Artificial neural networks for machining processes surface roughness modeling

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Optimization of Radial Basis Function neural network employed for prediction of surface roughness in hard turning process using Taguchi's orthogonal arrays

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Surface roughness of packable composite resins polished with various systems

Purpose: The aim of this study was to evaluate the surface roughness of four packable composite resins, SureFil™ (Dentsply, Petrópolis, Rio de Janeiro, Brazil), Prodigy Condensable™ (Kerr Co., Orange, CA, USA), Filtek P60™ (3M do Brasil, São Paulo, Brazil), and ALERT® (Jeneric/Pentron, Inc., Wallingford, CT, USA) and one microhybrid composite resin (Filtek Z250™, 3M do Brasil) after polishing with four finishing systems. Materials and Methods: Twenty specimens were made of each material (5 mm in diameter and 4 mm high) and were analyzed with a profilometer (Perthometer® S8P, Perthen, Mahr, Germany) to measure the mean surface roughness (Ra). The specimens were then divided into four groups according to the polishing system: group 1 - Sof-Lex™ (3M do Brasil), group 2 - Enhance™ (Dentsply), group 3 - Composite Finishing Kit (KG Sorensen, Barueri, São Paulo, Brazil), and group 4 - Jiffy Polisher Cups® (Ultradent Products, Inc., South Jordan, UT, USA). The specimens were polished and then evaluated for Ra, and the data were subjected to analysis of variance, analysis of covariance, and Tukey's test (p = .05). Results: The mean Ra of SureFil polished with Sof-Lex was significantly lower than that of KG points. Prodigy Condensable polished with Enhance showed a significantly less rough surface than when polished with Sof-Lex. Filtek P60 did not exhibit a significant difference with the various polishing systems. For ALERT the lowest mean Ra was obtained with Sof-Lex and the highest mean Ra with KG points. Regarding Filtek Z250, polishing with KG and Jiffy points resulted in a significantly lower mean Ra than when polished with Enhance. Conclusions: Packable composite resins display variable roughness depending on the polishing system used; the Sof-Lex disks and Jiffy points resulted in the best Ra values for the majority of the materials tested.

Weight loss and surface roughness of hard chairside reline resins after toothbrushing: Influence of postpolymerization treatments

Purpose: To evaluate the effect of 2 postpolymerization treatments on toothbrushing wear (weight loss) and surface roughness of 3 autopolymerized reline resins-Duraliner II (D) (Reliance Dental), Kooliner (K) (Coe Laboratories), and Tokuso Rebase Fast (T) (Tokuyama Dental)-and 1 heat-polymerized resin, Lucitone 550 (L) (Dentsply International). Materials and Methods: Specimens (40 x 10 x 2mm) of each material (n = 24) were prepared and divided into 3 groups: control (no postpolymerization treatment); water bath (immersion in water at 55°C); and microwave (microwave irradiation). Specimens were dried until constant weight was achieved and the surface roughness (Ra) was measured. Tests were performed in a toothbrush machine using 20,000 strokes of brushing at a weight of 200 g, with the specimens immersed in 1:1 dentifrice/water slurry. Specimens were reconditioned to constant weight and the weight loss (mg) and surface roughness were evaluated. Data were analyzed by 2-way analysis of variance and followed by Tukey test (α = .05). Results: In the control group, the weight loss of materials D and T was lower (P < .05) than that of L. No differences among materials were found after postpolymerization treatments (P > .05). The weight loss of material T (control = 0.5 mg) was significantly increased (P < .05) after postpolymerization treatments (water bath = 1.9 mg; microwave = 1.8 mg). For materials K and T, the toothbrushed surface roughness was higher (P < .05) after microwave and waterbath postpolymerization treatments. Material L showed increased surface roughness after microwave postpolymerization treatment. Conclusion: The toothbrushing wear resistance of L was not superior to the reline resins. The postpolymerization treatments did not improve the toothbrushing wear resistance of the materials and produced an increased surface roughness for materials L, K, and T.

Surface roughness of glass ionomer cements indicated for atraumatic restorative treatment (ART)

The purpose of this study was to evaluate the surface roughness of four conventional chemically cured glass ionomer cements (Fuji IX, Ketac Molar, Vidrion R and Vitromolar) commonly used in atraumatic restorative treatment (ART) immediately after material preparation. Twenty specimens of each glass ionomer cement were fabricated and surface roughness was measured after material setting. The specimens were further examined under scanning electron microscopy. Data were analyzed statistically by Kruskal-Wallis test and Mann-Whitney test at 5% significance level. Two-by-two comparisons showed statistically significant difference (p<0.05) between all materials, except for Ketac Molar and Vidrion R, which had statically similar results (p>0.05). Regarding their results of surface roughness, the materials can be presented in a crescent order, as follows: Ketac Molar < Vidrion R < Fuji IX < Vitromolar. In conclusion, from the tested glass ionomer cements, Fuji IX, Ketac Molar and Vidrion R presented acceptable surface roughness after setting reaction while Vitromolar showed remarkably higher surface roughness.

In vitro evaluation of surface roughness of 4 resin composites after the toothbrushing process and methods to recover superficial smoothness.

OBJECTIVE: This study evaluated the efficiency of repolishing, sealing with surface sealant, and the joining of both in decreasing the surface roughness of resin-based composites after a toothbrushing process. METHOD AND MATERIALS: Ten specimens of each composite (Alert, Z100, Definite, and Prodigy Condensable), measuring 2 mm in thickness and 4 mm in diameter, were made and submitted to finishing and polishing processes on both sides of the specimens using the Sof-Lex system. The specimens were then subjected to toothbrushing (30,000 cycles), and surface roughness (Ra) was analyzed with a Surfcorder SE 1700 profilometer. The upper surface of each composite was etched with 37% phosphoric acid, and the surface-penetrating sealant Protect-it was applied on 1 surface. The roughness of these surfaces was again measured. On the other side, the surface of the specimen was repolished, and the efficiency of this procedure was measured using the profilometer. The surface roughness resulting from the joining of the 2 methods was verified by applying, in the final stage, the surface-penetrating sealant on the repolished surface. Data were analyzed with analysis of variance and Tukey test (P <.05). RESULTS: Results showed that the lowest surface roughness values were obtained for Definite, Z100, and Prodigy Condensable after the repolishing process and after the repolishing plus sealing. For Alert, the joining of repolishing plus sealing promoted the lowest values of surface roughness. CONCLUSION: Of the resin-based composites, Alert demonstrated the highest values of surface roughness in all the techniques tested.

Neural network approach for surface roughness prediction in surface grinding

Several systems are currently tested in order to obtain a feasible and safe method for automation and control of grinding process. This work aims to predict the surface roughness of the parts of SAE 1020 steel ground in a surface grinding machine. Acoustic emission and electrical power signals were acquired by a commercial data acquisition system. The former from a fixed sensor placed near the workpiece and the latter from the electric induction motor that drives the grinding wheel. Both signals were digitally processed through known statistics, which with the depth of cut composed three data sets implemented to the artificial neural networks. The neural network through its mathematical logical system interpreted the signals and successful predicted the workpiece roughness. The results from the neural networks were compared to the roughness values taken from the worpieces, showing high efficiency and applicability on monitoring and controlling the grinding process. Also, a comparison among the three data sets was carried out.

Evaluation of hardness and surface roughness of two maxillofacial silicones following disinfection

The purpose of this study was to evaluate the Shore A hardness and surface roughness of two silicones for maxillofacial prosthetic treatment, under the influence of chemical disinfection and storage. Twenty-eight specimens were obtained, half of which were made of Silastic MDX 4-4210 silicone and, the other half were made of Silastic 732 RTV silicone. The specimens were divided into four groups: Silastic 732 RTV and MDX 4-4210 with disinfection 3 times a week with Efferdent tablets and the same materials without disinfection. The hardness of the materials was analyzed with a Shore A Durometer. The surface roughness was established by a digital portable roughness tester, initially and 2 months after the confection of the specimens. A variance test was applied (2-way ANOVA), followed by Tukey test (the level of significance was set at 1%). The storage time factor statistically influenced (p < 0.01) the materials' properties of hardness and roughness. MDX 4-4210 (28.59 Shore A, 0.789 Ra) presented higher values than Silastic 732 RTV (18.08 Shore A, 0.656 Ra) for both properties. Regarding the disinfection period, there was no significant difference in any of the materials tested. © 2009 Sociedade Brasileira de Pesquisa Odontológica.

In vitro surface roughness of different glass ionomer cements indicated for ART restorations

Aim: The aim of this in vitro study was to evaluate the surface roughness of three glass ionomer cements (GICs) indicated for ART restorations. Methods: Ten cylindrical specimens of three commercial glass ionomers cements (Vidrion R - S.S. White, Maxxion R - FGM and Vitromolar DFL) were prepared (n=30) without surface finishing or protection. Twenty-four hours after preparation, the surface roughness measurements were obtained as the mean of three readings of the surface of each specimen by profilometry. The roughness values (Ra, μm) were subjected to one-way ANOVA and Tukey's test (p<0.05). Results: No statistically significant differences were observed between Vidrion R (0.18 ± 0.05) and Vitromolar (0.21 ± 0.05), whereas Maxxion R presented significantly higher roughness values than those of the other materials. Conclusions: It may be concluded that characteristics of particle size and composition of the different GICs affected their surface roughness 24 h after preparation.

Anfis applied to the prediction of surface roughness in grinding of advanced ceramics

This paper introduces a methodology for predicting the surface roughness of advanced ceramics using Adaptive Neuro-Fuzzy Inference System (ANFIS). To this end, a grinding machine was used, equipped with an acoustic emission sensor and a power transducer connected to the electric motor rotating the diamond grinding wheel. The alumina workpieces used in this work were pressed and sintered into rectangular bars. Acoustic emission and cutting power signals were collected during the tests and digitally processed to calculate the mean, standard deviation, and two other statistical data. These statistics, as well the root mean square of the acoustic emission and cutting power signals were used as input data for ANFIS. The output values of surface roughness (measured during the tests) were implemented for training and validation of the model. The results indicated that an ANFIS network is an excellent tool when applied to predict the surface roughness of ceramic workpieces in the grinding process.