Filtern
Dokumenttyp
Sprache
- Englisch (12)
- Mehrsprachig (1)
Schlagworte
- TDLAS (4)
- Gas tomography (3)
- Gas Distribution Mapping (2)
- Gas dispersion simulation (2)
- Low-cost (2)
- Mobile Robot Olfaction (2)
- Mobile robot olfaction (2)
- Occupational health (2)
- Plume (2)
- Sensor network (2)
Organisationseinheit der BAM
- 8.1 Sensorik, mess- und prüftechnische Verfahren (13) (entfernen)
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.
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.
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.
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.
Air pollution within industrial scenarios is a major risk for workers, which is why detailed knowledge about the dispersion of dusts and gases is necessary. This paper introduces a system combining stationary low-cost and high-quality sensors, carried by ground robots and unmanned aerial vehicles. Based on these dense sampling capabilities, detailed distribution maps of dusts and gases will be created. This system enables various research opportunities, especially on the fields of distribution mapping and sensor planning. Standard approaches for distribution mapping can be enhanced with knowledge about the environment’s characteristics, while the effectiveness of new approaches, utilizing neural networks, can be further investigated. The influence of different sensor network setups on the predictive quality of distribution algorithms will be researched and metrics for the quantification of a sensor network’s quality will be investigated.
The development of algorithms for mapping gas distributions and localising gas sources is a challenging task, because gas dispersion is a highly dynamic process and it is impossible to capture ground truth data. Fluid-mechanical simulations are a suitable way to support the development of these algorithms. Several tools for gas dispersion simulation have been developed, but they are not suitable for simulations of large outdoor environments. In this paper, we present a concept of how an existing simulator can be extended to handle both indoor and large outdoor scenarios.
Remote gas sensors mounted on mobile robots enable the mapping of gas distributions in large or hardly accessible areas. A challenging task, however, is the generation of threedimensional distribution maps from these gas measurements.
Suitable reconstruction algorithms can be adapted, for instance, from the field of computed tomography (CT), but both their performance and strategies for selecting optimal measuring poses must be evaluated. For this purpose simulations are used, since, in contrast to field tests, they allow repeatable conditions. Although several simulation tools exist, they lack realistic models of remote gas sensors. Recently, we introduced a model for a Tunable Diode Laser Absorption Spectroscopy (TDLAS) gas sensor taking into account the conical shape of its laser beam. However, the novel model has not yet been validated with experiments. In this paper, we compare our model with a real sensor device and show that the assumptions made hold.
This presentation gives an introduction to the gas-sensitive aerial robots developed at BAM, including various application examples in the field of mobile robot olfaction: gas source localization and gas distribution mapping.
In this paper, we present and validate the concept of an autonomous aerial robot to reconstruct tomographic 2D slices of gas plumes in outdoor environments. Our platform, the so-called Unmanned Aerial Vehicle for Remote Gas Sensing (UAV-REGAS), combines a lightweight Tunable Diode Laser Absorption Spectroscopy (TDLAS) gas sensor with a 3-axis aerial stabilization gimbal for aiming at a versatile octocopter. While the TDLAS sensor provides integral gas concentration measurements, it does not measure the distance traveled by the laser diode’s beam nor the distribution of gas along the optical path. Thus, we complement the set-up with a laser rangefinder and apply principles of Computed Tomography (CT) to create a model of the spatial gas distribution from a set of integral concentration measurements. To allow for a fundamental ground truth evaluation of the applied gas tomography algorithm, we set up a unique outdoor test environment based on two 3D ultrasonic anemometers and a distributed array of 10 infrared gas transmitters. We present results showing its performance characteristics and 2D plume reconstruction capabilities under realistic conditions. The proposed system can be deployed in scenarios that cannot be addressed by currently available robots and thus constitutes a significant step forward for the field of Mobile Robot Olfaction (MRO).
Remote gas sensors like those based on the Tunable Diode Laser Absorption Spectroscopy (TDLAS) enable mobile robots to scan huge areas for gas concentrations in reasonable time and are therefore well suited for tasks such as gas emission surveillance and environmental monitoring. A further advantage of remote sensors is that the gas distribution is not disturbed by the sensing platform itself if the measurements are carried out from a sufficient distance, which is particularly interesting when a rotary-wing platform is used. Since there is no possibility to obtain ground truth measurements of gas distributions, simulations are used to develop and evaluate suitable olfaction algorithms. For this purpose several models of in-situ gas sensors have been developed, but models of remote gas sensors are missing. In this paper we present two novel 3D ray-tracer-based TDLAS sensor models. While the first model simplifies the laser beam as a line, the second model takes the conical shape of the beam into account. Using a simulated gas plume, we compare the line model with the cone model in terms of accuracy and computational cost and show that the results generated by the cone model can differ significantly from those of the line model.