We study and compare different neural network learning strategies: batch-mode learning, online learning, cyclic learning, and almost-cyclic learning. Incremental learning strategies require less storage capacity than batch-mode learning. However, due to the arbitrariness in the presentation order of the training patterns, incremental learning is a stochastic process; whereas batch-mode learning...

The absence of a stable operational state in polymerization reactors that operates in batches is factor that determine the need of a special control system. In this study, advanced control methodology is implemented for controlling the operation of a batch polymerization reactor for polystyrene production utilizing model predictive control. By utilizing a model of the polymerization process, th...

The optimal operation of batch processes has attracted more attention in recent years since, in the face of growing competition, it is a natural choice for reducing production costs, improving product quality, and meeting safety requirements and environmental regulations. Since the models currently available in industry are poor and carry a large amount of uncertainty, standard model-based opti...

This experiment examines two esterification reactions: the de-esterification of ethyl benzoate into benzoic acid and the transesterification of palm oil into biodiesel. Through the de-esterification of ethyl benzoate, we mimicked the processes and experimental designs that are involved in the production of API’s (active pharmaceutical ingredients). The transesterification of palm oil allowed us...

Introduction: Detergents lead to many environmental problems. The main aim of this study was to evaluate sequencing batch reactor (SBR) efficiency on Linear alkyl benzene sulfonate (LAS) removal. Materials and Methods: In this experimental study, to investigate the removal efficiency of LAS, a SBR reactor was used. A roughly 12-hour operating cycle was chosen which included the discharge time ...

The nitrogen removal from wastewater and landfill leachate has become a vital part of the overall treatment process because nitrogen compounds have the significant impact on the environment. Generally, biological nitrogen removal is used for nitrogen elimination from wastewater. In the last years, newly advanced anaerobic reactor systems such as up flow anaerobic sludge blanket (UASB), anaerobi...

h this paper we derive optimal state feedback laws for end-point optimization of a dynamic system where the final time is free and the system has a scalar inequality constraint. The existence of a singular region as well as the nuture of the state feedback law (static or dynamic) is completely characterized in terms of the system dynamics. Explicit synthesis formulae for the state feedback laws...

In the past, oxygen delignification studies were mostly performed in batch reactors, whereby the caustic and dissolved oxygen concentrations are changing during the reaction. Also the lignin content and cellulose degradation of the pulp are only established at the end of an experiment when the sample is removed from the reactor. To overcome these deficiencies, a differential reactor system (cal...

Current methods for generating kinetic data can be categorized as either sampling steady-state conditions in flow or generating timeseries data in batch.[1] The latter method has proven particularly useful in identifying complex kinetic mechanisms.[2] Unfortunately, both of these techniques have significant limitations. While continuous flow experiments, especially in microreactors, have advant...

The product of the biological sulphate reduction is sulphide. High concentrations of molecular H2S (g) can be inhibitory for microbial activity, especially at a reactor pH of 6 to 7. This paper focuses on the effect of high sulphide concentrations on the sulphate reduction rates. The results of three investigations operating a continuous reactor, a column reactor and batchtest reactors have sho...