A fuzzy neural network approach for online fault detection in waste water treatment process

• A fault detection system is proposed and tested.
• A FNN, using the adaptive computation algorithm, is applied to the predicting plant.
• This fault diagnosis method allows a quick revealing of the faults.
• The fault detection system owns more reliable diagnosis then the off-line methods.

In this paper, an effective strategy for fault detection of sludge volume index (SVI) sensor is proposed and tested on an experimental hardware setup in waste water treatment process (WWTP). The main objective of this fault detection strategy is to design a system which consists of the online sensors, the SVI predicting plant and fault diagnosis method. The SVI predicting plant is designed utilizing a fuzzy neural network (FNN), which is trained by a historical set of data collected during fault-free operation of WWTP. The fault diagnosis method, based on the difference between the measured concentration values and FNN predictions, allows a quick revealing of the faults. Then this proposed fault detection method is applied to a real WWTP and compared with other approaches. Experimental results show that the proposed fault detection strategy can obtain the fault signals of the SVI sensor online.

Figure optionsDownload as PowerPoint slide