Application of Machine Learning for Fenceline Monitoring of Odor Classes and Concentrations at a Wastewater Treatment Plant

Abstract

The development of low-cost sensors, the introduction of technical performance specifications, and increasingly effective machine learning algorithms for managing big data have led to a growing interest in the use of instrumental odor monitoring systems (IOMS) for odor measurements from industrial plants. The classification and quantification of odor concentration are the main goals of IOMS installed inside industrial plants in order to identify the most important odor sources and to assess whether the regulatory thresholds have been exceeded. This paper illustrates the use of two machine learning algorithms applied to the concurrent classification and quantification of odors. Random Forest was employed, which is a machine learning algorithm that thus far has not been used in the field of odor quantification and classification for complex industrial situations. Furthermore, the results were compared with commonly used algorithms in this field, such as artificial neural network (ANN), which was here employed in the form of a deep neural network. Both techniques were applied to the data collected from an IOMS installed for fenceline monitoring at a wastewater treatment plant. Cohen’s kappa and Normalized RMSE are used as specifical performance indicators for classification and regression: the indicators were calculated for the test dataset, and the results were compared with data in the literature obtained in contexts of similar complexity. A Cohen’s kappa of 97% was reached for the classification task, while the best Normalized RMSE, namely 4%, for the interval 20–2435 ouE/m3 was obtained with Random Forest.

A Survey and Perspective on Industrial Cyber-Physical Systems (ICPS): From ICPS to AI-Augmented ICPS

“…Gas emission [61]- [63] Product quality [64]- [66] Water quality [67] CNN [66] DeepFM [65] SVM [64], [67] RF [61]- [63] Control systems [64]- [66] Environments [61], [62], [67] Productivity [64]- [67] Sustainability [61], [62], [64], [67] In [47], researchers introduce a CNN-based model for detecting arc faults, known for their electrical hazards due to high temperatures. This detection model is designed to classify normal and abnormal states of load currents without the need for additional transformation.…”

“…The research in [61] focuses on predicting methane concentrations in shale gas fields for greenhouse gas emission measurement. [62] monitors odor concentrations and grades at wastewater treatment plants. Similarly, [63] predicts odor concentrations based on quantitative data from compounds emitted in urban areas, identifying odor emission sources.…”

Proceedings - The Eleventh International Symposium GRID 2022

“…On the other hand, Cangialosi, Bruno & De Santis, (2021) tested ML algorithms, namely RF and ANN for fenceline monitoring of odor classes and concentrations at the WWTP. By utilization of instrumental odor monitoring systems and application of ML models, the most important sources of odor could be identified and their concentrations could be compared to permissible limits stated in the regulative (Cangialosi, Bruno & De Santis, 2021).…”

Prioritization of Volatile Organic Compound Reduction in the Tire Manufacturing Industry through Speciation of Volatile Organic Compounds Emitted at the Fenceline

“…Simultaneously in the United States and Canada, in addition to overall VOC management, concentration regulations have been introduced at fencelines for large-scale establishments, such as oil refineries. These facilities emit potentially health-impacting, carcinogenic VOCs like benzene [11]. In the case of benzene, should the level exceed the defined action level of 9 µg/m 3 , a reduction plan must be implemented.…”