Refine
Document Type
- Journal article (3)
- Conference proceeding (1)
Language
- English (4)
Has full text
- yes (4)
Is part of the Bibliography
- yes (4)
Institute
- ESB Business School (3)
- Technik (1)
This paper presents a novel multi-modal CNN architecture that exploits complementary input cues in addition to sole color information. The joint model implements a mid-level fusion that allows the network to exploit cross modal interdependencies already on a medium feature-level. The benefit of the presented architecture is shown for the RGB-D image understanding task. So far, state-of-the-art RGB-D CNNs have used network weights trained on color data. In contrast, a superior initialization scheme is proposed to pre-train the depth branch of the multi-modal CNN independently. In an end-to-end training the network parameters are optimized jointly using the challenging Cityscapes dataset. In thorough experiments, the effectiveness of the proposed model is shown. Both, the RGB GoogLeNet and further RGB-D baselines are outperformed with a significant margin on two different tasks: semantic segmentation and object detection. For the latter, this paper shows how to extract object level groundtruth from the instance level annotations in Cityscapes in order to train a powerful object detector.
Manufacturing has to adapt to changing situations in order to stay competitive.It demands a flexible and easy-to-use integration of production equipment and ICT systems. The contribution of this paper is the presentation of the implementation of the Manufacturing Integration Assistant (MIALinx). The integration steps range from integrating sensors over collecting and rule-based processing of sensor information to the execution of required actions. Furthermore, we describe the implementation of MIALinx by commissioning it in a manufacturing environment to retrofit legacy machines for Industrie 4.0. Finally, we validate the suitability of our approach by applying our solution in a medium-size company.
In smart factories, maintenance is still an important aspect to safeguard the performance of their production. Especially in case of failures of machine components diagnosis is a time-consuming task. This paper presents an approach for a cyber-physical failure management system, which uses information from machines such as programmable logic controller or sensor data and IT systems to support the diagnosis and repairing process. Key element is a model combining the different information sources to detect deviations and to determine a probable failed component. Furthermore, the approach is prototypically implemented for leakage detection in compressed air networks.
The flexible and easy-to-use integration of production equipment and IT systems on the shop floor becomes more and more a success factor for manufacturing to adapt rapidly to changing situations. The approach of the Manufacturing Integration Assistant (MIALinx) is to simplify this challenge. The integration steps range from integrating sensors over collecting and rule-based processing of sensor information to the execution of required actions. This paper presents the implementation of MIALinx to retrofit legacy machines for Industry 4.0 in a manufacturing environment and focus on the concept and implementation of the easy-to-use user interface as a key element.