Methodology for an automatic and early manufacturing technology selection on a component level

Abstract

Production systems of the automotive industry process parts that were previously designed and manufactured according to different manufacturing technologies. In car body architectures, additive manufacturing (AM) has become a relevant technology for supplementing conventional manufacturing technologies, e.g., casting or forming technologies. This paper presents a methodology for an automatic and objective early-stage analysis of part features and the subsequent identification of the parts’ most suitable manufacturing technology. For this purpose, a comprehensive database is required, in which several technological and economic parameters need to be derived and predicted, including part requirements, production inherences, expected lifecycle costs, as well as geometric information. Based on this, data screening allows to effectively evaluate the technological and economic potential for a component to be manufactured either conventionally or additively in early product development phases. One core element is the part requirements derivation and analysis within one novel module of the part screening methodology. Subsequently, the product development process and the production system can be adapted according to the identified, most promising manufacturing technologies. Hence, this early-stage decision allows for cost reduction through an increased planning reliability. This work thus contributes to a successful co-evolution of smart product development and the production processes.

Automated geometric analysis of metallic components through picture recognition models for manufacturing technology assessments

“…The network begins with a layer of 28 × 28 input neurons that are Fig. 1 The four modules of the screening methodology, according to Buechler et al [4] used to encode the pixels of an image, e.g., as binary values for dark or bright areas. Three filters are overlappingly applied to the input layer and processed through a ReLu activation.…”

“…Fig. 17 The geometry module supplements the main author's screening methodology (orange) [4] as a part of the car body development and production process (color figure online) learning effect from epoch 2 to 5 and overfitting behavior from epoch 12 onwards with an increasing loss of validation. This behavior is triggered by the large image dimensions, as this approach cannot rely on pre-trained weights.…”

“…In the frame of this article and its application example, five manufacturing technologies are relevant and compared: deep drawing, casting, pressing, rolling, and additive manufacturing. A holistic comparison of potential manufacturing technologies on a component level needs to consider the following aspects [4,5]:…”

“…The screening methodology evaluates these alternatives based on fuzzy rule sets that represent the strengths and weaknesses of each manufacturing technology. Three modules have already been completed and published [4,6]: The requirements module derives requirements based on the components' positions in the final product. The production module analyzes the logistics and production inherences for different manufacturing technologies.…”

Metallographic examination as the feedback between product quality and manufacturing

“…Производство каждого изделия, конструкции или детали является результатом длинной цепочки разнообразных действий, начиная от проектирования и заканчивая сборкой. С каждым годом в реализации этого процесса все больше места отводится различным автоматизированным программам, позволяющим не только проектировать изделия с учетом обеспечения прочности, но и полностью разрабатывать технологии их изготовления [1][2][3]. Тем не менее случаи выхода из строя изделий или даже возникновения аварийных ситуаций происходят достаточно часто [4][5][6].…”