Date of Award
Dissertation - Restricted
Doctor of Philosophy (PhD)
Civil, Construction, and Environmental Engineering
Activated sludge bulking is a phenomenon whereby filamentous organisms in activated sludges over-proliferate. This situation is thought to be caused by environmental conditions within the activated sludge medium, which favor the growth of the filamentous species over that of the floc-formers. The result is sludge that has poor settling characteristics, and a loss of solids in the effluent. Studies have shown that although there are many filamentous species, only a few are commonly cited as being dominant in bulking sludges. The growth requirements of these organisms has been related to the aeration basin dissolved oxygen, food:to:microorganism ratios, nutrient imbalances, the sludge age, and hydraulic conditions within the activated sludge environment. Some researchers claim that if a specific environmental factor can be shown to influence the growth of a particular organism, then that factor can be manipulated and effectively used to control the growth of the organism. A contrary viewpoint is proposed by other researchers. These researchers claim that the cause and effect relationship defined for various filamentous species is often contradictory and that the interaction between coexistent factors is of more significance. Attempts to examine and investigate coexistent factors have been mostly empirical and far from conclusive. This dissertation provides a new, unique and powerful approach to studying activated sludge bulking. This approach is the use of Artificial Neural Networks, and in particular the Back-Propagation algorithm. Artificial Neural Networks are computer based models of natural neural systems. These networks are capable of learning similar to humans, in that they can generalize information into basic underlying rules and relationships, and make intelligent "inferences" about a given problem domain. The back-propagation algorithm is the most studied algorithm in the area of Artificial Neural Networks. This algorithm is essentially a gradient descent algorithm, and seeks to minimize the error between its output and a given target output. The algorithm has been used in several applications including natural language processing, noise filtering, robot control, system analysis, and time-series forecasting. The latter two application domains are implemented in the present research. Artificial Neural Networks have also been compared to traditional Artificial Intelligence schemes, such as Expert Systems. Expert Systems are claimed to demonstrate "heuristic" reasoning ability and mimic intelligent human behavior. A comparison between Artificial Neural Networks and Expert Systems is presented in the dissertation. The dissertation will show that Artificial Neural Networks can indeed provide some unique insights about the bulking phenomenon. It will also show that in some problem domains and applications Artificial Neural Networks are superior to Expert Systems.