No abstract

No abstract

Corrugation is proposed as a means of reducing the out-of-plane warpage in surface micromachined beams that result from an asymmetric vertical stress profile. Corrugation increases beam bending stiffness without increasing film thickness, making the beam more immune to intrinsic vertical stress gradients without requiring longer film deposition times, increased beam mass, or careful stress optimization. The technique was tested using a dual-thickness metal surface micromachining process with a photoresist sacrificial layer. Several corrugation patterns and geometries were tested, and the best performing pattern was implemented on a MEMS actuator array. The off-state to on-state capacitance delta of the array improved from 0.24 to 0.7pF and the beam curvature decreased from 180 to 50 nm compared with an uncorrugated array. Other device performance parameters, such as 30 V pull-in voltage and 5 billion cycle switching lifetime, were unaffected.

In components manufacturing, the Wire EDM is more popular due to its outstanding features of high dimensional accuracy, lower cost of production and good surface finish as there is no physical contact between the wire and work piece. However, for the steel with higher hardness, it is difficult to obtain these features up to the required extent. Moreover, with the help of optimum process parameters selection the WEDM performance characteristics should be improved. The most commonly studied responses for this process are material removal rate (MRR), Surface finish, Kerf width, wire consumption, roundness error. Among these, the responses like Kerf width, MRR and surface roughness are the primary responses. It is observed that pulse on time, pulse off time, servo voltage, peak current and wire feed are the influencing input parameters to these primary responses. Therefore, in the present work, the optimal level of input parameters is estimated for these responses using the Grey-Entropy-Fuzzy (GEF) and Genetic Algorithm (GA) during wire EDM of steel grade DC53 with high hardness of HRC58normally used in stamping dies, injection moulding and compression Moulding etc. To convert the multi objective problem into a single objective, the grey relational coefficient (GRC) has been calculated using Grey Relational Analysis and the weight-age of each response is approximated during the entropy method. To estimate the relation among the input parameters and single objective (GRC) fuzzy mathematical modelling technique termed as GEF has been applied. The optimal performance has been calculated using GA and GEF model is considered as fitness function. Five conformational tests on optimum parameter combination suggested by GA has been performed. The predicted values and experimental values have been found to be in good agreement with a standard error of 3.31% hence the prediction performance of the GREG-Fuzzy is quite satisfactory.

Performance of neural networks depends upon several input parameters. Several attempts have been made for optimization of neural network parameters using Taguchi methodology for achieving single objective such as computation effort, computation time, etc. Determination of optimum setting to these parameters still remains a difficult task. Trial-and-error method is one of the frequently used approaches to determine the optimal choice of these parameters. Keeping in view the problems with trial-and-error method, a systematic approach is required to find the optimum value of different parameters of neural network. In the present work, three most important distinct performance measures such as mean square error between actual and prediction, number of iteration, and total training time consumption have been probably considered first time concurrently. The multiobjective problem has been solved using Grey–Taguchi methodology. In this study, optimal combinations of different neural network parameters have been identified by using the Taguchi-based Grey relational analysis. The data set includes 81 sets of milling data corresponding to three-level full factorial experimental design for four cutting parameters, i.e. cutting speed, feed, axial depth of cut, and radial depth of cut, respectively. The output is average surface roughness for the experiment. The performance of different neural network models has been tabulated in L36 orthogonal array. Confidence interval has also been estimated for 95% consistency level to validate the optimum level of different parameters. It was found that the Taguchi-based Grey relational analysis approach can effectively be used as a structured method to optimize the neural network parameters settings, which can be easily implemented to enhance the performance of the neural network model with a relatively small size and time saving experiment. The result clearly indicates that the optimal combination of neural network parameters obtained by using the proposed approach performs better in terms of low mean square error, small number of iterations, and lesser training time required to perform the analysis which further results in lesser computation effort and processing time. Methodology proposed in this work can be utilized for any type of neural network application to find the optimum levels of different parameters.