Odour monitoring by the combination of sensors and neural networks

https://doi.org/10.1016/S1364-8152(98)00105-4Get rights and content

Abstract

The treatment of waste is always combined with odour emission which can be annoying to people living near waste treatment plants. To identify and evaluate these odour emissions, different methods are used. The most frequently applied “measuring instrument” is the human nose. However, various factors, e.g. form on the day, make assessment difficult. Therefore, it is necessary to develop a measuring method which is objective and efficient. One example is a combination of sensors and neural networks. With this device, called an “Electronic Nose”, it is not only possible to identify odour, but all kinds of substances, depending on the selectivities of the sensors, can be detected and monitored. With reference to the characteristic patterns of defined emission situations, process control is possible in order to classify the emitting parts of a plant.

Introduction

Regulations concerning odour control in Germany are very strict due to the high population density and the high number of existing waste treatment plants. Thus, it is almost impossible to find locations for treatment plants without annoying people with odour emissions. Many plants have already been built near residential areas and people complain about odour emissions. In particular, complaints about emissions from biowaste composting plants have increased in recent times. The acceptance in the population has decreased. Therefore, it is essential that systems for the identification, measurement and reduction of odours are developed.

Section snippets

Regulations and guidelines in Germany

In Germany, the Society of German Engineers (VDI) has produced a number of guidelines concerning odour emissions and monitoring. One important guideline is VDI 3881—Olfactometry. This guideline is concerned with olfactometry to determine odourant concentration. The odourant concentration of the gas sample to be measured is determined by dilution down to the odour threshold. The odour threshold is defined as the concentration of odorous substances at threshold level which leads to an odour

Methods of measuring odour emissions

Measurement of odours is difficult because of the specific structure of the odour molecule itself. There are no defined chemical or physical features which allow the prediction of odour-carrying qualities of substances. Substances with different molecular structures can have similar odours, just as substances with similar molecular structures can cause different odours (Jager, 1989, Kuchta and Jager, 1995).

There are different methods of measuring odour emissions especially from waste treatment

Conclusions

At the present time, olfactometry is state-of-the-art for odour determination in Germany, but it cannot be used as a continuous measuring method. The proposed approach is to combine the results of olfactometry with a gas sensor array in order to train an ANN, to obtain a system for on-line odour detection as an alternative to the human nose for routine analysis.

One problem is the varying composition of an odour mixture from waste treatment plants, which can cause the same odourant concentration

Acknowledgements

This study was sponsored by Deutsche Bundesstiftung Umwelt.

References (14)

  • Alpha M.O.S., 1995. FOX 2000 to FOX 4000—Electronic Nose User Manual. Alpha M.O.S.,...
  • Backhaus, K., Erickson, W., Plinke, W., 1987. Multivariate Analysenmethoden—Eine anwendungsorientierte Einführung....
  • Bockreis, A., Jager, J., 1998. Einsatz einer “künstlichen Nase” zur kontinuierlichen Geruchsüberwachung von...
  • GIRL, 1995. Feststellung und Beurteilung von Geruchsimmissionen-Geruchsimmissionsrichtlinie GIRL. Der Minister für...
  • Jager, J., 1989. Geruchsemissionen und -immissionen bei der Kompostierung. Müllhandbuch, Artikel 5330. Erich Schmidt...
  • Keller, H.B., 1994. Prozeßführung in Müllverbrennungsanlagen mit neuronalen Netzen. In: Modellbildung und intelligente...
  • Kuchta, K., Jager, J., 1995. Odour emissions at composting facilities. 1. International Symposium on Biological Waste...
There are more references available in the full text version of this article.

Cited by (20)

  • Environmental odour management by artificial neural network – A review

    2019, Environment International
    Citation Excerpt :

    By evaluating different algorithms, Bockreis and Jager (1999) able to show that ANN can have better learning, however, it doesn’t guarantee that the ANN could generalize well without simulating a new set of data observations that were excluded from the training set. ANN is a useful technique to predict the concentration of gaseous compounds (i.e., NH3 and H2S) (Strik et al., 2005; Iliyas et al., 2013), odour intensity (Janes et al., 2005) and odour concentration (Bockreis and Jager, 1999; Micone and Guy, 2007) (R2 ≤0.90). It can help to provide the operators’ accurate information about the emerging of gases even at trace levels, maintain the operational conditions of the process, comply with air quality standards and eventually, to control and minimize these pollutants.

  • Application of electronic nose for industrial odors and gaseous emissions measurement and monitoring - An overview

    2015, Talanta
    Citation Excerpt :

    The upsurge of population has caused the residential areas to be englobed near the industrial sites, further aggravating the problem. On the economic front also, such pollution hinders the development of residential areas or other public places near such plants [7, 11]. The need for a precise, economical and objective system that gives an explicit representation of odors and odorants responsible for the generation of odor is, therefore, undisputed.

  • Quantitative determination of pulp and paper industry emissions and associated odor intensity in methyl mercaptan equivalent using electronic nose

    2014, Atmospheric Environment
    Citation Excerpt :

    Moreover, while using such analytical instruments the odor perceived is not depicted. Till date, electronic nose developed for measurement of gaseous emissions generated from various industrial sites has found its application limited to the monitoring of VOCs (Pearce et al., 2003; Polikar et al., 2006) and for detection of singular compounds such as H2S, NH3, etc (Bockreis and Jager, 1999; Xu et al., 2000). The electronic nose has not been explored for measurement of reduced sulfur compounds generated from pulp and paper industries and the odor intensity associated with these compounds.

View all citing articles on Scopus
View full text