Analytische Chemie
Filtern
Dokumenttyp
- Beitrag zu einem Tagungsband (4) (entfernen)
Sprache
- Englisch (4)
Referierte Publikation
- ja (4) (entfernen)
Schlagworte
- Gas Distribution Mapping (2)
- Spatial Interpolation (2)
- Aerial robot (1)
- Convolutional LSTM (1)
- Deep Learning (1)
- Environmental monitoring (1)
- Gas tomography (1)
- Inter-robot measurements (1)
- Machine learning (1)
- Plume (1)
Organisationseinheit der BAM
- 8 Zerstörungsfreie Prüfung (4) (entfernen)
To better understand the dynamics in hazardous environments, gas distribution mapping aims to map the gas concentration levels of a specified area precisely. Sampling is typically carried out in a spatially sparse manner, either with a mobile robot or a sensor network and concentration values between known data points have to be interpolated. In this paper, we investigate sequential deep learning models that are able to map the gas distribution based on a multiple time step input from a sensor network. We propose a novel hybrid convolutional LSTM - transpose convolutional structure that we train with synthetic gas distribution data. Our results show that learning the spatial and temporal correlation of gas plume patterns outperforms a non-sequential neural network model.
Gas distribution mapping is important to have an accurate understanding of gas concentration levels in hazardous environments. A major problem is that in-situ gas sensors are only able to measure concentrations at their specific location. The gas distribution in-between the sampling locations must therefore be modeled. In this research, we interpret the task of spatial interpolation between sparsely distributed sensors as a task of enhancing an image's resolution, namely super-resolution. Because autoencoders are proven to perform well for this super-resolution task, we trained a convolutional encoder-decoder neural network to map the gas distribution over a spatially sparse sensor network. Due to the difficulty to collect real-world gas distribution data and missing ground truth, we used synthetic data generated with a gas distribution simulator for training and evaluation of the model. Our results show that the neural network was able to learn the behavior of gas plumes and outperforms simpler interpolation techniques.
Remote gas sensors mounted on mobile robots enable the mapping of gas distributions in large or poorly accessible areas. A challenging task however, is the generation of three-dimensional distribution maps from these spatially sparse gas measurements. To obtain high-quality reconstructions, the choice of optimal measuring poses is of great importance. Remote gas sensors, that are commonly used in Robot Assisted Gas Tomography (RAGT), require reflecting surfaces within the sensor’s range, limiting the possible sensing geometries, regardless of whether the robots are ground-based or airborne. By combining ground and aerial robots into a heterogeneous swarm whose agents are equipped with reflectors and remote gas sensors, remote inter-robot gas measurements become available, taking RAGT to the next dimension – releasing those constraints. In this paper, we demonstrate the feasibility of drone-to-drone measurements under realistic conditions and highlight the resulting opportunities.
Wireless sensor networks provide occupational health experts with valuable information about the distribution of air pollutants in an environment. However, especially low-cost sensors may produce faulty measurements or fail completely. Consequently, not only spatial coverage but also redundancy should be a design criterion for the deployment of a sensor network. For a sensor network deployed in a steel factory, we analyze the correlations between sensors and build machine learning forecasting models, to investigate how well the sensor network can compensate for the outage of sensors. While our results show promising prediction quality of the models, they also indicate the presence of spatially very limited events. We, therefore, conclude that initial measurements with, e.g., mobile units, could help to identify important locations to design redundant sensor networks.