With the rise of autonomous driving technology, concerns over the safety of AI-based systems have increased, particularly regarding their effect on human life and infrastructure. The complexity and unpredictable nature of AI-enabled software functions have disrupted traditional safety evaluation methods. In such a scenario, the quality control methods used at the manufacturing environments of sensors used for deploying AI-based perception functions need to be coupled with the downstream functions. This study focuses on investigating the impact of a specific production-related defect called blemish, which is caused by debris on image sensors of camera modules. The research aims to answer two fundamental questions: 1) How can blemish artifacts be mathematically modeled, and what is the process for developing a suitable dataset that incorporates this defect? 2) How can the influence of blemish artifacts on performance of object detection models be traced back to define quality requirements of the camera modules? This work takes a novel perspective by shifting the focus from improving model resilience to improving hardware quality camera modules by studying the effects of manufacturing defects on downstream functions. This research seeks to establish a framework to derive quality targets for front camera module manufacturing which can be extended to other sensors for similar applications.
Fiber reinforced polymers (FRP) provide favorable properties such as weight-specific strength and stiffness that are central for certain industries, such as aerospace or automotive manufacturing. Liquid composite molding (LCM) is a family of often employed, inexpensive, out-of-autoclave manufacturing techniques. Among them, resin transfer molding (RTM), offers a high degree of automation. Herein, textile preforms are saturated by a fluid polymer matrix in a closed mold.Both impregnation quality and level of fiber volume content are of crucial importance for the final part quality. We propose to simultaneously learn three major textile properties (fiber volume content and permeability in X and Y direction) presented as a three-dimensional map based on a sequence of camera images acquired in flow experiments and compare CNNs, ConvLSTMs, and Transformers. Moreover, we show how simulation-to-real transfer learning can improve a digital twin in FRP manufacturing, compared to simulation-only models and models based on sparse real data. The overall best metrics are: IOU 0.5031 and Accuracy 95.929 %, obtained by pretrained transformer models.
Machine Learning (ML), in particular classification with deep neural nets, can be applied to a variety of industrial tasks. It can augment established methods for controlling manufacturing processes such as statistical process control (SPC) to detect non-obvious patterns in high-dimensional input data. However, due to the widespread issue of model miscalibration in neural networks, there is a need for estimating the predictive uncertainty of these models. Many established approaches for uncertainty estimation output scores that are difficult to put into actionable insight. We therefore introduce the concept of certainty groups which distinguish the predictions of a neural network into the normal group and the certainty group. The certainty group contains only predictions with a very high accuracy that can be set up to 100%. We present an approach to compute these certainty groups and demonstrate our approach on two datasets from a PHM setting.