Datenanalyse in der intelligenten Fabrik

Niggemann, Oliver; Biswas, Gautam; Kinnebrew, John S.; Khorasgani, Hamed; Volgmann, Sören; Bunte, Andreas

doi:10.1007/978-3-662-45537-1_73-1

Cited by 9 publications

(11 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Typical study objectives in such systems are anomaly detection of sub‐optimal energy consumption, and root cause study. A suitable approach would be based on proposing solutions based on Machine Learning techniques Sisinni et al (2018), which complement traditional solutions based on EMS and MES models Niggemann et al (2015).…”

Section: Related Work and Contributionmentioning

confidence: 99%

“…However, the number of patents and scientific works integrating and linking both approaches (individual machine‐level and aggregate‐level) into applied solutions in the field of CPS manufacturing is scarce and very conceptual, with limited practical contributions Trappey et al (2016). One of the few studies – to the knowledge of the authors – is Niggemann et al (2015). In this study, the authors, for anomaly detection at the factory aggregate level, propose a solution based on probabilistic hybrid automata to detect incorrect event sequences and system timings, and self‐organizing maps that, by reducing the dimensions of the space, is able to detect unusual correlations between energy values.…”

Section: Related Work and Contributionmentioning

confidence: 99%

See 1 more Smart Citation

A novel approach for the detection of anomalous energy consumption patterns in industrial cyber‐physical systems

et al. 2022

View full text Add to dashboard Cite

Most scenarios emerging from the Industry 4.0 paradigm rely on the concept of cyber‐physical production systems (CPPS), which allow them to synergistically connect physical to digital setups so as to integrate them over all stages of product development. Unfortunately, endowing CPPS with AI‐based functionalities poses its own challenges: although advances in the performance of AI models keep blossoming in the community, their penetration in real‐world industrial solutions has not so far developed at the same pace. Currently, 90% of AI‐based models never reach production due to a manifold of assorted reasons not only related to complexity and performance: decisions issued by AI‐based systems must be explained, understood and trusted by their end users. This study elaborates on a novel tool designed to characterize, in a non‐supervised, human‐understandable fashion, the nominal performance of a factory in terms of production and energy consumption. The traceability and analysis of energy consumption data traces and the monitoring of the factory's production permit to detect anomalies and inefficiencies in the working regime of the overall factory. By virtue of the transparency of the detection process, the proposed approach elicits understandable information about the root cause from the perspective of the production line, process and/or machine that generates the identified inefficiency. This methodology allows for the identification of the machines and/or processes that cause energy inefficiencies in the manufacturing system, and enables significant energy consumption savings by acting on these elements. We assess the performance of our designed method over a real‐world case study from the automotive sector, comparing it to an extensive benchmark comprising state‐of‐the‐art unsupervised and semi‐supervised anomaly detection algorithms, from classical algorithms to modern generative neural counterparts. The superior quantitative results attained by our proposal complements its better interpretability with respect to the rest of algorithms in the comparison, which emphasizes the utmost relevance of considering the available domain knowledge and the target audience when design AI‐based industrial solutions of practical value. Finally, the work described in this paper has been successfully deployed on a large scale in several industrial factories with significant international projection.

show abstract

Section: Related Work and Contributionmentioning

confidence: 99%

Section: Related Work and Contributionmentioning

confidence: 99%

A novel approach for the detection of anomalous energy consumption patterns in industrial cyber‐physical systems

et al. 2022

View full text Add to dashboard Cite

show abstract

“…From a data perspective, production process data (e.g., workstations or machines), supplier data (e.g., suppliers or materials), production data (e.g., current events) and order data (e.g., customers or delivery dates) must be taken into account [22]. In addition, it is necessary to enable manual data input (FR rcs 5) in order to enter data if automated data acquisition or transfer is not possible (e.g., manual entry of an employee's absence) [36,37].…”

Section: Objective Of a Solutionmentioning

confidence: 99%

Design and Implementation of a Decision Support System for Production Scheduling in the Context of Cyber-Physical Systems

Freier¹,

Schümann²

2020

WI2020 Zentrale Tracks

View full text Add to dashboard Cite

The use of cyber-physical systems in production promises great potential for production scheduling since a larger information base is available for the scheduling of production orders. However, the mere acquisition of realtime data does not inherently lead to improvements. On the contrary, a targeted preparation of the data is required in order to prevent an information overload. Decision support systems that support decision makers in production scheduling can perform this task. However, the design of such systems in combination with cyber-physical systems has hardly been investigated so far. In this paper, we therefore design and implement a corresponding decision support system in a design science approach. For this, we identify meta-requirements based on a literature analysis and an interview study. Finally, we evaluate the created meta-artifact in a laboratory setting in order to obtain generalizable knowledge about building such a decision support system.

show abstract

“…[11] Besides the mentioned challenges, research states that it is important to model human expertise and especially production knowledge for a transformation of raw data into useful data. [12,13] Thus, in section four, an approach for modeling this production knowledge into a data based prediction of order-specific TT is presented. In section five, the approach is applied both with and without production knowledge to a data set containing real feedback data of a producing company from the machine equipment industry.…”

Section: Challenges and Consequences Of An Accurate Transition Time P...mentioning

confidence: 99%

Impact of Modeling Production Knowledge for a Data Based Prediction of Transition Times

Schuh

Prote

Hünnekes

et al. 2019

IFIP Advances in Information and Communication Technology

View full text Add to dashboard Cite

An increasing demand for customer-specific products is a major challenge for manufacturing companies. In many cases, companies attempt to satisfy this demand by increasing the number of product variants. In those companies, cost-oriented production processes have to be transformed into flexible workshop or island production structures in order to be able to produce this variety. This leads to an increasing complexity of production and subsequently planning. In order to reliably meet due dates, it is necessary to improve the quality of planning. This paper presents an approach for predicting transition times, the times between two production steps, by employing machine learning methods. In particular, the influence of the modelling of production knowledge of experienced employees on the prediction quality compared to a pure optimization of the methods' parameters is investigated.

show abstract

Datenanalyse in der intelligenten Fabrik

Cited by 9 publications

References 43 publications

A novel approach for the detection of anomalous energy consumption patterns in industrial cyber‐physical systems

A novel approach for the detection of anomalous energy consumption patterns in industrial cyber‐physical systems

Design and Implementation of a Decision Support System for Production Scheduling in the Context of Cyber-Physical Systems

Impact of Modeling Production Knowledge for a Data Based Prediction of Transition Times

Contact Info

Product

Resources

About