Benjamin Siegert

University of Stuttgart · Institute of Automation and Software Engineering

In this article, the concepts of transfer and continual learning are introduced. The ensuing review reveals promising approaches for industrial deep transfer learning, utilizing methods of both classes of algorithms. In the field of computer vision, it is already state-of-the-art. In others, e.g. fault prediction, it is barely starting. However, ov...

Anomalies represent deviations from the intended system operation and can lead to decreased efficiency as well as partial or complete system failure. As the causes of anomalies are often unknown due to complex system dynamics, efficient anomaly detection is necessary. Conventional detection approaches rely on statistical and time-invariant methods...

The early and robust detection of anomalies occurring in discrete manufacturing processes allows operators to prevent harm, e.g. defects in production machinery or products. While current approaches for data-driven anomaly detection provide good results on the exact processes they were trained on, they often lack the ability to flexibly adapt to ch...

Industrial transfer learning increases the adaptability of deep learning algorithms towards heterogenous and dynamic industrial use cases without high manual efforts. The appropriate selection of what to transfer can vastly improve a transfer's results. In this paper, a transfer case selection based upon clustering is presented. Founded on a survey...

Due to its probabilistic nature, fault prognostics is a prime example of a use case for deep learning utilizing big data. However, the low availability of such data sets combined with the high effort of fitting, parameterizing and evaluating complex learning algorithms to the heterogenous and dynamic settings typical for industrial applications oft...

Industrial transfer learning increases the adaptability of deep learning algorithms towards heterogenous and dynamic industrial use cases without high manual efforts. The appropriate selection of what to transfer can vastly improve a transfer’s results. In this paper, a transfer case selection based upon clustering is presented. Founded on a survey...

In recent years, the use of lithium-ion batteries has greatly expanded into products from many industrial sectors, e.g. cars, power tools or medical devices. An early prediction and robust understanding of battery faults could therefore greatly increase product quality in those fields. While current approaches for data-driven fault prediction provi...

Reconfiguration demand is increasing due to frequent requirement changes for manufacturing systems. Recent approaches aim at investigating feasible configuration alternatives from which they select the optimal one. This relies on processes whose behavior is not reliant on e.g. the production sequence. However, when machine learning is used, compone...

Trotz hoher Lösungspotenziale des maschinellen Lernens für gängige Probleme der Automatisierungstechnik finden sich in der Praxis wenig Anwendungsbeispiele. Um der Ursache hierfür auf den Grund zu gehen, zeigen die Autoren anhand von vier beispielhaften Anwendungsfällen die Hürden für konventionelles maschinelles Lernen auf und benennen Lösungsansä...

Many decision-making approaches rely on the exploration of solution spaces with regards to specified criteria. However, in complex environments, brute-force exploration strategies are usually not feasible. As an alternative, we propose the combination of an exploration task's vertical sub-division into layers representing different sequentially int...

Despite the high solution potential of machine learning for common problems in automation technology, there are only few examples of its application in real-world manufacturing practice. In order to find the reason for this phenomenon, the authors identify the hurdles for conventional machine learning using four exemplary use cases namely self-lear...

Real-life industrial use cases for machine learning oftentimes involve heterogeneous and dynamic assets, processes and data, resulting in a need to continuously adapt the learning algorithm accordingly. Industrial transfer learning offers to lower the effort of such adaptation by allowing the utilization of previously acquired knowledge in solving...

Nowadays, formal methods are used in various areas for the verification of programs or for code generation from models in order to increase the quality of software and to reduce costs. However, there are still fields in which formal methods haven’t been widely adopted, despite the large set of possible benefits offered. This is the case for the are...

In recent years, the use of lithium-ion batteries has greatly expanded into products from many industrial sectors, e.g. cars, power tools or medical devices. An early prediction and robust understanding of battery faults could therefore greatly increase product quality in those fields. While current approaches for data-driven fault prediction provi...

Nowadays, formal methods are used in various areas for the verification of programs or for code generation from models in order to increase the quality of software and to reduce costs. However, there are still fields in which formal methods have not been widely adopted, despite the large set of possible benefits offered. This is the case for the ar...

Deep learning promises performant anomaly detection on time-variant datasets, but greatly suffers from low availability of suitable training datasets and frequently changing tasks. Deep transfer learning offers mitigation by letting algorithms built upon previous knowledge from different tasks or locations. In this article, a modular deep learning...

Reconfiguration demand is increasing due to frequent requirement changes for manufacturing systems. Recent approaches aim at investigating feasible configuration alternatives from which they select the optimal one. This relies on processes whose behavior is not reliant on e.g. the production sequence. However, when machine learning is used, compone...

Anomalies represent deviations from the intended system operation and can lead to decreased efficiency as well as partial or complete system failure. As the causes of anomalies are often unknown due to complex system dynamics, efficient anomaly detection is necessary. Conventional detection approaches rely on statistical and time-invariant methods...

A multitude of high quality, high-resolution data is a cornerstone of the digital services associated with Industry 4.0. However, a great fraction of industrial machinery in use today features only a bare minimum of sensors and retrofitting new ones is expensive if possible at all. Instead, already existing sensors’ data streams could be utilized t...

The utilization of deep learning in the field of industrial automation is hindered by two factors: The amount and diversity of training data needed as well as the need to continuously retrain as the use case changes over time. Both problems can be addressed by industrial deep transfer learning allowing for the performant, continuous and potentially...

A requirement of future industrial automation systems is the application of intelligence in the context of their optimization, adaptation and reconfiguration. This paper begins with an introduction of the definition of (artificial) intelligence to derive a framework for artificial intelligence enhanced industrial automation systems: An artificial i...

The early and robust detection of anomalies occurring in discrete manufacturing processes allows operators to prevent harm, e.g. defects in production machinery or products. While current approaches for data-driven anomaly detection provide good results on the exact processes they were trained on, they often lack the ability to flexibly adapt to ch...

Digital Twins have been described as beneficial in many areas, such as virtual commissioning, fault prediction or reconfiguration planning. Equipping Digital Twins with artificial intelligence functionalities can greatly expand those beneficial applications or open up altogether new areas of application, among them cross-phase industrial transfer l...

In this article, the concepts of transfer and continual learning are introduced. The ensuing review reveals promising approaches for industrial deep transfer learning, utilizing methods of both classes of algorithms. In the field of computer vision, it is already state-of-the-art. In others, e.g. fault prediction, it is barely starting. However, ov...

Digital Twins have been described as beneficial in many areas, such as virtual commissioning, fault prediction or reconfiguration planning. Equip-ping Digital Twins with artificial intelligence functionalities can greatly expand those beneficial applications or open up altogether new areas of application, among them cross-phase industrial transfer...

It is expected that data-driven methods of artificial intelligence in the context of Industry 4.0 will shape the future of industrial manufacturing. Although the topic is very present in research, the extent of the actual use of these methods remains unclear. This article therefore analyzes scientific articles published between 2013 and 2018 to obt...

In this paper, a novel lightweight incremental class learning algorithm for live image recognition is presented. It features a dual memory architecture and is capable of learning formerly unknown classes as well as conducting its learning across multiple instances at multiple locations without storing any images. In addition to tests on the ImageNe...

Fault prediction based upon deep learning algorithms has great potential in industrial automation: By automatically adapting to different usage contexts, it would greatly expand the usefulness of current predictive maintenance solutions. However, restrictions regarding the centralized accumulation of data necessary for such automatic adaption call...

In this paper, a novel lightweight incremental class learning algorithm for live image recognition is presented. It features a dual memory architecture and is capable of learning formerly unknown classes as well as conducting its learning across multiple instances at multiple locations without storing any images. In addition to tests on the ImageNe...

Future production methods like cyber physical production systems (CPPS), flexibly linked assembly structures and the matrix production are characterized by highly flexible and reconfigurable cyber physical work cells. This leads to frequent job changes and shifting work environments. The resulting complexity within production increases the risk of...

A requirement of future industrial automation systems is the application of intelligence in the context of their optimization, adaptation and reconfiguration. This paper begins with an introduction of the definition of (artificial) intelligence to derive a framework for artificial intelligence enhanced industrial automation systems: An artificial i...

A multitude of high quality, high-resolution data is a cornerstone of the digital services associated with Industry 4.0. However, a great fraction of industrial machinery in use today features only a bare minimum of sensors and retrofitting new ones is expensive if possible at all. Instead, already existing sensors' data streams could be utilized t...

The utilization of deep learning in the field of industrial automation is hindered by two factors: The amount and diversity of training data needed as well as the need to continuously retrain as the use case changes over time. Both problems can be addressed by deep transfer learning allowing for the performant, continuous training on small, dispers...

It is expected that data-driven methods of artificial intelligence in the context of Industry 4.0 will shape the future of industrial manufacturing. Although the topic is very present in research, the extent of the actual use of these methods remains unclear. This article therefore analyzes scientific articles published between 2013 and 2018 to obt...

Future production methods like cyber physical production systems (CPPS), flexibly linked assembly structures and the matrix production are characterized by highly flexible and reconfigurable cyber physical work cells. This leads to frequent job changes and shifting work environments. The resulting complexity within production increases the risk of...

Kurzfassung Die Konzepte des digitalen Zwillings werden sowohl in der Wissenschaft als auch in der In-dustrie immer relevanter. Daraus ergeben sich viele verschiedene Sichtweisen. Ein Überblick über das vorherrschende Verständnis wird in diesem Beitrag gegeben. Darüber hinaus werden die notwendigen Aspekte eines digitalen Zwillings erläutert und de...

Die Konzepte des digitalen Zwillings werden sowohl in der Wissenschaft als auch in der Industrie immer relevanter. Daraus ergeben sich viele verschiedene Sichtweisen. Ein Überblick über das vorherrschende Verständnis wird in diesem Beitrag gegeben. Darüber hinaus werden die notwendigen Aspekte eines digitalen Zwillings erläutert und der Bedarf an z...

Machine learning algorithms rely on a broad database for high quality results. However, studies show that many companies are not willing to share their data with other companies, for example in the form of a shared data cloud. Therefore, the goal should be to make efficient machine learning possible with decentralized data storage that allows confi...

Für eine hohe Ergebnisqualität sind Machine Learning Algorithmen auf eine breite Datenbasis angewiesen. Studien zeigen jedoch, dass viele Unternehmen nicht bereit sind, ihre Daten mit anderen Unternehmen, beispielsweise in Form einer gemeinsamen Daten-Cloud, zu teilen. Ziel sollte es daher sein, effizientes maschinelles Lernen mit einer dezentralen...

Vorwort Zum 20. Mal trifft sich die Community zum Leitkongress der Mess- und Automatisierungstechnik AUTOMATION im Juli 2019. Unter dem Motto „Autonomous Systems and 5G in Connected Industries“ erwartet Sie ein anspruchsvolles Programm! Wie wirken sich künstliche Intelligenz und autonome Systeme auf die Fertigungs- und Prozessautomation der Zukunft...

Vorwort Zum 20. Mal trifft sich die Community zum Leitkongress der Mess- und Automatisierungstechnik AUTOMATION im Juli 2019. Unter dem Motto „Autonomous Systems and 5G in Connected Industries“ erwartet Sie ein anspruchsvolles Programm! Wie wirken sich künstliche Intelligenz und autonome Systeme auf die Fertigungs- und Prozessautomation der Zukunft...

Dass die Komplexität vernetzter Komponenten und deren Entwicklung zunehmen, ist hinlänglich bekannt. So zieht sich das Motiv „Komplexitätssteigerung“ wie ein roter Faden durch die verschiedenen Abschnitte des Statusreports. Deshalb wird auf das Motiv und dessen Ausprägung im Anschluss eingegangen. Wir haben folgendes Verständnis von Komplexität [1]...

In this thesis, a device for measuring the grid frequency, the root mean square voltage and the phasor angle of a single phase low voltage grid is being developed. The measurement device will work together with others as part of a wide area monitoring system detecting inter-­area oscillations and must therefore synchronize its measurement data thro...

In this thesis a program for the generation of coherent, high-resolution, synthetic electrical and thermal load profiles for different types of residential and non- residential buildings in Germany is being developed and surveyed. Based upon the bottom-up-method, scenarios are created using data provided by other authors. With these, simulations of...

In this thesis, an energy management system (EMS) capable of balancing reactive and active power demand and generation while respecting grid constraints is developed and surveyed. A modular approach is taken, using mixed-integer linear programming for unit commitment and economic dispatching and MATPOWER’s Newton-Raphson algorithm for power flow an...