Refine
Document Type
Language
- English (3)
Has full text
- yes (3)
Is part of the Bibliography
- yes (3)
Institute
Publisher
- Leibniz-Universität Hannover (3) (remove)
The seamless fusion of the virtual world of information with the real physical world of things is considered the key for mastering the increasing complexity of production networks in the context of Industry 4.0. This fusion, widely referred to as the Internet of Things (IoT), is primarily enabled through the use of automatic identification (Auto-ID) technologies as an interface between the two worlds. Existing Auto-ID technologies almost exclusively rely on artificial features or identifiers that are attached to an object for the sole purpose of identification. In fact, using artificial features for the purpose of identification causes additional efforts and is not even always applicable. This paper, therefore, follows an approach of using multiple natural object features defined by the technical product information from computer-aided design (CAD) models for direct identification. By extending optical instance-level 3D-Object recognition by means of additional non-optical sensors, a multi-sensor automatic identification system (AIS) is realised, capable of identifying unpackaged piece goods without the need for artificial identifiers. While the implementation of a prototype confirms the feasibility of the approach, first experiments show improved accuracy and distinctiveness in identification compared to optical instance-level 3D-Object recognition. This paper aims to introduce the concept of multisensor identification and to present the prototype multi-sensor AIS.
Classification model of supply chain events regarding their transferability to blockchain technology
(2021)
The blockchain technology represents a decentralized database that stores information securely in immutable data blocks. Regarding supply chain management, these characteristics offer potentials in increasing supply chain transparency, visibility, automation, and efficiency. In this context, first token-based mapping approaches exist to transfer certain supply chain events to the blockchain, such as the creation or assembly of parts as well as their transfer of ownership. However, the decentralized and immutable structure of blockchain technology also creates challenges. In particular, the scalability, storage capacity, and the special requirements for storage formats make it currently impossible to map all supply chain events unrestrictedly on the blockchain. As a first step, this paper identifies important supply chain events for different use cases combining blockchain technology and supply chain management. Secondly, the supply chain events are classified in terms of their expected technical properties and their relevance for the respective use case. Finally, the identified supply chain events are evaluated regarding their transferability to blockchain technology and a classification model is introduced.
Rising consumption due to a growing world population and increasing prosperity, combined with a linear economic system have led to a sharp increase in garbage collection, general pollution of the environment and the threat of resource scarcity. At the same time, the perception of environmental protection becomes more sensitive as the consequences of neglecting sustainable business and eco-efficiency become more visible. The Circular Economy (CE) could reduce waste production and is able to decouple economic growth from resource consumption, but most of the products currently in use are not designed for the reuse-forms of the CE. In addition, the decision-making process of the End of-Usage (EoU) products regarding the following steps has further weaknesses in terms of economic attractiveness for the participants, which leads to low return rates and thus the disposal is often the only alternative.
This paper proposes a model of the decision-making process, which uses machine learning. For this purpose, a Machine Learning (ML) classification is created, by applying the waterfall model. An artificial neural network (ANN) uses information about the model, use phase and the obvious symptoms of the product to predict the condition of individual components. The resulting information can be used in a downstream economic and ecological evaluation to assess the possible next steps. To test this process comprehensive training data is simulated to train the ANN. The decentralized implementation, cost savings and the possibility of an incentive system for the return of an end-of-usage product could lead to increased return rates. Since electronic devices in particular are attractive for the CE, laptops are the reference object of this work. However, the obtained findings are easily applicable to other electronic devices.