Use of machine learning algorithms for surface roughness prediction of printed parts in polyvinyl butyral via fused deposition modeling

Author(s):  
Azahara Cerro ◽  
Pablo E. Romero ◽  
Okan Yiğit ◽  
Andres Bustillo
Author(s):  
Dazhong Wu ◽  
Yupeng Wei ◽  
Janis Terpenny

To realize high quality, additively manufactured parts, real-time process monitoring and advanced predictive modeling tools are crucial for accelerating quality assurance and quality control in additive manufacturing. While previous research has demonstrated the effectiveness of physics- and model-based diagnosis and prognosis for additive manufacturing, very little research has been reported on real-time monitoring and prediction of surface roughness in fused deposition modeling (FDM). This paper presents a new data-driven approach to surface roughness prediction in FDM. A real-time monitoring system is developed to monitor the health condition of a 3D printer and FDM processes using multiple sensors. A predictive model is built by random forests (RFs). Experimental results have shown that the predictive model is capable of predicting the surface roughness of a printed part with very high accuracy.


Author(s):  
Mohammad Taufik ◽  
Prashant K. Jain

Surface roughness prediction studies in fused deposition modeling (FDM) process are usually based on a perimeter profile of each deposited layer. This study categorizes three types of build edge profile composed of perimeter, raster, and combination of both layer deposition patterns, which have been considered to reduce the predictive error of roughness models. Furthermore, an innovative approach based on combination of theoretical and empirical methods is used to analyze and predict the randomness in the geometry of build edge profiles. The same methodology is used to model the roughness profile and surface roughness behaviors. The proposed models have been tested for robustness against varying build orientations and with data available in the existing literature. The robustness of the proposed models is compared with the existing models. The results clearly demonstrate that the proposed models are very useful in reducing prediction errors.


2021 ◽  
Vol 896 ◽  
pp. 29-37
Author(s):  
Ján Milde ◽  
František Jurina ◽  
Jozef Peterka ◽  
Patrik Dobrovszký ◽  
Jakub Hrbál ◽  
...  

The article focused on the influence of part orientation on the surface roughness of cuboid parts during the process of fabricating by FDM technology. The components, in this case, is simple cuboid part with the dimensions 15 mm x 15mm x 30 mm. A geometrical model is defined that considers the shape of the material filaments after deposition, to define a theoretical roughness profile, for a certain print orientation angle. Five different print orientations in the X-axis of the cuboid part were set: 0°, 30°, 45°, 60°, and 90°. According to previous research in the field of FDM technology by the author, the internal structure (infill) was set at the value of 70%. The method of 3D printing was the Fused Deposition Modeling (FDM) and the material used in this research was thermoplastic ABS (Acrylonitrile butadiene styrene). For each setting, there were five specimens (twenty five prints in total). Prints were fabricated on a Zortrax M200 3D printer. After the 3D printing, the surface “A” was investigated by portable surface roughness tester Mitutoyo SJ-210. Surface roughness in the article is shown in the form of graphs (Fig.7). Results show increase in part roughness with increasing degree of part orientation. When the direction of applied layers on the measured surface was horizontal, significant improvement in surface roughness was observed. Findings in this paper can be taken into consideration when designing parts, as they can contribute in achieving lower surface roughness values.


2021 ◽  
pp. 251659842110311
Author(s):  
Shrikrishna Pawar ◽  
Dhananjay Dolas1

Fused deposition modeling (FDM) is one of the most commonly used additive manufacturing (AM) technologies, which has found application in industries to meet the challenges of design modifications without significant cost increase and time delays. Process parameters largely affect the quality characteristics of AM parts, such as mechanical strength and surface finish. This article aims to optimize the parameters for enhancing flexural strength and surface finish of FDM parts. A total of 18 test specimens of polycarbonate (PC)-ABS (acrylonitrile–butadiene–styrene) material are printed to analyze the effect of process parameters, viz. layer thickness, build orientation, and infill density on flexural strength and surface finish. Empirical models relating process parameters with responses have been developed by using response surface regression and further analyzed by analysis of variance. Main effect plots and interaction plots are drawn to study the individual and combined effect of process parameters on output variables. Response surface methodology was employed to predict the results of flexural strength 48.2910 MPa and surface roughness 3.5826 µm with an optimal setting of parameters of 0.14-mm layer thickness and 100% infill density along with horizontal build orientation. Experimental results confirm infill density and build orientation as highly significant parameters for impacting flexural strength and surface roughness, respectively.


Sign in / Sign up

Export Citation Format

Share Document