Filtern
Dokumenttyp
- Beitrag zu einem Tagungsband (13)
- Vortrag (11)
- Posterpräsentation (3)
- Zeitschriftenartikel (1)
Sprache
- Englisch (26)
- Deutsch (1)
- Mehrsprachig (1)
Schlagworte
- Mobile Robot Olfaction (8)
- Sensor network (8)
- Environmental monitoring (7)
- Low-cost (7)
- Gas Distribution Mapping (4)
- Mobile robot olfaction (4)
- Spatial Interpolation (4)
- Wireless Sensor Network (4)
- Dust sensor (3)
- Gas distribution mapping (3)
- LoRaWAN (3)
- Occupational health (3)
- RASEM (3)
- Wireless sensor network (3)
- Aerial Robot Olfaction (2)
- Aerial robot (2)
- Air Pollution (2)
- Air Quality (2)
- Air pollution (2)
- Convolutional LSTM (2)
- Deep Learning (2)
- Environmental Monitoring (2)
- Graph neural networks (2)
- Localization of gas sources (2)
- Machine learning (2)
- Nano UAV Swarm (2)
- Occupational Health (2)
- Plume (2)
- Sensing node (2)
- Sensor Network (2)
- Sensor drift (2)
- Sensor placement (2)
- Sequential Learning (2)
- Spatial interpolation (2)
- Super-Resolution (2)
- TDLAS (2)
- Tomographic reconstruction of gas plumes (2)
- Wireless sensing node (2)
- Aerial Robot (1)
- Air quality monitoring (1)
- Deep learning (1)
- Gas Tomography (1)
- Gas tomography (1)
- Ground Robot (1)
- Inter-robot measurements (1)
- Long term monitoring (1)
- Multisensor system (1)
- Tunable Diode Laser Absorption Spectroscopy (TDLAS) (1)
- Tunable Diode Laser Absorption Spectroscopy (TDLAS); UAV-REGAS (1)
- UAV-REGAS (1)
- WiFi (1)
Organisationseinheit der BAM
Eingeladener Vortrag
- nein (11)
The Sharp GP2Y1010AU0F is a widely used low-cost dust sensor, but despite its popularity, the manufacturer provides little information on the sensor. We installed 16 sensing nodes with Sharp dust sensors in a hot rolling mill of a steel factory. Our analysis shows a clear correlation between sensor drift and accumulated production of the steel factory. An eye should be kept on the long-term drift of the sensors to prevent early saturation. Two of 16 sensors experienced full saturation, each after around eight and ten months of operation.
Precise knowledge about the distribution of air pollutants is necessary to develop plausible occupational health measures. Combinatory systems, consisting of mobile robots and stationary sensors, can be effective solutions for the coverage of large measurement areas. However, further research is needed to fully understand their performance in comparison to traditional sensing strategies. Therefore, multiple sensor networks layouts will be set up in a simulation environment as well as in real industrial environments. Models for distribution mapping will be developed and evaluated to investigate the performance and opportunities of hybrid-mobility sensor networks for the task of distribution mapping.
Air pollution in industrial environments is a major risk. Precise knowledge about the distribution of air pollutants is necessary to develop plausible occupational health measures. Combinatory systems, consisting of mobile robots and stationary sensors, can be effective solutions for the coverage of large measurement areas.
The Motivation of RASEM (Robot-assisted Environmental Monitoring):
Monitoring of the air quality in industrial environments is inevitable to meet safety Standards.
Because of economic and practical reasons, measurements are carried out sparsely in terms of time and space.
Newest developments on the field of low cost sensor technology enable cost efficient long term monitoring of gases and dust
Gas Distribution Mapping (GDM) is essential in monitoring hazardous environments, where uneven sampling and spatial sparsity of data present significant challenges. Traditional methods for GDM often fall short in accuracy and expressiveness. Modern learning-based approaches employing Convolutional
Neural Networks (CNNs) require regular-sized input data, limiting their adaptability to irregular and sparse datasets typically encountered in GDM. This study addresses these shortcomings by showcasing Graph Neural Networks (GNNs) for learningbased GDM on irregular and spatially sparse sensor data. Our Radius-Based, Bi-Directionally connected GNN (RABI-GNN) was trained on a synthetic gas distribution dataset on which it outperforms our previous CNN-based model while overcoming its constraints. We demonstrate the flexibility of RABI-GNN by applying it to real-world data obtained in an industrial steel factory, highlighting promising opportunities for more accurate GDM models.
Gas distribution mapping (GDM) is a valuable tool for monitoring the distribution of gases in various applications, including environmental monitoring, emergency response, and industrial safety. While GDM is actively researched in the scope of gas-sensitive mobile robots (Mobile Robot Olfaction), there is a potential for broader applications utilizing sensor networks. This presentation gives an overview of the different approaches to GDM and motivate the use of a deep-neural network-based approach. As access to ground truth representations of gas distributions remains a challenge in GDM research, an approach for the simulation of realistic-shaped synthetic gas plumes is described, which was used for training Gas Distribution Decoder, a deep neural network for spatial interpolation of spatially sparse gas measurements.
Setting up sensors for the purpose of environmental monitoring should be a matter of days, but often drags over weeks or even months, preventing scientists from doing real research. Additionally, the newly developed hardware and software solutions are often reinventing existing wheels. In this short paper, we revisit the design of our environmental sensing node that has been monitoring industrial areas over a span of two years. We share our findings and lessons learned. Based on this, we outline how a new generation of sensing node(s) can look like.