Refine
Document type
- Conference Proceeding (12)
- Article (peer-reviewed) (4)
- Bachelor Thesis (4)
- Master's Thesis (1)
- Report (1)
Keywords
- Industry 4.0 (22) (remove)
Course of studies
Smart Condition Monitoring for Industry 4.0 Manufacturing Processes: An Ontology-Based Approach
(2019)
Combining Chronicle Mining and Semantics for Predictive Maintenance in Manufacturing Processes
(2020)
In the context of Industry 4.0, smart factories use advanced sensing and data analytic technologies to understand and monitor the manufacturing processes. To enhance production efficiency and reliability, statistical Artificial Intelligence (AI) technologies such as machine learning and data mining are used to detect and predict potential anomalies within manufacturing processes. However, due to the heterogeneous nature of industrial data, sometimes the knowledge extracted from industrial data is presented in a complex structure. This brings the semantic gap issue which stands for the lack of interoperability among different manufacturing systems. Furthermore, as the Cyber-Physical Systems (CPS) are becoming more knowledge-intensive, uniform knowledge representation of physical resources and real-time reasoning capabilities for analytic tasks are needed to automate the decision-making processes for these systems. These requirements highlight the potential of using symbolic AI for predictive maintenance.
To automate and facilitate predictive analytics in Industry 4.0, in this paper, we present a novel Knowledge-based System for Predictive Maintenance in Industry 4.0 (KSPMI). KSPMI is developed based on a novel hybrid approach that leverages both statistical and symbolic AI technologies. The hybrid approach involves using statistical AI technologies such as machine learning and chronicle mining (a special type of sequential pattern mining approach) to extract machine degradation models from industrial data. On the other hand, symbolic AI technologies, especially domain ontologies and logic rules, will use the extracted chronicle patterns to query and reason on system input data with rich domain and contextual knowledge. This hybrid approach uses Semantic Web Rule Language (SWRL) rules generated from chronicle patterns together with domain ontologies to perform ontology reasoning, which enables the automatic detection of machinery anomalies and the prediction of future events’ occurrence. KSPMI is evaluated and tested on both real-world and synthetic data sets.
This bachelor thesis deals with the changing qualification requirements caused by In-dustry 4.0 and provides an overview of the current qualifications of employees and the accompanying future training measures to improve their qualifications, using Daimler and its strategies as an example. The results regarding necessary future qualifications are derived from an extensive literature research as well as an employee survey and qualitative expert interviews. Previous studies depict that due to Industry 4.0 and the transformation from internal combustion engines to electrical engines many current job positions are dissolving, but in return new fields of work are being created. Conse-quently, to see what challenges companies and employees will face in the future, the-oretical concepts were described and analyzed. As theoretical basis the resource-based, competence based and knowledge-based view as well as the strategic leader-ship approach were chosen, which explain how companies grant their competitive ad-vantage and future success. Afterwards, the theoretical foundations were applied to the resources, competences, knowledge and leadership styles relevant to Industry 4.0. In addition, the company, which served as the research object, was presented with its business units, departments and strategies. Conclusively, the results state that it is necessary and possible to invest primarily in basic knowledge using further training measures. Additionally, more intensive communication is required for the effi-cient implementation of the company's strategy. Lastly, recommendations regarding training measures to increase competences, limitations and further measures are dis-cussed.
Within the 21st century data are the new raw material, is what Ms. Angela Merkel said at the CEBIT conference in 2016. Digitization, what means data-analysis in real-time as well as fast and steady changes in the technological environment, is a key factor nowadays. New processes, new daily tasks and new know-how are needed to survive in a steadily changing world. In succession, companies and private households need to adapt. Otherwise, these will be selected according to Darwin’s theory of evolution. “Survival of the smartest” – as the mantra of today. While some companies are already familiar with the changes introduced by industry 4.0, others are still challenged with catching up industry 3.0. In a smart world it is important to know in which digital maturity status the company is staying and where the company sees itself in the future. But especially for smaller companies the obstacles of realizing industry 4.0 or digitization are defined by high investment costs, a lack of human resources and high requirements in data protection. Therefore, the following thesis is handling this topic specifically within procurement and gives answers to the following questions: What is procurement 4.0? Do the massive changes mean the procurement-endgame? What are the new challenges that procurement has to face and what are the new competencies a purchaser has to adopt? On the basis of a survey the procurement department of the Sto SE & Co. KGaA is classifying the own digital Status quo in the digital capability maturity model. On the basis of the current project “Implementing a Supplier-Relationship-Management and Collaboration system (SRM)” the thesis is answering to the research question: “What approach is suitable to introduce an SRM-and Collaboration tool and how to implement this tool specifically in procurement?”
The rise of digital twins in the manufacturing industry is accompanied by new possibilities, like process automation and condition monitoring, real time simulations and quality and maintenance prediction are just a few advantages which can be realized. This paper takes a novel approach by extracting the fundamental knowledge of a data set from a production process and mapping it to an expert fuzzy rule set. Afterwards, new fundamental augmented data is generated by exploring the feature space of the previously generated fuzzy rule set. At the same time, a high number of artificial neural network (ANN)models with different hyperparameter configurations are created.
The best models are chosen, in line with the idea of survival of the fittest, and improved with the additional training data sets, generated by the fuzzy rule simulation. It is shown that ANN models can be improved by adding fundamental knowledge represented by the discovered fuzzy rules. Those models can represent digitized machines as digital twins. The architecture and effectiveness of the digital twin is evaluated within an industry 4.0 use case.