A neural network approach to the modelling and analysis of stereolithography processes

Lee, S H; Park, W S; Cho, H S; Zhang, W; Leu, Ming C.

doi:10.1243/0954405011519547

Cited by 5 publications

(5 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Polymer vat‐polymerization additive manufacturing (AM) technologies are frequently selected in dentistry to fabricate different devices such as casts, silicone indices, custom trays, surgical guides, positioning guides, interim restorations, and occlusal guards 1–4 . Even though the implementation of AM technologies is gradually increasing in restorative procedures, the optimal printing variables 5–13 that influence the manufacturing accuracy of each dental device based on the manufacturing trinomial selected, namely AM technology (stereolithography, direct light processing, or stereolithography liquid crystal display based), 14,15 3D printer (resolution and printer accuracy, 5,6 power of light source, wavelength power), 16,17 and resin (color, 18,19 polymerization initiators, and viscosity) remains unclear (Fig 1). 20–26 …”

Section: Figurementioning

confidence: 99%

Influence of the Rinsing Postprocessing Procedures on the Manufacturing Accuracy of Vat‐Polymerized Dental Model Material

Mostafavi

Methani

Piedra‐Cascón³

et al. 2021

Journal of Prosthodontics

View full text Add to dashboard Cite

Purpose: To evaluate the influence of rinsing solvents, namely isopropyl alcohol (IPA) and tripropylene glycol monomethyl ether (TPM), and rinsing times (5-, 7-, 9-, and 11-minutes) for the postprocessing procedures on the manufacturing accuracy of an additively manufactured dental model resin material. Material and Methods: The standard tessellation language (STL file) of the digital design of a bar (15 mm × 4 mm × 3 mm) was obtained. A resin dental material (E-Model Light; Envisiontec, Dearborn, MI) and a 3D printer (VIDA HD; Envisiontec) was selected to manufacture all the specimens using the STL file following the recommended printing parameters at a room temperature of 23°C. Two groups were generated based on the rinsing solvent used on the postprocessing procedures, namely isopropyl alcohol (IPA-group) and tripropylene glycol monomethyl ether (TPM-group). Each group was further divided into 4 subgroups (IPA-1 to IPA-4 and TPM-1 to TPM-4) depending on the rinsing time performed (5-, 7-, 9-, and 11minutes). Twenty specimens per subgroup were fabricated. The dimensions (length, width, and height) of all the specimens were measured using a low force digital caliper (Absolute Low Force Caliper Series 573; Mitutoyo, Takatsu-ku, Kawasaki, Kanagawa). Each measurement was performed 3 times and the mean value determined. The volume of each specimen was calculated using the formula V = l × w × h. Shapiro-Wilk test revealed that the data were not normally distributed. Data were analyzed using Kruskal-Wallis (α = 0.05), followed by pairwise Mann-Whitney U tests (α = 0.0018). Results: The IPA groups obtained significantly lower trueness and precision values compared with TPM groups (p < 0.0018). Among the IPA groups, IPA-1 subgroup obtained the highest trueness and precision values compared to the rest of the IPA subgroups. The TPM-1 and TPM-2 subgroups obtained the highest trueness and prevision values among the TPM group and among all the groups tested. No significant difference was found between the TMP-1 and TPM-2 subgroups (p > 0.0018). Conclusions: None of the manufacturing workflows tested were able to manufacture a perfect match of the bar virtual design dimensions. TPM solvent group obtained higher trueness and precision values compared to the IPA solvent group. The IPA-1 subgroup that replicated the manufacturer´s recommendations obtained the highest manufacturing accuracy among the IPA subgroup. TPM solvent used in a rinsing ultrasonic bath between 3 and 4 minutes followed by a second ultrasonic clean bath between 2 and 3 minutes of the just printed vat polymerized dental model specimens obtained the highest manufacturing accuracy values.

show abstract

Section: Figurementioning

confidence: 99%

Influence of the Rinsing Postprocessing Procedures on the Manufacturing Accuracy of Vat‐Polymerized Dental Model Material

Mostafavi

Methani

Piedra‐Cascón³

et al. 2021

Journal of Prosthodontics

View full text Add to dashboard Cite

show abstract

“…Algorithms, such as the ANNs, GA, case-based reasoning (CBR), GA methods coupled with data envelopment analysis, etc. have been widely applied to many fields such as bankruptcy prediction (Lee et al [16]), stock market prediction [1,9,12,17], and all types of sales prediction. Researchers have compared different prediction methods in references [8,13,18,19].…”

Section: Literature Surveymentioning

confidence: 99%

Sales forecasting for thin film transistor liquid crystal display products with data clustering and an evolving neural network model

Chang

Fan²,

Liu³

et al. 2008

Proceedings of the Institution of Mechanical Engineers, Part B:

View full text Add to dashboard Cite

There are specific characteristics in the thin film transistor liquid crystal display (TFT-LCD) industry, such as unexpected demand fluctuation, customized products that each customer will designate a specific key component, long lead time of procurement, and short product life cycle. This research presents a genetic algorithm integrated with a neural network model for monthly sales forecasting of TFT-LCD products in Taiwan. The practical situation and its requirements are explained and two systematic approaches are discussed: (a) a K-means clustering for historic sales data and new sales is forecasted by mapping its inputs into one of these clustered data, and (b) a neural network integrated with a genetic algorithm for supervised learning of the functional behaviour of time-series data and their approximation. The evolving neural network model is applied for modelling the system's behaviour with the possibility of exploiting expert information and systematic optimization. The model has been tested and satisfying results are shown with practical data.

show abstract

“…Various statistical and numerical methodologies have been implemented to predict and optimise several laser manufacturing processes including Artificial Neural Networks (ANN) (Lee et al 2001); Genetic Algorithms (GA) (Ye, Yuan and Zhou, 2009), Design of Experiments (DoE) (Karazi, Issa and Brabazon, 2009), Finite Element Analysis (FEA) (de Deus and Mazumder, 1996), Ant Colony optimisation (AC) (Wang and Xie, 2005), and Fuzzy Logic (FL) (Shen et al 2006). …”

Section: Introductionmentioning

confidence: 99%

Evaluation of the Effect of Nd:yvo4 Laser Parameters on Internal Micro-Channel Fabrication in Polycarbonate

Karazi

Brabazon

2011

Proceedings of the International Conference on Neural Computation Theory and Applications

View full text Add to dashboard Cite

Abstract:This paper presents the development of Artificial Neural Network (ANN) models for the prediction of laser machined internal micro-channels' dimensions and production costs. In this work, a pulsed Nd:YVO 4 laser was used for machining micro-channels in polycarbonate material. Six ANN multi-layered, feed-forward, back-propagation models are presented which were developed on three different training data sets. The analysed data was obtained from a 3 3 factorial design of experiments (DoE). The controlled parameters were laser power, P; pulse repetition frequency, PRF; and sample translation speed; U. Measured responses were the micro-channel width and the micro-machining operating cost per metre of produced microchannel. The responses were sufficiently predicted within the set micro-machining parameters limits. Three carefully selected statistical criteria were used for comparing the performance of the ANN predictive models. The comparison showed that model which had the largest amount of training data provided the highest degree of predictability. However, in cases where only a limited amount of ANN training data was available, then training data taken from a Face Centred Cubic (FCC) model design provided the highest level of predictability compared with the other examined training data sets.

show abstract

A neural network approach to the modelling and analysis of stereolithography processes

Cited by 5 publications

References 0 publications

Influence of the Rinsing Postprocessing Procedures on the Manufacturing Accuracy of Vat‐Polymerized Dental Model Material

Influence of the Rinsing Postprocessing Procedures on the Manufacturing Accuracy of Vat‐Polymerized Dental Model Material

Sales forecasting for thin film transistor liquid crystal display products with data clustering and an evolving neural network model

Evaluation of the Effect of Nd:yvo4 Laser Parameters on Internal Micro-Channel Fabrication in Polycarbonate

Contact Info

Product

Resources

About