Quality Management

The production of cooked ham involves a number of challenges. In production, cuts of meat are put through in a multi-stage curing and cooking process involving brine. This can lead to fluctuations in quality due to structural defects in the meat. The result: the brine is not optimally absorbed. An AI model trained on historical data intends to solve the problem.

While the digital world has already made its way into many other production areas, the bakery industry has so far benefited little from these technological developments. This is because many baking processes are manually controlled and rely on expert knowledge. In addition, the process data from the machines is still not automatically captured via sensors. This paper describes a procedure for digitizing baking processes by developing an IoT framework consisting of an IoT device including measurement methods, an edge gateway, and a simulation-based solution for process optimization.

n the automotive industry, preventive quality actions are applied to ensure the quality of the end products. During production ramp-up the occurrence of nonconformities can be a critical issue. Nonconformities with new and innovative products can be especially challenging due to limited experience of previously unknown processes. To address this challenge, an IT application has been developed to capture the organization's existing knowledge and use this to support the problem- solving team in applying an enhanced 8D method.

Customers are increasingly demanding electronic components with high quality, which forces companies to continuously fulfil these requirements. This leads to a high number of inspection gates with high inspection severity and a high number of pseudo defects. Double inspections by process experts reduce these defects but generate high inspection costs. Autonomously acting inspection systems meet this challenge. Within this article, a machine learning algorithm was integrated into the solder paste inspection process to form an autonomous quality inspection system.

Visual inspections of product surfaces are predominantly carried out by employees, whereby automation approaches with camera and image processing systems show great potential. Cobots are also being incorporated into quality assurance processes. In the following, the integration possibilities of cobots in visual inspection are discussed and a decision model is presented that can be used to check visual inspection processes for their cobot suitability. The decision model is designed for direct integration into already existing cobot suitability inspection processes and serves as an initial strategic decision-making aid.

Manufacturing companies must work economically while delivering quality - in some industries with a zero-defect tolerance. Quality control often is carried out manually and with a time delay, thus errors can only be corrected at a late stage. Using artificial intelligence (AI), visual quality control can be automated, carried out in real time and integrated into the production process - making it more accurate, efficient and cost-effective. A case example shows the advantages of tackling AI issues in interdisciplinary teams with partners.

Manufacturing Analytics is the evaluation and use of data in the production context. This article shows which potentials can be realised by Manufacturing Analytics in the context of reactive quality management. First, a general definition of the term Manufacturing Analytics is given and then its classification in the context of quality management is carried out. On the basis of a literature analysis and the evaluation of existing use cases, findings regarding the potentials for reactive quality processes are derived. This shows that Manufacturing Analytics is particularly promising and can be used in root cause analysis, defect detection and avoidance. Subsequently, an application example is presented.

There are numerous analysis methods available to support engineers working on continuous improvement projects. Digital transformation facilitates to reduce the effort for data acquisition and processing. The Institute of Production Management and Technology and the medical company Dräger have jointly developed a web application for multi-method analysis. This article describes its data structure and technology.

Optical systems are a popular choice for quality inspection because they are not only contactless and precise but also comparably fast. Particularly in cases where a 100% quality inspection is required low measurement and evaluation time is of essential importance. With high production rates of several parts per second, manual inspection is not feasible anymore and the evaluation needs to be automatically carried out by algorithms. In this article we propose a fast method for anomaly detection in image data based on principal component analysis and filtering. The method shows competitive performance on a data set of challenging surface inspection.

As manufacturing technologies are scaled down from macro to micro level, unexpec-ted process behavior emerges, so called size effects. This also regards reliable optical quality inspection, as tolerances in micrometer range require microscopic solutions. Optical magnification comes with a strong reduction in field of depth as well as a decrease in the measured area, which makes exact positioning and possibly measurements at different depth levels necessary. Here we present and evaluate a demonstrator platform for the automatic measurement of micro parts using a light field camera.