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 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.

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.

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.

Effect of brushing with conventional versus whitening dentifrices on surface roughness and biofilm formation of dental ceramics

The aim of this study was to evaluate the effect of conventional and whitening dentifrices on the weight loss, surface roughness, and early in situ biofilm formation on the surface of dental ceramics. Standardized feldspar ceramic specimens (Vita VM7 and Vita VM13) were submitted to the following experimental conditions: no brushing; brushing without a dentifrice; brushing with a conventional dentifrice; and brushing with a whitening dentifrice. A brushing machine was used to simulate brushing. The mass and surface roughness of all specimens from the test groups were evaluated prior to and after brushing. Ten participants used an oral device for eight hours to evaluate the biofilm formed in situ on the specimens. Scanning electron microscopy was used for qualitative and quantitative analysis of the biofilm. ANOVA and Tukey tests were used to analyze the results of weight loss, surface roughness, and presence of bacteria. A one-way Kruskal-Wallis test was used for bacterial colonization results. For both ceramics, brushing with a whitening dentifrice resulted in weight loss that was significantly greater when compared to brushing without a dentifrice or with a conventional dentifrice. Increased surface roughness was noticed on VM13 ceramic samples with both dentifrices, whereas only conventional dentifrice had a significant effect on the surface roughness of VM7 samples. For both VM7 and VM13, no difference was found between the experimental conditions with regard to the presence or number of bacteria. Cocci and short rods were the predominant microbial morphotypes. Granular or fibrillar acellular material partially covered the specimens. Brushing with a whitening dentifrice resulted in significant weight loss of ceramic restorations, while brushing with both conventional and whitening dentifrices can roughen ceramic surfaces. The increase in roughness was not clinically significant to contribute to increased biofilm formation.

Influence of polishing procedures on the surface roughness of dental ceramics made by different techniques

The aim of this study was to evaluate the influence of 2 different surface polishing procedures - glazing (GZ) and manual polishing (MP) - on the roughness of ceramics processed by computer-aided design/computer-aided manufacturing (CAD/CAM) and conventional systems (stratification technique). Eighty ceramic discs (diameter: 8 mm, thickness: 1 mm) were prepared and divided among 8 groups (n = 10) according to the type of ceramic disc and polishing method: 4 GZ and 4 MP. Specimens were glazed according to each manufacturer's recommendations. Two silicone polishing points were used on the ceramic surface for manual polishing. Roughness was measured using a surface roughness tester. The roughness measurements were made along a distance of 2 mm on the sample surface and the speed of reading was 0.1 mm/s. Three measurements were taken for each sample. The data (μm) were statistically analyzed using analysis of variance (ANOVA) and Tukey's test (α = 0.05). Qualitative analysis was performed using scanning electron microscopy (SEM). The mean (± SD) roughness values obtained for GZ were: 1.1 ± 0.40 μm; 1.0 ± 0.31 μm; 1.6 ± 0.31 μm; and 2.2 ± 0.73 μm. For MP, the mean values were: 0.66 ± 0.13 μm; 0.43 ± 0.14 μm; 1.6 ± 0.55 μm; and 2.0 ± 0.63 μm. The mean roughness values were significantly affected by the ceramic type (P = 0.0001) and polishing technique (P = 0.0047). The SEM images confirmed the roughness data. The manually polished glass CAD/CAM ceramics promoted lower surface roughness than did the glazed feldspathic dental ceramics.

Effect of air-particle abrasion protocols on the biaxial flexural strength, surface characteristics and phase transformation of zirconia after cyclic loading

This study evaluated the effect of air-particle abrasion protocols on the biaxial flexural strength, surface characteristics and phase transformation of zirconia after cyclic loading. Disc-shaped zirconia specimens (Ø: 15mm, thickness: 1.2mm) (N=32) were submitted to one of the air-particle abrasion protocols (n=8 per group): (a) 50μm Al2O3 particles, (b) 110μm Al2O3 particles coated with silica (Rocatec Plus), (c) 30μm Al2O3 particles coated with silica (CoJet Sand) for 20s at 2.8bar pressure. Control group received no air-abrasion. All specimens were initially cyclic loaded (×20,000, 50N, 1Hz) in water at 37°C and then subjected to biaxial flexural strength testing where the conditioned surface was under tension. Zirconia surfaces were characterized and roughness was measured with 3D surface profilometer. Phase transformation from tetragonal to monoclinic was determined by Raman spectroscopy. The relative amount of transformed monoclinic zirconia (FM) and transformed zone depth (TZD) were measured using XRD. The data (MPa) were analyzed using ANOVA, Tukey's tests and Weibull modulus (m) were calculated for each group (95% CI). The biaxial flexural strength (MPa) of CoJet treated group (1266.3±158A) was not significantly different than that of Rocatec Plus group (1179±216.4A,B) but was significantly higher than the other groups (Control: 942.3±74.6C; 50μm Al2O3: 915.2±185.7B,C). Weibull modulus was higher for control (m=13.79) than those of other groups (m=4.95, m=5.64, m=9.13 for group a, b and c, respectively). Surface roughness (Ra) was the highest with 50μm Al2O3 (0.261μm) than those of other groups (0.15-0.195μm). After all air-abrasion protocols, FM increased (15.02%-19.25%) compared to control group (11.12%). TZD also showed increase after air-abrasion protocols (0.83-1.07μm) compared to control group (0.59μm). Air-abrasion protocols increased the roughness and monoclinic phase but in turn abrasion with 30μm Al2O3 particles coated with silica has increased the biaxial flexural strength of the tested zirconia. © 2013 Elsevier Ltd.

Effect finishing and polishing procedures on the surface roughness of IPS Empress 2 ceramic

Objective. To evaluate the surface roughness of IPS Empress 2 ceramic when treated with different finishing/polishing protocols. Materials and methods. Sixteen specimens of IPS Empress 2 ceramic were made from wax patterns obtained using a stainless steel split mold. The specimens were glazed (Stage 0-S0, control) and divided into two groups. The specimens in Group 1 (G1) were finished/polished with a KG Sorensen diamond point (S1), followed by KG Sorensen siliconized points (S2) and final polishing with diamond polish paste (S3). In Group 2 (G2), the specimens were finished/polished using a Shofu diamond point (S1), as well as Shofu siliconized points (S2) and final polishing was performed using Porcelize paste (S3). After glazing (S0) and following each polishing procedure (S1, S2 or S3), the surface roughness was measured using TALYSURF Series 2. The average surface roughness results were analyzed using ANOVA followed by Tukey post-hoc tests (α = 0.01) Results. All of the polishing procedures yielded higher surface roughness values when compared to the control group (S0). S3 yielded lower surface roughness values when compared to S1 and S2. Conclusions. The proposed treatments negatively affected the surface roughness of the glazed IPS Empress 2 ceramic. © 2013 Informa Healthcare.