摘要
With the combination of a new theoretical formula, physical simulation experiments, the technology of artificial neural network and database, an intelligent system for the prediction of sheet metal drawing capability is constructed for the first time. A modified criterion for sheet metal drawing capability is proposed in this paper, namely, the Technological Limiting Drawing Ratio, TLDR = f(R, n, s, t, F, μ,r_d,r_p…). Based on the studies of other scholars, a new formula is derived to predict the TLDR in this paper. Then a series of orthogonal physical simulation experiments are designed to investigate the effect of technological parameters on the TLDR, and the results are analyzed in the paper. Then the predicting system is constructed with the combination of the theoretical formula, orthogonal experiments, the technology of artifocial neural network and database. The predicted results show good agreements with experimental data, so it can be used to avoid the blindness in the selection of sheet metal before stamping. The system operates under the Windows operating system, and it supports the mechanism of Client/Server as well as Intranet, so the system has high engineering value.
With the combination of a new theoretical formula, physical simulation experiments, the technology of artificial neural network and database, an intelligent system for the prediction of sheet metal drawing capability is constructed for the first time. A modified criterion for sheet metal drawing capability is proposed in this paper, namely, the Technological Limiting Drawing Ratio, TLDR = f(R, n, s, t, F, μ,r_d,r_p…). Based on the studies of other scholars, a new formula is derived to predict the TLDR in this paper. Then a series of orthogonal physical simulation experiments are designed to investigate the effect of technological parameters on the TLDR, and the results are analyzed in the paper. Then the predicting system is constructed with the combination of the theoretical formula, orthogonal experiments, the technology of artifocial neural network and database. The predicted results show good agreements with experimental data, so it can be used to avoid the blindness in the selection of sheet metal before stamping. The system operates under the Windows operating system, and it supports the mechanism of Client/Server as well as Intranet, so the system has high engineering value.
