Doctoral Thesis
Refine
Document Type
- Doctoral Thesis (6) (remove)
Has Fulltext
- yes (6)
Is part of the Bibliography
- yes (6)
Keywords
- 5G (1)
- Bauteil (1)
- Biometric Systems (1)
- Ethernet (1)
- Industry 4.0 (1)
- Nachhaltigkeit (1)
- Polypropylen (1)
- Rezyklatkunststoffe (1)
- Synchronization (1)
- Time-Sensitive Networking (1)
The manufacturing industry is undergoing a transformation marked by the emergence of Industry 4.0 and Industry 5.0 paradigms, which are characterized by the integration and automation of machinery. Thereby, the machinery evolves into Cyber-Physical Systems (CPSs). These CPSs consist of software and hardware modules implementing complex manufacturing processes. The ongoing integration of machinery, and external technologies, e.g., the Industrial Internet of Things (IIoT), led to an evolving Smart Manufacturing (SM) environment. At the same time, legacy machinery, the brownfield machinery, exists side-by-side with modern CPSs. The brownfield machinery might be integrated by retrofitting in the modern manufacturing process. Therefore, the evolution of the SM domain thriven by the Industry 4.0 and Industry 5.0 paradigms leads to a more complex SM environment. Moreover, the integration and ongoing adaption of technologies and processes introduce novel relationships and dependencies between employed machinery and systems. Fault Diagnosis (FD) in such a complex SM environment becomes more time-consuming and laborious. A side effect of the ongoing evolution is the advancing capabilities of the machinery and the ability to produce data. Therewith, not only complex data has to be analyzed during any FD but also vast quantities. The search for the origin of the fault is challenging. Additionally, technical challenges in the SM environment hinder a thorough FD. For instance, the available bandwidth for data transmission is unequal to the capabilities of the machinery to produce vast data quantities. Therefore, the application challenge exists to focus on specific areas of the SM environment while choosing a reasonable granularity in data surveillance to cover the fault traces without losing too much information. Thereby, any FD depends heavily on the domain knowledge of the professionals entrusted with the FD task. On top, there is also economic pressure, which raises the tension on the employed professionals as an unexpected downtime, and the loss in production quantity equals the economic loss.
The thesis introduces context-aware FD to mitigate the risen complexity of the SM environment and support the professionals in their work. By supporting the professionals, the time for FD can be reduced, which results in faster fault amendment and reduced cost-intensive production downtimes. The Context-Aware Diagnosis in Smart Manufacturing (TAOISM) Visual Analytics (VA) model backs the context-aware FD. The TAOISM VA model is the theoretical foundation for the context-aware FD and defines the data layer, the models layer, the visualization layer, and the knowledge layer for SM. Hereby, the VA model enables the definition of context, context models, and context hierarchies for their integration in the respective layers. The main idea behind the context-aware FD is to use the narrowing character of the context definition to slice vast amounts of data into manageable context-separated data groups. Thereby, the context model works as a virtual boundary across machinery and systems, which encloses the physical domain (hardware) and the immaterial domain (software) equally. Further, the thesis focuses on contextual faults, which arise from context model violations, and proposes approaches for collecting contextual data. Also, the automated building of context models and the extraction and transformation of contextual data is part of the thesis. Employing the context models impacts each layer of the proposed TAOISM VA model. For each layer, various approaches show the impact of the context models and their employment in three different application scenarios for FD in SM. The performed research is tested and verified in the scenarios of Robotics Application Development (RAD), Maintenance of Industrial Inspection Machines (MIIM) and Abnormal Event Management in Production Lines (AEMPL). Along with employing context models, data augmentation with context models is proposed. Along with other benefits, the presented data augmentation technique has the ability to balance undersampled datasets, which would enable a reduction of data recordings for any context-aware FD in the future. Thereby, the data augmentation technique is to answer the existing inaccuracies in an SM environment, which also impacts the quality of any employed Artificial Intelligence (AI). Another approach targets the unsupervised selection of production-relevant variables to focus FD-related data recordings and surveillance on areas of the SM environment active during production automatically without any domain knowledge involved. The hypothesis, which was proven right, was that faults, especially contextual faults, occur more often on active software and hardware modules. Another challenge from the vast amount of data is that labeling data for AI becomes uneconomical, even for small fault cases in AI. As a result, evaluating any AI model in SM becomes challenging, as standard measures, e.g., accuracy, precision, recall, and F1-score, cannot be applied. In this case, the thesis proposes novel AI performance metrics that decouple comparability and correctness to enable the evaluation of AI models in an SM environment. All the contributions have led to the development of two distinct Proof of Concepts (PoCs). The PoCs are the reference implementation of the context-aware FD and reflect a knowledge-based FD Expert System (ES) and an unsupervised data-driven FD system. The latter was part of the thorough evaluation of the context-aware FD by two groups of domain experts and junior professionals. The successful qualitative evaluation not only hints towards a working context-aware FD but also unveils future research directions and a future vision for SM. Additional domain expert interviews expose the views on the relevancy of a context-aware FD in SM for the future. In general, the evaluation hints towards a context-aware FD, which has versatile applicability, usability, and suitability in SM-related FD.
The overall objective of this dissertation is to enable a more efficient and effective point cloud and mesh partition for artists and 3D application developers. In this dissertation, 3D scans are assumed as the source data material of the 3D application development, reducing the manual and time-consuming modelling of virtual objects. Furthermore, the scanned data is assumed to be processed to a point cloud and reconstructed to a polygon mesh. The mesh has to be partitioned into the objects of interest to design specific interactions with a game engine. Interviews revealed that the partition is manually conducted on a mesh with a 3D manipulation software, which is time-consuming. The partition creation should be automated to increase efficiency and effectiveness. Freely available point cloud and mesh partition algorithms require an expert with appropriate programming skills and field knowledge, which makes them difficult to use. More precisely, the algorithms cannot be used in existing workflows as they are not implemented in a common graphical 3D manipulation software. Beneath these problems, the partition automation should work on real-world data and have a low runtime to raise efficiency. Different sub-research objectives were formulated from these problems and requirements, leading to novel approaches in the domains of: (a) sequential partition creation with deep reinforcement and imitation learning, (b) episodic partition creation with graph neural networks, (c) match-based reward calculation and (d) synthetic scene generation. One sub-research objective is the replacement of a human expert with an agent. In this context, a novel deep reinforcement learning (DRL) partition framework is presented. Experiments were conducted using this framework combined with the region growing algorithm and synthetic scenes created by a self-developed scene generator. The maximum reward could almost be achieved with a fine-tuned PointNet and by evaluating the wall and non-wall objects separately. This approach is not applicable to real-world scenes, which is necessary to achieve the efficiency and effectiveness objective. Therefore, another DRL partition approach is introduced, where an agent unifies superpoints in the so-called superpoint growing environment. The point cloud is divided into superpoints, which will be unified into the objects of interest by an agent. The experimental results show that this approach can be applied to real-world scenes. Beneath the application of DRL, an imitation learning approach was developed, increasing the agent’s performance in the superpoint growing environment. The runtime in the sequential superpoint growing environment is poor, as each union decision requires a neural network call. Hence, a further sub-research objective is to improve the runtime. An episodic environment was developed as a solution, only requiring one graph neural network call. Similarities between superpoints are estimated in this environment and passed to a union algorithm. The differences between two graph neural network architectures and two union algorithms were experimentally investigated. According to the results, calculating the superpoint similarities with a correlation of the embedded node features is more robust than the similarity estimation with a sigmoid activation function. The reward function, used in the DRL partition approaches, was realised by a matching procedure. As this function influences the partition quality, another sub-research objective is to investigate the differences between various match types. Matching functions from the literature were compared, and another match type was introduced. The usage of different match types in the learning process was experimentally evaluated. Although an agent gets more feedback with all match types, the best results (visual and in terms of the partition size) were achieved by only using first-order matches in the reward function. The synthetic scenes of the region growing approach lack realism as the lighting information is ignored, which can be important to train networks for the partition task. Therefore, a further sub-research objective is to develop a scene generator where the lighting is taken into account. After its development, the generated scenes were experimentally evaluated in a pre-training task. It turned out that the lighting information is important for a pre-training as larger accuracies were achieved. Furthermore, a faster convergence can be achieved with the pre-trained network instead of training a network on a target data set from scratch.
Another sub-research objective targets the development of a usable partition interface. In this context, the Blender add-on OpenXtract was developed, containing five open-source point cloud partition algorithms. The partition algorithms were extended by approximating geodesic distances so that the edges of meshes are used. An experiment has shown that the extended algorithms produce larger accuracies, which is considered an increase in effectiveness. Moreover, unstructured interviews revealed that OpenXtract can improve the effectiveness and efficiency of the partition creation.
Diese Arbeit verbindet durch die Einordnung in den Nachhaltigkeitswissenschaften als multidisziplinäres Wissenschaftsgebiet einen ingenieurstechnischen- und einen sozialwissenschaftlichen Teil. Im ingenieurstechnischen Teil konnten Indizien dafür gefunden werden, dass Rezyklatkunststoffe hinsichtlich deren mechanischen Eigenschaften in hochbelasteten Strukturbauteilen eingesetzt werden können und somit Neuwarekunststoffe substituieren. Dazu werden Neuwaren- und Rezyklatkunststoffe aus Polyprophylen mit 30 Gewichtsprozent Talkumfüllung systematisch untersucht. Dabei wird der Einfluss von Kerben, Bindenähten, Mittelspannung, Temperatur und Alterung auf die mechanischen Eigenschaften unter statischer und zyklischer Belastung untersucht. Begleitende analytische Untersuchungen beschreiben die molekularen und kristallinen Unterschiede von Neuwaren- und Rezyklatkunststoffen. Damit können Rückschlüsse auf die mechanischen Eigenschaften gezogen werden und lassen sich dadurch wissenschaftlich begründen.
Die ermittelten mechanischen Kennwerte unter statischer und zyklischer Belastung fließen in ein Kerbspannungskonzept nach dem höchst beanspruchten Werkstoffvolumen V80 und nach dem Spannungsgradienten χ* ein. Lokale Beanspruchungskennwerte werden nach dem in dieser Arbeit entwickelten Konzept der relativen inelastischen Dehnungen ermittelt.
Damit wird an einem Geräteträger einer Geschirrspülmaschine ein zyklischer Festigkeitsnachweis erbracht, dass der Geräteträger aus dem untersuchten Rezyklatmaterial die geforderte Lebensdauer ertragen kann. Begleitende numerische Berechnungen und Bauteilversuche unter Einsatzbedingungen validieren die Lebensdauerabschätzung.
Im sozialwissenschaftlichen Teil dieser Arbeit wird untersucht, wie Rezyklate aus ihrer technologischen Nische in eine breite Anwendung gelangen können. Dazu wird das Modell der Multi-Level Perspective nach Geels [Gee02] verwendet. Um Rezyklate aus der technologischen Nische zu heben, bedarf es einer Strategie von verschiedenen Akteuren aus unterschiedlichen Ebenen. Dabei soll die Strategie Faktoren ermitteln, die es ermöglichen, das Rezyklate ein eigenes Regime bilden können. Diese Strategie wird in leitfadengestützten Experteninterviews mit Akteurgruppen aus dem sozioökonomischen, -technischen und -politischen Bereich, erfragt. Dabei wird mit Hilfe einer inhaltlich strukturierenden qualitativen Inhaltsanalyse die Strategie abgeleitet, die Rezyklate verstärkter in technischen Anwendungen einsetzt und wie sich der Markt hierfür zukünftig weiterentwickeln muss.
Biometric systems have experienced a large development in recent
years since they are accurate, secure, and in many cases, more user
convenient than traditional credential-based access control systems. Inspite of their benefits, biometric systems are still vulnerable to attack presentations (APs), which can be easily launched by a fraudulentsubject without having a wide expert knowledge. This way, he/she can gain access to several applications, such as bank accounts and smartphone unlocking, where biometric systems are frequently deployed. In order to mitigate such threats and increase the security of biometric systems, the development of reliable Presentation Attack
Detection (PAD) algorithms is of utmost importance to the research
community.In the context of PAD, we explore in this Thesis different strategies and methods in order to improve the generalisation capability of PAD schemes. To that end, we propose the definition of a semantic common feature space which successfully discriminates bona fide presentations (BPs)1 from APs. In essence, this process is seeking for those significant features extracted from known PAI species samples that are observed in unknown PAI species. In addition, we explore several handcrafted techniques in order to build a reliable description of features per biometric characteristic studied. The experimental evaluation shows that a common feature space can be computed through the fusion between generative models and discriminative approaches. Remarkable detection performances for high-security thresholds lead to the construction of a convenient (i.e., low BP rejection rates or Bona fide Presentation Classification Error Rate (BPCER)) and secure (i.e., low AP acceptance rates or Attack Presentation Classification Error Rate (APCER)) PAD subsystem.
Factory automation becomes a subject of the transformation through Industry 4.0 and Industrial Internet of Things, and this introduces a new set of requirements due to novel industrial use cases. Future industrial communication is based on a unified network infrastructure that serves diverse communication services ranging from time-critical to best-effort data. Driven by the industrial domain, Time-Sensitive Networking (TSN) is the communication technology for enabling full connectivity in the smart factory. In conjunction to the Ethernet-based TSN, wireless technologies become a key enabler for future automation scenarios in order to support mobility and modularity aspects that are being demanded by flexible manufacturing and advanced automation. The latest cellular networking standard 5G develops the Ultra Reliable Low Latency Communication profile which supports the novel requirements through an advanced Quality of Service framework
and an enhanced 5G New Radio physical layer. The convergence of TSN and 5G is a promising solution for future industrial networks. Time synchronization is a key aspect of industrial communication networks. It establishes a common sense of time between all network nodes. This is one enabler for the alignment of time-critical processes across
distributed systems such as time-triggered data transmission to achieve ultra reliable bounded low latency, i.e. deterministic communication.
This work researches the time synchronization in converged TSN/5G networks. A comprehensive use case analysis identifies potential applications and their corresponding requirements for the integration of converged TSN/5G networks. Particular use cases are highlighted due to their stringent requirements regarding synchronization. According
network topologies are derived which are later used to review practical aspects of the synchronization. In order to research the synchronization in converged TSN/5G networks, the involved heterogeneous procedures are modeled. Consequently, the individual
models are merged to establish a novel model which describes the joint synchronization in converged TSN/5G networks and thus allows to investigate how the heterogeneous mechanism engage. Departing from this joint synchronization model, potential improvements are derived. The discussed improvements are manifold and address the distribution
of timing information, the reference clock selection, and the correction of timing information. As evaluation, the joint synchronization model is applied to generic networks under worst-case parameterization, that is derived from related specification and standardization works. This allows to study the general behavior of the synchronization in converged TSN/5G networks. Supplementary, the joint synchronization model is also applied to use case specific networks. This permits to obtain a practical perspective of the
synchronization in converged TSN/5G networks. These analyses yield the determination of synchronization boundaries which indicate the worst to be expected synchronization quality in the given networks. Consequent simulative experiments validate the previous evaluation of the synchronization in converged TSN/5G networks. It draws a more natural picture of the synchronization as probabilistic parameterization and random effects are considered.
This work shows that a synchronization accuracy well below 1 μs can be achieved converged TSN/5G networks. At the same time it is shown that the synchronization strongly depends on the actual network architecture and the quality of the 5G Radio Access Network (RAN) synchronization. The size of the network affects the synchronization accuracy since each intermediate device between the reference clock and the synchronization target introduces additional inaccuracy to the synchronization. The RAN synchronization, on the other hand, is the big challenge in converged TSN/5G networks as it comprises the
radio link which exposes uncertainty and varying transmission characteristics. But just that enables the synchronization of distributed devices.
Biometric recognition systems are part of our daily life. They enable
a user-convenient authentication alternative to passwords or tokens
as well as high security identity assessment for law enforcement and
border control. However, with a rising usage in general, fraudulent use increases as well. One drawback of biometrics in general is the lack of renewable biometric characteristics. While it is possible to change a password or token, biometric characteristics (e. g. the fingerprint) stays the same throughout a lifespan. Hence, biometric systems are required to ensure privacy protection in order to prevent misuse of sensitive data. In this context, this Thesis evaluates cryptographic solutions that enable storage and real time comparison of biometric data in the encrypted domain. Furthermore, long-term security is achieved by post-quantum secure mechanisms.In addition to those privacy concerns, presentation attacks targeting the capture device are threatening legit operations. Since no information about inner system modules are required to use a presentation attack instrument (PAI) at the capture device, also non-experts could attack the biometric system. Thus, presentation attack detection (PAD) modules are essential to distinguish between bona fide presentations
and attack presentations. In this regard, different methods for fingerprint PAD are analysed in this Thesis, including benchmarks on
several classifiers based on handcrafted features as well as deep learning techniques. The results show that the PAD performance depends
on material properties of the used PAI species in combination with the
captured data type. However, fusing multiple approaches enhances the
detection rates for both convenient and secure application scenarios.