The FGLOCTweet Corpus: An English tweet-based corpus for fine-grained location-detection tasks

Location detection in social-media microtexts is an important natural language processing task for emergency-based contexts where locative references are identified in text data. Spatial information obtained from texts is essential to understand where an incident happened, where people are in need of help and/or which areas have been affected. This information contributes to raising emergency situation awareness, which is then passed on to emergency responders and competent authorities to act as quickly as possible. Annotated text data are necessary for building and evaluating location-detection systems. The problem is that available corpora of tweets for location-detection tasks are either lacking or, at best, annotated with coarse-grained location types (e.g. cities, towns, countries, some buildings, etc.). To bridge this gap, we present our semi-automatically annotated corpus, the Fine-Grained LOCation Tweet Corpus (FGLOCTweet Corpus), an English tweet-based corpus for fine-grained location-detection tasks, including fine-grained locative references (i.e. geopolitical entities, natural landforms, points of interest and traffic ways) together with their surrounding locative markers (i.e. direction, distance, movement or time). It includes annotated tweet data for training and evaluation purposes, which can be used to advance research in location detection, as well as in the study of the linguistic representation of place or of the microtext genre of social media.

Investigating the Condition Monitoring Potential of Oil Conductivity for Wear Identification in Electro Hydrostatic Actuators

To meet future goals of more electric airplanes conventional hydraulic airplane control systems, consisting of redundant centralized pumps within the airplane’s fuselage, need to be substituted for compact electro-hydraulic actuators (EHA). The capsulated architecture of EHAs results in higher safety due to separate hydraulic circuits, simple practicability of redundancy, decreased maintenance because of simplified error location detection as well as an overall reduction in weight and complexity of the airplane control system. Currently, EHAs are only used as backup devices as the reliability does not achieve normative requirements for a frontline application. Thus, recent studies aim to increase the reliability. The axial piston pump of current EHA is the source of most failures. High dynamic requirements and challenging operation points and environments result in wear of contact pairs such as swash plate/piston shoes, pistons/cylinder block and cylinder block/valve plate. In the scope of the project MODULAR at ifas one goal is to increase the robustness of the contact surfaces. A second goal addresses the topic of developing a condition monitoring approach to constantly track the pumps’ health status. Next to signals such as pressures and temperatures, acceleration and oil status signals describing the actual particle contamination are needed. In this contribution different methods of oil status detection are explained and the method of electric conductivity analysis for condition monitoring is further investigated. Filtered HLP46 is used and impurities in form of metallic powders are added. Furthermore, degraded oil of a disc-on-disc Tribometer test bench is measured and compared.

FORMATION OF THE OPTOELECTRONIC SYSTEM DIRECTIONAL DIAGRAM USING FIBER-OPTIC CABLE

The method of forming directional diagrams (RD) with the possibility of controlling it in space is described. The method of forming of the object location detection zone of complex shape in the transmitter-receiver optical system with the help of fiber-optic cables (OIC) is substantiated and created. The problem of a circular field of view of a multi-channel optoelectronic system (ECO) creating, designed for advanced high-speed objects at short distance detection has been solved. According to the results of laboratory tests of the developed ECO model is established that in the working range of distances of a location of 0,5 ... 10,0 m reliable detection of the target high-speed and high-precision registration of object in all DS directions is reached.

Development of Laboratory-scale Lamb Wave-based Health Monitoring System for Laminated Composites

This paper presents the development process of a laboratory-scale Lamb wave-based structural health monitoring (SHM) system for laminated composite plates. Piezoelectric patches are used in pairs as actuator/sensor to evaluate the time of flight (TOF), i.e. the time difference between the transmitted/received signals of a damaged plate and those of a healthy plate. The damage detection scheme is enabled by means of evaluating the TOF from at least three actuator/receiver pairs. In this work, experiments were performed on two GFRP plates, one healthy and the other one with artificial delamination. Nine piezoelectric transducers were mounted on each plate and the detection of the delamination location was demonstrated, using 4 pairs and 20 pairs of actuators/sensors. The combinations of fewer and more actuators/sensor pairs both provided a damage location that was in good agreement with the artificial damage location. The developed SHM system using simple and affordable equipment is suitable for supporting fundamental studies on damage detection, such as the development of an algorithm for location detection using the optimum number of actuator/sensor pairs.