Fondazione Bruno Kessler Research Institute, via Sommarive 18, Trento, Italy.
E.T.C. Engineering Solutions, Trento, Italy.
Environ Monit Assess. 2020 Jan 29;192(2):148. doi: 10.1007/s10661-020-8064-1.
Wastewater treatment plants use many sensors to control energy consumption and discharge quality. These sensors produce a vast amount of data which can be efficiently monitored by automatic systems. Consequently, several different statistical and learning methods are proposed in the literature which can automatically detect faults. While these methods have shown promising results, the nonlinear dynamics and complex interactions of the variables in wastewater data necessitate more powerful methods with higher learning capacities. In response, this study focusses on modelling faults in the oxidation and nitrification process. Specifically, this study investigates a method based on deep neural networks (specifically, long short-term memory) compared with statistical and traditional machine-learning methods. The network is specifically designed to capture temporal behaviour of sensor data. The proposed method is evaluated on a real-life dataset containing over 5.1 million sensor data points. The method achieved a fault detection rate (recall) of over 92%, thus outperforming traditional methods and enabling timely detection of collective faults.
污水处理厂使用许多传感器来控制能源消耗和排放质量。这些传感器产生大量的数据，可以通过自动系统进行有效地监测。因此，文献中提出了几种不同的统计和学习方法，可以自动检测故障。虽然这些方法已经显示出了有希望的结果，但废水数据中变量的非线性动力学和复杂相互作用需要具有更高学习能力的更强大的方法。有鉴于此，本研究专注于建模氧化和硝化过程中的故障。具体来说，本研究调查了一种基于深度神经网络（特别是长短期记忆）的方法，并将其与统计和传统机器学习方法进行了比较。该网络专门用于捕捉传感器数据的时间行为。所提出的方法在一个包含超过 510 万个传感器数据点的真实数据集上进行了评估。该方法实现了超过 92%的故障检测率（召回率），从而优于传统方法，并能够及时检测到集体故障。
