scalability, (2) interpretibility and (3) robust probabilistic performance across engineering problems. The lack of interpretibility of complex machine learning models prevents their use in various problems including engineering computation assessments. Many consumers of machine learning models would not trust the results if they cannot understand the method. Thus, the SHapley Additive exPlanations (SHAP) approach is employed to interpret the developed machine learning models.FindingsThe proposed framework can be applied to a variety of engineering problems including seismic damage assessment of structures. The performance of the proposed framework is investigated using two case studies of failure identification in reinforcement concrete (RC) columns and shear walls. In addition, the reproducibility, reliability and generalizability of the results were validated and the results of the framework were compared to the benchmark studies. The results of the proposed framework outperformed the benchmark results with high statistical significance.Originality/valueAlthough, the current study reveals that the geometric input features and reinforcement indices are the most important variables in failure modes detection, better model can be achieved with employing more robust strategies to establish proper database to decrease the errors in some of the failure modes identification.

Novel topological design of 3D Kagome structure for additive manufacturing

2018 ◽  
Vol 24 (2) ◽  
pp. 261-269 ◽  
Author(s):  
Rong Wang ◽  
Jianzhong Shang ◽  
Xin Li ◽  
Zhuo Wang ◽  
Zirong Luo
Keyword(s):  
3D Printing ◽  
Computer Aided Design ◽  
Fused Deposition Modeling ◽  
Lattice Structure ◽  
Topology Design ◽  
Original Structure ◽  
Compression Tests ◽  
Content Type ◽  
Fused Deposition ◽  
And Topology

Purpose This paper aims to present a new topology method in designing the lightweight and complex structures for 3D printing. Design/methodology/approach Computer-aided design (CAD) and topology design are the two main approaches for 3D truss lattices designing in 3D printing. Though these two ways have their own advantages and have been used by the researchers in different engineering situations, these two methods seem to be incompatible. A novel topology method is presented in this paper which can combine the merits of both CAD and topology design. It is generally based on adding materials to insufficient parts in a given structure so the resulting topology evolves toward an optimum. Findings By using the topology method, an optimized-Kagome structure is designed and both 3D original-Kagome structure and 3D optimized-Kagome structure are manufactured by fused deposition modeling (FDM) 3D printer with ABS and the compression tests results show that the 3D optimized-Kagome has a higher specific stiffness and strength than the original one. Originality/value The presented topology method is the first work that using the original structure-based topology algorithm other than a boundary condition-based topology algorithm for 3D printing lattice and it can be considered as general way to optimize a commonly used light-weight lattice structure in strength and stiffness.

Dynamic Behavior of Acrylonitrile Butadiene Styrene Under Impact Loads

2015 ◽  
Author(s):  
Alex Peterson ◽  
Denzell Bolling ◽  
Adewale Olasumboye ◽  
Ed Habtour ◽  
Jaret C. Riddick ◽  
...  
Keyword(s):  
Strain Rate ◽  
Computer Aided Design ◽  
Fused Deposition Modeling ◽  
Split Hopkinson Pressure Bar ◽  
Impact Load ◽  
Acrylonitrile Butadiene Styrene ◽  
Fused Deposition ◽  
Computer Aided ◽  
The Impact ◽  
Butadiene Styrene

This paper is aimed at providing a better understanding of the potential energy absorption benefits of components fabricated using fused deposition modeling (FDM) additive manufacturing. Using FDM, it is possible to print three-dimensional (3-D) objects created through the use of computer-aided design and computer-aided manufacturing software coupled with computer codes that enable the layer-by-layer deposition of material to form the 3-D component. Also known as direct digital manufacturing or 3-D printing, AM offers the benefit of being able to rotate printing orientation during processing to manipulate the design build and ultimately control mechanical and structural properties when subjected to dynamic loads. In this work, tensile test specimens were first fabricated to characterize the general mechanical behavior of the of 3D-printed Acrylonitrile Butadiene Styrene (ABS) material to assess its potential strain rate dependency. The mechanical evaluation under the quasi-static load was also necessary to determine the properties necessary to characterize the dynamic evolution of ABS in compression at various strain rates. ABS specimens were subsequently subjected to high strain rate deformation through the use of the Split Hopkinson Pressure Bar. During compression a new phenomenon described as a multistage collapse in which the samples undergo multiple stages of contraction and expansion was observed as the impact load was applied.

3D printing of generative art using the assembly and deformation of direction-specified parts

2016 ◽  
Vol 22 (4) ◽  
pp. 636-644 ◽  
Author(s):  
Yaususi Kanada
Keyword(s):  
3D Printing ◽  
Computer Aided Design ◽  
Fused Deposition Modeling ◽  
Three Dimensional ◽  
3D Models ◽  
Control Technique ◽  
Content Type ◽  
Fused Deposition ◽  
A New Technique ◽  
Printing Direction

Purpose A methodology for designing and printing three-dimensional (3D) objects with specified printing-direction using fused deposition modeling (FDM), which was proposed by a previous paper, enables the expression of natural directions, such as hair, fabric or other directed textures, in modeled objects. This paper aims to enhance this methodology for creating various shapes of generative visual objects with several specialized attributes. Design/methodology/approach The proposed enhancement consists of two new methods and a new technique. The first is a method for “deformation”. It enables deforming simple 3D models to create varieties of shapes much more easily in generative design processes. The second is the spiral/helical printing method. The print direction (filament direction) of each part of a printed object is made consistent by this method, and it also enables seamless printing results and enables low-angle overhang. The third, i.e. the light-reflection control technique, controls the properties of filament while printing with transparent polylactic acid. It enables the printed objects to reflect light brilliantly. Findings The proposed methods and technique were implemented in a Python library and evaluated by printing various shapes, and it is confirmed that they work well, and objects with attractive attributes, such as the brilliance, can be created. Research limitations/implications The methods and technique proposed in this paper are not well-suited to industrial prototyping or manufacturing that require strength or intensity. Practical implications The techniques proposed in this paper are suited for generatively producing various a small number of products with artistic or visual properties. Originality/value This paper proposes a completely different methodology for 3D printing than the conventional computer-aided design (CAD)-based methodology and enables products that cannot be created by conventional methods.

Comparative evaluation of an open-source FDM system

2014 ◽  
Vol 20 (3) ◽  
pp. 205-214 ◽  
Author(s):  
Wayne M. Johnson ◽  
Matthew Rowell ◽  
Bill Deason ◽  
Malik Eubanks
Keyword(s):  
Open Source ◽  
Computer Aided Design ◽  
Laser Scanning ◽  
Fused Deposition Modeling ◽  
Low Cost ◽  
Dimensional Accuracy ◽  
Scanning System ◽  
Content Type ◽  
Geometric Dimensioning And Tolerancing ◽  
Fused Deposition

Purpose – The purpose of this paper is to present a qualitative and quantitative comparison and evaluation of an open-source fused deposition modeling (FDM) additive manufacturing (AM) system with a proprietary FDM AM system based on the fabrication of a custom benchmarking model. Design/methodology/approach – A custom benchmarking model was fabricated using the two AM systems and evaluated qualitatively and quantitatively. The fabricated models were visually inspected and scanned using a 3D laser scanning system to examine their dimensional accuracy and geometric dimensioning and tolerancing (GD&T) performance with respect to the computer-aided design (CAD) model geometry. Findings – The open-source FDM AM system (CupCake CNC) successfully fabricated most of the features on the benchmark, but the model did suffer from greater thermal warping and surface roughness, and limitations in the fabrication of overhang structures compared to the model fabricated by the proprietary AM system. Overall, the CupCake CNC provides a relatively accurate, low-cost alternative to more expensive proprietary FDM AM systems. Research limitations/implications – This work is limited in the sample size used for the evaluation. Practical implications – This work will provide the public and research AM communities with an improved understanding of the performance and capabilities of an open-source AM system. It may also lead to increased use of open-source systems as research testbeds for the continued improvement of current AM processes, and the development of new AM system designs and processes. Originality/value – This study is one of the first comparative evaluations of an open-source AM with a proprietary AM system.

scholarly journals Enhancing Surface Fault Detection Using Machine Learning for 3D Printed Products

2021 ◽  
Vol 4 (2) ◽  
pp. 34
Author(s):  
Vaibhav Kadam ◽  
Satish Kumar ◽  
Arunkumar Bongale ◽  
Seema Wazarkar ◽  
Pooja Kamat ◽  
...  
Keyword(s):  
Machine Learning ◽  
Fault Detection ◽  
Computer Aided Design ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Fused Deposition Modelling ◽  
Layer By Layer ◽  
Fused Deposition ◽  
Detection Approach ◽  
3D Printed

In the era of Industry 4.0, the idea of 3D printed products has gained momentum and is also proving to be beneficial in terms of financial and time efforts. These products are physically built layer-by-layer based on the digital Computer Aided Design (CAD) inputs. Nonetheless, 3D printed products are still subjected to defects due to variation in properties and structure, which leads to deterioration in the quality of printed products. Detection of these errors at each layer level of the product is of prime importance. This paper provides the methodology for layer-wise anomaly detection using an ensemble of machine learning algorithms and pre-trained models. The proposed combination is trained offline and implemented online for fault detection. The current work provides an experimental comparative study of different pre-trained models with machine learning algorithms for monitoring and fault detection in Fused Deposition Modelling (FDM). The results showed that the combination of the Alexnet and SVM algorithm has given the maximum accuracy. The proposed fault detection approach has low experimental and computing costs, which can easily be implemented for real-time fault detection.

A study on revolute joints in 3D-printed non-assembly mechanisms

2016 ◽  
Vol 22 (6) ◽  
pp. 901-933 ◽  
Author(s):  
Xiangzhi Wei ◽  
Yaobin Tian ◽  
Ajay Joneja
Keyword(s):  
Computer Aided Design ◽  
Fused Deposition Modeling ◽  
Dynamic Performance ◽  
Axial Direction ◽  
Physical Models ◽  
Content Type ◽  
Cad System ◽  
Fused Deposition ◽  
Revolute Joints ◽  
3D Printed

Purpose The purpose of this paper is to explore a new design for the journal of revolute joints that can improve the dynamic performance of 3D printed non-assembly mechanisms. Design/methodology/approach The design improves upon previous proposed designs that use drum-shaped journals in place of cylindrical ones. The authors introduce an innovative new worm-shaped journal. The authors also propose a systematic and efficient procedure to identify the best parameter values for defining the exact shape of the journal. Using three different mechanisms for the experiments, the paper constructs 3D computer-aided design (CAD) models using the design as well as cylindrical and drum-shaped designs. The parameters for the optimum geometry for each type of design are determined by dynamic simulation using the CAD system. Actual prototypes of the ideal designs are constructed using a commercial fused deposition modeling (FDM) machine for physical comparisons. Findings This paper shows that in simulations as well in physical models, the proposed design outperforms the previous designs significantly. Research limitations/implications This study was mainly focused on the FDM process, and the authors have not yet explored other processes. One limitation of this approach is that it requires the mechanism to be printed along the axial direction of the revolute joint. Originality/value This paper proposes a new design for the journal in 3D printed revolute joints. A clear advantage of the design is that it can easily be used to replace normal revolute joins in non-assembly models without affecting any other parts of the geometry. Therefore, with relatively little effort, the authors can print non-assembly mechanisms with improved dynamic performance.

Reverse Engineering a Hedge Trimmer: A Practical Approach to Incorporate Geometric Dimensioning and Tolerancing (GD&T) Effectively in an Undergraduate Freshman Engineering Course

2020 ◽  
Author(s):  
Tikran Kocharian ◽  
Sanjivan Manoharan
Keyword(s):  
Reverse Engineering ◽  
Computer Aided Design ◽  
Fused Deposition Modeling ◽  
Real Life ◽  
Cad Model ◽  
Geometric Dimensioning And Tolerancing ◽  
Fused Deposition ◽  
Dimensioning And Tolerancing ◽  
Engineering Drawings ◽  
Broad Subject

Abstract Geometric Dimensioning and Tolerancing (GD&T), due to the inherent complexity, is a challenging topic to teach and learn, especially at the undergraduate freshman level. Many institutes either cover GD&T on a superficial level or choose to overlook it. Incorporating such a broad subject in an already busy curricula remains a major challenge for many academic institutes, including ours. The knowledge and skill level of our students in GD&T at the beginning of their co-op is a major concern for several employers. These employers have to expend significant resources to train our students and graduates. To address this growing concern, a practical project was incorporated into a freshman introductory engineering course; a Ryobi hedge trimmer Model No. RY39500 was utilized. The students were divided into five groups, and each group was given a mechanical component from the assembly. First, each group was tasked with taking the necessary measurements to create a Computer Aided Design (CAD) model of their component in an effort to commence the reverse engineering process. The CAD model was then additively manufactured using fused deposition modeling. A detailed drawing of each component was created and GD&T concepts and symbols were applied to the drawing following ASME/ANSI Y14.5-2009 standards. The project was very well received by the students. It enhanced their understanding and skills necessary to implement GD&T concepts and symbols both in practice and in preparing engineering drawings. The 3-D printed parts were shared among the groups and the manufactured parts were fit together to replicate the real life assembling.

Sign in / Sign up

Export Citation Format

Share Document