男西服规格尺寸设计对成衣的合体性和板型有着直接的影响，在现今的服装企业中，这项工作对制板师的经验依赖程度比较高，容易因人员流动影响成衣质量。随着人工神经网络等人工智能技术的发展，本文构建了一种可用于男西服规格尺寸设计的改进型BP神经网络模型，并探讨和分析了隐含层神经元数、传递函数、动量因子等影响神经网络性能的关键因素，经过多次仿真测试，表明利用改进型BP网络可以实现由人体关键部位的净体数据自动生成男西服成衣规格尺寸。若经过进一步完善，此方法还能应用于其他服装品种的规格尺寸设计，有利于提高服装企业的制板效率和成衣的适体率。%The fitness and pattern shape of men’s suit depend on the design of its specification. In apparel enterprises of modern times, the design of specifications of men’s suit relies on the experience of pattern makers, and the quality of men’s suit may be influenced easily by dismission of experienced pattern makers. With the development of artificial intelligence and its application in textile industry, an innovative BP neural network model was built to auto-generate specifications of men’s suit. Afterwards, the factors influencing the performances of BP neural network model, such as the numbers of neurons in hidden layer, the transfer function and momentum terms, were analyzed. After simulation testing, it was indicated that it was feasible to auto-generate specifications of men’s suit by an innovative BP neural network model. And this method could also be applied to design specifications of other varieties of clothing, which is conducive to improving work efficiency of pattern-making and apter rate of men’s suit.
展开▼
