Colin Reiff

Abstract

Robotic vision tasks require a large amount of annotated data for effective training and performance. However, the manual creation of such datasets is a complex and time-consuming process. Particularly for smaller companies or those with high product variability, there is a need to optimise the resources dedicated to creating datasets for machine vision applications. This paper investigates novel ways to acquire annotated vision data through the integration of collaborative robots. Two methods are outlined to streamline the generation of annotated datasets. One of these methods is then used to construct a dataset tailored for 6D robotic gripping of an automotive connector. The effectiveness of automated annotated dataset generation is demonstrated by training a deep learning model to accurately estimate the orientation of the automotive connector.

Abstract

Manufacturing-X steht für eine branchenübergreifende Initiative zum Aufbau eines föderativen Datenökosystems nach demokratischen Werten. Digitale Souveränität, Gleichberechtigung, Vertrauen und Sicherheit sind tragende Säulen einer Datokratie. Ziel ist es, die Wettbewerbsfähigkeit des Industriestandorts Deutschland auszubauen, bei gleichzeitiger Stärkung von Resilienz und Nachhaltigkeit. Dieser Artikel beschreibt einen technologischen Umsetzungsvorschlag.

Abstract

Software-Defined Manufacturing (SDM) is a new paradigm for how to manufacture in the Industry 4.0 factory of the future. The approach requires a fundamental change in thinking and reinvention of central business models in production technology. This paper discusses the main challenges on the way to a software-defined factory of the future and illustrates possible solutions. An exemplary future factory is presented, in which the validation of the solutions is carried out. For this purpose, cloud-based Computerized Numerical Control (CNC) is considered as use case. Experimental results demonstrate the proof of concept and show the potential for further applications.

Abstract

Manufacturing-X represents the idea of a decentralized data economy. The aim is to increase sustainability, competitiveness and resilience by digitizing supply chains. Technically, this requires three technologies. First, a standardized data model to ensure interoperability across company boundaries. Second, a solution to realize sovereign inter-organizational data exchange. And thirdly, a component for the company’s internal data communication. Asset Administration Shell (AAS), Eclipse Dataspace Connector (EDSC) and Open Platform Communication Unified Architecture (OPC UA) are suitable solutions. This paper introduces an appropriate architecture to combine these technologies in an industrial production environment and discusses existing challenges, limitations and future potentials.

Abstract

Die Stuttgarter Maschinenfabrik stellt eine vollständig digitalisierte Produktionsumgebung dar, in der vom Kunden individualisierte Produkte selbstorganisiert hergestellt werden. Dafür ist eine neue technologische Infrastruktur in Kombination mit einem durchgängigen Einsatz von digitalen Zwillingen erforderlich. Das erlaubt eine hohe Freiheit bei der Entwicklung von neuen Anwendungen und die nötige Flexibilität im Maschinenpark. Die Artikelserie soll beispielhafte Aspekte der Stuttgarter Maschinenfabrik beleuchten, um das Umsetzungsprojekt vorzustellen.

Abstract

Additive manufacturing is becoming increasingly important for industrial applications. Especially laser powder bed fusion processes play a decisive role. However, the technology often lacks in reliability and part quality due to complex process interactions and disturbing influences. To counteract these limitations, a flexible and high-dynamic control of relevant process parameters, taking into account the transient process conditions, is indispensable. Currently, the most process parameters are often kept constant, since the used control systems do not offer real-time capable interfaces for intervention. To enable the adjustment of parameters during the process, an open control architecture for galvanometer scanners and laser sources was developed. The architecture is based on an industrial control system in combination with a field-programmable gate array (FPGA) communicating via a real-time fieldbus. The novel control architecture is used to integrate a model-based feedforward control, adjusting the laser power, scan speed and scan strategy based on the current powder bed temperature calculated by a two-dimensional thermal model during run time. An integrated learning algorithm autonomously tunes the process parameters during the manufacturing process and determines the optimal combination of laser power, scan speed and powder bed temperature to achieve a homogeneous melt pool. On average, the standard deviation of the powder bed temperature along the scan path was reduced by 48% for the simulated test cases.

Abstract

Process planning in manufacturing today focuses on optimizing the conflicting targets of cost, quality, and time. Due to increasing social awareness and subsequent governmental regulation, environmental impact becomes a fourth major aspect. Eventually, sustainability in manufacturing ensures future competitiveness. In this paper, a framework for the planning of sustainable manufacturing is proposed. It is based on the abstraction and generalization of manufacturing resources and part descriptions, which are matched and ranked using a multi-criteria decision analysis method. Manufacturing resources provide values for cost, quality, time and environmental impacts, which multiply with their usage within a manufacturing task for a specific part. The framework is validated with a detailed modeling of a laser machine as a resource revealing benefits and optimization potential of the underlying data model. Finally, the framework is applied to a use case of a flange part with two different manufacturing strategies, i.e., laser metal-wire deposition and conventional milling. The most influential parameters regarding the environmental impacts are the raw material input, the manufacturing energy consumption and the machine production itself. In general, the framework enabled the identification of non-predetermined manufacturing possibilities and the comprehensive comparison of production resources.

Abstract

Bei mehrstufigen Produktionssystemen rotierender Bauteile kann bereits ein kleiner Fehler zu Ausschuss führen. Um die Wettbewerbsfähigkeit europäischer Unternehmen zu gewährleisten, wird eine Null-Fehler Fertigung angestrebt. Wir stellen dafür eine Web-App vor, welche Bauteilvariationen automatisch erkennen und Fehlerkompensationsstrategien ableiten kann. Das Potential des mehrstufigen Produktionssystems wird genutzt um Fehler am Bauteil im Produktionsfluss durch eine geeignete Steuerung und Regelung zu beheben.

Abstract

In many sectors such as the aerospace industry, the manufacturing of rotating components is based on multi-stage production systems to achieve the complex requirements of high quality products. Even in the presence of Industry 4.0 and the increasing connectivity, these systems are very prone to failure due to the high level of potential influences of both the system and the products, ultimately leading to defects. The project “ForZDM”, funded by the EU under Horizon2020, envisions reducing scrap rate by avoiding and compensating defects at an early stage thus guaranteeing a high quality product. This paper presents an approach using an existing manufacturing line to compensate the dimensional deviations of an inner contour of a turbine shaft at an early stage. Based on measurements of the inner contour, a new rotation axis for the subsequent manufacturing processes is calculated in order to avoid unbalances at the end-of-line control. Different algorithms are developed and integrated in a web-based application to find an optimal rotation axis under consideration of the to-be-manufactured outer contour in an operator-friendly usage on the shop floor. The application is connected with the measurement system and the subsequent CNC machine which enables automatic execution and data transfer.

Abstract

With the increasing number of sensors installed in production systems and the associated amount of recorded data, a high potential for optimizing manufacturing processes is offered. Based on the gathered information, data analyzing methods can be used to identify correlations and thus, optimize complex multi-stage production systems with the goal of zero-defect manufacturing. For this purpose, multiple statistical methods have to be applied, which is often a time-consuming task and currently requires trained and experienced specialists. Furthermore, the investigated data must be kept up to date for the early recognition of changes possibly leading to cost-intensive scrap and production downtimes. To address these issues, a web-based platform with an intuitive user interface was developed. The platform can access and process various data sources using modular methods. In addition, as part of continuous monitoring, the results of these analyzing steps can be dynamically calculated. The aim of the platform is to make complex analysis processes accessible to machine operators and thus to combine domain expertise and statistical knowledge. The paper describes the underlying architecture and the relevant interfaces of the platform.

Abstract

During manufacturing, geometrical deviations occur, e.g. due to heating processes. In multi-stage production systems, these errors propagate and lead to expensive rework or, even, to unusable products. In this paper, a method for smart centering of rotation-symmetric parts is introduced. The method is used in the scope of achieving zero-defect manufacturing processes. For this purpose, the products are measured and automatically compared with the required specifications. Based on the identified deviations, process parameters can be adjusted and thus, defects can be compensated in downstream production steps. The method is exemplified in the context of an industrial use case.

Abstract

Die vorgestellte Smart Centering Strategie zielt darauf ab, eine wirtschaftlichere Fertigung von rotationssymmetrischen Bauteilen durch eine intelligente Ausrichtung der Rotationsachse zu erreichen. Dazu wurden Ansätze der Null-Fehler-Fertigung in einem industriellen Anwendungsfall realisiert und in Form eines cyber-physischen Systems in die Prozesskette integriert. Um Fehler, bedingt durch Verformungen des Ausgangmaterials zu kompensieren, werden sowohl die Soll-Geometrie als auch die tatsächliche Geometrie des Bauteils berücksichtigt. Für ei-nen Vergleich beider Geometrien wurden verschiedene Modellierungsmethoden vorgestellt und diskutiert. Darauf aufbauend wurden Algorithmen entwickelt, welche die Position der Referenzbohrung zur Festlegung der Rotationsachse hinsichtlich verschiedener Kriterien optimieren. Darüber hinaus werden für den Fall, dass eine Welle voraussichtlich nicht gefertigt werden kann, weitere Soll-Geometrien über-prüft und so alternative Vorschläge zur Fertigung gemacht. Das System berechnet eine Vielzahl von Parametern, wie Unwucht und minimaler Abstand der Soll-Geometrie zur Ist-Geometrie und kann dadurch zur weiteren Verbesserung der gesamten Prozesskette verwendet werden. Folglich können auf Basis der Auswertung dieser Daten, zukünftig Toleranzen gesenkt und dadurch Material eingespart und der Werkzeugverschleiß sowie die benötigt Bearbeitungsdauer reduziert werden.

Abstract

A significant limitation for the use of additive manufacturing (AM) processes in an industrial context is the uncertainty about possible manufacturing conditions, costs and resulting part properties related to the used machines and materials. Since a large range of processes, machines, and materials are available on the market, the choice of optimal configuration for a user-specific part is often challenging. To simplify the development and design processes and to support the respective user in production planning, an architecture is presented, which allows an estimation of manufacturing conditions of AM technologies. The system consists of a database, which contains data about available machines, materials and additional information for quality assurance. For this purpose, defined parameters of machines registered in the network are directly retrieved from the machine control via OPC-UA communication standard. Subsequently, in a logic layer, the gathered information is matched with the requested part geometry and with additional customer requirements. As a result, the user can assess the influences of his decisions regarding design, material and machine selection at an early phase of the product development process, which ensures the basic feasibility and the planned production as well as the estimation of quality and costs.

Abstract

Multi-stage production systems concede for low error and failure margins within every single machining and assembly step to not degrade product quality. Especially during multi-stage production of rotating parts, minor defects during a single step can corrupt a workpiece beyond repair. Since multistage production systems are complex, inter-connected chains of machining steps, a global approach to handling and compensating error emergence and propagation is for reaching Zero-Defect Manufacturing indispensable. We introduce Part Variation Modeling within a knowledge capturing platform to monitor centrally gathered metrological data for deviations. Further, a parametric model is presented allowing for description of rotating parts and enabling identification of deviations at every stage. Based on our inter-stage correlation analysis technique, the parametric model enables description of Part Variation Modes of a piece given current machine states and historic deviation likelihood as will be presented.

Abstract

In the context of the optimization of multi-stage production systems, a large number of process, workpiece and machine data are recorded using sensor systems. However, since not all influencing factors and possible defects, especially in highly complex process chains, can be detected by physical sensors, the machine operator’s experience and his ability to identify non-conformances play a decisive role for achieving zero-defect manufacturing of high-quality parts. In order to make use of these aspects for defect and process analyses as well as for downstream compensation, rework measures and data-driven optimization strategies, a user interface connected to a central database is required. The user interface aims to enable standardized recording of identified defects and performed rework. For this purpose, a game engine is used to allow a user-friendly operation using touch gestures and a three-dimensional visualization of the workpiece. The web-based tool is implemented on the front end of a database enabling a cross-platform access from various devices.

Abstract

In Selective Laser Sintering, powdery materials are locally melted layer by layer by the energy input of a laser. The temperatures within the powder bed and the energy input of the laser have a decisive influence on the properties of the workpiece to be manufactured. Poor temperature conditions can lead to distortion due to premature crystallization, uncontrolled growth or other defects within the part. In order to avoid the production of time-consuming and cost-intensive scrap but also to meet the requirements for mass personalized products, it is of considerable economic importance to identify and apply optimal fabrication parameters. For this purpose, an approach for an industrially scaled inline process control for Selective Laser Sintering is introduced. In combination with monitoring systems, e.g. thermographic cameras, the presented architecture can be used to adjust fabrication parameters to the transient conditions in order to guarantee high-quality results and the reliability of the process.

Abstract

In October 2017, the High-Performance Center »Mass Personalization« was launched in Stuttgart, a research initiative of the local Fraunhofer Institutes and the University of Stuttgart. The pilot phase of 2.5 years focusses on the major requirements of enabling technologies for successfully transferring Mass Personalization into the health, automotive and building sector. The research program is divided into 3 sector-related pilot projects with focus on an early involvement of the related industries to ensure that the developed methods and processes meet the requirements for industry application. This paper presents the pilot project 2, which is related to the automotive and building sector.

Abstract

The increasing complexity of parts and the growing quality requirements pose new challenges for today’s manufacturing industry. Multi-Stage Production Systems, which are known for complex links and sequences of many different process steps, must be adapted to these requirements. This means, being cost-effective and flexible while still meeting high quality standards. The idea of Zero-Defect Manufacturing aims to reduce scrap, rework and special operations by analyzing and optimizing multi-stage production systems through data-driven and learning-based approaches. A Knowledge Capturing Platform concept is introduced to extract a deeper understanding from collected data with inter-stage correlation methods, part variation approaches along the line and intelligent monitoring systems.