Concept and Implementation of a Software Architecture for Unifying Data Transfer in Automated Production Systems

Trunzer, Emanuel; Lötzerich, Simon; Vogel‐Heuser, Birgit

doi:10.1007/978-3-662-57805-6_1

Cited by 8 publications

(3 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…If considered confidential, the alarm IDs are obfuscated by replacing them with hashes or entirely random values known only to the CPA. Similarly, the original timestamps are shifted by a constant amount to obfuscate the time of an alarm's occurrence [32]. Thus, data-driven RCA may be outsourced to publicly hosted cloud resources, even for confidential alarm data.…”

Section: Details Of the Distributed Rca Proceduresmentioning

confidence: 99%

A Distributed Framework for Knowledge-Driven Root-Cause Analysis on Evolving Alarm Data–An Industrial Case Study

Wilch

Vogel‐Heuser

Mager³

et al. 2023

IEEE Robot. Autom. Lett.

Self Cite

View full text Add to dashboard Cite

Root-cause Analysis (RCA) of alarms is a wellestablished research area in automated Production Systems (aPS).Many RCA algorithms have been proposed and successfully evaluated and new ones are being developed. Recently, researchers focus on the incorporation of formalized information about the technical process in the analysis to gather further evidence for common root causes. In industrial applications, alarm data are usually preprocessed to accommodate for use case-specific properties and prepare subsequent analysis steps. Consequently, this letter proposes a generalized RCA framework, for which an arbitrary number of preprocessing, data-driven RCA, and postprocessing algorithms can be selected, to support varying use cases. The framework was successfully evaluated in an industrial case study, using 1.8 million alarms recorded over 450 days from an industrial nonwoven production plant and analyzed using formalized information from process documentation and expert interviews. Seven preprocessing algorithms, one data-driven RCA algorithm, and nine postprocessing algorithms typical for continuous and hybrid technical processes were realized in an otherwise entirely use case-agnostic implementation.Index Terms-Software architecture for robotic and automation, Big Data in robotics and automation.

show abstract

Section: Details Of the Distributed Rca Proceduresmentioning

confidence: 99%

A Distributed Framework for Knowledge-Driven Root-Cause Analysis on Evolving Alarm Data–An Industrial Case Study

Wilch

Vogel‐Heuser

Mager³

et al. 2023

IEEE Robot. Autom. Lett.

Self Cite

View full text Add to dashboard Cite

show abstract

“…The IMPROVE architecture relies on a common data model embedded inside the middleware to overcome the drawbacks of heterogeneous data handling, proprietary tools, and a unique way of data processing. According to [12], the implementation of the standard interface is made by the data management and integration broker, which transfers and routes data between the components and layers of the so-called Unified Data Transfer Architecture.…”

Section: Fundamentals and Related Workmentioning

confidence: 99%

Towards a Self-Adaptive Architecture for Federated Learning of Industrial Automation Systems

Franco

Van

Dreiser

et al. 2021

2021 International Symposium on Software Engineering for Adaptive and Self-Managing Systems (SEAMS)

View full text Add to dashboard Cite

Emerging Industry 4.0 architectures deploy datadriven applications and artificial intelligence services across multiple locations under varying ownership, and require specific data protection and privacy considerations to not expose confidential data to third parties. For this reason, federated learning provides a framework for optimizing machine learning models in single manufacturing facilities without requiring access to training data. In this paper, we propose a self-adaptive architecture for federated learning of industrial automation systems. Our approach considers the involved entities on the different levels of abstraction of an industrial ecosystem. To achieve the goal of global model optimization and reduction of communication cycles, each factory internally trains the model in a self-adaptive manner and sends it to the centralized cloud server for global aggregation. We model a multi-assignment optimization problem by dividing the dataset into a number of subsets equal to the number of devices. Each device chooses the right subset to optimize the model at each local iteration. Our initial analysis shows the convergence property of the algorithm on a training dataset with different numbers of factories and devices. Moreover, these results demonstrate higher model accuracy with our self-adaptive architecture than the federated averaging approach for the same number of communication cycles.

show abstract

“…The study will be more gelled with Industry 4.0 [16], which will be automating the error correction procedure and also allowing the resources to be shared and available over the network. The data about the resources, their scheduling, and their programs will be stored in the databases [17] which can be used as a knowledge base in the future [18].…”

Section: Introductionmentioning

confidence: 99%

Managing Delays for Realtime Error Correction and Compensation of an Industrial Robot in an Open Network

Asif,

Webb

2023

Machines

View full text Add to dashboard Cite

The calibration of articulated arms presents a substantial challenge within the manufacturing domain, necessitating sophisticated calibration systems often reliant on the integration of costly metrology equipment for ensuring high precision. However, the logistical complexities and financial burden associated with deploying these devices across diverse systems hinder their widespread adoption. In response, Industry 4.0 emerges as a transformative paradigm by enabling the integration of manufacturing devices into networked environments, thereby providing access through cloud-based infrastructure. Nonetheless, this transition introduces a significant concern in the form of network-induced delays, which can significantly impact realtime calibration procedures. To address this pivotal challenge, the present study introduces an innovative framework that adeptly manages and mitigates network-induced delays. This framework leverages two key components: controller and optimiser, specifically the MPC (Model Predictive Controller) in conjunction with the Extended Kalman Filter (EKF), and a Predictor, characterised as the Dead Reckoning Model (DRM). Collectively, these methodologies are strategically integrated to address and ameliorate the temporal delays experienced during the calibration process. Significantly expanding upon antecedent investigations, the study transcends prior boundaries by implementing an advanced realtime error correction system across networked environments, with particular emphasis on the intricate management of delays originating from network traffic dynamics. The fundamental aim of this research extension is twofold: firstly, it aims to enhance realtime system performance on open networks, while concurrently achieving an impressive level of error correction precision at 0.02 mm. The employment of the proposed methodologies is anticipated to effectively surmount the intricacies and challenges associated with network-induced delays. Subsequently, this endeavour serves to catalyse accurate and efficient calibration procedures in the context of realtime manufacturing scenarios. This research significantly advances the landscape of error correction systems and lays a robust groundwork for the optimised utilisation of networked manufacturing devices within the dynamic realm of Industry 4.0 applications.

show abstract

Concept and Implementation of a Software Architecture for Unifying Data Transfer in Automated Production Systems

Cited by 8 publications

References 18 publications

A Distributed Framework for Knowledge-Driven Root-Cause Analysis on Evolving Alarm Data–An Industrial Case Study

A Distributed Framework for Knowledge-Driven Root-Cause Analysis on Evolving Alarm Data–An Industrial Case Study

Towards a Self-Adaptive Architecture for Federated Learning of Industrial Automation Systems

Managing Delays for Realtime Error Correction and Compensation of an Industrial Robot in an Open Network

Contact Info

Product

Resources

About