Predicting Product Precision in Fused Deposition Modeling Based on Artificial Neural Network

2011 ◽  
Vol 4 (6) ◽  
pp. 2193-2197 ◽  
Author(s):  
Liangbo Ji ◽  
Tianrui Zhou
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Fused Deposition Modeling ◽  
Fused Deposition ◽  
Deposition Modeling ◽  
Artificial Neural

Knowledge-Based Design of Artificial Neural Network Topology for Additive Manufacturing Process Modeling: A New Approach and Case Study for Fused Deposition Modeling

2018 ◽  
Vol 141 (2) ◽  
Author(s):  
Hari P. N. Nagarajan ◽  
Hossein Mokhtarian ◽  
Hesam Jafarian ◽  
Saoussen Dimassi ◽  
Shahriar Bakrani-Balani ◽  
...  
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Additive Manufacturing ◽  
Fused Deposition Modeling ◽  
Expert Knowledge ◽  
Fused Deposition ◽  
Knowledge Based ◽  
Deposition Modeling ◽  
Artificial Neural

Additive manufacturing (AM) continues to rise in popularity due to its various advantages over traditional manufacturing processes. AM interests industry, but achieving repeatable production quality remains problematic for many AM technologies. Thus, modeling different process variables in AM using machine learning can be highly beneficial in creating useful knowledge of the process. Such developed artificial neural network (ANN) models would aid designers and manufacturers to make informed decisions about their products and processes. However, it is challenging to define an appropriate ANN topology that captures the AM system behavior. Toward that goal, an approach combining dimensional analysis conceptual modeling (DACM) and classical ANNs is proposed to create a new type of knowledge-based ANN (KB-ANN). This approach integrates existing literature and expert knowledge of the AM process to define a topology for the KB-ANN model. The proposed KB-ANN is a hybrid learning network that encompasses topological zones derived from knowledge of the process and other zones where missing knowledge is modeled using classical ANNs. The usefulness of the method is demonstrated using a case study to model wall thickness, part height, and total part mass in a fused deposition modeling (FDM) process. The KB-ANN-based model for FDM has the same performance with better generalization capabilities using fewer weights trained, when compared to a classical ANN.

Knowledge-Based Optimization of Artificial Neural Network Topology for Process Modeling of Fused Deposition Modeling

2018 ◽  
Author(s):  
Hari P. N. Nagarajan ◽  
Hesam Jafarian ◽  
Azarakhsh Hamedi ◽  
Hossein Mokhtarian ◽  
Romaric Prod'hon ◽  
...  
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Fused Deposition Modeling ◽  
Performance Metrics ◽  
Expert Knowledge ◽  
Production Quality ◽  
Fused Deposition ◽  
Knowledge Based ◽  
Deposition Modeling ◽  
Artificial Neural

Additive manufacturing (AM) continues to rise in popularity due to its various advantages over traditional manufacturing processes. AM interests industry, but achieving repeatable production quality remains problematic for many AM technologies. Thus, modeling the influence of process variables on the production quality in AM can be highly beneficial in creating useful knowledge of the process and product. An approach combining dimensional analysis conceptual modeling, mutual information based analysis, experimental sampling, factors selection, and modeling based on Knowledge-Based Artificial Neural Network (KB-ANN) is proposed for Fused Deposition Modeling (FDM) process. KB-ANN reduces the excessive amount of training samples required in traditional neural networks. The developed KB-ANN’s topology for FDM, integrates existing literature and expert knowledge of the process. The KB-ANN is compared to conventional ANN using prescribed performance metrics. This research presents a methodology to concurrently perform experiments, classify influential factors, limit the effect of noise in the modeled system, and model using KB-ANN. This research can contribute to the qualification efforts of AM technologies.

Feature Extraction and Optimum Part Deposition Orientation for FDM

2015 ◽  
Vol 793 ◽  
pp. 642-646 ◽  
Author(s):  
Khairul Fauzi Karim ◽  
D. Hazry ◽  
A.H. Zulkifli ◽  
S. Faiz Ahmed ◽  
Zuradzman Mohamad Razlan ◽  
...  
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Feature Extraction ◽  
Fused Deposition Modeling ◽  
Support Structure ◽  
Fused Deposition ◽  
Deposition Modeling ◽  
Artificial Neural ◽  
Artificial Neural Network Ann ◽  
Selection Of

Support generation is an essential for Fused Deposition Modeling (FDM) process which is dependent on part deposition orientation. Various part deposition orientation result in formation of different support and non-support features. Present work focuses on extracting the support features containing Externally-Supported Features (ESF) which are able to determine the volume and number of support structure. The methodology proposed in this work uses these information as an input for Artificial Neural Network (ANN) in order to automate the selection of optimum part deposition orientation. The results produced in present methodology can be predicted and are in agreement with the results published earlier.

Precision Model of Predicting FDM Rapid Prototype Based on BP Neural Network

2008 ◽  
Vol 392-394 ◽  
pp. 891-897
Author(s):  
G.Q. Shang ◽  
C.H. Sun ◽  
X.F. Chen ◽  
J.H. Du
Keyword(s):  
Neural Network ◽  
Bp Neural Network ◽  
Fused Deposition Modeling ◽  
Rapid Prototype ◽  
Fused Deposition ◽  
Novel Approach ◽  
Deposition Modeling ◽  
Hidden Layer ◽  
Parts Manufacturing ◽  
Bp Neural Network Model

Fused deposition modeling (FDM) has been widely applied in complex parts manufacturing and rapid tooling and so on. The precision of prototype was affected by many factors during FDM, so it is difficult to depict the process using a precise mathematical model. A novel approach for establishing a BP neural network model to predict FDM prototype precision was proposed in this paper. Firstly, based on analyzing effect of each factor on prototyping precision, some key parameters were confirmed to be feature parameters of BP neural networks. Then, the dimensional numbers of input layer and middle hidden layer were confirmed according to practical conditions, and therefore the model structure was fixed. Finally, the structure was trained by a great lot of experimental data, a model of BP neural network to predict precision of FDM prototype was constituted. The results show that the error can be controlled within 10%, which possesses excellent capability of predicting precision.

Dimensional Prediction for FDM Machines Using Artificial Neural Network and Support Vector Regression

2019 ◽  
Author(s):  
Jiaqi Lyu ◽  
Souran Manoochehri
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Linear Regression ◽  
Support Vector Regression ◽  
Process Parameters ◽  
Multivariate Linear Regression ◽  
Support Vector ◽  
Ann Model ◽  
Fused Deposition ◽  
Artificial Neural

Abstract With the development of Fused Deposition Modeling (FDM) technology, the quality of fabricated parts is getting more attention. The present study highlights the predictive model for dimensional accuracy in the FDM process. Three process parameters, namely extruder temperature, layer thickness, and infill density, are considered in the model. To achieve better prediction accuracy, three models are studied, namely multivariate linear regression, Artificial Neural Network (ANN), and Support Vector Regression (SVR). The models are used to characterize the complex relationship between the input variables and dimensions of fabricated parts. Based on the experimental data set, it is found that the ANN model performs better than the multivariate linear regression and SVR models. The ANN model is able to study more quality characteristics of fabricated parts with more process parameters of FDM.

scholarly journals Enhancing 3D Printing Producibility in Polylactic Acid Using Fused Filament Fabrication Fused Deposition Modelling and Machine Learning

2020 ◽  
Author(s):  
Mahmoud Moradi ◽  
M. Saleh Meiabadi ◽  
Mojtaba Karami Moghadam ◽  
Sina Ardabili ◽  
Shahab S. Band ◽  
...  
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Production Cost ◽  
Fused Deposition Modeling ◽  
Deformation Property ◽  
Fused Filament Fabrication ◽  
Fused Deposition ◽  
Surface Method ◽  
Deposition Modeling ◽  
Part Thickness

Abstract Polylactic Polylactic acid (PLA) is one of the high applicable material which is used in the 3D printers due to some significant features like its deformation property and affordable costacid (PLA) is brittle in nature with extensive deformation property. For improvement of the end-use quality, it is of significant importance to enhance the quality of Fused Filament Fabrication (FFF)fused deposition modeling (FDM)-printed objects in PLA. The purpose of this investigation is to boost toughness and to reduce the production cost of the FDMFFF-printed tensile test samples with the desired part thickness. Due to prevent from many numerous and idle printing samples the response Surface Method (RSM) is used.To attain the research purpose number of experiments are designed and analyzed by the Response Surface Method (RSM). The statistical analysis is performed to deal with this concern considering extruder temperature (ET), infill percentage (IP), and layer thickness (LT) as controlled factors. The tensile test specimens are printed based on the designed experiments, and the tensile strength tests are conducted by SANTAM 150 universal testing machine based on ASTM D638. The pattern for filling is designed based on honeycomb which is applied to produce lightweight and high-strength specimens. The area under Force- Extension curve up to fracture is acquired as the toughness of the printed specimens. This study also developed a modeling process using artificial neural network (ANN) and artificial neural network- genetic algorithm (ANN-GA) techniques to develop an accurate estimation for toughness, part thickness, and production cost dependent variables. Results were evaluated by correlation coefficient and RMSE values. According to the modeling results, ANN-GA as a hybrid machine learning (ML) technique could could successfully improveenhances the accuracy of modeling about 7.5, 11.5 and 4.5 % for toughness, part thickness, and production cost, respectively, in comparison with those for the single ANN method. On the other side, the optimization results confirm that the optimized specimen is cost-effective and able to comparatively undergo deformation, which enables the usability of printed PLA objects. The research is accomplished under the constraints of PLA compatibility with existing Fused Filament Fabrication fused deposition modeling installation, in the absence of the functional assistant of the machine in the absence of the functional assistant of the machine. Although the mechanical properties and dimensional accuracy of PLA have already been studied, there is little literature on the toughness of the printed PLA with honeycomb internal fill pattern.

scholarly journals Surface roughness prediction of FFF-fabricated workpieces by artificial neural network and Box–Behnken method

2021 ◽  
Vol 12 ◽  
pp. 17
Author(s):  
Karin Kandananond
Keyword(s):  
Neural Network ◽  
Surface Roughness ◽  
Artificial Neural Network ◽  
Layer Thickness ◽  
Prediction Equation ◽  
Cylindrical Shape ◽  
Fused Deposition ◽  
Bed Temperature ◽  
Artificial Neural ◽  
Printing Speed

Fused Filament Fabrication (FFF) or Fused Deposition Modelling (FDM) or three-dimension (3D) printing are rapid prototyping processes for workpieces. There are many factors which have a significant effect on surface quality, including bed temperature, printing speed, and layer thickness. This empirical study was conducted to determine the relationship between the above-mentioned factors and average surface roughness (Ra). Workpieces of cylindrical shape were fabricated by an FFF system with a Polylactic acid (PLA) filament. The surface roughness was measured at five different positions on the bottom and top surface. A response surface (Box-Behnken) method was utilised to design the experiment and statistically predict the response. The total number of treatments was sixteen, while five measurements (Ra1, Ra2, Ra3, Ra4 and Ra5) were carried out for each treatment. The settings of each factor were as follows: bed temperature (80, 85, and 90 °C), printing speed (40, 80 and 120 mm/s), and layer thickness (0.10, 0.25 and 0.40 mm). The prediction equation of surface roughness was then derived from the analysis. The same set of data was also used as the inputs for a machine learning method, an artificial neural network (ANN), to construct the prediction equation of surface roughness. Rectified linear unit (ReLU) was utilised as the activation function of ANN. Two training algorithms (resilient backpropagation with weight backtracking and globally convergent resilient backpropagation) were applied to train multi-layer perceptrons. Moreover, the different number of neurons in each hidden layer was also studied and compared. Another interesting aspect of this study is that the ANN was based on a limited number of training samples. Finally, the prediction errors of each method were compared, to benchmark the prediction performance of the two methods: Box-Behnken and ANN.

scholarly journals Modeling, analysis, and optimization of dimensional accuracy of FDM-fabricated parts using definitive screening design and deep learning feedforward artificial neural network

2021 ◽  
Vol 9 (1) ◽  
pp. 115-129
Author(s):  
Omar Ahmed Mohamed ◽  
Syed Hasan Masood ◽  
Jahar Lal Bhowmik
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Dimensional Accuracy ◽  
Second Order ◽  
Fused Deposition ◽  
Screening Design ◽  
Definitive Screening ◽  
Cylindrical Parts ◽  
Artificial Neural ◽  
Definitive Screening Design

AbstractAdditive manufacturing (AM) technologies such as fused deposition modeling (FDM) rely on the quality of manufactured products and the process capability. Currently, the dimensional accuracy and stability of any AM process is essential for ensuring that customer specifications are satisfied at the highest standard, and variations are controlled without significantly affecting the functioning of processes, machines, and product structures. This study aims to investigate the effects of FDM fabrication conditions on the dimensional accuracy of cylindrical parts. In this study, a new class of experimental design techniques for integrated second-order definitive screening design (DSD) and an artificial neural network (ANN) are proposed for designing experiments to evaluate and predict the effects of six important operating variables. By determining the optimum fabrication conditions to obtain better dimensional accuracies for cylindrical parts, the time consumption and number of complex experiments are reduced considerably in this study. The optimum fabrication conditions generated through a second-order DSD are verified with experimental measurements. The results indicate that the slice thickness, part print direction, and number of perimeters significantly affect the percentage of length difference, whereas the percentage of diameter difference is significantly affected by the raster-to-raster air gap, bead width, number of perimeters, and part print direction. Furthermore, the results demonstrate that a second-order DSD integrated with an ANN is a more attractive and promising methodology for AM applications.

Sign in / Sign up

Export Citation Format

Share Document