8.1 Sensorik, mess- und prüftechnische Verfahren
Filtern
Erscheinungsjahr
- 2023 (3) (entfernen)
Dokumenttyp
- Beitrag zu einem Tagungsband (3) (entfernen)
Sprache
- Englisch (3)
Referierte Publikation
- ja (3) (entfernen)
Schlagworte
Organisationseinheit der BAM
Simulating a Gas Source Localization Algorithm with Gas Dispersion Produced by Recorded Outdoor Wind
(2023)
This paper reports the use of the first gas dispersion simulator capable of introducing large wind fluctuations into simulations. The proposed simulator enables testing of a modification made to a gas source localization algorithm in a realistic scenario in order to study how the change affects it. Gas source localization in an outdoor environment is a challenging task mainly due to the complexity of the gas spread caused by the unpredictable nature of constantly changing wind. Therefore, a novel use of outdoor wind in developing a gas source localization system by simulation is presented in this paper. To consider the characteristic of sudden but large and unpredictable changes in wind direction, we propose to use recorded outdoor wind to simulate a realistic outdoor gas dispersion which has been done for the first time to the best of our knowledge. With the use of this simulator, we have tested a modification to a mobile robot-based gas source localization algorithm. Multiple simulations of the modified and the original particle filter-based algorithm have been done to study the effect of the tested modification. The results showed that a small difference in the algorithm can greatly impact the results. From this study, we show that the use of simulation consisting of the necessary traits to evaluate outdoor gas source localization, has the potential to accelerate the development of a reliable localization system.
Gas source localization (GSL) helps mitigate the impact of industrial accidents and natural disasters. While GSL may be dangerous and time-consuming when performed by humans, swarms of agile and inexpensive nano aerial robots may increase the safety and efficiency of gas source localizations. Since the small payloads of nano aerial robots limit the sensing and computing resources, strategies adapted from biological swarms, such as colonies of social insects, are used to coordinate robot swarms. Most swarm GSL strategies are based on the assumption that the maxima of gas concentrations are sufficiently close to the gas sources. However, prior studies have indicated that the occurrence of “bouts”, a metric for the intermittency of gas distributions, may advantageously be used as a more accurate gas source proximity indicator. This paper presents a swarm GSL strategy employing bouts as source proximity indicators and a bio-inspired pheromone system for communication. Nano aerial robots, deployed in this study, act as agents and emit pheromone markers in an artificial environment upon detecting bouts. Leveraging the concept of artificial potential fields, the agents switch between exploiting the knowledge of the swarm by following pheromone gradients and exploring the search space by targeting a random point. The agents are repelled by each other and by walls to avoid collisions. The swarm GSL strategy is implemented into three nano aerial robots and validated in a real-world experiment in an indoor environment with a single gas source. The results indicate that the the swarm GSL strategy presented in this paper is capable of GSL in indoor environments and that the intermittency of gas distributions is a better source proximity indicator than the mean concentration.
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.