P13.1 - Modular design of a gas mixing apparatus for complex trace gas mixtures

Arendes, D.; Lensch, Henrik; Amann, Johannes; Schütze, Andrea; Baur, Tobias

doi:10.5162/15dss2021/p13.1

Cited by 8 publications

(6 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The dataset used throughout this study was recorded with a custom gas mixing apparatus (GMA) [34][35][36]. The GMA allows us to offer precisely known gas mixtures to multiple sensors simultaneously.…”

Section: Datasetmentioning

confidence: 99%

Comparison of Transfer Learning and Established Calibration Transfer Methods for Metal Oxide Semiconductor Gas Sensors

et al. 2023

View full text Add to dashboard Cite

Although metal oxide semiconductors are a promising candidate for accurate indoor air quality assessments, multiple drawbacks of the gas sensors prevent their widespread use. Examples include poor selectivity, instability over time, and sensor poisoning. Complex calibration methods and advanced operation modes can solve some of those drawbacks. However, this leads to long calibration times, which are unsuitable for mass production. In recent years, multiple attempts to solve calibration transfer have been made with the help of direct standardization, orthogonal signal correction, and many more methods. Besides those, a new promising approach is transfer learning from deep learning. This article will compare different calibration transfer methods, including direct standardization, piecewise direct standardization, transfer learning for deep learning models, and global model building. The machine learning methods to calibrate the initial models for calibration transfer are feature extraction, selection, and regression (established methods) and a custom convolutional neural network TCOCNN. It is shown that transfer learning can outperform the other calibration transfer methods regarding the root mean squared error, especially if the initial model is built with multiple sensors. It was possible to reduce the number of calibration samples by up to 99.3% (from 10 days to approximately 2 h) and still achieve an RMSE for acetone of around 18 ppb (15 ppb with extended individual calibration) if six different sensors were used for building the initial model. Furthermore, it was shown that the other calibration transfer methods (direct standardization and piecewise direct standardization) also work reasonably well for both machine learning approaches, primarily when multiple sensors are used for the initial model.

show abstract

Section: Datasetmentioning

confidence: 99%

Comparison of Transfer Learning and Established Calibration Transfer Methods for Metal Oxide Semiconductor Gas Sensors

et al. 2023

View full text Add to dashboard Cite

show abstract

“…The dataset used throughout this study to evaluate the benefits of transfer learning in the field of deep learning is generated with our recently developed novel gas mixing apparatus (GMA), which allows up to 16 independent gases to be arbitrarily mixed over a wide concentration range. Details about this GMA are described in [18] and further details can be found in [19,20]. The GMA is used to provide well-known complex gas mixtures to three commercially available MOS sensors, i.e., SPG40 (Sensirion AG, Stäfa, Switzerland), with two sensors from one batch and the third from a different one.…”

Section: Datasetmentioning

confidence: 99%

Deep Learning Based Calibration Time Reduction for MOS Gas Sensors with Transfer Learning

et al. 2022

View full text Add to dashboard Cite

In this study, methods from the field of deep learning are used to calibrate a metal oxide semiconductor (MOS) gas sensor in a complex environment in order to be able to predict a specific gas concentration. Specifically, we want to tackle the problem of long calibration times and the problem of transferring calibrations between sensors, which is a severe challenge for the widespread use of MOS gas sensor systems. Therefore, this contribution aims to significantly diminish those problems by applying transfer learning from the field of deep learning. Within the field of deep learning, transfer learning has become more and more popular. Nowadays, building a model (calibrating a sensor) based on pre-trained models instead of training from scratch is a standard routine. This allows the model to train with inherent information and reach a suitable solution much faster or more accurately. For predicting the gas concentration with a MOS gas sensor operated dynamically using temperature cycling, the calibration time can be significantly reduced for all nine target gases at the ppb level (seven volatile organic compounds plus carbon monoxide and hydrogen). It was possible to reduce the calibration time by up to 93% and still obtain root-mean-squared error (RMSE) values only double the best achieved RMSEs. In order to obtain the best possible transferability, different transfer methods and the influence of different transfer data sets for training were investigated. Finally, transfer learning based on neural networks is compared to a global calibration model based on feature extraction, selection, and regression to place the results in the context of already existing work.

show abstract

“…For reliable operation the manufacturer recommends a monthly recalibration in the data sheet [8]. 2 Overall schematic of the GMA based on [7] If a common setting in dilution mode for module 4, chosen at random, is considered, a large difference in the set concentrations with and without offset errors can be observed. One example is shown in Table 2, where the first line describes the set state and the second line the real set values due to the offset error.…”

Section: Basic Functional Investigationmentioning

confidence: 99%

“…Since calibration measurements take a long time, it makes sense to optimize the gas adjustment time considering the GMA utilization. In order to find a sensible optimum, investigations in this respect were already carried out on existing GMAs during the design phase of the GMA [7]. In order to verify the obtained results on the new apparatus and, if necessary, to optimize them further, additional measurements were carried out.…”

Section: Optimization Of Gma Time Constantmentioning

confidence: 99%