TY - CONF A1 - Winkler, Nicolas P. T1 - Super-Resolution for Gas Distribution Mapping: Convolutional Encoder Decoder Network N2 - 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. T2 - 19th International Symposium on Olfaction and Electronic Nose CY - Aveiro, Portugal DA - 29.05.2022 KW - Gas Distribution Mapping KW - Spatial Interpolation KW - Deep Learning KW - Super-Resolution KW - Sensor Network PY - 2022 AN - OPUS4-54954 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Winkler, Nicolas P. T1 - Revisiting Environmental Sensing Nodes: Lessons Learned and Way Forward N2 - 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. T2 - SMSI 2023 Conference Sensor and Measurement Science International CY - Nuremberg, Germany DA - 08.05.2023 KW - Sensing node KW - Sensor network KW - Environmental monitoring KW - Low-cost KW - LoRaWAN PY - 2023 AN - OPUS4-57455 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Winkler, Nicolas P. T1 - Gather Dust and Get Dusted: Long-Term Drift and Cleaning of Sharp GP2Y1010AU0F Dust Sensor in a Steel Factory N2 - 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. T2 - 38th Danubia-Adria Symposium on Advances in Experimental Mechanics CY - Poros, Greece DA - 20.09.2022 KW - Low-cost KW - Sensor network KW - Dust sensor KW - Sensor drift PY - 2022 AN - OPUS4-55908 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Winkler, Nicolas P. T1 - DeepGDM: Deep Learning for Gas Distribution Mapping N2 - 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. T2 - AASS Seminar CY - Örebro, Sweden DA - 08.06.2023 KW - Deep learning KW - Mobile robot olfaction KW - Environmental monitoring PY - 2023 AN - OPUS4-57635 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Johann, Sergej A1 - Winkler, Nicolas P. A1 - Bartholmai, Matthias ED - Kourkoulis, S. K. T1 - Multi-sensor system for long-term monitoring with WiFi and LoRaWAN technology N2 - In many cases, science falls back on self-developed prototype systems, which are used and developed for the measurement and execution of the tasks. About 80 % of the development is based on the same hardware design, which is used in only one application scenario and then discarded. For the most part, there are also uncalibrated sensors, since it is costly to calibrate a complicated sensor measurement system or the entire measurement chain since access to the sensor systems is not always available. This paper describes a conceptual design to implement a versatile sensor system with the motivation to fuse the data recording and data reception, which can cover large areas with the help of LoRaWAN (Long Range Wide Area Network) technology. To overcome disadvantages of LoRaWAN, namely the slow data rates, the proposed sensor system can also cover smaller areas with the widespread WiFi technology. An enormous advantage over individual complete systems in the form of a prototype, is the rapid expansion, uncomplicated calibration of the individual sensors and the ecological relief. A modular design is used, where individual stacks with sensors and peripherals can be added separately. The stacks are standalone low-power systems and can be calibrated, maintained, and replaced separately and do not require the entire measurement chain. The measured and sent values are stored locally on the main stack and sent to the data collector (gateway) and evaluated by means of the automated selection between WiFi and LoRaWAN. T2 - 38th Danubia-Adria Symposium on Advances in Experimental Mechanics CY - Athens, Greece DA - 20.09.2022 KW - Multisensor system KW - LoRaWAN KW - WiFi KW - Long term monitoring PY - 2022 SP - 1 EP - 2 AN - OPUS4-56462 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - JOUR A1 - Alcalde-Vasquez, R. A1 - Moreno-Pedraza, A. A1 - Rosas-Román, I. A1 - Guillén-Alonso, H. A1 - Riedel, Jens A1 - Partida-Martínez, L. P. A1 - Winkler, R. T1 - MoBiMS: A Modular Miniature Mass Analyzer for the Real-Time 2 Monitoring of Gases and Volatile Compounds in Biological Systems N2 - Living organisms constantly interact with their environment, including through the exchange of gases. Respiration and the release and uptake of volatile organic compounds (VOCs) create dynamic microenvironments in biological systems. Studying the kinetics of volatiles in biological systems requires expensive instruments, and data analysis is challenging. Therefore, we aimed to design a minimal analytical device for measuring the composition of gaseous mixtures in realtime. We built the ‘Modular Biological Mass Spectrometer’ (MoBiMS) from 3D-printed parts and custom sensors to fit a wide array of experimental set-ups. We tested the chemical detection range and temporal resolution of the MoBiMS employing pure compounds and complex biological samples. Compounds with a higher than 0.4 mmHg vapor pressure and a molecular weight up to 154 g/mol were reliably sensed within seconds. The generated electron impact (EI) spectra were directly comparable with standard databases like the NIST EI library. Under a direct analysis approach, the MoBiMS identified the characteristic odor of banana (Musa sp.), that is, isoamyl acetate; tracked the dynamics of CO2 release while the Alka-Seltzer® reaction occurred showed the kinetics of the transient production and consumption of carbon dioxide during photosynthesis. MoBiMS also discriminated between volatile compounds ions coming from tobacco (Nicotiana benthamiana) leaves and the surrounding air through untargeted analysis. The small footprint of the MoBiMS and its relatively low energy consumption facilitate in situ analyses, as an additional gas supply is not necessary with EI ionization. The MoBiMS is easy to assemble, and its construction and operation are very cost-efficient compared to commercial devices. The analytical performance of the MoBiMS is suitable for real-time studies of biological systems, environmental monitoring, and medical diagnostics. KW - Mass spectrometry KW - Instrumentation KW - Miniaturization KW - Volatiles PY - 2022 DO - https://doi.org/10.1016/j.microc.2021.107090 SN - 0026-265X VL - 175 PB - Elsevier B.V. CY - Amsterdam AN - OPUS4-56528 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Winkler, Nicolas P. T1 - Learning From the Past: Sequential Deep Learning for Gas Distribution Mapping N2 - 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. T2 - ROBOT2022: Fifth Iberian Robotics Conference CY - Zaragoza, Spain DA - 22.11.2022 KW - Gas Distribution Mapping KW - Spatial Interpolation KW - Sequential Learning KW - Convolutional LSTM PY - 2022 AN - OPUS4-56415 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Rolle, Annette A1 - Winkler, H. P. A1 - Probst, Ulrich A1 - Ballheimer, Viktor A1 - Neumeyer, Tino T1 - Verification of design leakage rates for activity release calculation N2 - The mechanical and thermal loadings associated with the routine, normal and accident conditions of transport can have a significant effect on the leak tightness of the sealing system of transport casks for spent fuel and high radioactive waste. Applicants are requested by BAM to provide test programmes for verification of design leakage rates of the sealing system under the possible loads. Two test series initiated to clarify the dependency of the standard leakage rate on dynamic lid displacement as well as the dependency of the useful elastic recovery ru of a metallic seal on temperature and time, are outlined in this paper as examples of present investigations: Sliding tests simulating a lid displacement possible by a horizontal drop of the cask are carried out at the controlled drop test facility of BAM with test flange pairs equipped with metallic Helicoflex seals. For specification of covering values for the useful elastic recovery ru GNS has started a very comprehensive test programme with overall 70 metallic seals installed in test flanges which are stored for a period of one year at three different temperatures up to 150°C. This paper gives an overview about the current approach of BAM in the assessment of cask tightness and informs about the status of the running test series. T2 - PATRAM 2013 - 17th International symposium on the packaging and transportation of radioactive materials CY - San Francisco, CA, USA DA - 2013-08-18 KW - Radioactive material KW - Safety assessment KW - Leakage rate KW - Leak tightness KW - Sealing behavior PY - 2013 SP - 1 EP - 7 PB - Omnipress AN - OPUS4-32194 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - JOUR A1 - Schubert, Sven A1 - Probst, Ulrich A1 - Winkler, H. P. T1 - Behaviour of metallic seals in CASTOR casks under normal and accident conditions of transport: qualification requirements KW - Transport cask KW - Seal KW - Leak tightness KW - Accident KW - Qualification program KW - Transportbehälter KW - Radioaktive Stoffe KW - Dichtung KW - Dichtheit KW - Unfall KW - Qualifikationsprogramm PY - 2009 DO - https://doi.org/10.1179/174651009X12555104004055 SN - 1746-5095 SN - 1746-5109 SN - 0957-476X VL - 20 IS - 4 SP - 179 EP - 182 PB - Ramtrans Publ. CY - Ashford AN - OPUS4-20708 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Winkler, Nicolas P. T1 - Gas Distribution Mapping With Radius-Based, Bi-directional Graph Neural Networks (RABI-GNN) N2 - 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. T2 - International Symposium on Olfaction and Electronic Nose (ISOEN) CY - Grapevine, TX, USA DA - 12.05.2024 KW - Gas distribution mapping KW - Spatial interpolation KW - Graph neural networks KW - Mobile robot olfaction PY - 2024 AN - OPUS4-60106 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER -