جستجوی مقالات مرتبط با کلیدواژه « فرآیند مهرزنی » در نشریات گروه « مکانیک »

Increasing the depth of microchannels on metallic bipolar plates (BPPs) in PEM fuel cells leads to an increase in the efficiency. In this research, the stamping process has been applied for manufacturing of the BPPs made of commercially pure titanium with a direct parallel flow field. The effect of process parameters including die clearance, forming speed, and sheet/die friction coefficient on the filling rate and thinning of the BPPs was investigated. The required tests were designed via the response surface method (RSM), implemented by a validated finite elements (FE) model, and the desired outputs were extracted. Then, a quadratic equation was presented for predicting the filling rate based on the input parameters using the regression method. In the following, using the artificial bee colony algorithm, the coefficients of the mentioned equation were enhanced and its error was decreased almost by 53%. Finally, an artificial neural network (ANN) was used to predict the filling rate. The results demonstrated that the proposed ANN model is very effective and approximates the filling rate of the microchannel with high accuracy.

In addition to the need for lightweight properties, the metallic bipolar plates in the PEM fuel cells should work in a humid and acidic environment. Due to its low density and excellent corrosion resistance, titanium is a proper candidate for manufacturing bipolar plates. In this paper, the manufacturing of bipolar plates made of commercially pure titanium with an initial thickness of 0.1 mm was investigated using the stamping process. A four-channel die with a parallel flow field was used in the experiments. To estimate the formability of microchannels of the bipolar plates, the response surface method, genetic algorithm, and adaptive neural fuzzy inference system were employed. Die clearance, stamping speed, and friction coefficient between the sheet and die were considered input variables, whereas the die filling rate was as output. The designed experiments using the response surface method were used to train the meta-heuristic techniques. The results showed that the regression model obtained from the response surface method predicts the die filling rate with acceptable accuracy. Furthermore, the coefficients of the equation obtained from the regression have been improved using the genetic algorithm and the error rate has been reduced by about 53%. Finally, an adaptive neural fuzzy inference system was used to predict the die filling. The results showed that the proposed system is very feasible and approximates the maximum filling rate with high accuracy.